WO2025130422A1 - Information processing method and apparatus, terminal side device and network side device - Google Patents

Abstract

The present disclosure provides an information processing method and apparatus, a terminal side device and a network side device. The method comprises: a terminal side device sends a first message to a network side device, wherein the first message carries at least one of the following information: first indication information, used for indicating a first object; first information associated with the first object; a cell identifier associated with the first object. The first object comprises a first artificial intelligence (AI) model and/or a first AI function, and the first information is related to input and/or output.

Description

Information processing method, device, terminal side equipment and network side equipment

This disclosure claims the priority of the Chinese patent application filed with the China Patent Office on December 20, 2023, with application number 202311762806.X and application name “Information processing method, device, terminal side device and network side device”, all contents of which are incorporated herein by reference.

Technical Field

The present disclosure relates to the field of communication technology, and in particular to an information processing method, apparatus, terminal side equipment and network side equipment.

Background Art

In the New Radio (NR) system, in order to combat the path loss in high-frequency scenarios, the transmitter and receiver obtain matching beam pairs through beam management (BM) to improve beamforming gain. In the current beam management process, the base station needs to send reference signals on all transmit beams (Tx beams), resulting in a large consumption of reference signal resources. At the same time, the terminal (User Equipment, UE) side needs to measure the reference signal sent on each Tx beam for all receive beams (Rx beams), resulting in a large measurement overhead.

In order to reduce reference signal resource consumption, measurement overhead and latency, consider using artificial intelligence (AI) or machine learning (ML) technology to predict the optimal beam (or beam pair) based on the measurement results of some beams (or beam pairs) or historical beam (or beam pair) measurements. Since the angle, shape and other information of the transmitted beam are proprietary information on the network side and cannot be informed to the UE, when using AI or ML technology to implement beam management for the AI model deployed on the UE side, there may be inconsistencies between the input and/or output of the model training phase and the input and/or output of the inference phase, which will cause the AI model to be unavailable, and thus the beam management performance cannot be guaranteed. However, there is currently no specific solution for how network-side devices can determine whether an AI model or AI function is available.

Summary of the invention

The present disclosure provides an information processing method, apparatus, terminal-side equipment, and network-side equipment, which solve the problem that there is currently no specific solution for how network-side equipment can determine whether an AI model or AI function is available.

An embodiment of the present disclosure provides an information processing method, including:

The terminal side device sends a first message to the network side device; wherein the first message carries at least one of the following information:

First indication information, used to indicate a first object; the first object includes a first AI model and/or a first AI function;

first information associated with the first object, the first information being related to input and/or output;

A cell identifier associated with the first object.

In some embodiments, the terminal side device sends a first message to the network side device, including:

The terminal side device receives a second message sent by the network side device; wherein the second message carries a cell identifier;

The terminal side device sends the first message to the network side device according to the cell identifier; wherein the first AI model is an AI model associated with the cell identifier, and/or the first AI function is an AI function associated with the cell identifier.

In some embodiments, the terminal side device sends the first message to the network side device according to the cell identifier, including:

The terminal side device determines a first object associated with the cell identifier from at least one existing AI model and/or AI function;

The terminal side device sends the first message to the network side device.

In some embodiments, the terminal side device sends a first message to the network side device, including:

The terminal side device receives a third message sent by the network side device; wherein the third message carries a cell identifier and the first information;

The terminal side device sends the first message to the network side device based on the cell identifier and the first information; wherein the first AI model is an AI model associated with the cell identifier and the first information, and/or the first AI function is an AI function associated with the cell identifier and the first information.

In some embodiments, the terminal side device sends the first message to the network side device according to the cell identifier and the first information, including:

The terminal side device determines, from at least one existing AI model and/or AI function, a first object associated with the cell identifier and the first information;

The terminal side device sends the first message to the network side device.

In some embodiments, before the terminal side device sends the first message to the network side device, the method further includes:

The terminal side device receives the reference signal sent by the network side device;

The terminal side device performs measurement according to the reference signal to obtain a measurement result;

The terminal side device performs model training according to the measurement result to determine a first AI model;

The terminal side device establishes a correspondence between the first AI model and the cell identifier and/or the first information, and/or establishes a correspondence between the first AI function corresponding to the first AI model and the cell identifier and/or the first information.

In some embodiments, before the terminal side device establishes a correspondence between the first AI model and the cell identifier and/or the first information, and/or before establishing a correspondence between the first AI function corresponding to the first AI model and the cell identifier and/or the first information, it also includes:

The terminal side device receives a fourth message sent by the network side device; wherein the fourth message carries a cell identifier and/or the first information.

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

Beam codebook identifier;

Time-related information of the reference signal.

In some embodiments, the time-related information of the reference signal includes:

The time stamp of the reference signal;

The time offset value of the reference signal.

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

The first AI model that is already available or supported by the terminal device;

The first AI function that is already available or supported by the terminal device;

The first AI model available for network-side devices;

The first AI function available for network-side devices.

In some embodiments, the information processing method further includes:

The terminal side device performs model recognition of the first AI model;

and/or,

The terminal side device performs function identification of the first AI function.

The present disclosure provides an information processing method, including:

The network side device receives the first message sent by the terminal side device;

The network side device performs relevant processing of the first object according to the first message;

The first message carries at least one of the following information:

First indication information, used to indicate a first object; the first object includes a first AI model and/or a first AI function;

first information associated with the first object, the first information being related to input and/or output;

A cell identifier associated with the first object.

In some embodiments, before the network side device receives the first message sent by the terminal side device, the method further includes:

The network side device sends a second message to the terminal side device; wherein the second message carries a cell identifier; the first AI model is an AI model associated with the cell identifier, and/or the first AI function is an AI function associated with the cell identifier.

In some embodiments, before the network side device receives the first message sent by the terminal side device, the method further includes:

The network side device sends a third message to the terminal side device; wherein the third message carries a cell identifier and first information; the first AI model is an AI model associated with the cell identifier and the first information, and/or the first AI function is an AI function associated with the cell identifier and the first information.

In some embodiments, before the network side device receives the first message sent by the terminal side device, the method further includes:

The network side device sends a reference signal and/or a fourth message to the terminal side device; wherein the reference signal is used to train the first AI model and/or train the AI model corresponding to the first AI function; and the fourth message carries a cell identifier and/or the first information.

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

Beam codebook identifier;

Time-related information of the reference signal.

In some embodiments, the time-related information of the reference signal includes:

The time stamp of the reference signal;

The time offset value of the reference signal.

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

The first AI model that is already available or supported by the terminal device;

The first AI function that is already available or supported by the terminal device;

The first AI model available for network-side devices;

The first AI function available for network-side devices.

In some embodiments, the network side device performs related processing of the first object according to the first message, including:

In the case where the first message carries the first information, the network side device determines a first object associated with the first information, and performs relevant processing of the first object;

or,

In the case where the first message carries the cell identifier and the first information, the network side device determines a first object associated with the cell identifier and the first information, and performs relevant processing of the first object.

In some embodiments, the performing of the related processing of the first object includes at least one of the following:

activating or deactivating the first object;

activating or deactivating configuration information related to the first object;

Send configuration information related to the first object.

The embodiment of the present disclosure provides an information processing device, including a memory, a transceiver, and a processor;

The memory is used to store computer programs; the transceiver is used to send and receive data under the control of the processor; the processor is used to read the computer program in the memory and perform the following operations:

Sending a first message to a network side device; wherein the first message carries at least one of the following information:

First indication information, used to indicate a first object; the first object includes a first AI model and/or a first AI function;

first information associated with the first object, the first information being related to input and/or output;

A cell identifier associated with the first object.

In some embodiments, the processor is configured to read the computer program in the memory and perform the following operations:

Receiving a second message sent by the network side device; wherein the second message carries a cell identifier;

According to the cell identifier, the first message is sent to the network side device; wherein the first AI model is an AI model associated with the cell identifier, and/or the first AI function is an AI function associated with the cell identifier.

In some embodiments, the processor is configured to read the computer program in the memory and perform the following operations:

Determine a first object associated with the cell identifier from at least one existing AI model and/or AI function;

Send the first message to the network side device.

In some embodiments, the processor is configured to read the computer program in the memory and perform the following operations:

receiving a third message sent by the network side device; wherein the third message carries a cell identifier and the first information;

According to the cell identifier and the first information, the first message is sent to the network side device; wherein the first AI model is an AI model associated with the cell identifier and the first information, and/or the first AI function is an AI function associated with the cell identifier and the first information.

In some embodiments, the processor is configured to read the computer program in the memory and perform the following operations:

Determine, from at least one existing AI model and/or AI function, a first object associated with the cell identifier and the first information;

Send the first message to the network side device.

In some embodiments, the processor is configured to read the computer program in the memory and perform the following operations:

Receiving a reference signal sent by the network side device;

Perform measurement according to the reference signal to obtain a measurement result;

Perform model training according to the measurement results to determine a first AI model;

A correspondence between the first AI model and the cell identifier and/or the first information is established, and/or a correspondence between the first AI function corresponding to the first AI model and the cell identifier and/or the first information is established.

In some embodiments, the processor is configured to read the computer program in the memory and perform the following operations:

Receive a fourth message sent by the network side device; wherein the fourth message carries a cell identifier and/or the first information.

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

Beam codebook identifier;

Time-related information of the reference signal.

In some embodiments, the time-related information of the reference signal includes:

The time stamp of the reference signal;

The time offset value of the reference signal.

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

The first AI model that is already available or supported by the terminal device;

The first AI function that is already available or supported by the terminal device;

The first AI model available for network-side devices;

The first AI function available for network-side devices.

In some embodiments, the processor is configured to read the computer program in the memory and perform the following operations:

Performing model recognition of a first AI model;

and/or,

Perform function identification of the first AI function.

The present disclosure provides a terminal side device, including:

A transceiver unit, configured to send a first message to a network side device; wherein the first message carries at least one of the following information:

First indication information, used to indicate a first object; the first object includes a first AI model and/or a first AI function;

first information associated with the first object, the first information being related to input and/or output;

A cell identifier associated with the first object.

The embodiment of the present disclosure provides an information processing device, including a memory, a transceiver, and a processor;

The memory is used to store computer programs; the transceiver is used to send and receive data under the control of the processor; the processor is used to read the computer program in the memory and perform the following operations:

Receive a first message sent by a terminal side device;

According to the first message, perform relevant processing of the first object;

The first message carries at least one of the following information:

First indication information, used to indicate a first object; the first object includes a first AI model and/or a first AI function;

first information associated with the first object, the first information being related to input and/or output;

A cell identifier associated with the first object.

In some embodiments, the processor is configured to read the computer program in the memory and perform the following operations:

Sending a second message to the terminal side device; wherein the second message carries a cell identifier; the first AI model is an AI model associated with the cell identifier, and/or the first AI function is an AI function associated with the cell identifier.

In some embodiments, the processor is configured to read the computer program in the memory and perform the following operations:

Sending a third message to the terminal side device; wherein the third message carries a cell identifier and first information; the first AI model is an AI model associated with the cell identifier and the first information, and/or the first AI function is an AI function associated with the cell identifier and the first information.

In some embodiments, the processor is configured to read the computer program in the memory and perform the following operations:

Sending a reference signal and/or a fourth message to the terminal side device; wherein the reference signal is used to train the first AI model and/or train the AI model corresponding to the first AI function; and the fourth message carries a cell identifier and/or the first information.

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

Beam codebook identifier;

Time-related information of the reference signal.

In some embodiments, the time-related information of the reference signal includes:

The time stamp of the reference signal;

The time offset value of the reference signal.

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

The first AI model that is already available or supported by the terminal device;

The first AI function that is already available or supported by the terminal device;

The first AI model available for network-side devices;

The first AI function available for network-side devices.

In some embodiments, the processor is configured to read the computer program in the memory and perform the following operations:

In a case where the first message carries the first information, determining a first object associated with the first information, and performing relevant processing of the first object;

or,

In the case where the first message carries the cell identifier and the first information, a first object associated with the cell identifier and the first information is determined, and related processing of the first object is performed.

In some embodiments, the processor is configured to read the computer program in the memory and perform at least one of the following operations:

activating or deactivating the first object;

activating or deactivating configuration information related to the first object;

Send configuration information related to the first object.

The present disclosure provides a network side device, including:

A receiving unit, configured to receive a first message sent by a terminal side device;

A processing unit, configured to perform relevant processing of the first object according to the first message;

The first message carries at least one of the following information:

First indication information, used to indicate a first object; the first object includes a first AI model and/or a first AI function;

First information associated with a first object; the first information being related to input and/or output;

A cell identifier associated with the first object.

An embodiment of the present disclosure provides a processor-readable storage medium, wherein the processor-readable storage medium stores a computer program, and the computer program is used to enable the processor to execute the steps of the information processing method described above.

The beneficial effects of the above technical solution disclosed in the present invention are:

In an embodiment of the present disclosure, a first message is sent from a terminal side device to a network side device, and the first message carries: first indication information for indicating a first object, first information associated with the first object, and at least one of a cell identifier associated with the first object, so as to notify the network side device of the first object (including a first AI model and/or a first AI function) determined by the terminal side device to be available on the network side device, or to assist the network side device in determining whether the first object is available, thereby ensuring that the network side device can perform relevant processing of the first object based on the result that the first object is available or unavailable, so as to avoid misuse of the AI model or AI function, thereby ensuring communication performance.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG1 is a flowchart showing an information processing method of a terminal side device according to an embodiment of the present disclosure;

FIG2 shows one of the flow charts of interaction between a terminal side device and a network side device according to an embodiment of the present disclosure;

FIG3 shows a second flow chart of interaction between a terminal side device and a network side device according to an embodiment of the present disclosure;

FIG4 shows a third flow chart of interaction between a terminal side device and a network side device according to an embodiment of the present disclosure;

FIG5 is a flowchart showing an information processing method of a network side device according to an embodiment of the present disclosure;

FIG6 is a schematic diagram showing a correspondence relationship between a first object, a cell identifier and first information according to an embodiment of the present disclosure;

FIG7 is a second schematic diagram showing a correspondence between a first object, a cell identifier and first information according to an embodiment of the present disclosure;

FIG8 is a third schematic diagram showing the correspondence between the first object, the cell identifier and the first information according to an embodiment of the present disclosure;

FIG9 is a block diagram showing an information processing device of a terminal side device according to an embodiment of the present disclosure;

FIG10 is a block diagram of a terminal side device according to an embodiment of the present disclosure;

FIG11 is a block diagram showing an information processing device of a network side device according to an embodiment of the present disclosure;

FIG. 12 is a block diagram of a network-side device according to an embodiment of the present disclosure.

DETAILED DESCRIPTION

In order to make the technical problems, technical solutions and advantages to be solved by the present disclosure clearer, the following will be described in detail with reference to the accompanying drawings and specific embodiments. In the following description, specific details such as specific configurations and components are provided only to help fully understand the embodiments of the present disclosure. Therefore, it should be clear to those skilled in the art that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. In addition, for clarity and brevity, the description of known functions and structures is omitted.

It should be understood that the references to "one embodiment" or "an embodiment" throughout the specification mean that specific features, structures, or characteristics associated with the embodiment are included in at least one embodiment of the present disclosure. Therefore, the references to "in one embodiment" or "in an embodiment" appearing throughout the specification do not necessarily refer to the same embodiment. In addition, these specific features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

In various embodiments of the present disclosure, it should be understood that the sequence numbers of the following processes do not imply the order of execution, and the order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present disclosure.

Additionally, the terms "system" and "network" are often used interchangeably herein.

The technical solution provided by the embodiments of the present disclosure can be applicable to a variety of systems, such as the fifth-generation mobile communication technology (5th-Generation, 5G) system and the sixth-generation mobile communication technology (6th-Generation, 6G) system. For example, applicable systems may be global system of mobile communication (GSM) system, code division multiple access (CDMA) system, wideband code division multiple access (WCDMA) general packet radio service (GPRS) system, long term evolution (LTE) system, LTE frequency division duplex (FDD) system, LTE time division duplex (TDD) system, long term evolution advanced (LTE-A) system, universal mobile telecommunication system (UMTS), worldwide interoperability for microwave access (WiMAX) system, 5G new radio (NR) system, 6G system, etc. These systems include terminal side equipment and network side equipment. The system can also include core network parts, such as Evolved Packet System (EPS), 5G System (5G System, 5GS), 6G system, etc.

The network side device and the terminal side device can each use one or more antennas for multiple input multiple output (MIMO) transmission. MIMO transmission can be single user MIMO (SU-MIMO) or multi-user MIMO (MU-MIMO). and quantity, MIMO transmission can be two-dimensional MIMO (2Dimension MIMO, 2D-MIMO), three-dimensional MIMO (3Dimension MIMO, 3D-MIMO), full-dimensional MIMO (Full Dimension MIMO, FD-MIMO) or massive MIMO (massive-MIMO), and it can also be diversity transmission, precoded transmission, or beamforming transmission, etc.

In the embodiments of the present disclosure, the term "and/or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and/or B may represent three situations: A exists alone, A and B exist at the same time, and B exists alone. The character "/" generally indicates that the associated objects before and after are in an "or" relationship.

The term "plurality" in the embodiments of the present disclosure refers to two or more than two, and other quantifiers are similar thereto.

The following will be combined with the drawings in the embodiments of the present disclosure to clearly and completely describe the technical solutions in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present disclosure.

The following is an introduction to the related technologies involved in this disclosure:

There are two sub-use cases for AI-based beam management:

BM-case1: Spatial beam prediction, that is, predicting the Top-K beams (or beam pairs) in Set A based on Set B measured at a certain moment;

BM-case2: Time domain beam prediction, that is, predicting the Top-K beams (or beam pairs) of Set A at the next N’ moments based on Set B measured at the historical N moments.

Among them, Set B represents the input beam set corresponding to the AI model or function, Set A represents the output beam set corresponding to the AI model or function; Top-K beams (or beam pairs) represent the optimal beams (or beam pairs). For BM-case1, Set B can be a subset of Set A, or Set B can be different from Set A (such as Set B is a wide beam and Set A is a narrow beam); for BM-case2, in addition to the above two cases, Set B can also be the same as Set A.

Life Cycle Management (LCM) of AI or ML models refers to the complete process of AI or ML models from generation to end, including data collection, model training, model update, recognition, reasoning, monitoring, activation or deactivation or switching or rollback, etc.

LCM is divided into two modes: LCM based on AI or ML model identification (ID) and LCM based on AI or ML function. Among them, LCM based on AI or ML model ID refers to the indication management of AI or ML model on the UE side through model ID; LCM based on AI or ML function refers to the management of AI or ML function on the UE side by the network side, such as activation or deactivation of the function.

As data-driven algorithms, AI or ML algorithms have generalization problems, that is, AI or ML models trained in scenario 1 are difficult to use in scenario 2. For example: in AI-based beam management, if the transmit beam codebook corresponding to the reference signal used for model training is inconsistent with the transmit beam codebook corresponding to the model reasoning stage, the performance of model reasoning may be poor. If the AI model is deployed on the network side, the network side can ensure the consistency of the transmit beam codebook corresponding to the reference signal for model training and the transmit beam codebook corresponding to the model reasoning stage. If the AI model is deployed on the UE side, the interaction between the network side and the UE side is required to determine whether the beam codebook in the training stage is consistent with the beam codebook in the reasoning stage.

If the input and/or output of the model training (i.e. Set B and/or Set A) is different from the input and/or output of the model during inference If the beam codebooks of base station 1 that sends the reference signal for model training and base station 2 that sends the reference signal for model reasoning are inconsistent, the AI model or function reported by the UE may be difficult to be used correctly after the UE accesses base station 2.

Considering that the beam codebook information such as the angle and shape of the transmit beam on the network side is proprietary information on the network side, it cannot be informed to the UE. If the transmit beam codebook corresponding to the reference signal used for model training is inconsistent with the transmit beam codebook corresponding to the model inference stage, the AI model may not be available. If the network-side device cannot guarantee the availability of the AI model or AI function when sending a reference signal for model inference, the beam management performance may be poor due to the mismatch between the sent reference signal and the AI model or AI function. However, there is currently no specific solution for how network-side devices determine whether the AI model or AI function is available in the scenario where the AI model is deployed on the UE side.

The disclosed embodiments provide an information processing method, apparatus, terminal-side device, and network-side device, so as to enable the network-side device to determine whether an AI model or AI function is available, thereby ensuring the beam management performance based on AI or ML technology. Among them, the method and the device (or the terminal-side device or the network device) are based on the same application concept. Since the principles of solving the problem by the method and the device (or the terminal-side device or the network device) are similar, the implementation of the method and the device (or the terminal-side device or the network device) can refer to each other, and the repeated parts will not be repeated.

As shown in FIG1 , the present disclosure provides an information processing method, comprising the following steps:

Step 11: The terminal side device sends a first message to the network side device; wherein the first message carries at least one of the following information:

The first indication information is used to indicate the first object;

first information associated with the first object;

A cell identifier associated with the first object.

In some embodiments, the first object includes a first AI model and/or a first AI function. For example: the first AI model is obtained based on artificial intelligence or machine learning, and the first AI model may also be referred to as a first ML model. The first AI function may correspond to one or more AI models, and the functions of the one or more AI models are the same, that is, the one or more AI models all support the implementation of the first AI function. Correspondingly, the first AI function may also be referred to as the first ML function, that is, the first ML function may correspond to one or more ML models. In some embodiments, the UE may support activation or deactivation of one or more AI models corresponding to the AI function, that is, the switching of the AI model corresponding to an AI function may be transparent to the network side.

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

a first AI model that is already available or supported by the terminal-side device; for example, when the first object is a first AI model, the first AI model may be an AI model that is already available on the terminal-side device, or an AI model that is supported by the terminal-side device;

The first AI function already existing or supported by the terminal side device; for example, when the first object is the first AI function, the first AI function may be an AI function already existing in the terminal side device, or an AI function supported by the terminal side device.

A first AI model available to the network-side device; for example, when the first object is a first AI model, the first AI model may be an AI model that can be supported by the network-side device among the existing AI models of the terminal-side device;

The first AI function available to the network side device; for example, when the first object is the first AI function, the first AI function may be an AI function among the existing AI functions of the terminal side device that can support the use of the network side device.

In some embodiments, the first message can be used to notify the network side device of the first object (including the first AI model and/or the first AI function) determined by the terminal side device to be available on the network side device. That is, in the embodiments of the present disclosure, for the AI model and/or AI function deployed on the terminal side device, the terminal side device can decide whether the deployed AI model and/or AI function supports the use of the network side device, and notify the network side device. For example, the terminal side device indicates that the first object is the first AI model and/or the first AI function available to the network side device through the first indication information carried in the first message.

In some embodiments, the first message can also be used to assist the network side device in determining whether the first object is available. That is, in the embodiment of the present disclosure, for the AI model and/or AI function deployed by the terminal side device, the network side device can decide whether the first object (including the first AI model and/or the first AI function) is available based on the first message sent by the terminal side device. For example, when the network side device learns the AI model and/or AI function deployed by the terminal side device (which can be learned in an explicit or implicit manner), the first message can carry the first information associated with the first object, and/or the cell identifier associated with the first object, to assist the network side device in determining whether the first object is available. For another example: when the network side device does not learn the AI model and/or AI function deployed by the terminal side device, in addition to carrying the first information associated with the first object, and/or the cell identifier associated with the first object, the first message can also carry the first indication information, which is used to indicate the first object that the terminal side device already has or is available, to assist the network side device in determining whether the first object is available.

It should be noted that the AI model and/or AI function deployed by the terminal side device includes: a first AI model that is already available or supported by the terminal side device, and/or a first AI function that is already available or supported by the terminal side device.

In some embodiments, the first information is related to input and/or output. For example, the first information is related to input and/or output and may refer to at least one of the following:

The first information is related to an input of the first AI model;

The first information is related to an input of an AI model corresponding to the first AI function;

The first information is related to the output of the first AI model;

The first information is related to an output of an AI model corresponding to the first AI function.

In some embodiments, the terminal side device includes but is not limited to at least one of the following: terminal device or user equipment (UE), UE side server, etc. The network side device includes but is not limited to at least one of the following: access network equipment, core network equipment, etc.

In the above scheme, the terminal side device sends a first message to the network side device, and carries in the first message: first indication information for indicating the first object, first information associated with the first object, and at least one of the cell identifiers associated with the first object, so as to notify the network side device of the first object (including the first AI model and/or the first AI function) determined by the terminal side device to be available on the network side device, or to assist the network side device in determining whether the first object is available, thereby ensuring that the network side device can perform relevant processing of the first object based on the result of whether the first object is available or unavailable, so as to avoid the misuse of the AI model or AI function, thereby ensuring communication performance.

For example, taking the network side device as an access network device, when the terminal accesses the access network device, the network side device may send a first message to the network side device to notify the network side device of the first object (including the first AI model and/or the first AI function) determined by the terminal side device to be available on the network side device, or to assist the network side device in determining whether the first object is available. In some embodiments, the first AI model and/or the first AI function may be used to implement communication-related functions or optimize communication performance. For example, taking the first AI model and/or the first AI function as an example for implementing beam management, the network side device may send a reference signal corresponding to the first AI model and/or the first AI function to the terminal when determining the available first AI model and/or the first AI function based on the first message, so as to implement AI-based beam management and ensure higher beam management performance. Of course, it should be noted that the embodiments of the present disclosure are not limited to sending a first message to the network side device when the terminal accesses, for example, it can also be applied to other scenarios, and the present disclosure can also be applied to other scenarios other than beam management, and the embodiments of the present disclosure are not limited to this.

In some embodiments, the terminal side device sends a first message to the network side device, including:

The terminal side device receives a second message sent by the network side device; wherein the second message carries a cell identifier;

The terminal side device sends the first message to the network side device according to the cell identifier; wherein the first AI model is an AI model associated with the cell identifier, and/or the first AI function is an AI function associated with the cell identifier.

The first message may carry first information associated with the first object; or the first message may carry first indication information for indicating the first object and the first information associated with the first object.

In some embodiments, the second message may be a broadcast message or other message types, but the embodiments of the present disclosure are not limited thereto.

For example, the cell identifier may be a cell index or a cell ID.

For example, in the case where the terminal side device deploys AI models and/or AI functions, for example, the terminal side device has trained N AI models, and these N models correspond to M AI functions (where N and M are positive integers, and M≤N), and establish a correspondence between the N AI models or M AI functions and the cell identifier and the first information. Taking three AI models or AI functions as an example, AI model or AI function #1 corresponds to cell identifier #1 and first information #1, AI model or AI function #2 corresponds to cell identifier #1 and first information #2, and AI model or AI function #3 corresponds to cell identifier #2 and first information #3. For example, if the cell identifier carried in the second message sent by the network side device is: cell identifier #1, then the terminal side device carries the first information #1 and the first information #2 when sending the first message to the network side device based on the cell identifier #1, so as to assist the network device in determining whether the AI model or AI function #1 corresponding to the cell identifier #1 and the first information #1, and the AI model or AI function #2 corresponding to the cell identifier #1 and the first information #2 are available.

In some embodiments, the terminal side device sends the first message to the network side device according to the cell identifier, including:

The terminal side device determines a first object associated with the cell identifier from at least one existing AI model and/or AI function;

The terminal side device sends the first message to the network side device.

For example, continuing with the above-mentioned three AI models or AI functions, for example, if the cell identifier carried in the second message sent by the network side device is: cell identifier #1, the terminal side device determines, based on the cell identifier #1, that the first object corresponding to the cell identifier #1 is the AI model or AI function #1 and the AI model or AI function #2, and carries the first information #1 corresponding to the AI model or AI function #1 and the first information #2 corresponding to the AI model or AI function #2 when sending the first message to the network side device, so as to assist the network device in determining whether the AI model or AI function #1 corresponding to the cell identifier #1 and the first information #1, and the AI model or AI function #2 corresponding to the cell identifier #1 and the first information #2 are available.

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

Beam codebook identifier;

Time-related information of the reference signal.

In some embodiments, the time-related information of the reference signal includes:

A time identifier of a reference signal; for example, the time identifier may be a time index defined with a certain time granularity (such as hours, etc.).

The time offset value of the reference signal.

Example 1: Taking the network side device as a base station as an example, the base station broadcasts the second message, carrying a cell identifier. The UE side device determines whether the cell identifier of the reference signal used in model training is consistent with the cell identifier broadcast by the base station. If the cell identifier sent by the base station is consistent with the cell identifier corresponding to the reference signal used in model training of the UE side device, the beam codebook identifier corresponding to the reference signal used in model training is reported to the base station, so that the base station can determine whether the AI model or AI function is available based on whether the beam codebook identifier reported by the terminal is consistent with the beam codebook identifier corresponding to the AI model or AI function used for inference.

Example 2: Continuing with the example of the network-side device being a base station, the base station broadcasts a second message carrying a cell identifier. The UE-side device determines whether the cell identifier of the reference signal used in model training is consistent with the cell identifier broadcast by the base station. If the cell identifier sent by the base station is consistent with the cell identifier corresponding to the reference signal used in model training for the UE-side device, the time-related information corresponding to the reference signal used in model training is reported to the base station. In this way, the base station can determine, based on the time-related information reported by the terminal, whether the beam codebook of the reference signal used in model training corresponding to the time-related information is consistent or similar to the beam codebook corresponding to the AI model or AI function used for inference, so as to determine whether the AI model or AI function is available.

In this embodiment, the base station broadcasts a cell identifier, and the UE-side device determines whether there is an AI model or AI function corresponding to it (i.e., an AI model or AI function that may potentially support the use of the base station) based on the cell identifier broadcast by the base station, and reports the first information corresponding to the reference signal used in the training of the AI model or AI function (such as a beam codebook identifier and/or time-related information) to the base station to assist the base station in determining whether the AI model or AI function is available. For example: the base station determines that the beam codebook corresponding to the reference signal used in the training of the AI model or AI function is consistent or similar to the beam codebook corresponding to the AI model or AI function used for reasoning based on the first information, then determines whether the AI model or AI function is available, otherwise it is determined to be unavailable. In this way, when the base station determines the result that the AI model or AI function is available or unavailable, it can avoid the situation where the AI model or AI function is used incorrectly due to beam codebook mismatch, thereby ensuring the performance of AI-based beam management.

In some embodiments, before the terminal side device sends the first message to the network side device, the method further includes:

The terminal side device receives the reference signal sent by the network side device;

The terminal side device performs measurement according to the reference signal to obtain a measurement result;

The terminal side device performs model training according to the measurement result to determine a first AI model;

The terminal side device establishes a correspondence between the first AI model and the cell identifier and/or the first information, and/or establishes a correspondence between the first AI function corresponding to the first AI model and the cell identifier and/or the first information.

In some embodiments, before the terminal side device establishes a correspondence between the first AI model and the cell identifier and/or the first information, and/or before establishing a correspondence between the first AI function corresponding to the first AI model and the cell identifier and/or the first information, it also includes:

The terminal side device receives the fourth message sent by the network side device, wherein the fourth message carries the cell identifier and/or the first information. For example, the fourth message may be a broadcast message or other message types, and the embodiment of the present disclosure is not limited thereto.

For example: when the network side device configures or sends the reference signal, it carries the beam codebook identifier and/or time-related information to inform the terminal side device of the beam codebook identifier corresponding to the reference signal and/or the time-related information of the reference signal. Considering that the beam codebook is proprietary information of the network side device, different beam codebook identifiers can be used here to represent different beam codebooks corresponding to the reference signal. For example, if the reference signal sent corresponds to beam codebook identifier 1, it means beam codebook 1 corresponding to the reference signal (the angle, shape and other information of the beam corresponding to beam codebook 1 is known by the network side device, and the terminal side device only needs to know the reference signal corresponding to beam codebook identifier 1), thereby avoiding the network side device from exposing proprietary information and realizing the availability judgment of the AI model and/or AI function.

It should be noted that the network side device sends a reference signal to the terminal side device for the terminal side device to perform model training, and the network side device sends a fourth message to the terminal side device, carrying the cell identifier corresponding to the reference signal for model training and/or the first information corresponding to the reference signal for model training, for the terminal side device to establish the corresponding relationship. Here, the network device that sends the reference signal and/or the fourth message to the terminal side device and the network side device that receives the first message sent by the terminal side device may be the same or different. For example: network device 1 sends a reference signal and/or the fourth message for model training to the terminal side device, and the terminal side device may access the network side device 1 at a certain moment after model training, then the terminal side device may send the first message to the network side device 1; or network device 1 sends a reference signal and/or the fourth message for model training to the terminal side device, and the terminal side device may access the network side device 2 after model training, then the terminal side device may send the first message to the network side device 2.

It should be noted that in the embodiments of the present disclosure, the UE or the UE-side server may perform model training and model storage. For example, when the UE-side server performs model training and model storage, the communication between the UE and the UE-side server belongs to the internal behavior of the UE. The embodiments of the present disclosure do not discuss the communication process between the UE and the UE-side server, and the UE and the UE-side server are collectively referred to as UE-side devices.

For example, the UE side device believes that the AI model or AI function can be applied only when the cell identifiers in the training and inference stages are consistent. If they are consistent, the UE side device reports the first information corresponding to the AI model or AI function through the model identification or function identification process. The first information can be the beam codebook identifier and/or time-related information corresponding to the reference signal. The base station The first information reported by the device determines whether the AI model or AI function is available. If so, the corresponding AI model or AI function processing is executed. As shown in Figure 2, the specific process includes:

Step 1: The base station configures and sends reference signals to UE1 and UE2 for UE-side devices to collect data and perform model training;

In some embodiments, when the base station sends a reference signal, it provides a cell identity and first information corresponding to the reference signal. For example, the cell identity and the first information can be sent to UE1 and UE2 by broadcasting.

Step 2: The UE-side device trains a model to establish a correspondence between the AI model or AI function and the cell identifier and the first information;

For example: the corresponding relationship may be that one cell identifier and the first information correspond to one AI model or AI function, or one cell identifier and the first information correspond to multiple AI models or AI functions.

Step 3: UE3 accesses the cell of the base station and receives the cell identifier broadcast by the base station;

Step 4: The UE-side device determines whether there is an AI model or AI function associated with the cell identifier received in step 3;

Step 5: If yes, UE3 performs model identification or function identification to notify the base station of the AI model or AI function associated with the cell identifier received in step 3; or reports the AI model or AI function associated with the cell identifier received in step 3, and reports the first information corresponding to the AI model or AI function;

Step 6: The base station determines whether the AI model or AI function in step 5 is available according to the first information reported by UE3;

Step 7: If the AI model or AI function is available, the base station performs relevant processing of the AI model or AI function.

In some embodiments, the terminal side device sends a first message to the network side device, including:

The terminal side device receives a third message sent by the network side device; wherein the third message carries a cell identifier and the first information;

The terminal side device sends the first message to the network side device based on the cell identifier and the first information; wherein the first AI model is an AI model associated with the cell identifier and the first information, and/or the first AI function is an AI function associated with the cell identifier and the first information.

For example, the cell identifier may be a cell index or a cell ID.

For example, in the case where the terminal side device deploys an AI model and/or AI function, for example, the terminal side device has trained N AI models, and these N models correspond to M AI functions (where N and M are positive integers, and M≤N), and establish a correspondence between the N AI models or M AI functions and the cell identifier and the first information. Taking three AI models or AI functions as an example, AI model or AI function #1 corresponds to cell identifier #1 and first information #1, AI model or AI function #2 corresponds to cell identifier #1 and first information #2, and AI model or AI function #3 corresponds to cell identifier #2 and first information #3. For example, the cell identifier carried in the second message sent by the network side device is: cell identifier #1, and the first information is: first information #1. Then, the terminal side device carries the first indication information when sending the first message to the network side device based on the cell identifier #1 and the first information #1, which is used to indicate that the first object is the AI model or AI function #1, so as to notify the network device that the AI model or AI function #1 corresponding to the cell identifier #1 and the first information #1 is available.

In some embodiments, the terminal side device sends a signal to the network side according to the cell identifier and the first information. The device sends the first message, including:

The terminal side device determines, from at least one existing AI model and/or AI function, a first object associated with the cell identifier and the first information;

The terminal side device sends the first message to the network side device.

For example, continuing with the above-mentioned three AI models or AI functions, for example, the cell identifier carried in the second message sent by the network side device is: cell identifier #1 and first information #1, then the terminal side device determines, based on the cell identifier #1 and the first information #1, that the first object corresponding to the cell identifier #1 and the first information #1 is the AI model or AI function #1, and carries the first indication information when sending the first message to the network side device, which is used to indicate that the first object is the AI model or AI function #1, so as to notify the network side device that the AI model or AI function #1 corresponding to the cell identifier #1 and the first information #1 is available.

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

Beam codebook identifier;

Time-related information of the reference signal.

In some embodiments, the time-related information of the reference signal includes:

A time identifier of a reference signal; for example, the time identifier may be a time index defined with a certain time granularity (such as hours, etc.).

The time offset value of the reference signal.

For example: Taking the network side device as a base station, the base station broadcasts a second message carrying a cell identifier and a beam codebook identifier. The UE side device determines whether the cell identifier and beam codebook identifier of the reference signal used in model training are consistent with the cell identifier and beam codebook identifier broadcast by the base station. If the cell identifier and beam codebook identifier sent by the base station are consistent with the cell identifier and beam codebook identifier corresponding to the reference signal used in the UE side device model training, it is determined that the corresponding AI model or AI function is available and notified to the network side device.

In this embodiment, the base station broadcasts the cell identifier and the beam codebook identifier, and the UE-side device determines whether the corresponding AI model or AI function is available based on the cell identifier and beam codebook identifier broadcast by the base station, and notifies the base station of the result of the determination of whether it is available. In this way, when the base station determines whether the AI model or AI function is available or unavailable, it can avoid the situation where the AI model or AI function is mistakenly used due to beam codebook mismatch, thereby ensuring the performance of AI-based beam management.

In some embodiments, before the terminal side device sends the first message to the network side device, the method further includes:

The terminal side device receives the reference signal sent by the network side device;

The terminal side device performs measurement according to the reference signal to obtain a measurement result;

The terminal side device performs model training according to the measurement result to determine a first AI model;

The terminal side device establishes a correspondence between the first AI model and the cell identifier and/or the first information, and/or establishes a correspondence between the first AI function corresponding to the first AI model and the cell identifier and/or the first information.

In some embodiments, before the terminal side device establishes a correspondence between the first AI model and the cell identifier and/or the first information, and/or before establishing a correspondence between the first AI function corresponding to the first AI model and the cell identifier and/or the first information, it also includes:

The terminal side device receives a fourth message sent by the network side device; wherein the fourth message carries a cell For example, the fourth message may be a broadcast message or other message types, and the embodiment of the present disclosure is not limited thereto.

For example: when the network side device configures or sends the reference signal, it carries the beam codebook identifier and/or time-related information to inform the terminal side device of the beam codebook identifier corresponding to the reference signal and/or the time-related information of the reference signal. The network side device sends a reference signal to the terminal side device for the terminal side device to perform model training; the network side device sends a fourth message to the terminal side device, carrying the cell identifier corresponding to the reference signal used for model training and/or the first information corresponding to the reference signal used for model training, for the terminal side device to establish the corresponding relationship.

It should be noted that in the embodiments of the present disclosure, the UE or the UE-side server may perform model training and model storage. For example, when the UE-side server performs model training and model storage, the communication between the UE and the UE-side server belongs to the internal behavior of the UE. The embodiments of the present disclosure do not discuss the communication process between the UE and the UE-side server, and the UE and the UE-side server are collectively referred to as UE-side devices.

For example, the process of a UE-side device determining whether an AI model or AI function is available is shown in FIG3 . The specific process includes:

Step 1: The base station configures and sends reference signals to UE1 and UE2 for UE-side devices to collect data and perform model training;

In some embodiments, when sending a reference signal, the base station provides a cell identifier and first information corresponding to the reference signal. For example, the cell identifier and first information may be sent to UE1 and UE2 in a broadcasting manner.

Step 2: The UE-side device trains a model to establish a correspondence between the AI model or AI function and the cell identifier and the first information;

For example: the corresponding relationship may be that one cell identifier and the first information correspond to one AI model or AI function, or one cell identifier and the first information correspond to multiple AI models or AI functions.

Step 3: UE3 accesses the cell of the base station and receives the cell identifier and first information broadcast by the base station;

Step 4: The UE-side device determines whether there is an AI model or AI function associated with the cell identifier and the first information received in step 3;

Step 5: If it exists, UE3 performs model identification or function identification to notify the base station of the AI model or AI function that is associated with the cell identifier and the first information received in step 3; or reports the AI model or AI function that is associated with the cell identifier and the first information received in step 3.

In some embodiments, before the terminal side device sends the first message to the network side device, the method further includes:

The terminal side device receives the reference signal sent by the network side device;

The terminal side device performs measurement according to the reference signal to obtain a measurement result;

The terminal side device performs model training according to the measurement result to determine a first AI model;

The terminal side device establishes a correspondence between the first AI model and the cell identifier and/or the first information, and/or establishes a correspondence between the first AI function corresponding to the first AI model and the cell identifier and/or the first information.

In some embodiments, the terminal side device establishes a correspondence between the first AI model and the cell identifier and/or the first information, and/or establishes a correspondence between the first AI function corresponding to the first AI model and the cell identifier and/or the first information Before the corresponding relationship between them, it also includes:

The terminal side device receives the fourth message sent by the network side device, wherein the fourth message carries the cell identifier and/or the first information. For example, the fourth message may be a broadcast message or other message types, and the embodiment of the present disclosure is not limited thereto.

In this embodiment, the terminal side device may establish a correspondence between the first AI model and the cell identifier and/or the first information during the model training process, and/or establish a correspondence between the first AI function corresponding to the first AI model and the cell identifier and/or the first information. In some embodiments, when sending a reference signal for model training, the network side device may also provide first information corresponding to the reference signal (such as a beam codebook identifier and/or time-related information sent by base station broadcast or notified offline) to establish the correspondence.

For example, the terminal side device may establish a correspondence between the first AI model and the cell identifier and/or the first information during the model training process, and/or establish a correspondence between the first AI function corresponding to the first AI model and the cell identifier and/or the first information, and report it to the base station. For example, when the base station learns about the first AI model and/or the first AI function deployed by the terminal side device, the first message may carry the cell identifier associated with the first AI model and/or the first AI function, and/or the first information associated with the first AI model and/or the first AI function. For another example: when the base station does not learn about the first AI model and/or the first AI function deployed by the terminal side device, in addition to carrying the cell identifier associated with the first AI model and/or the first AI function, and/or the first information associated with the first AI model and/or the first AI function, the first message may also carry the first indication information for indicating the first AI model and/or the first AI function.

In this way, the base station can determine whether the first AI model and/or the first AI function are available based on the cell identifier and the first information associated with the first AI model and/or the first AI function reported by the UE. For example: if the first information includes a beam codebook identifier, the base station can determine whether the AI model or AI function is available based on whether the beam codebook identifier reported by the terminal is consistent with the beam codebook identifier corresponding to the AI model or AI function used for reasoning. For another example: if the first information includes time-related information, the base station can determine whether the AI model or AI function is available by determining whether the beam codebook of the reference signal used in the model training corresponding to the time-related information is consistent or similar to the beam codebook corresponding to the AI model or AI function used for reasoning based on the time-related information reported by the terminal.

In this embodiment, the terminal side device reports to the base station the correspondence between the first AI model and the cell identifier and/or the first information established during the model training process, and/or the correspondence between the first AI function corresponding to the first AI model and the cell identifier and/or the first information. The base station determines whether the first AI model or the first AI function is available based on the correspondence. In this way, the base station performs relevant processing of the first AI model or the first AI function based on the result that the first AI model or the first AI function is available or unavailable, which can avoid the situation where the AI model or AI function is used incorrectly due to beam codebook mismatch, thereby ensuring the performance of AI-based beam management.

It should be noted that in the embodiments of the present disclosure, the UE or the UE-side server may perform model training and model storage. For example, when the UE-side server performs model training and model storage, the communication between the UE and the UE-side server belongs to the internal behavior of the UE. The embodiments of the present disclosure do not discuss the communication process between the UE and the UE-side server, and the UE and the UE-side server are collectively referred to as UE-side devices.

It should also be noted that the network side equipment includes access network equipment and/or core network equipment. For example, the function for storing the corresponding relationship in the network side equipment and the function of sending the reference signal are deployed in different nodes (or devices). For example, the first node of the network side equipment stores the correspondence between the cell identifier and the first information and the corresponding AI model and/or AI function. The communication between the base station and the first node belongs to the network side behavior, and the base station and the node are collectively referred to as network side equipment.

For example, in the process of reporting the model training from the terminal side device to the network side device, a correspondence between the first AI model and the cell identifier and/or the first information is established, and/or a correspondence between the first AI function corresponding to the first AI model and the cell identifier and/or the first information is established, and the network side device determines whether the AI model or AI function is available. As shown in FIG. 4, the specific process includes:

Step 0: A network side device (such as a first node) pre-establishes a correspondence between a cell identifier and first information and a beam codebook;

Step 1: The base station configures and sends reference signals to UE1 and UE2 for UE-side devices to collect data and perform model training;

In some embodiments, when sending a reference signal, the base station provides a cell identifier and first information corresponding to the reference signal. For example, the cell identifier and first information may be sent to UE1 and UE2 in a broadcasting manner.

Step 2: The UE-side device trains a model to establish a correspondence between the AI model or AI function and the cell identifier and the first information;

For example: the corresponding relationship may be that one cell identifier and the first information correspond to one AI model or AI function, or one cell identifier and the first information correspond to multiple AI models or AI functions.

Step 3: UE3 performs model identification or function identification to inform the base station to establish a correspondence between the first AI model and the cell identifier and/or the first information during its model training process, and/or to establish a correspondence between the first AI function corresponding to the first AI model and the cell identifier and/or the first information; or, report the correspondence between the first AI model and the cell identifier and/or the first information established during the model training process, and/or to establish a correspondence between the first AI function corresponding to the first AI model and the cell identifier and/or the first information to the base station.

Step 4: The network side device determines whether the corresponding beam codebooks are consistent or similar based on the corresponding relationship in step 0 and the corresponding relationship reported by UE3 in step 3.

Step 5: If it is determined in step 4 that the beam codebooks are consistent or similar, then relevant processing of the first AI model and/or the first AI function is performed.

In some embodiments, when the first message does not include the first indication information, the information processing method further includes: the terminal side device performing model identification of the first AI model; and/or the terminal side device performing function identification of the first AI function.

In this embodiment, the terminal side device can use model identification or function identification to enable the network side device to learn the first AI model and/or the first AI model function it deploys.

The terminal side device involved in the embodiments of the present disclosure may be a device that provides voice and/or data connectivity to a user, a handheld device with a wireless connection function, or other processing devices connected to a wireless modem (such as terminal devices), or may also be a server on the terminal side. The name of the terminal device may be different in different systems. For example, the terminal device can be called User Equipment (UE). The wireless terminal side device can communicate with one or more core networks (CN) via the Radio Access Network (RAN). The wireless terminal device can be a mobile terminal device, such as a mobile phone (or "cellular" phone) and a computer with a mobile terminal device, for example, a portable, pocket-sized, handheld, computer-built-in or vehicle-mounted mobile device, which exchanges language and/or data with the wireless access network. For example, Personal Communication Service (PCS) phones, cordless phones, Session Initiated Protocol (SIP) phones, Wireless Local Loop (WLL) stations, Personal Digital Assistants (PDA) and other devices. The wireless terminal device may also be referred to as a system, a subscriber unit, a subscriber station, a mobile station, a mobile station, a remote station, an access point, a remote terminal device, an access terminal device, a user terminal device, a user agent, and a user device, but is not limited in the embodiments of the present disclosure.

As shown in FIG5 , the present disclosure provides an information processing method, comprising the following steps:

Step 51: The network side device receives the first message sent by the terminal side device.

Step 52: The network side device performs relevant processing of the first object according to the first message.

The first message carries at least one of the following information:

First indication information, used to indicate a first object; the first object includes a first AI model and/or a first AI function;

first information associated with the first object, the first information being related to input and/or output;

A cell identifier associated with the first object.

In some embodiments, before the network side device receives the first message sent by the terminal side device, the method further includes:

The network side device sends a second message to the terminal side device; wherein the second message carries a cell identifier; the first AI model is an AI model associated with the cell identifier, and/or the first AI function is an AI function associated with the cell identifier.

In some embodiments, before the network side device receives the first message sent by the terminal side device, the method further includes:

The network side device sends a third message to the terminal side device; wherein the third message carries a cell identifier and first information; the first AI model is an AI model associated with the cell identifier and the first information, and/or the first AI function is an AI function associated with the cell identifier and the first information.

In some embodiments, before the network side device receives the first message sent by the terminal side device, the method further includes:

The network side device sends a reference signal and/or a fourth message to the terminal side device; wherein the reference signal is used to train the first AI model and/or train the AI model corresponding to the first AI function; and the fourth message carries a cell identifier and/or the first information.

For example, the cell identifier and/or the first information carried by the fourth message may be used to establish a correspondence between the first AI model and the cell identifier and/or the first information, or to establish a correspondence between the first AI function and the cell identifier and/or the first information.

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

Beam codebook identifier;

Time-related information of the reference signal.

In some embodiments, the time-related information of the reference signal includes:

The time stamp of the reference signal;

The time offset value of the reference signal.

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

The first AI model that is already available or supported by the terminal device;

The first AI function that is already available or supported by the terminal device;

The first AI model available for network-side devices;

The first AI function available for network-side devices.

In some embodiments, when the first indication information carried by the first message is used to indicate that the first object is a first AI model and/or a first AI function available to the network side device, the network side device determines that the first object is available and performs relevant processing of the first object.

In some embodiments, the network side device performs related processing of the first object according to the first message, including:

In the case where the first message carries the first information, the network side device determines a first object associated with the first information, and performs relevant processing of the first object;

or,

In the case where the first message carries the cell identifier and the first information, the network side device determines a first object associated with the cell identifier and the first information, and performs relevant processing of the first object.

For example: when the network side device learns the AI model and/or AI function deployed by the terminal side device (which can be learned in an explicit or implicit manner), for example, the network side device also learns the correspondence between the AI model and/or AI function deployed by the terminal side device and the first information (or the correspondence between the AI model and/or AI function and the first information is pre-agreed between the network side device and the terminal side device), the network side device can determine that the first object associated with the first information is available based on the first information associated with the first object carried by the first message, and perform relevant processing of the first object.

For example: when the network side device learns the AI model and/or AI function deployed by the terminal side device (which may be learned explicitly or implicitly), for example, the network side device also learns the correspondence between the AI model and/or AI function deployed by the terminal side device and the first information and the cell identifier (or the correspondence between the AI model and/or AI function and the first information and the cell identifier is pre-agreed between the network side device and the terminal side device), the network side device can determine that the first object associated with the cell identifier and the first information is available based on the first information associated with the first object carried by the first message and the cell identifier associated with the first object, and perform relevant processing of the first object.

In some embodiments, the performing of the related processing of the first object includes at least one of the following:

activating or deactivating the first object;

activating or deactivating configuration information related to the first object;

Send configuration information related to the first object.

For example: activating or deactivating the first object includes but is not limited to at least one of the following: activating or deactivating the first AI model, activating or deactivating the first AI function, activating or deactivating all or part of the AI models corresponding to the first AI function, etc.

For example: activating or deactivating configuration information related to the first object includes but is not limited to at least one of the following: activating or deactivating configuration information related to the first AI model, activating or deactivating configuration information related to the first AI function.

For example, at least one (or at least one set) of configuration information may be pre-configured or agreed upon based on a protocol for the first AI model and/or the first AI function, and one or more of the configuration information may be activated when the first AI model and/or the first AI function is needed to implement the corresponding communication function or optimize the communication performance. In some embodiments, the configuration information related to the first AI model may be configuration information related to the input of the first AI model; the configuration information related to the first AI function may be configuration information related to the input of the AI model corresponding to the first AI function. For example, taking the first AI model and/or the first AI function for beam management as an example, the configuration information may be configuration information of the reference signal.

For example: sending configuration information related to the first object includes but is not limited to at least one of the following: sending configuration information related to the first AI model, sending configuration information related to the first AI function.

In some embodiments, the configuration information related to the first AI model may be configuration information related to the input of the first AI model; the configuration information related to the first AI function may be configuration information related to the input of the AI model corresponding to the first AI function. For example, taking the first AI model and/or the first AI function for beam management as an example, the configuration information may be configuration information of a reference signal.

It should be noted that the information processing method of the above-mentioned network side device and the information processing method of the above-mentioned terminal side device in the embodiment of the present disclosure are based on the same inventive concept, and their embodiments can refer to each other and can achieve the same technical effect, and the similarities will not be repeated.

The network side devices involved in the embodiments of the present disclosure include access network devices, core network devices, etc. For example, it can be a base station, which can include multiple cells that provide services for terminals. Depending on the specific application scenario, the base station can also be called an access point, or it can be a device in the access network that communicates with the wireless terminal side device through one or more sectors on the air interface, or other names. The network side device can be used to interchange received air frames with Internet Protocol (IP) packets, and serve as a router between the wireless terminal device and the rest of the access network, where the rest of the access network may include an Internet Protocol (IP) communication network. The network side device can also coordinate the attribute management of the air interface. For example, the network side device involved in the embodiments of the present disclosure may be a network side device (Base Transceiver Station, BTS) in the Global System for Mobile communications (GSM) or Code Division Multiple Access (CDMA), or a network side device (NodeB) in Wide-band Code Division Multiple Access (WCDMA), or an evolved network side device (evolutional Node B, eNB or e-NodeB) in the long term evolution (LTE) system, or a 5G base station (gNB) in the 5G network architecture (next generation system), or a home evolved Node B (HeNB), a relay node, a home base station (femto), or a pico base station (pico). Or 6G base stations, etc., which are not limited in the embodiments of the present disclosure. In some network structures, the network side equipment may include centralized unit (CU) nodes and distributed unit (DU) nodes, and the centralized unit and the distributed unit may also be arranged geographically separately.

The following is a description of the information processing method provided by the embodiment of the present disclosure in conjunction with a specific embodiment:

Embodiment 1: The UE-side device deploys an AI or ML model for spatial beam prediction.

Step 1: During the data collection phase, the UE side device receives the reference signal sent by the network side device (such as the base station), and provides the cell identifier (such as the cell index or cell ID) and the time-related information of the reference signal to the UE. The base station may use different beam codebooks in different time periods, and the network side knows the codebook information corresponding to the base station in each time period. The time-related information can be at least one of the following:

a) a time identifier of a reference signal, such as a time index defined at a certain time granularity (e.g., hours);

b) time offset value of the reference time;

Step 2: The UE side device builds a training data set to train the AI model based on the collected reference signal, cell identifier and time related information. For example, the UE side device trains several AI models to form three AI functions. The association between these three AI functions and the cell identifier and time identifier is shown in Figure 6.

Step 3: A UE accesses a cell and receives a cell ID broadcasted by the base station as cell ID #1;

Step 4: The UE identifies that among the existing AI functions of the UE-side device, the AI functions associated with the cell identifier #1 are AI function #1 and AI function #2;

Step 5: The UE identifies the AI function #1 and the AI function #2, or reports the supported functions as the AI function #1 and the AI function #2, and reports the time identifier of the AI function #1 as the time identifier #1 and the time identifier of the AI function #2 as the time identifier #2;

Step 6: The base station receives the information reported by the UE and determines that the current beam codebook (for example, the beam codebook corresponding to the reference signal used for reasoning of the AI model or AI function) is the same as the beam codebook corresponding to time identifier #2, and then determines that AI function #2 is available;

Step 7: The base station performs relevant processing of AI function #2, such as activating the AI function or AI model corresponding to AI function #2, or activating the configuration information corresponding to AI function #2, or sending the configuration information corresponding to AI function #2.

Embodiment 2: The UE-side device deploys an AI or ML model for spatial beam prediction.

Step 0: The network side device establishes the corresponding relationship between the cell identifier and the time identifier and the beam codebook, as shown in Figure 7;

Step 1: During the data collection phase, the UE side device receives the reference signal sent by the network side device (such as the base station), and provides the cell identifier (such as the cell index or cell ID) and the time-related information of the reference signal to the UE side device. The base station may use different beam codebooks in different time periods, and the network side device knows the codebook information corresponding to the base station in each time period. The time-related information can be at least one of the following:

a) a time identifier of a reference signal, such as a time index defined at a certain time granularity (e.g., hours);

b) time offset value of the reference time;

Step 2: The UE side device builds a training data set to train the AI model based on the collected reference signal, cell identifier and time related information. For example, the UE side device trains several AI models to form three AI functions. These three AI functions are related to The association relationship between the cell identifier and the time identifier is: AI function #1 is associated with cell identifier #1 and time identifier #1, AI function #2 is associated with cell identifier #1 and time identifier #2, and AI function #3 is associated with cell identifier #2 and time identifier #3.

Step 3: The UE performs function identification and reports that AI function #1 is associated with cell identifier #1 and time identifier #1, AI function #2 is associated with cell identifier #1 and time identifier #2, and AI function #3 is associated with cell identifier #2 and time identifier #3;

Step 4: The network side device determines whether the AI function is available based on the information reported by the UE; for example, the current cell identifier and time identifier are: cell identifier #3, time identifier #1, and associated beam codebook #2 (for example, the beam codebook corresponding to the reference signal used for inference of the AI model corresponding to the AI function is: beam codebook #2, and the network side device learns that beam codebook #2 is associated with cell identifier #3 and time identifier #1), and the cell identifier #1 and time identifier #2 corresponding to AI function #2 in the information reported by the UE are also associated with beam codebook #2, then the network side device determines that AI function #2 is available;

Step 5: The base station performs relevant processing of AI function #2. For example, the base station activates the AI function or AI model corresponding to the AI function #2, or activates the configuration information corresponding to the AI function #2, or sends the configuration information corresponding to the AI function #2. Embodiment 3: The UE-side device deploys an AI or ML model for spatial beam prediction.

Step 1: Data collection phase: The UE side device receives the reference signal sent by the base station and provides the cell identifier and beam codebook identifier to the UE;

Step 2: The UE side device constructs a training data set to train the AI model based on the collected reference signal, cell identifier and beam codebook identifier. For example, the UE side device trains 3 AI models, and the association relationship between these 3 AI models and the cell identifier and beam codebook identifier is shown in Figure 8.

Step 3: A UE accesses the cell of the base station and receives the cell identifier and beam codebook identifier broadcast by the base station: cell identifier #1, beam codebook identifier #1;

Step 4: The UE identifies that the AI model #1 is associated with the cell identifier #1 and the beam codebook identifier #1, and the UE determines that the AI model #1 is available;

Step 5: The UE performs model identification of AI model #1, or reports that the supported (or available) model is AI model #1.

In the disclosed embodiment, it is determined whether the beam codebook corresponding to the reference signal used in model training and the beam codebook used in reasoning are consistent or similar based on the cell identifier and the first information, so as to determine whether the AI model or AI function is available, so as to ensure that the network side device can know or determine whether the AI model or AI function is available, so as to avoid the misuse of the AI model or AI function due to beam codebook mismatch, thereby ensuring the beam prediction performance based on AI technology.

The above embodiments introduce the information processing method of the present invention. The following embodiments will further illustrate the corresponding apparatus, terminal side equipment and network side equipment in conjunction with the accompanying drawings.

As shown in FIG9 , an embodiment of the present disclosure provides an information processing device, including a memory 91, a transceiver 92, and a processor 93; wherein the memory 91 is used to store computer programs; the transceiver 92 is used to send and receive data under the control of the processor 93; the transceiver 92 is used to receive and send data under the control of the processor 93; the processor 93 is used to read the computer program in the memory 91 and perform the following operations:

Sending a first message to a network side device; wherein the first message carries at least one of the following information:

First indication information, used to indicate a first object; the first object includes a first artificial intelligence AI model and/or a first AI function;

first information associated with the first object, the first information being related to input and/or output;

A cell identifier associated with the first object.

In some embodiments, the processor is configured to read the computer program in the memory and perform the following operations:

Receiving a second message sent by the network side device; wherein the second message carries a cell identifier;

According to the cell identifier, the first message is sent to the network side device; wherein the first AI model is an AI model associated with the cell identifier, and/or the first AI function is an AI function associated with the cell identifier.

In some embodiments, the processor is configured to read the computer program in the memory and perform the following operations:

Determine a first object associated with the cell identifier from at least one existing AI model and/or AI function;

Send the first message to the network side device.

In some embodiments, the processor is configured to read the computer program in the memory and perform the following operations:

receiving a third message sent by the network side device; wherein the third message carries a cell identifier and the first information;

According to the cell identifier and the first information, the first message is sent to the network side device; wherein the first AI model is an AI model associated with the cell identifier and the first information, and/or the first AI function is an AI function associated with the cell identifier and the first information.

In some embodiments, the processor is configured to read the computer program in the memory and perform the following operations:

Determine, from at least one existing AI model and/or AI function, a first object associated with the cell identifier and the first information;

Send the first message to the network side device.

In some embodiments, the processor is configured to read the computer program in the memory and perform the following operations:

Receiving a reference signal sent by the network side device;

Perform measurement according to the reference signal to obtain a measurement result;

Perform model training according to the measurement results to determine a first AI model;

A correspondence between the first AI model and the cell identifier and/or the first information is established, and/or a correspondence between the first AI function corresponding to the first AI model and the cell identifier and/or the first information is established.

In some embodiments, the processor is configured to read the computer program in the memory and perform the following operations:

Receive a fourth message sent by the network side device; wherein the fourth message carries a cell identifier and/or the first information.

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

Beam codebook identifier;

Time-related information of the reference signal.

In some embodiments, the time-related information of the reference signal includes:

The time stamp of the reference signal;

The time offset value of the reference signal.

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

The first AI model that is already available or supported by the terminal device;

The first AI function that is already available or supported by the terminal device;

The first AI model available for network-side devices;

The first AI function available for network-side devices.

In some embodiments, the processor is configured to read the computer program in the memory and perform the following operations:

Performing model recognition of a first AI model;

and/or,

Perform function identification of the first AI function.

Among them, in Figure 9, the bus architecture may include any number of interconnected buses and bridges, specifically one or more processors represented by processor 93 and various circuits of memory represented by memory 91 are linked together. The bus architecture can also link various other circuits such as peripherals, voltage regulators and power management circuits together, which are all well known in the art and are therefore not further described herein. The bus interface provides an interface. The transceiver 92 may be a plurality of components, namely, a transmitter and a receiver, providing a unit for communicating with various other devices on a transmission medium, and these transmission media include transmission media such as wireless channels, wired channels, and optical cables. For different user devices, the user interface 94 may also be an interface capable of externally connecting or internally connecting required devices, and the connected devices include but are not limited to a keypad, a display, a speaker, a microphone, a joystick, and the like.

The processor 93 is responsible for managing the bus architecture and general processing, and the memory 91 can store data used by the processor 93 when performing operations.

In some embodiments, the processor 93 can be a central processing unit (CPU), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or a complex programmable logic device (CPLD), and the processor can also adopt a multi-core architecture.

The processor calls the computer program stored in the memory to execute any of the methods provided by the embodiments of the present disclosure according to the obtained executable instructions. The processor and the memory can also be arranged physically separately.

It should be noted here that the above-mentioned device provided by the embodiment of the present disclosure can implement all the method steps implemented by the information processing method embodiment of the above-mentioned terminal side device, and can achieve the same technical effect. The parts and beneficial effects of this embodiment that are the same as the method embodiment will not be described in detail here.

As shown in FIG10 , the embodiment of the present disclosure provides a terminal side device 1000, including:

The transceiver unit 1010 is configured to send a first message to a network side device; wherein the first message carries at least one of the following information:

First indication information, used to indicate a first object; the first object includes a first artificial intelligence AI model and/or a first AI function;

first information associated with the first object, the first information being related to input and/or output;

A cell identifier associated with the first object.

In some embodiments, the transceiver unit 1010 is further configured to:

Receiving a second message sent by the network side device; wherein the second message carries a cell identifier;

According to the cell identifier, the first message is sent to the network side device; wherein the first AI model is an AI model associated with the cell identifier, and/or the first AI function is an AI function associated with the cell identifier.

In some embodiments, the transceiver unit 1010 is further configured to:

Determine a first object associated with the cell identifier from at least one existing AI model and/or AI function;

Send the first message to the network side device.

In some embodiments, the transceiver unit 1010 is further configured to:

receiving a third message sent by the network side device; wherein the third message carries a cell identifier and the first information;

According to the cell identifier and the first information, the first message is sent to the network side device; wherein the first AI model is an AI model associated with the cell identifier and the first information, and/or the first AI function is an AI function associated with the cell identifier and the first information.

In some embodiments, the transceiver unit 1010 is further configured to:

Determine, from at least one existing AI model and/or AI function, a first object associated with the cell identifier and the first information;

Send the first message to the network side device.

In some embodiments, the terminal side device 1000 further includes:

A first receiving unit, configured to receive a reference signal sent by the network side device;

A measuring unit, configured to perform measurement according to the reference signal to obtain a measurement result;

A training unit, configured to perform model training according to the measurement results to determine a first AI model;

An establishing unit is used to establish a correspondence between the first AI model and the cell identifier and/or the first information, and/or establish a correspondence between the first AI function corresponding to the first AI model and the cell identifier and/or the first information.

In some embodiments, the terminal side device 1000 further includes:

The second receiving unit is used to receive a fourth message sent by the network side device; wherein the fourth message carries a cell identifier and/or the first information.

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

Beam codebook identifier;

Time-related information of the reference signal.

In some embodiments, the time-related information of the reference signal includes:

The time stamp of the reference signal;

The time offset value of the reference signal.

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

The first AI model that is already available or supported by the terminal device;

The first AI function that is already available or supported by the terminal device;

The first AI model available for network-side devices;

The first AI function available for network-side devices.

In some embodiments, the terminal side device 1000 further includes:

The identification unit is used to perform model identification of the first AI model; and/or perform function identification of the first AI function.

It should be noted here that the above-mentioned terminal side device provided by the embodiment of the present disclosure can implement all the method steps implemented by the information processing method embodiment of the above-mentioned terminal side device, and can achieve the same technical effect. The parts and beneficial effects of this embodiment that are the same as the method embodiment will not be described in detail here.

In order to better achieve the above-mentioned purpose, as shown in FIG11 , an embodiment of the present disclosure provides an information processing device, including a memory 111, a transceiver 112, and a processor 113; wherein the memory 111 is used to store computer programs; the transceiver 112 is used to send and receive data under the control of the processor 113; the transceiver 112 is used to receive and send data under the control of the processor 113; the processor 113 is used to read the computer program in the memory 111 and perform the following operations:

Receive a first message sent by a terminal side device;

According to the first message, perform relevant processing of the first object;

The first message carries at least one of the following information:

First indication information, used to indicate a first object; the first object includes a first artificial intelligence AI model and/or a first AI function;

first information associated with the first object, the first information being related to input and/or output;

A cell identifier associated with the first object.

In some embodiments, the processor is configured to read the computer program in the memory and perform the following operations:

Sending a second message to the terminal side device; wherein the second message carries a cell identifier; the first AI model is an AI model associated with the cell identifier, and/or the first AI function is an AI function associated with the cell identifier.

In some embodiments, the processor is configured to read the computer program in the memory and perform the following operations:

Sending a third message to the terminal side device; wherein the third message carries a cell identifier and first information; the first AI model is an AI model associated with the cell identifier and the first information, and/or the first AI function is an AI function associated with the cell identifier and the first information.

In some embodiments, the processor is configured to read the computer program in the memory and perform the following operations:

Sending a reference signal and/or a fourth message to the terminal side device; wherein the reference signal is used to train the first AI model and/or train the AI model corresponding to the first AI function; and the fourth message carries a cell identifier and/or the first information.

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

Beam codebook identifier;

Time-related information of the reference signal.

In some embodiments, the time-related information of the reference signal includes:

The time stamp of the reference signal;

The time offset value of the reference signal.

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

The first AI model that is already available or supported by the terminal device;

The first AI function that is already available or supported by the terminal device;

The first AI model available for network-side devices;

The first AI function available for network-side devices.

In some embodiments, the processor is configured to read the computer program in the memory and perform the following operations:

In a case where the first message carries the first information, determining a first object associated with the first information, and performing relevant processing of the first object;

or,

In the case where the first message carries the cell identifier and the first information, a first object associated with the cell identifier and the first information is determined, and related processing of the first object is performed.

In some embodiments, the processor is configured to read the computer program in the memory and perform at least one of the following operations:

activating or deactivating the first object;

activating or deactivating configuration information related to the first object;

Send configuration information related to the first object.

In FIG. 11 , the bus architecture may include any number of interconnected buses and bridges, specifically one or more processors represented by processor 113 and various circuits of memory represented by memory 111 are linked together. The bus architecture may also link together various other circuits such as peripherals, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described herein. The bus interface provides an interface. The transceiver 112 may be a plurality of components, namely, a transmitter and a receiver, providing a unit for communicating with various other devices on a transmission medium, which transmission medium includes a wireless channel, a wired channel, an optical cable, and other transmission media. The processor 113 is responsible for managing the bus architecture and general processing, and the memory 111 may store data used by the processor 113 when performing operations.

The processor 113 can be a central processing unit (CPU), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or a complex programmable logic device (CPLD). The processor can also adopt a multi-core architecture.

It should be noted here that the above-mentioned device provided by the embodiment of the present disclosure can implement all the method steps implemented by the information processing method embodiment of the above-mentioned network side device, and can achieve the same technical effect. The parts and beneficial effects of this embodiment that are the same as the method embodiment will not be described in detail here.

As shown in FIG. 12 , an embodiment of the present disclosure provides a network side device 1200, including:

A receiving unit 1210 is configured to receive a first message sent by a terminal side device;

The processing unit 1220 is configured to perform relevant processing of the first object according to the first message;

The first message carries at least one of the following information:

First indication information, used to indicate a first object; the first object includes a first artificial intelligence AI model and/or a first AI function;

First information associated with a first object; the first information being related to input and/or output;

A cell identifier associated with the first object.

In some embodiments, the network side device 1200 further includes:

A first sending unit is used to send a second message to the terminal side device; wherein the second message carries a cell identifier; the first AI model is an AI model associated with the cell identifier, and/or the first AI function is an AI function associated with the cell identifier.

In some embodiments, the network side device 1200 further includes:

A second sending unit is used to send a third message to the terminal side device; wherein the third message carries a cell identifier and first information; the first AI model is an AI model associated with the cell identifier and the first information, and/or the first AI function is an AI function associated with the cell identifier and the first information.

In some embodiments, the network side device 1200 further includes:

A third sending unit is used to send a reference signal and/or a fourth message to the terminal side device; wherein the reference signal is used to train the first AI model and/or train the AI model corresponding to the first AI function; and the fourth message carries a cell identifier and/or the first information.

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

Beam codebook identifier;

Time-related information of the reference signal.

In some embodiments, the time-related information of the reference signal includes:

The time stamp of the reference signal;

The time offset value of the reference signal.

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

The first AI model that is already available or supported by the terminal device;

The first AI function that is already available or supported by the terminal device;

The first AI model available for network-side devices;

The first AI function available for network-side devices.

In some embodiments, the processing unit 1220 is further configured to:

In a case where the first message carries the first information, determining a first object associated with the first information, and performing relevant processing of the first object;

or,

In the case where the first message carries the cell identifier and the first information, a first object associated with the cell identifier and the first information is determined, and related processing of the first object is performed.

In some embodiments, the processing unit 1220 is further configured to:

activating or deactivating the first object;

activating or deactivating configuration information related to the first object;

Send configuration information related to the first object.

It should be noted here that the above-mentioned network side device provided in the embodiment of the present disclosure can implement all the method steps implemented by the information processing method embodiment of the above-mentioned network side device, and can achieve the same technical effect. The parts and beneficial effects that are the same as the method embodiment in this embodiment will not be described in detail here.

It should be noted that the division of units in the embodiments of the present disclosure is schematic and is only a logical function division. There may be other division methods in actual implementation. In addition, each functional unit in each embodiment of the present disclosure may be integrated into a processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a processor-readable storage medium. Based on this understanding, the technical solution of the present disclosure is essentially or the part that contributes to the relevant technology or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) or a processor (processor) to perform all or part of the steps of the method described in each embodiment of the present disclosure. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk and other media that can store program code.

The embodiments of the present disclosure also provide a processor-readable storage medium, which stores a computer program. The computer program is used to enable the processor to execute the steps of the information processing method of the above-mentioned terminal side device, or the steps of the information processing method of the network side device, and can achieve the same technical effect. The parts and beneficial effects of this embodiment that are the same as those of the method embodiment will not be described in detail here.

The processor-readable storage medium can be any available medium or data storage device that the processor can access, including but not limited to magnetic storage (such as floppy disks, hard disks, magnetic tapes, magneto-optical disks (MO)), optical storage (such as compact discs (CD), digital video discs (DVD), Blu-ray discs (BD), high-definition versatile discs (HVD), etc.), and semiconductor memory (such as ROM, erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), non-volatile memory (NAND (Non-volatile Memory Device) FLASH), solid-state drives (SSD)), etc.

It should be understood by those skilled in the art that the embodiments of the present disclosure may be provided as methods, systems, or computer program products. Therefore, the present disclosure may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present disclosure may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage and optical storage, etc.) containing computer-usable program code. Mode.

The present disclosure is described with reference to the flowchart and/or block diagram of the method, device (system), and computer program product according to the embodiment of the present disclosure. It should be understood that each process and/or box in the flowchart and/or block diagram, as well as the combination of the process and/or box in the flowchart and/or block diagram can be implemented by computer executable instructions. These computer executable instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device produce a device for implementing the functions specified in one process or multiple processes in the flowchart and/or one box or multiple boxes in the block diagram.

These processor-executable instructions may also be stored in a processor-readable memory that can direct a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the processor-readable memory produce a product including an instruction device that implements the functions specified in one or more processes in the flowchart and/or one or more boxes in the block diagram.

These processor-executable instructions may also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more processes in the flowchart and/or one or more boxes in the block diagram.

In addition, it should be noted that in the apparatus and method of the present invention, it is obvious that each component or each step can be decomposed and/or recombined. These decompositions and/or recombinations should be regarded as equivalent schemes of the present invention. Moreover, the steps of performing the above-mentioned series of processing can be naturally performed in chronological order according to the order of description, but it is not necessary to perform them in chronological order, and some steps can be performed in parallel or independently of each other. For those of ordinary skill in the art, it is understood that all or any steps or components of the method and apparatus of the present invention can be implemented in any computing device (including processors, storage media, etc.) or a network of computing devices in hardware, firmware, software or a combination thereof, which can be achieved by those of ordinary skill in the art using their basic programming skills after reading the description of the present invention.

It should be noted that it should be understood that the division of the above modules is only a division of logical functions. In actual implementation, they can be fully or partially integrated into one physical entity, or they can be physically separated. And these modules can all be implemented in the form of software called by processing elements; they can also be all implemented in the form of hardware; some modules can also be implemented in the form of software called by processing elements, and some modules can be implemented in the form of hardware. For example, a module can be a separately established processing element, or it can be integrated in a chip of the above-mentioned device. In addition, it can also be stored in the memory of the above-mentioned device in the form of program code, and called and executed by a processing element of the above-mentioned device. The implementation of other modules is similar. In addition, these modules can be fully or partially integrated together, or they can be implemented independently. The processing element described here can be an integrated circuit with signal processing capabilities. In the implementation process, each step of the above method or each module above can be completed by an integrated logic circuit of hardware in the processor element or instructions in the form of software.

For example, each module, unit, sub-unit or sub-module may be one or more integrated circuits configured to implement the above method, such as one or more application specific integrated circuits (ASICs), Or, one or more microprocessors (digital signal processor, DSP), or, one or more field programmable gate arrays (Field Programmable Gate Array, FPGA), etc. For another example, when a module above is implemented in the form of a processing element scheduling program code, the processing element can be a general-purpose processor, such as a central processing unit (Central Processing Unit, CPU) or other processors that can call program codes. For another example, these modules can be integrated together and implemented in the form of a system-on-a-chip (System-On-a-Chip, SOC).

The terms "first", "second", etc. in the specification and claims of the present disclosure are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present disclosure described here, such as those illustrated or described here, are implemented in a sequence other than the order. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices. In addition, the use of "and/or" in the specification and claims represents at least one of the connected objects, such as A and/or B and/or C, indicating the inclusion of 7 situations including single A, single B, single C, and both A and B exist, both B and C exist, both A and C exist, and both A, B and C exist. Similarly, the use of "at least one of A and B" in the specification and claims should be understood as "single A, single B, or both A and B exist".

Obviously, those skilled in the art can make various changes and modifications to the present disclosure without departing from the spirit and scope of the present disclosure. Thus, if these modifications and variations of the present disclosure fall within the scope of the claims of the present disclosure and their equivalents, the present disclosure is also intended to include these modifications and variations.

Claims (61)

An information processing method, comprising: The terminal side device sends a first message to the network side device; wherein the first message carries at least one of the following information: First indication information, used to indicate a first object; the first object includes a first artificial intelligence AI model and/or a first AI function; first information associated with the first object, the first information being related to input and/or output; A cell identifier associated with the first object. The information processing method according to claim 1, wherein the terminal side device sends the first message to the network side device, comprising: The terminal side device receives a second message sent by the network side device; wherein the second message carries a cell identifier; The terminal side device sends the first message to the network side device according to the cell identifier; wherein the first AI model is an AI model associated with the cell identifier, and/or the first AI function is an AI function associated with the cell identifier. The information processing method according to claim 2, wherein the terminal side device sends the first message to the network side device according to the cell identifier, comprising: The terminal side device determines a first object associated with the cell identifier from at least one existing AI model and/or AI function; The terminal side device sends the first message to the network side device. The information processing method according to claim 1, wherein the terminal side device sends the first message to the network side device, comprising: The terminal side device receives a third message sent by the network side device; wherein the third message carries a cell identifier and the first information; The terminal side device sends the first message to the network side device based on the cell identifier and the first information; wherein the first AI model is an AI model associated with the cell identifier and the first information, and/or the first AI function is an AI function associated with the cell identifier and the first information. The information processing method according to claim 4, wherein the terminal side device sends the first message to the network side device according to the cell identifier and the first information, comprising: The terminal side device determines, from at least one existing AI model and/or AI function, a first object associated with the cell identifier and the first information; The terminal side device sends the first message to the network side device. The information processing method according to any one of claims 1 to 5, wherein, before the terminal side device sends the first message to the network side device, it also includes: The terminal side device receives the reference signal sent by the network side device; The terminal side device performs measurement according to the reference signal to obtain a measurement result; The terminal side device performs model training according to the measurement result to determine a first AI model; The terminal side device establishes a correspondence between the first AI model and the cell identifier and/or the first information, and/or establishes a correspondence between the first AI function corresponding to the first AI model and the cell identifier and/or the first information. The information processing method according to claim 6, wherein the terminal side device establishes a correspondence between the first AI model and the cell identifier and/or the first information, and/or before establishing a correspondence between the first AI function corresponding to the first AI model and the cell identifier and/or the first information, further comprising: The terminal side device receives a fourth message sent by the network side device; wherein the fourth message carries a cell identifier and/or the first information. The information processing method according to claim 1, wherein the first information includes at least one of the following: Beam codebook identifier; Time-related information of the reference signal. The information processing method according to claim 8, wherein the time-related information of the reference signal comprises: The time stamp of the reference signal; The time offset value of the reference signal. The information processing method according to claim 1, wherein the first object includes at least one of the following: The first AI model that is already available or supported by the terminal device; The first AI function that is already available or supported by the terminal device; The first AI model available for network-side devices; The first AI function available for network-side devices. The information processing method according to any one of claims 1 to 10, further comprising: The terminal side device performs model recognition of the first AI model; and/or, The terminal side device performs function identification of the first AI function. An information processing method, comprising: The network side device receives the first message sent by the terminal side device; The network side device performs relevant processing of the first object according to the first message; The first message carries at least one of the following information: First indication information, used to indicate a first object; the first object includes a first artificial intelligence AI model and/or a first AI function; first information associated with the first object, the first information being related to input and/or output; A cell identifier associated with the first object. The information processing method according to claim 12, wherein, before the network side device receives the first message sent by the terminal side device, it also includes: The network side device sends a second message to the terminal side device; wherein the second message carries a cell identifier; The first AI model is an AI model associated with the cell identifier, and/or the first AI function is an AI function associated with the cell identifier. The information processing method according to claim 12, wherein, before the network side device receives the first message sent by the terminal side device, it also includes: The network side device sends a third message to the terminal side device; wherein the third message carries a cell identifier and first information; the first AI model is an AI model associated with the cell identifier and the first information, and/or the first AI function is an AI function associated with the cell identifier and the first information. The information processing method according to any one of claims 12 to 14, wherein, before the network side device receives the first message sent by the terminal side device, it also includes: The network side device sends a reference signal and/or a fourth message to the terminal side device; wherein the reference signal is used to train the first AI model and/or train the AI model corresponding to the first AI function; and the fourth message carries a cell identifier and/or the first information. The information processing method according to claim 12, wherein the first information includes at least one of the following: Beam codebook identifier; Time-related information of the reference signal. The information processing method according to claim 16, wherein the time-related information of the reference signal comprises: The time stamp of the reference signal; The time offset value of the reference signal. The information processing method according to claim 12, wherein the first object includes at least one of the following: The first AI model that is already available or supported by the terminal device; The first AI function that is already available or supported by the terminal device; The first AI model available for network-side devices; The first AI function available for network-side devices. The information processing method according to claim 12, wherein the network side device performs related processing of the first object according to the first message, comprising: In the case where the first message carries the first information, the network side device determines a first object associated with the first information, and performs relevant processing of the first object; or, In the case where the first message carries the cell identifier and the first information, the network side device determines a first object associated with the cell identifier and the first information, and performs relevant processing of the first object. The information processing method according to claim 19, wherein the performing of the related processing of the first object comprises at least one of the following: activating or deactivating the first object; activating or deactivating configuration information related to the first object; Send configuration information related to the first object. An information processing device comprises a memory, a transceiver, and a processor; The memory is used to store computer programs; the transceiver is used to send and receive data under the control of the processor; the processor is used to read the computer program in the memory and perform the following operations: Sending a first message to a network side device; wherein the first message carries at least one of the following information: First indication information, used to indicate a first object; the first object includes a first artificial intelligence AI model and/or a first AI function; first information associated with the first object, the first information being related to input and/or output; A cell identifier associated with the first object. The information processing device according to claim 21, wherein the processor is configured to read the computer program in the memory and perform the following operations: Receiving a second message sent by the network side device; wherein the second message carries a cell identifier; According to the cell identifier, the first message is sent to the network side device; wherein the first AI model is an AI model associated with the cell identifier, and/or the first AI function is an AI function associated with the cell identifier. The information processing device according to claim 21, wherein the processor is configured to read the computer program in the memory and perform the following operations: Determine a first object associated with the cell identifier from at least one existing AI model and/or AI function; Send the first message to the network side device. The information processing device according to claim 21, wherein the processor is configured to read the computer program in the memory and perform the following operations: receiving a third message sent by the network side device; wherein the third message carries a cell identifier and the first information; According to the cell identifier and the first information, the first message is sent to the network side device; wherein the first AI model is an AI model associated with the cell identifier and the first information, and/or the first AI function is an AI function associated with the cell identifier and the first information. The information processing device according to claim 24, wherein the processor is configured to read the computer program in the memory and perform the following operations: Determine, from at least one existing AI model and/or AI function, a first object associated with the cell identifier and the first information; Send the first message to the network side device. The information processing device according to any one of claims 21 to 25, wherein the processor is configured to read the computer program in the memory and perform the following operations: Receiving a reference signal sent by the network side device; Perform measurement according to the reference signal to obtain a measurement result; Perform model training according to the measurement results to determine a first AI model; A correspondence between the first AI model and the cell identifier and/or the first information is established, and/or a correspondence between the first AI function corresponding to the first AI model and the cell identifier and/or the first information is established. The information processing device according to claim 26, wherein the processor is configured to read the computer program in the memory and perform the following operations: Receive a fourth message sent by the network side device; wherein the fourth message carries a cell identifier and/or the first information. The information processing device according to claim 21, wherein the first information includes at least one of the following: Beam codebook identifier; Time-related information of the reference signal. The information processing device according to claim 28, wherein the time-related information of the reference signal comprises: The time stamp of the reference signal; The time offset value of the reference signal. The information processing device according to claim 21, wherein the first object includes at least one of the following: The first AI model that is already available or supported by the terminal device; The first AI function that is already available or supported by the terminal device; The first AI model available for network-side devices; The first AI function available for network-side devices. The information processing device according to any one of claims 21 to 30, wherein the processor is configured to read the computer program in the memory and perform the following operations: Performing model recognition of a first AI model; and/or, Perform function identification of the first AI function. A terminal side device, comprising: A transceiver unit, configured to send a first message to a network side device; wherein the first message carries at least one of the following information: First indication information, used to indicate a first object; the first object includes a first artificial intelligence AI model and/or a first AI function; first information associated with the first object, the first information being related to input and/or output; A cell identifier associated with the first object. The terminal side device according to claim 32, wherein the transceiver unit is further used for: Receiving a second message sent by the network side device; wherein the second message carries a cell identifier; According to the cell identifier, the first message is sent to the network side device; wherein the first AI model is an AI model associated with the cell identifier, and/or the first AI function is an AI function associated with the cell identifier. The terminal side device according to claim 33, wherein the transceiver unit is further used for: Determine a first object associated with the cell identifier from at least one existing AI model and/or AI function; Send the first message to the network side device. The terminal side device according to claim 32, wherein the transceiver unit is further used for: receiving a third message sent by the network side device; wherein the third message carries a cell identifier and the first information; According to the cell identifier and the first information, the first message is sent to the network side device; wherein the first AI model is an AI model associated with the cell identifier and the first information, and/or the first AI function is an AI function associated with the cell identifier and the first information. The terminal side device according to claim 35, wherein the transceiver unit is further used for: Determine, from at least one existing AI model and/or AI function, a first object associated with the cell identifier and the first information; Send the first message to the network side device. The terminal side device according to any one of claims 32 to 36, further comprising: A first receiving unit, configured to receive a reference signal sent by the network side device; A measuring unit, configured to perform measurement according to the reference signal to obtain a measurement result; A training unit, configured to perform model training according to the measurement results to determine a first AI model; An establishing unit is used to establish a correspondence between the first AI model and the cell identifier and/or the first information, and/or establish a correspondence between the first AI function corresponding to the first AI model and the cell identifier and/or the first information. The terminal side device according to claim 37 further includes: The second receiving unit is used to receive a fourth message sent by the network side device; wherein the fourth message carries a cell identifier and/or the first information. The terminal side device according to claim 32, wherein the first information includes at least one of the following: Beam codebook identifier; Time-related information of the reference signal. The terminal side device according to claim 39, wherein the time-related information of the reference signal includes: The time stamp of the reference signal; The time offset value of the reference signal. The terminal-side device according to claim 32, wherein the first object includes at least one of the following: The first AI model that is already available or supported by the terminal device; The first AI function that is already available or supported by the terminal device; The first AI model available for network-side devices; The first AI function available for network-side devices. The terminal side device according to any one of claims 32 to 41, further comprising: The identification unit is used to perform model identification of the first AI model; and/or perform function identification of the first AI function. An information processing device comprises a memory, a transceiver, and a processor; The memory is used to store computer programs; the transceiver is used to send and receive data under the control of the processor; the processor is used to read the computer program in the memory and perform the following operations: Receive a first message sent by a terminal side device; According to the first message, perform relevant processing of the first object; The first message carries at least one of the following information: First indication information, used to indicate a first object; the first object includes a first artificial intelligence AI model and/or a first AI function; first information associated with the first object, the first information being related to input and/or output; A cell identifier associated with the first object. The information processing device according to claim 43, wherein the processor is configured to read the computer program in the memory and perform the following operations: Sending a second message to the terminal side device; wherein the second message carries a cell identifier; the first AI model is an AI model associated with the cell identifier, and/or the first AI function is an AI function associated with the cell identifier. The information processing device according to claim 43, wherein the processor is configured to read the computer program in the memory and perform the following operations: Sending a third message to the terminal side device; wherein the third message carries a cell identifier and first information; the first AI model is an AI model associated with the cell identifier and the first information, and/or the first AI function is an AI function associated with the cell identifier and the first information. The information processing device according to any one of claims 43 to 45, wherein the processor is configured to read the computer program in the memory and perform the following operations: Sending a reference signal and/or a fourth message to the terminal side device; wherein the reference signal is used to train the first AI model and/or train the AI model corresponding to the first AI function; and the fourth message carries a cell identifier and/or the first information. The information processing device according to claim 43, wherein the first information includes at least one of the following: Beam codebook identifier; Time-related information of the reference signal. The information processing device according to claim 47, wherein the time-related information of the reference signal comprises: The time stamp of the reference signal; The time offset value of the reference signal. The information processing device according to claim 43, wherein the first object includes at least one of the following: The first AI model that is already available or supported by the terminal device; The first AI function that is already available or supported by the terminal device; The first AI model available for network-side devices; The first AI function available for network-side devices. The information processing device according to claim 43, wherein the processor is configured to read the computer program in the memory and perform the following operations: In a case where the first message carries the first information, determining a first object associated with the first information, and performing relevant processing of the first object; or, In the case where the first message carries the cell identifier and the first information, a first object associated with the cell identifier and the first information is determined, and related processing of the first object is performed. The information processing device according to claim 50, wherein the processor is configured to read the computer program in the memory and perform at least one of the following operations: activating or deactivating the first object; activating or deactivating configuration information related to the first object; Send configuration information related to the first object. A network side device, comprising: A receiving unit, configured to receive a first message sent by a terminal side device; A processing unit, configured to perform relevant processing of the first object according to the first message; The first message carries at least one of the following information: First indication information, used to indicate a first object; the first object includes a first artificial intelligence AI model and/or a first AI function; First information associated with a first object; the first information being related to input and/or output; A cell identifier associated with the first object. The network side device according to claim 52, wherein the network side device further comprises: A first sending unit is used to send a second message to the terminal side device; wherein the second message carries a cell identifier; the first AI model is an AI model associated with the cell identifier, and/or the first AI function is an AI function associated with the cell identifier. The network side device according to claim 52, wherein the network side device further comprises: A second sending unit is used to send a third message to the terminal side device; wherein the third message carries a cell identifier and first information; the first AI model is an AI model associated with the cell identifier and the first information, and/or the first AI function is an AI function associated with the cell identifier and the first information. The network side device according to any one of claims 52 to 54, wherein the network side device further comprises: A third sending unit is used to send a reference signal and/or a fourth message to the terminal side device; wherein the reference signal is used to train the first AI model and/or train the AI model corresponding to the first AI function; and the fourth message carries a cell identifier and/or the first information. The network side device according to claim 52, wherein the first information includes at least one of the following: Beam codebook identifier; Time-related information of the reference signal. The network side device according to claim 56, wherein the time-related information of the reference signal includes: The time stamp of the reference signal; The time offset value of the reference signal. The network side device according to claim 52, wherein the first object includes at least one of the following: The first AI model that is already available or supported by the terminal device; The first AI function that is already available or supported by the terminal device; The first AI model available for network-side devices; The first AI function available for network-side devices. The network side device according to claim 52, wherein the processing unit is further configured to: In a case where the first message carries the first information, determining a first object associated with the first information, and performing relevant processing of the first object; or, In the case where the first message carries the cell identifier and the first information, a first object associated with the cell identifier and the first information is determined, and related processing of the first object is performed. The network side device according to claim 59, wherein the processing unit is further used for at least one of the following: activating or deactivating the first object; activating or deactivating configuration information related to the first object; Send configuration information related to the first object. A processor-readable storage medium storing a computer program for causing the processor to execute the steps of the information processing method according to any one of claims 1 to 20.