[go: up one dir, main page]

WO2025108195A1 - 模型确定方法、装置及通信设备 - Google Patents

模型确定方法、装置及通信设备 Download PDF

Info

Publication number
WO2025108195A1
WO2025108195A1 PCT/CN2024/132393 CN2024132393W WO2025108195A1 WO 2025108195 A1 WO2025108195 A1 WO 2025108195A1 CN 2024132393 W CN2024132393 W CN 2024132393W WO 2025108195 A1 WO2025108195 A1 WO 2025108195A1
Authority
WO
WIPO (PCT)
Prior art keywords
information
model
terminal device
reference signal
scene information
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
PCT/CN2024/132393
Other languages
English (en)
French (fr)
Inventor
贾承璐
邬华明
杨昂
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Vivo Mobile Communication Co Ltd
Original Assignee
Vivo Mobile Communication Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Vivo Mobile Communication Co Ltd filed Critical Vivo Mobile Communication Co Ltd
Publication of WO2025108195A1 publication Critical patent/WO2025108195A1/zh
Pending legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/14—Network analysis or design
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/14—Network analysis or design
    • H04L41/145—Network analysis or design involving simulating, designing, planning or modelling of a network
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/16—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks using machine learning or artificial intelligence
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W24/00—Supervisory, monitoring or testing arrangements
    • H04W24/06—Testing, supervising or monitoring using simulated traffic

Definitions

  • the present application belongs to the field of communication technology, and specifically relates to a model determination method, device and communication equipment.
  • model supervision is an important part of the lifecycle management of machine learning models.
  • the existing model supervision methods based on model input/output only indicate whether the current model is valid, but do not indicate which machine learning model should be applied to the environment in which the current terminal device is located.
  • some data information corresponding to the terminal device such as location information and communication data, will change, and the data characteristics will also change accordingly. If the environment in which the current terminal device is located does not match the machine learning model running in the terminal device or the network-side device, it will affect the efficiency and accuracy of data processing, and thus affect the communication quality of the terminal device.
  • the embodiments of the present application provide a model determination method, apparatus, and communication device, which can solve the problem in the related art that it is impossible to indicate which machine learning model should be applied to the environment in which the current terminal device is located.
  • a model determination method comprising:
  • the first device determines a first model based on the first information
  • the first device activates the first model
  • the first information includes any one of the following:
  • Scene information of the terminal device and a mapping relationship between the machine learning model and the scene information;
  • the first device is the terminal device or a network side device;
  • Model information of the machine learning model associated with the scene information in which the terminal device is located is located.
  • a data transmission method comprising:
  • the second device sends sixth information to the first device, where the sixth information includes at least one of the following:
  • third information where the third information is used to indicate an association relationship between the position coordinates and the scene information
  • a first indication where the first indication is used to indicate scene information of a terminal device
  • the second indication is used to indicate a mapping relationship between the machine learning model and the scene information
  • a third indication is used to indicate a machine learning model associated with the scene information in which the terminal device is located.
  • a model determination device which is applied to a first device, and the device includes:
  • a model determination module configured to determine a first model based on the first information
  • a model activation module used for activating the first model
  • the first information includes any one of the following:
  • Scene information of the terminal device and a mapping relationship between the machine learning model and the scene information;
  • the first device is the terminal device or a network side device;
  • Model information of the machine learning model associated with the scene information in which the terminal device is located is located.
  • a data transmission apparatus which is applied to a second device, and the apparatus includes:
  • the information sending module is used to send sixth information to the first device, where the sixth information includes at least one of the following:
  • third information where the third information is used to indicate an association relationship between the position coordinates and the scene information
  • a first indication where the first indication is used to indicate scene information of a terminal device
  • the second indication is used to indicate a mapping relationship between the machine learning model and the scene information
  • a third indication is used to indicate a machine learning model associated with the scene information in which the terminal device is located.
  • a communication device which includes 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, the steps of the model determination method as described in the first aspect are implemented, or the steps of the data transmission method as described in the second aspect are implemented.
  • a model determination system comprising: a first device and a second device, wherein the first device can be used to execute the steps of the model determination method as described in the first aspect above, and the second device can be used to execute the steps of the data transmission method as described in the second aspect above.
  • a readable storage medium on which a program or instruction is stored.
  • the program or instruction is executed by a processor, the steps of the model determination method as described in the first aspect are implemented, or the steps of the data transmission method as described in the second aspect are implemented.
  • a chip 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 instruction to implement the method described in the first aspect, or to implement the method described in the second aspect.
  • a computer program/program product is provided, wherein the computer program/program product is stored in a storage medium and is executed by at least one processor to implement the steps of the method described in the first aspect or the second aspect.
  • a model determination apparatus/device which includes the apparatus/device (configured to) be used to execute steps to implement the model determination method as described in the first aspect.
  • a data transmission apparatus/device is provided, wherein the apparatus/device (configured to) is used to execute steps to implement the data transmission method as described in the first aspect.
  • the embodiment of the present application associates the machine learning model with the scene.
  • the first device can determine which model should be applied in the current environment based on the scene information of the terminal device and the mapping relationship between the machine learning model and the scene information; or, the first device can directly determine the machine learning model associated with the scene information of the current terminal device based on the model information in the first information, and activate the model.
  • the first device can determine which model should be applied based on the first information, thereby ensuring that during the movement of the terminal device, the machine learning model running in the terminal device or the network-side device can always adapt to the scene of the terminal device, thereby ensuring the accuracy and efficiency of data processing.
  • FIG1 is a block diagram of a wireless communication system to which an embodiment of the present application can be applied;
  • FIG2 is a flow chart of a model determination method in an embodiment of the present application.
  • FIG3 is a schematic diagram of the structure of a neural network model in an embodiment of the present application.
  • FIG4 is a schematic diagram of a neuron in an embodiment of the present application.
  • FIG5 is a schematic diagram of a flow chart of a model determination method in an embodiment of the present application.
  • FIG6 is a flow chart of another model determination method in an embodiment of the present application.
  • FIG7 is a flow chart of a model determination method in an embodiment of the present application.
  • FIG8 is a flow chart of another model determination method in an embodiment of the present application.
  • FIG9 is a flow chart of a data transmission method in an embodiment of the present application.
  • FIG10 is a structural block diagram of a model determination device in an embodiment of the present application.
  • FIG11 is a structural block diagram of a data transmission device in an embodiment of the present application.
  • FIG12 is a structural block diagram of a communication device in an embodiment of the present application.
  • FIG13 is a block diagram of a terminal device in an embodiment of the present application.
  • FIG14 is a structural block diagram of a network side device in an embodiment of the present application.
  • FIG15 is a structural block diagram of another network-side device in an embodiment of the present application.
  • first, second, etc. in the specification and claims 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 under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the objects distinguished by “first” and “second” are generally of the same type, and the number of objects is not limited.
  • the first object can be one or more.
  • “and/or” in the specification and claims represents at least one of the connected objects, and the character “/" generally represents that the objects associated with each other are in an "or” relationship.
  • LTE Long Term Evolution
  • LTE-A Long Term Evolution
  • CDMA Code Division Multiple Access
  • TDMA Time Division Multiple Access
  • FDMA Frequency Division Multiple Access
  • OFDMA Orthogonal Frequency Division Multiple Access
  • SC-FDMA Single-carrier Frequency Division Multiple Access
  • NR new radio
  • FIG1 shows a block diagram of a wireless communication system applicable to an embodiment of the present application.
  • the wireless communication system includes a terminal device 11 and a network side device 12.
  • the terminal device 11 may be a mobile phone, a tablet computer (Tablet Personal Computer), a laptop computer (Laptop Computer) or a notebook computer, a personal digital assistant (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)/ Virtual reality (VR) equipment, robots, wearable devices (Wearable Device), vehicle-mounted equipment (VUE), pedestrian terminal (PUE), smart home (home appliances with wireless communication functions, such as refrigerators, televisions, washing machines or furniture, etc.), game consoles, personal computers (personal computers, PCs), teller machines or self-service machines and other terminal side devices, wearable devices include: smart watches, smart bracelets, smart headphones, smart glasses, smart jewelry (
  • the network side device 12 may include access network equipment or core network equipment, wherein the access network device 12 may also be called wireless access network equipment, wireless access network (Radio Access Network, RAN), wireless access network function or wireless access network unit.
  • the access network device 12 may include a base station, a WLAN access point or a WiFi node, etc.
  • the base station may be called a node B, an evolved node B (eNB), an access point, a base transceiver station (Base Transceiver Station, BTS), a radio base station, a radio transceiver, a basic service set (Basic Service Set, BSS), an extended service set (Extended Service Set, ESS), a home B node, a home evolved B node, a transmitting and receiving point (Transmitting Receiving Point, TRP) or some other suitable term in the field.
  • the base station is not limited to specific technical vocabulary. 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 (Mobility Management Entity, MME), access mobility management function (Access and Mobility Management Function, AMF), session management function (Session Management Function, SMF), user plane function (User Plane Function, UPF), policy control function (Policy Control Function, PCF), policy and charging rules function unit (Policy and Charging Rules Function, PCRF), edge application service discovery function (Edge Application Server Discovery ...
  • MME mobility management entity
  • AMF Access and Mobility Management Function
  • SMF Session Management Function
  • SMF Session Management Function
  • UPF User Plane Function
  • Policy Control Function Policy Control Function
  • PCRF Policy and Charging Rules Function
  • edge application service discovery function Edge Application Server Discovery ...
  • the embodiment of the present application provides a model determination method.
  • FIG. 2 a flow chart of a model determination method provided by the embodiment of the present application is shown. The method is applied to a first device, as shown in FIG. 2 , and the method may specifically include:
  • Step 201 A first device determines a first model based on first information.
  • Step 202 The first device activates the first model.
  • the first information includes any one of the following:
  • Scene information of the terminal device and a mapping relationship between the machine learning model and the scene information;
  • the first device is the terminal device or a network side device;
  • Model information of the machine learning model associated with the scene information in which the terminal device is located is located.
  • the first device may be a terminal device or a network side device.
  • the terminal device may include a conventional terminal device and/or a positioning reference unit.
  • the conventional terminal device may be the terminal device 11 in Figure 1.
  • the positioning reference unit Positioning Reference Unit, PRU
  • PRU Positioning Reference Unit
  • the PRU can send a positioning reference signal (Positioning reference signal, PRS) to the transmission and receiving point (Transmission and Receiving Point, TRP), so that the TRP can measure and report the uplink (Up-Link, UL) positioning measurement values of the PRU from a known position, such as RTOA, UL-AoA, gNB Rx-Tx time difference, etc.
  • PRS Positioning reference signal
  • TRP Transmission and Receiving Point
  • the location server may compare the PRU measurements with expected measurements at known PRU locations to determine correction terms for other nearby target devices, and then correct the DL and/or UL location measurements of the other target devices based on the correction terms.
  • the network side device can be the access network device in Figure 1, such as a base station or a newly defined artificial intelligence processing node on the access network side, or it can be the core network device in Figure 1, such as a network data analysis function (Network Data Analytics Function, NWDAF), a positioning management function (Location Management Function, LMF), or a newly defined processing node on the core network side, or it can be a combination of the above multiple nodes.
  • NWDAF Network Data Analytics Function
  • LMF Location Management Function
  • a newly defined processing node on the core network side or it can be a combination of the above multiple nodes.
  • the machine learning model can be trained by a network-side device, and the network-side device sends the trained machine learning model to the terminal device through model transfer/delivery.
  • the network-side device records the association between the model identifier of each machine learning model and the scenario information.
  • the machine learning model is trained by a third-party server, which sends the trained machine learning model to the terminal device and/or network side device, and sends the association between the model identifier of the machine learning model and the scene information to the terminal device and/or network side device.
  • the machine learning model in the embodiment of the present application can be an artificial intelligence (AI) model, such as any one of a fully connected neural network, a convolutional neural network, a decision tree, a support vector machine, and a Bayesian classifier.
  • AI artificial intelligence
  • the neural network may include one or more input layers, one or more hidden layers, and an output layer.
  • the data to be processed [X1, X2...Xn] are respectively input into the neural network from the corresponding input layer, and the output result Y is obtained after being processed by the input layer, the hidden layer, and the output layer.
  • the neural network is composed of neurons, and a schematic diagram of the neuron is shown in Figure 4.
  • a1, a2,...aK represent inputs
  • w represents weights (i.e., multiplicative coefficients)
  • b represents biases (i.e., additive coefficients)
  • ⁇ (.) represents activation functions.
  • Common activation functions include Sigmoid (mapping variables between 0 and 1), tanh (translation and contraction of Sigmoid), linear rectification function/rectified linear unit (Rectified Linear Unit, ReLU), etc.
  • the model training process is introduced as follows:
  • the parameters of the neural network can be optimized by the gradient optimization algorithm.
  • the gradient optimization algorithm is a type of algorithm that minimizes or maximizes the objective function (sometimes also called the loss function), and the objective function is often a mathematical combination of model parameters and data. For example, given the data X and its corresponding label Y, a neural network model f(.) can be constructed, then the predicted output f(x) can be obtained based on the input x, and the difference between the predicted value and the true value (fx-Y) can be calculated, which is the loss function.
  • the optimization goal of the gradient optimization algorithm is to find the appropriate w (i.e. weight) and b (i.e. bias) to minimize the value of the above loss function, and the smaller the loss value, the closer the model is to the actual situation.
  • the common optimization algorithms are basically based on the error back propagation (BP) algorithm.
  • BP error back propagation
  • the basic idea of the BP algorithm is that the learning process consists of two processes: the forward propagation of the signal and the back propagation of the error.
  • the input sample is transmitted from the input layer, processed by each hidden layer layer by layer, and then transmitted to the output layer. If the actual output of the output layer does not match the expected output, it will enter the back propagation stage of the error.
  • Error back propagation is to propagate the output error layer by layer through the hidden layer to the input layer in some form, and distribute the error to all units in each layer, so as to obtain the error signal of each layer unit, and this error signal is used as the basis for correcting the weights of each unit.
  • This process of adjusting the weights of each layer of the signal forward propagation and error back propagation is repeated.
  • the process of continuous adjustment of weights is the learning and training process of the network. This process continues until the error of the network output is reduced to an acceptable level, or until the pre-set number of learning times is reached.
  • these optimization algorithms calculate the derivative/partial derivative of the current neuron based on the error/loss obtained by the loss function, add the influence of the learning rate, the previous gradient/derivative/partial derivative, etc., get the gradient, and pass the gradient to the previous layer.
  • the machine learning model may also be referred to as an AI unit, an AI model, an ML (machine learning) model, an ML unit, an AI structure, an AI function, an AI characteristic, a neural network, a neural network function, a neural network function, etc., or the AI unit/AI model may also refer to a processing unit capable of implementing specific algorithms, formulas, processing procedures, capabilities, etc.
  • the AI unit/AI model may be a processing method, algorithm, function, module or unit for a specific data set, or the AI unit/AI model may be a processing method, algorithm, function, module or unit running on AI/ML related hardware such as a GPU, NPU, TPU, ASIC, etc., and the present invention does not specifically limit this.
  • the specific data set includes the input and/or output of the AI unit/AI model.
  • the identifier of the AI unit/AI model may be an AI model identifier, an AI structure identifier, an AI algorithm identifier, or an identifier of a specific data set associated with the AI unit/AI model, or an identifier of a specific scenario, environment, channel feature, or device related to the AI/ML, or an identifier of a function, feature, capability, or module related to the AI/ML, which is not specifically limited in the embodiments of the present application.
  • the first device may determine the first model based on the first information. For example, the first device determines the machine learning model associated with the scene information of the terminal device according to the scene information of the terminal device and the mapping relationship between the machine learning model and the scene information, and determines the model as the first model. Alternatively, in the case where the first information includes model information of the machine learning model associated with the scene information of the terminal device, the first device may directly determine the machine learning model indicated by the model information as the first model.
  • the first device can activate the first model, thereby using the first model to process the data generated by the terminal device in the current scenario.
  • the machine learning model running in the first device can be used to process the data corresponding to the terminal device, such as determining the location information of the terminal device, analyzing the communication quality of the cell where the terminal device is located, and performing access control on the terminal device, etc.
  • the machine learning model running in the first device may not meet the data processing requirements of the scene where the terminal device is currently located.
  • the terminal device can determine the first model that matches the scene where the terminal device is currently located based on the first information and activate it.
  • the scene information of the terminal device may include, but is not limited to, the scene ID, scene information, scene category, area ID, area information, area category, data set ID, data set information, data set category, etc. of the scene in which the terminal device is located.
  • the granularity of the scene or area or data set may be a cell.
  • the scene ID, area ID, and data set ID may be associated with the physical cell identifier (PCI) of one or more cells, so as to determine the scene ID, area ID, and data set ID corresponding to the first device according to the cell in which the first device is located.
  • the granularity of the scene or area or data set may also be smaller than the cell.
  • a scene may be a factory building, a building, or even a floor in a building in a cell.
  • a machine learning model can correspond to one or more scenarios, regions, or datasets.
  • the first device can determine that the currently running machine learning model can no longer meet the computing requirements of the current scene. In other words, in the scene currently located by the first device, the machine learning model currently running in the first device is an invalid model. In this case, the first device can switch the running machine learning model to the first model.
  • the embodiment of the present application associates the machine learning model with the scene.
  • the first device can determine which model should be applied in the current environment based on the scene information of the terminal device and the mapping relationship between the machine learning model and the scene information; or, the first device can directly determine the machine learning model associated with the scene information of the current terminal device based on the model information in the first information, and activate the model.
  • the first device can determine which model should be applied based on the first information, thereby ensuring that during the movement of the terminal device, the machine learning model running in the terminal device or the network-side device can always adapt to the scene of the terminal device, thereby ensuring the accuracy and efficiency of data processing.
  • the method further includes:
  • the first device obtains scene information where the terminal device is located
  • the first device obtains a mapping relationship between a machine learning model and scene information.
  • the mapping relationship between the machine learning model and the scene information can be generated by a network-side device or a third-party server that trains the model.
  • the mapping relationship between the machine learning model and the scene information can be sent to the first device by a network-side device or a third-party server that trains the model;
  • the network-side device can locally generate a mapping relationship between the machine learning model and the scene information based on the model training process;
  • the network-side device can read the mapping relationship between the machine learning model and the scene information from the third-party server.
  • the first device may also obtain the scene information of the terminal device in a variety of ways.
  • the first device obtains the scene information in which the terminal device is located, including:
  • Step S11 The first device acquires second information, where the second information is used to indicate communication information of the terminal device, and the second information is associated with scene information where the terminal device is located;
  • Step S12 The first device determines the scene information of the terminal device according to the second information.
  • the second information is associated with the scene in which the first device is located, for example, the second information is associated with the scene ID, area ID, data set ID, scene category, area category, data set category and other information in which the first device is currently located.
  • the second information may include the cell ID, reference signal ID, transmission and reception point ID, area ID, tracking area (Tracking Area) ID and the like corresponding to the first device.
  • the first device can determine the scene information of the terminal device based on the second information.
  • the first device acquiring the second information includes:
  • the first device measures the reference signal and determines second information based on the measurement result.
  • a schematic flow chart of a model determination method provided by an embodiment of the present application is shown.
  • the first device if the first device is a terminal device, the first device can determine the second information by measuring a reference signal.
  • the first device acquires the second information, including:
  • the first device receives second information sent by the terminal device.
  • the second information can be generated by the terminal device according to the measurement result of the reference signal and then sent to the network side device.
  • the network side device itself does not need to perform any measurement operation on the reference signal.
  • the first device determines the scene information of the terminal device according to the second information, including:
  • the first device acquires an association relationship between the communication information and the scene information
  • the first device determines the scene information of the terminal device according to the second information and the association between the communicated information and the scene information.
  • the association between the communication information and the scene may be sent by the second device to the first device, or may be specified by the protocol.
  • the first device is a network side device, such as an access network device
  • the second device may be a core network device
  • the first device is a terminal device
  • the second device may be a network side device or a high-level terminal device.
  • the first device After the first device acquires the second information, it can determine the scene information of the terminal device based on the communication information indicated by the second information and the association between the communication information and the scene information.
  • the first device is a network side device
  • the network side device after the network side device receives the second information reported by the terminal device, it can determine the scene information of the terminal device based on the communication information indicated by the second information, and the association between the communication information and the scene information, and then further combine the association between the machine learning model and the scene information to determine the first model and activate it.
  • the first device is a terminal device
  • the terminal device can determine the scene information of the terminal device based on the communication information indicated by the second information and the association between the communication information and the scene information, and then further combine the association between the machine learning model and the scene information to determine the first model and activate it.
  • the terminal device can also send the second information to the network side device, and the network side device determines the scene information of the terminal device based on the second information and indicates it to the terminal device.
  • the first device determines the scene information of the terminal device according to the second information, including:
  • Step S21 The first device sends the second information to a network side device
  • Step S22 The first device receives a first indication sent by the network side device; the first indication is used to indicate scene information of the first device.
  • the first device is a terminal device
  • the terminal device can determine the second information by measuring the reference signal and send the second information to the network side device.
  • the network side device determines the scene information in which the terminal device is currently located based on the second information and the association between the communication information and the scene information, and indicates the scene information to the terminal device through a first indication.
  • the terminal device determines and activates the first model based on the scene information indicated by the first indication and the association between the machine learning model and the scene information.
  • the network side device determines the scene information in which the terminal device is currently located based on the communication information indicated by the second information and the association between the communication information and the scene information, and further determines the machine learning model associated with the scene information in which the terminal device is currently located based on the association between the machine learning model and the scene information, that is, the first model, and indicates the first model to the terminal device through a third indication.
  • the first device obtains the scene information of the terminal device, including:
  • the first device receives a first indication and a second indication sent by a second device, wherein the first indication is used to indicate scene information of the terminal device; and the second indication is used to indicate a mapping relationship between a machine learning model and the scene information.
  • the scene information of the terminal device and the mapping relationship between the machine learning model and the scene information can also be indicated to the first device by the second device.
  • the second device in the embodiment of the present application can be a network side device or a high-level terminal device.
  • the first device is a network side device, such as an access network device
  • the second device can be a core network device
  • the first device is a terminal device
  • the second device can be a network side device or a high-level terminal device.
  • the first indication and the second indication may be carried in the same signaling, and the second device simultaneously sends the first indication and the second indication to the first device through a certain signaling, and the first device determines and activates the first model based on the received first indication and the second indication.
  • the second device may send the first indication to the first device through one signaling, and send the second indication to the first device through other signaling.
  • the signaling carrying the first indication and/or the second indication may include but is not limited to: Radio Resource Control Protocol (RRC) signaling, Radio Link Layer Control Protocol (RLA) signaling, Media Access Control (MAC) signaling, LTE Positioning Protocol (LPP) signaling, NR Positioning Protocol A (NRPPa) signaling, downlink control information (DCI), etc.
  • RRC Radio Resource Control Protocol
  • RLA Radio Link Layer Control Protocol
  • MAC Media Access Control
  • LPP LTE Positioning Protocol
  • NRPPa NR Positioning Protocol A
  • DCI downlink control information
  • the first indication is sent by the second device to the first device
  • the machine learning model is trained by a third-party server
  • the third-party server sends the second indication to the first device.
  • the method further includes:
  • the first device receives a third indication sent by the second device, where the third indication is used to indicate a machine learning model associated with scene information in which the terminal device is located.
  • the third indication may be sent by the second device to the first device.
  • the first device may directly determine the machine learning model indicated by the third indication as the first model to be activated.
  • the second device can determine the scene information of the terminal device based on the location information of the terminal device, and then determine the machine learning model that matches the scene currently located by the terminal device based on the association between the scene information and the machine learning model, generate a third indication and send it to the first device.
  • the first device can send the scene information of the terminal device to the second device, and the second device determines the machine learning model associated with the scene currently located by the terminal device based on the scene information and the association between the machine learning model and the scene information, and generates a third indication and sends it to the first device.
  • the first device measures the reference signal, and determines the second information based on the measurement result, including:
  • Step S31 The first device measures a first reference signal when receiving a fourth indication; the fourth indication is used to instruct the first device to measure at least one reference signal;
  • Step S32 The first device determines the second information based on a first measurement result of the first reference signal.
  • the first device is a terminal device.
  • the terminal device may measure the first reference signal when receiving the fourth indication, and determine the second information based on a first measurement result of the first reference signal.
  • the fourth indication may be sent by the second device to the first device, or may be sent by other devices to the first device. In another possible application scenario, the fourth indication may also be automatically triggered by a higher layer of the first device when certain measurement conditions are met.
  • the first reference signal may include but is not limited to: positioning reference signal, downlink channel sounding reference signal (Channel-State-Information Reference Signal, CSI-RS), uplink sounding signal (Sounding Reference Signal, SRS), synchronization signal block (Synchronization Signal Block, SSB), time-frequency tracking reference signal (Tracking Reference Signal, TRS), etc.
  • the first device measures the reference signal, and determines the second information based on the measurement result, including:
  • Step S41 The first device receives a second reference signal sent by a reference point
  • Step S42 The first device measures the second reference signal, and determines second information based on a second measurement result of the second reference signal.
  • the first device is a terminal device
  • the terminal device may also measure a second reference signal from a receiving reference point, and determine second information based on a second measurement result of the second reference signal.
  • the second information may include a cell ID, a reference signal ID, a receiving reference point ID, a scene ID, an area ID, a tracking area ID, etc. corresponding to the terminal device.
  • the second information includes at least one of the following:
  • the first parameter being used to indicate a communication resource of the terminal device
  • the second communication information, the fifth parameter is used to indicate the communication area where the terminal device is located.
  • the first communication information includes at least one of the following:
  • the reference signal information includes at least one of the following:
  • the second parameter is used to indicate a reference signal resource
  • the second parameter, the third parameter is used to indicate reference signal measurement information
  • the third parameter, the fourth parameter is used to indicate reference signal reporting information.
  • the first parameter may be a reference signal resource ID, a reference signal resource set ID, etc.
  • the second parameter may be a reference signal measurement ID, a reference signal measurement configuration ID, etc.
  • the third parameter may be a reference signal reporting ID, a reference signal reporting configuration ID.
  • the communication indicator information includes at least one of the following:
  • the fourth parameter can be a statistical value or representation of signal quality, such as signal-to-noise ratio (SNR), signal to interference plus noise ratio (SINR), RSRP, reference signal received quality (RSRQ), signal power, noise power, interference power, etc.; or such as L1-RSRP, L1-SINR, L1-RSRP, L1-RSRQ, L3-RSRP, L3-SINR, L3-RSRP, L3-RSRQ, etc.
  • SNR signal-to-noise ratio
  • SINR signal-to-noise ratio
  • SINR signal to interference plus noise ratio
  • RSRP reference signal received quality
  • the beam information may include information such as a beam index and a beam direction.
  • the first device measures the reference signal, and determines the second information based on the measurement result, including:
  • Step S51 The first device measures a reference signal to obtain a measurement result
  • Step S52 The first device determines a target reference signal resource according to the measurement result, and determines second information according to resource information of the target reference signal resource.
  • the target reference signal resource includes at least one of the following:
  • N N first target reference signal resources among the reference signal resources configured for each transmission/reception point; the reference signal received power of the N first target reference signal resources is greater than the reference signal received power of other reference signal resources of the same transmission/reception point; N is a positive integer;
  • Reference signal resources configured at each transmitting and receiving point.
  • the first device is a terminal device, which can screen out N first target reference signal resources whose reference signal receiving power is greater than other reference signal resources of the same sending and receiving point from the reference signal resources configured for each sending and receiving point, and determine the second information based on resource information of the first target reference signal resources, such as reference signal ID, reference signal measurement ID, reference signal reporting ID and other information.
  • the terminal device may also filter out a second target reference signal resource whose reference signal received power is greater than or equal to a preset threshold from each reference signal resource configured by each transmission and reception point, thereby determining the second information according to resource information of the second target reference signal resource, such as reference signal ID, reference signal measurement ID, reference signal reporting ID, etc.
  • the preset threshold may be indicated by a network side device or may be specified by a protocol, which is not specifically limited in the embodiments of the present application.
  • the terminal device determines the second information based on the reference signal resources configured for each transmitting and receiving point, without screening the reference signal resources.
  • the terminal device can screen the target reference signal resources based on any one of items A1 to A3, and determine the second information based on the screened target reference signal resources, and then determine the scene information of the terminal device.
  • the determined scene information is adapted to the reference signal resources configured at the sending and receiving points, and meets the specific reference signal receiving power, thereby ensuring the reliability of the determined scene information, which is conducive to improving the reliability of the first model finally determined, thereby ensuring that during the movement of the terminal device, the machine learning model running in the terminal device can always adapt to the reference signal resources configured at the sending and receiving points.
  • the resource information includes at least one of the following:
  • the terminal device can determine the second information based on resource information such as the reference signal receiving power, reference signal resource representation, beam identification, beam direction, etc. of the target reference signal resource (including at least one item of A1 to A3).
  • resource information such as the reference signal receiving power, reference signal resource representation, beam identification, beam direction, etc. of the target reference signal resource (including at least one item of A1 to A3).
  • the first device obtains the scene information of the terminal device, including:
  • Step S61 The first device obtains location information of the terminal device, where the location information is associated with scene information where the terminal device is located;
  • Step S62 The first device determines the scene information of the terminal device according to the location information and the association between the location coordinates and the scene information.
  • the first device in addition to determining the scene information of the terminal device based on the second information, can also determine the scene information of the terminal device based on the location information of the terminal device and the association between the location coordinates and the scene information.
  • the location information of the terminal device can be determined by the terminal device based on an AI model or other positioning methods, such as satellite positioning, GPS positioning system, Beidou positioning system, Bluetooth positioning, radar positioning, and other positioning methods based on mobile communication networks, such as positioning methods based on NR systems, LTE systems, etc.
  • an AI model or other positioning methods such as satellite positioning, GPS positioning system, Beidou positioning system, Bluetooth positioning, radar positioning, and other positioning methods based on mobile communication networks, such as positioning methods based on NR systems, LTE systems, etc.
  • the association relationship between the location coordinates and the scene information can be determined by a network side device, can be specified by a protocol, or can be sent by a second device to a first device.
  • the embodiments of the present application do not specifically limit this.
  • the second device can be a network side device or a high-level terminal device.
  • the first device is an access network device, such as a base station
  • the second device can be a core network device
  • the first device is a terminal device
  • the second device can be a network side device or a high-level terminal device.
  • the method further includes:
  • the first device receives third information sent by the second device, where the third information is used to indicate an association relationship between the location coordinates and the scene information.
  • the second device may also indicate the association relationship between the location coordinates and the scene information to the first device through the third information.
  • the first device After the first device receives the third information, it can determine the scene information of the terminal device based on the location information of the terminal device and the association relationship between the location coordinates and the scene information, and then determine the first model based on the scene information and the association relationship between the machine learning model and the scene information.
  • the first device sends the determined scene information, such as scene ID, area ID, data set ID, etc., to the second device, and the second device determines a machine learning model that matches the scene information reported by the first device and indicates it to the first device.
  • the determined scene information such as scene ID, area ID, data set ID, etc.
  • the first device obtains the location information of the terminal device, including:
  • the first device determines current location information based on positioning technology
  • the first device receives fourth information sent by the terminal device, where the fourth information is used to indicate location information of the terminal device.
  • the location information of the terminal device can be determined by the terminal device itself according to an AI model or other positioning methods, such as satellite positioning, GPS positioning system, Beidou positioning system, Bluetooth positioning, radar positioning, and other positioning methods based on mobile communication networks, such as positioning methods based on NR systems, LTE systems, etc.
  • AI model or other positioning methods such as satellite positioning, GPS positioning system, Beidou positioning system, Bluetooth positioning, radar positioning, and other positioning methods based on mobile communication networks, such as positioning methods based on NR systems, LTE systems, etc.
  • the scene information can be determined by combining the association between the location coordinates and the scene information.
  • the terminal device reports the location information to the network side device through the fourth information, and the network side device determines the scene information of the terminal device based on the location information of the terminal device and the association between the location coordinates and the scene, and indicates the determined scene information to the terminal device through the first indication.
  • the terminal device After the terminal device determines the scene information, it can further determine the first model in combination with the association between the machine learning model and the scene information.
  • the network-side device determines the scene information of the terminal device based on the location information reported by the terminal device, and further determines the machine learning model associated with the scene information of the terminal device in combination with the association between the machine learning model and the scene information, that is, the first model, and indicates the first model to the terminal device through a third indication.
  • FIG8 a flow chart of another model determination method provided by an embodiment of the present application is shown.
  • the location information of the terminal device can be reported to the first device by the terminal device through the fourth information.
  • the terminal device can simultaneously report the method for obtaining the location information and the reliability or confidence to the first device.
  • the network side device After receiving the location information reported by the terminal device, the network side device can determine the scene information of the terminal device based on the location information and the association between the location coordinates and the scene information. Further, the network side device can determine the first model associated with the scene information of the terminal device based on the association between the machine learning model and the scene information.
  • the first device activating the first model includes:
  • the first device deactivates the second model and activates the first model.
  • the first device can deactivate the second model and activate the first model.
  • the first model and the second model in the present application are not limited to a certain AI model.
  • the first model and the second model in the present application may include one or more AI models, or may be an AI function, and an AI function may be associated with one or more AI models.
  • deactivating the second model may be to simultaneously deactivate one or more AI models included in the second model, or to simultaneously deactivate one or more AI functions referred to by the second model.
  • activating the first model may be to simultaneously activate one or more AI models included in the first model, or to simultaneously activate one or more AI functions referred to by the first model.
  • the deactivation operation and the activation operation may be independent of each other.
  • the first model determined by the first device based on the first information includes the machine learning model currently running in the first device, then the machine learning model currently running in the first device is valid and no deactivation operation is required. In this case, the normal operation of the currently running machine learning model can be maintained, and then the AI models and/or AI functions included in the first model, except for the currently running machine learning model, can be activated.
  • the AI models and/or AI functions included in the first model only include the AI models and/or AI functions currently running in the first device, then there is no need to perform deactivation and activation operations.
  • the activation operation cannot be performed.
  • no AI model or AI function is currently running in the first device, then there is no need to perform deactivation.
  • the embodiment of the present application deactivates the second model and activates the first model when the currently running second model does not match the first model, thereby ensuring that the machine learning model running in the first device can always adapt to the scene in which the terminal device is located during the movement of the terminal device, thereby ensuring the accuracy and efficiency of data processing.
  • the method further includes:
  • the first device sends fifth information to the network side device.
  • the fifth information includes at least one of the following:
  • the activation time of the first model is the activation time of the first model.
  • the model identifier of the deactivated second model, the model identifier of the first model to be activated, and at least one of the activation time of the first model can be sent to the network side device through the fifth information.
  • the activation time of the first model is used to indicate the time of model switching, for example, the model switching is performed after M time units, including deactivating the second model and activating the first model.
  • the embodiment of the present application provides a model determination method, which associates the machine learning model with the scene.
  • the first device can determine which model should be applied in the current environment based on the scene information of the terminal device and the mapping relationship between the machine learning model and the scene information; or, the first device can directly determine the machine learning model associated with the scene information of the current terminal device based on the model information in the first information, and activate the model.
  • the first device can determine which model should be applied based on the first information, thereby ensuring that during the movement of the terminal device, the machine learning model running in the terminal device or the network side device can always adapt to the scene of the terminal device, thereby ensuring the accuracy and efficiency of data processing.
  • the embodiment of the present application provides a data transmission method.
  • FIG. 9 a flow chart of a data transmission method provided by the embodiment of the present application is shown. The method is applied to a second device, as shown in FIG. 9 , and the method may specifically include:
  • Step 501 The second device sends sixth information to the first device.
  • the six pieces of information include at least one of the following:
  • third information where the third information is used to indicate an association relationship between the position coordinates and the scene information
  • a first indication where the first indication is used to indicate scene information in which the terminal device is located;
  • the second indication is used to indicate a mapping relationship between the machine learning model and the scene information
  • a third indication is used to indicate a machine learning model associated with the scene information in which the terminal device is located.
  • the second device in the embodiment of the present application can be a network side device or a high-level terminal device.
  • the first device is a network side device, such as an access network device
  • the second device can be a core network device
  • the first device is a terminal device
  • the second device can be a network side device or a high-level terminal device.
  • the third information is used to indicate the association between the location coordinates and the scene information.
  • the second device can indicate the association between the location coordinates and the scene information to the first device through the third information.
  • the first device After the first device receives the third information, it can determine the scene information of the terminal device based on the location information of the terminal device and the association between the location coordinates and the scene information, and then determine the first model based on the scene information and the association between the machine learning model and the scene information.
  • the first indication may include, but is not limited to, a scenario ID, scenario information, scenario category, area ID, area information, area category, dataset ID, dataset information, dataset category, etc. of the scenario in which the first device is located.
  • the granularity of the scenario, area, or dataset may be a cell.
  • the scenario ID, area ID, and dataset ID may be associated with the Physical Cell Identifier (PCI) of one or more cells, so as to determine the scenario ID, area ID, and dataset ID corresponding to the first device according to the cell in which the first device is located.
  • PCI Physical Cell Identifier
  • the granularity of the scenario, area, or dataset may also be smaller than the cell.
  • a scenario may be a factory building, a building, or even a floor in a building in a cell.
  • a machine learning model may correspond to one or more scenarios, areas, or datasets.
  • the machine learning model can be trained by the second device, and the second device records the association between the model identifier of each machine learning model and the scene information.
  • the machine learning model is trained by a third-party server, and the third-party server sends the trained machine learning model to the first device, and sends the association between the machine learning model and the scene information to the first device and/or the second device.
  • the second device can send the association relationship between the machine learning model and the scene information to the first device through the second indication, so that the first device determines the first model based on the second indication.
  • the second device may also determine the machine learning model associated with the scene information where the terminal device is located based on the scene information where the terminal device is located and the positional relationship between the machine learning model and the scene information, and indicate the model information of the model to the first device through a third indication.
  • the third indication may include model information of the machine learning model associated with the scene information where the terminal device is located, such as a model identifier.
  • an embodiment of the present application provides a data transmission method, whereby the second device can send to the first device at least one of the association relationship between the location coordinates and the scene information, the scene information of the terminal device, the mapping relationship between the machine learning model and the scene information, and the model information of the machine learning model associated with the scene information of the terminal device through the sixth information, so that the first device can determine which model should be applied in the scene currently located by the terminal device based on the received sixth information.
  • the model determination method provided in the embodiment of the present application can be executed by a model determination device.
  • the model determination device provided in the embodiment of the present application is described by taking the model determination method executed by the model determination device as an example.
  • the embodiment of the present application provides a model determination device.
  • a structural block diagram of a model determination device provided by the embodiment of the present application is shown, and the device can be applied to a first device.
  • the device can specifically include:
  • a model determination module 601 is used to determine a first model based on first information
  • the first information includes any one of the following:
  • Scene information of the terminal device and a mapping relationship between the machine learning model and the scene information;
  • the first device is the terminal device or a network side device;
  • Model information of the machine learning model associated with the scene information in which the terminal device is located is located.
  • the device further comprises:
  • a scene information acquisition module used to acquire scene information of the terminal device
  • the first relationship acquisition module is used to obtain the mapping relationship between the machine learning model and the scene information.
  • the scene information acquisition module includes:
  • a first acquisition submodule used to acquire second information, where the second information is used to indicate communication information of the terminal device, and the second information is associated with scene information where the terminal device is located;
  • the first determination submodule is used to determine the scene information of the terminal device according to the second information.
  • the first acquisition submodule includes:
  • the measuring unit is used to measure the reference signal and determine the second information based on the measurement result.
  • the first acquisition submodule includes:
  • the first receiving unit is used to receive second information sent by the terminal device.
  • the first determining submodule includes:
  • a first acquisition unit used for the first device to acquire an association relationship between the communication information and the scene information
  • the first determination unit is used to determine the scene information of the terminal device according to the second information and the association relationship between the communicated information and the scene information.
  • the first determining submodule includes:
  • a first sending unit configured to send the second information to a network side device
  • the second receiving unit is used to receive a first indication sent by the network side device; the first indication is used to indicate the scene information of the first device.
  • the scene information acquisition module includes:
  • a second acquisition submodule is used to acquire the location information of the terminal device, where the location information is associated with the scene information where the terminal device is located;
  • the second determination submodule is used to determine the scene information of the terminal device according to the position information and the association relationship between the position coordinates and the scene information.
  • the scene information acquisition module further includes:
  • the first receiving submodule is used to receive third information sent by the second device, where the third information is used to indicate the association relationship between the position coordinates and the scene information.
  • the second acquisition submodule includes:
  • a second determining unit configured to determine current location information based on positioning technology when the first device is a terminal device
  • the third receiving unit is used to receive fourth information sent by the terminal device when the first device is a network side device, and the fourth information is used to indicate the location information of the terminal device.
  • the scene information acquisition module includes:
  • the second receiving submodule is used to receive a first indication and a second indication sent by a second device, wherein the first indication is used to indicate the scene information of the terminal device; and the second indication is used to indicate the mapping relationship between the machine learning model and the scene information.
  • the device further comprises:
  • a third indication receiving module is used to receive a third indication sent by a second device, where the third indication is used to indicate a machine learning model associated with scene information in which the terminal device is located.
  • the measuring unit is specifically used to:
  • the fourth indication is used to instruct the first device to measure at least one reference signal
  • the second information is determined based on a first measurement result of the first reference signal.
  • the measuring unit is specifically used to:
  • the second reference signal is measured, and the second information is determined based on a second measurement result of the second reference signal.
  • the second information includes at least one of the following:
  • the first parameter being used to indicate a communication resource of the terminal device
  • the second communication information, the fifth parameter is used to indicate the communication area where the terminal device is located.
  • the first communication information includes at least one of the following:
  • the reference signal information includes at least one of the following:
  • the second parameter is used to indicate a reference signal resource
  • the second parameter, the third parameter is used to indicate reference signal measurement information
  • the third parameter, the fourth parameter is used to indicate reference signal reporting information.
  • the communication indicator information includes at least one of the following:
  • the measuring unit is specifically used to:
  • the target reference signal resource includes at least one of the following:
  • N first target reference signal resources among the reference signal resources configured for each transmission/reception point; the reference signal received power of the N first target reference signal resources is greater than the reference signal received power of other reference signal resources of the same transmission/reception point; N is a positive integer;
  • Reference signal resources configured for each transmitting and receiving point.
  • the resource information includes at least one of the following:
  • model activation module includes:
  • the model activation submodule is used to deactivate the second model and activate the first model when the currently running second model does not match the first model.
  • the device further comprises:
  • a fifth information sending module is used to send fifth information to the network side device, where the fifth information includes at least one of the following:
  • the activation time of the first model is the activation time of the first model.
  • the model determination 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 the electronic device, such as an integrated circuit or a chip.
  • the model determination device provided in the embodiment of the present application can implement the various processes implemented in the aforementioned method embodiment and achieve the same technical effect. To avoid repetition, it will not be repeated here.
  • the embodiment of the present application provides a data transmission device.
  • a structural block diagram of a data transmission device provided by the embodiment of the present application is shown, and the device can be applied to a second device.
  • the device may specifically include:
  • the information sending module 701 is used to send sixth information to the first device.
  • the six pieces of information include at least one of the following:
  • third information where the third information is used to indicate an association relationship between the position coordinates and the scene information
  • a first indication where the first indication is used to indicate scene information of a terminal device
  • the second indication is used to indicate a mapping relationship between the machine learning model and the scene information
  • a third indication is used to indicate a machine learning model associated with the scene information in which the terminal device is located.
  • the data transmission device in the embodiment of the present application may be an electronic device, such as an electronic device with an operating system, or may be a component in the electronic device, such as an integrated circuit or a chip.
  • the data transmission device provided in the embodiment of the present application can implement the various processes implemented in the aforementioned method embodiment and achieve the same technical effect. To avoid repetition, it will not be described here.
  • an embodiment of the present application further provides a communication device 900, including a processor 901 and a memory 902, the memory 902 storing programs or instructions that can be run on the processor 901, for example, when the communication device 900 is a network side device, the program or instruction is executed by the processor 901 to implement the various steps of the aforementioned model determination method embodiment, or to implement the various steps of the aforementioned data transmission method embodiment, and can achieve the same technical effect.
  • the communication device 900 is a terminal device
  • the program or instruction is executed by the processor 901 to implement the various steps of the aforementioned model determination method embodiment, or to implement the various steps of the aforementioned data transmission method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.
  • FIG13 it is a schematic diagram of the hardware structure of a terminal device implementing an embodiment of the present application.
  • the terminal device 1000 includes but is not limited to: a radio frequency unit 1001, a network module 1002, an audio output unit 1003, an input unit 1004, a sensor 1005, a display unit 1006, a user input unit 1007, an interface unit 1008, a memory 1009 and at least some of the components of the processor 1010.
  • the terminal device 1000 can also include a power supply (such as a battery) for supplying power to each component, and the power supply can be logically connected to the processor 1010 through a power management system, so as to manage charging, discharging, and power consumption management through the power management system.
  • a power supply such as a battery
  • the terminal device structure shown in FIG13 does not constitute a limitation on the terminal device, and the terminal device 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.
  • the input unit 1004 may include a graphics processing unit (GPU) 10041 and a microphone 10042, and the graphics processor 10041 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 1006 may include a display panel 10061, and the display panel 10061 may be configured in the form of a liquid crystal display, an organic light emitting diode, etc.
  • the user input unit 1007 includes a touch panel 10071 and at least one of other input devices 10072.
  • the touch panel 10071 is also called a touch screen.
  • the touch panel 10071 may include two parts: a touch detection device and a touch controller.
  • Other input devices 10072 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.
  • the RF unit 1001 can transmit the data to the processor 1010 for processing; in addition, the RF unit 1001 can send uplink data to the network side device.
  • the RF unit 1001 includes but is not limited to an antenna, an amplifier, a transceiver, a coupler, a low noise amplifier, a duplexer, etc.
  • the memory 1009 can be used to store software programs or instructions and various data.
  • the memory 1009 may mainly include a first storage area for storing programs or instructions and a second storage area for storing data, wherein the first storage area may 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.
  • the memory 1009 may include a volatile memory or a non-volatile memory, or the memory 1009 may include both volatile and non-volatile memories.
  • the non-volatile memory may 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 1009 in the embodiment of the present application includes but is not limited to these and any other suitable types of memory.
  • the processor 1010 may include one or more processing units; optionally, the processor 1010 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 1010.
  • the embodiment of the present application also provides a network side device, including a processor and a communication interface, 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 aforementioned method embodiment.
  • the network side device embodiment corresponds to the aforementioned network side device method embodiment, and each implementation process and implementation method of the network side device in the aforementioned method embodiment can be applied to the network side device embodiment, and can achieve the same technical effect.
  • the embodiment of the present application further provides a network side device, as shown in FIG14, the network side device 1100 includes: an antenna 111, a radio frequency device 112, a baseband device 113, a processor 114 and a memory 115.
  • the antenna 111 is connected to the radio frequency device 112.
  • the radio frequency device 112 receives information through the antenna 111 and sends the received information to the baseband device 113 for processing.
  • the baseband device 113 processes the information to be sent and sends it to the radio frequency device 112, and the radio frequency device 112 processes the received information and sends it out through the antenna 111.
  • the method executed by the network-side device in the above embodiment may be implemented in the baseband device 113, which includes a baseband processor.
  • the baseband device 113 may include, for example, at least one baseband board, on which a plurality of chips are arranged, as shown in FIG14 , wherein one of the chips is, for example, a baseband processor, which is connected to the memory 115 through a bus interface to call a program in the memory 115 and execute the network device operations shown in the above method embodiment.
  • the network side device may also include a network interface 116, which is, for example, a common public radio interface (CPRI).
  • a network interface 116 which is, for example, a common public radio interface (CPRI).
  • CPRI common public radio interface
  • the network side device 1100 of the embodiment of the present invention also includes: instructions or programs stored in the memory 115 and executable on the processor 114.
  • the processor 114 calls the instructions or programs in the memory 115 to execute the methods executed by the modules in Figure 10 or Figure 11 and achieve the same technical effect. To avoid repetition, it will not be repeated here.
  • the embodiment of the present application also provides a network side device.
  • the network side device 1200 includes: a processor 1201, a network interface 1202 and a memory 1203.
  • the network interface 1202 is, for example, a common public radio interface (CPRI).
  • CPRI common public radio interface
  • the network side device 1200 of the embodiment of the present invention also includes: instructions or programs stored in the memory 1203 and executable on the processor 1201.
  • the processor 1201 calls the instructions or programs in the memory 1203 to execute the method executed by each module shown in Figure 10 or Figure 11, 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.
  • a program or instruction is stored.
  • the various processes of the aforementioned 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 device 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.
  • 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 aforementioned method embodiment and achieve the same technical effect. To avoid repetition, it will not be repeated here.
  • 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 aforementioned method embodiments and can achieve the same technical effects. To avoid repetition, they are not described here.
  • An embodiment of the present application also provides a model determination system, including: a first device and a second device, wherein the first device can be used to execute the steps of the model determination method described in the first aspect above, and the second device can be used to execute the steps of the data transmission method described in the second aspect above.
  • the technical solution of the present application can be embodied in the form of a computer software product, which is stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.
  • a storage medium such as ROM/RAM, magnetic disk, optical disk
  • a terminal which can be a mobile phone, computer, server, air conditioner, or network device, etc.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Software Systems (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Computation (AREA)
  • Medical Informatics (AREA)
  • Artificial Intelligence (AREA)
  • Theoretical Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Physics & Mathematics (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Mobile Radio Communication Systems (AREA)

Abstract

本申请公开了一种模型确定方法、装置及通信设备，属于通信技术领域，本申请实施例的模型确定方法包括：第一设备基于第一信息确定第一模型；所述第一设备激活所述第一模型；其中，所述第一信息包括以下任一项：终端设备所处的场景信息，以及机器学习模型与场景信息之间的映射关系；所述第一设备为所述终端设备或网络侧设备；与所述终端设备所处的场景信息相关联的机器学习模型的模型信息。

Description

模型确定方法、装置及通信设备
相关申请的交叉引用
本申请要求在2023年11月20日提交中国专利局、申请号为202311550325.2、名称为“模型确定方法、装置及通信设备”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请属于通信技术领域，具体涉及一种模型确定方法、装置及通信设备。
背景技术
目前3GPP讨论已经确认模型监督是机器学习模型生命周期管理的重要内容，但已有的基于模型输入/输出的模型监督方法只指示了当前的模型是否有效，而没有指示当前终端设备所处的环境应该应用何种机器学习模型。终端设备所处的环境不同，终端设备对应的一些数据信息，如位置信息、通信数据等就会发生变化，数据特征也随之变化。如果当前终端设备所处的环境与终端设备或网络侧设备中运行的机器学习模型不匹配，就会影响数据处理效率及准确度，进而影响终端设备的通信质量。
发明内容
本申请实施例提供一种模型确定方法、装置及通信设备，能够解决相关技术中无法指示当前终端设备所处的环境应该应用何种机器学习模型的问题。
第一方面，提供了一种模型确定方法，包括：
第一设备基于第一信息确定第一模型；
所述第一设备激活所述第一模型；
其中，所述第一信息包括以下任一项：
终端设备所处的场景信息，以及机器学习模型与场景信息之间的映射关系；所述第一设备为所述终端设备或网络侧设备；
与所述终端设备所处的场景信息相关联的机器学习模型的模型信息。
第二方面，提供了一种数据传输方法，包括：
第二设备向第一设备发送第六信息，所述六信息包括以下至少一项：
第三信息，所述第三信息用于指示位置坐标与场景信息之间的关联关系；
第一指示，所述第一指示用于指示终端设备的场景信息；
第二指示，所述第二指示用于指示机器学习模型与场景信息之间的映射关系；
第三指示，所述第三指示用于指示与所述终端设备所处的场景信息相关联的机器学习模型。
第三方面，提供了一种模型确定装置，应用于第一设备，所述装置包括：
模型确定模块，用于基于第一信息确定第一模型；
模型激活模块，用于激活所述第一模型；
其中，所述第一信息包括以下任一项：
终端设备所处的场景信息，以及机器学习模型与场景信息之间的映射关系；所述第一设备为所述终端设备或网络侧设备；
与所述终端设备所处的场景信息相关联的机器学习模型的模型信息。
第四方面，提供了一种数据传输装置，应用于第二设备，所述装置包括：
信息发送模块，用于向第一设备发送第六信息，所述六信息包括以下至少一项：
第三信息，所述第三信息用于指示位置坐标与场景信息之间的关联关系；
第一指示，所述第一指示用于指示终端设备的场景信息；
第二指示，所述第二指示用于指示机器学习模型与场景信息之间的映射关系；
第三指示，所述第三指示用于指示与所述终端设备所处的场景信息相关联的机器学习模型。
第五方面，提供了一种通信设备，该通信设备包括处理器和存储器，所述存储器存储可在所述处理器上运行的程序或指令，所述程序或指令被所述处理器执行时实现如第一方面所述的模型确定方法的步骤，或者实现如第二方面所述的数据传输方法的步骤。
第六方面，提供了一种模型确定系统，包括：第一设备和第二设备，所述第一设备可用于执行如上述第一方面所述的模型确定方法的步骤，所述第二设备可用于执行如上述第二方面所述的数据传输方法的步骤。
第七方面，提供了一种可读存储介质，所述可读存储介质上存储程序或指令，所述程序或指令被处理器执行时实现如第一方面所述的模型确定方法的步骤，或者实现如第二方面所述的数据传输方法的步骤。
第八方面，提供了一种芯片，所述芯片包括处理器和通信接口，所述通信接口和所述处理器耦合，所述处理器用于运行程序或指令，实现如第一方面所述的方法，或实现如第二方面所述的方法。
第九方面，提供了一种计算机程序/程序产品，所述计算机程序/程序产品被存储在存储介质中，所述计算机程序/程序产品被至少一个处理器执行以实现如第一方面或者第二方面所述的方法的步骤。
第十方面，提供了一种模型确定装置/设备，其中，包括所述装置/设备(被配置成)用于执行以实现如第一方面所述的模型确定方法的步骤。
第十一方面，提供了一种数据传输装置/设备，其中，包括所述装置/设备(被配置成)用于执行以实现如第一方面所述的数据传输方法的步骤。
本申请实施例将机器学习模型与场景进行了关联，第一设备可以根据终端设备所处的场景信息，以及机器学习模型与场景信息之间的映射关系，确定当前环境中应该应用何种模型；或者，第一设备可以直接根据第一信息中的模型信息确定与当前终端设备所处的场景信息相关联的机器学习模型，并激活该模型。在本申请实施例中，第一设备可以根据第一信息确定应该应用何种模型，从而保证在终端设备移动过程中，终端设备或网络侧设备中运行的机器学习模型能够始终与该终端设备所处的场景适配，保障了数据处理的准确度和处理效率。
附图说明
图1是本申请实施例可应用的一种无线通信系统的框图；
图2是本申请实施例中的一种模型确定方法的流程图；
图3是本申请实施例中的一种神经网络模型的结构示意图；
图4是本申请实施例中的一种神经元的示意图；
图5是本申请实施例中的一种模型确定方法的流程示意图；
图6是本申请实施例中的另一种模型确定方法的流程示意图；
图7本申请实施例中的一种模型确定方法的流程示意图；
图8本申请实施例中的另一种模型确定方法的流程示意图；
图9是本申请实施例中的一种数据传输方法的流程图；
图10是本申请实施例中的一种模型确定装置的结构框图；
图11是本申请实施例中的一种数据传输装置的结构框图；
图12是本申请实施例中的一种通信设备的结构框图；
图13是本申请实施例中的一种终端设备的结构框图；
图14是本申请实施例中的一种网络侧设备的结构框图；
图15是本申请实施例中另一种网络侧设备的结构框图。
具体实施方式
下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚描述，显然，所描述的实施例是本申请一部分实施例，而不是全部的实施例。基于本申请中的实施例，本领域普通技术人员所获得的所有其他实施例，都属于本申请保护的范围。
本申请的说明书和权利要求书中的术语“第一”、“第二”等是用于区别类似的对象，而不用于描述特定的顺序或先后次序。应该理解这样使用的术语在适当情况下可以互换，以便本申请的实施例能够以除了在这里图示或描述的那些以外的顺序实施，且“第一”、“第二”所区别的对象通常为一类，并不限定对象的个数，例如第一对象可以是一个，也可以是多个。此外，说明书以及权利要求中“和/或”表示所连接对象的至少其中之一，字符“/”一般表示前后关联对象是一种“或”的关系。
值得指出的是，本申请实施例所描述的技术不限于长期演进型(Long Term Evolution，LTE)/LTE的演进(LTE-Advanced，LTE-A)系统，还可用于其他无线通信系统，诸如码分多址(Code Division Multiple Access，CDMA)、时分多址(Time Division Multiple Access，TDMA)、频分多址(Frequency Division Multiple Access，FDMA)、正交频分多址(Orthogonal Frequency Division Multiple Access，OFDMA)、单载波频分多址(Single-carrier Frequency Division Multiple Access，SC-FDMA)和其他系统。本申请实施例中的术语“系统”和“网络”常被可互换地使用，所描述的技术既可用于以上提及的系统和无线电技术，也可用于其他系统和无线电技术。以下描述出于示例目的描述了新空口(New Radio，NR)系统，并且在以下大部分描述中使用NR术语，但是这些技术也可应用于NR系统应用以外的应用，如第6代(6th Generation，6G)通信系统。
图1示出本申请实施例可应用的一种无线通信系统的框图。无线通信系统包括终端设备11和网络侧设备12。其中，终端设备11可以是手机、平板电脑(Tablet Personal Computer)、膝上型电脑(Laptop Computer)或称为笔记本电脑、个人数字助理(Personal Digital Assistant，PDA)、掌上电脑、上网本、超级移动个人计算机(ultra-mobile personal computer，UMPC)、移动上网装置(Mobile Internet Device，MID)、增强现实(augmented reality，AR)/虚拟现实(virtual reality，VR)设备、机器人、可穿戴式设备(Wearable Device)、车载设备(VUE)、行人终端(PUE)、智能家居(具有无线通信功能的家居设备，如冰箱、电视、洗衣机或者家具等)、游戏机、个人计算机(personal computer，PC)、柜员机或者自助机等终端侧设备，可穿戴式设备包括：智能手表、智能手环、智能耳机、智能眼镜、智能首饰(智能手镯、智能手链、智能戒指、智能项链、智能脚镯、智能脚链等)、智能腕带、智能服装等。需要说明的是，在本申请实施例并不限定终端设备11的具体类型。网络侧设备12可以包括接入网设备或核心网设备，其中，接入网设备12也可以称为无线接入网设备、无线接入网(Radio Access Network,RAN)、无线接入网功能或无线接入网单元。接入网设备12可以包括基站、WLAN接入点或WiFi节点等，基站可被称为节点B、演进节点B(eNB)、接入点、基收发机站(Base Transceiver Station，BTS)、无线电基站、无线电收发机、基本服务集(Basic Service Set，BSS)、扩展服务集(Extended Service Set，ESS)、家用B节点、家用演进型B节点、发送接收点(Transmitting Receiving Point，TRP)或所述领域中其他某个合适的术语，只要达到相同的技术效果，所述基站不限于特定技术词汇，需要说明的是，在本申请实施例中仅以NR系统中的基站为例进行介绍，并不限定基站的具体类型。核心网设备可以包含但不限于如下至少一项：核心网节点、核心网功能、移动管理实体(Mobility Management Entity，MME)、接入移动管理功能(Access and Mobility Management Function，AMF)、会话管理功能(Session Management Function，SMF)、用户平面功能(User Plane Function，UPF)、策略控制功能(Policy Control Function，PCF)、策略与计费规则功能单元(Policy and Charging Rules Function，PCRF)、边缘应用服务发现功能(Edge Application Server Discovery Function，EASDF)、统一数据管理(Unified Data Management，UDM)，统一数据仓储(Unified Data Repository，UDR)、归属用户服务器(Home Subscriber Server，HSS)、集中式网络配置(Centralized network configuration，CNC)、网络存储功能(Network Repository Function，NRF)，网络开放功能(Network Exposure Function，NEF)、本地NEF(Local NEF，或L-NEF)、绑定支持功能(Binding Support Function，BSF)、应用功能(Application Function，AF)等。需要说明的是，在本申请实施例中仅以NR系统中的核心网设备为例进行介绍，并不限定核心网设备的具体类型。
下面结合附图，通过一些实施例及其应用场景对本申请实施例提供的模型确定方法进行详细地说明。
本申请实施例提供了一种模型确定方法。参照图2，示出了本申请实施例提供的一种模型确定方法的流程图。该方法应用于第一设备，如图2所示，该方法具体可以包括：
步骤201、第一设备基于第一信息确定第一模型。
步骤202、所述第一设备激活所述第一模型。
其中，所述第一信息包括以下任一项：
终端设备所处的场景信息，以及机器学习模型与场景信息之间的映射关系；所述第一设备为所述终端设备或网络侧设备；
与所述终端设备所处的场景信息相关联的机器学习模型的模型信息。
需要说明的是，在本申请实施例中，所述第一设备可以是终端设备，也可以是网络侧设备。所述终端设备可以包括常规终端设备和/或定位参考单元。其中，所述常规终端设备可以是图1中的终端设备11。所述定位参考单元(Positioning Reference Unit，PRU)可以执行定位测量，例如参考信号时差(Reference signal time difference，RSTD)、参考信号接收功率(Reference Signal Receiving Power，RSRP)、UE Rx-Tx时间差测量等，并将这些测量结果报告给定位服务器。此外，PRU可以向发送接收点(Transmission and Receiving Point，TRP)发送定位参考信号(Positioning reference signal,PRS)，使得TRP能够测量和报告来自已知位置的PRU的上行链路(Up-Link，UL)定位测量值，例如RTOA、UL-AoA、gNB Rx-Tx时间差等。位置服务器可以将PRU测量值与已知PRU位置处的预期测量值进行比较，以确定附近其他目标设备的校正项，然后基于该校正项来校正其他目标设备的DL和/或UL位置测量值。
所述网络侧设备可以是图1中的接入网设备，如基站或接入网侧新定义的人工智能处理节点，还可以是图1中的核心网设备，如网络数据分析功能(Network Data Analytics Function，NWDAF)、定位管理功能(Location Management Function，LMF)，或者核心网侧新定义的处理节点，还可以是上述多个节点的组合。
在本申请实施例中，机器学习模型可以由网络侧设备训练，网络侧设备通过模型转移/交付(model transfer/delivery)将训练好的机器学习模型发送给终端设备，网络侧设备中记录有各个机器学习模型的模型标识和场景信息之间的关联关系。
或者，机器学习模型由第三方服务器训练，第三方服务器将训练好的机器学习模型发送给终端设备和/或网络侧设备，并将机器学习模型的模型标识和场景信息之间的关联关系发送给终端设备和/或网络侧设备。
需要说明的是，本申请实施例中的机器学习模型可以为人工智能(Artificial Intelligence，AI)模型，例如全连接神经网络、卷积神经网络、决策树、支持向量机、贝叶斯分类器中的任意一种。以神经网络模型为例，其示意图可如图3所示。如图3所示，神经网络可以包括一个或多个输入层、一个或多个隐层和一个输出层。待处理数据[X1,X2…Xn]分别从对应的输入层输入至神经网络中，经过输入层、隐层和输出层的处理，得到输出结果Y。另外，神经网络由神经元组成，神经元的示意图如图4所示。其中在图4中，a1,a2,…aK表示输入，w表示权值(即乘性系数)，b表示偏置(即加性系数)，σ(.)表示激活函数。常见的激活函数包括Sigmoid(将变量映射到0、1之间)、tanh(对Sigmoid的平移和收缩)、线性整流函数/修正线性单元(Rectified Linear Unit，ReLU)等。
此外，以神经网络模型为例，对模型训练的过程进行如下介绍：
其中，神经网络的参数可以通过梯度优化算法进行优化。梯度优化算法是一类最小化或者最大化目标函数(有时候也称为损失函数)的算法，而目标函数往往是模型参数和数据的数学组合。例如给定数据X和其对应的标签Y，可以构建一个神经网络模型f(.)，则根据输入x就可以得到预测输出f(x)，并且可以计算出预测值和真实值之间的差距(fx-Y)，这个就是损失函数。其中，梯度优化算法的优化目标是找到合适的w(即权值)和b(即偏置)使上述的损失函数的值达到最小，而损失值越小，则说明模型越接近于真实情况。
目前常见的优化算法，基本都是基于误差反向传播(error Back Propagation，BP)算法。BP算法的基本思想是，学习过程由信号的正向传播与误差的反向传播两个过程组成。正向传播时，输入样本从输入层传入，经各隐层逐层处理后，传向输出层。若输出层的实际输出与期望的输出不符，则转入误差的反向传播阶段。误差反传则是将输出误差以某种形式通过隐层向输入层逐层反传，并将误差分摊给各层的所有单元，从而获得各层单元的误差信号，此误差信号即作为修正各单元权值的依据。这种信号正向传播与误差反向传播的各层权值调整过程，是周而复始地进行的。其中，权值不断调整的过程，也就是网络的学习训练过程。此过程一直进行到网络输出的误差减少到可接受的程度，或进行到预先设定的学习次数为止。
另外，常见的优化算法有梯度下降(Gradient Descent)、随机梯度下降(Stochastic Gradient Descent，SGD)、小批量梯度下降(mini-batch gradient descent)、动量法(Momentum)、Nesterov(发明者的名字，具体为带动量的随机梯度下降)自适应梯度下降(ADAptive GRADient descent，Adagrad)、Adagrad的扩展算法(Adadelta)、均方根误差降速(root mean square prop，RMSprop)、自适应动量估计(Adaptive Moment Estimation，Adam)等。
这些优化算法在误差反向传播时，都是根据损失函数得到的误差/损失，对当前神经元求导数/偏导，加上学习速率、之前的梯度/导数/偏导等影响，得到梯度，将梯度传给上一层。
本申请实施例中机器学习模型也可称为AI单元、AI模型、ML(machine learning)模型、ML单元、AI结构、AI功能、AI特性、神经网络、神经网络函数、神经网络功能等，或者所述AI单元/AI模型也可以是指能够实现与AI相关的特定的算法、公式、处理流程、能力等的处理单元，或者所述AI单元/AI模型可以是针对特定数据集的处理方法、算法、功能、模块或单元，或者所述AI单元/AI模型可以是运行在GPU、NPU、TPU、ASIC等AI/ML相关硬件上的处理方法、算法、功能、模块或单元，本发明对此不做具体限定。可选地，所述特定数据集包括AI单元/AI模型的输入和/或输出。
可选地，所述AI单元/AI模型的标识，可以是AI模型标识、AI结构标识、AI算法标识，或者所述AI单元/AI模型关联的特定数据集的标识，或者所述AI/ML相关的特定场景、环境、信道特征、设备的标识，或者所述AI/ML相关的功能、特性、能力或模块的标识，本申请实施例对此不做具体限定。
在本申请实施例中，第一设备可以基于第一信息确定第一模型。例如，第一设备根据终端设备所处的场景信息，和机器学习模型与场景信息之间的映射关系，确定与终端设备所处的场景信息相关联的机器学习模型，并将该模型确定为第一模型。或者，在第一信息包括与终端设备所处的场景信息相关联的机器学习模型的模型信息的情况下，第一设备可以直接将该模型信息所指示的机器学习模型确定为第一模型。
确定出第一模型之后，第一设备就可以激活第一模型，从而利用第一模型对终端设备在当前所处场景下产生的数据进行处理。
可以理解的是，在第一设备为网络侧的情况下，运行在第一设备中的机器学习模型可以用于处理终端设备对应的数据，例如确定终端设备的位置信息、分析终端设备所处小区的通信质量、对终端设备进行接入控制，等等。当终端设备所处的场景发生变化时，第一设备中运行的机器学习模型可能不能满足终端设备当前所处场景的数据处理需求，在这种情况下，终端设备可以根据第一信息确定出与终端设备当前所处场景相匹配的第一模型并激活。
需要说明的是，在本申请实施例中，终端设备所处的场景信息可以包括但不限于终端设备所处场景的场景标识(scenario ID)、场景信息(scenario information)、场景类别(scenario category)、区域标识(area ID)、区域信息(area information)、区域类别(area category)、数据集标识(dataset ID)、数据集信息(dataset information)、数据集类别(dataset category)等。其中，场景或区域或数据集的颗粒度可以是小区，在一种可能的实现方式中，可以将场景ID、区域ID、数据集ID与一个或多个小区的物理小区标识(Physical Cell Identifier，PCI)关联，从而根据第一设备所处的小区确定第一设备对应的场景ID、区域ID和数据集ID。在另一种可能的实现方式中，场景或区域或数据集的颗粒度也可以小于小区，比如AI定位，一个场景可以是小区内的一个厂房、一栋楼甚至是一栋楼里的某一层。
一个机器学习模型可以对应一个或多个场景、区域或数据集。
在本发明实施例中，如果第一设备基于第一信息确定的第一模型与第一设备中当前运行的机器学习模型不相同，第一设备就可以确定当前运行的机器学习模型已经无法满足当前所处场景的计算需求，换言之，在第一设备当前所处的场景中，第一设备中当前运行的机器学习模型为无效模型。在这种情况下，第一设备就可以将正在运行的机器学习模型切换为第一模型。
本申请实施例将机器学习模型与场景进行了关联，第一设备可以根据终端设备所处的场景信息，以及机器学习模型与场景信息之间的映射关系，确定当前环境中应该应用何种模型；或者，第一设备可以直接根据第一信息中的模型信息确定与当前终端设备所处的场景信息相关联的机器学习模型，并激活该模型。在本申请实施例中，第一设备可以根据第一信息确定应该应用何种模型，从而保证在终端设备移动过程中，终端设备或网络侧设备中运行的机器学习模型能够始终与该终端设备所处的场景适配，保障数据处理的准确度和处理效率。
可选地，在所述第一设备基于第一信息确定第一模型之前，所述方法还包括：
所述第一设备获取所述终端设备所处的场景信息；
所述第一设备获取机器学习模型与场景信息之间的映射关系。
在本申请实施例中，机器学习模型与场景信息之间的映射关系可以由训练模型的网络侧设备或第三方服务器生成。示例性地，如果第一设备为终端设备，那么机器学习模型与场景信息之间的映射关系可以由训练模型的网络侧设备或第三方服务器发送给第一设备；如果第一设备为网络侧设备，那么在该网络侧设备进行模型训练的情况下，该网络侧设备可以基于模型训练过程本地生成机器学习模型与场景信息之间的映射关系；在由第三方服务器进行模型训练的情况下，该网络侧设备可以从第三方服务器中读取机器学习模型与场景信息之间的映射关系。
同样地，第一设备也可以通过多种方式获取终端设备所处的场景信息。
作为一种示例，所述第一设备获取所述终端设备所处的场景信息，包括：
步骤S11、所述第一设备获取第二信息，所述第二信息用于指示所述终端设备的通信信息，所述第二信息与所述终端设备所处的场景信息相关联；
步骤S12、所述第一设备根据所述第二信息确定所述终端设备的场景信息。
其中，第二信息与第一设备所处的场景相关联，比如，第二信息与第一设备当前所处的场景ID、区域ID、数据集ID、场景类别、区域类别、数据集类别等信息关联。作为一种示例，所述第二信息可以包括第一设备对应的小区ID、参考信号ID、发送接收点ID、区域ID、跟踪区域(Tracking Area)ID等。
在本申请实施例中，第一设备可以根据第二信息确定终端设备所处的场景信息。
可选地，在所述第一设备为终端设备的情况下，所述第一设备获取第二信息，包括：
所述第一设备对参考信号进行测量，并基于测量结果确定第二信息。
参照图5，示出了本申请实施例提供的一种模型确定方法的流程示意图。如图5所示，如果第一设备为终端设备，那么第一设备可以通过测量参考信号确定第二信息。
可选地，在所述第一设备为网络侧设备的情况下，所述第一设备获取第二信息，包括：
所述第一设备接收所述终端设备发送的第二信息。
参照图6，示出了本申请实施例提供的另一种模型确定方法的流程示意图。如图6所示，如果第一设备为网络侧设备，那么第二信息可以由终端设备根据参考信号的测量结果生成第二信息之后，发送给网络侧设备。网络侧设备本身无需对参考信号进行任何测量操作。
可选地，所述第一设备根据所述第二信息确定所述终端设备的场景信息，包括：
所述第一设备获取通信信息与场景信息之间的关联关系；
所述第一设备根据所述第二信息，以及所通信信息与场景信息之间的关联关系，确定所述终端设备的场景信息。
其中，通信信息与场景之间的关联关系可以是第二设备发送给第一设备的，也可以是协议规定的。在第一设备为网络侧设备的情况下，比如第一设备为接入网设备，那么第二设备可以是核心网设备；在第一设备为终端设备的情况下，第二设备可以是网络侧设备，或者是终端设备的高层。
第一设备获取到第二信息之后，可以基于第二信息所指示的通信信息，以及通信信息与场景信息之间的关联关系，确定出终端设备所处的场景信息。
示例性地，如图6所示，如果第一设备为网络侧设备，网络侧设备接收到终端设备上报的第二信息之后，可以根据第二信息所指示的通信信息，以及通信信息与场景信息之间的关联关系确定出终端设备所处的场景信息，然后再进一步结合机器学习模型与场景信息之间的关联关系，确定出第一模型并激活。
如图5所示，如果第一设备为终端设备，终端设备通过对参考信号进行测量确定出第二信息之后，可以根据第二信息所指示的通信信息，以及通信信息与场景信息之间的关联关系确定出终端设备所处的场景信息，然后再进一步结合机器学习模型与场景信息之间的关联关系，确定出第一模型并激活。或者，终端设备也可以将第二信息发送给网络侧设备，由网络侧设备基于第二信息确定出该终端设备所处的场景信息并指示给该终端设备。
可选地，所述第一设备根据所述第二信息确定所述终端设备的场景信息，包括：
步骤S21、所述第一设备将所述第二信息发送给网络侧设备；
步骤S22、所述第一设备接收所述网络侧设备发送的第一指示；所述第一指示用于指示所述第一设备的场景信息。
如图5所示，在本申请一种可能的应用场景中，第一设备为终端设备，终端设备可以通过测量参考信号确定第二信息，并将第二信息发送给网络侧设备。网络侧设备基于第二信息以及通信信息与场景信息之间的关联关系，确定出终端设备当前所处的场景信息，并通过第一指示将场景信息指示给终端设备，终端设备再根据第一指示所指示的场景信息，以及机器学习模型与场景信息之间的关联关系确定出第一模型并激活。
或者，网络侧设备基于第二信息指示的通信信息，以及通信信息与场景信息之间的关联关系，确定出终端设备当前所处的场景信息，并进一步基于机器学习模型与场景信息之间的关联关系确定出与终端设备当前所处场景信息相关联的机器学习模型，也即第一模型，并通过第三指示将第一模型指示给终端设备。
在本申请的一种可选实施例中，所述第一设备获取所述终端设备所处的场景信息，包括：
所述第一设备接收第二设备发送的第一指示和第二指示，所述第一指示用于指示所述终端设备的场景信息；所述第二指示用于指示机器学习模型与场景信息之间的映射关系。
在本申请的另一种可能的应用场景中，终端设备所处的场景信息，以及机器学习模型与场景信息之间的映射关系也可以由第二设备指示给第一设备。
需要说明的是，本申请实施例中的第二设备可以是网络侧设备，也可以是终端设备的高层。例如，在第一设备为网络侧设备的情况下，比如第一设备为接入网设备，那么第二设备可以是核心网设备；在第一设备为终端设备的情况下，第二设备可以是网络侧设备，或者是终端设备的高层。
作为一种示例，第一指示和第二指示可以被携带在同一个信令中，第二设备通过某一个信令同时向第一设备发送第一指示和第二指示，第一设备根据接收到的第一指示和第二指示确定第一模型并激活。或者，第二设备可以通过一个信令向第一设备发送第一指示，通过其他信令向第一设备发送第二指示。其中，携带第一指示和/或第二指示的信令可以包括但不限于：无线资源控制协议(Radio Resource Control，RRC)信令、无线链路层控制协议(Radio Link Control，RLA)信令、媒体访问控制(Media Access Control，MAC)信令、LTE定位协议(LTE Positioning Protocol，LPP)信令、NR定位协议A(NRPPa)信令、下行链路控制信息(Downlink Control Information，DCI)等。
作为另一种示例，第一指示由第二设备发送给第一设备，机器学习模型由第三方服务器训练，并由第三方服务器向第一设备发送第二指示。
可选地，在所述第一设备基于第一信息确定第一模型之前，所述方法还包括：
所述第一设备接收第二设备发送的第三指示，所述第三指示用于指示与所述终端设备所处的场景信息相关联的机器学习模型。
在本申请实施例中，第三指示可以由第二设备发送给第一设备。第一设备在接收到第三指示之后，可以直接将第三指示所指示的机器学习模型确定为待激活的第一模型。
可以理解的是，第二设备可以根据终端设备的位置信息确定出终端设备所处的场景信息，进而根据场景信息与机器学习模型之间的关联关系确定出与终端设备当前所处场景相匹配的机器学习模型，生成第三指示并发送给第一设备。或者，第一设备可以将终端设备所处的场景信息发送给第二设备，由第二设备根据该场景信息以及机器学习模型与场景信息之间的关联关系，确定出与终端设备当前所处场景相关联的机器学习模型，生成第三指示并发送给第一设备。
可选地，所述第一设备对参考信号进行测量，并基于测量结果确定第二信息，包括：
步骤S31、所述第一设备在接收到第四指示的情况下，对第一参考信号进行测量；所述第四指示用于指示所述第一设备对至少一种参考信号进行测量；
步骤S32、所述第一设备基于所述第一参考信号的第一测量结果确定所述第二信息。
在一种可能的应用场景中，第一设备为终端设备，终端设备可以在接收到第四指示的情况下对第一参考信号进行测量，并基于第一参考信号的第一测量结果确定第二信息。
需要说明的是，第四指示可以是第二设备发送给第一设备的，也可以是其他设备发送给第一设备的。在另一种可能的应用场景中，第四指示也可以是在满足一定测量条件的情况下，由第一设备的高层自动触发的。
其中，第一参考信号可以包括但不限于：定位参考信号、下行信道探测参考信号(Channel-State-Information Reference Signal，CSI-RS)、上行探测信号(Sounding Reference Signal，SRS)、同步信号块(Synchronization Signal Block，SSB)、时频跟踪参考信号(Tracking Reference Signal，TRS)等。
可选地，所述第一设备对参考信号进行测量，并基于测量结果确定第二信息，包括：
步骤S41、所述第一设备接收参考点发送的第二参考信号；
步骤S42、所述第一设备对所述第二参考信号进行测量，并基于所述第二参考信号的第二测量结果确定第二信息。
在本申请实施例中，第一设备为终端设备，终端设备也可以对来自接收参考点的第二参考信号进行测量，并基于第二参考信号的第二测量结果确定第二信息。作为一种示例，第二信息可以包括终端设备对应的小区ID、参考信号ID、接收参考点ID、场景ID、区域ID、跟踪区域(Tracking Area)ID等。
可选地，所述第二信息包括以下至少一项：
第一通信信息，所述第一参数用于指示所述终端设备的通信资源；
第二通信信息，所述第五参数用于指示所述终端设备所处的通信区域。
可选地，所述第一通信信息包括以下至少一项：
所述第一设备的参考信号信息；
所述第一设备的通信指标信息。
可选地，所述参考信号信息包括以下至少一项：
第一参数，所述第二参数用于指示参考信号资源；
第二参数，所述第三参数用于指示参考信号测量信息；
第三参数，所述第四参数用于指示参考信号上报信息。
其中，第一参数可以是参考信号资源ID、参考信号资源集ID等。第二参数可以是参考信号测量ID、参考信号测量配置ID等。第三参数可以是参考信号上报ID、参考信号上报配置ID。
可选地，所述通信指标信息包括以下至少一项：
第四参数，所述第一参数用于指示信道质量；
波束信息；
信道状态信息；
多径平均时延；
多径时延扩展。
其中，第四参数可以是信号质量的统计值或表示，例如信噪比(Signal-to-noise Ratio，SNR)、信号与干扰加噪声比(Signal to Interference plus Noise Ratio，SINR)、RSRP、参考信号接收质量(Reference Signal Received Quality，RSRQ)、信号功率、噪声功率、干扰功率等；或者如L1-RSRP、L1-SINR、L1-RSRP、L1-RSRQ、L3-RSRP、L3-SINR、L3-RSRP、L3-RSRQ等。
波束信息可以包括波束索引(index)、波束方向等信息。
在本申请的一种可选实施例中，所述第一设备对参考信号进行测量，并基于测量结果确定第二信息，包括：
步骤S51、所述第一设备对参考信号进行测量，得到测量结果；
步骤S52、所述第一设备根据所述测量结果确定目标参考信号资源，并根据所述目标参考信号资源的资源信息确定第二信息。
其中，所述目标参考信号资源包括以下至少一项：
A1、每一个发送接收点配置的参考信号资源中的N个第一目标参考信号资源；所述N个第一目标参考信号资源的参考信号接收功率大于同一发送接收点的其他参考信号资源的参考信号接收功率；N为正整数；
A2、从每一个发送接收点配置的参考信号资源中筛选出的第二目标参考信号资源；所述第二目标参考信号资源的参考信号接收功率大于或等于预设门限；
A3、每一个发送接收点配置的参考信号资源。
在本申请实施例中，第一设备为终端设备，终端设备可以从每一个发送接收点配置的各个参考信号资源中筛选出N个参考信号接收功率大于同一发送接收点的其他参考信号资源的第一目标参考信号资源，根据第一目标参考信号资源的资源信息，如参考信号ID、参考信号测量ID、参考信号上报ID等信息确定第二信息。
或者，终端设备也可以从每一个发送接收点配置的各个参考信号资源中筛选出参考信号接收功率大于或等于预设门限的第二目标参考信号资源，从而根据第二目标参考信号资源的资源信息，如参考信号ID、参考信号测量ID、参考信号上报ID等信息确定第二信息。其中，预设门限可以是网络侧设备指示的，也可以是协议规定的，对此本申请实施例不做具体限定。
或者，终端设备根据每一个发送接收点配置的参考信号资源确定第二信息，无需对参考信号资源进行筛选。
在本申请实施例中，终端设备可以基于A1至A3项中的任一项，对目标参考信号资源进行筛选，并基于筛选出来的目标参考信号资源确定第二信息，进而确定终端设备所处的场景信息，确定的场景信息与发送接收点配置的参考信号资源适配，且满足特定的参考信号接收功率，保证了确定出来的场景信息的可靠性，有利于提升最终确定出来的第一模型的可靠性，从而保证了在终端设备移动的过程中，终端设备中运行的机器学习模型能够始终与发送接收点配置的参考信号资源适配。
可选地，所述资源信息包括以下至少一项：
参考信号接收功率；
参考信号资源标识；
波束标识；
波束方向。
在本申请实施例中，终端设备可以根据目标参考信号资源(包括A1至A3中的至少一项)的参考信号接收功率、参考信号资源表示、波束标识、波束方向等资源信息确定第二信息。
在本申请的另一种可选实施例中，所述第一设备获取所述终端设备所处的场景信息，包括：
步骤S61、所述第一设备获取所述终端设备的位置信息，所述位置信息与所述终端设备所处的场景信息相关联；
步骤S62、所述第一设备根据所述位置信息，以及位置坐标与场景信息之间的关联关系，确定所述终端设备的场景信息。
在本申请实施例中，第一设备除了可以根据第二信息确定终端设备的场景信息之外，还可以根据终端设备的位置信息，以及位置坐标与场景信息之间的关联关系，确定终端设备的场景信息。
可以理解的是，终端设备的位置信息可由终端设备根据AI模型或其他定位方法确定，如卫星定位，GPS定位系统、北斗定位系统、蓝牙定位、雷达定位，以及其他基于移动通信网络的定位方法，如基于NR系统、LTE系统的定位方法等。
位置坐标与场景信息之间的关联关系，可以由网络侧设备确定，也可以由协议规定，还可以由第二设备发送给第一设备，对此，本申请实施例不做具体限定。需要说明的是，第二设备可以是网络侧设备，也可以是终端设备的高层。例如，在第一设备为接入网设备的情况下，比如基站，第二设备可以是核心网设备；在第一设备为终端设备的情况下，第二设备可以是网络侧设备，或者是终端设备的高层。
可选地，在所述第一设备根据所述位置信息，以及位置坐标与场景信息之间的关联关系，确定所述终端设备的场景信息之前，所述方法还包括：
所述第一设备接收第二设备发送的第三信息，所述第三信息用于指示位置坐标与场景信息之间的关联关系。
在本申请的一种可能的应用场景中，第二设备也可以通过第三信息，将位置坐标与场景信息之间的关联关系指示给第一设备，第一设备接收到第三信息之后，根据终端设备的位置信息以及位置坐标与场景信息之间的关联关系，就可以确定出终端设备所处的场景信息，进而根据场景信息以及机器学习模型与场景信息之间的关联关系，确定第一模型。
或者，第一设备将确定出的场景信息，例如场景ID、区域ID、数据集ID等发送给第二设备，由第二设备根据第一设备上报的场景信息确定与之相匹配的机器学习模型并指示给第一设备。
可选地，所述第一设备获取所述终端设备的位置信息，包括：
在所述第一设备为终端设备的情况下，所述第一设备基于定位技术确定当前的位置信息；
在所述第一设备为网络侧设备的情况下，所述第一设备接收所述终端设备发送的第四信息，所述第四信息用于指示所述终端设备的位置信息。
参照图7，示出了本申请实施例提供的一种模型确定方法的流程图，如图7所示，如果第一设备为终端设备，那么终端设备的位置信息可以由终端设备自行根据AI模型或其他定位方法确定，如卫星定位，GPS定位系统、北斗定位系统、蓝牙定位、雷达定位，以及其他基于移动通信网络的定位方法，如基于NR系统、LTE系统的定位方法等。
终端设备确定出位置信息之后，结合位置坐标与场景信息之间的关联关系，就可以确定出场景信息。或者，终端设备通过第四信息将位置信息上报给网络侧设备，由网络侧设备根据终端设备的位置信息，以及位置坐标与场景之间的关联关系，确定终端设备的场景信息，并通过第一指示将确定出的场景信息指示给终端设备。
终端设备确定出场景信息之后，可以进一步结合机器学习模型与场景信息之间的关联关系，确定第一模型。或者，由网络侧设备基于终端设备上报的位置信息，确定出终端设备的场景信息，并进一步结合机器学习模型与场景信息之间的关联关系，确定出与终端设备的场景信息相关联的机器学习模型，也即第一模型，并通过第三指示将第一模型指示给终端设备。
参照图8，示出了本申请实施例提供的另一种模型确定方法的流程示意图。如图8所示，如果第一设备为网络侧设备，终端设备的位置信息可以由终端设备通过第四信息上报给第一设备。可选地，在第一设备为网络侧设备的情况下，终端设备可以同时向第一设备上报位置信息的获取方法及可靠性或置信度。
网络侧设备接收到终端设备上报的位置信息之后，根据该位置信息，以及位置坐标与场景信息之间的关联关系，就可以确定出终端设备的场景信息。进一步地，网络侧设备基于机器学习模型与场景信息之间的关联关系，就可以确定出与终端设备所处的场景信息相关联的第一模型。
可选地，所述第一设备激活所述第一模型，包括：
所述第一设备在当前运行的第二模型与所述第一模型不匹配的情况下，对所述第二模型去激活，并激活所述第一模型。
在本申请实施例中，如果第一设备中当前运行的第二模型与第一模型不匹配，说明当前运行的第二模型已经无法满足第一设备当前所处的第一场景的数据处理需求，在这种情况下，第一设备可以对第二模型去激活，并激活第一模型。
需要说明的是，本申请中的第一模型、第二模型并不限定为某一个AI模型，换言之，本申请中的第一模型、第二模型均可以包括一个或多个AI模型，也可以是一个AI功能，一个AI功能可以关联一个或多个AI模型。相应地，对第二模型去激活，可以是同时去激活第二模型所包含的一个或多个AI模型，或者是同时去激活第二模型指代的一个或多个AI功能。同样地，对第一模型进行激活，可以是同时激活第一模型所包含的一个或多个AI模型，或者是同时激活第一模型指代的一个或多个AI功能。
此外，去激活操作和激活操作可以是相互独立的，例如，如果第一设备基于第一信息确定的第一模型中包含第一设备中当前运行的机器学习模型，那么说明第一设备中当前运行的机器学习模型是有效的，无需进行去激活操作，在这种情况下，可以保持当前运行的机器学习模型的正常运行，然后对第一模型所包含的AI模型或AI功能中，除当前运行的机器学习模型之外的AI模型和/或AI功能进行激活即可。或者，如果第一模型所包含的AI模型和/或AI功能就仅包含第一设备中当前运行的AI模型和/或AI功能，那就无需再执行去激活操作和激活操作。或者，如果在第一设备中不存在与第一模型所包含的AI模型和/或AI功能相匹配的AI模型和/或AI功能，那么就无法执行激活操作。或者，如果第一设备中当前没有任何AI模型或AI功能正在运行，那么也就无需执行去激活操作。
需要说明的是，在本申请实施例中，如果对某个AI功能去激活，那么该AI功能关联的所有AI模型均失效；同样地，如果激活某个AI功能，那么该AI功能关联的所有AI模型均为有效模型。
本申请实施例通过在当前运行的第二模型与所述第一模型不匹配的情况下，对第二模型去激活，并激活第一模型，从而保证在终端设备移动过程中，第一设备中运行的机器学习模型能够始终与该终端设备所处的场景适配，保障了数据处理的准确度和处理效率。
可选地，在所述第一设备为终端设备的情况下，所述方法还包括：
所述第一设备向网络侧设备发送第五信息。
其中，所述第五信息包括以下至少一项：
所述第一模型的模型标识；
所述第二模型的模型标识；
所述第一模型的激活时间。
在本申请实施例中，终端设备确定出待激活的第一模型之后，可以将去激活的第二模型的模型标识、待激活的第一模型的模型标识，以及第一模型的激活时间中的至少一项通过第五信息发送给网络侧设备。其中，第一模型的激活时间用于指示模型切换的时间，例如，在M个时间单元之后进行模型切换，包括对第二模型去激活、激活第一模型。
综上，本申请实施例提供了一种模型确定方法，将机器学习模型与场景进行了关联，第一设备可以根据终端设备所处的场景信息，以及机器学习模型与场景信息之间的映射关系，确定当前环境中应该应用何种模型；或者，第一设备可以直接根据第一信息中的模型信息确定与当前终端设备所处的场景信息相关联的机器学习模型，并激活该模型。在本申请实施例中，第一设备可以根据第一信息确定应该应用何种模型，从而保证在终端设备移动过程中，终端设备或网络侧设备中运行的机器学习模型能够始终与该终端设备所处的场景适配，保障了数据处理的准确度和处理效率。
本申请实施例提供了一种数据传输方法。参照图9，示出了本申请实施例提供的一种数据传输方法的流程图。该方法应用于第二设备，如图9所示，该方法具体可以包括：
步骤501、第二设备向第一设备发送第六信息。
其中，所述六信息包括以下至少一项：
第三信息，所述第三信息用于指示位置坐标与场景信息之间的关联关系；
第一指示，所述第一指示用于指示终端设备所处的场景信息；
第二指示，所述第二指示用于指示机器学习模型与场景信息之间的映射关系；
第三指示，所述第三指示用于指示与所述终端设备所处的场景信息相关联的机器学习模型。
需要说明的是，本申请实施例中的第二设备可以是网络侧设备，也可以是终端设备的高层。例如，在第一设备为网络侧设备的情况下，比如第一设备为接入网设备，那么第二设备可以是核心网设备；在第一设备为终端设备的情况下，第二设备可以是网络侧设备，或者是终端设备的高层。
第三信息用于指示位置坐标与场景信息之间的关联关系。在本申请的一种可能的应用场景中，第二设备可以通过第三信息，将位置坐标与场景信息之间的关联关系指示给第一设备，第一设备接收到第三信息之后，根据终端设备的位置信息以及位置坐标与场景信息之间的关联关系，就可以确定出终端设备所处的场景信息，进而根据场景信息以及机器学习模型与场景信息之间的关联关系，确定第一模型。
第一指示可以包括但不限于第一设备所处场景的场景标识(scenario ID)、场景信息(scenario information)、场景类别(scenario category)、区域标识(area ID)、区域信息(area information)、区域类别(area category)、数据集标识(dataset ID)、数据集信息(dataset information)、数据集类别(dataset category)等。其中，场景或区域或数据集的颗粒度可以是小区，在一种可能的实现方式中，可以将场景ID、区域ID、数据集ID与一个或多个小区的物理小区标识(Physical Cell Identifier，PCI)关联，从而根据第一设备所处的小区确定第一设备对应的场景ID、区域ID和数据集ID。在另一种可能的实现方式中，场景或区域或数据集的颗粒度也可以小于小区，比如AI定位，一个场景可以是小区内的一个厂房、一栋楼甚至是一栋楼里的某一层。一个机器学习模型可以对应一个或多个场景、区域或数据集。
在本申请实施例中，机器学习模型可以由第二设备训练，第二设备中记录有各个机器学习模型的模型标识和场景信息之间的关联关系。或者，机器学习模型由第三方服务器训练，第三方服务器将训练好的机器学习模型发送给第一设备，并将机器学习模型和场景信息之间的关联关系发送给第一设备和/或第二设备。
第二设备可以通过第二指示将机器学习模型与场景信息之间的关联关系发送给第一设备，以便第一设备基于第二指示确定第一模型。
或者，第二设备也可以根据终端设备所处的场景信息，以及机器学习模型与场景信息之间的位置关系确定出与所述终端设备所处的场景信息相关联的机器学习模型，并通过第三指示将该模型的模型信息指示给第一设备。第三指示可以包括与所述终端设备所处的场景信息相关联的机器学习模型的模型信息，如模型标识。
综上，本申请实施例提供了一种数据传输方法，第二设备可以通过第六信息将位置坐标与场景信息之间的关联关系、终端设备所处的场景信息、机器学习模型与场景信息之间的映射关系、与终端设备所处的场景信息相关联的机器学习模型的模型信息中的至少一项发送给第一设备，以便第一设备基于接收到的第六信息确定在终端设备当前所处的场景中应该应用何种模型。
本申请实施例提供的模型确定方法，执行主体可以为模型确定装置。本申请实施例中以模型确定装置执行模型确定方法为例，说明本申请实施例提供的模型确定装置。
本申请实施例提供了一种模型确定装置。参照图10，示出了本申请实施例提供了一种模型确定装置的结构框图，该装置可应用于第一设备。如图10所示，该装置具体可以包括：
模型确定模块601，用于基于第一信息确定第一模型；
模型激活模块602，用于激活所述第一模型；
其中，所述第一信息包括以下任一项：
终端设备所处的场景信息，以及机器学习模型与场景信息之间的映射关系；所述第一设备为所述终端设备或网络侧设备；
与所述终端设备所处的场景信息相关联的机器学习模型的模型信息。
可选地，所述装置还包括：
场景信息获取模块，用于获取所述终端设备所处的场景信息；
第一关系获取模块，用于获取机器学习模型与场景信息之间的映射关系。
可选地，所述场景信息获取模块，包括：
第一获取子模块，用于获取第二信息，所述第二信息用于指示所述终端设备的通信信息，所述第二信息与所述终端设备所处的场景信息相关联；
第一确定子模块，用于根据所述第二信息确定所述终端设备的场景信息。
可选地，在所述第一设备为终端设备的情况下，所述第一获取子模块，包括：
测量单元，用于对参考信号进行测量，并基于测量结果确定第二信息。
可选地，在所述第一设备为网络侧设备的情况下，所述第一获取子模块，包括：
第一接收单元，用于接收所述终端设备发送的第二信息。
可选地，所述第一确定子模块，包括：
第一获取单元，用于第一设备获取通信信息与场景信息之间的关联关系；
第一确定单元，用于根据所述第二信息，以及所通信信息与场景信息之间的关联关系，确定所述终端设备的场景信息。
可选地，所述第一确定子模块，包括：
第一发送单元，用于将所述第二信息发送给网络侧设备；
第二接收单元，用于接收所述网络侧设备发送的第一指示；所述第一指示用于指示所述第一设备的场景信息。
可选地，所述场景信息获取模块，包括：
第二获取子模块，用于获取所述终端设备的位置信息，所述位置信息与所述终端设备所处的场景信息相关联；
第二确定子模块，用于根据所述位置信息，以及位置坐标与场景信息之间的关联关系，确定所述终端设备的场景信息。
可选地，所述场景信息获取模块还包括：
第一接收子模块，用于接收第二设备发送的第三信息，所述第三信息用于指示位置坐标与场景信息之间的关联关系。
可选地，所述第二获取子模块，包括：
第二确定单元，用于在所述第一设备为终端设备的情况下，基于定位技术确定当前的位置信息；
第三接收单元，用于在所述第一设备为网络侧设备的情况下，接收所述终端设备发送的第四信息，所述第四信息用于指示所述终端设备的位置信息。
可选地，所述场景信息获取模块，包括：
第二接收子模块，用于接收第二设备发送的第一指示和第二指示，所述第一指示用于指示所述终端设备的场景信息；所述第二指示用于指示机器学习模型与场景信息之间的映射关系。
可选地，所述装置还包括：
第三指示接收模块，用于接收第二设备发送的第三指示，所述第三指示用于指示与所述终端设备所处的场景信息相关联的机器学习模型。
可选地，所述测量单元，具体用于：
在接收到第四指示的情况下，对第一参考信号进行测量；所述第四指示用于指示所述第一设备对至少一种参考信号进行测量；
基于所述第一参考信号的第一测量结果确定所述第二信息。
可选地，所述测量单元，具体用于：
接收参考点发送的第二参考信号；
对所述第二参考信号进行测量，并基于所述第二参考信号的第二测量结果确定所述第二信息。
可选地，所述第二信息包括以下至少一项：
第一通信信息，所述第一参数用于指示所述终端设备的通信资源；
第二通信信息，所述第五参数用于指示所述终端设备所处的通信区域。
可选地，所述第一通信信息包括以下至少一项：
所述第一设备的参考信号信息；
所述第一设备的通信指标信息。
可选地，所述参考信号信息包括以下至少一项：
第一参数，所述第二参数用于指示参考信号资源；
第二参数，所述第三参数用于指示参考信号测量信息；
第三参数，所述第四参数用于指示参考信号上报信息。
可选地，所述通信指标信息包括以下至少一项：
第四参数，所述第一参数用于指示信道质量；
波束信息；
信道状态信息；
多径平均时延；
多径时延扩展。
可选地，所述测量单元，具体用于：
对参考信号进行测量，得到测量结果；
根据所述测量结果确定目标参考信号资源，并根据所述目标参考信号资源的资源信息确定第二信息；
其中，所述目标参考信号资源包括以下至少一项：
每一个发送接收点配置的参考信号资源中的N个第一目标参考信号资源；所述N个第一目标参考信号资源的参考信号接收功率大于同一发送接收点的其他参考信号资源的参考信号接收功率；N为正整数；
从每一个发送接收点配置的参考信号资源中筛选出的第二目标参考信号资源；所述第二目标参考信号资源的参考信号接收功率大于或等于预设门限；
每一个发送接收点配置的参考信号资源。
可选地，所述资源信息包括以下至少一项：
参考信号接收功率；
参考信号资源标识；
波束标识；
波束方向。
可选地，所述模型激活模块，包括：
模型激活子模块，用于在当前运行的第二模型与所述第一模型不匹配的情况下，对所述第二模型去激活，并激活所述第一模型。
可选地，所述装置还包括：
第五信息发送模块，用于向网络侧设备发送第五信息，所述第五信息包括以下至少一项：
所述第一模型的模型标识；
所述第二模型的模型标识；
所述第一模型的激活时间。
本申请实施例中的模型确定装置可以是电子设备，例如具有操作系统的电子设备，也可以是电子设备中的部件，例如集成电路或芯片。
本申请实施例提供的模型确定装置能够实现前述的方法实施例实现的各个过程，并达到相同的技术效果，为避免重复，这里不再赘述。
本申请实施例提供了一种数据传输装置。参照图11，示出了本申请实施例提供了一种数据传输装置的结构框图，该装置可应用于第二设备。如图11所示，该装置具体可以包括：
信息发送模块701，用于向第一设备发送第六信息。
其中，所述六信息包括以下至少一项：
第三信息，所述第三信息用于指示位置坐标与场景信息之间的关联关系；
第一指示，所述第一指示用于指示终端设备的场景信息；
第二指示，所述第二指示用于指示机器学习模型与场景信息之间的映射关系；
第三指示，所述第三指示用于指示与所述终端设备所处的场景信息相关联的机器学习模型。
本申请实施例中的数据传输装置可以是电子设备，例如具有操作系统的电子设备，也可以是电子设备中的部件，例如集成电路或芯片。
本申请实施例提供的数据传输装置能够实现前述的方法实施例实现的各个过程，并达到相同的技术效果，为避免重复，这里不再赘述。
可选的，如图12所示，本申请实施例还提供一种通信设备900，包括处理器901和存储器902，存储器902上存储有可在所述处理器901上运行的程序或指令，例如，该通信设备900为网络侧设备时，该程序或指令被处理器901执行时实现前述的模型确定方法实施例的各个步骤，或者实现前述的数据传输方法实施例的各个步骤，且能达到相同的技术效果。该通信设备900为终端设备时，该程序或指令被处理器901执行时实现前述的模型确定方法实施例的各个步骤，或者实现前述的数据传输方法实施例的各个步骤，且能达到相同的技术效果，为避免重复，这里不再赘述。
如图13所示，为实现本申请实施例的一种终端设备的硬件结构示意图。
该终端设备1000包括但不限于：射频单元1001、网络模块1002、音频输出单元1003、输入单元1004、传感器1005、显示单元1006、用户输入单元1007、接口单元1008、存储器1009以及处理器1010等中的至少部分部件。
本领域技术人员可以理解，终端设备1000还可以包括给各个部件供电的电源(比如电池)，电源可以通过电源管理系统与处理器1010逻辑相连，从而通过电源管理系统实现管理充电、放电，以及功耗管理等功能。图13中示出的终端设备结构并不构成对终端设备的限定，终端设备可以包括比图示更多或更少的部件，或者组合某些部件，或者不同的部件布置，在此不再赘述。
应理解的是，本申请实施例中，输入单元1004可以包括图形处理单元(Graphics Processing Unit，GPU)10041和麦克风10042，图形处理器10041对在视频捕获模式或图像捕获模式中由图像捕获装置(如摄像头)获得的静态图片或视频的图像数据进行处理。显示单元1006可包括显示面板10061，可以采用液晶显示器、有机发光二极管等形式来配置显示面板10061。用户输入单元1007包括触控面板10071以及其他输入设备10072中的至少一种。触控面板10071，也称为触摸屏。触控面板10071可包括触摸检测装置和触摸控制器两个部分。其他输入设备10072可以包括但不限于物理键盘、功能键(比如音量控制按键、开关按键等)、轨迹球、鼠标、操作杆，在此不再赘述。
本申请实施例中，射频单元1001接收来自网络侧设备的下行数据后，可以传输给处理器1010进行处理；另外，射频单元1001可以向网络侧设备发送上行数据。通常，射频单元1001包括但不限于天线、放大器、收发信机、耦合器、低噪声放大器、双工器等。
存储器1009可用于存储软件程序或指令以及各种数据。存储器1009可主要包括存储程序或指令的第一存储区和存储数据的第二存储区，其中，第一存储区可存储操作系统、至少一个功能所需的应用程序或指令(比如声音播放功能、图像播放功能等)等。此外，存储器1009可以包括易失性存储器或非易失性存储器，或者，存储器1009可以包括易失性和非易失性存储器两者。其中，非易失性存储器可以是只读存储器(Read-Only Memory，ROM)、可编程只读存储器(Programmable ROM，PROM)、可擦除可编程只读存储器(Erasable PROM，EPROM)、电可擦除可编程只读存储器(Electrically EPROM，EEPROM)或闪存。易失性存储器可以是随机存取存储器(Random Access Memory，RAM)，静态随机存取存储器(Static RAM，SRAM)、动态随机存取存储器(Dynamic RAM，DRAM)、同步动态随机存取存储器(Synchronous DRAM，SDRAM)、双倍数据速率同步动态随机存取存储器(Double Data Rate SDRAM，DDRSDRAM)、增强型同步动态随机存取存储器(Enhanced SDRAM，ESDRAM)、同步连接动态随机存取存储器(Synch link DRAM，SLDRAM)和直接内存总线随机存取存储器(Direct Rambus RAM，DRRAM)。本申请实施例中的存储器1009包括但不限于这些和任意其它适合类型的存储器。
处理器1010可包括一个或多个处理单元；可选的，处理器1010集成应用处理器和调制解调处理器，其中，应用处理器主要处理涉及操作系统、用户界面和应用程序等的操作，调制解调处理器主要处理无线通信信号，如基带处理器。可以理解的是，上述调制解调处理器也可以不集成到处理器1010中。
本申请实施例还提供一种网络侧设备，包括处理器和通信接口，所述通信接口和所述处理器耦合，所述处理器用于运行程序或指令，实现前述方法实施例的步骤。该网络侧设备实施例与上述网络侧设备方法实施例对应，上述方法实施例中网络侧设备的各个实施过程和实现方式均可适用于该网络侧设备实施例中，且能达到相同的技术效果。
具体地，本申请实施例还提供一种网络侧设备，如图14所示，该网络侧设备1100包括：天线111、射频装置112、基带装置113、处理器114和存储器115。天线111与射频装置112连接。在上行方向上，射频装置112通过天线111接收信息，将接收的信息发送给基带装置113进行处理。在下行方向上，基带装置113对要发送的信息进行处理，并发送给射频装置112，射频装置112对收到的信息进行处理后经过天线111发送出去。
以上实施例中网络侧设备执行的方法可以在基带装置113中实现，该基带装置113包括基带处理器。
基带装置113例如可以包括至少一个基带板，该基带板上设置有多个芯片，如图14所示，其中一个芯片例如为基带处理器，通过总线接口与存储器115连接，以调用存储器115中的程序，执行以上方法实施例中所示的网络设备操作。
该网络侧设备还可以包括网络接口116，该接口例如为通用公共无线接口(common public radio interface，CPRI)。
具体地，本发明实施例的网络侧设备1100还包括：存储在存储器115上并可在处理器114上运行的指令或程序，处理器114调用存储器115中的指令或程序执行图10或图11中各模块执行的方法，并达到相同的技术效果，为避免重复，故不在此赘述。
本申请实施例还提供了一种网络侧设备。如图15所示，该网络侧设备1200包括：处理器1201、网络接口1202和存储器1203。其中，网络接口1202例如为通用公共无线接口(common public radio interface，CPRI)。
具体地，本发明实施例的网络侧设备1200还包括：存储在存储器1203上并可在处理器1201上运行的指令或程序，处理器1201调用存储器1203中的指令或程序执行图10或图11所示各模块执行的方法，并达到相同的技术效果，为避免重复，故不在此赘述。
本申请实施例还提供一种可读存储介质，所述可读存储介质上存储有程序或指令，该程序或指令被处理器执行时实现前述方法实施例的各个过程，且能达到相同的技术效果，为避免重复，这里不再赘述。
其中，所述处理器为上述实施例中所述的终端设备中的处理器。所述可读存储介质，包括计算机可读存储介质，如计算机只读存储器ROM、随机存取存储器RAM、磁碟或者光盘等。
本申请实施例另提供了一种芯片，所述芯片包括处理器和通信接口，所述通信接口和所述处理器耦合，所述处理器用于运行程序或指令，实现前述方法实施例的各个过程，且能达到相同的技术效果，为避免重复，这里不再赘述。
应理解，本申请实施例提到的芯片还可以称为系统级芯片，系统芯片，芯片系统或片上系统芯片等。
本申请实施例另提供了一种计算机程序/程序产品，所述计算机程序/程序产品被存储在存储介质中，所述计算机程序/程序产品被至少一个处理器执行以实现前述方法实施例的各个过程，且能达到相同的技术效果，为避免重复，这里不再赘述。
本申请实施例还提供了一种模型确定系统，包括：第一设备及第二设备，所述第一设备可用于执行如上第一方面所述的模型确定方法的步骤，所述第二设备可用于执行如上第二方面所述的数据传输方法的步骤。
需要说明的是，在本文中，术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、物品或者装置不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、物品或者装置所固有的要素。在没有更多限制的情况下，由语句“包括一个……”限定的要素，并不排除在包括该要素的过程、方法、物品或者装置中还存在另外的相同要素。此外，需要指出的是，本申请实施方式中的方法和装置的范围不限按示出或讨论的顺序来执行功能，还可包括根据所涉及的功能按基本同时的方式或按相反的顺序来执行功能，例如，可以按不同于所描述的次序来执行所描述的方法，并且还可以添加、省去或组合各种步骤。另外，参照某些示例所描述的特征可在其他示例中被组合。
通过以上的实施方式的描述，本领域的技术人员可以清楚地了解到上述实施例方法可借助软件加必需的通用硬件平台的方式来实现，当然也可以通过硬件，但很多情况下前者是更佳的实施方式。基于这样的理解，本申请的技术方案本质上或者说对现有技术做出贡献的部分可以以计算机软件产品的形式体现出来，该计算机软件产品存储在一个存储介质(如ROM/RAM、磁碟、光盘)中，包括若干指令用以使得一台终端(可以是手机，计算机，服务器，空调器，或者网络设备等)执行本申请各个实施例所述的方法。
上面结合附图对本申请的实施例进行了描述，但是本申请并不局限于上述的具体实施方式，上述的具体实施方式仅仅是示意性的，而不是限制性的，本领域的普通技术人员在本申请的启示下，在不脱离本申请宗旨和权利要求所保护的范围情况下，还可做出很多形式，均属于本申请的保护之内。

Claims (25)

  1. 一种模型确定方法，其中，包括：
    第一设备基于第一信息确定第一模型；
    所述第一设备激活所述第一模型；
    其中，所述第一信息包括以下任一项：
    终端设备所处的场景信息，以及机器学习模型与场景信息之间的映射关系；所述第一设备为所述终端设备或网络侧设备；
    与所述终端设备所处的场景信息相关联的机器学习模型的模型信息。
  2. 根据权利要求1所述的方法，其中，在所述第一设备基于第一信息确定第一模型之前，所述方法还包括：
    所述第一设备获取所述终端设备所处的场景信息；
    所述第一设备获取机器学习模型与场景信息之间的映射关系。
  3. 根据权利要求2所述的方法，其中，所述第一设备获取所述终端设备所处的场景信息，包括：
    所述第一设备获取第二信息，所述第二信息用于指示所述终端设备的通信信息，所述第二信息与所述终端设备所处的场景信息相关联；
    所述第一设备根据所述第二信息确定所述终端设备的场景信息。
  4. 根据权利要求3所述的方法，其中，在所述第一设备为终端设备的情况下，所述第一设备获取第二信息，包括：
    所述第一设备对参考信号进行测量，并基于测量结果确定第二信息。
  5. 根据权利要求3所述的方法，其中，在所述第一设备为网络侧设备的情况下，所述第一设备获取第二信息，包括：
    所述第一设备接收所述终端设备发送的第二信息。
  6. 根据权利要求3至5所述的方法，其中，所述第一设备根据所述第二信息确定所述终端设备的场景信息，包括：
    所述第一设备获取通信信息与场景信息之间的关联关系；
    所述第一设备根据所述第二信息，以及所通信信息与场景信息之间的关联关系，确定所述终端设备的场景信息。
  7. 根据权利要求4所述的方法，其中，所述第一设备根据所述第二信息确定所述终端设备的场景信息，包括：
    所述第一设备将所述第二信息发送给网络侧设备；
    所述第一设备接收所述网络侧设备发送的第一指示；所述第一指示用于指示所述第一设备的场景信息。
  8. 根据权利要求2所述的方法，其中，所述第一设备获取所述终端设备所处的场景信息，包括：
    所述第一设备获取所述终端设备的位置信息，所述位置信息与所述终端设备所处的场景信息相关联；
    所述第一设备根据所述位置信息，以及位置坐标与场景信息之间的关联关系，确定所述终端设备的场景信息。
  9. 根据权利要求8所述的方法，其中，在所述第一设备根据所述位置信息，以及位置坐标与场景信息之间的关联关系，确定所述终端设备的场景信息之前，所述方法还包括：
    所述第一设备接收第二设备发送的第三信息，所述第三信息用于指示位置坐标与场景信息之间的关联关系。
  10. 根据权利要求8所述的方法，其中，所述第一设备获取所述终端设备的位置信息，包括：
    在所述第一设备为终端设备的情况下，所述第一设备基于定位技术确定当前的位置信息；
    在所述第一设备为网络侧设备的情况下，所述第一设备接收所述终端设备发送的第四信息，所述第四信息用于指示所述终端设备的位置信息。
  11. 根据权利要求2所述的方法，其中，所述第一设备获取所述终端设备所处的场景信息，包括：
    所述第一设备接收第二设备发送的第一指示和第二指示，所述第一指示用于指示所述终端设备的场景信息；所述第二指示用于指示机器学习模型与场景信息之间的映射关系。
  12. 根据权利要求1所述的方法，其中，在所述第一设备基于第一信息确定第一模型之前，所述方法还包括：
    所述第一设备接收第二设备发送的第三指示，所述第三指示用于指示与所述终端设备所处的场景信息相关联的机器学习模型。
  13. 根据权利要求4所述的方法，其中，所述第一设备对参考信号进行测量，并基于测量结果确定第二信息，包括：
    所述第一设备在接收到第四指示的情况下，对第一参考信号进行测量；所述第四指示用于指示所述第一设备对至少一种参考信号进行测量；
    所述第一设备基于所述第一参考信号的第一测量结果确定所述第二信息。
  14. 根据权利要求4所述的方法，其中，所述第一设备对参考信号进行测量，并基于测量结果确定第二信息，包括：
    所述第一设备接收参考点发送的第二参考信号；
    所述第一设备对所述第二参考信号进行测量，并基于所述第二参考信号的第二测量结果确定所述第二信息。
  15. 根据权利要求3至7、13、14所述的方法，其中，所述第二信息包括以下至少一项：
    第一通信信息，所述第一参数用于指示所述终端设备的通信资源；
    第二通信信息，所述第五参数用于指示所述终端设备所处的通信区域。
  16. 根据权利要求15所述的方法，其中，所述第一通信信息包括以下至少一项：
    所述第一设备的参考信号信息；
    所述第一设备的通信指标信息。
  17. 根据权利要求16所述的方法，其中，所述参考信号信息包括以下至少一项：
    第一参数，所述第二参数用于指示参考信号资源；
    第二参数，所述第三参数用于指示参考信号测量信息；
    第三参数，所述第四参数用于指示参考信号上报信息。
  18. 根据权利要求4所述的方法，其中，所述第一设备对参考信号进行测量，并基于测量结果确定第二信息，包括：
    所述第一设备对参考信号进行测量，得到测量结果；
    所述第一设备根据所述测量结果确定目标参考信号资源，并根据所述目标参考信号资源的资源信息确定第二信息；
    其中，所述目标参考信号资源包括以下至少一项：
    每一个发送接收点配置的参考信号资源中的N个第一目标参考信号资源；所述N个第一目标参考信号资源的参考信号接收功率大于同一发送接收点的其他参考信号资源的参考信号接收功率；N为正整数；
    从每一个发送接收点配置的参考信号资源中筛选出的第二目标参考信号资源；所述第二目标参考信号资源的参考信号接收功率大于或等于预设门限；
    每一个发送接收点配置的参考信号资源。
  19. 根据权利要求1所述的方法，其中，所述第一设备激活所述第一模型，包括：
    所述第一设备在当前运行的第二模型与所述第一模型不匹配的情况下，对所述第二模型去激活，并激活所述第一模型。
  20. 根据权利要求19所述的方法，其中，在所述第一设备为终端设备的情况下，所述方法还包括：
    所述第一设备向网络侧设备发送第五信息，所述第五信息包括以下至少一项：
    所述第一模型的模型标识；
    所述第二模型的模型标识；
    所述第一模型的激活时间。
  21. 一种数据传输方法，其中，包括：
    第二设备向第一设备发送第六信息，所述六信息包括以下至少一项：
    第三信息，所述第三信息用于指示位置坐标与场景信息之间的关联关系；
    第一指示，所述第一指示用于指示终端设备的场景信息；
    第二指示，所述第二指示用于指示机器学习模型与场景信息之间的映射关系；
    第三指示，所述第三指示用于指示与所述终端设备所处的场景信息相关联的机器学习模型。
  22. 一种模型确定装置，其中，应用于第一设备，所述装置包括：
    模型确定模块，用于基于第一信息确定第一模型；
    模型激活模块，用于激活所述第一模型；
    其中，所述第一信息包括以下任一项：
    终端设备所处的场景信息，以及机器学习模型与场景信息之间的映射关系；所述第一设备为所述终端设备或网络侧设备；
    与所述终端设备所处的场景信息相关联的机器学习模型的模型信息。
  23. 一种数据传输装置，其中，应用于第二设备，所述装置包括：
    信息发送模块，用于向第一设备发送第六信息，所述六信息包括以下至少一项：
    第三信息，所述第三信息用于指示位置坐标与场景信息之间的关联关系；
    第一指示，所述第一指示用于指示终端设备的场景信息；
    第二指示，所述第二指示用于指示机器学习模型与场景信息之间的映射关系；
    第三指示，所述第三指示用于指示与所述终端设备所处的场景信息相关联的机器学习模型。
  24. 一种通信设备，其中，包括处理器和存储器，所述存储器存储可在所述处理器上运行的程序或指令，所述程序或指令被所述处理器执行时实现如权利要求1至20任一项所述的模型确定方法的步骤，或者实现如权利要求21所述的数据传输方法的步骤。
  25. 一种可读存储介质，其中，所述可读存储介质上存储程序或指令，所述程序或指令被处理器执行时实现如权利要求1至20任一项所述的模型确定方法，或者实现如权利要求21所述的数据传输方法的步骤。
PCT/CN2024/132393 2023-11-20 2024-11-15 模型确定方法、装置及通信设备 Pending WO2025108195A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202311550325.2A CN120021208A (zh) 2023-11-20 2023-11-20 模型确定方法、装置及通信设备
CN202311550325.2 2023-11-20

Publications (1)

Publication Number Publication Date
WO2025108195A1 true WO2025108195A1 (zh) 2025-05-30

Family

ID=95704667

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2024/132393 Pending WO2025108195A1 (zh) 2023-11-20 2024-11-15 模型确定方法、装置及通信设备

Country Status (2)

Country Link
CN (1) CN120021208A (zh)
WO (1) WO2025108195A1 (zh)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2019240771A1 (en) * 2018-06-12 2019-12-19 Nokia Technologies Oy User device positioning
CN113938232A (zh) * 2020-07-13 2022-01-14 华为技术有限公司 通信的方法及通信装置
CN114826941A (zh) * 2022-04-27 2022-07-29 中国电子科技集团公司第五十四研究所 一种无线通信网络ai模型配置方法
CN116234000A (zh) * 2021-11-30 2023-06-06 维沃移动通信有限公司 定位方法及通信设备
CN116567806A (zh) * 2022-01-29 2023-08-08 维沃移动通信有限公司 基于人工智能ai模型的定位方法及通信设备

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2019240771A1 (en) * 2018-06-12 2019-12-19 Nokia Technologies Oy User device positioning
CN113938232A (zh) * 2020-07-13 2022-01-14 华为技术有限公司 通信的方法及通信装置
CN116234000A (zh) * 2021-11-30 2023-06-06 维沃移动通信有限公司 定位方法及通信设备
CN116567806A (zh) * 2022-01-29 2023-08-08 维沃移动通信有限公司 基于人工智能ai模型的定位方法及通信设备
CN114826941A (zh) * 2022-04-27 2022-07-29 中国电子科技集团公司第五十四研究所 一种无线通信网络ai模型配置方法

Also Published As

Publication number Publication date
CN120021208A (zh) 2025-05-20

Similar Documents

Publication Publication Date Title
EP4472306A1 (en) Positioning method based on artificial intelligence (ai) model, and communication device
WO2023098661A1 (zh) 定位方法及通信设备
WO2023134650A1 (zh) 信息交互方法、装置及通信设备
WO2023103911A1 (zh) 测量方法、装置、设备及存储介质
US20250227507A1 (en) Ai model processing method and apparatus, and communication device
WO2023125951A1 (zh) 通信模型配置方法、装置和通信设备
US20250193833A1 (en) Data collection method and apparatus
WO2024067434A1 (zh) Rs配置方法、装置、终端及网络侧设备
WO2024083004A1 (zh) Ai模型配置方法、终端及网络侧设备
WO2024125525A1 (zh) Ai算力上报方法、终端及网络侧设备
WO2025108195A1 (zh) 模型确定方法、装置及通信设备
WO2024027576A1 (zh) 一种ai网络模型的性能监督方法、装置和通信设备
CN118785189A (zh) Csi预测性能的监测方法、装置、终端及网络侧设备
WO2024208167A1 (zh) 信息处理方法、信息处理装置、终端及网络侧设备
WO2025108390A1 (zh) 基于ai模型的定位方法、装置、设备及可读存储介质
WO2025092998A1 (zh) 信息传输方法、装置及设备
WO2025092999A1 (zh) 模型性能监督方法、装置及设备
WO2025140432A1 (zh) 信息上报方法及装置
WO2024217405A1 (zh) 终端定位方法、装置、终端、网络侧设备及介质
WO2024208136A1 (zh) 信息传输方法、信息处理方法、装置、终端及网络侧设备
WO2025031325A1 (zh) 基于参考模型的通信方法及设备
WO2025185549A1 (zh) 信息传输方法、装置及相关设备
WO2025031405A1 (zh) 通信设备的测试方法和装置、终端、网络侧设备及介质
WO2025036223A1 (zh) 信息上报方法、信息接收方法及设备
WO2025036188A1 (zh) 信息传输方法、装置、终端及网络侧设备

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 24893353

Country of ref document: EP

Kind code of ref document: A1