WO2025140070A1 - Network element searching method and apparatus, network element registration method and apparatus, and communication device - Google Patents

Abstract

The present application relates to the technical field of communications, and discloses a network element searching method and apparatus, a network element registration method and apparatus, and a communication device. The network element searching method in the embodiments of the present application comprises: a first network element receives a first message from a second network element, wherein the first message is used for requesting to search for a network element having model training capabilities, and the model training capabilities include a training capability for a positioning model; and the first network element sends a second message to the second network element, wherein the second message is used for feeding back a network element search result.

Description

Network element search method, network element registration method, device and communication equipment

CROSS-REFERENCE TO RELATED APPLICATIONS

This application claims priority to Chinese Patent Application No. 202311857641.4 filed on December 29, 2023, the entire contents of which are incorporated herein by reference.

Technical Field

The present application belongs to the field of communication technology, and specifically relates to a network element search method, a network element registration method, a device and a communication device.

Background Art

In the related technologies, the positioning service (LCS) is executed and provided by multiple network elements such as the Access and Mobility Management Function (AMF) and Location Management Function (LMF) in the core network, which results in low positioning accuracy.

Summary of the invention

The embodiments of the present application provide a network element search method, a network element registration method, an apparatus and a communication device, which can solve the problem of low positioning accuracy existing in the related art.

In a first aspect, a network element search method is provided, which is performed by a first network element, and the method includes:

The first network element receives a first message from the second network element, where the first message is used to request to find a network element with a model training capability, where the model training capability includes a positioning model training capability;

The first network element sends a second message to the second network element, where the second message is used to feed back a network element search result.

In a second aspect, a network element search method is provided, which is performed by a second network element, and the method includes:

The second network element sends a first message to the first network element, where the first message is used to request to find a network element with a model training capability, where the model training capability includes a positioning model training capability;

The second network element receives a second message from the first network element, where the second message is used to feed back a network element search result.

According to a third aspect, a network element search method is provided, which is performed by a third network element. The method includes:

The third network element receives a fourth message from the second network element, where the fourth message is used to request acquisition of a target model, where the target model includes a positioning model.

In a fourth aspect, a network element search method is provided, which is performed by a first device, and the method includes:

The first device sends a sixth message to the second network element, where the sixth message is used to request to obtain a target model, where the target model includes a positioning model.

In a fifth aspect, a network element registration method is provided, which is performed by a first network element, and the method includes:

The first network element receives a third message from a third network element, where the third message is used to request registration of relevant information of the third network element, and the third message includes tenth information, where the tenth information is used to indicate that the third network element has model training capability, and the model training capability includes training capability of a positioning model.

In a sixth aspect, a network element registration method is provided, which is performed by a third network element, and the method includes:

The third network element sends a third message to the first network element, where the third message is used to request registration of relevant information of the third network element. The third message includes tenth information, where the tenth information is used to indicate that the third network element has model training capability, and the model training capability includes training capability of a positioning model.

In a seventh aspect, a network element search device is provided, which is applied to a first network element, and the device includes:

A first receiving module, configured to receive a first message from a second network element, wherein the first message is used to request to find a network element having a model training capability, wherein the model training capability includes a positioning model training capability;

A sending module is used to send a second message to the second network element, where the second message is used to feed back the network element search result.

In an eighth aspect, a network element search device is provided, which is applied to a second network element, and the device includes:

A first sending module, configured to send a first message to a first network element, wherein the first message is used to request to find a network element having a model training capability, wherein the model training capability includes a positioning model training capability;

The first receiving module is used to receive a second message from the first network element, where the second message is used to feed back a network element search result.

In a ninth aspect, a network element search device is provided, which is applied to a third network element, and the device includes:

The receiving module is used to receive a fourth message from the second network element, where the fourth message is used to request to obtain a target model, where the target model includes a positioning model.

In a tenth aspect, a network element search device is provided, which is applied to a first device, and the device includes:

The sending module is used to send a sixth message to the second network element, where the sixth message is used to request to obtain a target model, where the target model includes a positioning model.

In an eleventh aspect, a network element registration device is provided, which is applied to a first network element, and the device includes:

A receiving module is used to receive a third message from a third network element, wherein the third message is used to request registration of relevant information of the third network element, and the third message includes tenth information, wherein the tenth information is used to indicate that the third network element has model training capability, and the model training capability includes the training capability of the positioning model.

In a twelfth aspect, a network element registration device is provided, which is applied to a third network element, and the device includes:

A sending module is used to send a third message to the first network element, wherein the third message is used to request registration of relevant information of the third network element, and the third message includes tenth information, wherein the tenth information is used to indicate that the third network element has model training capability, and the model training capability includes the training capability of the positioning model.

In the thirteenth aspect, a communication device is provided, which includes a processor and a memory, wherein the memory stores a program or instruction that can be executed on the processor, and when the program or instruction is executed by the processor, the steps of the method described in the first aspect or the second aspect or the third aspect or the fourth aspect or the fifth aspect or the sixth aspect are implemented.

In a fourteenth aspect, a communication device is provided, including a processor and a communication interface; wherein the communication interface is used to: receive a first message from a second network element, the first message is used to request to find a network element with a model training capability, the model training capability includes a positioning model training capability; send a second message to the second network element, the second message is used to feedback a network element search result;

or,

The communication interface is used to: send a first message to a first network element, the first message is used to request to find a network element with model training capability, the model training capability includes the training capability of the positioning model; receive a second message from the first network element, the second message is used to feedback the network element search result;

or,

The communication interface is used to: receive a fourth message from the second network element, the fourth message is used to request to obtain a target model, the target model includes a positioning model;

or,

The communication interface is used to: send a sixth message to the second network element, where the sixth message is used to request to obtain a target model, where the target model includes a positioning model;

or,

The communication interface is used to: receive a third message from a third network element, the third message is used to request registration of relevant information of the third network element, the third message includes tenth information, the tenth information is used to indicate that the third network element has a model training capability, and the model training capability includes a positioning model training capability;

or,

The communication interface is used to: send a third message to the first network element, the third message is used to request registration of relevant information of the third network element, the third message includes tenth information, the tenth information is used to indicate that the third network element has model training capabilities, and the model training capabilities include positioning model training capabilities.

In the fifteenth aspect, a readable storage medium is provided, on which a program or instruction is stored. When the program or instruction is executed by a processor, the steps of the method described in the first aspect are implemented, or the steps of the method described in the second aspect are implemented, or the steps of the method described in the third aspect are implemented, or the steps of the method described in the fourth aspect are implemented, or the steps of the method described in the fifth aspect are implemented, or the steps of the method described in the sixth aspect are implemented.

In the sixteenth aspect, a wireless communication system is provided, including: a first network element and a second network element, wherein the first network element can be used to execute the steps of the method described in the first aspect, and the second network element can be used to execute the steps of the method described in the second aspect.

In the seventeenth aspect, a wireless communication system is provided, including: a first network element and a third network element, wherein the first network element can be used to execute the steps of the method described in the fifth aspect, and the third network element can be used to execute the steps of the method described in the sixth aspect.

In aspect 18, a chip is provided, comprising a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run a program or instructions to implement the method described in aspect 1, or the method described in aspect 2, or the method described in aspect 3, or the method described in aspect 4, or the method described in aspect 5, or the method described in aspect 6.

In the nineteenth aspect, a computer program/program product is provided, wherein the computer program/program product is stored in a storage medium, and the program/program product is executed by at least one processor to implement the steps of the method described in the first aspect, or the steps of the method described in the second aspect, or the steps of the method described in the third aspect, or the steps of the method described in the fourth aspect, or the steps of the method described in the fifth aspect, or the steps of the method described in the sixth aspect.

In the embodiment of the present application, the first network element receives a first message from the second network element, the first message is used to request to find a network element with model training capability, the model training capability includes the training capability of the positioning model; the first network element sends a second message to the second network element, the second message is used to feedback the network element search result. In this way, by finding a network element with the training capability of the positioning model, the positioning model can participate in the positioning service, thereby improving the positioning accuracy.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG1 is a block diagram of a wireless communication system provided in an embodiment of the present application;

FIG2 is a flow chart of MT-LR in the related art;

FIG3 shows five cases of AI positioning defined in the related art;

FIG4 is a flow chart of a network element search method provided in an embodiment of the present application;

FIG5 is a flow chart of a network element search method provided in an embodiment of the present application;

FIG6 is a flow chart of a network element search method provided in an embodiment of the present application;

FIG7 is a flow chart of a network element search method provided in an embodiment of the present application;

FIG8 is a flow chart of a network element registration method provided in an embodiment of the present application;

FIG9 is a flow chart of a network element registration method provided in an embodiment of the present application;

FIG10 is a flow chart of Example 1 provided in the embodiments of the present application;

FIG11 is a flow chart of Example 2 provided in the embodiments of the present application;

FIG12 is a flow chart of Example 3 provided in the embodiments of the present application;

13 is a structural diagram of a network element search device provided in an embodiment of the present application;

14 is a structural diagram of a network element search device provided in an embodiment of the present application;

15 is a structural diagram of a network element search device provided in an embodiment of the present application;

16 is a structural diagram of a network element search device provided in an embodiment of the present application;

17 is a structural diagram of a network element registration device provided in an embodiment of the present application;

FIG18 is a structural diagram of a network element registration device provided in an embodiment of the present application;

FIG19 is a structural diagram of a communication device provided in an embodiment of the present application;

FIG20 is a schematic diagram of the hardware structure of a terminal provided in an embodiment of the present application;

21 is a schematic diagram of the hardware structure of an access network device provided in an embodiment of the present application;

Figure 22 is a schematic diagram of the hardware structure of a core network device provided in an embodiment of the present application.

DETAILED DESCRIPTION

The following will be combined with the drawings in the embodiments of the present application to clearly describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field belong to the scope of protection of this application.

The terms "first", "second", etc. of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the terms used in this way are interchangeable where appropriate, so that the embodiments of the present application can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first" and "second" are generally of one type, and the number of objects is not limited, for example, the first object can be one or more. In addition, "or" in the present application represents at least one of the connected objects. For example, "A or B" covers three schemes, namely, Scheme 1: including A but not including B; Scheme 2: including B but not including A; Scheme 3: including both A and B. The character "/" generally indicates that the objects associated with each other are in an "or" relationship.

The term "indication" in this application can be a direct indication (or explicit indication) or an indirect indication (or implicit indication). A direct indication can be understood as the sender explicitly informing the receiver of specific information, operations to be performed, or request results in the sent indication; an indirect indication can be understood as the receiver determining the corresponding information according to the indication sent by the sender, or making a judgment and determining the operation to be performed or the request result according to the judgment result.

It is worth noting that the technology described in the embodiments of the present application is not limited to the Long Term Evolution (LTE)/LTE-Advanced (LTE-A) system, but can also be used in other wireless communication systems, such as Code Division Multiple Access (CDMA), Time Division Multiple Access (TDMA), Frequency Division Multiple Access (FDMA), Orthogonal Frequency Division Multiple Access (OFDMA), Single-carrier Frequency Division Multiple Access (SC-FDMA) or other systems. The terms "system" and "network" in the embodiments of the present application are often used interchangeably, and the described technology can be used for the above-mentioned systems and radio technologies as well as other systems and radio technologies. The following description describes a New Radio (NR) system for example purposes, and NR terms are used in most of the following descriptions, but these technologies can also be applied to systems other than NR systems, such as ^6th Generation (6G) communication systems.

FIG1 shows a block diagram of a wireless communication system applicable to the embodiment of the present application. The wireless communication system includes a terminal 11 and a network side device 12 . Among them, the terminal 11 can be a mobile phone, a tablet computer (Tablet Personal Computer), a laptop computer (Laptop Computer), a notebook computer, a personal digital assistant (PDA), a handheld computer, a netbook, an ultra-mobile personal computer (Ultra-mobile Personal Computer, UMPC), a mobile Internet device (Mobile Internet Device, MID), an augmented reality (Augmented Reality, AR), a virtual reality (Virtual Reality, VR) device, a robot, a wearable device (Wearable Device), a flight vehicle (flight vehicle), a vehicle user equipment (VUE), a shipborne equipment, a pedestrian terminal (Pedestrian User Equipment, PUE), a smart home (home appliances with wireless communication functions, such as refrigerators, televisions, washing machines or furniture, etc.), a game console, a personal computer (Personal Computer, PC), a teller machine or a self-service machine and other terminal side devices. Wearable devices include: smart watches, smart bracelets, smart headphones, smart glasses, smart jewelry (smart bracelets, smart bracelets, smart rings, smart necklaces, smart anklets, smart anklets, etc.), smart wristbands, smart clothing, etc. Among them, the vehicle-mounted device can also be called a vehicle-mounted terminal, a vehicle-mounted controller, a vehicle-mounted module, a vehicle-mounted component, a vehicle-mounted chip or a vehicle-mounted unit, etc. In addition to the above-mentioned terminal devices, it can also be a chip in the terminal, such as a modem chip, a system-on-chip (SoC). It should be noted that the specific type of the terminal 11 is not limited in the embodiment of the present application. The network side device 12 may include an access network device or a core network device, wherein the access network device may also be called a radio access network (RAN) device, a radio access network function or a radio access network unit. The access network device may include a base station, a wireless local area network (WLAN) access point (AP) or a wireless fidelity (WiFi) node, etc. Among them, the base station can be called Node B (Node B, NB), Evolved Node B (Evolved Node B, eNB), the next generation Node B (the next generation Node B, gNB), New Radio Node B (New Radio Node B, NR Node B), access point, Relay Base Station (Relay Base Station, RBS), Serving Base Station (Serving Base Station, SBS), Base Transceiver Station (Base Transceiver Station, BTS), radio base station, radio transceiver, base The base station is not limited to specific technical terms as long as the same technical effect is achieved. It should be noted that in the embodiments of the present application, only the base station in the NR system is taken as an example for introduction, and the specific type of the base station is not limited.

The core network equipment may include but is not limited to at least one of the following: core network nodes, core network functions, mobility management entity (MME), access mobility management function (AMF), session management function (SMF), user plane function (UPF), policy control function (PCF), policy and charging rules function unit (PCRF), edge application service discovery function (EASDF), unified data management (UDM), unified data warehouse (UDRM), etc. The following are some functions of the present invention: the core network device of the NR system is used as an example, the core network device of the NR system is used as an example, and the specific type of the core network device is not limited.

This application involves positioning service (LCS) and artificial intelligence (AI) technology. The following is an introduction to these two aspects.

LCS is implemented and provided by AMF, LMF and other network elements in the core network. LCS messages are exchanged between the user equipment (UE) and the LCS client or AF. A typical process is the Mobile Terminated Location Request (MT-LR).

Figure 2 shows the MT-LR process. As shown in Figure 2, the MT-LR process is initiated by an external third-party application (i.e., LCS client) or by AF via NEF, and finally obtains the UE's location information via network elements such as GMLC, AMF, and LMF. Some steps in Figure 2 are described as follows:

Step 1a (or 1b-1 or 1b-2 or 1-c): LCS client, Network Function (NF) or AF (through NEF) sends a request to (H)GMLC to obtain the location and speed (optional) of the target UE, which can be identified by Generic Public Subscription Identifier (GPSI) or Subscription Permanent Identifier (SUPI). Taking step 1c as an example, NF (e.g. NWDAF) calls Ngmlc_Location_ProvideLocation service operation to (H)GMLC.

Step 2: (H)GMLC invokes Nudm_SDM_Get service operation on the target UE’s UDM to get the privacy settings of the UE identified by its GPSI or SUPI. The UDM returns the target UE privacy settings of the UE. (H)GMLC checks the UE LCS privacy profile.

Step 5: (H)GMLC or Voice Group Call Multicast Listener Control (VGMLC) invokes the Namf_Location_ProvidePositioningInfo service operation to the AMF to request the current location of the UE. The service operation includes the SUPI, client type, and may include the required LCS Quality of Service (QoS), supported Universal Geographical Area Description (GAD) configuration, planned location time, service type, and other attributes received or determined in step 1.

Steps 10 to 13: The AMF selects the LMF based on the available information defined in the relevant standard protocols or based on the AMF local configuration. The LMF selection takes into account the 5G Access Network (5G-AN) currently serving the UE. The selection can use NRF query.

The AMF invokes the Nlmf_Location_DetermineLocation service operation to the LMF to request the current location of the UE.

The LMF performs one or more positioning procedures described in the relevant standard protocols. In this step, the LMF may request the transfer of positioning-related N1 messages to the UE or the transfer of network positioning messages to the UE's serving Next Generation Radio Access Network (NG-RAN) node (gNB or NG-eNB) using the Namf_Communication_N1N2MessageTransfer service operation. The LMF shall determine the geographic location and may optionally determine the location in local coordinates.

Step 22: AMF returns a Namf_Location_ProvidePositioningInfo response to the (V)GMLC (or Home Gateway Mobile Location Center (HGMLC) for roaming when the NL3 reference point is not supported) and indicates the notification result.

Step 24a (or 24b-1 or 24b-2 or 24c): If the LCS client, NF or AF allows positioning of the target UE, the (H)GMLC sends a location service response to the LCS client, NF or AF (through NEF).

It should be noted that the positioning accuracy is low when the positioning is performed through the process shown in FIG. 2 .

With the development of AI technology, AI technology is gradually being applied to more and more scenarios. AI technology is expected to be applied to communication scenarios (such as positioning scenarios), for example, setting up network elements in the core network responsible for core network intelligence-related operations (such as model training, model reasoning, etc.).

The AI positioning model (also known as the Machine Learning (ML) positioning model) can directly or assistedly perform positioning through reasoning, thereby saving a lot of measurement resources and reducing computing power consumption, and can generate more accurate positioning results.

In the relevant discussion, five cases of AI positioning are defined. As shown in Figure 3, cases 1, 2a, and 2b are all downlink positioning, and the Positioning Reference Signal (PRS) is sent; cases 3a and 3b are all uplink positioning, and the Sounding Reference Signal (SRS) is sent. In cases 1 and 2a, the AI positioning model is set in the terminal, as shown in Figure 3. For case 1 or case 2a, the UE can measure the PRS sent by the base station, and then infer the AI positioning information based on the measurement information through the AI positioning model; in case 3a, the AI positioning model is set on the gNB side, as shown in Figure 3, the base station can obtain the AI positioning information based on the SRS measurement information reported by the UE, and then infer the AI positioning information based on the measurement information through the AI positioning model; in cases 2b and 3b, the AI positioning model is set on the LMF side, as shown in Figure 3. For case 2b, the UE reports the measurement information based on PRS to the LMF, and the LMF inputs the measurement information reported by the UE into the AI positioning model to obtain the AI positioning result, or, as shown in Figure 3, for case 3b, the base station reports the measurement information based on SRS to the LMF, and the LMF inputs the measurement information reported by the base station into the AI positioning model to obtain the AI positioning result.

However, the relevant standard protocols do not specify that the core network can train models, nor do they specify what capabilities the network elements need to support model training. They also do not specify how other network elements or devices can obtain the required models from a network element after it has trained a model.

In view of this, the present application provides a network element search method, a network element registration method, an apparatus and a communication device to solve the problem of low positioning accuracy existing in the related art.

In the following, in combination with the accompanying drawings, the network element search method, network element registration method, network element search device, and network element registration device provided in the embodiments of the present application are described in detail through some embodiments and their application scenarios.

FIG4 shows a flow chart of a network element search method provided by an embodiment of the present application. As shown in FIG4 , the network element search method includes the following steps:

Step 401: A first network element receives a first message from a second network element, where the first message is used to request to find a network element with a model training capability, where the model training capability includes a positioning model training capability;

Step 402: The first network element sends a second message to the second network element, where the second message is used to feed back the network element search result.

In the embodiment of the present application, the first network element may be a network element with a storage function, the first network element may store network element information, and thus have the ability and conditions to search for network elements, and the first network element may be a network element of a core network. For example, the first network element may be a network element such as an NRF or an AMF.

The second network element can communicate and interact with the first network element, and request the first network element to search for network elements with model training capabilities. From the perspective of request initiation, the second network element can be the request initiator, that is, the second network element directly initiates a network element search request to the first network element. The second network element may not be the request initiator. In this case, the second network element acts as an intermediate requester, that is, other network elements or devices first send a network element search request to the second network element, and then the second network element sends a network element search request to the first network element. From the perspective of positioning requirements, the second network element may be a positioning demander or not. The second network element may be, for example, a core network element such as AMF, LMF or SMF.

In one implementation, the “model training capability” mentioned in the embodiments of the present application is “AI positioning model training capability” or “ability to train an AI positioning model”. In one implementation, the network element that the second network element requests to search needs to have the ability to train an AI positioning model.

In the embodiment of the present application, the model training capability includes but is not limited to the training capability of the positioning model. For ease of understanding, this type of network element with model training capability can be referred to as a third network element. As an example, the third network element includes NWDAF, model training logical function (Model Training logical function, MTLF) or analysis logical function (Analytics logical function, AnLF), etc.

In the related technology, NWDAF is a network data analysis function network element that supports the collection of network element or terminal related data and can provide information such as statistics and predictions. NWDAF can collect data from network elements such as AMF, SMF or operations, administration and maintenance (OAM). Taking NWDAF applied to positioning services as an example, NWDAF obtains the location information of the terminal by collecting data through AMF, and the predicted terminal location information is coarse-grained, such as the Tracking Area (TA) level or the cell level. In other words, NWDAF needs to collect data through AMF to predict the terminal location information, and the terminal location information is limited to which cell or TA the terminal is currently in. If the consumer of NWDAF initiates a service request to NWDAF and requests NWDAF to collect relevant information or give a prediction, then NWDAF will collect information from different network elements according to the parameters in the request message. After NWDAF performs statistics and analysis, it returns the results to the NWDAF consumer.

In the embodiment of the present application, NWDAF can be used as a network element with model training capability, and its trained positioning model can realize AI positioning, that is, NWDAF can be a network element with AI positioning model training capability. In the embodiment of the present application, the AI positioning model can infer the location information corresponding to the data based on the collected measurement data and other data, so that the terminal location information can be predicted more intelligently and more accurately.

It should be noted that the embodiment of the present application uses NWDAF as a representative of network elements with model training capabilities. The network elements with model training capabilities may also be other network elements or devices, and the embodiment of the present application does not limit this.

In the embodiment of the present application, the first network element receives a first message from the second network element, the first message is used to request to find a network element with model training capability, the model training capability includes the training capability of the positioning model; the first network element sends a second message to the second network element, the second message is used to feedback the network element search result. In this way, by finding a network element with the training capability of the positioning model, the positioning model can participate in the positioning service, thereby improving the positioning accuracy.

The first message can be understood as a network element search request or a network element discovery request. Taking the first network element as NRF and the second network element as AMF as an example, AMF can send a network element search request to NRF through Nnrf_NFDiscovery_Request service, etc., to request to find a network element that meets the conditions. The first message can carry network element type indication information to indicate the type of network element requested to be searched. The first message can carry area indication information to indicate the service scope of the network element requested to be searched, etc. The first message can also carry other indication information.

In some embodiments, the first message includes at least one of the following information:

The first information is used to indicate that the network element requested to be searched needs to have the model training capability;

The second information is used to indicate the user object of the model trained by the network element requested to be searched;

The third information is used to indicate the usage area of the model trained by the network element requested to be searched;

The fourth information is used to indicate the positioning mode of the model trained by the network element requested to be searched;

The fifth information is used to indicate the reasoning method of the model trained by the network element requested to be searched;

The sixth information is used to indicate the type of inference result of the model trained by the network element requested to be searched;

The seventh information is used to indicate the input data type of the model trained by the network element requested to be searched;

The eighth information is used to indicate the task type of the model trained by the network element requested to be searched.

Taking the positioning model as an example, the first information can be understood as the indication information of the ability to train the positioning model, which is used to indicate that the network element requested for search must have the ability to train the positioning model. The eighth information can be understood as the indication information of the required positioning task, such as the analysis ID or functionality ID of AI positioning.

In one implementation, the first information is used to indicate that the network element requested to be searched needs to have the ability to train an AI positioning model.

It should be noted that the above-mentioned first information can be explicit indication information or implicit indication information. In the case of explicit indication information, the first message needs to include the first information; in the case of implicit indication information, the first message does not need to include the first information, and the message name or other information associated with the first information can be used to indicate that the network element requested to be searched needs to have the model training capability.

Optionally, the second information can be understood as indicating that the model trained by the network element requested for search supports/can/is allowed to be used by a certain type of equipment, for example, UE, Positioning Reference Unit (PRU), gNB, LMF, etc. It should be noted that the above-mentioned trained model can be a positioning model or an AI positioning model.

Optionally, the third information may be understood as indicating that the model (support) trained by the network element requested for search may be/allowed to be used within a certain usage area.

When the first message includes the second information and the third information, it can be understood that the first message indicates that the model trained by the requested network element supports/can/is allowed to be used by a certain type of equipment in a certain usage area, such as a certain cell or a certain TA.

Optionally, the fourth information can be understood as a positioning mode that the model trained by the network element requested to be searched can/is allowed to use, that is, for a certain positioning mode, the model trained by the network element can be used, or in other words, the model is trained for a certain positioning mode. Specifically, the positioning mode may refer to, for example, an uplink positioning method, a downlink positioning method, a PRS-based positioning method, or an SRS-based positioning method. It should be noted that the positioning mode may also be an uplink positioning method based on AI/ML, a downlink positioning method based on AI/ML, a positioning method based on AI/ML and PRS, a positioning method based on AI/ML and SRS, etc. It should be noted that the positioning mode may also directly correspond to Case 1, Case 2a, Case 2b, Case 3a, Case 3b, etc. in the existing discussion.

It should be noted that in this article, the meanings of positioning mode and positioning method are similar and can be replaced with each other.

Optionally, the fifth information mentioned above can be understood as a certain reasoning method used by the model trained by the network element requested to be searched, that is, for a certain reasoning method, the model trained by the network element can be used, or in other words, the model is trained for a certain reasoning method. Specifically, the reasoning method may refer to, for example, direct reasoning positioning or indirect reasoning positioning. It should be noted that direct reasoning positioning means that a device directly obtains the positioning result, or directly obtains the positioning result based on the model, that is, using a certain AI/ML positioning model, and the output result of the model is the positioning result; indirect reasoning positioning means that a certain device cannot directly obtain the positioning result, but can obtain information such as intermediate features, or a certain device obtains information such as intermediate features based on the model, that is, using a certain AI/ML positioning model, and the output result of the model is intermediate features, etc. The device needs to further process/calculate based on the intermediate features to obtain the positioning result.

Optionally, the sixth information can be understood as the inference result of the model trained by the network element requested to be searched belonging to a certain type, or the data type that the model trained by the network element needs to output. Specifically, the inference result type can be understood as the inference result type of the positioning model, such as intermediate features data, location information, etc.

Optionally, the seventh information can be understood as the input data of the model trained by the network element requested to be searched belongs to a certain type, or the data type required to be input by the model trained by the network element. For example, the positioning-related data used for positioning model training include: measurement data, such as channel impulse response (CIR), power delay profile (PDP), delay profile (DP), reference signal received power (RSRP), reference signal received power path (RSRPP), reference signal time difference (RSTD), etc.; intermediate features data, such as time of arrival (TOA), path phase, etc.; assistance data, such as reference signal (RS) configuration, etc.

It should be noted that, each information in the embodiments of the present application may refer to indication information, such as the first information may be the first indication information, the second information may be the second indication information, and so on.

In this implementation manner, by carrying one or more items of the above information in the first message, the network element requested to be searched can be made to better meet the requirements.

In some embodiments, the second message includes any of the following:

Information of a target network element, where the target network element is a network element having the model training capability;

The ninth message is used to indicate that the search failed.

After step 401, the first network element may search in its stored network element information (such as network element registration information) to find out whether there is at least one target network element with model training capability. If the first network element finds the target network element, the information of the target network element may be fed back to the second network element through a second message, which may include network element information and capability information of the target network element. The network element information may include its own identification information (such as NF instance ID, Fully Qualified Domain Name (FQDN) or NF IP address (address), network element instance ID, etc.), NF type (type), network element type and other information. If the first network element fails to search, that is, no network element with model training capability is found, a response message of search failure may be fed back to the second network element through a second message.

It should be noted that the target network element may be one or more network elements among the aforementioned third network elements.

In some embodiments, the method further comprises:

The first network element determines a target network element based on the first message, and information of the target network element matches information in the first message.

After step 401 and before step 402, the first network element may compare the information in the first message sent by the second network element in step 401 with the network element information (such as network element registration information) to find out at least one target network element that meets the conditions. The information of the target network element matches the information in the first message, which can be understood as that the information of the target network element is the same as the information in the second message, or that the information in the first message includes the information of the target network element, or that the information of the target network element includes the information in the first message.

In this implementation manner, by determining a network element that matches the information in the first message as the target network element, the determined target network element can be made to better meet the requirements.

In some embodiments, the first network element determines the target network element according to the first message, including at least one of the following:

The first message includes first information, where the first information is used to indicate that the network element requested to be searched needs to have the model training capability, and the first network element determines the target network element according to the first information, wherein the target network element is a network element with the model training capability;

The first message includes second information, where the second information is used to indicate a usage object of the model trained by the network element requested to be searched, and the first network element determines the target network element according to the second information, wherein the usage object of the model trained by the target network element matches the second information;

The first message includes third information, where the third information is used to indicate a usage area of a model trained by the network element requested to be searched, and the first network element determines the target network element according to the third information, wherein the usage area of the model trained by the target network element matches the third information;

The first message includes fourth information, where the fourth information is used to indicate a positioning mode of a model trained by the network element requested to be searched, and the first network element determines the target network element according to the fourth information, wherein the positioning mode of the model trained by the target network element matches the fourth information;

The first message includes fifth information, where the fifth information is used to indicate the reasoning mode of the model trained by the network element requested to be searched, and the first network element determines the target network element according to the fifth information, wherein the model reasoning mode of the model trained by the target network element matches the fifth information;

The first message includes sixth information, where the sixth information is used to indicate a type of inference result of a model trained by the network element requested to be searched, and the first network element determines the target network element according to the sixth information, wherein the type of inference result of the model trained by the target network element matches the sixth information;

The first message includes seventh information, where the seventh information is used to indicate an input data type of a model trained by the network element requested to be searched, and the first network element determines the target network element according to the seventh information, wherein the input data type of the model trained by the target network element matches the seventh information;

The first message includes eighth information, and the eighth information is used to indicate the task type of the model trained by the network element requested to be searched. The first network element determines the target network element based on the eighth information, wherein the task type of the model trained by the target network element matches the eighth information.

As an example, in the case where the first message includes the indication information of the training positioning model capability, the first network element may determine whether each network element is a third network element that meets the condition according to whether the indication information of the training positioning model capability matches the capability indication information of the network element. If a certain network element is a third network element that meets the condition, the first network element may determine the third network element as the target network element.

As another example, when the first message includes the indication information of the positioning model usage object, the first network element may determine whether each network element is a third network element that meets the conditions according to whether the indication information of the positioning model usage object matches the usage object capability information of the positioning model trained by the network element. If a certain network element is a third network element that meets the conditions, the first network element may determine the third network element as the target network element.

As another example, when the first message includes indication information of the positioning model use area, the first network element may determine whether each network element is a third network element that meets the conditions according to whether the indication information of the positioning model use area matches the use area capability information of the positioning model trained by the network element. If a network element is a third network element that meets the conditions, the first network element may determine the third network element as the target network element.

As another example, when the first message includes both indication information of the positioning model usage object and indication information of the positioning model usage area, the model trained by the network element requested to be searched by the first message supports/can/is allowed to be used by a certain type of device in a certain usage area.

As another example, when the first message includes both the indication information of the training positioning model capability and the indication information of the positioning model use object, the first network element can judge whether each network element is a third network element that meets the conditions according to whether the indication information of the training positioning model capability matches the capability indication information of the network element, and whether the indication information of the positioning model use object matches the user object capability information of the positioning model trained by the network element. If the capability indication information of a third network element matches the indication information of the training positioning model capability, and the user object capability information of the positioning model trained by the third network element matches the indication information of the positioning model use object, the first network element can determine the network element as the target network element.

Other matching methods are similar and will not be described in detail here.

In the embodiment of the present application, the information of the target network element determined by the first network element may come from information sent in advance by other network elements, or from registration information provided by the target network element when it is pre-registered on the first network element. The following provides a related scheme for the target network element to register on the first network element.

In some embodiments, the method further comprises:

The first network element receives a third message from the target network element, where the third message is used to request registration of relevant information of the target network element.

The third message can be understood as a registration request message. The third message can carry all the information requested by the target network element for registration, and may include network element information and capability information of the target network element, wherein the network element information includes, for example, its own identification information (such as NF instance ID, Fully Qualified Domain Name (FQDN) or NF IP address (address), network element instance ID, etc.), NF type (type), network element type and other information.

In some embodiments, the third message includes at least one of the following information:

Tenth information, used to indicate that the target network element has a model training capability, where the model training capability includes a positioning model training capability;

The eleventh information is used to indicate the user of the model corresponding to the model training capability;

The twelfth information is used to indicate the usage area of the model corresponding to the model training capability;

Thirteenth information, used to indicate the positioning mode of the model corresponding to the model training capability;

The fourteenth information is used to indicate the reasoning method of the model corresponding to the model training capability;

Fifteenth information, used to indicate the inference result type of the model corresponding to the model training capability;

The sixteenth information is used to indicate the input data type of the model corresponding to the model training capability;

The seventeenth information is used to indicate the task type of the model corresponding to the model training capability.

The third message may carry network element capability information, and the above information may be understood as network element capability information. For example, the tenth information may be understood as indicating that the network element supports training of models for (AI) positioning, or indicating that the network element has the capability to train positioning-related models.

Taking the training of the positioning model as an example of the model training capability, the (supported) use objects of the model can be understood as objects that are allowed to use the positioning model, such as UE, PRU, gNB or LMF.

The (supported) usage area of the model may be understood as an area where the positioning model is allowed or can be used, such as a certain cell or a certain TA.

The positioning mode of the model (supported) can be understood as the positioning method supported by the positioning model, such as an uplink positioning method, a downlink positioning method, a PRS-based positioning method, or an SRS-based positioning method. It should be noted that the positioning mode can also be an uplink positioning method based on AI/ML, a downlink positioning method based on AI/ML, a positioning method based on AI/ML and PRS, a positioning method based on AI/ML and SRS, etc. It should be noted that the positioning mode can also directly correspond to Case 1, Case 2a, Case 2b, Case 3a, Case 3b, etc. in the existing discussion.

The reasoning method of the model (supported) can be understood as the positioning reasoning method supported by the positioning model, such as direct reasoning positioning or indirect reasoning positioning.

The input data type of the model (supported) can be understood as the data type that needs to be input into the model, such as the positioning-related data used for positioning model training, including: measurement data, such as Channel Impulse Response (CIR), Power Delay Profile (PDP), Delay Profile (DP), Reference Signal Received Power (RSRP), Reference Signal Received Power Path (RSRPP), Reference Signal Time Difference (RSTD), etc.; intermediate features data, such as Time of Arrival (TOA), path phase (path phase), etc.; assistance data, such as Reference Signal (RS) configuration, etc.

The inference result type of the model (supported) can be understood as the inference result type of the positioning model, such as intermediate features data, location information, etc.

The task type of the model (supported) can be understood as the type of positioning task supported by the positioning model. The type of positioning task can be indicated by the positioning task identifier supported by the third network element, such as the analytics ID for AI positioning (such as analytics ID is AI positioning), etc.; or, the type of positioning task can be indicated by the model function type or task description information, such as supported model type (supported model type), functionality ID, analytics ID or task type (task type), etc., which are used to illustrate the function or purpose of the supported model.

Any information included in the third message can be used as information of the target network element and stored by the first network element to facilitate the first network element to search for network elements. That is to say, after the first network element receives the registration request message from the target network element, it can save the network element registration information or network element capability information. The first network element can also feedback the registration request message to the target network element. Specifically, after receiving the registration request message, the first network element stores the network element registration information and sends a response message, such as an Nnrf_NFManagement_NFRegister response message, to notify the target network element that the registration is successful.

In this implementation, by pre-registering the target network element on the first network element, the first network element can directly obtain relevant information of the target network element, thereby enabling the first network element to search for network elements more efficiently, which is beneficial for the first network element to find a network element that better meets the needs.

It should be noted that this implementation method uses the target network element as a representative to illustrate the registration method involved in the embodiment of the present application. Any third network element with model training capabilities can register on the first network element with reference to the registration method of the target network element.

The above is a network element search method on the first network element side, and the following provides a network element search method on the second network element side.

FIG5 shows a flow chart of a network element search method provided by an embodiment of the present application. As shown in FIG5 , the network element search method includes the following steps:

Step 501: The second network element sends a first message to the first network element, where the first message is used to request to find a network element with model training capability, where the model training capability includes a positioning model training capability;

Step 502: The second network element receives a second message from the first network element, where the second message is used to feed back a network element search result.

In the embodiment of the present application, the second network element sends a first message to the first network element, the first message is used to request to find a network element with model training capability, and the model training capability includes the training capability of the positioning model; the second network element receives a second message from the first network element, and the second message is used to feedback the network element search result. In this way, by requesting to find a network element with the training capability of the positioning model, the positioning model can participate in the positioning service, thereby improving the positioning accuracy.

In some embodiments, the first message includes at least one of the following information:

The first information is used to indicate that the network element requested to be searched needs to have the model training capability;

The second information is used to indicate the user object of the model trained by the network element requested to be searched;

The third information is used to indicate the usage area of the model trained by the network element requested to be searched;

The fourth information is used to indicate the positioning mode of the model trained by the network element requested to be searched;

The fifth information is used to indicate the reasoning method of the model trained by the network element requested to be searched;

The sixth information is used to indicate the type of inference result of the model trained by the network element requested to be searched;

The seventh information is used to indicate the input data type of the model trained by the network element requested to be searched;

The eighth information is used to indicate the task type of the model trained by the network element requested to be searched.

In some embodiments, the second message includes any of the following:

Information of a target network element, where the target network element is a network element having the model training capability;

The ninth message is used to indicate that the search failed.

In some embodiments, the second message includes information of the target network element;

The method further comprises:

The second network element sends a fourth message to the target network element, where the fourth message is used to request to obtain a target model, where the target model includes a positioning model.

Optionally, the second network element sends the fourth message to the target network element based on the network element information of the target network element.

It should be noted that the positioning model of the embodiment of the present application may also be an AI positioning model, or a model used for positioning/AI positioning, etc.

The second network element may further interact with the target network element and send a fourth message to the target network element to request to obtain the target model. The fourth message may be understood as a model request message, such as Nnwdaf_MLModelProvision_Subscribe or Nnwdaf_MLModelInfo_Request.

In some embodiments, the fourth message includes at least one of the following information:

The eighteenth information is used to indicate a request to obtain the target model;

Nineteenth information, used to indicate the user of the target model;

The twentieth information is used to indicate the usage area of the target model;

The twenty-first information is used to indicate the positioning mode of the target model;

The 22nd information is used to indicate the reasoning method of the target model;

The twenty-third information is used to indicate the inference result type of the target model;

The twenty-fourth information is used to indicate the input data type of the target model;

The twenty-fifth information is used to indicate the task type of the target model.

Taking the target model as the positioning model as an example, the eighteenth information can be understood as the indication information of requesting to obtain the positioning model, which is used to indicate that the request is to request to obtain the positioning model. The fourth message can also be used as the indication information of implicitly requesting the positioning model. For example, the target network element can deduce that the fourth message is used to request the positioning model through at least one of the service name and the indication information of the positioning task in the fourth message. The nineteenth information can be understood as the use object supported/allowed by the positioning model requested to be obtained. The twentieth information can be understood as the use area supported/allowed by the positioning model requested to be obtained. The twenty-first information can be understood as the positioning mode supported/allowed by the positioning model requested to be obtained. The twenty-second information can be understood as the reasoning method supported/allowed by the positioning model requested to be obtained. The twenty-third information can be understood as the reasoning result type supported/allowed by the positioning model requested to be obtained. The twenty-fourth information can be understood as the input data type supported/allowed by the positioning model requested to be obtained. The twenty-fifth information can be understood as the task type supported/allowed by the positioning model requested to be obtained.

For other information, please refer to the second to eighth information mentioned above. To avoid repetition, they will not be elaborated here.

In this implementation manner, by carrying one or more items of the above information in the fourth message, the network element requested to be searched by the second network element can better meet the needs of the second network element.

In some embodiments, the method further comprises:

The second network element receives a fifth message from the target network element, where the fifth message includes relevant information of the target model.

In some embodiments, the relevant information of the target model includes at least one of the following:

Address information of the target model;

The model file corresponding to the target model (model file);

Identification information of the target model (such as model ID);

The relevant information of the network elements of the target model is stored.

The address information of the target model can be understood as the storage address information of the target model, such as IP address, Uniform Resource Locator (URL).

The relevant information of the network element of the target model can be understood as the network element information storing the target model. The network element information may include FQDN or address information (such as IP address, Media Access Control (MAC) address), etc.

In addition, the relevant information of the target model may also include indication information of the effective area of the target model or indication information of the effective time of the target model, etc.

As mentioned above, the second network element may include network elements such as AMF, LMF or SMF. As an example, when the second network element is LMF and the target network element is NWDAF, the interaction between the second network element and the target network element may not be direct interaction, but forwarded by other network elements such as GMLC. Specifically, LMF sends a model request message to NWDAF through GMLC, and NWDAF sends model-related information to LMF through GMLC.

It should be noted that when the target network element fails to acquire a model, such as being unable to provide a model that meets the conditions, or there is no data that meets the conditions to train the model, the target network element may send a message indicating that the model acquisition failed to the second network element to inform the second network element that the model request failed.

In some embodiments, before the second network element sends the first message to the first network element, the method further includes:

The second network element receives a sixth message from the first device, where the sixth message is used to request acquisition of a target model, where the target model includes a positioning model.

The sixth message can be understood as a model request message.

In this implementation, the second network element does not send the first message to the first network element as a request initiator, nor does it send the first message to the first network element as a model demander, but sends the first message to the first network element based on the model request of the first device. In this case, the first device can be understood as a request initiator or a model demander.

In some embodiments, the method further comprises:

The second network element sends a seventh message to the first device, where the seventh message includes relevant information of the target model.

After the second network element obtains the relevant information of the target model sent by the target network element, the second network element may forward the relevant information of the target model to the first device. In this way, the first device can obtain the target model according to the relevant information of the target model, so that the first device can use the target model.

In some embodiments, before the second network element sends the first message to the first network element, the method further includes:

The second network element receives an eighth message from the second device, where the eighth message is used to request to obtain positioning information.

In this implementation, the second network element may be, for example, LMF, which decides to trigger the model request after receiving the location request of the second device. In this case, the second network element may be understood as a request initiator or a model demander.

In some embodiments, the method further comprises:

When the target model is acquired, the second network element determines the positioning information based on the target model and positioning-related data.

Specifically, LMF can obtain the target model based on the model-related information. LMF can also interact with a device such as UE to obtain measurement information or other positioning-related data, and generate positioning result data based on the acquired target model and positioning-related data, and feed back the positioning result data to a second device such as UE or AF.

The above is a network element search method on the second network element side. The related implementation methods on the first network element side can be applied to the second network element side and can achieve the same technical effect. To avoid repetition, this will not be described in detail. The following provides a network element search method on the third network element side.

FIG6 shows a flow chart of a network element search method provided by an embodiment of the present application. As shown in FIG6 , the network element search method includes the following steps:

Step 601: The third network element receives a fourth message from the second network element, where the fourth message is used to request to obtain a target model, where the target model includes a positioning model.

In the embodiment of the present application, the third network element receives a fourth message from the second network element, wherein the fourth message is used to request to obtain a target model, wherein the target model includes a positioning model. In this way, by requesting to obtain the positioning model, the positioning model can participate in the positioning service, thereby improving the positioning accuracy.

In some embodiments, the fourth message includes at least one of the following information:

The eighteenth information is used to indicate a request to obtain the target model;

Nineteenth information, used to indicate the user of the target model;

The twentieth information is used to indicate the usage area of the target model;

The twenty-first information is used to indicate the positioning mode of the target model;

The 22nd information is used to indicate the reasoning method of the target model;

The twenty-third information is used to indicate the inference result type of the target model;

The twenty-fourth information is used to indicate the input data type of the target model;

The twenty-fifth information is used to indicate the task type of the target model.

In some embodiments, the method further comprises:

The third network element sends a fifth message to the second network element based on the fourth message, and the fifth message includes relevant information of the target model. The target model is a model pre-trained by the third network element, or a model trained by the third network element based on the fourth message.

After receiving the fourth message and before sending the fifth message, the third network element may perform model selection or model training to obtain a model that meets the conditions. Specifically, the third network element selects an existing model that meets the conditions based on the received model request message. If there is no existing model that meets the conditions, the third network element may perform model training based on the model request message to generate a new model that meets the conditions.

A model that meets the conditions means that the information of the model matches the information in the model request message. For example, the usage object of the model (supported) is the model usage object in the model request message; for another example, the positioning mode of the model (applicable) is the required positioning mode in the model request message.

In some embodiments, the relevant information of the target model includes at least one of the following:

Address information of the target model;

A model file corresponding to the target model;

identification information of the target model;

The relevant information of the network elements of the target model is stored.

In some embodiments, the method further comprises:

The third network element sends a third message to the first network element, where the third message is used to request registration of relevant information of the third network element. The third message includes tenth information, where the tenth information is used to indicate that the third network element has model training capability, where the model training capability includes training capability of a positioning model.

In some embodiments, the third message further includes at least one of the following information:

The eleventh information is used to indicate the user of the model corresponding to the model training capability;

The twelfth information is used to indicate the usage area of the model corresponding to the model training capability;

Thirteenth information, used to indicate the positioning mode of the model corresponding to the model training capability;

The fourteenth information is used to indicate the reasoning method of the model corresponding to the model training capability;

Fifteenth information, used to indicate the inference result type of the model corresponding to the model training capability;

The sixteenth information is used to indicate the input data type of the model corresponding to the model training capability;

The seventeenth information is used to indicate the task type of the model corresponding to the model training capability.

The above is a network element search method on the third network element side. The relevant implementation methods on the first network element side and the second network element side can be applied to the third network element side and can achieve the same technical effect. To avoid repetition, this will not be described in detail. The following provides a network element search method on the first device side.

FIG7 shows a flow chart of a network element search method provided by an embodiment of the present application. As shown in FIG7 , the network element search method includes the following steps:

Step 701: The first device sends a sixth message to the second network element, where the sixth message is used to request to obtain a target model, where the target model includes a positioning model.

The first device may include, for example, a UE, a PRU, or a RAN.

In the embodiment of the present application, the first device sends a sixth message to the second network element, the sixth message is used to request to obtain a target model, the target model includes a positioning model. In this way, by requesting to obtain the positioning model, the positioning model can participate in the positioning service, thereby improving the positioning accuracy.

In some embodiments, the method further comprises:

The first device receives a seventh message from the second network element, where the seventh message includes relevant information of the target model.

In some embodiments, the relevant information of the target model includes at least one of the following:

Address information of the target model;

A model file corresponding to the target model;

identification information of the target model;

The relevant information of the network elements of the target model is stored.

The above is the network element search method on the first device side. The relevant implementation methods on the first network element side, the second network element side and the third network element side can all be applied to the first device side and can achieve the same technical effect. To avoid repetition, they will not be elaborated on.

The embodiment of the present application also provides a separate network element registration method, and the network element registration methods on the first network element side and the third network element side are described below respectively.

FIG8 shows a flow chart of a network element registration method provided by an embodiment of the present application. As shown in FIG8 , the network element registration method includes the following steps:

Step 801: A first network element receives a third message from a third network element, where the third message is used to request registration of relevant information of the third network element, and the third message includes tenth information, where the tenth information is used to indicate that the third network element has model training capability, and the model training capability includes positioning model training capability.

The third message can be understood as a registration request message. The third message can carry the target network element's own identification information (such as NF instance ID, FQDN or NF's IP address, network element instance identification, etc.), NF type, network element type and other information. The third message can also carry network element capability information, such as the tenth information. The tenth information can be understood as indicating that the network element supports training models for (AI) positioning, or, in other words, indicating that the network element has the ability to train positioning-related models.

After the first network element receives the registration request message from the third network element, it can save the network element registration information or network element capability information. The first network element can also feedback the registration request message to the third network element. Specifically, after receiving the registration request message, the first network element stores the network element registration information and sends a response message, such as an Nnrf_NFManagement_NFRegister response message, to notify the target network element that the registration is successful.

In an embodiment of the present application, a first network element receives a third message from a third network element, the third message is used to request registration of relevant information of the third network element, the third message includes tenth information, the tenth information is used to indicate that the third network element has model training capability, and the model training capability includes the training capability of the positioning model. In this way, by requesting registration of network element information of the third network element with model training capability, other network elements or devices can search for the third network element to obtain the positioning model to participate in the positioning service, thereby improving the positioning accuracy.

In some embodiments, the third message further includes at least one of the following information:

The eleventh information is used to indicate the user of the model corresponding to the model training capability;

The twelfth information is used to indicate the usage area of the model corresponding to the model training capability;

Thirteenth information, used to indicate the positioning mode of the model corresponding to the model training capability;

The fourteenth information is used to indicate the reasoning method of the model corresponding to the model training capability;

Fifteenth information, used to indicate the inference result type of the model corresponding to the model training capability;

The sixteenth information is used to indicate the input data type of the model corresponding to the model training capability;

The seventeenth information is used to indicate the task type of the model corresponding to the model training capability.

FIG9 shows a flow chart of a network element registration method provided by an embodiment of the present application. As shown in FIG9 , the network element registration method includes the following steps:

Step 901: The third network element sends a third message to the first network element, where the third message is used to request registration of relevant information of the third network element, and the third message includes tenth information, where the tenth information is used to indicate that the third network element has model training capability, and the model training capability includes positioning model training capability.

In the embodiment of the present application, the third network element sends a third message to the first network element, the third message is used to request the registration of relevant information of the third network element, the third message includes tenth information, the tenth information is used to indicate that the third network element has model training capability, and the model training capability includes the training capability of the positioning model. In this way, the third network element with model training capability can enable other network elements or devices to search for the third network element to obtain the positioning model to participate in the positioning service by requesting the registration of network element information, thereby improving the positioning accuracy.

In some embodiments, the third message further includes at least one of the following information:

The eleventh information is used to indicate the user of the model corresponding to the model training capability;

The twelfth information is used to indicate the usage area of the model corresponding to the model training capability;

Thirteenth information, used to indicate the positioning mode of the model corresponding to the model training capability;

The fourteenth information is used to indicate the reasoning method of the model corresponding to the model training capability;

Fifteenth information, used to indicate the inference result type of the model corresponding to the model training capability;

The sixteenth information is used to indicate the input data type of the model corresponding to the model training capability;

The seventeenth information is used to indicate the task type of the model corresponding to the model training capability.

In order to better understand the technical solution of the present application, the following specific embodiments are provided to exemplify the network element registration method and the network element search method of the present application. In addition, it should be noted that the details not described in the method embodiments corresponding to Figures 4 to 9 can be referred to the relevant description of any of the following embodiments, and the relevant description of any of the following embodiments is applicable to the method embodiments corresponding to Figures 4 to 9. To avoid repetition, no further description will be given.

Example 1: Network element registration process

In this embodiment, the network element registration process is specifically described by taking the first network element as NRF/AMF and the third network element as NWDAF as an example.

As shown in Figure 10, NWDAF represents the model training network element, which can also be other network elements or devices with model training capabilities; NRF represents the network storage function network element, which can also be other network elements or devices with storage functions, such as AMF. As shown in Figure 10, the network element registration process of this embodiment includes the following steps:

Step 1: NWDAF sends a request to NRF to request network element information registration. For example, NWDAF may send a network element registration message, such as Nnrf_NFManagement_NFRegister Request message, to NRF.

Specifically, when NWDAF sends a registration message to NRF, in addition to its own identification information (such as NF instance ID, FQDN, IP address of NF, network element instance identification information), NF type, network element type and other information, it can also carry network element capability information, where the network element capability information includes at least one of the following:

The capability indication of training positioning model is used to indicate that the network element supports training models for (AI) positioning, or has the capability of training positioning-related models;

The positioning method applicable to the positioning model is used to indicate the positioning method supported by the trained positioning model, such as at least one of the following: uplink positioning method, downlink positioning method, PRS-based, SRS-based;

Positioning reasoning methods corresponding to the positioning model, such as direct reasoning positioning and indirect reasoning positioning;

The user of the positioning model is used to indicate the objects that are allowed to use the positioning model, such as UE, PRU, gNB, LMF, etc.

The input data type of the positioning model is used to indicate the positioning related data used for positioning model training, such as measurement data (such as CIR, PDP, DP, RSRP, RSRPP or RSTD), intermediate feature data (such as TOA, path phase); auxiliary data (such as RS configuration), etc.

The output data type of the positioning model is used to indicate the type of inference result of the positioning model, such as intermediate features, location, location information, etc.

The indication of supported positioning tasks is used to indicate the positioning task identifiers supported by the NWDAF, such as analytics ID for AI positioning (analytics ID = AI positioning), or model functional type or task description information, such as supported model type, functionality ID, analytics ID or task type, etc., which is used to illustrate the functions or uses of the supported models.

Step 2: NRF saves the network element registration message or network element capability information.

Step 3: NRF sends a successful registration message to NWDAF.

Specifically, after receiving the registration message, NRF stores the network element registration information of NWDAF and sends a response message (for example, Nnrf_NFManagement_NFRegister response) to notify NWDAF that the registration is successful.

Example 2: Network element search process

In this embodiment, the network element search process is specifically described by taking the first network element as NRF/AMF, the second network element as AMF/LMF/SMF, the third network element as NWDAF, and the first device as UE/gNB/PRU as an example.

As shown in Figure 11, NWDAF represents the model training network element, which can also be other network elements or devices with model training capabilities; NRF/AMF represents the network storage function network element, which can also be other network elements or devices with storage functions; AMF/LMF/SMF represents the network element or device requesting the positioning model in the core network; UE/gNB/PRU represents the device requesting the positioning model outside the core network. As shown in Figure 11, the network element search process of this embodiment includes the following steps:

Step 1: UE/gNB/PRU triggers a model request and requests AMF/LMF to obtain the model; it may also be that LMF itself decides to trigger the model request after receiving the positioning task request (see Example 3 for details); it may also be other model request triggering methods.

Step 2: AMF and other devices send a network element search request (such as Nnrf_NFDiscovery_Request service) to NRF to find NWDAF network elements that meet the conditions. The network element search request can carry the network element type (used to indicate the type of network element to be searched, such as NWDAF network element), area information (used to indicate the service scope of the network element to be searched), and at least one of the following:

The capability indication of training the positioning model is used to indicate that the network element to be searched needs to have the capability of training the positioning model;

A positioning model usage object, or a target positioning model usage object, indicating a usage object of the positioning model of the network element being searched (need to be supported);

The required positioning method, or the target positioning method, indicates the positioning mode of the positioning model of the network element to be searched (need to be supported);

The required positioning reasoning method, or the target positioning reasoning method, indicates the positioning reasoning method of the positioning model of the network element to be searched (need to be supported);

The required inference result type, or target inference result type, indicates the inference result type of the positioning model of the network element to be searched (need to be supported);

The required input data type, or target input data type, indicates the input data type of the positioning model of the network element being searched (need to be supported);

Indicative information of the required positioning task, such as analytics ID and functionality ID for AI positioning;

It should be noted that when the AMF is both the network element that is prepared to perform model search and the network element that stores network element capability information, step 2 can be skipped and the AMF can select the network element that meets the conditions by itself.

Step 3: NRF feeds back the NWDAF information that meets the conditions, such as NF instance ID, IP address of NF, or FQDN, etc. For example, it can be fed back through Nnrf_NFDiscovery_Request response message.

Specifically, NRF can match the information in the network element search request sent by AMF/LMF/SMF in step 2 with the network element registration information to find at least one NWDAF that meets the conditions. Specifically, NRF/AMF determines whether the NWDAF is a NWDAF that meets the conditions based on whether the capability indication information of the trained positioning model matches the capability indication information of the trained positioning model in the network element capability; for example, if the positioning model usage object indication information matches the usage object capability information of the positioning model of the NWDAF, then it is a NWDAF that meets the conditions; other matching methods are similar and will not be elaborated here.

It should be noted that when the NRF search fails, such as not finding a NWDAF that meets the conditions, the NRF can feedback a request message of the search failure to the AMF, etc.

Step 4: AMF sends a model request message to the target NWDAF to request the positioning model. The model request message may carry the information in step 2. The model request message includes, for example, Nnwdaf_MLModelProvision_Subscribe or Nnwdaf_MLModelInfo_Request.

Specifically, the AMF sends a model request message to the NWDAF found in steps 2 to 3, requesting the NWDAF to feedback a model that meets the conditions. The message may carry:

Indication information for requesting a positioning model, used to indicate that the request is for obtaining a positioning model; the indication information may also be an implicit indication, such as combining the indication information of the service name and/or the positioning task to indicate that the message is for requesting a positioning model;

Indicative information of the required positioning task, such as analytics ID and functionality ID for AI positioning;

A model user object, or a target model user object, indicating a user object of the requested model;

The desired positioning method, or target positioning method, indicates the requested positioning mode of the model;

The required output data type, or inference result type, target inference result type, etc., indicates the inference result type of the requested model;

The required input data type, or target input data type, indicates the input data type of the requested model.

Step 5: NWDAF performs model training or model selection to obtain a model that meets the requirements.

Step 6: NWDAF sends model-related information to AMF. The model-related information may include the model storage address or the address information of the model storage network element.

Step 7: AMF sends model-related information to devices such as UE/gNB/PRU. The model-related information may include the model storage address or the address information of the model storage network element.

Example 3: Network element search process

In this embodiment, the network element search process is specifically described by taking the first network element as NRF/AMF, the second network element as LMF, the third network element as NWDAF, the first device as UE/RAN, and the second device as AF as an example.

As shown in Figure 12, NWDAF represents the model training network element, which can also be other network elements or devices with model training capabilities; NRF/AMF represents the network storage function network element, which can also be other network elements or devices with storage functions; AMF represents the network element or device requesting the positioning model in the core network; UE/RAN (or AF) represents the device requesting positioning outside the core network. As shown in Figure 12, the network element search process of this embodiment includes the following steps:

Step 0a (or 0b): UE/RAN (or AF) sends a positioning request message to LMF, requesting LMF to perform positioning interaction. It should be noted that AF here represents an application network element, which can also be a third-party network element. At the same time, the device executing step 0b can also be a network element inside the core network, such as a NWDAF.

Step 1: LMF sends a network element search request to NRF to find an NWDAF that meets the requirements.

Step 2: NRF feeds back the NWDAF network element information that meets the conditions.

Step 3: The LMF sends a model request message to the target NWDAF to request the acquisition of the positioning model. The model request message includes, for example, Nnwdaf_MLModelProvision_Subscribe or Nnwdaf_MLModelInfo_Request.

Specifically, LMF sends a model request message to the NWDAF found in step 1 to step 2, requesting NWDAF to feedback a model that meets the conditions. The message may carry:

Indication information for requesting a positioning model, used to indicate that the request is for obtaining a positioning model; the indication information may also be an implicit indication, such as combining the indication information of the service name and/or the positioning task to indicate that the message is for requesting a positioning model;

Indicative information of the required positioning task, such as analytics ID and functionality ID for AI positioning;

A model user object, or a target model user object, indicating a user object of the requested model;

The desired positioning method, or target positioning method, indicates the requested positioning mode of the model;

The required output data type, or inference result type, target inference result type, etc., indicates the inference result type of the requested model;

The required input data type, or target input data type, indicates the input data type of the requested model.

It should be noted that the interaction between LMF and NWDAF may not be direct interaction, but indirect interaction forwarded through GMLC. Specifically, LMF sends a model request message to NWDAF through GMLC, and NWDAF sends model related information to LMF through GMLC.

Step 4: NWDAF performs model training or model selection to obtain a model that meets the requirements.

Specifically, NWDAF obtains a model that meets the conditions based on the model request message received in step 3. It can generate a new model through model training, or select an existing model that meets the conditions through model selection. A model that meets the conditions means that the information of the model matches the information in the model request message. For example, the user object of the model is the model user object in the request message, and the positioning mode of the model (applicable) is the required positioning mode in the request message. Other matching methods are similar and will not be elaborated here.

Step 5: NWDAF feeds back the model-related information that meets the conditions to LMF. The model-related information can be the model storage address (IP address, URL), or the model file (model file), or the network element information stored in the model, or the model ID, etc. The network element information includes FQDN or address information (such as IP address, MAC address), etc. In addition, it may also carry other model-related information such as the model's effective area information or effective time information.

It should be noted that when NWDAF fails to obtain a model, such as being unable to provide a model that meets the conditions, or having no data that meets the conditions to train the model, NWDAF sends a message to LMF etc. indicating that the model acquisition failed, to inform LMF that the model request failed.

Step 6: LMF interacts with UE and other devices to obtain measurement information or other positioning-related data; LMF generates a positioning result based on the acquired positioning model, and can feed back the positioning result to the requester of step 0a (or step 0b), such as UE (or AF).

In summary, the embodiments of the present application provide a network element registration method for positioning model training capabilities. A network element (such as model training network elements such as NWDAF) can send information related to its positioning model training capabilities to other network elements (such as NRF, AMF, etc.) to notify other network elements that it has information such as positioning model training capabilities, so that other network elements (such as AMF, LMF, SMF, etc.) can find network elements with positioning model training capabilities through search, selection, etc., so as to perform further interaction in the future to obtain positioning models, etc.

The network element search method provided in the embodiment of the present application may be executed by a network element search device. The network element registration method provided in the embodiment of the present application may be executed by a network element registration device. In the embodiment of the present application, the network element search method performed by a network element search device is taken as an example, and the network element registration method performed by a network element registration device is taken as an example to sequentially explain the network element search device and the network element registration device provided in the embodiment of the present application.

FIG13 shows a structural diagram of a network element search device provided in an embodiment of the present application, and the network element search device can be applied to a first network element. As shown in FIG13 , the network element search device 1300 includes:

A first receiving module 1301 is used to receive a first message from a second network element, where the first message is used to request to find a network element with a model training capability, where the model training capability includes a positioning model training capability;

The sending module 1302 is used to send a second message to the second network element, where the second message is used to feed back the network element search result.

Optionally, the first message includes at least one of the following information:

The first information is used to indicate that the network element requested to be searched needs to have the model training capability;

The second information is used to indicate the user object of the model trained by the network element requested to be searched;

The third information is used to indicate the usage area of the model trained by the network element requested to be searched;

The fourth information is used to indicate the positioning mode of the model trained by the network element requested to be searched;

The fifth information is used to indicate the reasoning method of the model trained by the network element requested to be searched;

The sixth information is used to indicate the type of inference result of the model trained by the network element requested to be searched;

The seventh information is used to indicate the input data type of the model trained by the network element requested to be searched;

The eighth information is used to indicate the task type of the model trained by the network element requested to be searched.

Optionally, the second message includes any one of the following items:

Information of a target network element, where the target network element is a network element having the model training capability;

The ninth message is used to indicate that the search failed.

Optionally, the network element searching device 1300 further includes:

A processing module is used to determine a target network element according to the first message, wherein information of the target network element matches information in the first message.

Optionally, the processing module is specifically used for at least one of the following:

In a case where the first message includes first information, and the first information is used to indicate that the network element requested to be searched needs to have the model training capability, determining the target network element according to the first information, wherein the target network element is a network element having the model training capability;

In a case where the first message includes second information, and the second information is used to indicate a user object of the model trained by the network element requested to be searched, determining the target network element according to the second information, wherein the user object of the model trained by the target network element matches the second information;

In a case where the first message includes third information, the third information is used to indicate a usage area of a model trained by the network element requested to be searched, determining the target network element according to the third information, wherein the usage area of the model trained by the target network element matches the third information;

In a case where the first message includes fourth information, and the fourth information is used to indicate a positioning mode of a model trained by the network element requested to be searched, determining the target network element according to the fourth information, wherein the positioning mode of the model trained by the target network element matches the fourth information;

In a case where the first message includes fifth information, and the fifth information is used to indicate the reasoning mode of the model trained by the network element requested to be searched, determining the target network element according to the fifth information, wherein the model reasoning mode of the model trained by the target network element matches the fifth information;

In a case where the first message includes sixth information, and the sixth information is used to indicate a type of inference result of a model trained by the network element requested to be searched, determining the target network element according to the sixth information, wherein the type of inference result of the model trained by the target network element matches the sixth information;

In a case where the first message includes seventh information, and the seventh information is used to indicate an input data type of a model trained by the network element requested to be searched, determining the target network element according to the seventh information, wherein the input data type of the model trained by the target network element matches the seventh information;

In a case where the first message includes eighth information, and the eighth information is used to indicate a task type of a model trained by the network element requested to be searched, the target network element is determined based on the eighth information, wherein the task type of the model trained by the target network element matches the eighth information.

Optionally, the network element searching device 1300 further includes:

The second receiving module is used to receive a third message from the target network element, where the third message is used to request to register relevant information of the target network element.

Optionally, the third message includes at least one of the following information:

Tenth information, used to indicate that the target network element has a model training capability, where the model training capability includes a positioning model training capability;

The eleventh information is used to indicate the user of the model corresponding to the model training capability;

The twelfth information is used to indicate the usage area of the model corresponding to the model training capability;

Thirteenth information, used to indicate the positioning mode of the model corresponding to the model training capability;

The fourteenth information is used to indicate the reasoning method of the model corresponding to the model training capability;

Fifteenth information, used to indicate the inference result type of the model corresponding to the model training capability;

The sixteenth information is used to indicate the input data type of the model corresponding to the model training capability;

The seventeenth information is used to indicate the task type of the model corresponding to the model training capability.

FIG14 shows a structural diagram of a network element search device provided in an embodiment of the present application, and the network element search device can be applied to a second network element. As shown in FIG14 , the network element search device 1400 includes:

A first sending module 1401 is used to send a first message to a first network element, where the first message is used to request to find a network element with a model training capability, where the model training capability includes a positioning model training capability;

The first receiving module 1402 is used to receive a second message from the first network element, where the second message is used to feed back a network element search result.

Optionally, the first message includes at least one of the following information:

The first information is used to indicate that the network element requested to be searched needs to have the model training capability;

The second information is used to indicate the user object of the model trained by the network element requested to be searched;

The third information is used to indicate the usage area of the model trained by the network element requested to be searched;

The fourth information is used to indicate the positioning mode of the model trained by the network element requested to be searched;

The fifth information is used to indicate the reasoning method of the model trained by the network element requested to be searched;

The sixth information is used to indicate the type of inference result of the model trained by the network element requested to be searched;

The seventh information is used to indicate the input data type of the model trained by the network element requested to be searched;

The eighth information is used to indicate the task type of the model trained by the network element requested to be searched.

Optionally, the second message includes any one of the following items:

Information of a target network element, where the target network element is a network element having the model training capability;

The ninth message is used to indicate that the search failed.

Optionally, the second message includes information of the target network element;

The network element searching device 1400 further includes:

The second sending module is used to send a fourth message to the target network element, where the fourth message is used to request to obtain a target model, where the target model includes a positioning model.

Optionally, the fourth message includes at least one of the following information:

The eighteenth information is used to indicate a request to obtain the target model;

Nineteenth information, used to indicate the user of the target model;

The twentieth information is used to indicate the usage area of the target model;

The twenty-first information is used to indicate the positioning mode of the target model;

The 22nd information is used to indicate the reasoning method of the target model;

The twenty-third information is used to indicate the inference result type of the target model;

The twenty-fourth information is used to indicate the input data type of the target model;

The twenty-fifth information is used to indicate the task type of the target model.

Optionally, the network element searching device 1400 further includes:

The second receiving module is used to receive a fifth message from the target network element, where the fifth message includes relevant information of the target model.

Optionally, the relevant information of the target model includes at least one of the following:

Address information of the target model;

A model file corresponding to the target model;

identification information of the target model;

The relevant information of the network elements of the target model is stored.

Optionally, the network element searching device 1400 further includes:

The third receiving module is used to receive a sixth message from the first device, where the sixth message is used to request to obtain a target model, where the target model includes a positioning model.

Optionally, the network element searching device 1400 further includes:

The third sending module is used to send a seventh message to the first device, where the seventh message includes relevant information of the target model.

Optionally, the network element searching device 1400 further includes:

The fourth receiving module is used to receive an eighth message from the second device, where the eighth message is used to request to obtain positioning information.

Optionally, the network element searching device 1400 further includes:

A processing module is used to determine the positioning information based on the target model and positioning related data when the target model is acquired.

FIG15 shows a structural diagram of a network element search device provided in an embodiment of the present application, and the network element search device can be applied to a third network element. As shown in FIG15 , the network element search device 1500 includes:

The receiving module 1501 is used to receive a fourth message from the second network element, where the fourth message is used to request to obtain a target model, where the target model includes a positioning model.

Optionally, the fourth message includes at least one of the following information:

The eighteenth information is used to indicate a request to obtain the target model;

Nineteenth information, used to indicate the user of the target model;

The twentieth information is used to indicate the usage area of the target model;

The twenty-first information is used to indicate the positioning mode of the target model;

The 22nd information is used to indicate the reasoning method of the target model;

The twenty-third information is used to indicate the inference result type of the target model;

The twenty-fourth information is used to indicate the input data type of the target model;

The twenty-fifth information is used to indicate the task type of the target model.

Optionally, the network element searching device 1500 further includes:

The first sending module is used to send a fifth message to the second network element based on the fourth message, and the fifth message includes relevant information of the target model. The target model is a model pre-trained by the third network element, or a model trained by the third network element based on the fourth message.

Optionally, the relevant information of the target model includes at least one of the following:

Address information of the target model;

A model file corresponding to the target model;

identification information of the target model;

The relevant information of the network elements of the target model is stored.

Optionally, the network element searching device 1500 further includes:

The second sending module is used to send a third message to the first network element, where the third message is used to request registration of relevant information of the third network element, and the third message includes tenth information, where the tenth information is used to indicate that the third network element has model training capability, and the model training capability includes the training capability of the positioning model.

Optionally, the third message further includes at least one of the following information:

The eleventh information is used to indicate the user of the model corresponding to the model training capability;

The twelfth information is used to indicate the usage area of the model corresponding to the model training capability;

Thirteenth information, used to indicate the positioning mode of the model corresponding to the model training capability;

The fourteenth information is used to indicate the reasoning method of the model corresponding to the model training capability;

Fifteenth information, used to indicate the inference result type of the model corresponding to the model training capability;

The sixteenth information is used to indicate the input data type of the model corresponding to the model training capability;

The seventeenth information is used to indicate the task type of the model corresponding to the model training capability.

FIG16 shows a structural diagram of a network element search device provided in an embodiment of the present application, and the network element search device can be applied to a first device. As shown in FIG16 , the network element search device 1600 includes:

The sending module 1601 is used to send a sixth message to the second network element, where the sixth message is used to request to obtain a target model, where the target model includes a positioning model.

Optionally, the network element searching device 1600 further includes:

A receiving module is used to receive a seventh message from the second network element, where the seventh message includes relevant information of the target model.

Optionally, the relevant information of the target model includes at least one of the following:

Address information of the target model;

A model file corresponding to the target model;

identification information of the target model;

The relevant information of the network elements of the target model is stored.

The network element search device in the embodiment of the present application can be an electronic device, such as an electronic device with an operating system, or a component in an electronic device, such as an integrated circuit or a chip. The electronic device can be a terminal, or it can be other devices other than a terminal. Exemplarily, the terminal can include but is not limited to the types of terminals listed above, and other devices can be servers, network attached storage (NAS), etc., which are not specifically limited in the embodiment of the present application.

The network element search device provided in the embodiment of the present application can implement each process implemented by the method embodiments of Figures 4 to 7 and achieve the same technical effect. To avoid repetition, it will not be repeated here.

FIG17 shows a structural diagram of a network element registration device provided in an embodiment of the present application, and the network element registration device can be applied to a first network element. As shown in FIG17 , the network element registration device 1700 includes:

Receiving module 1701 is used to receive a third message from a third network element, where the third message is used to request registration of relevant information of the third network element, and the third message includes tenth information, where the tenth information is used to indicate that the third network element has model training capabilities, and the model training capabilities include positioning model training capabilities.

Optionally, the third message further includes at least one of the following information:

The eleventh information is used to indicate the user of the model corresponding to the model training capability;

The twelfth information is used to indicate the usage area of the model corresponding to the model training capability;

Thirteenth information, used to indicate the positioning mode of the model corresponding to the model training capability;

The fourteenth information is used to indicate the reasoning method of the model corresponding to the model training capability;

Fifteenth information, used to indicate the inference result type of the model corresponding to the model training capability;

The sixteenth information is used to indicate the input data type of the model corresponding to the model training capability;

The seventeenth information is used to indicate the task type of the model corresponding to the model training capability.

FIG18 shows a structural diagram of a network element registration device provided in an embodiment of the present application, and the network element registration device can be applied to a third network element. As shown in FIG18 , the network element registration device 1800 includes:

Sending module 1801 is used to send a third message to the first network element, where the third message is used to request registration of relevant information of the third network element, and the third message includes tenth information, where the tenth information is used to indicate that the third network element has model training capability, and the model training capability includes the training capability of the positioning model.

Optionally, the third message further includes at least one of the following information:

The eleventh information is used to indicate the user of the model corresponding to the model training capability;

The twelfth information is used to indicate the usage area of the model corresponding to the model training capability;

Thirteenth information, used to indicate the positioning mode of the model corresponding to the model training capability;

The fourteenth information is used to indicate the reasoning method of the model corresponding to the model training capability;

Fifteenth information, used to indicate the inference result type of the model corresponding to the model training capability;

The sixteenth information is used to indicate the input data type of the model corresponding to the model training capability;

The seventeenth information is used to indicate the task type of the model corresponding to the model training capability.

The network element registration device in the embodiment of the present application can be an electronic device, such as an electronic device with an operating system, or a component in an electronic device, such as an integrated circuit or a chip. The electronic device can be a terminal, or it can be other devices other than a terminal. Exemplarily, the terminal can include but is not limited to the types of terminals listed above, and other devices can be servers, network attached storage (NAS), etc., which are not specifically limited in the embodiment of the present application.

The network element registration device provided in the embodiment of the present application can implement the various processes implemented by the method embodiments of Figures 8 to 9 and achieve the same technical effect. To avoid repetition, it will not be repeated here.

It should be noted that the processing module in the network element registration device provided in Fig. 13 can be embedded in or independent of the processor in the form of hardware. Correspondingly, the processing module in the network element registration device provided in Fig. 14 can be embedded in or independent of the processor in the form of hardware.

As shown in Figure 19, an embodiment of the present application also provides a communication device 1900, including a processor 1901 and a memory 1902, and the memory 1902 stores a program or instruction that can be run on the processor 1901. When the program or instruction is executed by the processor 1901, it implements the various steps of the above-mentioned network element search method embodiment, or implements the various steps of the above-mentioned network element registration method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

An embodiment of the present application also provides a communication device, including a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run a program or instruction to implement the steps of the method embodiment shown in Figure 4, or the steps of the method embodiment shown in Figure 5, or the steps of the method embodiment shown in Figure 6, or the steps of the method embodiment shown in Figure 7, or the steps of the method embodiment shown in Figure 8, or the steps of the method embodiment shown in Figure 9, and can achieve the same technical effect.

In the embodiment of the present application, the communication device may include a terminal or a network side device.

Specifically, Figure 20 is a schematic diagram of the hardware structure of a terminal implementing an embodiment of the present application.

The terminal 2000 includes but is not limited to: a radio frequency unit 2001, a network module 2002, an audio output unit 2003, an input unit 2004, a sensor 2005, a display unit 2006, a user input unit 2007, an interface unit 2008, a memory 2009 and at least some of the components of the processor 2010.

Those skilled in the art will appreciate that the terminal 2000 may also include a power source (such as a battery) for supplying power to each component, and the power source may be logically connected to the processor 2010 through a power management system, so as to implement functions such as managing charging, discharging, and power consumption management through the power management system. The terminal structure shown in FIG20 does not constitute a limitation on the terminal, and the terminal may include more or fewer components than shown in the figure, or combine certain components, or arrange components differently, which will not be described in detail here.

It should be understood that in the embodiment of the present application, the input unit 2004 may include a graphics processing unit (GPU) 20041 and a microphone 20042, and the graphics processing unit 20041 processes the image data of the static picture or video obtained by the image capture device (such as a camera) in the video capture mode or the image capture mode. The display unit 2006 may include a display panel 20061, and the display panel 20061 may be configured in the form of a liquid crystal display, an organic light emitting diode, etc. The user input unit 2007 includes a touch panel 20071 and at least one of other input devices 20072. The touch panel 20071 is also called a touch screen. The touch panel 20071 may include two parts: a touch detection device and a touch controller. Other input devices 20072 may include, but are not limited to, a physical keyboard, function keys (such as a volume control key, a switch key, etc.), a trackball, a mouse, and a joystick, which will not be repeated here.

In the embodiment of the present application, after receiving downlink data from the network side device, the RF unit 2001 can transmit the data to the processor 2010 for processing; in addition, the RF unit 2001 can send uplink data to the network side device. Generally, the RF unit 2001 includes but is not limited to an antenna, an amplifier, a transceiver, a coupler, a low noise amplifier, a duplexer, etc.

The memory 2009 can be used to store software programs or instructions and various data. The memory 2009 can mainly include a first storage area for storing programs or instructions and a second storage area for storing data, wherein the first storage area can store an operating system, an application program or instruction required for at least one function (such as a sound playback function, an image playback function, etc.), etc. In addition, the memory 2009 can include a volatile memory or a non-volatile memory. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), a static random access memory (SRAM), a dynamic random access memory (DRAM), a synchronous dynamic random access memory (SDRAM), a double data rate synchronous dynamic random access memory (DDRSDRAM), an enhanced synchronous dynamic random access memory (ESDRAM), a synchronous link dynamic random access memory (SLDRAM) and a direct memory bus random access memory (DRRAM). The memory 2009 in the embodiment of the present application includes but is not limited to these and any other suitable types of memory.

The processor 2010 may include one or more processing units; optionally, the processor 2010 integrates an application processor and a modem processor, wherein the application processor mainly processes operations related to an operating system, a user interface, and application programs, and the modem processor mainly processes wireless communication signals, such as a baseband processor. It is understandable that the modem processor may not be integrated into the processor 2010.

The radio frequency unit 2001 is used for:

A sixth message is sent to the second network element, where the sixth message is used to request acquisition of a target model, where the target model includes a positioning model.

Optionally, the radio frequency unit 2001 is further configured to:

A seventh message is received from the second network element, where the seventh message includes relevant information of the target model.

Optionally, the relevant information of the target model includes at least one of the following:

Address information of the target model;

A model file corresponding to the target model;

identification information of the target model;

The relevant information of the network elements of the target model is stored.

In summary, in the embodiments of the present application, a request can be made to obtain a positioning model, so that the positioning model can participate in the positioning service, thereby improving the positioning accuracy.

The embodiment of the present application also provides an access network device, including a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run a program or instruction to implement the steps of the method embodiment shown in Figure 7. The access network device embodiment corresponds to the first device side method embodiment described above. Each implementation process and implementation method of the first device side method embodiment described above can be applied to the access network device embodiment, and can achieve the same technical effect.

Specifically, an embodiment of the present application also provides an access network device. As shown in Figure 21, the access network device 2100 includes: an antenna 211, a radio frequency device 212, a baseband device 213, a processor 214 and a memory 215. The antenna 211 is connected to the radio frequency device 212. In the uplink direction, the radio frequency device 212 receives information through the antenna 211 and sends the received information to the baseband device 213 for processing. In the downlink direction, the baseband device 213 processes the information to be sent and sends it to the radio frequency device 212. The radio frequency device 212 processes the received information and sends it out through the antenna 211.

The method executed by the access network device in the above embodiment may be implemented in the baseband device 213, which includes a baseband processor.

The baseband device 213 may include, for example, at least one baseband board, on which a plurality of chips are arranged, as shown in FIG. 21 , wherein one of the chips is, for example, a baseband processor, which is connected to the memory 215 through a bus interface to call a program in the memory 215 and execute the network device operations shown in the above method embodiment.

The access network device may also include a network interface 216, which is, for example, a Common Public Radio Interface (CPRI).

Specifically, the access network device 2100 of the embodiment of the present application also includes: instructions or programs stored in the memory 215 and executable on the processor 214. The processor 214 calls the instructions or programs in the memory 215 to execute the methods executed by the modules shown in Figure 16 and achieve the same technical effect. To avoid repetition, it will not be repeated here.

The embodiment of the present application also provides a core network device. As shown in FIG22 , the core network device 2200 includes: a processor 2201, a network interface 2202, and a memory 2203. The network interface 2202 is, for example, a common public radio interface (CPRI).

Specifically, the core network device 2200 of the embodiment of the present application also includes: instructions or programs stored in the memory 2203 and executable on the processor 2201. The processor 2201 calls the instructions or programs in the memory 2203 to execute the methods executed by the modules shown in Figure 13, Figure 14, or Figure 15, and achieves the same technical effect. To avoid repetition, it will not be repeated here.

An embodiment of the present application also provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, the various processes of the above-mentioned network element search method embodiment are implemented, or the various processes of the above-mentioned network element registration method embodiment are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

The processor is the processor in the terminal described in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory ROM, a random access memory RAM, a magnetic disk or an optical disk. In some examples, the readable storage medium may be a non-transient readable storage medium.

An embodiment of the present application further provides a chip, which includes a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the various processes of the above-mentioned network element search method embodiment, or to implement the various processes of the above-mentioned network element registration method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

The embodiments of the present application further provide a computer program/program product, which is stored in a storage medium, and is executed by at least one processor to implement the various processes of the above-mentioned network element search method embodiment, or to implement the various processes of the above-mentioned network element registration method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

An embodiment of the present application also provides a communication system, including: a first network element and a second network element, wherein the first network element can be used to execute the steps executed by the first network element in the above-mentioned network element search method, and the second network element can be used to execute the steps executed by the second network element in the above-mentioned network element search method.

In one implementation, the communication system further includes a third network element, and the third network element can be used to execute the steps executed by the third network element in the network element search method as described above.

In another implementation, the communication system further includes a first device, and the first device can be used to execute the steps executed by the first device in the network element search method as described above.

An embodiment of the present application also provides a communication system, including: a first network element and a third network element, wherein the first network element can be used to execute the steps executed by the first network element in the network element registration method as described above, and the third network element can be used to execute the steps executed by the third network element in the network element registration method as described above.

It should be noted that, in this article, the terms "comprise", "include" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises one..." does not exclude the presence of other identical elements in the process, method, article or device including the element. In addition, it should be pointed out that the scope of the method and device in the embodiment of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in reverse order according to the functions involved, for example, the described method may be performed in an order different from that described, and various steps may also be added, omitted or combined. In addition, the features described with reference to certain examples may be combined in other examples.

Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of a computer software product plus a necessary general hardware platform, and of course, can also be implemented by hardware. The computer software product is stored in a storage medium (such as ROM, RAM, disk, CD, etc.), including several instructions to enable a terminal or a network-side device to execute the methods described in each embodiment of the present application.

The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms of implementation methods without departing from the purpose of the present application and the scope of protection of the claims, and these implementation methods are all within the protection of the present application.

Claims (51)

A network element search method, comprising: The first network element receives a first message from the second network element, where the first message is used to request to find a network element with a model training capability, where the model training capability includes a positioning model training capability; The first network element sends a second message to the second network element, where the second message is used to feed back a network element search result. The method according to claim 1, wherein the first message includes at least one of the following information: The first information is used to indicate that the network element requested to be searched needs to have the model training capability; The second information is used to indicate the user object of the model trained by the network element requested to be searched; The third information is used to indicate the usage area of the model trained by the network element requested to be searched; The fourth information is used to indicate the positioning mode of the model trained by the network element requested to be searched; The fifth information is used to indicate the reasoning method of the model trained by the network element requested to be searched; The sixth information is used to indicate the type of inference result of the model trained by the network element requested to be searched; The seventh information is used to indicate the input data type of the model trained by the network element requested to be searched; The eighth information is used to indicate the task type of the model trained by the network element requested to be searched. The method according to claim 1 or 2, wherein the second message includes any one of the following: Information of a target network element, where the target network element is a network element having the model training capability; The ninth message is used to indicate that the search failed. The method according to any one of claims 1 to 3, wherein the method further comprises: The first network element determines a target network element based on the first message, and information of the target network element matches information in the first message. The method according to claim 4, wherein the first network element determines the target network element according to the first message, comprising at least one of the following: The first message includes first information, where the first information is used to indicate that the network element requested to be searched needs to have the model training capability, and the first network element determines the target network element according to the first information, wherein the target network element is a network element with the model training capability; The first message includes second information, where the second information is used to indicate a usage object of the model trained by the network element requested to be searched, and the first network element determines the target network element according to the second information, wherein the usage object of the model trained by the target network element matches the second information; The first message includes third information, where the third information is used to indicate a usage area of a model trained by the network element requested to be searched, and the first network element determines the target network element according to the third information, wherein the usage area of the model trained by the target network element matches the third information; The first message includes fourth information, where the fourth information is used to indicate a positioning mode of a model trained by the network element requested to be searched, and the first network element determines the target network element according to the fourth information, wherein the positioning mode of the model trained by the target network element matches the fourth information; The first message includes fifth information, where the fifth information is used to indicate the reasoning mode of the model trained by the network element requested to be searched, and the first network element determines the target network element according to the fifth information, wherein the model reasoning mode of the model trained by the target network element matches the fifth information; The first message includes sixth information, where the sixth information is used to indicate a type of inference result of a model trained by the network element requested to be searched, and the first network element determines the target network element according to the sixth information, wherein the type of inference result of the model trained by the target network element matches the sixth information; The first message includes seventh information, where the seventh information is used to indicate an input data type of a model trained by the network element requested to be searched, and the first network element determines the target network element according to the seventh information, wherein the input data type of the model trained by the target network element matches the seventh information; The first message includes eighth information, and the eighth information is used to indicate the task type of the model trained by the network element requested to be searched. The first network element determines the target network element based on the eighth information, wherein the task type of the model trained by the target network element matches the eighth information. The method according to any one of claims 3 to 5, wherein the method further comprises: The first network element receives a third message from the target network element, where the third message is used to request registration of relevant information of the target network element. The method according to claim 6, wherein the third message includes at least one of the following information: Tenth information, used to indicate that the target network element has a model training capability, where the model training capability includes a positioning model training capability; The eleventh information is used to indicate the user of the model corresponding to the model training capability; The twelfth information is used to indicate the usage area of the model corresponding to the model training capability; Thirteenth information, used to indicate the positioning mode of the model corresponding to the model training capability; The fourteenth information is used to indicate the reasoning method of the model corresponding to the model training capability; Fifteenth information, used to indicate the inference result type of the model corresponding to the model training capability; The sixteenth information is used to indicate the input data type of the model corresponding to the model training capability; The seventeenth information is used to indicate the task type of the model corresponding to the model training capability. A network element search method, comprising: The second network element sends a first message to the first network element, where the first message is used to request to find a network element with a model training capability, where the model training capability includes a positioning model training capability; The second network element receives a second message from the first network element, where the second message is used to feed back a network element search result. The method according to claim 8, wherein the first message includes at least one of the following information: The first information is used to indicate that the network element requested to be searched needs to have the model training capability; The second information is used to indicate the user object of the model trained by the network element requested to be searched; The third information is used to indicate the usage area of the model trained by the network element requested to be searched; The fourth information is used to indicate the positioning mode of the model trained by the network element requested to be searched; The fifth information is used to indicate the reasoning method of the model trained by the network element requested to be searched; The sixth information is used to indicate the type of inference result of the model trained by the network element requested to be searched; The seventh information is used to indicate the input data type of the model trained by the network element requested to be searched; The eighth information is used to indicate the task type of the model trained by the network element requested to be searched. The method according to claim 8 or 9, wherein the second message includes any one of the following: Information of a target network element, where the target network element is a network element having the model training capability; The ninth message is used to indicate that the search failed. The method according to claim 10, wherein the second message includes information of the target network element; The method further comprises: The second network element sends a fourth message to the target network element, where the fourth message is used to request to obtain a target model, where the target model includes a positioning model. The method according to claim 11, wherein the fourth message includes at least one of the following information: The eighteenth information is used to indicate a request to obtain the target model; Nineteenth information, used to indicate the user of the target model; The twentieth information is used to indicate the usage area of the target model; The twenty-first information is used to indicate the positioning mode of the target model; The 22nd information is used to indicate the reasoning method of the target model; The twenty-third information is used to indicate the inference result type of the target model; The twenty-fourth information is used to indicate the input data type of the target model; The twenty-fifth information is used to indicate the task type of the target model. The method according to claim 11 or 12, wherein the method further comprises: The second network element receives a fifth message from the target network element, where the fifth message includes relevant information of the target model. The method according to claim 13, wherein the relevant information of the target model includes at least one of the following: Address information of the target model; A model file corresponding to the target model; identification information of the target model; The relevant information of the network elements of the target model is stored. The method according to any one of claims 8 to 14, wherein before the second network element sends the first message to the first network element, the method further comprises: The second network element receives a sixth message from the first device, where the sixth message is used to request acquisition of a target model, where the target model includes a positioning model. The method according to claim 15, wherein the method further comprises: The second network element sends a seventh message to the first device, where the seventh message includes relevant information of the target model. The method according to any one of claims 8 to 14, wherein before the second network element sends the first message to the first network element, the method further comprises: The second network element receives an eighth message from the second device, where the eighth message is used to request to obtain positioning information. The method according to claim 17, wherein the method further comprises: When the target model is acquired, the second network element determines the positioning information based on the target model and positioning related data. A network element search method, comprising: The third network element receives a fourth message from the second network element, where the fourth message is used to request acquisition of a target model, where the target model includes a positioning model. The method according to claim 19, wherein the fourth message includes at least one of the following information: The eighteenth information is used to indicate a request to obtain the target model; Nineteenth information, used to indicate the user of the target model; The twentieth information is used to indicate the usage area of the target model; The twenty-first information is used to indicate the positioning mode of the target model; The 22nd information is used to indicate the reasoning method of the target model; The twenty-third information is used to indicate the inference result type of the target model; The twenty-fourth information is used to indicate the input data type of the target model; The twenty-fifth information is used to indicate the task type of the target model. The method according to claim 19 or 20, wherein the method further comprises: The third network element sends a fifth message to the second network element based on the fourth message, and the fifth message includes relevant information of the target model. The target model is a model pre-trained by the third network element, or a model trained by the third network element based on the fourth message. The method according to claim 21, wherein the relevant information of the target model includes at least one of the following: Address information of the target model; A model file corresponding to the target model; identification information of the target model; The relevant information of the network elements of the target model is stored. The method according to any one of claims 19 to 22, wherein the method further comprises: The third network element sends a third message to the first network element, where the third message is used to request registration of relevant information of the third network element. The third message includes tenth information, where the tenth information is used to indicate that the third network element has model training capability, where the model training capability includes training capability of a positioning model. The method according to claim 23, wherein the third message further includes at least one of the following information: The eleventh information is used to indicate the user of the model corresponding to the model training capability; The twelfth information is used to indicate the usage area of the model corresponding to the model training capability; Thirteenth information, used to indicate the positioning mode of the model corresponding to the model training capability; The fourteenth information is used to indicate the reasoning method of the model corresponding to the model training capability; Fifteenth information, used to indicate the inference result type of the model corresponding to the model training capability; The sixteenth information is used to indicate the input data type of the model corresponding to the model training capability; The seventeenth information is used to indicate the task type of the model corresponding to the model training capability. A network element search method, comprising: The first device sends a sixth message to the second network element, where the sixth message is used to request to obtain a target model, where the target model includes a positioning model. The method according to claim 25, wherein the method further comprises: The first device receives a seventh message from the second network element, where the seventh message includes relevant information of the target model. The method according to claim 26, wherein the relevant information of the target model includes at least one of the following: Address information of the target model; A model file corresponding to the target model; identification information of the target model; The relevant information of the network elements of the target model is stored. A network element registration method, comprising: The first network element receives a third message from a third network element, where the third message is used to request registration of relevant information of the third network element, and the third message includes tenth information, where the tenth information is used to indicate that the third network element has model training capability, and the model training capability includes training capability of a positioning model. The method according to claim 28, wherein the third message further includes at least one of the following information: The eleventh information is used to indicate the user of the model corresponding to the model training capability; The twelfth information is used to indicate the usage area of the model corresponding to the model training capability; Thirteenth information, used to indicate the positioning mode of the model corresponding to the model training capability; The fourteenth information is used to indicate the reasoning method of the model corresponding to the model training capability; Fifteenth information, used to indicate the inference result type of the model corresponding to the model training capability; The sixteenth information is used to indicate the input data type of the model corresponding to the model training capability; The seventeenth information is used to indicate the task type of the model corresponding to the model training capability. A network element registration method, the method further comprising: The third network element sends a third message to the first network element, where the third message is used to request registration of relevant information of the third network element. The third message includes tenth information, where the tenth information is used to indicate that the third network element has model training capability, and the model training capability includes training capability of a positioning model. The method according to claim 30, wherein the third message further includes at least one of the following information: The eleventh information is used to indicate the user of the model corresponding to the model training capability; The twelfth information is used to indicate the usage area of the model corresponding to the model training capability; Thirteenth information, used to indicate the positioning mode of the model corresponding to the model training capability; The fourteenth information is used to indicate the reasoning method of the model corresponding to the model training capability; Fifteenth information, used to indicate the inference result type of the model corresponding to the model training capability; The sixteenth information is used to indicate the input data type of the model corresponding to the model training capability; The seventeenth information is used to indicate the task type of the model corresponding to the model training capability. A network element search device, applied to a first network element, comprising: A first receiving module, configured to receive a first message from a second network element, wherein the first message is used to request to find a network element having a model training capability, wherein the model training capability includes a positioning model training capability; A sending module is used to send a second message to the second network element, where the second message is used to feed back the network element search result. The device according to claim 32, further comprising: A processing module is used to determine a target network element according to the first message, wherein information of the target network element matches information in the first message. The apparatus according to claim 33, wherein the processing module is specifically used for at least one of the following: In a case where the first message includes first information, and the first information is used to indicate that the network element requested to be searched needs to have the model training capability, determining the target network element according to the first information, wherein the target network element is a network element having the model training capability; In a case where the first message includes second information, and the second information is used to indicate a user object of the model trained by the network element requested to be searched, determining the target network element according to the second information, wherein the user object of the model trained by the target network element matches the second information; In a case where the first message includes third information, the third information is used to indicate a usage area of a model trained by the network element requested to be searched, determining the target network element according to the third information, wherein the usage area of the model trained by the target network element matches the third information; In a case where the first message includes fourth information, and the fourth information is used to indicate a positioning mode of a model trained by the network element requested to be searched, determining the target network element according to the fourth information, wherein the positioning mode of the model trained by the target network element matches the fourth information; In a case where the first message includes fifth information, and the fifth information is used to indicate the reasoning mode of the model trained by the network element requested to be searched, determining the target network element according to the fifth information, wherein the model reasoning mode of the model trained by the target network element matches the fifth information; In a case where the first message includes sixth information, and the sixth information is used to indicate a type of inference result of a model trained by the network element requested to be searched, determining the target network element according to the sixth information, wherein the type of inference result of the model trained by the target network element matches the sixth information; In a case where the first message includes seventh information, and the seventh information is used to indicate an input data type of a model trained by the network element requested to be searched, determining the target network element according to the seventh information, wherein the input data type of the model trained by the target network element matches the seventh information; In a case where the first message includes eighth information, and the eighth information is used to indicate a task type of a model trained by the network element requested to be searched, the target network element is determined based on the eighth information, wherein the task type of the model trained by the target network element matches the eighth information. The device according to claim 33 or 34, further comprising: The second receiving module is used to receive a third message from the target network element, where the third message is used to request to register relevant information of the target network element. A network element search device, applied to a second network element, comprising: A first sending module, configured to send a first message to a first network element, wherein the first message is used to request to find a network element having a model training capability, wherein the model training capability includes a positioning model training capability; The first receiving module is used to receive a second message from the first network element, where the second message is used to feed back a network element search result. The apparatus according to claim 36, wherein the second message includes information of a target network element; The device also includes: The second sending module is used to send a fourth message to the target network element, where the fourth message is used to request to obtain a target model, where the target model includes a positioning model. The apparatus according to claim 37, further comprising: The second receiving module is used to receive a fifth message from the target network element, where the fifth message includes relevant information of the target model. The device according to any one of claims 36 to 38, further comprising: The third receiving module is used to receive a sixth message from the first device, where the sixth message is used to request to obtain a target model, where the target model includes a positioning model. The apparatus according to claim 39, further comprising: The third sending module is used to send a seventh message to the first device, where the seventh message includes relevant information of the target model. The device according to any one of claims 36 to 38, further comprising: The fourth receiving module is used to receive an eighth message from the second device, where the eighth message is used to request to obtain positioning information. The apparatus according to claim 41, further comprising: The processing module is used to determine the positioning information based on the target model and the positioning related data when the target model is acquired. A network element search device, applied to a third network element, comprising: The receiving module is used to receive a fourth message from the second network element, where the fourth message is used to request to obtain a target model, where the target model includes a positioning model. The apparatus according to claim 43, further comprising: The first sending module is used to send a fifth message to the second network element based on the fourth message, and the fifth message includes relevant information of the target model. The target model is a model pre-trained by the third network element, or a model trained by the third network element based on the fourth message. The device according to claim 43 or 44, further comprising: The second sending module is used to send a third message to the first network element, where the third message is used to request registration of relevant information of the third network element, and the third message includes tenth information, where the tenth information is used to indicate that the third network element has model training capability, and the model training capability includes the training capability of the positioning model. A network element search device, applied to a first device, comprising: The sending module is used to send a sixth message to the second network element, where the sixth message is used to request to obtain a target model, where the target model includes a positioning model. The apparatus according to claim 46, further comprising: A receiving module is used to receive a seventh message from the second network element, where the seventh message includes relevant information of the target model. A network element registration device, applied to a first network element, comprising: A receiving module is used to receive a third message from a third network element, wherein the third message is used to request registration of relevant information of the third network element, and the third message includes tenth information, wherein the tenth information is used to indicate that the third network element has model training capability, and the model training capability includes the training capability of the positioning model. A network element registration device, applied to a third network element, comprising: A sending module is used to send a third message to the first network element, wherein the third message is used to request registration of relevant information of the third network element, and the third message includes tenth information, wherein the tenth information is used to indicate that the third network element has model training capability, and the model training capability includes the training capability of the positioning model. A communication device comprises a processor and a memory, wherein the memory stores a program or instruction that can be run on the processor, and when the program or instruction is executed by the processor, it implements the steps of the network element search method as described in any one of claims 1 to 7, or implements the steps of the network element search method as described in any one of claims 8 to 18, or implements the steps of the network element search method as described in any one of claims 19 to 24, or implements the steps of the network element search method as described in any one of claims 25 to 27, or implements the steps of the network element registration method as described in claim 28 or 29, or implements the steps of the network element registration method as described in claim 30 or 31. A readable storage medium storing a program or instruction, wherein the program or instruction, when executed by a processor, implements the steps of the network element search method as described in any one of claims 1 to 7, or implements the steps of the network element search method as described in any one of claims 8 to 18, or implements the steps of the network element search method as described in any one of claims 19 to 24, or implements the steps of the network element search method as described in any one of claims 25 to 27, or implements the steps of the network element registration method as described in claim 28 or 29, or implements the steps of the network element registration method as described in claim 30 or 31.