Information transmission method and apparatus, and communication device

Abstract

The invention discloses an information transmission method and device and communication equipment, and belongs to the technical field of communication, and the information transmission method comprises the steps that first equipment receives first information from second equipment, the first information comprises at least one piece of first indication information and second indication information, and the first indication information comprises at least one piece of second indication information; the first indication information is used for indicating data characteristic related information corresponding to at least one device, and the second indication information is used for indicating prediction related information; the first device executes a first operation based on the first information, and the first operation is an operation related to artificial intelligence AI.

Description

Technical Field

[0001] This application belongs to the field of communication technology, specifically relating to an information transmission method, apparatus, and communication equipment. Background Technology

[0002] In some communication scenarios (such as beam prediction and Channel State Information (CSI) prediction), communication devices can use artificial intelligence (AI) models (or AI units or AI functions) to make relevant predictions. However, in practical applications, the performance of AI models is unstable, which affects communication performance. Summary of the Invention

[0003] This application provides an information transmission method, apparatus, and communication device that can solve the problem of unstable performance of AI models.

[0004] In a first aspect, an information transmission method is provided, executed by a first device, the method comprising:

[0005] The first device receives first information from the second device, the first information including at least one of first indication information and second indication information, wherein the first indication information is used to indicate data characteristic related information corresponding to at least one device, and the second indication information is used to indicate prediction related information;

[0006] Based on the first information, the first device performs a first operation, which is an artificial intelligence (AI) related operation.

[0007] Secondly, a method for transmitting information is provided, executed by a second device, the method comprising:

[0008] The second device sends first information to the first device. The first information includes at least one of first indication information and second indication information. The first indication information is used to indicate data characteristic related information corresponding to at least one device, and the second indication information is used to indicate prediction related information.

[0009] Thirdly, a method for transmitting information is provided, executed by a third device, the method comprising:

[0010] The third device sends third information to the second device, the third information being used to indicate data characteristic-related information corresponding to the third device.

[0011] Fourthly, an information transmission device is provided, the device comprising:

[0012] A receiving module is configured to receive first information from a second device, the first information including at least one of first indication information and second indication information, wherein the first indication information is used to indicate data characteristic related information corresponding to at least one device, and the second indication information is used to indicate prediction related information.

[0013] The processing module is used to perform a first operation based on the first information, wherein the first operation is an artificial intelligence (AI) related operation.

[0014] Fifthly, an information transmission device is provided, the device comprising:

[0015] A first sending module is configured to send first information to a first device. The first information includes at least one of first indication information and second indication information. The first indication information is used to indicate data characteristic related information corresponding to at least one device, and the second indication information is used to indicate prediction related information.

[0016] Sixthly, an information transmission device is provided, the device comprising:

[0017] The sending module is used to send third information to the second device, the third information being used to indicate data characteristic related information corresponding to the third device.

[0018] In a seventh aspect, an information transmission apparatus is provided, the apparatus being configured to perform the steps of the method described in the first aspect, or to implement the steps of the method described in the second aspect, or to implement the steps of the method described in the third aspect.

[0019] In an eighth aspect, a terminal is provided, the terminal including a processor and a memory, the memory storing a program or instructions executable on the processor, the program or instructions, when executed by the processor, implementing the steps of the method as described in the first aspect.

[0020] In a ninth aspect, a terminal is provided, including a processor and a communication interface, wherein the communication interface is configured to: receive first information from a second device, the first information including at least one of first indication information and second indication information, wherein the first indication information is configured to indicate data characteristic related information corresponding to at least one device, and the second indication information is configured to indicate prediction related information; the processor is configured to: perform a first operation based on the first information, the first operation being an artificial intelligence (AI) related operation.

[0021] In a tenth aspect, a network-side device is provided, the network-side device including a processor and a memory, the memory storing a program or instructions executable on the processor, the program or instructions, when executed by the processor, implementing the steps of the method as described in the second aspect, or implementing the steps of the method as described in the third aspect.

[0022] Eleventhly, a network-side device is provided, including a processor and a communication interface, wherein the communication interface is used to: send first information to a first device, the first information including at least one of first indication information and second indication information, wherein the first indication information is used to indicate data characteristic related information corresponding to at least one device, and the second indication information is used to indicate prediction related information.

[0023] In a twelfth aspect, a network-side device is provided, including a processor and a communication interface, wherein the communication interface is used to send third information to a second device, the third information being used to indicate data characteristic-related information corresponding to the third device.

[0024] In a thirteenth aspect, a readable storage medium is provided, on which a program or instructions are stored, which, when executed by a processor, implement the steps of the method described in the first aspect, or the steps of the method described in the second aspect, or the steps of the method described in the third aspect.

[0025] In a fourteenth aspect, a wireless communication system is provided, comprising: a terminal and a network-side device, wherein the terminal is configured to perform the steps of the method described in the first aspect, and the network-side device is configured to perform the steps of the method described in the second aspect, or the steps of the method described in the third aspect.

[0026] In a fifteenth aspect, a chip is provided, the chip including a processor and a communication interface coupled to the processor, the processor being configured to run a program or instructions to implement the method as described in the first aspect, or the method as described in the second aspect, or the method as described in the third aspect.

[0027] In a sixteenth aspect, a computer program / program product is provided, which is stored in a storage medium and is executed by at least one processor to implement the steps of the information transmission method as described in the first aspect, or the steps of the information transmission method as described in the second aspect, or the steps of the information transmission method as described in the second aspect.

[0028] In this embodiment, a first device receives first information from a second device. The first information includes at least one of first indication information and second indication information. The first indication information indicates data characteristic-related information corresponding to at least one device, and the second indication information indicates prediction-related information. Based on the first information, the first device performs a first operation, which is an AI-related operation. This allows the first device to perform AI-related operations based on the acquired first information, ensuring that the AI-related operations match the device's data characteristics or conform to the indicated prediction-related information. This helps improve the performance stability of the AI ​​model, AI unit, or AI function. Attached Figure Description

[0029] Figure 1 This is a schematic diagram of a network structure applicable to the embodiments of this application;

[0030] Figure 2 This is a flowchart of an information transmission method provided in an embodiment of this application;

[0031] Figure 3 This is a flowchart of an information transmission method provided in an embodiment of this application;

[0032] Figure 4 This is a flowchart of another information transmission method provided in the embodiments of this application;

[0033] Figures 5 to 6 This is a flowchart of Example 1;

[0034] Figures 7 to 8 This is a flowchart of Example 2;

[0035] Figures 9 to 10 This is a flowchart of Example 3;

[0036] Figure 11 This is a flowchart of Example 4;

[0037] Figure 12 This is a structural diagram of an information transmission device provided in an embodiment of this application;

[0038] Figure 13 This is a structural diagram of an information transmission device provided in an embodiment of this application;

[0039] Figure 14 This is a structural diagram of an information transmission device provided in an embodiment of this application;

[0040] Figure 15 This is a structural diagram of a communication device provided in an embodiment of this application;

[0041] Figure 16This is a structural diagram of a terminal provided in an embodiment of this application;

[0042] Figure 17 This is a structural diagram of a network-side device provided in an embodiment of this application;

[0043] Figure 18 This is a structural diagram of another network-side device provided in an embodiment of this application. Detailed Implementation

[0044] The technical solutions of the embodiments of this application will be clearly described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application are within the scope of protection of this application.

[0045] The terms "first," "second," etc., used in this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such terms can be used interchangeably where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first" and "second" are generally of the same class, not limited in number; for example, the first object can be one or more. Furthermore, "or" in this application indicates at least one of the connected objects. For example, the scope of protection for "A or B" covers at least three scenarios: Scenario 1: including A but not B; Scenario 2: including B but not A; Scenario 3: including both A and B. In addition, the terms "A and / or B," "at least one of A and B," and "at least one of A or B" also cover at least the above three scenarios. The character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0046] The term "instruction" in this application can be either a direct instruction (or explicit instruction) or an indirect instruction (or implicit instruction). A direct instruction can be understood as one in which the sender explicitly informs the receiver of specific information, the operation to be performed, or the requested result, etc., in the instruction sent. An indirect instruction can be understood as one in which the receiver determines the corresponding information based on the instruction sent by the sender, or makes a judgment and determines the operation to be performed or the requested result, etc., based on the judgment result.

[0047] It is worth noting that the technologies described in this application are not limited to Long Term Evolution (LTE) / LTE-Advanced (LTE-A) systems, but can also be used in other wireless communication systems, such as Code Division Multiple Access (CDMA), Time Division Multiple Access (TDMA), Frequency Division Multiple Access (FDMA), Orthogonal Frequency Division Multiple Access (OFDMA), Single-carrier Frequency-Division Multiple Access (SC-FDMA), or other systems. The terms "system" and "network" in this application are often used interchangeably, and the described technologies can be used with the systems and radio technologies mentioned above, as well as with other systems and radio technologies. The following description describes New Radio (NR) systems for illustrative purposes, and the term NR is used in most of the following description; however, these technologies can also be applied to systems other than NR systems, such as 6th generation (6G) radio systems. th Generation 6G communication system.

[0048] Figure 1This diagram illustrates a block diagram of a wireless communication system applicable to embodiments of this application. The wireless communication system includes a terminal 11 and a network-side device 12. The terminal 11 can be a mobile phone, tablet computer, laptop computer, notebook computer, personal digital assistant (PDA), handheld computer, netbook, ultra-mobile personal computer (UMPC), mobile internet device (MID), augmented reality (AR), virtual reality (VR) device, robot, wearable device, flight vehicle, vehicle user equipment (VUE), shipboard equipment, pedestrian user equipment (PUE), smart home devices (home appliances with wireless communication capabilities, such as refrigerators, televisions, washing machines, or furniture), game consoles, personal computers (PCs), ATMs, or self-service machines, etc. Wearable devices include: smartwatches, smart bracelets, smart headphones, smart glasses, smart jewelry (smart bracelets, smart chains, smart rings, smart necklaces, smart anklets, smart anklets, etc.), smart wristbands, smart clothing, etc. Among these, in-vehicle devices can also be referred to as in-vehicle terminals, in-vehicle controllers, in-vehicle modules, in-vehicle components, in-vehicle chips, or in-vehicle units, etc. It should be noted that the specific type of terminal 11 is not limited in this application embodiment. Network-side equipment 12 may include access network equipment or core network equipment, wherein access network equipment may also be referred to as Radio Access Network (RAN) equipment, radio access network function, or radio access network unit. Access network equipment may include base stations, Wireless Local Area Network (WLAN) access points (APs), or Wireless Fidelity (WiFi) nodes, etc.The term "base station" can be referred to as Node B (NB), Evolved Node B (eNB), Next Generation Node B (gNB), New Radio Node B (NR Node B), Access Point, Relay Base Station (RBS), Serving Base Station (SBS), Base Transceiver Station (BTS), Radio Base Station, Radio Transceiver, Basic Service Set (BSS), Extended Service Set (ESS), Home Node B (HNB), Home Evolved Node B, Transmit / Receive Point (TRP), or any other suitable term in the relevant field, as long as the same technical effect is achieved. The term "base station" is not limited to any specific technical terminology. It should be noted that this application embodiment only uses a base station in an NR system as an example for description and does not limit the specific type of base station.

[0049] Core network equipment, also known as core network nodes, core network functions, or core network elements, includes, but is not limited to, at least one of the following: Mobility Management Entity (MME), Access and Mobility Management Function (AMF), Session Management Function (SMF), User Plane Function (UPF), Policy Control Function (PCF), Policy and Charging Rules Function (PCRF), Edge Application Server Discovery Function (EASDF), Unified Data Management (UDM), Unified Data Repository (UDR), Home Subscriber Server (HSS), Centralized network configuration (CNC), Network Repository Function (NRF), Network Exposure Function (NEF), Local NEF (or L-NEF), and Binding Support Function. Support Functions (BSF), Application Functions (AF), Location Management Functions (LMF), Gateway Mobile Location Centres (GMLC), and Network Data Analytics Functions (NWDAF), etc. It should be noted that this application embodiment only uses core network equipment in the NR system as an example and does not limit the specific type of core network equipment. If the name of the core network equipment mentioned in this application embodiment changes in subsequent protocol versions (e.g., 6G), it will still be within the scope of protection of this application.

[0050] Optionally, the core network equipment can be implemented by one or more functional modules in a single device, or by multiple devices working together; this application does not specifically limit this. It is understood that the aforementioned functional modules can be network elements in hardware devices, software functional modules running on dedicated hardware, or virtualized functional modules instantiated on a platform (e.g., a cloud platform).

[0051] Before describing the embodiments of this application, the relevant technologies are briefly introduced below:

[0052] I. AI-based Beam Prediction - Model Training

[0053] In the AI-based beam prediction use cases discussed in 5G, a training sample includes model input and ground truth / labels during training data collection. The model input includes (historical) partial or complete beam quality, beam identifiers, measurement resource identifiers, or timestamps, etc.; the ground truth / labels are (future) all beam qualities, strongest beam identifiers, or timestamps, etc.

[0054] II. AI-based Beam Prediction - Model Inference

[0055] In the AI-based beam prediction use cases discussed in 5G, during model inference, an inference sample includes model inputs. These model inputs include (historical) partial or complete beam quality, beam identifiers, measurement resource identifiers, or timestamps, etc.

[0056] Whether it's the training samples or the inference samples mentioned above, the information in the model input and labels, including beam quality, beam identifier, and measurement resource identifier, is related to the physical characteristics of the transmitted beam on the base station side.

[0057] In practice, due to the varying hardware and software configurations of each base station, it's highly likely that model training is conducted using training data collected at base station A, while model inference is performed at base station B. This leads to a mismatch between the characteristics of the training and inference data, resulting in unstable inference performance and consequently affecting wireless transmission quality.

[0058] Taking AI-based beam prediction as an example, if the model input only includes the Reference Signal Received Power (RSRP) and beam identification information for the corresponding beam, but not information describing the physical characteristics of the transmitted beam, then it is necessary to ensure the consistency of the transmitted beam data characteristics between inference and training. Information related to the physical characteristics of the transmitted beam can include, for example, the beam's directionality, beamforming weights, beamforming codebook, and the mapping relationship between weights and beam identification. If the above information about the transmitted beam does not match between inference and training, it will lead to a deterioration in the model's inference performance.

[0059] In view of this, embodiments of this application provide an information transmission method, an information transmission device, and a communication equipment to solve the problem of unstable performance of AI models in related technologies.

[0060] The information transmission method provided in this application will be described in detail below with reference to the accompanying drawings and through some embodiments and application scenarios.

[0061] Figure 2 This diagram illustrates a flowchart of an information transmission method provided in an embodiment of this application. Figure 2 As shown, the information transmission method includes the following steps:

[0062] Step 201: The first device receives first information from the second device, the first information including at least one of first indication information and second indication information, wherein the first indication information is used to indicate data characteristic related information corresponding to at least one device, and the second indication information is used to indicate prediction related information;

[0063] Step 202: The first device performs a first operation based on the first information, wherein the first operation is an AI-related operation.

[0064] In this application embodiment, AI-related operations may include, for example, data characteristic consistency judgment related to AI unit or AI function, model activation of AI unit, model deactivation of AI unit, model inference of AI unit, model training of AI unit, collection of model training dataset of AI unit, module monitoring of AI unit, and model fine-tuning of AI unit, etc. This application embodiment does not limit these operations.

[0065] The first device can be understood as a device that performs model inference for the AI ​​unit; for example, the first device could be a terminal. The second device can be understood as a mapping device between data characteristics and related information. Additionally, the second device can also be a device that performs consistency judgment on data characteristics related to the collection of model inference data for the AI ​​unit; for example, the second device could be a base station or a core network function (such as LMF or other network elements).

[0066] The explanation of AI units / AI models is as follows:

[0067] In this application embodiment, the AI ​​unit / AI model may also be referred to as an AI unit, AI model, machine learning (ML) model, ML unit, AI structure, AI function, AI characteristic, machine learning model, neural network, neural network function, neural network functionality, etc. Alternatively, the AI ​​unit / AI model may refer to a processing unit capable of implementing specific algorithms, formulas, processing flows, capabilities, etc. related to AI. Alternatively, the AI ​​unit / AI model may be a processing method, algorithm, function, module, or unit for a specific dataset. Alternatively, the AI ​​unit / AI model may be a processing method, algorithm, function, module, or unit running on AI / ML related hardware such as GPU, NPU, TPU, and ASIC. This application embodiment does not specifically limit these aspects. Optionally, the specific dataset includes the input and / or output of the AI ​​unit / AI model.

[0068] Optionally, AI units / AI models can be identified by AI unit / AI model identifiers. The AI ​​unit / AI model identifier can be an AI model identifier, an AI structure identifier, an AI algorithm identifier, or an identifier of a specific dataset associated with the AI ​​unit / AI model, or an identifier of a specific scenario, environment, channel characteristics, or device related to the AI / ML, or an identifier of a function, characteristic, capability, or module related to the AI / ML.

[0069] In this embodiment, the data characteristic information related to the device can be understood as information related to the data characteristics of the device. The data characteristics of the device can be understood as the device's wireless characteristics (that is, there is a correspondence between the device's data characteristics and its wireless characteristics), or as the device's related configuration (that is, there is a correspondence between the device's data characteristics and its related configuration), or as the characteristics of the wireless environment in which the device exists (that is, there is a correspondence between the device's data characteristics and its wireless environment), or as the mapping relationship between the device's related configuration and the mapped data. The device's wireless characteristics or related configuration can be divided into two categories: first wireless characteristics and second wireless characteristics. The first wireless characteristic can be understood as a fixed wireless characteristic, or a hardware-directly related wireless characteristic, or a station-type related wireless characteristic. The second wireless characteristic can be understood as an adjustable wireless characteristic, or a software-adjustable wireless characteristic.

[0070] In step 201, the first device receives first information from the second device. If the first information includes first indication information, the first device can know whether the AI ​​unit or AI function that the first device can obtain matches the corresponding data characteristics of the second device. This can prevent the AI ​​unit or AI function enabled by the first device from not matching the corresponding data characteristics of the second device.

[0071] When the first information includes the second instruction information, it can be understood that the AI ​​units or AI functions available to the first device match the data characteristics corresponding to the second device. In other words, the second device performs its own judgment, determining that the AI ​​units or AI functions available to the first device match the data characteristics corresponding to the second device. Therefore, the second device directly sends the second instruction information to request the first device to perform a prediction. It should be noted that in this application embodiment, "prediction" can be replaced with "reasoning".

[0072] In this embodiment of the application, the first device receives first information and performs AI-related operations based on the first information, which can ensure that the AI-related operations match the data characteristics of the device, or ensure that the AI-related operations conform to the indicated prediction-related information. This helps to improve the performance stability of the AI ​​model, AI unit, or AI function.

[0073] In some embodiments, the first indication information includes at least one of the following:

[0074] The first data characteristic corresponding to the second device;

[0075] AI information related to the first data characteristic;

[0076] Cell information related to the first data characteristic;

[0077] The second data characteristic corresponding to the third device;

[0078] AI information related to the second data characteristic;

[0079] Cells whose data characteristics are consistent with the second data characteristic.

[0080] If the first indication information includes the first data characteristics corresponding to the second device, the first device can know the data characteristics corresponding to the second device, so the first device can determine whether the data characteristics of the AI ​​unit or AI function that the device can obtain match the data characteristics corresponding to the second device. If they match, the first device can use the corresponding AI unit or AI function to predict the cell where the second device is located.

[0081] In this application embodiment, AI information may include, for example, AI features or AI functions. AI features and AI functions are explained as follows: AI feature + specific configuration, i.e., AI function. For example, the AI ​​feature is beam management, and the AI ​​function is time-domain beam prediction configured for a base station with 32 transmit beams.

[0082] For the first instruction information, which includes AI information related to the first data characteristics, the second device directly helps the first device determine the AI ​​characteristics or AI functions that can be activated, which can save the computing power and computational complexity of the first device.

[0083] In this embodiment of the application, the cell information may include at least one of the following:

[0084] Cell ID;

[0085] Cell group ID;

[0086] List of residential communities;

[0087] Public Land Mobile Network (PLMN) ID;

[0088] PLMN group ID;

[0089] NR Cell Global Identifier (NCGI);

[0090] Tracking Area Identity (TAI);

[0091] Track the region group ID;

[0092] RAN-based Notification Area (RNA);

[0093] RAN group ID;

[0094] Cell Global Identity (CGI) is a unified identifier for the community.

[0095] Cell group global identifier (CGGI);

[0096] Carrier frequency information;

[0097] Physical Cell Identifier (PCI);

[0098] Physical cell group identifier;

[0099] Geographical location area.

[0100] For the first indication information including cell information related to the first data characteristic, the first indication information indicates cells whose data characteristics are consistent with the first data characteristic. The cell information can be understood or replaced as a list of consistent cells (the same descriptions thereafter can be understood in the same way and will not be repeated). If the first device moves to another cell, it can directly make corresponding predictions by comparing with the list of consistent cells, without having to wait for the cell handover to ask the target cell before it can start predictions. This can save the signaling interaction between the first device and other cells. Alternatively, the first device can also determine whether to switch to an adjacent cell based on whether the data characteristics of adjacent cells match. This can ensure that the first device switches to an appropriate cell.

[0101] Regarding the first indication information including the second data characteristics corresponding to the third device, the first device can know the data characteristics corresponding to the third device. If the first device moves to the cell where the third device is located, it can pre-determine whether prediction can be enabled based on the second data characteristics, without having to wait until the cell handover to query the cell where the third device is located before enabling prediction. This can save air interface signaling interaction between the first device and the third device. Alternatively, based on the second data characteristics, the first device can determine whether it can switch to the cell where the third device is located, which can ensure that the first device switches to the appropriate cell.

[0102] For the first instruction information including the AI ​​information related to the second data characteristics, the second device directly helps the first device determine the AI ​​characteristics or AI functions that can be activated when switching to the cell where the third device is located, which can save the computing power and computational complexity of the first device.

[0103] For the first indication information including cell information related to the second data characteristic, the first indication information indicates cells whose data characteristics are consistent with the second data characteristic. The cell information can be understood or replaced as a consistent cell list. If the first device moves to another cell, it can directly make a corresponding prediction by comparing the consistent cell list, without having to wait for the cell handover to ask the target cell before starting the prediction; or, the first device can determine whether to switch to an adjacent cell based on whether the data characteristics of adjacent cells match, which can ensure that the first device switches to a suitable cell.

[0104] In some embodiments, the first indication information includes at least one of the following:

[0105] At least one first association information, wherein the at least one first association information is associated with the first data characteristic;

[0106] AI information related to at least one first associated information, namely, AI characteristics or AI functions that maintain data characteristic consistency with the first associated information;

[0107] The cell information related to at least one first association information, that is, the cell that maintains data characteristics consistency with the first association information;

[0108] When the first data characteristic is associated with multiple first associated information, the activation time information of the multiple first associated information (i.e., different first associated information is activated according to time);

[0109] The first sub-indicator is used to indicate the association relationship between the plurality of first associated information and AI information;

[0110] At least one second association information, wherein the at least one second association information is associated with the second data characteristic;

[0111] AI information related to at least one second associated information, namely, AI characteristics or AI functions that maintain data characteristic consistency with the second associated information;

[0112] The cell information related to at least one second association information, that is, the cell that maintains data characteristics consistency with the second association information;

[0113] The second sub-indicator is used to indicate whether the second associated information has changed.

[0114] In this embodiment, the first data characteristic may include at least one first association information. The first association information is used to indicate the first data characteristic, which can avoid exposing the physical characteristics (or wireless characteristics or related configurations) of the second device, thereby protecting the data privacy of the second device.

[0115] Accordingly, by indicating the second data characteristics through the second association information, the physical characteristics (or wireless characteristics or related configurations) of the third device can be avoided, thereby protecting the data privacy of the third device.

[0116] The first associated information, the second associated information, and any other associated information are visible to the first device, but the first device cannot parse out the corresponding configuration information, and therefore cannot know the physical implementation characteristics of the second device, the third device, and other network-side devices.

[0117] In some embodiments, the first association information includes a first association identifier (ID), or the first association information includes at least one of a first association ID, a first cell ID, and a first timestamp, wherein the first cell ID is the cell ID of the second device.

[0118] In some embodiments, the second association information includes a second association ID, or the second association information includes at least one of a second association ID, a second cell ID, and a second timestamp, wherein the second cell ID is the cell ID of the third device.

[0119] In this embodiment of the application, the first association ID, the second association ID, and other association IDs can all be understood as global association information. The same association ID corresponds to the same physical meaning in any cell.

[0120] Alternatively, in this embodiment, the first association ID, second association ID, and other association IDs can all be understood as local association information. For example, the first association ID is only valid within the scope associated with the first cell ID, and the second association ID is only valid within the scope associated with the second cell ID. The association ID corresponding to cell 1 is 1, and the association ID corresponding to cell 2 is also 1, which can represent different network physical implementations. In this case, the association ID needs to be combined with the cell ID, or both the cell ID and the timestamp, to represent complete association information, so that the network device can determine the corresponding data characteristics or network configuration based on the association information. Whether the data characteristics or network configuration represented by the association ID of cell 1 and the association ID of cell 2 match can be determined by cell 1 or cell 2. By introducing cell-local association IDs, the problem of excessively high maintenance costs for global association IDs can be solved.

[0121] First timestamp, second timestamp, and other timestamps can be understood as timestamps associated with related information. By introducing timestamps, associated IDs within a cell can be recycled and redistributed at different times, avoiding the problem of an excessive number of associated IDs within a cell and reducing the maintenance cost of associated IDs within a cell.

[0122] For the second cell ID, the second device indicates the identifier of the corresponding third device. This can indicate to the first device the association relationship between the second association information and the second cell ID, or the matching relationship between the third association information and the second cell ID. This avoids the situation where the first device needs to interact with the third device to determine whether to start prediction after switching to the cell where the third device is located. Alternatively, the first device can determine whether to switch to the cell where the third device is located based on whether the data characteristics of the cell where the third device is located match, which can ensure that the first device switches to the appropriate cell.

[0123] In addition, the first association information, the second association information, and other association information may also include association mapping data. The association mapping data may include vectors, two-dimensional matrices, or multi-dimensional matrices, or other forms of data. This application embodiment will not provide examples of each of these.

[0124] For periodic notifications, the first indication information may also include an indication of whether the first associated information has changed. This indication can be represented by 1 bit. If it remains unchanged, no additional information needs to be sent, which saves transmission overhead. Correspondingly, the first indication information may also include an indication of whether the second associated information has changed (i.e., a second sub-indication), which will not be elaborated further.

[0125] In the case where the first data characteristic is associated with multiple first associated information, regarding the activation time information of the multiple first associated information, when the first associated information of the second device is different in different periods, the first device can send the activation time information of multiple first associated information to the first device at once, without having to send it multiple times.

[0126] Regarding the indication of the association relationship between the multiple first association information and AI information (i.e., the first sub-indication), when multiple AI functions that can be activated by the second device correspond to different first association information, the relationship between the two can be indicated to the first device.

[0127] Regarding the second association information (i.e., the association information of the third device), it avoids the situation where the first device needs to interact with the third device after switching to the cell where the third device is located to determine whether to start prediction. The first device can determine whether to start prediction for the cell where the third device is located based on the second association information before, during, or after the handover. Alternatively, the first device can determine whether to switch to the cell where the third device is located based on whether the data characteristics of the cell match, which can ensure that the first device switches to the appropriate cell.

[0128] Regarding the AI ​​information related to the second association information, this avoids the situation where the first device needs to interact with the third device after switching to the cell where the third device is located to determine whether to initiate prediction. Furthermore, since the second device directly instructs on the AI ​​information associated with the second association information, it also reduces the computational power required for the first device to make the decision. Alternatively, the first device can determine whether to switch to the cell where the third device is located based on whether the AI ​​information matches the second association information, ensuring that the first device switches to the appropriate cell.

[0129] Regarding the cell information related to the second association information, this avoids the situation where the first device, after switching to a neighboring cell, still needs to interact with the base station of the neighboring cell to determine whether to initiate prediction. Alternatively, the first device can determine whether to switch to a neighboring cell and which neighboring cell to switch to based on the cell ID or cell list related to the second association information, which ensures that the first device switches to the appropriate cell.

[0130] In some embodiments, the first operation includes at least one of the following:

[0131] Identify the AI ​​unit or AI function that matches the first data characteristic corresponding to the second device;

[0132] Determine a first dataset that matches the first data characteristic;

[0133] Determine the AI ​​unit or AI function corresponding to the first dataset;

[0134] Initiate prediction for the cell where the second device is located;

[0135] Activate the second AI unit or the second AI function, wherein the second AI unit or the second AI function is an AI unit or AI function whose data characteristics match the first data characteristics;

[0136] Perform inactive model monitoring on the second AI unit or the second AI function;

[0137] Deactivate the third AI unit or the third AI function, wherein the third AI unit or the third AI function is an AI unit or AI function whose data characteristics do not match the first data characteristics;

[0138] Collect the first training data and associate the first training data with the first data characteristics;

[0139] Based on the first training data, a fourth AI unit or a fourth AI function is generated, and the fourth AI unit or the fourth AI function is associated with the first data characteristics.

[0140] If the first operation includes determining the AI ​​unit or AI function that matches the data characteristics corresponding to the second device, and initiating prediction for the cell where the second device is located, the first device can ensure that the AI ​​unit or AI function it uses matches the data characteristics corresponding to the second device through the first operation. Under this premise, the first device can make a prediction; otherwise, it will not make a prediction. This can ensure the stability of the inference performance of the AI ​​unit or AI function used by the first device, thereby ensuring the prediction effect.

[0141] Taking the first operation as an example, which includes activating the second AI unit or the second AI function, the first device can use the activated AI unit or AI function to make predictions through the first operation. This can ensure that the activated AI unit or AI function matches the data characteristics of the second device, ensuring the prediction effect and thereby improving the communication performance of the first device.

[0142] Taking the first operation, which includes inactive model monitoring of the second AI unit or function, as an example, it can be understood as first initiating prediction, then monitoring the prediction results, and only initiating the reporting of the prediction results if the monitoring results meet preset conditions. Since the first device knows whether the data characteristics of the second AI unit or function match the network data characteristics, this can reduce the requirements for inactive model monitoring of the second AI unit while ensuring model inference performance. For example, it can reduce the monitoring duration or the number of monitored samples. For instance, if the data characteristics do not match, assuming 10,000 samples need to be monitored, but if the data characteristics match, monitoring only 100 samples can achieve good inference performance.

[0143] Taking the first operation, which includes deactivating the third AI unit or the third AI function, as an example, it can be understood as turning off prediction. This can avoid the problem that the predicted value does not meet expectations due to the use of an AI unit or AI function whose data characteristics do not match the data characteristics corresponding to the second device, thereby avoiding the waste of the computing power of the first device.

[0144] If the first operation includes determining a first dataset that matches the data characteristics corresponding to the second device, and determining the AI ​​unit or AI function corresponding to the first dataset, the first device can ensure that the dataset used matches the data characteristics corresponding to the second device through the first operation, thereby ensuring the stability of the inference performance of the AI ​​unit or AI function used by the first device.

[0145] Taking the first operation as an example, which includes collecting first training data and associating the first training data with the data characteristics corresponding to the second device, the first device can add data characteristic attributes to the collected training data through the first operation, thereby facilitating subsequent use or serving as a basis for judgment.

[0146] Taking the first operation as an example, which includes generating a fourth AI unit or a fourth AI function based on the first training data, and associating the fourth AI unit or the fourth AI function with the data characteristics corresponding to the second device, the first device can add data characteristic attributes to the generated AI unit or AI function through the first operation, thereby facilitating subsequent use or serving as a basis for judgment.

[0147] Regardless of which of the above operations are included in the first operation, it can ensure that the training or inference of the AI ​​unit or AI function matches the data characteristics, which helps to improve the inference stability of the AI ​​unit or AI function.

[0148] In this embodiment of the application, by receiving the first information and performing the first operation based on the first information, it is possible to ensure that the training or inference of the AI ​​unit or AI function matches the data characteristics, which helps to improve the inference stability of the AI ​​unit or AI function.

[0149] In some embodiments, the at least one device further includes a third device;

[0150] The first operation further includes at least one of the following:

[0151] Based on the data characteristics of the third device, determine whether to switch to the cell where the third device is located;

[0152] Identify an AI unit or AI function that matches the data characteristics corresponding to the third device;

[0153] Determine a second dataset that matches the data characteristics corresponding to the third device;

[0154] Determine the AI ​​unit or AI function corresponding to the second dataset;

[0155] If the first device switches to the cell where the third device is located, prediction of the cell where the third device is located is initiated;

[0156] When the first device switches to the cell where the third device is located, second training data is collected, and the second training data is associated with the data characteristics corresponding to the third device;

[0157] Based on the second training data, a fifth AI unit or a fifth AI function is generated, and the fifth AI unit or the fifth AI function is associated with the data characteristics corresponding to the third device.

[0158] In this embodiment, the first indication information may include not only indication information related to the data characteristics of the second device, but also indication information related to the data characteristics of the third device. For example, the second device may be the serving base station of the first device, and the third device may be any adjacent base station other than the serving base station; the number of third devices may be one or more. The third device can determine its own data characteristics, interact with its adjacent base stations (such as the second device) regarding its own data characteristics, and determine whether its own data characteristics match the data characteristics of other devices, the data characteristics of a certain AI unit, or the data characteristics of a certain dataset.

[0159] In this way, based on the first information, the first device can also obtain the data characteristics of the adjacent base stations. On the one hand, the first device can directly determine whether to switch to the cell where the third device is located based on the data characteristics of the third device in the first information, which can improve the efficiency of cell handover. On the other hand, if the first device moves, switches, or reselects to a neighboring cell, the first device can directly make corresponding predictions based on the data characteristics of the adjacent base stations without having to confirm after the handover to start the prediction, which can improve the prediction efficiency. Alternatively, the first device can also determine whether to switch to the adjacent cell based on whether the data characteristics of the adjacent cells match, which can ensure that the first device switches to the appropriate cell.

[0160] In some embodiments, the method further includes:

[0161] The first device sends second information to the second device. The second information includes third indication information, which is used to indicate data characteristic related information corresponding to the first AI unit or the first AI function. The first AI unit or the first AI function is an AI unit or AI function that the first device can obtain.

[0162] In this embodiment, the first device actively sends second information to the second device (i.e., the serving cell in the connected state) to request the data characteristic matching status corresponding to one or more AI units or AI functions. In this way, the first device does not need to continuously receive the first information from the second device, which can further reduce the signaling overhead of the first device.

[0163] In some embodiments, the first device sends second information to the second device, including:

[0164] When the first condition is met, the first device sends the second information to the second device;

[0165] The first condition includes at least one of the following:

[0166] Prepare to activate or start the first AI unit or the first AI function;

[0167] The communication index of the cell where the second device is located was detected to be lower than a preset threshold;

[0168] Deterioration in the inference performance of the first AI unit or the first AI function was detected.

[0169] The first device undergoes cell handover or cell reselection.

[0170] Preparing to activate or start the first AI unit or the first AI function can be understood as preparing to activate or start a certain AI feature / AI use case.

[0171] In this embodiment, the first device sends the second information to the second device only when the first condition is met, which can avoid the frequent sending of the second information and thus save signaling interaction between the first device and the second device.

[0172] In some embodiments, the third indication information includes at least one of the following:

[0173] The third data characteristic corresponding to the first AI unit or the first AI function;

[0174] AI information related to the third data characteristic;

[0175] Here, the second information can be understood as the matching status between the network data characteristics and the terminal AI function data characteristics. The second information can be carried in at least one of the following: a scheduling request (SR) / buffer status report (BSR) (i.e., the mechanism for reusing uplink scheduling requests) and a CSI report.

[0176] In some embodiments, the third indication information includes at least one of the following:

[0177] At least one third association information, wherein the at least one third association information is associated with the third data characteristic;

[0178] The first set includes multiple sets of the third associated information;

[0179] AI information related to the third associated information;

[0180] AI information related to the first set.

[0181] In this embodiment, the third data characteristics can be indicated by the third association information, which can avoid exposing the physical characteristics (or wireless characteristics) of the first AI unit or the first AI function associated with the first device peer device (such as a network-side device), thereby protecting the data privacy of the corresponding device (such as a network-side device that provides training data for training the first unit or the first AI function).

[0182] In addition, the third instruction information may also include information such as the number of third related information and the number of first sets.

[0183] When the third instruction information includes the first set, the first device can collect data from multiple related information together for training during training data collection.

[0184] In some embodiments, the first indication information includes at least one of the following:

[0185] The third sub-indicator is used to indicate whether the first data characteristic corresponding to the second device matches the third data characteristic;

[0186] The fourth sub-indicator is used to indicate whether the second data characteristic corresponding to the third device matches the third data characteristic;

[0187] The third data characteristic;

[0188] AI information related to the third data characteristic;

[0189] The cell information related to the third data characteristic;

[0190] The first data characteristic;

[0191] AI information related to the first data characteristic;

[0192] Cell information related to the first data characteristic;

[0193] The second data characteristic;

[0194] AI information related to the second data characteristic;

[0195] The cell information related to the second data characteristic.

[0196] In this embodiment, for the first indication information including the third sub-indication, the first device can know whether the data characteristics of the AI ​​function or AI unit that the device can obtain match the data characteristics of the corresponding second device. If they match, prediction can be enabled.

[0197] Regarding the first instruction information including the fourth sub-instruction, the first device can determine whether the data characteristics of the AI ​​functions or AI units that it can acquire match the data characteristics of the third device, and use this to determine whether to switch to the cell where the third device is located. If the first device can switch to the cell where the third device is located, prediction will be started directly after switching to the cell where the third device is located.

[0198] For the first indication information including AI information related to the third data characteristic, i.e., AI information used to indicate that the data characteristic is consistent with the third data characteristic, the second device, based on the third data characteristic, directly indicates an AI characteristic or AI function that matches the data characteristics of the AI ​​function or AI unit available to the first device. Thus, after the first device switches to the cell where the third device is located, the first device can directly start prediction, thereby saving the computing power for decision-making and reducing computational complexity.

[0199] For the first indication information including cell information related to the third data characteristic, i.e., for cells whose data characteristics are consistent with the third data characteristic, the first device can determine whether to switch to a neighboring cell of the cell where the third device is located based on this information. This ensures that the first device switches to a suitable cell. When the first device switches from the cell where the third device is located to another cell, it can save signaling interaction with other cells. If the data characteristics match, prediction can begin; if the data characteristics do not match, prediction will not be initiated.

[0200] For the rest, please refer to the relevant explanations mentioned above, which will not be repeated here.

[0201] When the third indication information includes third related information or the first set, the first indication information may specifically include at least one of the following:

[0202] An indication of whether the data characteristics match those of the third related information (i.e., the fifth or sixth sub-indicator);

[0203] AI information that matches the data characteristics of the third-party related information;

[0204] Cell information that matches the data characteristics of the third related information;

[0205] An indication of whether the data characteristics match those of the first set can include the following cases: match, full match, partial match, and no match.

[0206] The first set of AI information is an indication of the relationship between the first set and the AI ​​information (i.e., the first sub-indicator), that is, which one or more third-related information in the first set matches which one or more AI functions or AI characteristics.

[0207] An indication of the matching data characteristics of multiple third-related information in the first set, that is, which or several third-related information in the first set have data characteristics that match the data characteristics of the second device.

[0208] Specifically, regarding the indication of whether the data characteristics of the aforementioned associated information match, the first device can determine whether the data characteristics of the AI ​​unit or AI function that the device can acquire match the data characteristics of the second device. If they match, the prediction of the cell where the second device is located can be enabled.

[0209] For the AI ​​information that matches the data characteristics of the third associated information, the second device directly indicates the AI ​​function or AI characteristic that matches the data characteristics of the second device based on the third associated information. In this way, the first device can save the computing power for decision-making and reduce the computational complexity.

[0210] For cell information whose data characteristics match the third associated information, the first device can determine whether to switch to a neighboring cell of the cell where the third device is located, ensuring that the first device switches to a suitable cell. When the first device switches from the cell where the third device is located to another cell, signaling interactions with other cells can be saved. If the data characteristics match, prediction can begin; otherwise, prediction will not be initiated.

[0211] The indication of whether the data characteristics of the first set match is similar to the first one in terms of its beneficial effect, except that it can be based on multiple third-party related information.

[0212] The beneficial effects of the first set of AI function matching indicators mentioned above are similar to those of the second set, except that they can be based on multiple third-party related information.

[0213] The indication of matching the data characteristics of multiple third-related information in the first set mentioned above has similar beneficial effects to the first point, except that it can be based on multiple third-related information.

[0214] In some embodiments, the first indication information includes at least one of the following:

[0215] The first indication information includes at least one of the following:

[0216] At least one first association information, wherein the at least one first association information is associated with a first data characteristic corresponding to the second device;

[0217] AI information related to at least one first associated information;

[0218] Cell information related to at least one first associated information;

[0219] When the first data characteristic is associated with multiple first associated information, the activation time information of the multiple first associated information;

[0220] The first sub-indicator is used to indicate the association relationship between the plurality of first associated information and AI information;

[0221] At least one second association information, wherein the at least one second association information is associated with the second data characteristic;

[0222] AI information related to at least one second associated information;

[0223] The cell information related to at least one second associated information;

[0224] The second sub-indicator is used to indicate whether the second associated information has changed;

[0225] At least one third association information, wherein the at least one third association information is associated with the third data characteristic;

[0226] AI information related to at least one third-party associated information;

[0227] The cell information related to at least one third-party associated information;

[0228] The fifth sub-indicator is used to indicate whether the third data characteristic associated with the at least one third association information matches the first data characteristic corresponding to the second device;

[0229] The sixth sub-indicator is used to indicate whether the third data characteristic associated with the at least one third associated information matches the second data characteristic corresponding to the third device.

[0230] In this embodiment, compared with the first indication information in the previous embodiment, the last five items are added. That is, if the first device sends the third associated information to the second device in the second information, the first indication information may also include the last five items.

[0231] Regarding the third-related information, for example, if the second information includes 10 third-related information items, then the first indication information can include one or more of the third-related information items that match the data characteristics corresponding to the second device. For another example, if the second device receives a third-related information item from the first device at 8:00 AM, the first device performs a model download update at 9:00 AM, and then sends another third-related information item to the second device, then the second device can indicate in the first indication information which third-related information item's data characteristics match the data characteristics corresponding to the second device.

[0232] Regarding AI information related to the third associated information, the second device directly indicates the AI ​​information associated with the third associated information, which can also reduce the computing power required for the first device to make decisions. In one possible implementation, if the second information includes 10 AI functions, then the first indication information may include one or more AI information that matches the data characteristics corresponding to the second device.

[0233] For cell information related to the third association information, the second device directly indicates the cell associated with the third association information. When the first device switches to another cell, it can save signaling interaction with other cells.

[0234] In some embodiments, the first information includes the second indication information, and the second indication information includes at least one of the following:

[0235] Request the predicted value reported by the first device;

[0236] First association information, which is associated with a first data characteristic corresponding to the second device;

[0237] The third association information is associated with the third data characteristic;

[0238] The seventh sub-indicator is used to indicate whether the matched third data feature can be used for training data collection, model fine-tuning, or model training of the AI ​​unit.

[0239] For example, the seventh sub-indicator is used to indicate that the third related information is applicable to model inference or module monitoring, but not to training data collection.

[0240] The second indication information can be called a predicted value indication. In this embodiment, when the first information includes a predicted value indication, the first device can use the first AI unit or the first AI function to obtain the predicted value related to the second device and report the prediction result. Thus, the first device directly initiates prediction and obtains the predicted value based on the predicted value indication from the second device. After receiving the predicted value reported by the first device, the second device can configure beams, scheduling, etc., that better match the wireless characteristics of the first device based on the predicted value, thereby improving the communication performance of the first device.

[0241] When the first device sends second information to the second device, and this second information includes third association information, the predicted value indicated by the predicted value indicator can be understood as a predicted value related to the AI ​​unit or AI function matched with the third association information. In other words, the second device directly determines the corresponding AI unit or AI function based on the matched data characteristics and directly requests the predicted value from the first device, performing the configuration related to the predicted value request. This saves the signaling interaction required for the first device to initiate the corresponding prediction request to the second device based on the matched AI unit or AI function.

[0242] In some embodiments, when the second indication information includes the third association information but does not include the first association information, the third association information is associated with model inference or model monitoring functions, and the third association information is not expected to be used for training data collection or model fine-tuning or model training; or, the configuration information corresponding to the third association information is not expected to be used for training data collection or model fine-tuning or model training.

[0243] For example, when the at least one third association ID is associated with model inference or model monitoring functions, the at least one third association ID is not expected to be used for model fine-tuning, model training, or data collection, or the configuration information associated with the at least one third association ID is not expected to be used for model fine-tuning, model training, or data collection. It should be noted that the model inference, model monitoring, model fine-tuning, model training, or data collection can be determined through direct signaling indication functions or through implicit configuration information. For example, the model inference function can be configured directly in the CSI report (explicit), or prediction result feedback can be configured in the CSI report (implicit), or the UE can be configured with performance monitoring event reporting.

[0244] In some embodiments, where the second indication information includes the first associated information but does not include the third associated information, the first associated information is permitted to be used for training data collection or model fine-tuning or model training, or the configuration information corresponding to the first associated information is permitted to be used for training data collection or model fine-tuning or model training; the third associated information in the second information is not expected to be used for model inference or model monitoring, or the configuration information corresponding to the third associated information in the second information is not expected to be used for model inference or model monitoring.

[0245] In some embodiments, where the second indication information includes the first association information and the third association information, at least one of the first association information and the third association information is permitted for use in model inference or module monitoring, and at least one of the first association information and the third association information is permitted for use in training data collection or model fine-tuning or model training.

[0246] The use and definition of timestamps differ at different stages, such as model inference, model monitoring, and training data collection. (Note: When combined with timestamps, it indicates that the associated ID is a valid associated ID within the cell.) Examples are provided below:

[0247] Case 1 (Model Inference Only): The first device sends a third data feature (including a third timestamp). In this case, the third timestamp is related to the third associated information, such as the timestamp when the training data was collected.

[0248] Scenario 2 (Training data collection only): The first device sends the third data feature, but the first information does not contain the matching third data feature, and only the first data feature is sent (inference cannot be performed by default). In this case, the third timestamp is related to the third associated information, such as the timestamp when the training data is collected. In this case, the first data feature includes the cell ID and the associated ID, but does not include the timestamp.

[0249] However, when the first device completes the collection of training data and associates the first data characteristic with the dataset, it binds the first cell ID, the first timestamp, the first association ID, and the data. At this point, the first timestamp is either the timestamp associated when the first device collected the data, or the timestamp when the first information was received. However, the first timestamp may not be included in the first information.

[0250] Scenario 3 (Simultaneously supporting model inference and training data collection): The first device sends a third data feature (including a third timestamp, defined as above), and the second device sends a first message including the first data feature and the matching third data feature. In this case, the first data feature may not include the first timestamp, while the matching third data feature may include the third timestamp.

[0251] The first device can determine the AI ​​unit or AI function used for prediction based on third association information that matches the first data characteristics, such as the first information including a matching third association ID, a third cell ID, and a third timestamp.

[0252] On the other hand, the first device can collect training data. When the first device completes the collection of training data and associates the first data characteristics with the dataset, it will bind the first cell ID, the first timestamp, the first association ID, and the data. At this time, the first timestamp is either the timestamp associated when the first device collected the data or the timestamp when the first information was received. However, the first timestamp may not be included in the first information.

[0253] In some embodiments, the first information is carried in at least one of the following messages:

[0254] Broadcast messages; Channel State Information (CSI) configuration messages; Resource set configuration information; Resource configuration information; Beam management set B resource or resource set configuration information; Beam management set A resource or resource set configuration information; AI unit prediction reporting messages; AI unit model monitoring reporting messages; AI unit inference reporting messages; Medium Access Control Control Element (MACCE); Radio Resource Control (RRC) messages.

[0255] The broadcast message can be a System Information Block (SIB) message, carrying a value tag to indicate whether the wireless characteristics of the network device have changed. The value tag is a constant. The terminal compares the currently stored value tag with the value tag in the received broadcast message. If they are the same, it means there is no change; otherwise, it means there is a change and the corresponding SIBx needs to be read.

[0256] CSI configuration messages may include CSI measurement configuration information (e.g., CSI-MeasConfig), CSI reporting configuration information (e.g., CSI-ReportConfig), and CSI measurement resource configuration information (e.g., CSI-ResourceConfig).

[0257] The configuration information for the resource set can be, for example, CSI-SSB-ResourceSet or NZP-CSI-RS-ResourceSet.

[0258] Resource configuration information could be, for example, NZP-CSI-RS-Resource.

[0259] In some embodiments, when the first information is carried in the CSI configuration message and the first indication information simultaneously indicates the first data characteristic and the matching third data characteristic corresponding to the second device, the CSI configuration message is associated with the first association ID and the third association ID, or the CSI configuration message is associated with the first association ID, the third association ID, the first cell ID and the third cell ID, or the CSI configuration message is associated with the first association ID, the third association ID, the first cell ID, the third cell ID and the third timestamp.

[0260] The aforementioned "association" can be replaced with "configuration". That is, when the first information is carried in the CSI configuration message, and the first indication information simultaneously indicates the first data characteristic and the matching third data characteristic corresponding to the second device, the CSI configuration message configures the first association ID and the third association ID, or the CSI configuration message configures the first association ID, the third association ID, the first cell ID and the third cell ID, or the CSI configuration message configures the first association ID, the third association ID, the first cell ID, the third cell ID and the third timestamp.

[0261] In some embodiments, where the first information is carried in the CSI configuration message, the first indication information simultaneously indicates the first data characteristic and the matching third data characteristic corresponding to the second device, and the CSI configuration message configures a fourth association ID, and the information element (IE) of the fourth association ID is associated with or configured with a fifth association ID; or, where the first information is carried in the CSI configuration message, the first indication information simultaneously indicates the first data characteristic and the matching third data characteristic corresponding to the second device, and the CSI configuration message configures a fourth association ID and a fourth cell ID, and the IE of the fourth association ID is associated with or configured with a fifth association ID and a fifth cell ID, then the fourth association ID is the first association ID, the fourth cell ID is the first cell ID, and the fifth association ID is the third association ID, and the fifth cell ID is the third cell ID; or, the fourth association ID is the third association ID, the fourth cell ID is the third cell ID, and the fifth association ID is the first association ID, and the fifth cell ID is the first cell ID.

[0262] For example, in some embodiments, when the first information is carried in the CSI configuration message, and the first indication information simultaneously indicates a first data characteristic and a matching third data characteristic corresponding to the second device, the CSI configuration message includes at least one of the following:

[0263] The CSI configuration message configures a first associated ID, and the IE of the first associated ID is associated with or configured with a third associated ID;

[0264] The CSI configuration message configures a first associated ID, and the IE of the first associated ID is associated with or configured with a third associated ID and a third cell ID;

[0265] The CSI configuration message configures a first associated ID, and the IE of the first associated ID is associated with or configured with a third associated ID, a third cell ID, and a third timestamp;

[0266] The CSI configuration message configures the association ID as the first association ID, and the association ID in the IE is configured to be associated with or configured as the third association ID;

[0267] In the CSI configuration message, the association ID is configured as the first association ID, and the association ID is configured as the third association ID and the cell ID is configured as the third cell ID in the IE of the association ID.

[0268] In the CSI configuration message, the associated ID is configured as the first associated ID, and the associated ID is configured in the IE as the third associated ID, the cell ID is configured as the third cell ID, and the timestamp is configured as the third timestamp.

[0269] The CSI configuration message configures a third associated ID, a third cell ID, and a third timestamp, and the third associated ID is associated with or configured with a first associated ID in the IE of the IE.

[0270] The CSI configuration message configures a third association ID, a third cell ID, and a third timestamp, and the IE of the third association ID is associated with or configured with a first association ID and a first cell ID;

[0271] The CSI configuration message is configured with Association ID = Third Association ID, Cell ID = Third Cell ID, Timestamp = Third Timestamp, and the Association ID is associated with or configured as the First Association ID in the IE.

[0272] The CSI configuration message is configured with Association ID = Third Association ID, Cell ID = Third Cell ID, and Timestamp = Third Timestamp, and the IE of the Association ID is associated or configured with Association ID = First Association ID and Cell ID = First Cell ID.

[0273] Optionally, the CSI configuration message described above also includes a request for the predicted value to be reported by the first device.

[0274] For example, in some embodiments, where the first information is carried in the CSI configuration message, the first indication information indicates a matching third data characteristic, and the CSI configuration message includes at least one of the following:

[0275] The CSI configuration message configures the predicted value, measurement resources, third association ID, third cell ID, and third timestamp requested from the first device; (assuming the third association ID is the cell local ID).

[0276] The CSI configuration message configures the predicted value, measurement resources, third association ID, and third cell ID requested from the first device; (assuming the third association ID is the cell local ID).

[0277] The CSI configuration message configures the predicted value, measurement resource, and third association ID requested from the first device; (assuming the third association ID is a global ID).

[0278] For example, after the UE accesses cell 2, it reports support for association ID = third association ID and cell ID = third cell identifier cell 1 via the second information. Based on the received third association ID and third cell identifier, the network configures corresponding reference signal resources and reporting resources for the terminal to perform model inference or model monitoring. These reference signal resources or reporting resources are associated with the third association ID, or with both the third association ID and the third cell ID, or vice versa. In this case, the network does not expect the UE to use the reference signal resources for model training or data collection.

[0279] Alternatively, the network may configure corresponding reference signal resources and reporting resources for the terminal based on the received third association ID and third cell identifier, for the terminal to perform model inference or model monitoring. The reference signal resources or reporting resources may be associated with the first association ID, or associated with the first association ID and the first cell ID.

[0280] If the data characteristics represented by the second piece of information are consistent with the data characteristics of the serving base station, then the following situations may be included:

[0281] Scenario 1: The serving base station sends the cell ID or association ID from the second information. In this case, the UE can only perform model inference, not training data collection, because it does not know the local association ID of the serving base station.

[0282] Scenario 2: The serving base station sends its local association ID without indicating whether it matches the second piece of information. In this case, the UE can only collect training data and cannot initiate model inference or model monitoring. The implied meaning is that the data characteristics indicated by the base station and the second piece of information do not match.

[0283] Scenario 3: The serving base station sends its own local association ID, and also sends the cell ID or association ID from the associated second information. In this case, the UE can simultaneously perform training data collection, model inference, and model monitoring.

[0284] This situation can easily expose the base station implementation, because this information will indicate that a historical base station has the same configuration as the current base station.

[0285] In some embodiments, the data characteristics are used to indicate at least one of the first configuration information, the second configuration information, and the mapping characteristics;

[0286] The first configuration information includes at least one of the following:

[0287] Number of antenna elements;

[0288] The number of antenna elements in the horizontal dimension;

[0289] The number of antenna elements in the vertical dimension;

[0290] Antenna spacing;

[0291] Antenna spacing in the horizontal dimension;

[0292] Antenna spacing in the vertical dimension;

[0293] Mechanical tilt angle;

[0294] Antenna height;

[0295] The orientation of the antenna panel;

[0296] The second configuration information includes at least one of the following:

[0297] Number of beams;

[0298] Number of beams in the horizontal dimension;

[0299] Number of beams in the vertical dimension;

[0300] Beam pointing;

[0301] Half-power beamwidth;

[0302] Beamforming codebook;

[0303] Beamforming codebook in the horizontal dimension;

[0304] Beamforming codebook in the vertical dimension;

[0305] Electron downtilt angle;

[0306] The mapping property includes at least one of the following:

[0307] The mapping relationship between the first configuration information and the associated information;

[0308] The mapping relationship between the second configuration information and the associated information;

[0309] Mapping relationship between physical beam and reference signal RS identifier;

[0310] Mapping relationship between physical beams and beam identifiers.

[0311] Here, the wireless characteristics corresponding to the first configuration information can be understood as the first wireless characteristics, and the wireless characteristics corresponding to the second configuration information can be understood as the second wireless characteristics.

[0312] The above are method embodiments on the first device side. The following describes method embodiments on the second device side.

[0313] Figure 3 This diagram illustrates a flowchart of an information transmission method provided in an embodiment of this application. Figure 3 As shown, the information transmission method includes the following steps:

[0314] Step 301: The second device sends first information to the first device. The first information includes at least one of first indication information and second indication information. The first indication information is used to indicate data characteristic related information corresponding to at least one device, and the second indication information is used to indicate prediction related information.

[0315] In this embodiment, the second device sends first information to the first device, enabling the first device to obtain data characteristics or prediction value indications corresponding to at least one device. Thus, the first device can determine AI units or AI functions that are consistent with the data characteristics based on the data characteristics corresponding to at least one device. This helps to improve the inference stability of AI units or AI functions. Alternatively, the first device can directly make predictions based on the prediction value indications of the second device. This can save the signaling interaction required for the first device to initiate a corresponding prediction request to the second device based on the matched AI unit or AI function.

[0316] In some embodiments, the first indication information includes at least one of the following:

[0317] The first data characteristic corresponding to the second device;

[0318] Artificial intelligence (AI) information related to the first data characteristic;

[0319] Cell information related to the first data characteristic.

[0320] In some embodiments, the first indication information includes at least one of the following:

[0321] At least one first association information, wherein the at least one first association information is associated with the first data characteristic;

[0322] AI information related to at least one first associated information;

[0323] Cell information related to at least one first associated information;

[0324] When the first data characteristic is associated with multiple first associated information, the activation time information of the multiple first associated information;

[0325] The first sub-indicator is used to indicate the association relationship between the plurality of first associated information and AI information.

[0326] In some embodiments, the first association information includes a first association identifier ID, or the first association information includes at least one of a first association ID, a first cell ID, and a first timestamp, wherein the first cell ID is the cell ID of the second device.

[0327] In some embodiments, the method further includes:

[0328] The second device receives second information from the first device. The second information includes third indication information, which is used to indicate data characteristic related information corresponding to the first AI unit or the first AI function. The first AI unit or the first AI function is an AI unit or AI function that can be obtained by the first device.

[0329] In some embodiments, the third indication information includes at least one of the following:

[0330] The third data characteristic;

[0331] The AI ​​information related to the third data characteristic.

[0332] In some embodiments, the third indication information includes at least one of the following:

[0333] At least one third association information, wherein the at least one third association information is associated with the third data characteristic;

[0334] The first set includes multiple sets of the third associated information;

[0335] AI information related to the third associated information;

[0336] AI information related to the first set.

[0337] In some embodiments, the third association information includes a third association ID, or the third association information includes at least one of a third association ID, a third cell ID, and a third timestamp, wherein the third cell ID is the cell ID associated with the first AI unit or the first AI function.

[0338] In some embodiments, the first indication information includes at least one of the following:

[0339] The third sub-indicator is used to indicate whether the first data characteristic corresponding to the second device matches the third data characteristic;

[0340] The fourth sub-indicator is used to indicate whether the second data characteristic corresponding to the third device matches the third data characteristic;

[0341] The third data characteristic;

[0342] AI information related to the third data characteristic;

[0343] The cell information related to the third data characteristic;

[0344] The first data characteristic;

[0345] AI information related to the first data characteristic;

[0346] Cell information related to the first data characteristic.

[0347] In some embodiments, the first indication information includes at least one of the following:

[0348] At least one first association information, wherein the at least one first association information is associated with a first data characteristic corresponding to the second device;

[0349] AI information related to at least one first associated information;

[0350] Cell information related to at least one first associated information;

[0351] When the first data characteristic is associated with multiple first associated information, the activation time information of the multiple first associated information;

[0352] The first sub-indicator is used to indicate the association relationship between the plurality of first associated information and AI information;

[0353] At least one third association information, wherein the at least one third association information is associated with the third data characteristic;

[0354] AI information related to at least one third-party associated information;

[0355] The cell information related to at least one third-party associated information;

[0356] The fifth sub-indicator is used to indicate whether the third data characteristic associated with the at least one third association information matches the first data characteristic corresponding to the second device;

[0357] The sixth sub-indicator is used to indicate whether the third data characteristic associated with the at least one third associated information matches the second data characteristic corresponding to the third device.

[0358] In some embodiments, the second indication information includes at least one of the following:

[0359] Request the predicted value reported by the first device;

[0360] First association information, which is associated with a first data characteristic corresponding to the second device;

[0361] The third association information is associated with the third data characteristic;

[0362] The seventh sub-indicator is used to indicate whether the matched third data feature can be used for training data collection, model fine-tuning, or model training of the AI ​​unit.

[0363] In some embodiments, when the second indication information includes the third association information but does not include the first association information, the third association information is associated with model inference or model monitoring functions, and the third association information is not expected to be used for training data collection or model fine-tuning or model training; or, the configuration information corresponding to the third association information is not expected to be used for training data collection or model fine-tuning or model training.

[0364] In some embodiments, where the second indication information includes the first associated information but does not include the third associated information, the first associated information is permitted to be used for training data collection or model fine-tuning or model training, or the configuration information corresponding to the first associated information is permitted to be used for training data collection or model fine-tuning or model training; the third associated information in the second information is not expected to be used for model inference or model monitoring, or the configuration information corresponding to the third associated information in the second information is not expected to be used for model inference or model monitoring.

[0365] In some embodiments, where the second indication information includes the first association information and the third association information, at least one of the first association information and the third association information is permitted for use in model inference or module monitoring, and at least one of the first association information and the third association information is permitted for use in training data collection or model fine-tuning or model training.

[0366] In some embodiments, the first information is carried in at least one of the following messages:

[0367] Broadcast messages; Channel State Information (CSI) configuration messages; Resource set configuration information; Resource configuration information; Beam Management Set B resource or resource set configuration information; Beam Management Set A resource or resource set configuration information; AI unit prediction reporting messages; AI unit model monitoring reporting messages; AI unit inference reporting messages; Media Access Control Unit (MAC CE); Radio Resource Control (RRC) messages.

[0368] In some embodiments, when the first information is carried in the CSI configuration message and the first indication information simultaneously indicates the first data characteristic and the matching third data characteristic corresponding to the second device, the CSI configuration message is associated with the first association ID and the third association ID, or the CSI configuration message is associated with the first association ID, the third association ID, the first cell ID and the third cell ID, or the CSI configuration message is associated with the first association ID, the third association ID, the first cell ID, the third cell ID and the third timestamp.

[0369] In some embodiments, where the first information is carried in the CSI configuration message, the first indication information simultaneously indicates the first data characteristic and the matching third data characteristic corresponding to the second device, and the CSI configuration message configures a fourth association ID, and the information element IE of the fourth association ID is associated with or configured with a fifth association ID; or, where the first information is carried in the CSI configuration message, the first indication information simultaneously indicates the first data characteristic and the matching third data characteristic corresponding to the second device, and the CSI configuration message configures a fourth association ID and a fourth cell ID, and the IE of the fourth association ID is associated with or configured with a fifth association ID and a fifth cell ID, the fourth association ID is the first association ID, the fourth cell ID is the first cell ID, and the fifth association ID is the third association ID, and the fifth cell ID is the third cell ID; or, the fourth association ID is the third association ID, the fourth cell ID is the third cell ID, and the fifth association ID is the first association ID, and the fifth cell ID is the first cell ID.

[0370] In some embodiments, the method further includes:

[0371] The second device receives third information from the third device, the third information being used to indicate data characteristic related information corresponding to the third device.

[0372] In this implementation, the second device interacts with the third device, enabling the second device to obtain the data characteristics corresponding to the third device. In one implementation, the third device can proactively interact with the second device to exchange its own data characteristics without the second device sending a request, thus saving the signaling overhead required for the second device to send a request.

[0373] In some embodiments, the third information includes at least one of the following:

[0374] The second data characteristic corresponding to the third device;

[0375] AI information related to the second data characteristic;

[0376] The cell information related to the second data characteristic.

[0377] In some embodiments, the third information includes at least one of the following:

[0378] At least one second association information, wherein the at least one second association information is associated with the second data characteristic;

[0379] AI information related to at least one second associated information;

[0380] The cell information related to at least one second associated information;

[0381] The second sub-indicator is used to indicate whether the second associated information has changed.

[0382] In some embodiments, the second association information includes a second association ID, or the second association information includes at least one of a second association ID, a second cell ID, and a second timestamp, wherein the second cell ID is the cell ID of the third device.

[0383] In some embodiments, before the second device receives third information from the third device, the method further includes:

[0384] The second device sends a fourth message to the third device, the fourth message being used to request data characteristic-related information from the third device.

[0385] In this implementation, the third device interacts with the second device based on a request from the second device, sharing its corresponding data characteristics. This way, the third device only interacts with the second device upon receiving a request, reducing unnecessary signaling interactions.

[0386] In some embodiments, the fourth information includes at least one of the following:

[0387] A target set, which is determined based on a first set provided by the first device;

[0388] Target association information, which is determined based on third association information provided by the first device or first association information corresponding to the second device;

[0389] AI information related to the target association information;

[0390] The target-related information includes cell information;

[0391] The fourth instruction information is used to indicate a request for the third device to provide association information associated with the second data characteristic corresponding to the third device;

[0392] The fifth instruction information is used to instruct the third device to provide cell information whose data characteristics are consistent with the second data characteristics;

[0393] The sixth instruction information is used to instruct the third device to provide AI information related to the second data characteristic;

[0394] The seventh instruction information is used to instruct the third device to confirm whether the second data characteristic matches the data characteristic corresponding to the target association information;

[0395] The eighth instruction information is used to instruct the third device to provide cell information whose data characteristics match those of the target association information;

[0396] The ninth instruction information is used to instruct the third device to provide AI information that matches the data characteristics corresponding to the target association information.

[0397] In this implementation, the number of target-related information can be one or more.

[0398] In some embodiments, when the second device receives the third association information, the target association information is determined based on the third association information; when the second device does not receive the third association information, the target association information is determined based on the first association information.

[0399] Optionally, the target association information includes the target association ID, or the target association information includes at least one of the target association ID, the target cell ID, and the target timestamp.

[0400] For example, if the second device receives a third cell ID provided by the first device, the target cell ID is determined based on the third cell ID provided by the first device; if the second device does not receive a third cell ID provided by the first device, the target cell ID is determined based on the first cell ID corresponding to the second device.

[0401] or,

[0402] If the second device receives a third timestamp provided by the first device, the target timestamp is determined based on the third timestamp provided by the first device; if the second device does not receive a third timestamp provided by the first device, the target timestamp is determined based on the first timestamp provided by the second device.

[0403] or,

[0404] If the second device receives a third associated ID provided by the first device, the target associated ID is determined based on the third associated ID provided by the first device; if the second device does not receive a third associated ID provided by the first device, the target associated ID is determined based on the first associated ID corresponding to the second device.

[0405] In some embodiments, the second device performs a second operation, the second operation including at least one of the following:

[0406] Based on the first association information and the third information of the second device, a cell whose data characteristics are consistent with the first association information is determined;

[0407] Based on the third information, the second association information of the third device is obtained;

[0408] Send the first message.

[0409] In some embodiments, the third information includes at least one of the following:

[0410] The tenth indication information is used to indicate whether the second data characteristic matches the data characteristic associated with the target association information;

[0411] The second data characteristic;

[0412] AI information related to the second data characteristic;

[0413] The cell information related to the second data characteristic.

[0414] In some embodiments, the third information further includes at least one of the following:

[0415] The tenth indication information is used to indicate whether the second data characteristic matches the data characteristic associated with the target association information;

[0416] The second association information is associated with the second data characteristic;

[0417] The second related information is related to the cell information;

[0418] AI information related to the second association information;

[0419] The second sub-indicator is used to indicate whether the second associated information has changed.

[0420] In some embodiments, the first indication information further includes at least one of the following:

[0421] The fourth sub-indicator is used to indicate whether the second data characteristic corresponding to the third device matches the third data characteristic;

[0422] The second data characteristic;

[0423] AI information related to the second data characteristic;

[0424] The cell information related to the second data characteristic.

[0425] In some embodiments, the first indication information further includes at least one of the following:

[0426] The second association information is associated with the second data characteristic;

[0427] The second related information is related to the cell information;

[0428] AI information related to the second association information;

[0429] The second sub-indicator is used to indicate whether the second associated information has changed;

[0430] The sixth sub-indicator is used to indicate whether the third data characteristic associated with the at least one third associated information matches the second data characteristic.

[0431] For relevant descriptions of the embodiments in this application, please refer to... Figure 2 The relevant descriptions of the method embodiments, which can achieve the same technical effects, will not be repeated here to avoid repetition.

[0432] The above are method embodiments for the second device side. The following describes method embodiments for the third device side.

[0433] Figure 4 This diagram illustrates a flowchart of an information transmission method provided in an embodiment of this application. Figure 4 As shown, the information transmission method includes the following steps:

[0434] Step 401: The third device sends third information to the second device, the third information being used to indicate data characteristic related information corresponding to the third device.

[0435] In some embodiments, the third information includes at least one of the following:

[0436] The second data characteristic corresponding to the third device;

[0437] AI information related to the second data characteristic;

[0438] The cell information related to the second data characteristic.

[0439] In some embodiments, the third information includes at least one of the following:

[0440] At least one second association information, wherein the at least one second association information is associated with the second data characteristic;

[0441] AI information related to at least one second associated information;

[0442] The cell information related to at least one second associated information;

[0443] The second sub-indicator is used to indicate whether the second associated information has changed.

[0444] In some embodiments, the second association information includes a second association ID, or the second association information includes at least one of a second association ID, a second cell ID, and a second timestamp, wherein the second cell ID is the cell ID of the third device.

[0445] In some embodiments, before the third device sends the third information to the second device, the method further includes:

[0446] The third device receives fourth information from the second device, the fourth information being used to request data characteristic-related information corresponding to the third device.

[0447] In some embodiments, the fourth information includes at least one of the following:

[0448] A target set, which is determined based on a first set provided by the first device;

[0449] Target association information, which is determined based on third association information provided by the first device or first association information corresponding to the second device;

[0450] AI information related to the target association information;

[0451] The target-related information includes cell information;

[0452] The fourth instruction information is used to indicate a request for the third device to provide association information associated with the second data characteristic corresponding to the third device;

[0453] The fifth instruction information is used to instruct the third device to provide cell information whose data characteristics are consistent with the second data characteristics;

[0454] The sixth instruction information is used to instruct the third device to provide AI information related to the second data characteristic;

[0455] The seventh instruction information is used to instruct the third device to confirm whether the second data characteristic matches the data characteristic corresponding to the target association information;

[0456] The eighth instruction information is used to instruct the third device to provide cell information whose data characteristics match those of the target association information;

[0457] The ninth instruction information is used to instruct the third device to provide AI information that matches the data characteristics corresponding to the target association information.

[0458] In some embodiments, the third information includes at least one of the following:

[0459] The tenth indication information is used to indicate whether the second data characteristic matches the data characteristic associated with the target association information;

[0460] The second data characteristic;

[0461] AI information related to the second data characteristic;

[0462] The cell information related to the second data characteristic.

[0463] In some embodiments, the third information includes at least one of the following:

[0464] The tenth indication information is used to indicate whether the second data characteristic matches the data characteristic associated with the target association information;

[0465] The second association information is associated with the second data characteristic;

[0466] The second related information is related to the cell information;

[0467] AI information related to the second association information;

[0468] The second sub-indicator is used to indicate whether the second associated information has changed.

[0469] For relevant descriptions of the embodiments in this application, please refer to... Figure 2 and Figure 3 The relevant descriptions of the method embodiments, which can achieve the same technical effects, will not be repeated here to avoid repetition.

[0470] The following provides several specific embodiments to illustrate the interaction process between the first device, the second device, and the third device. In the following embodiments, the first device is a terminal, the second device is a serving base station (i.e., a serving cell), the third device is a neighboring base station (i.e., a neighboring cell), and the associated information is associated information.

[0471] Example 1: The serving cell actively indicates the data characteristics of its own cell.

[0472] The main idea of ​​this embodiment is that the network-side device actively indicates the association information that represents the data characteristics of the network-side device to the terminal, thereby solving the problem of terminal power consumption waste caused by the terminal needing to blindly try local AI units to find an AI unit that matches the data characteristics of the serving cell. This not only shortens the time for the terminal to start the AI ​​unit and reduces latency, but also reduces the power consumption of the terminal in finding a matching AI unit.

[0473] like Figure 5 As shown, it includes the following steps:

[0474] Step 1: The second device determines the first association information based on the data characteristics corresponding to the devices in this cell;

[0475] Optionally, the second device sends first information to the first device when the second condition is met. The second condition includes at least one of the following:

[0476] The wireless characteristics of the second device have changed;

[0477] The first device undergoes cell handover, and the wireless characteristics corresponding to the associated information change before and after the handover;

[0478] The second device accurately activates the AI ​​unit on the first device side.

[0479] Optionally, the second device sends the first information to the first device according to the first cycle.

[0480] The second device sends the first message only when the second condition is met, which avoids excessive signaling overhead caused by continuously sending the first message. Alternatively, the second device can send the first message at a longer interval (i.e., the first interval), which can also avoid the first device receiving the first message frequently.

[0481] Step 2: The first device receives first information from the second device. This first information includes first association information of the second device. The first association information is used to indicate the data characteristics (including wireless characteristics and mapping characteristics) corresponding to the second device.

[0482] Optionally, the first information includes the first association information of the second device (e.g., the first association ID), and also includes at least one of the following:

[0483] Signage for the service area;

[0484] AI information (e.g., AI features) related to the first associated information.

[0485] Optionally, the wireless characteristic information on the second device side includes at least one of the following:

[0486] The first wireless characteristic, namely the fixed wireless characteristic, or the hardware-dependent wireless characteristic, or the station-dependent wireless characteristic;

[0487] The second wireless characteristic is the adjustable wireless characteristic.

[0488] The first information can be carried in at least one of the following: broadcast message, CSI measurement resource configuration, CSI reporting configuration, MACCE, or RRC reconfiguration message (when the first device is a UE and a cell handover occurs).

[0489] Optionally, the first wireless feature includes at least one of the following:

[0490] Number of antenna elements (including horizontal and vertical dimensions);

[0491] Antenna spacing (including horizontal and vertical dimensions);

[0492] Mechanical tilt angle;

[0493] Antenna height;

[0494] Antenna panel orientation.

[0495] Optionally, the second wireless feature includes at least one of the following:

[0496] Beam pointing;

[0497] Half-power beamwidth (also known as the 3dB bandwidth of the beam);

[0498] Beamforming codebook (including horizontal and vertical dimensions);

[0499] Electron downtilt angle.

[0500] Step 3: The first device determines the consistency of wireless characteristics based on the first information (i.e., determines whether there is a matching AI unit or AI function).

[0501] Optionally, such as Figure 6 As shown, the first device performs a first operation based on first information, the first operation including at least one of the following:

[0502] Collect training data and associate it with the first association information;

[0503] Training data is collected to generate AI units, which are then associated with the first set of related information.

[0504] Identify AI functions that match the first associated information;

[0505] Identify the dataset that matches the first associated information;

[0506] Identify the AI ​​unit that matches the first associated information;

[0507] Predictions for starting service in designated areas.

[0508] Optionally, if an AI unit matching the first association information exists, the first device performs at least one of the following operations:

[0509] Activate the second AI unit, which is an AI unit whose data characteristics match those of the first associated information;

[0510] The second AI unit is monitored in a non-active state (i.e., prediction is initiated first, then the prediction results are monitored, and the prediction results are only reported if the monitoring results meet preset conditions). In this way, since the first device knows whether the data characteristics of the second AI unit or its function match the network data characteristics, the requirements for non-active state model monitoring of the second AI unit can be reduced while ensuring model inference performance. For example, the monitoring duration or the number of monitored samples can be reduced. For instance, if the data characteristics do not match, monitoring 10,000 samples might be necessary, but if the data characteristics match, monitoring only 100 samples can achieve good inference performance.

[0511] Optionally, if no AI unit matches the first association information, the first device performs the following operation:

[0512] Deactivate the third AI unit, which is the currently running AI unit and whose wireless data characteristics do not match those of the first associated information.

[0513] By deactivating the third AI unit and turning off prediction, we can avoid the problem of predictions not meeting expectations due to data mismatch and avoid wasting the computing power of the first device.

[0514] Example 2: Serving cell actively instructs on data characteristics of its own cell and neighboring cells

[0515] Example 1 indicates the data characteristics of the serving cell, while the main idea of ​​this example is that the first information also includes the data characteristics of neighboring cells (third device). On the one hand, the first device can determine whether to switch to a neighboring cell of the cell where the third device is located based on this information, which can ensure that the first device switches to a suitable cell. On the other hand, it solves the prediction delay problem caused by the UE needing to receive information from the neighboring cell before it can start prediction after switching to a neighboring cell. It can save the overhead required for the UE to receive signaling from multiple cells, reduce the power consumption of the UE, and shorten the time to start target cell prediction after switching to a neighboring cell.

[0516] like Figure 7 As shown, it includes the following steps:

[0517] Step 0a (optional): Before step 0b, the second device sends fourth information to the third device, the fourth information being used to request data characteristics corresponding to the third device. The fourth information includes at least one of the following:

[0518] Target-related information (can be one or more, without limitation);

[0519] AI functions corresponding to target association information;

[0520] The cell ID corresponding to the target association information;

[0521] The number of target-related information items;

[0522] The fourth instruction information is used to instruct the third device to provide its second associated information;

[0523] The fifth instruction information is used to instruct the third device to provide a cell ID or cell list that is consistent with its second associated information.

[0524] Optionally, the fourth information includes target association information, or fourth instruction information, or a combination of fourth and fifth instruction information.

[0525] Optionally, the second device determines the target association information based on the association information of the second device.

[0526] For example, when the associated ID is a global ID, the target associated information includes the associated ID; when the associated ID is a cell-local valid ID, the target associated information includes the associated ID and the cell ID; or the target associated information includes the associated ID, the cell ID, and the timestamp.

[0527] Step 0b: Before step 1, the second device obtains third information from the third device, the third information including at least one of the following:

[0528] At least one second associated information of the third device;

[0529] The cell ID or cell list is consistent with the second association information of the third device;

[0530] The cell ID of the third device.

[0531] Optionally, if the third device receives target association information from the second device, the third information may further include at least one of the following:

[0532] Does the data characteristic match the information associated with the target?

[0533] AI capabilities that match the data characteristics of information associated with the target.

[0534] Optionally, the third device performs a third operation, which includes at least one of the following:

[0535] Based on the fourth information, determine whether the data characteristics of the third device match the data characteristics of the target-related information;

[0536] Identify cell IDs or cell lists that maintain consistent data characteristics with the target-related information;

[0537] Identify AI functions that match the characteristics of the information data associated with the target.

[0538] Step 1: The second device performs a second operation, including at least one of the following:

[0539] Based on the first association information and the third information of the second device, determine the cell ID or cell list that is consistent with the data characteristics of the first association information;

[0540] Based on the third information, obtain the second associated information of the third device;

[0541] Based on the third information, obtain the cell ID or cell list that has the same data characteristics as the second related information;

[0542] Send the first message.

[0543] Step 2: The first device obtains first information from the second device (serving cell). The first information includes at least one first association information and at least one second association information, and may also include at least one of the following:

[0544] The identification of the community for the second device;

[0545] AI functions related to the first association information of the second device;

[0546] The cell ID or cell list that maintains wireless characteristics consistent with the first association information of the second device;

[0547] Data characteristic indications corresponding to the association information of the second device;

[0548] The second device has multiple activation patterns for first associated information (e.g., different first associated information is activated at different times);

[0549] The signage for the third-party equipment in the community;

[0550] AI functions related to the second associated information of the third device;

[0551] The cell ID or cell list that maintains wireless characteristics consistent with the second association information of the third device;

[0552] Data characteristic indications corresponding to the second associated information of the third device;

[0553] The third device has multiple activation patterns for second associated information (e.g., different first associated information is activated at different times).

[0554] For example, when the associated ID is a global ID, the first associated information includes the first associated ID, and the second associated information includes the second associated ID; when the associated ID is a cell-local valid ID, the first associated information includes the first associated ID and the cell ID of the second device, and the second associated information includes the second associated ID and the cell ID of the third device.

[0555] After obtaining the initial information, the first device can determine whether to switch to the cell where the third device is located, ensuring that the first device switches to the appropriate cell. Alternatively, after switching to the cell where the third device is located, the terminal can quickly initiate single-cell prediction for the third device, thereby reducing the latency of initiating prediction.

[0556] Optionally, the data characteristic information of the second device includes the first association information of the second device and the identifier of the cell of the second device; the data characteristics of the third device include the second association information of the third device and the cell ID of the third device.

[0557] Optionally, the data characteristic information of the second device includes the first association information of the second device, the identifier of the cell of the second device, and the cell ID or cell list that maintains the same data characteristics as the first association information of the second device; the data characteristics of the third device include the second association information of the third device and the cell ID of the third device, and the cell ID or cell list that maintains the same data characteristics as the second association information of the third device.

[0558] Step 3: As Figure 8 As shown, the first device performs a first operation based on whether to switch to the third device, the first operation including at least one of the following:

[0559] Training data is collected and associated with the first association information of the second device;

[0560] Collect training data, generate AI units, and associate each AI unit with at least one piece of information associated with its training dataset (if data was collected from multiple cells, the associated information of multiple cells can be associated).

[0561] AI function to determine the match between the first association information of the second device;

[0562] Determine the dataset that matches the first association information of the second device;

[0563] Identify the AI ​​unit that matches the first association information of the second device;

[0564] Predictions for activating service cells;

[0565] Based on the data characteristics of the third device, determine whether to switch to the cell where the third device is located;

[0566] After switching to the cell where the third device is located, training data is collected and associated with the previously stored second association information of the third device;

[0567] After switching to the cell where the third device is located, training data is collected to generate an AI unit, and the AI ​​unit is associated with at least one piece of information related to its training dataset (if data is collected in multiple cells, the associated information of multiple cells can be associated).

[0568] After switching to the cell where the third device is located, determine the AI ​​function that matches the second association information of the previously stored third device;

[0569] After switching to the cell where the third device is located, determine the dataset that matches the second association information of the third device that was previously stored;

[0570] After switching to the cell where the third device is located, identify the AI ​​unit that matches the second association information of the previously stored third device.

[0571] Example 3: UE actively requests matching information from the serving cell

[0572] Examples 1 and 2 involve the network actively instructing network devices on their corresponding data characteristics. The main idea of ​​this example is that the terminal actively requests the data characteristic matching status of the third associated information from the second device (the serving cell in the connected state). This solves the problem that the terminal needs to continuously receive messages from the second device, thereby reducing the terminal's signaling overhead and power consumption caused by eavesdropping.

[0573] like Figure 9 As shown, it includes the following steps:

[0574] Step 1: The first device determines whether a first condition is met. If the first condition is met, it sends second information to the second device. The first condition includes at least one of the following:

[0575] Prepare to activate or launch an AI feature / AI use case;

[0576] Deterioration in communication indicators was detected;

[0577] Deterioration in the inference performance of the AI ​​unit was detected;

[0578] The terminal is undergoing cell handover or cell reselection.

[0579] The terminal only sends the second information when the first condition is met, thus avoiding the frequent sending of the second information and saving signaling interaction.

[0580] Step 2: The first device sends second information to the second device. The second information is used to request a match between network data characteristics and terminal AI function data characteristics. The second information includes at least one of the following:

[0581] The third related information (a certain AI unit is only associated with one related information);

[0582] The first set (a set of third-party related information, where an AI unit can be associated with multiple sets of third-party related information);

[0583] The third set of related information or the AI ​​functions associated with the first set;

[0584] The third set of related information or the characteristic indication of the first set of related information;

[0585] The number of third-party related information;

[0586] The number of elements in the first set;

[0587] The target area (i.e., the target cell) to be queried.

[0588] When the associated ID is a global ID, the third associated information includes the third associated ID; or, if the associated ID is a cell-locally valid ID, the third associated information includes the third associated ID and the third cell ID; or, the third associated information includes the third associated ID, the third cell ID, and the third timestamp.

[0589] The second information may be carried in at least one of the following: SR / BSR (mechanism for multiplexing uplink scheduling requests), CSIreport.

[0590] Step 3a (optional): Before step 3b, the second device sends fourth information to the third device, the fourth information being used to request data characteristics corresponding to the third device. The fourth information includes at least one of the following:

[0591] Target association information (can be one or more);

[0592] AI functions corresponding to target association information;

[0593] The number of related information items for the target.

[0594] Optionally, the second device determines the target association information based on the third association information or the first set.

[0595] Step 3b (optional): The second device obtains third information from the third device, the third information including at least one of the following:

[0596] An indication of whether the data characteristics match those of the information associated with the target;

[0597] AI capabilities that match the data characteristics of information associated with the target.

[0598] Optionally, the third device performs a third operation, which includes at least one of the following:

[0599] Based on the fourth information, determine whether the data characteristics of the third device match the data characteristics of the target-related information;

[0600] Identify cell IDs or cell lists that maintain consistent data characteristics with the target-related information;

[0601] Identify AI functions that match the characteristics of the information data associated with the target.

[0602] Step 4: The second device performs a second operation, which includes at least one of the following:

[0603] Based on the second information, determine whether the data characteristics corresponding to the second device match the data characteristics of the third associated information;

[0604] Based on the third information, determine whether the data characteristics corresponding to the third device match the data characteristics of the third associated information;

[0605] Based on the second and third information, determine the cell ID or cell list that is consistent with the data characteristics of the third related information;

[0606] AI functions that match the characteristics of the third related information data are determined based on the second and third information.

[0607] Based on the second information, determine whether the data characteristics of the second device match the data characteristics of the first set;

[0608] Based on the third information, determine whether the data characteristics of the third device match the data characteristics of the first set;

[0609] Based on the second and third information, determine the cell ID or cell list that is consistent with the characteristics of the first set of data;

[0610] Based on the second and third information, determine the AI ​​function that matches the characteristics of the first set of data;

[0611] Send the first message.

[0612] Step 5: The second device sends first information to the first device, the first information including at least one of the following:

[0613] Cell IDs or cell lists that are consistent with the data characteristics of the third related information (which may or may not be based on the target area queried in the second information);

[0614] AI functions that match the characteristics of third-party related information data;

[0615] Cell IDs or cell lists that are consistent with the data characteristics of the first set (which may or may not be based on the target area queried in the second information);

[0616] AI features that match the data characteristics of the first set.

[0617] Step 6: The first device performs a first operation, which includes at least one of the following:

[0618] Determine whether the data characteristics of the cell where the second device is located match the third related information;

[0619] Determine whether the data characteristics of the cell where the second device is located match those of the first set;

[0620] Cell prediction is initiated by activating the second device.

[0621] Optionally, if the first information further includes data characteristic matching information corresponding to the third device, then the first device determines to perform the first operation based on whether to switch to the cell where the third device is located, and the first operation includes at least one of the following:

[0622] Determine whether the data characteristics of the cell where the second device is located match the third related information;

[0623] Determine whether the data characteristics of the cell where the second device is located match those of the first set;

[0624] Cell prediction with the second device activated;

[0625] Based on the data characteristics of the third device, determine whether to switch to the cell where the third device is located;

[0626] Determine whether the data characteristics of the cell where the third device is located match the third associated information;

[0627] Determine whether the data characteristics of the cell where the third device is located match the first set;

[0628] After switching to the cell where the third device is located, cell prediction for the third device is initiated.

[0629] The detailed flowchart is as follows: Figure 10 As shown.

[0630] Example 4: The UE actively requests matching information from the serving cell, and the serving cell directly requests the predicted value.

[0631] Example 3 involves the terminal actively requesting the data characteristic matching of the third association information from the second device (the serving cell in the connected state). The main idea of ​​this example is that the network directly determines the corresponding AI function based on the matching of the third association information or the first set, and requests the corresponding prediction value from the UE. This eliminates the need for the terminal to determine the AI ​​function, thereby reducing the terminal's computing power consumption and the signaling overhead of requesting the network to start prediction.

[0632] like Figure 11As shown, it includes the following steps:

[0633] Step 1: Same as Example 3;

[0634] Step 2: Same as Example 3;

[0635] Step 3: The second device performs a second operation, which includes at least one of the following:

[0636] Based on the second information, determine whether the data characteristics corresponding to the second device match the data characteristics of the third associated information;

[0637] AI functionality based on matching the characteristics of second information with those of third related information;

[0638] Based on the second information, determine whether the data characteristics of the second device match the data characteristics of the first set;

[0639] The AI ​​function that matches the characteristics of the first set of data is determined based on the second information;

[0640] The predicted value requested from the terminal is determined based on the second information;

[0641] Send the first message.

[0642] Step 4: After step 2, the second device sends first information to the first device, the first information including the predicted value requested from the first device.

[0643] Step 5: The first device acquires the first information and performs a first operation based on the first information. The first operation includes:

[0644] Perform predictions and reporting related to the second equipment (serving cell).

[0645] Example 5: UE actively requests matching information from the serving cell - Network configuration report configuration (assuming the associated ID is local information)

[0646] Example 4 involves the terminal requesting data characteristic matching information for the second associated ID from the second device (the serving cell in connected state). The network directly configures the corresponding predicted value. Here, it's assumed the associated ID is a global piece of information. This solves the problem that a third associated ID generated for data collection or AI unit association in cell 1 can correspond to the same physical meaning in cell 2. Therefore, cell 2 can determine whether its data characteristics match the third associated ID based on the associated ID in the second information. The main idea of ​​this example is: assuming the associated ID is cell-local information, for example, the associated ID in cell 1 = 1 and the associated ID in cell 2 = 1, representing different network physical implementations. Whether the physical implementation or network configuration corresponding to the associated ID in cell 1 and cell 2 matches is determined by cell 2 or cell 1. This solves the problem of excessively high maintenance costs for global IDs.

[0647] Refer to the flowchart in Example 4 ( Figure 11 The process includes the following steps:

[0648] Step 1: Same as Example 4;

[0649] Step 2: The terminal sends second information to the second device. The second information is used to request a match between network data characteristics and the terminal's AI function data characteristics. The second information includes at least one of the following:

[0650] At least one third cell identifier, wherein the at least one first cell identifier is the identifier of a cell associated with a third association ID;

[0651] At least one third timestamp, which is a timestamp associated with a third associated ID or a first set;

[0652] At least one third associated ID;

[0653] At least one first set (including multiple third-related information);

[0654] At least one third-party associated ID or AI function associated with the first set;

[0655] At least one third associated ID or characteristic indication of the first set association;

[0656] The number of at least one third associated ID;

[0657] The number of at least one first set.

[0658] Among them, the third cell identifier allows the associated ID to be valid only within the cell, which reduces the maintenance cost of the ID compared to the global ID; the third timestamp allows the associated IDs within a cell to be recycled and redistributed at different times, avoiding an excessive number of associated IDs within the cell and reducing the maintenance cost of associated IDs within the cell.

[0659] The second information may be carried in at least one of the following:

[0660] SR / BSR (Mechanism for reusing uplink scheduling requests); CSI report.

[0661] Step 3a (optional): The second device sends fourth information to the third device, the fourth information being used to request whether the data characteristics of the third device match the target data characteristics. The fourth information includes at least one of the following: the target cell identifier associated with the target association information (in this embodiment, it is determined based on the third cell identifier; in embodiment 2, it is determined based on the cell identifier of the second device);

[0662] The target timestamp associated with the target information (in this embodiment, it is determined based on the third timestamp; in embodiment 2, it is based on the first timestamp corresponding to the cell identifier of the second device (the timestamp that the second device wants to query));

[0663] The target set, in this embodiment, is determined by the first set (the first set is a set of third associated information, which includes at least one of cell identifier, association ID, and timestamp);

[0664] The target association ID (can be one or more) associated with the target association information;

[0665] The AI ​​function or AI feature corresponding to the target associated ID;

[0666] The number of target associated IDs.

[0667] Optionally, the second device determines the target cell identifier based on the third cell identifier;

[0668] Optionally, the second device determines the target timestamp based on a third timestamp;

[0669] Step 3b (optional): The second device obtains third information from the third device, the third information including at least one of the following:

[0670] Does the data characteristic match the information associated with the target?

[0671] AI capabilities that match the data characteristics of information associated with the target;

[0672] The association ID associated with the target information;

[0673] The timestamp associated with the target information;

[0674] The cell identifier associated with the target information.

[0675] Optionally, the third device performs a third operation, which includes at least one of the following:

[0676] Based on the fourth information, it is determined whether the data characteristics of the third device match the target data characteristics, wherein the target data characteristics are determined by the target association ID, the target cell identifier, and the target timestamp;

[0677] Identify cell IDs or cell lists that are consistent with the target data characteristics;

[0678] Identify AI functions or AI characteristics that match the characteristics of the target data.

[0679] Step 4: The second device performs a second operation, which includes at least one of the following:

[0680] Based on the second information, it is determined whether the data characteristics of the second device match the third data characteristics, wherein the third data characteristics are determined by at least one of the third association ID, the third timestamp, and the third cell identifier;

[0681] AI functions that match the characteristics of the third data based on the second information;

[0682] Based on the second information, it is determined whether the data characteristics of the second device match the data characteristics of the first set, where the first set is a set of third data characteristics;

[0683] Based on the second information, determine the AI ​​function or AI characteristic that matches the characteristics of the first set of data;

[0684] The predicted value requested from the terminal is determined based on the second information;

[0685] Send the first message.

[0686] Step 5: The first network device sends first information to the terminal, the first information including at least one of the following:

[0687] The predicted value requested from the terminal;

[0688] At least one first association ID, wherein the at least one first association ID is related to a third association ID associated with the second information;

[0689] At least one third associated ID.

[0690] Optionally, the first information may also include at least one of the following:

[0691] At least one timestamp associated with at least one third-party ID or a third-party cell ID;

[0692] At least one cell ID associated with the at least one third associated ID or third cell ID;

[0693] At least one timestamp associated with a third association ID or a third cell ID;

[0694] At least one cell ID associated with a third association ID or a third cell ID;

[0695] First set;

[0696] The seventh sub-indicator is used to indicate that the third association ID is applicable to model inference or model monitoring, but not to training data collection.

[0697] Optionally, the first information is carried by the reporting configuration. The reporting configuration includes at least one of the following: prediction reporting configuration, inference reporting configuration, and monitoring reporting configuration.

[0698] Optionally, at least one second association ID or third association ID is configured or associated with at least one of the following: configuration information for CSI measurements (e.g., CSI-MeasConfig), configuration information for CSI reports (e.g., CSI-ReportConfig), configuration information for CSI resource lists (e.g., CSI-ResourceConfig), configuration information for resource sets (e.g., CSI-SSB-ResourceSet, NZP-CSI-RS-ResourceSet), configuration information for resources (e.g., NZP-CSI-RS-Resource), configuration information for Set B resources or resource sets, and configuration information for Set A resources or resource sets.

[0699] If the data characteristics represented by the second piece of information are consistent with the data characteristics of the serving base station, then the following situations may be included:

[0700] Scenario 1: The serving base station sends the cell ID or association ID from the second information. In this case, the UE can only perform model inference, not training data collection, because it does not know the local association ID of the serving base station.

[0701] Scenario 2: The serving base station sends its local association ID without indicating whether it matches the second piece of information. In this case, the UE can only collect training data and cannot initiate model inference or model monitoring. The implied meaning is that the data characteristics indicated by the base station and the second piece of information do not match.

[0702] Scenario 3: The serving base station sends its own local association ID, and also sends the cell ID or association ID from the associated second information. In this case, the UE can simultaneously perform training data collection, model inference, and model monitoring.

[0703] This situation can easily expose the base station implementation, because this information will indicate that a historical base station has the same configuration as the current base station.

[0704] Step 6: The terminal obtains the first information and makes predictions and reports related to the second device (serving cell) based on the first information.

[0705] Optionally, if the first information includes a seventh sub-instruction, the terminal performs model inference and model monitoring based on the first information. If training data collection is required, the first association ID needs to be additionally requested from the second device.

[0706] The above are the relevant descriptions of Examples 1 to 5.

[0707] Through the solutions described in the above embodiments, the network-side device actively indicates the association information of the implicit representation of the data characteristics of the serving cell and neighboring cell network devices, or the UE actively requests the matching of the association information of the AI ​​unit with the data characteristics of the serving cell and neighboring cells. This avoids the UE blindly trying multiple AI units (e.g., using inactive model monitoring) before finding an AI unit that matches the cell data characteristics and initiating predictions related to the serving cell. The first device can also use the data characteristics of neighboring cells as one of the criteria for deciding whether to switch to a neighboring cell. After switching to a neighboring cell, the terminal can determine whether to enable predictions for the neighboring cell based on pre-stored information. This can reduce the terminal's power consumption and computing power, shorten the decision latency for initiating serving cell prediction, and shorten the decision latency for initiating target cell prediction after handover.

[0708] In this embodiment of the application, the correspondence (or mapping relationship) between associated information (such as associated ID) and data characteristics (or wireless characteristics) is explained as follows:

[0709] Table 1: Correspondence between the associated information available to the second or third device and the first wireless characteristic

[0710]

[0711] The mapping relationship between the associated information and the first wireless characteristic is preferably a one-to-one mapping, but in some special cases, a one-to-many mapping relationship is also possible.

[0712] Table 2: Correspondence between the associated information available to the second or third device and the second wireless characteristics

[0713]

[0714]

[0715] The mapping relationship between the associated information and the second wireless characteristic is preferably a one-to-one mapping, but in some special cases, a one-to-many mapping relationship is also possible.

[0716] Table 3: Correspondence between the associated information available to the second or third device and the first and second wireless characteristics.

[0717]

[0718]

[0719] The associated information can be mapped to the first wireless characteristic and the second wireless characteristic. Preferably, it is a one-to-one mapping, but in some special cases, a one-to-many mapping relationship is also possible.

[0720] It should be noted that the embodiments of this application can be applied to various communication scenarios, such as beam prediction, CSI prediction, etc.

[0721] The information transmission method provided in this application can be executed by an information transmission device. This application uses an information transmission device executing the information transmission method as an example to illustrate the information transmission device provided in this application.

[0722] This application provides an information transmission device. As an example, the information transmission device may be a communication device or a component within a communication device, such as a chip. The communication device may be a terminal, a network-side device, or a server, etc. Exemplarily, the terminal may include, but is not limited to, the type of terminal 11 listed above, and the network-side device may include, but is not limited to, the type of network-side device 12 listed above. This application does not impose specific limitations.

[0723] The information transmission device includes a receiving module, a transmitting module, and a processing module. These modules can be implemented in software or hardware. When implemented in hardware, the processing module can be implemented by a processor. For example, the processor can include general-purpose processors, special-purpose processors, such as a Central Processing Unit (CPU), microprocessor, Digital Signal Processor (DSP), Artificial Intelligence (AI) processor, Graphics Processing Unit (GPU), Application Specific Integrated Circuit (ASIC), Network Processor (NP), Field Programmable Gate Array (FPGA), or other programmable logic devices, gate circuits, transistors, discrete hardware components, etc. The receiving and transmitting modules can be implemented by a communication interface, which can include one or more of the following: transceiver, pins, circuits, bus, radio frequency unit, etc.

[0724] For details, see Figure 12 When the information transmission device is a terminal or a component within a terminal, the information transmission device 1200 includes:

[0725] The receiving module 1201 is configured to receive first information from the second device, the first information including at least one of first indication information and second indication information, wherein the first indication information is used to indicate data characteristic related information corresponding to at least one device, and the second indication information is used to indicate prediction related information.

[0726] The processing module 1202 is used to perform a first operation based on the first information, wherein the first operation is an operation related to artificial intelligence (AI).

[0727] Optionally, the first indication information includes at least one of the following:

[0728] The first data characteristic corresponding to the second device;

[0729] AI information related to the first data characteristic;

[0730] Cell information related to the first data characteristic;

[0731] The second data characteristic corresponding to the third device;

[0732] AI information related to the second data characteristic;

[0733] Cell information related to the second data characteristic;

[0734] or,

[0735] The first indication information includes at least one of the following:

[0736] At least one first association information, wherein the at least one first association information is associated with the first data characteristic;

[0737] AI information related to at least one first associated information;

[0738] Cell information related to at least one first associated information;

[0739] When the first data characteristic is associated with multiple first associated information, the activation time information of the multiple first associated information;

[0740] The first sub-indicator is used to indicate the association relationship between the plurality of first associated information and AI information;

[0741] At least one second association information, wherein the at least one second association information is associated with the second data characteristic;

[0742] AI information related to at least one second associated information;

[0743] The cell information related to at least one second associated information;

[0744] The second sub-indicator is used to indicate whether the second associated information has changed.

[0745] Optionally, the first association information includes a first association identifier ID, or the first association information includes at least one of a first association ID, a first cell ID, and a first timestamp, wherein the first cell ID is the cell ID of the second device;

[0746] or,

[0747] The second association information includes a second association ID, or the second association information includes at least one of a second association ID, a second cell ID, and a second timestamp, wherein the second cell ID is the cell ID of the third device.

[0748] Optionally, the device further includes:

[0749] The sending module is used to send second information to the second device. The second information includes third indication information, which is used to indicate data characteristic related information corresponding to the first AI unit or the first AI function. The first AI unit or the first AI function is an AI unit or AI function that can be obtained by the first device.

[0750] Optionally, the sending module is specifically used for:

[0751] If the first condition is met, send the second information to the second device;

[0752] The first condition includes at least one of the following:

[0753] Prepare to activate or start the first AI unit or the first AI function;

[0754] The communication index of the cell where the second device is located was detected to be lower than a preset threshold;

[0755] Deterioration in the inference performance of the first AI unit or the first AI function was detected.

[0756] The first device undergoes cell handover or cell reselection.

[0757] Optionally, the third indication information includes at least one of the following:

[0758] The third data characteristic corresponding to the first AI unit or the first AI function;

[0759] AI information related to the third data characteristic;

[0760] or,

[0761] The third indication information includes at least one of the following:

[0762] At least one third association information, wherein the at least one third association information is associated with the third data characteristic;

[0763] The first set includes multiple sets of the third associated information;

[0764] AI information related to the third associated information;

[0765] AI information related to the first set.

[0766] Optionally, the third association information includes a third association ID, or the third association information includes at least one of a third association ID, a third cell ID, and a third timestamp, wherein the third cell ID is the cell ID associated with the first AI unit or the first AI function.

[0767] Optionally, the first indication information includes at least one of the following:

[0768] The third sub-indicator is used to indicate whether the first data characteristic corresponding to the second device matches the third data characteristic corresponding to the first AI unit or the first AI function.

[0769] The fourth sub-indicator is used to indicate whether the second data characteristic corresponding to the third device matches the third data characteristic;

[0770] The third data characteristic;

[0771] AI information related to the third data characteristic;

[0772] The cell information related to the third data characteristic;

[0773] The first data characteristic;

[0774] AI information related to the first data characteristic;

[0775] Cell information related to the first data characteristic;

[0776] The second data characteristic;

[0777] AI information related to the second data characteristic;

[0778] Cell information related to the second data characteristic;

[0779] or,

[0780] The first indication information includes at least one of the following:

[0781] At least one first association information, wherein the at least one first association information is associated with a first data characteristic corresponding to the second device;

[0782] AI information related to at least one first associated information;

[0783] Cell information related to at least one first associated information;

[0784] When the first data characteristic is associated with multiple first associated information, the activation time information of the multiple first associated information;

[0785] The first sub-indicator is used to indicate the association relationship between the plurality of first associated information and AI information;

[0786] At least one second association information, wherein the at least one second association information is associated with the second data characteristic;

[0787] AI information related to at least one second associated information;

[0788] The cell information related to at least one second associated information;

[0789] The second sub-indicator is used to indicate whether the second associated information has changed;

[0790] At least one third association information, wherein the at least one third association information is associated with the third data characteristic;

[0791] AI information related to at least one third-party associated information;

[0792] The cell information related to at least one third-party associated information;

[0793] The fifth sub-indicator is used to indicate whether the third data characteristic associated with the at least one third association information matches the first data characteristic corresponding to the second device;

[0794] The sixth sub-indicator is used to indicate whether the third data characteristic associated with the at least one third associated information matches the second data characteristic corresponding to the third device.

[0795] Optionally, the second indication information includes at least one of the following:

[0796] Request the predicted value reported by the first device;

[0797] First association information, which is associated with a first data characteristic corresponding to the second device;

[0798] The third association information is associated with the third data characteristic corresponding to the first AI unit or the first AI function;

[0799] The seventh sub-indicator is used to indicate whether the matched third data feature can be used for training data collection, model fine-tuning, or model training of the AI ​​unit.

[0800] Optionally, if the second indication information includes the third association information but does not include the first association information, the third association information is associated with model inference or model monitoring functions, and the third association information is not expected to be used for training data collection, model fine-tuning or model training; or, the configuration information corresponding to the third association information is not expected to be used for training data collection, model fine-tuning or model training.

[0801] or,

[0802] When the second indication information includes the first associated information but does not include the third associated information, the first associated information is permitted to be used for training data collection, model fine-tuning, or model training; or, the configuration information corresponding to the first associated information is permitted to be used for training data collection, model fine-tuning, or model training. The third associated information in the second information is not expected to be used for model inference or model monitoring; or, the configuration information corresponding to the third associated information in the second information is not expected to be used for model inference or model monitoring.

[0803] or,

[0804] When the second indication information includes the first association information and the third association information, at least one of the first association information and the third association information is allowed to be used for model inference or module monitoring, and at least one of the first association information and the third association information is allowed to be used for training data collection or model fine-tuning or model training.

[0805] Optionally, the first information is carried in at least one of the following messages:

[0806] Broadcast messages; Channel State Information (CSI) configuration messages; Resource set configuration information; Resource configuration information; Beam Management Set B resource or resource set configuration information; Beam Management Set A resource or resource set configuration information; AI unit prediction reporting messages; AI unit model monitoring reporting messages; AI unit inference reporting messages; Media Access Control Unit (MAC CE); Radio Resource Control (RRC) messages.

[0807] Optionally, when the first information is carried in the CSI configuration message, and the first indication information simultaneously indicates the first data characteristic and the matching third data characteristic corresponding to the second device, the CSI configuration message is associated with the first association ID and the third association ID; or, the CSI configuration message is associated with the first association ID, the third association ID, the first cell ID and the third cell ID; or, the CSI configuration message is associated with the first association ID, the third association ID, the first cell ID, the third cell ID and the third timestamp.

[0808] or,

[0809] In the case where the first information is carried in the CSI configuration message, the first indication information simultaneously indicates the first data characteristic and the matching third data characteristic corresponding to the second device, and the CSI configuration message configures a fourth association ID, and the information element IE of the fourth association ID is associated with or configured with a fifth association ID; or, in the case where the first information is carried in the CSI configuration message, the first indication information simultaneously indicates the first data characteristic and the matching third data characteristic corresponding to the second device, and the CSI configuration message configures a fourth association ID and a fourth cell ID, and the IE of the fourth association ID is associated with or configured with a fifth association ID and a fifth cell ID, the fourth association ID is the first association ID, the fourth cell ID is the first cell ID, and the fifth association ID is the third association ID, and the fifth cell ID is the third cell ID; or, the fourth association ID is the third association ID, the fourth cell ID is the third cell ID, and the fifth association ID is the first association ID, and the fifth cell ID is the first cell ID.

[0810] Optionally, the data characteristics are used to indicate at least one of the first configuration information, the second configuration information, and the mapping characteristics;

[0811] The first configuration information includes at least one of the following:

[0812] Number of antenna elements;

[0813] The number of antenna elements in the horizontal dimension;

[0814] The number of antenna elements in the vertical dimension;

[0815] Antenna spacing;

[0816] Antenna spacing in the horizontal dimension;

[0817] Antenna spacing in the vertical dimension;

[0818] Mechanical tilt angle;

[0819] Antenna height;

[0820] The orientation of the antenna panel;

[0821] The second configuration information includes at least one of the following:

[0822] Number of beams;

[0823] Number of beams in the horizontal dimension;

[0824] Number of beams in the vertical dimension;

[0825] Beam pointing;

[0826] Half-power beamwidth;

[0827] Beamforming codebook;

[0828] Beamforming codebook in the horizontal dimension;

[0829] Beamforming codebook in the vertical dimension;

[0830] Electron downtilt angle;

[0831] The mapping property includes at least one of the following:

[0832] The mapping relationship between the first configuration information and the associated information;

[0833] The mapping relationship between the second configuration information and the associated information;

[0834] Mapping relationship between physical beam and reference signal RS identifier;

[0835] Mapping relationship between physical beams and beam identifiers.

[0836] Optionally, the first operation includes at least one of the following:

[0837] Identify the AI ​​unit or AI function that matches the first data characteristic corresponding to the second device;

[0838] Determine a first dataset that matches the first data characteristic;

[0839] Determine the AI ​​unit or AI function corresponding to the first dataset;

[0840] Initiate prediction for the cell where the second device is located;

[0841] Activate the second AI unit or the second AI function, wherein the second AI unit or the second AI function is an AI unit or AI function whose data characteristics match the first data characteristics;

[0842] Perform inactive model monitoring on the second AI unit or the second AI function;

[0843] Deactivate the third AI unit or the third AI function, wherein the third AI unit or the third AI function is an AI unit or AI function whose data characteristics do not match the first data characteristics;

[0844] Collect the first training data and associate the first training data with the first data characteristics;

[0845] Based on the first training data, a fourth AI unit or a fourth AI function is generated, and the fourth AI unit or the fourth AI function is associated with the first data characteristics.

[0846] Optionally, the at least one device further includes a third device;

[0847] The first operation further includes at least one of the following:

[0848] Based on the second data characteristics corresponding to the third device, determine whether to switch to the cell where the third device is located;

[0849] Identify the AI ​​unit or AI function that matches the second data characteristic;

[0850] Determine a second dataset that matches the second data characteristic;

[0851] Determine the AI ​​unit or AI function corresponding to the second dataset;

[0852] If the first device switches to the cell where the third device is located, prediction of the cell where the third device is located is initiated;

[0853] When the first device switches to the cell where the third device is located, second training data is collected, and the second training data is associated with the second data characteristics;

[0854] Based on the second training data, a fifth AI unit or a fifth AI function is generated, and the fifth AI unit or the fifth AI function is associated with the second data characteristics.

[0855] The information transmission device provided in this application embodiment can achieve... Figure 2 The various processes implemented in the method embodiments achieve the same technical effect, and will not be described again here to avoid repetition.

[0856] The information transmission method provided in this application can be executed by an information transmission device. This application uses an information transmission device executing the information transmission method as an example to illustrate the information transmission device provided in this application.

[0857] This application provides an information transmission device. As an example, the information transmission device may be a communication device or a component within a communication device, such as a chip. The communication device may be a terminal, a network-side device, or a server, etc. Exemplarily, the terminal may include, but is not limited to, the type of terminal 11 listed above, and the network-side device may include, but is not limited to, the type of network-side device 12 listed above. This application does not impose specific limitations.

[0858] The information transmission device includes a receiving module, a transmitting module, and a processing module. These modules can be implemented in software or hardware. When implemented in hardware, the processing module can be implemented by a processor. For example, the processor can include general-purpose processors, special-purpose processors, such as a Central Processing Unit (CPU), microprocessor, Digital Signal Processor (DSP), Artificial Intelligence (AI) processor, Graphics Processing Unit (GPU), Application Specific Integrated Circuit (ASIC), Network Processor (NP), Field Programmable Gate Array (FPGA), or other programmable logic devices, gate circuits, transistors, discrete hardware components, etc. The receiving and transmitting modules can be implemented by a communication interface, which can include one or more of the following: transceiver, pins, circuits, bus, radio frequency unit, etc.

[0859] Specifically, see Figure 13 When the information transmission device is a network-side device or a component within a network-side device, the information transmission device 1300 includes:

[0860] The first sending module 1301 is used to send first information to the first device. The first information includes at least one of first indication information and second indication information. The first indication information is used to indicate data characteristic related information corresponding to at least one device, and the second indication information is used to indicate prediction related information.

[0861] Optionally, the first indication information includes at least one of the following:

[0862] The first data characteristic corresponding to the second device;

[0863] Artificial intelligence (AI) information related to the first data characteristic;

[0864] Cell information related to the first data characteristic;

[0865] or,

[0866] The first indication information includes at least one of the following:

[0867] At least one first association information, wherein the at least one first association information is associated with the first data characteristic;

[0868] AI information related to at least one first associated information;

[0869] Cell information related to at least one first associated information;

[0870] When the first data characteristic is associated with multiple first associated information, the activation time information of the multiple first associated information;

[0871] The first sub-indicator is used to indicate the association relationship between the plurality of first associated information and AI information.

[0872] Optionally, the first association information includes a first association identifier ID, or the first association information includes at least one of a first association ID, a first cell ID, and a first timestamp, wherein the first cell ID is the cell ID of the second device.

[0873] Optionally, the device further includes:

[0874] The first receiving module is configured to receive second information from the first device. The second information includes third indication information, which is used to indicate data characteristic related information corresponding to the first AI unit or the first AI function. The first AI unit or the first AI function is an AI unit or AI function that can be obtained by the first device.

[0875] Optionally, the third indication information includes at least one of the following:

[0876] The third data characteristic corresponding to the first AI unit or the first AI function;

[0877] AI information related to the third data characteristic;

[0878] or,

[0879] The third indication information includes at least one of the following:

[0880] At least one third association information, wherein the at least one third association information is associated with the third data characteristic;

[0881] The first set includes multiple sets of the third associated information;

[0882] AI information related to the third associated information;

[0883] AI information related to the first set.

[0884] Optionally, the third association information includes a third association ID, or the third association information includes at least one of a third association ID, a third cell ID, and a third timestamp, wherein the third cell ID is the cell ID associated with the first AI unit or the first AI function.

[0885] Optionally, the first indication information includes at least one of the following:

[0886] The third sub-indicator is used to indicate whether the first data characteristic corresponding to the second device matches the third data characteristic corresponding to the first AI unit or the first AI function.

[0887] The third data characteristic;

[0888] AI information related to the third data characteristic;

[0889] The cell information related to the third data characteristic;

[0890] The first data characteristic;

[0891] AI information related to the first data characteristic;

[0892] Cell information related to the first data characteristic;

[0893] or,

[0894] The first indication information includes at least one of the following:

[0895] At least one first association information, wherein the at least one first association information is associated with a first data characteristic corresponding to the second device;

[0896] AI information related to at least one first associated information;

[0897] Cell information related to at least one first associated information;

[0898] When the first data characteristic is associated with multiple first associated information, the activation time information of the multiple first associated information;

[0899] The first sub-indicator is used to indicate the association relationship between the plurality of first associated information and AI information;

[0900] At least one third association information, wherein the at least one third association information is associated with the third data characteristic;

[0901] AI information related to at least one third-party associated information;

[0902] The cell information related to at least one third-party associated information;

[0903] The fifth sub-indicator is used to indicate whether the third data characteristic associated with the at least one third association information matches the first data characteristic corresponding to the second device.

[0904] Optionally, the second indication information includes at least one of the following:

[0905] Request the predicted value reported by the first device;

[0906] First association information, which is associated with a first data characteristic corresponding to the second device;

[0907] The third association information is associated with the third data characteristic corresponding to the first AI unit or the first AI function;

[0908] The seventh sub-indicator is used to indicate whether the matched third data feature can be used for training data collection, model fine-tuning, or model training of the AI ​​unit.

[0909] Optionally, if the second indication information includes the third association information but does not include the first association information, the third association information is associated with model inference or model monitoring functions, and the third association information is not expected to be used for training data collection, model fine-tuning or model training; or, the configuration information corresponding to the third association information is not expected to be used for training data collection, model fine-tuning or model training.

[0910] or,

[0911] When the second indication information includes the first associated information but does not include the third associated information, the first associated information is permitted to be used for training data collection, model fine-tuning, or model training; or, the configuration information corresponding to the first associated information is permitted to be used for training data collection, model fine-tuning, or model training. The third associated information in the second information is not expected to be used for model inference or model monitoring; or, the configuration information corresponding to the third associated information in the second information is not expected to be used for model inference or model monitoring.

[0912] or,

[0913] When the second indication information includes the first association information and the third association information, at least one of the first association information and the third association information is allowed to be used for model inference or module monitoring, and at least one of the first association information and the third association information is allowed to be used for training data collection or model fine-tuning or model training.

[0914] Optionally, the first information is carried in at least one of the following messages:

[0915] Broadcast messages; Channel State Information (CSI) configuration messages; Resource set configuration information; Resource configuration information; Beam Management Set B resource or resource set configuration information; Beam Management Set A resource or resource set configuration information; AI unit prediction reporting messages; AI unit model monitoring reporting messages; AI unit inference reporting messages; Media Access Control Unit (MAC CE); Radio Resource Control (RRC) messages.

[0916] Optionally, when the first information is carried in the CSI configuration message, and the first indication information simultaneously indicates the first data characteristic and the matching third data characteristic corresponding to the second device, the CSI configuration message is associated with the first association ID and the third association ID; or, the CSI configuration message is associated with the first association ID, the third association ID, the first cell ID and the third cell ID; or, the CSI configuration message is associated with the first association ID, the third association ID, the first cell ID, the third cell ID and the third timestamp.

[0917] or,

[0918] In the case where the first information is carried in the CSI configuration message, the first indication information simultaneously indicates the first data characteristic and the matching third data characteristic corresponding to the second device, and the CSI configuration message configures a fourth association ID, and the information element IE of the fourth association ID is associated with or configured with a fifth association ID; or, in the case where the first information is carried in the CSI configuration message, the first indication information simultaneously indicates the first data characteristic and the matching third data characteristic corresponding to the second device, and the CSI configuration message configures a fourth association ID and a fourth cell ID, and the IE of the fourth association ID is associated with or configured with a fifth association ID and a fifth cell ID, the fourth association ID is the first association ID, the fourth cell ID is the first cell ID, and the fifth association ID is the third association ID, and the fifth cell ID is the third cell ID; or, the fourth association ID is the third association ID, the fourth cell ID is the third cell ID, and the fifth association ID is the first association ID, and the fifth cell ID is the first cell ID.

[0919] Optionally, the device further includes:

[0920] The second receiving module is used to receive third information from the third device, the third information being used to indicate data characteristic related information corresponding to the third device.

[0921] Optionally, the third information includes at least one of the following:

[0922] The second data characteristic corresponding to the third device;

[0923] AI information related to the second data characteristic;

[0924] Cell information related to the second data characteristic;

[0925] or,

[0926] The third information includes at least one of the following:

[0927] At least one second association information, wherein the at least one second association information is associated with the second data characteristic;

[0928] AI information related to at least one second associated information;

[0929] The cell information related to at least one second associated information;

[0930] The second sub-indicator is used to indicate whether the second associated information has changed.

[0931] Optionally, the second association information includes a second association ID, or the second association information includes at least one of a second association ID, a second cell ID, and a second timestamp, wherein the second cell ID is the cell ID of the third device.

[0932] Optionally, the device further includes:

[0933] The second sending module is used to send fourth information to the third device, the fourth information being used to request data characteristic related information corresponding to the third device.

[0934] Optionally, the fourth information includes at least one of the following:

[0935] A target set, which is determined based on a first set provided by the first device;

[0936] Target association information, which is determined based on third association information provided by the first device or first association information corresponding to the second device;

[0937] AI information related to the target association information;

[0938] The target-related information includes cell information;

[0939] The fourth instruction information is used to indicate a request for the third device to provide association information associated with the second data characteristic corresponding to the third device;

[0940] The fifth instruction information is used to instruct the third device to provide cell information whose data characteristics are consistent with the second data characteristics;

[0941] The sixth instruction information is used to instruct the third device to provide AI information related to the second data characteristic;

[0942] The seventh instruction information is used to instruct the third device to confirm whether the second data characteristic matches the data characteristic corresponding to the target association information;

[0943] The eighth instruction information is used to instruct the third device to provide cell information whose data characteristics match those of the target association information;

[0944] The ninth instruction information is used to instruct the third device to provide AI information that matches the data characteristics corresponding to the target association information.

[0945] Optionally, if the second device receives the third association information, the target association information is determined based on the third association information; if the second device does not receive the third association information, the target association information is determined based on the first association information.

[0946] Optionally, the third information includes at least one of the following:

[0947] The tenth indication information is used to indicate whether the second data characteristic matches the data characteristic associated with the target association information;

[0948] The second data characteristic;

[0949] AI information related to the second data characteristic;

[0950] Cell information related to the second data characteristic;

[0951] or,

[0952] The third information includes at least one of the following:

[0953] The tenth indication information is used to indicate whether the second data characteristic matches the data characteristic associated with the target association information;

[0954] The second association information is associated with the second data characteristic;

[0955] The second related information is related to the cell information;

[0956] AI information related to the second association information;

[0957] The second sub-indicator is used to indicate whether the second associated information has changed.

[0958] Optionally, the first indication information further includes at least one of the following:

[0959] The fourth sub-indicator is used to indicate whether the second data characteristic corresponding to the third device matches the third data characteristic;

[0960] The second data characteristic;

[0961] AI information related to the second data characteristic;

[0962] Cell information related to the second data characteristic;

[0963] or,

[0964] The first indication information also includes at least one of the following:

[0965] The second association information is associated with the second data characteristic;

[0966] The second related information is related to the cell information;

[0967] AI information related to the second association information;

[0968] The second sub-indicator is used to indicate whether the second associated information has changed;

[0969] The sixth sub-indicator is used to indicate whether the third data characteristic associated with the at least one third associated information matches the second data characteristic.

[0970] The information transmission device provided in this application embodiment can achieve... Figure 3 The various processes implemented in the method embodiments achieve the same technical effect, and will not be described again here to avoid repetition.

[0971] Specifically, see Figure 14 When the information transmission device is a network-side device or a component within a network-side device, the information transmission 1400 includes:

[0972] The sending module 1401 is used to send third information to the second device, the third information being used to indicate data characteristic related information corresponding to the third device.

[0973] Optionally, the third information includes at least one of the following:

[0974] The second data characteristic corresponding to the third device;

[0975] AI information related to the second data characteristic;

[0976] Cell information related to the second data characteristic;

[0977] or,

[0978] The third information includes at least one of the following:

[0979] At least one second association information, wherein the at least one second association information is associated with the second data characteristic;

[0980] AI information related to at least one second associated information;

[0981] The cell information related to at least one second associated information;

[0982] The second sub-indicator is used to indicate whether the second associated information has changed.

[0983] Optionally, the second association information includes a second association ID, or the second association information includes at least one of a second association ID, a second cell ID, and a second timestamp, wherein the second cell ID is the cell ID of the third device.

[0984] Optionally, the device further includes:

[0985] The receiving module is used to receive fourth information from the second device, the fourth information being used to request data characteristic related information corresponding to the third device.

[0986] Optionally, the fourth information includes at least one of the following:

[0987] A target set, the target set being determined based on a first set provided by a first device;

[0988] Target association information, which is determined based on third association information provided by the first device or first association information corresponding to the second device;

[0989] AI information related to the target association information;

[0990] The target-related information includes cell information;

[0991] The fourth instruction information is used to indicate a request for the third device to provide association information associated with the second data characteristic corresponding to the third device;

[0992] The fifth instruction information is used to instruct the third device to provide cell information whose data characteristics are consistent with the second data characteristics;

[0993] The sixth instruction information is used to instruct the third device to provide AI information related to the second data characteristic;

[0994] The seventh instruction information is used to instruct the third device to confirm whether the second data characteristic matches the data characteristic corresponding to the target association information;

[0995] The eighth instruction information is used to instruct the third device to provide cell information whose data characteristics match those of the target association information;

[0996] The ninth instruction information is used to instruct the third device to provide AI information that matches the data characteristics corresponding to the target association information.

[0997] Optionally, the third information includes at least one of the following:

[0998] The tenth indication information is used to indicate whether the second data characteristic matches the data characteristic associated with the target association information;

[0999] The second data characteristic;

[1000] AI information related to the second data characteristic;

[1001] Cell information related to the second data characteristic;

[1002] or,

[1003] The third information includes at least one of the following:

[1004] The tenth indication information is used to indicate whether the second data characteristic matches the data characteristic associated with the target association information;

[1005] The second association information is associated with the second data characteristic;

[1006] The second related information is related to the cell information;

[1007] AI information related to the second association information;

[1008] The second sub-indicator is used to indicate whether the second associated information has changed.

[1009] The information transmission device provided in this application embodiment can achieve... Figure 4 The various processes implemented in the method embodiments achieve the same technical effect, and will not be described again here to avoid repetition.

[1010] like Figure 15As shown in the illustration, this application also provides a communication device 1500, including a processor 1501 and a memory 1502. The memory 1502 stores a program or instructions that can run on the processor 1501. For example, when the communication device 1500 is a first device, the program or instructions executed by the processor 1501 implement the various steps of the first device-side method embodiment described above, and achieve the same technical effect. When the communication device 1500 is a second device, the program or instructions executed by the processor 1501 implement the various steps of the second device-side method embodiment described above, and achieve the same technical effect. When the communication device 1500 is a third device, the program or instructions executed by the processor 1501 implement the various steps of the third device-side method embodiment described above, and achieve the same technical effect. To avoid repetition, further details are omitted here.

[1011] This application embodiment also provides a terminal, including a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement, for example... Figure 2 The steps in the method embodiment shown are illustrated. This terminal embodiment corresponds to the first device-side method embodiment described above. All implementation processes and methods of the above method embodiments can be applied to this terminal embodiment and achieve the same technical effect. The terminal can be... Figure 12 The information transmission device shown. Specifically, Figure 16 A schematic diagram of the hardware structure of a terminal to implement an embodiment of this application.

[1012] The terminal 1600 includes, but is not limited to, at least some of the following components: radio frequency unit 1601, network module 1602, audio output unit 1603, input unit 1604, sensor 1605, display unit 1606, user input unit 1607, interface unit 1608, memory 1609, and processor 1610.

[1013] Those skilled in the art will understand that the terminal 1600 may also include a power supply (such as a battery) for supplying power to various components. The power supply may be logically connected to the processor 1610 through a power management system, thereby enabling functions such as managing charging, discharging, and power consumption through the power management system. Figure 16 The terminal structure shown does not constitute a limitation on the terminal. The terminal may include more or fewer components than shown, or combine certain components, or have different component arrangements, which will not be elaborated here.

[1014] It should be understood that, in this embodiment, the input unit 1604 may include a graphics processor 16041 and a microphone 16042. The graphics processor 16041 processes image data of still images or videos obtained by an image capture device (such as a camera) in video capture mode or image capture mode. The display unit 1606 may include a display panel 16061, which may be configured in the form of a liquid crystal display, an organic light-emitting diode, or the like. The user input unit 1607 includes at least one of a touch panel 16071 and other input devices 16072. The touch panel 16071 is also called a touch screen. The touch panel 16071 may include a touch detection device and a touch controller. Other input devices 16072 may include, but are not limited to, physical keyboards, function keys (such as volume control buttons, power buttons, etc.), trackballs, mice, and joysticks, which will not be described in detail here.

[1015] In this embodiment, after receiving downlink data from the network-side device, the radio frequency unit 1601 can transmit it to the processor 1610 for processing; in addition, the radio frequency unit 1601 can send uplink data to the network-side device. Typically, the radio frequency unit 1601 includes, but is not limited to, antennas, amplifiers, transceivers, couplers, low-noise amplifiers, duplexers, etc.

[1016] The memory 1609 can be used to store software programs or instructions, as well as various data. The memory 1609 may primarily include a first storage area for storing programs or instructions and a second storage area for storing data. The first storage area may store the operating system, application programs or instructions required for at least one function (such as sound playback, image playback, etc.). Furthermore, the memory 1609 may include volatile memory or non-volatile memory. The non-volatile memory may be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory can be random access memory (RAM), static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct memory bus RAM (DRRAM). The memory 1609 in this embodiment includes, but is not limited to, these and any other suitable types of memory.

[1017] Processor 1610 may include one or more processing units; optionally, processor 1610 integrates an application processor and a modem processor, wherein the application processor mainly handles operations involving the operating system, user interface, and applications, and the modem processor mainly handles wireless communication signals, such as a baseband processor. It is understood that the aforementioned modem processor may also not be integrated into processor 1610.

[1018] The radio frequency unit 1601 is used for:

[1019] Receive first information from a second device, the first information including at least one of first indication information and second indication information, wherein the first indication information is used to indicate data characteristic related information corresponding to at least one device, and the second indication information is used to indicate prediction related information;

[1020] Processor 1610 is used for:

[1021] Based on the first information, a first operation is performed, which is an operation related to artificial intelligence (AI).

[1022] In this embodiment of the application, by receiving the first information and performing the first operation based on the first information, it is possible to ensure that the training or inference of the AI ​​unit or AI function matches the data characteristics, which helps to improve the performance stability of the AI ​​unit or AI function.

[1023] It is understood that the implementation process of each implementation method mentioned in this embodiment can refer to the relevant description of the information transmission method embodiment and achieve the same or corresponding technical effects. To avoid repetition, it will not be described again here.

[1024] This application embodiment also provides a network-side device, including a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement, for example... Figure 3 or Figure 4 The steps of the method embodiment shown are illustrated. This network-side device embodiment corresponds to the second or third device-side method embodiment described above. All implementation processes and methods of the above method embodiments can be applied to this network-side device embodiment and achieve the same technical effects.

[1025] Specifically, embodiments of this application also provide a network-side device, which can be... Figure 13 or Figure 14 The information transmission device shown. For example... Figure 17 As shown, the network-side device 1700 includes: an antenna 171, a radio frequency (RF) device 172, a baseband device 173, a processor 174, and a memory 175. The antenna 171 is connected to the RF device 172. In the uplink direction, the RF device 172 receives information through the antenna 171 and transmits the received information to the baseband device 173 for processing. In the downlink direction, the baseband device 173 processes the information to be transmitted and sends it to the RF device 172. The RF device 172 processes the received information and transmits it through the antenna 171.

[1026] The method executed by the network-side device in the above embodiments can be implemented in the baseband device 173, which includes a baseband processor.

[1027] Baseband device 173 may include, for example, at least one baseband board on which multiple chips are disposed, such as Figure 17 As shown, one of the chips is, for example, a baseband processor, which is connected to the memory 175 via a bus interface to call the program in the memory 175 and execute the network device operation shown in the above method embodiment.

[1028] The network-side device may also include a network interface 176, such as a Common Public Radio Interface (CPRI).

[1029] Specifically, the network-side device 1700 in this application embodiment further includes: instructions or programs stored in memory 175 and executable on processor 174, wherein processor 174 calls the instructions or programs in memory 175 to execute. Figure 13 or Figure 14 The methods executed by each module shown achieve the same technical effect, and to avoid repetition, they will not be described in detail here.

[1030] Specifically, embodiments of this application also provide a network-side device. For example... Figure 18 As shown, the network-side device 1800 includes: a processor 1801, a network interface 1802, and a memory 1803. This network-side device can be... Figure 13 or Figure 14 The information transmission device shown. The network interface 1802 is, for example, a common public radio interface (CPRI).

[1031] Specifically, the network-side device 1800 in this application embodiment further includes: instructions or programs stored in memory 1803 and executable on processor 1801, wherein processor 1801 calls the instructions or programs in memory 1803 to execute. Figure 13 The methods executed by each module shown achieve the same technical effect, and to avoid repetition, they will not be described in detail here.

[1032] This application also provides a readable storage medium storing a program or instructions. When the program or instructions are executed by a processor, they implement the various processes of the above-described information transmission method embodiments, or implement the various processes of the above-described information transmission method embodiments and achieve the same technical effect. To avoid repetition, further details are omitted here.

[1033] The processor mentioned above is the processor in the terminal described in the above embodiments. The readable storage medium includes computer-readable storage media, such as computer read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk. In some examples, the readable storage medium may be a non-transient readable storage medium.

[1034] This application embodiment also provides a chip, which includes a processor and a communication interface. The communication interface is coupled to the processor. The processor is used to run programs or instructions to implement the various processes of the above-described information transmission method embodiments, or to implement the various processes of the above-described information transmission method embodiments and achieve the same technical effect. To avoid repetition, it will not be described again here.

[1035] It should be understood that the chip mentioned in the embodiments of this application may also be referred to as a system-on-a-chip, system chip, chip system, or system-on-a-chip, etc.

[1036] This application also provides a computer program / program product, which is stored in a storage medium and executed by at least one processor to implement the various processes of the above-described information transmission method embodiments, or to implement the various processes of the above-described information transmission method embodiments and achieve the same technical effect. To avoid repetition, it will not be described again here.

[1037] This application also provides a communication system, including: a terminal and a network-side device, wherein the terminal can be used to perform the steps of the information transmission method described above, and the network-side device can be used to perform the steps of the information transmission method described above.

[1038] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[1039] From the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of computer software products plus necessary general-purpose hardware platforms, and of course, they can also be implemented by hardware. The computer software product is stored in a storage medium (such as ROM, RAM, magnetic disk, optical disk, etc.) and includes several instructions to cause the terminal or network-side device to execute the methods described in the various embodiments of this application.

[1040] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other implementations under the guidance of this application without departing from the spirit and scope of the claims. All of these implementations are within the protection scope of this application.

Claims

1. An information transmission method, characterized in that, include: The first device receives first information from the second device, the first information including at least one of first indication information and second indication information, wherein the first indication information is used to indicate data characteristic related information corresponding to at least one device, and the second indication information is used to indicate prediction related information; Based on the first information, the first device performs a first operation, which is an artificial intelligence (AI) related operation.

2. The method according to claim 1, characterized in that, The first indication information includes at least one of the following: The first data characteristic corresponding to the second device; AI information related to the first data characteristic; Cell information related to the first data characteristic; The second data characteristic corresponding to the third device; AI information related to the second data characteristic; Cell information related to the second data characteristic; or, The first indication information includes at least one of the following: At least one first association information, wherein the at least one first association information is associated with the first data characteristic; AI information related to at least one first associated information; Cell information related to at least one first associated information; When the first data characteristic is associated with multiple first associated information, the activation time information of the multiple first associated information; The first sub-indicator is used to indicate the association relationship between the plurality of first associated information and AI information; At least one second association information, wherein the at least one second association information is associated with the second data characteristic; AI information related to at least one second associated information; The cell information related to at least one second associated information; The second sub-indicator is used to indicate whether the second associated information has changed.

3. The method according to claim 2, characterized in that, The first association information includes a first association identifier ID, or the first association information includes at least one of a first association ID, a first cell ID, and a first timestamp, wherein the first cell ID is the cell ID of the second device; or, The second association information includes a second association ID, or the second association information includes at least one of a second association ID, a second cell ID, and a second timestamp, wherein the second cell ID is the cell ID of the third device.

4. The method according to claim 1, characterized in that, Also includes: The first device sends second information to the second device. The second information includes third indication information, which is used to indicate data characteristic related information corresponding to the first AI unit or the first AI function. The first AI unit or the first AI function is an AI unit or AI function that the first device can obtain.

5. The method according to claim 4, characterized in that, The first device sends second information to the second device, including: When the first condition is met, the first device sends the second information to the second device; The first condition includes at least one of the following: Prepare to activate or start the first AI unit or the first AI function; The communication index of the cell where the second device is located was detected to be lower than a preset threshold; Deterioration in the inference performance of the first AI unit or the first AI function was detected. The first device undergoes cell handover or cell reselection.

6. The method according to claim 4 or 5, characterized in that, The third indication information includes at least one of the following: The third data characteristic corresponding to the first AI unit or the first AI function; AI information related to the third data characteristic; or, The third indication information includes at least one of the following: At least one third association information, wherein the at least one third association information is associated with the third data characteristic; The first set includes multiple sets of the third associated information; AI information related to the third associated information; AI information related to the first set.

7. The method according to claim 6, characterized in that, The third association information includes a third association ID, or the third association information includes at least one of a third association ID, a third cell ID, and a third timestamp, wherein the third cell ID is the cell ID associated with the first AI unit or the first AI function.

8. The method according to any one of claims 4 to 7, characterized in that, The first indication information includes at least one of the following: The third sub-indicator is used to indicate whether the first data characteristic corresponding to the second device matches the third data characteristic corresponding to the first AI unit or the first AI function. The fourth sub-indicator is used to indicate whether the second data characteristic corresponding to the third device matches the third data characteristic; The third data characteristic; AI information related to the third data characteristic; The cell information related to the third data characteristic; The first data characteristic; AI information related to the first data characteristic; Cell information related to the first data characteristic; The second data characteristic; AI information related to the second data characteristic; Cell information related to the second data characteristic; or, The first indication information includes at least one of the following: At least one first association information, wherein the at least one first association information is associated with a first data characteristic corresponding to the second device; AI information related to at least one first associated information; Cell information related to at least one first associated information; When the first data characteristic is associated with multiple first associated information, the activation time information of the multiple first associated information; The first sub-indicator is used to indicate the association relationship between the plurality of first associated information and AI information; At least one second association information, wherein the at least one second association information is associated with the second data characteristic; AI information related to at least one second associated information; The cell information related to at least one second associated information; The second sub-indicator is used to indicate whether the second associated information has changed; At least one third association information, wherein the at least one third association information is associated with the third data characteristic; AI information related to at least one third-party associated information; The cell information related to at least one third-party associated information; The fifth sub-indicator is used to indicate whether the third data characteristic associated with the at least one third association information matches the first data characteristic corresponding to the second device; The sixth sub-indicator is used to indicate whether the third data characteristic associated with the at least one third associated information matches the second data characteristic corresponding to the third device.

9. The method according to any one of claims 4 to 7, characterized in that, The second instruction information includes at least one of the following: Request the predicted value reported by the first device; First association information, which is associated with a first data characteristic corresponding to the second device; The third association information is associated with the third data characteristic corresponding to the first AI unit or the first AI function; The seventh sub-indicator is used to indicate whether the matched third data feature can be used for training data collection, model fine-tuning, or model training of the AI ​​unit.

10. The method according to claim 9, characterized in that, In the case where the second indication information includes the third association information but does not include the first association information, the third association information is associated with model inference or model monitoring functions, and the third association information is not expected to be used for training data collection or model fine-tuning or model training; or, the configuration information corresponding to the third association information is not expected to be used for training data collection or model fine-tuning or model training. or, When the second indication information includes the first associated information but does not include the third associated information, the first associated information is permitted to be used for training data collection, model fine-tuning, or model training; or, the configuration information corresponding to the first associated information is permitted to be used for training data collection, model fine-tuning, or model training. The third associated information in the second information is not expected to be used for model inference or model monitoring; or, the configuration information corresponding to the third associated information in the second information is not expected to be used for model inference or model monitoring. or, When the second indication information includes the first association information and the third association information, at least one of the first association information and the third association information is allowed to be used for model inference or module monitoring, and at least one of the first association information and the third association information is allowed to be used for training data collection or model fine-tuning or model training.

11. The method according to any one of claims 1 to 10, characterized in that, The first information is carried in at least one of the following messages: Broadcast messages; Channel State Information (CSI) configuration messages; Resource set configuration information; Resource configuration information; Beam Management Set B resource or resource set configuration information; Beam Management Set A resource or resource set configuration information; AI unit prediction reporting messages; AI unit model monitoring reporting messages; AI unit inference reporting messages; Media Access Control Unit (MAC CE); Radio Resource Control (RRC) messages.

12. The method according to claim 11, characterized in that, When the first information is carried in the CSI configuration message, and the first indication information simultaneously indicates the first data characteristic and the matching third data characteristic corresponding to the second device, the CSI configuration message is associated with the first association ID and the third association ID, or the CSI configuration message is associated with the first association ID, the third association ID, the first cell ID and the third cell ID, or the CSI configuration message is associated with the first association ID, the third association ID, the first cell ID, the third cell ID and the third timestamp; or, In the case where the first information is carried in the CSI configuration message, the first indication information simultaneously indicates the first data characteristic and the matching third data characteristic corresponding to the second device, and the CSI configuration message configures a fourth association ID, and the information element IE of the fourth association ID is associated with or configured with a fifth association ID; or, in the case where the first information is carried in the CSI configuration message, the first indication information simultaneously indicates the first data characteristic and the matching third data characteristic corresponding to the second device, and the CSI configuration message configures a fourth association ID and a fourth cell ID, and the IE of the fourth association ID is associated with or configured with a fifth association ID and a fifth cell ID, the fourth association ID is the first association ID, the fourth cell ID is the first cell ID, and the fifth association ID is the third association ID, and the fifth cell ID is the third cell ID; or, the fourth association ID is the third association ID, the fourth cell ID is the third cell ID, and the fifth association ID is the first association ID, and the fifth cell ID is the first cell ID.

13. The method according to any one of claims 1 to 12, characterized in that, The data characteristics are used to indicate at least one of the first configuration information, the second configuration information, and the mapping characteristics; The first configuration information includes at least one of the following: Number of antenna elements; The number of antenna elements in the horizontal dimension; The number of antenna elements in the vertical dimension; Antenna spacing; Antenna spacing in the horizontal dimension; Antenna spacing in the vertical dimension; Mechanical tilt angle; Antenna height; The orientation of the antenna panel; The second configuration information includes at least one of the following: Number of beams; Number of beams in the horizontal dimension; Number of beams in the vertical dimension; Beam pointing; Half-power beamwidth; Beamforming codebook; Beamforming codebook in the horizontal dimension; Beamforming codebook in the vertical dimension; Electron downtilt angle; The mapping property includes at least one of the following: The mapping relationship between the first configuration information and the associated information; The mapping relationship between the second configuration information and the associated information; Mapping relationship between physical beam and reference signal RS identifier; Mapping relationship between physical beams and beam identifiers.

14. The method according to any one of claims 1 to 13, characterized in that, The first operation includes at least one of the following: Identify the AI ​​unit or AI function that matches the first data characteristic corresponding to the second device; Determine a first dataset that matches the first data characteristic; Determine the AI ​​unit or AI function corresponding to the first dataset; Initiate prediction for the cell where the second device is located; Activate the second AI unit or the second AI function, wherein the second AI unit or the second AI function is an AI unit or AI function whose data characteristics match the first data characteristics; Perform inactive model monitoring on the second AI unit or the second AI function; Deactivate the third AI unit or the third AI function, wherein the third AI unit or the third AI function is an AI unit or AI function whose data characteristics do not match the first data characteristics; Collect the first training data and associate the first training data with the first data characteristics; Based on the first training data, a fourth AI unit or a fourth AI function is generated, and the fourth AI unit or the fourth AI function is associated with the first data characteristics.

15. The method according to claim 14, characterized in that, The at least one device also includes a third device; The first operation further includes at least one of the following: Based on the second data characteristics corresponding to the third device, determine whether to switch to the cell where the third device is located; Identify the AI ​​unit or AI function that matches the second data characteristic; Determine a second dataset that matches the second data characteristic; Determine the AI ​​unit or AI function corresponding to the second dataset; If the first device switches to the cell where the third device is located, prediction of the cell where the third device is located is initiated; When the first device switches to the cell where the third device is located, second training data is collected, and the second training data is associated with the second data characteristics; Based on the second training data, a fifth AI unit or a fifth AI function is generated, and the fifth AI unit or the fifth AI function is associated with the second data characteristics.

16. An information transmission method, characterized in that, include: The second device sends first information to the first device. The first information includes at least one of first indication information and second indication information. The first indication information is used to indicate data characteristic related information corresponding to at least one device, and the second indication information is used to indicate prediction related information.

17. The method according to claim 16, characterized in that, The first indication information includes at least one of the following: The first data characteristic corresponding to the second device; Artificial intelligence (AI) information related to the first data characteristic; Cell information related to the first data characteristic; or, The first indication information includes at least one of the following: At least one first association information, wherein the at least one first association information is associated with the first data characteristic; AI information related to at least one first associated information; Cell information related to at least one first associated information; When the first data characteristic is associated with multiple first associated information, the activation time information of the multiple first associated information; The first sub-indicator is used to indicate the association relationship between the plurality of first associated information and AI information.

18. The method according to claim 17, characterized in that, The first association information includes a first association identifier ID, or the first association information includes at least one of a first association ID, a first cell ID, and a first timestamp, wherein the first cell ID is the cell ID of the second device.

19. The method according to claim 16, characterized in that, Also includes: The second device receives second information from the first device. The second information includes third indication information, which is used to indicate data characteristic related information corresponding to the first AI unit or the first AI function. The first AI unit or the first AI function is an AI unit or AI function that can be obtained by the first device.

20. The method according to claim 19, characterized in that, The third indication information includes at least one of the following: The third data characteristic corresponding to the first AI unit or the first AI function; AI information related to the third data characteristic; or, The third indication information includes at least one of the following: At least one third association information, wherein the at least one third association information is associated with the third data characteristic; The first set includes multiple sets of the third associated information; AI information related to the third associated information; AI information related to the first set.

21. The method according to claim 20, characterized in that, The third association information includes a third association ID, or the third association information includes at least one of a third association ID, a third cell ID, and a third timestamp, wherein the third cell ID is the cell ID associated with the first AI unit or the first AI function.

22. The method according to any one of claims 19 to 21, characterized in that, The first indication information includes at least one of the following: The third sub-indicator is used to indicate whether the first data characteristic corresponding to the second device matches the third data characteristic corresponding to the first AI unit or the first AI function. The third data characteristic; AI information related to the third data characteristic; The cell information related to the third data characteristic; The first data characteristic; AI information related to the first data characteristic; Cell information related to the first data characteristic; or, The first indication information includes at least one of the following: At least one first association information, wherein the at least one first association information is associated with a first data characteristic corresponding to the second device; AI information related to at least one first associated information; Cell information related to at least one first associated information; When the first data characteristic is associated with multiple first associated information, the activation time information of the multiple first associated information; The first sub-indicator is used to indicate the association relationship between the plurality of first associated information and AI information; At least one third association information, wherein the at least one third association information is associated with the third data characteristic; AI information related to at least one third-party associated information; The cell information related to at least one third-party associated information; The fifth sub-indicator is used to indicate whether the third data characteristic associated with the at least one third association information matches the first data characteristic corresponding to the second device.

23. The method according to any one of claims 19 to 21, characterized in that, The second instruction information includes at least one of the following: Request the predicted value reported by the first device; First association information, which is associated with a first data characteristic corresponding to the second device; The third association information is associated with the third data characteristic corresponding to the first AI unit or the first AI function; The seventh sub-indicator is used to indicate whether the matched third data feature can be used for training data collection, model fine-tuning, or model training of the AI ​​unit.

24. The method according to claim 23, characterized in that, In the case where the second indication information includes the third association information but does not include the first association information, the third association information is associated with model inference or model monitoring functions, and the third association information is not expected to be used for training data collection or model fine-tuning or model training; or, the configuration information corresponding to the third association information is not expected to be used for training data collection or model fine-tuning or model training. or, When the second indication information includes the first associated information but does not include the third associated information, the first associated information is permitted to be used for training data collection, model fine-tuning, or model training; or, the configuration information corresponding to the first associated information is permitted to be used for training data collection, model fine-tuning, or model training. The third associated information in the second information is not expected to be used for model inference or model monitoring; or, the configuration information corresponding to the third associated information in the second information is not expected to be used for model inference or model monitoring. or, When the second indication information includes the first association information and the third association information, at least one of the first association information and the third association information is allowed to be used for model inference or module monitoring, and at least one of the first association information and the third association information is allowed to be used for training data collection or model fine-tuning or model training.

25. The method according to any one of claims 16 to 24, characterized in that, The first information is carried in at least one of the following messages: Broadcast messages; Channel State Information (CSI) configuration messages; Resource set configuration information; Resource configuration information; Beam Management Set B resource or resource set configuration information; Beam Management Set A resource or resource set configuration information; AI unit prediction reporting messages; AI unit model monitoring reporting messages; AI unit inference reporting messages; Media Access Control Unit (MAC CE); Radio Resource Control (RRC) messages.

26. The method according to claim 25, characterized in that, When the first information is carried in the CSI configuration message, and the first indication information simultaneously indicates the first data characteristic and the matching third data characteristic corresponding to the second device, the CSI configuration message is associated with the first association ID and the third association ID, or the CSI configuration message is associated with the first association ID, the third association ID, the first cell ID and the third cell ID, or the CSI configuration message is associated with the first association ID, the third association ID, the first cell ID, the third cell ID and the third timestamp; or, In the case where the first information is carried in the CSI configuration message, the first indication information simultaneously indicates the first data characteristic and the matching third data characteristic corresponding to the second device, and the CSI configuration message configures a fourth association ID, and the information element IE of the fourth association ID is associated with or configured with a fifth association ID; or, in the case where the first information is carried in the CSI configuration message, the first indication information simultaneously indicates the first data characteristic and the matching third data characteristic corresponding to the second device, and the CSI configuration message configures a fourth association ID and a fourth cell ID, and the IE of the fourth association ID is associated with or configured with a fifth association ID and a fifth cell ID, the fourth association ID is the first association ID, the fourth cell ID is the first cell ID, and the fifth association ID is the third association ID, and the fifth cell ID is the third cell ID; or, the fourth association ID is the third association ID, the fourth cell ID is the third cell ID, and the fifth association ID is the first association ID, and the fifth cell ID is the first cell ID.

27. The method according to any one of claims 16 to 26, characterized in that, Also includes: The second device receives third information from the third device, the third information being used to indicate data characteristic related information corresponding to the third device.

28. The method according to claim 27, characterized in that, The third information includes at least one of the following: The second data characteristic corresponding to the third device; AI information related to the second data characteristic; Cell information related to the second data characteristic; or, The third information includes at least one of the following: At least one second association information, wherein the at least one second association information is associated with the second data characteristic; AI information related to at least one second associated information; The cell information related to at least one second associated information; The second sub-indicator is used to indicate whether the second associated information has changed.

29. The method according to claim 28, characterized in that, The second association information includes a second association ID, or the second association information includes at least one of a second association ID, a second cell ID, and a second timestamp, wherein the second cell ID is the cell ID of the third device.

30. The method according to any one of claims 27 to 29, characterized in that, Before the second device receives the third information from the third device, the method further includes: The second device sends a fourth message to the third device, the fourth message being used to request data characteristic-related information from the third device.

31. The method according to claim 30, characterized in that, The fourth piece of information includes at least one of the following: A target set, which is determined based on a first set provided by the first device; Target association information, which is determined based on third association information provided by the first device or first association information corresponding to the second device; AI information related to the target association information; The target-related information includes cell information; The fourth instruction information is used to indicate a request for the third device to provide association information associated with the second data characteristic corresponding to the third device; The fifth instruction information is used to instruct the third device to provide cell information whose data characteristics are consistent with the second data characteristics; The sixth instruction information is used to instruct the third device to provide AI information related to the second data characteristic; The seventh instruction information is used to instruct the third device to confirm whether the second data characteristic matches the data characteristic corresponding to the target association information; The eighth instruction information is used to instruct the third device to provide cell information whose data characteristics match those of the target association information; The ninth instruction information is used to instruct the third device to provide AI information that matches the data characteristics corresponding to the target association information.

32. The method according to claim 31, characterized in that, If the second device receives the third association information, the target association information is determined based on the third association information; if the second device does not receive the third association information, the target association information is determined based on the first association information.

33. The method according to claim 31 or 32, characterized in that, The third information includes at least one of the following: The tenth indication information is used to indicate whether the second data characteristic matches the data characteristic associated with the target association information; The second data characteristic; AI information related to the second data characteristic; Cell information related to the second data characteristic; or, The third information includes at least one of the following: The tenth indication information is used to indicate whether the second data characteristic matches the data characteristic associated with the target association information; The second association information is associated with the second data characteristic; The second related information is related to the cell information; AI information related to the second set of associated information; The second sub-indicator is used to indicate whether the second associated information has changed.

34. The method according to any one of claims 27 to 33, characterized in that, The first indication information also includes at least one of the following: The fourth sub-indicator is used to indicate whether the second data characteristic corresponding to the third device matches the third data characteristic corresponding to the third device; The second data characteristic; AI information related to the second data characteristic; Cell information related to the second data characteristic; or, The first indication information also includes at least one of the following: The second association information is associated with the second data characteristic; The second related information is related to the cell information; AI information related to the second set of associated information; The second sub-indicator is used to indicate whether the second associated information has changed; The sixth sub-indicator is used to indicate whether the third data characteristic associated with the at least one third associated information matches the second data characteristic.

35. An information transmission method, characterized in that, include: The third device sends third information to the second device, the third information being used to indicate data characteristic-related information corresponding to the third device.

36. The method according to claim 35, characterized in that, The third information includes at least one of the following: The second data characteristic corresponding to the third device; AI information related to the second data characteristic; Cell information related to the second data characteristic; or, The third information includes at least one of the following: At least one second association information, wherein the at least one second association information is associated with the second data characteristic; AI information related to at least one second associated information; The cell information related to at least one second associated information; The second sub-indicator is used to indicate whether the second associated information has changed.

37. The method according to claim 36, characterized in that, The second association information includes a second association ID, or the second association information includes at least one of a second association ID, a second cell ID, and a second timestamp, wherein the second cell ID is the cell ID of the third device.

38. The method according to claim 35, characterized in that, Before the third device sends the third information to the second device, the method further includes: The third device receives fourth information from the second device, the fourth information being used to request data characteristic-related information corresponding to the third device.

39. The method according to claim 38, characterized in that, The fourth piece of information includes at least one of the following: A target set, the target set being determined based on a first set provided by a first device; Target association information, which is determined based on third association information provided by the first device or first association information corresponding to the second device; AI information related to the target association information; The target-related information includes cell information; The fourth instruction information is used to indicate a request for the third device to provide association information associated with the second data characteristic corresponding to the third device; The fifth instruction information is used to instruct the third device to provide cell information whose data characteristics are consistent with the second data characteristics; The sixth instruction information is used to instruct the third device to provide AI information related to the second data characteristic; The seventh instruction information is used to instruct the third device to confirm whether the second data characteristic matches the data characteristic corresponding to the target association information; The eighth instruction information is used to instruct the third device to provide cell information whose data characteristics match those of the target association information; The ninth instruction information is used to instruct the third device to provide AI information that matches the data characteristics corresponding to the target association information.

40. The method according to claim 39, characterized in that, The third information includes at least one of the following: The tenth indication information is used to indicate whether the second data characteristic matches the data characteristic associated with the target association information; The second data characteristic; AI information related to the second data characteristic; Cell information related to the second data characteristic; or, The third information includes at least one of the following: The tenth indication information is used to indicate whether the second data characteristic matches the data characteristic associated with the target association information; The second association information is associated with the second data characteristic; The second related information is related to the cell information; AI information related to the second set of associated information; The second sub-indicator is used to indicate whether the second associated information has changed.

41. An information transmission device, characterized in that, The device includes: A receiving module is configured to receive first information from a second device, the first information including at least one of first indication information and second indication information, wherein the first indication information is used to indicate data characteristic related information corresponding to at least one device, and the second indication information is used to indicate prediction related information. The processing module is used to perform a first operation based on the first information, wherein the first operation is an artificial intelligence (AI) related operation.

42. The apparatus according to claim 41, characterized in that, Also includes: The sending module is used to send second information to the second device. The second information includes third indication information, which is used to indicate data characteristic related information corresponding to the first AI unit or the first AI function. The first AI unit or the first AI function is an AI unit or AI function that can be obtained by the first device.

43. The apparatus according to claim 41 or 42, characterized in that, The first operation includes at least one of the following: Identify the AI ​​unit or AI function that matches the first data characteristic corresponding to the second device; Determine a first dataset that matches the first data characteristic; Determine the AI ​​unit or AI function corresponding to the first dataset; Initiate prediction for the cell where the second device is located; Activate the second AI unit or the second AI function, wherein the second AI unit or the second AI function is an AI unit or AI function whose data characteristics match the first data characteristics; Perform inactive model monitoring on the second AI unit or the second AI function; Deactivate the third AI unit or the third AI function, wherein the third AI unit or the third AI function is an AI unit or AI function whose data characteristics do not match the first data characteristics; Collect the first training data and associate the first training data with the first data characteristics; Based on the first training data, a fourth AI unit or a fourth AI function is generated, and the fourth AI unit or the fourth AI function is associated with the first data characteristics.

44. The apparatus according to claim 43, characterized in that, The at least one device also includes a third device; The first operation further includes at least one of the following: Based on the second data characteristics corresponding to the third device, determine whether to switch to the cell where the third device is located; Identify the AI ​​unit or AI function that matches the second data characteristic; Determine a second dataset that matches the second data characteristic; Determine the AI ​​unit or AI function corresponding to the second dataset; If the first device switches to the cell where the third device is located, prediction of the cell where the third device is located is initiated; When the first device switches to the cell where the third device is located, second training data is collected, and the second training data is associated with the second data characteristics; Based on the second training data, a fifth AI unit or a fifth AI function is generated, and the fifth AI unit or the fifth AI function is associated with the second data characteristics.

45. An information transmission device, characterized in that, The device includes: A first sending module is configured to send first information to a first device. The first information includes at least one of first indication information and second indication information. The first indication information is used to indicate data characteristic related information corresponding to at least one device, and the second indication information is used to indicate prediction related information.

46. ​​The apparatus according to claim 45, characterized in that, Also includes: The first receiving module is configured to receive second information from the first device. The second information includes third indication information, which is used to indicate data characteristic related information corresponding to the first AI unit or the first AI function. The first AI unit or the first AI function is an AI unit or AI function that can be obtained by the first device.

47. The apparatus according to claim 45 or 46, characterized in that, Also includes: The second receiving module is used to receive third information from the third device, the third information being used to indicate data characteristic related information corresponding to the third device.

48. The apparatus according to claim 47, characterized in that, Also includes: The second sending module is used to send fourth information to the third device, the fourth information being used to request data characteristic related information corresponding to the third device.

49. An information transmission device, characterized in that, The device includes: The sending module is used to send third information to the second device, the third information being used to indicate data characteristic related information corresponding to the third device.

50. The apparatus according to claim 49, characterized in that, Also includes: The receiving module is used to receive fourth information from the second device, the fourth information being used to request data characteristic related information corresponding to the third device.

51. A communication device, characterized in that, It includes a processor and a memory, the memory storing a program or instructions that can run on the processor, the program or instructions being executed by the processor to implement the steps of the information transmission method as claimed in any one of claims 1 to 15, or to implement the steps of the information transmission method as claimed in any one of claims 16 to 34, or to implement the steps of the information transmission method as claimed in any one of claims 35 to 40.

52. A readable storage medium, characterized in that, The readable storage medium stores a program or instructions that, when executed by a processor, implement the steps of the information transmission method as described in any one of claims 1 to 15, or the steps of the information transmission method as described in any one of claims 16 to 34, or the steps of the information transmission method as described in any one of claims 35 to 40.

53. A computer program product, characterized in that, It includes computer instructions that, when executed by a processor, implement the steps of the information transmission method as described in any one of claims 1 to 15, or the steps of the information transmission method as described in any one of claims 16 to 34, or the steps of the information transmission method as described in any one of claims 35 to 40.

Images