Information transmission method, terminal and network device

Abstract

The application provides an information transmission method, a terminal and network equipment, wherein the information transmission method comprises the following steps: a first network equipment sends configuration information to a terminal, the configuration information is used for configuring the terminal to execute intelligent operation, so that the terminal can execute intelligent operation based on the configuration information, uses an intelligent model to adjust network parameters or replaces a traditional protocol, and network performance can be improved and air interface and protocol complexity can be reduced.

Description

Technical Field

[0001] This invention relates to the field of communication technology, and in particular to an information transmission method, terminal, and network device. Background Technology

[0002] Artificial intelligence (AI) and machine learning (ML) have received widespread attention from academia and industry in recent years. 5G networks face numerous challenges arising from joint optimization, such as latency, reliability, connection density, and user experience. Simultaneously, 5G networks also need to address the complex system designs brought about by the new characteristics of 5G, such as centralized unit (CU) and distributed unit (DU) architectures, dual-connectivity architectures, beamforming, and network slicing.

[0003] In existing technologies, AI information about the interaction between terminals and network devices is concentrated at the application layer. In other words, the information exchanged is all application-level information. For 5G networks, this information is the same as ordinary data, generated between the service server and the terminal application layer. 5G networks, especially access networks, do not perceive the content of this data and only undertake the function of transparent transmission. Network element devices do not participate in the end-to-end process of AI algorithm optimization. Summary of the Invention

[0004] This invention provides an information transmission method, terminal, and network device to address the problem in the prior art where network devices do not assist in configuring intelligent models to optimize network transmission.

[0005] To solve the above-mentioned technical problems, the present invention is implemented as follows:

[0006] In a first aspect, embodiments of the present invention provide an information transmission method for a first network device, comprising:

[0007] Configuration information is sent to the terminal, and the configuration information is used to configure the terminal to perform intelligent-related operations.

[0008] In a second aspect, embodiments of the present invention provide an information transmission method for a terminal, comprising:

[0009] Receive configuration information sent by the first network device;

[0010] Perform the intelligent-related operations configured in the configuration information.

[0011] Thirdly, embodiments of the present invention provide a network device, including: a processor and a transceiver;

[0012] The transceiver is used to send configuration information to the terminal, and the configuration information is used to configure the terminal to perform intelligent-related operations.

[0013] Fourthly, embodiments of the present invention provide a terminal, characterized in that it includes: a processor and a transceiver;

[0014] The transceiver is used to receive configuration information sent by the first network device;

[0015] The processor is used to execute the intelligent-related operations configured in the configuration information.

[0016] Fifthly, embodiments of the present invention provide a network device, comprising:

[0017] The sending module is used to send configuration information to the terminal, and the configuration information is used to configure the terminal to perform intelligent related operations.

[0018] Sixthly, embodiments of the present invention provide a terminal, including:

[0019] The receiving module is used to receive configuration information sent by the first network device;

[0020] The execution module is used to execute the intelligent-related operations configured in the configuration information.

[0021] In a seventh aspect, embodiments of the present invention provide a network device, including a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of the information transmission method as described in the first aspect.

[0022] Eighthly, embodiments of the present invention provide a terminal including a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of the information transmission method as described in the second aspect.

[0023] Ninthly, embodiments of the present invention provide a computer-readable storage medium storing a computer program, wherein when executed by a processor, the computer program implements the steps of the information transmission method as described in the first aspect, or, when executed by the processor, the computer program implements the steps of the information transmission method as described in the second aspect.

[0024] In this embodiment of the invention, a first network device sends configuration information to a terminal. The configuration information is used to configure the terminal to perform intelligent-related operations, so that the terminal can use an intelligent model based on the configuration information to adjust network parameters or replace traditional protocols, thereby improving network performance and reducing the complexity of the air interface and protocols. Attached Figure Description

[0025] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0026] Figure 1 This is a flowchart of an information transmission method provided in an embodiment of the present invention;

[0027] Figure 2 This is another flowchart of an information transmission method provided in an embodiment of the present invention;

[0028] Figure 3a , Figure 3b This is an interaction diagram between a network device and a terminal provided in an embodiment of the present invention;

[0029] Figure 4 This is a structural diagram of a terminal provided in an embodiment of the present invention;

[0030] Figure 5 This is another structural diagram of the terminal provided in an embodiment of the present invention;

[0031] Figure 6 This is a structural diagram of a network device provided in an embodiment of the present invention;

[0032] Figure 7 This is another structural diagram of the network device provided in the embodiment of the present invention. Detailed Implementation

[0033] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0034] See Figure 1 , Figure 1 This is a flowchart of an information transmission method provided in an embodiment of the present invention, used in a first network device, such as... Figure 1 As shown, the information transmission method includes the following steps:

[0035] Step 101: Send configuration information to the terminal. The configuration information is used to configure the terminal to perform intelligent-related operations. The configuration information includes at least one of the following:

[0036] The system configures the intelligent model information for the terminal; configures the terminal to perform inference based on the indicated intelligent model information; configures the terminal to perform intelligent model training instructions; configures the terminal to perform intelligent model updates instructions; configures the terminal to report the trained intelligent model or the updated intelligent model information; configures the terminal to report data information reporting conditions and / or the reported data information, which is used for intelligent model training or inference; configures the terminal to transmit data information for reporting data information, which is used for intelligent model training or inference; configures the terminal to transmit execution result data, which is the data obtained by the terminal performing the intelligent-related operations.

[0037] In one scenario, to reduce the amount of data transmitted, the updated intelligent model information described above is described using incremental information.

[0038] The updated intelligent model information can be used to perform joint training with the network-side intelligent model.

[0039] In other words, the configuration information is configured with at least one of the following:

[0040] The intelligent model information used by the terminal for inference; the intelligent model information used by the terminal for training; the intelligent model information used by the terminal for updating; the intelligent model information reported by the terminal after training, or the intelligent model information reported after updating; the reporting conditions and / or the reported data information of the terminal, which is used for training or inference of the intelligent model; and the transmission resource information, such as bearer information or channel information, for the terminal to report intelligent model information, data information, or execution result data.

[0041] Intelligent operations can be understood as operations related to artificial intelligence. Artificial intelligence includes, but is not limited to, intelligent methods such as machine learning, deep learning, reinforcement learning, and neural networks; artificial intelligence models include, but are not limited to, intelligent models such as machine learning models, deep learning models, reinforcement learning models, and neural network models.

[0042] In this implementation, the first network device sends configuration information to the terminal. The configuration information is used to configure the terminal to perform intelligent-related operations, so that the terminal can perform intelligent-related operations based on the configuration information, such as using intelligent models to adjust network parameters or replace traditional protocols, which can improve network performance and reduce the complexity of air interface and protocols.

[0043] Unlike existing technologies, the method in this embodiment of the invention configures intelligent-related operations through the 5G protocol layer. These operations are processed by the 5G access network layer and / or core network layer, rather than simply transmitting them transparently as general data. In other words, from the perspective of device functionality, the network-side device no longer transmits data generated between the service server and the terminal application layer. Instead, it implements methods and processes for configuring and transmitting AI-related parameters and models at the wireless air interface, thereby enabling network devices to assist in optimizing the configuration of intelligent models.

[0044] In other words, from the perspective of data transmission, unlike the prior art, in the method of this invention, the transmission of intelligent-related parameters and models is through the control plane, rather than through the data plane as data between the business server and the terminal application layer.

[0045] This invention addresses the problems of modeling difficulties and problem-solving challenges encountered when using AI as a network optimization method in related technologies. It provides methods and processes for configuring and transmitting AI-related parameters and models over the wireless air interface. Furthermore, it provides methods for transmitting data related to intelligent operations between the network and terminals, even when data generated within the network does not have end-to-end sessions / bearers. This enables network-side intelligent network optimization (such as optimizations in mobility, load balancing, and device energy saving). These methods can also allow AI modules to replace traditional wireless modules (such as channel estimation, load balancing, and encoding / decoding) to optimize network performance, reduce network costs, and improve user experience.

[0046] The aforementioned intelligent-related operations include at least one of the following operations:

[0047] A sending operation is used to send the data indicated by the configuration information to a first network device, the data being used for training or inference of an intelligent model;

[0048] as well as,

[0049] Processing operations related to intelligent models.

[0050] The data indicated by the configuration information mentioned above may include one or more of the following: sensor information, geographic location information, service-level perception information, and wireless-related information. Different information can be used for different network optimization use cases. For example, sensor information and geographic location information can be used for training or inference of intelligent models for user trajectory prediction.

[0051] Among them, sensor information can be barometer, altimeter, gyroscope, etc.; service-level perception information can be video version switching times, average throughput, initial playback latency, cache level, etc.; wireless-related information can be channel quality information, CSI feedback information, etc.

[0052] The configuration information may also include data such as the intelligent model trained on the terminal, or the intelligent model updated on the terminal.

[0053] The processing operations include at least one of the following:

[0054] Reasoning is performed using the intelligent model indicated by the configuration information;

[0055] Train the intelligent model indicated by the configuration information;

[0056] Update the intelligent model indicated by the configuration information;

[0057] Report the trained intelligent model;

[0058] as well as,

[0059] Report the updated intelligent model.

[0060] The terminal can perform the above processing operations based on the received configuration information.

[0061] As can be seen from the above description, some processing in the method of the specific embodiment of the present invention requires the support of the terminal. In order to make the configuration operation more efficient and accurate, the method of the specific embodiment of the present invention can also achieve more efficient and accurate configuration operation by collecting the terminal's capability information.

[0062] In other words, the above information transmission method may further include: receiving intelligent-related support capability information sent by the terminal. The support capability information includes at least one of the following:

[0063] Whether it supports sending data, which is used for training or inference of intelligent models; the types of data that can be sent; whether it supports intelligent-related applications; and the types of intelligent models that are supported.

[0064] For example, if the terminal does not support sending data for training or inference of the intelligent model, but supports training and inference of the intelligent model, then the terminal can be configured to use the intelligent model indicated by the configuration information for inference, or to train the intelligent model indicated by the configuration information, etc., but the terminal will not be configured to report the training results or inference results.

[0065] For example, if a terminal sensor can detect air pressure and altitude but not speed information, the network side can configure the terminal to report air pressure and altitude data, but not speed data.

[0066] For example, if the terminal supports intelligent applications, the network side can configure operations such as training related models, and can also configure the reporting of data corresponding to the supported intelligent applications in order to train the model corresponding to the intelligent application.

[0067] As can be seen from the above description, by collecting terminal capabilities, the network side can make targeted configurations based on the terminal capabilities, which improves the efficiency and effectiveness of configuration from a configuration perspective.

[0068] In a specific embodiment of the present invention, the configuration information described above can be set autonomously by the network-side device, but it can also come from other network platforms. That is, in one embodiment of this application, before sending the configuration information to the terminal in step 101, the information transmission method further includes:

[0069] The system receives the configuration information sent by a second network device. The second network device is at least one of an access network element, a network management system, a core network element, and an edge computing node; for example, the second network device is a centralized big data platform, an edge big data platform, etc.

[0070] The configuration information sent by the second network device to the first network device can be displayed information transmitted on the interface, or information encapsulated in a container.

[0071] In one embodiment of this application, after step 101, sending configuration information to the terminal, the above information transmission method further includes:

[0072] Receive the execution result data obtained from performing the intelligent related operations sent by the terminal.

[0073] The configuration information also indicates transmission resource information for sending the execution result data, which may be at least one of signaling radio bearer, data radio bearer, and physical channel. The terminal sends the execution result data to the first network device according to the signaling radio bearer, data radio bearer, or physical channel indicated in the configuration information. Furthermore, the first network device may send the received execution result data to a second network device.

[0074] In the above, the execution result data is at least one of the following:

[0075] The configuration information indicates the data, which is used for training or inference of the intelligent model;

[0076] The training results obtained by training the intelligent model indicated by the configuration information;

[0077] The updated intelligent model indicated by the updated configuration information yields an updated result.

[0078] In the above-described manner, the configuration information is transmitted via Radio Resource Control (RRC) signaling, Non-Access-Stratum (NAS) signaling, Media Access Control (MAC) signaling, or Physical Layer signaling. The first network device can send configuration information to the terminal via control; for example, the configuration information can be sent to the terminal via RRC reconfiguration signaling or dedicated configuration information RRC signaling.

[0079] See Figure 2 , Figure 2 This is a flowchart of an information transmission method provided in an embodiment of the present invention, used in a terminal, such as... Figure 2 As shown, the information transmission method includes the following steps:

[0080] Step 201: Receive configuration information sent by the first network device.

[0081] The configuration information includes at least one of the following:

[0082] The system configures the intelligent model information for the terminal; configures the terminal to perform inference based on the indicated intelligent model information; configures the terminal to perform intelligent model training instructions; configures the terminal to perform intelligent model updates instructions; configures the terminal to report the trained or updated intelligent model information; configures the terminal to report data information reporting conditions and / or the reported data information; the data information is used for intelligent model training or inference; configures the terminal to transmit data information for reporting data, the data information being used for intelligent model training or inference; configures the terminal to transmit execution result data, the execution result data being the data obtained by the terminal performing the intelligent-related operations.

[0083] In other words, the configuration information is configured with at least one of the following:

[0084] The intelligent model information used by the terminal for inference; the intelligent model information used by the terminal for training; the intelligent model information used by the terminal for updating; the intelligent model information reported by the terminal after training, or the intelligent model information reported after updating; the reporting conditions and / or the reported data information of the terminal, which is used for training or inference of the intelligent model; and the transmission resource information, such as bearer information or channel information, for the terminal to report intelligent model information, data information, or execution result data.

[0085] Step 202: Execute the intelligent-related operations configured in the configuration information.

[0086] In this embodiment, the terminal receives configuration information sent by the first network device; it executes the intelligent-related operations configured in the configuration information, enabling the terminal to use the intelligent model to adjust network parameters or replace traditional protocols, thereby improving network performance and reducing the complexity of the air interface and protocols.

[0087] The aforementioned intelligent-related operations include at least one of the following operations:

[0088] A sending operation is used to send the data indicated by the configuration information to a first network device, the data being used for training or inference of an intelligent model;

[0089] Processing operations related to intelligent models.

[0090] The configuration information indicated above may include one or more of the following: sensor information, geographic location information, service-level perception information, and wireless-related information. Different information can be used for different network optimization use cases. For example, sensor information and geographic location information can be used for training or inference of intelligent models for user trajectory prediction. Sensor information may include barometer, altimeter, gyroscope, etc.; service-level perception information may include video version switching counts, average throughput, initial playback latency, cache level, etc.; wireless-related information may include channel quality information, CSI feedback information, etc. The configuration information indicated may also include data information such as the intelligent model trained by the terminal, or the intelligent model updated by the terminal.

[0091] The processing operation includes at least one of the following operations:

[0092] The intelligent model indicated by the configuration information is used for inference, training the intelligent model indicated by the configuration information, updating the intelligent model indicated by the configuration information, reporting the trained intelligent model, and reporting the updated intelligent model.

[0093] The terminal can perform the above processing operations based on the received configuration information.

[0094] The above information transmission method further includes: sending the intelligent-related support capability information. The support capability information includes at least one of the following:

[0095] Whether it supports sending data, which is used for training or inference of intelligent models; the types of data that can be sent; whether it supports intelligent-related applications; and the types of intelligent models that are supported.

[0096] In one embodiment of this application, after step 202, which involves executing the intelligence-related operations configured by the configuration information, the method further includes:

[0097] Send the execution result data obtained from performing the intelligent related operations.

[0098] The configuration information also indicates the transmission resources for sending the execution result data, such as at least one of a signaling radio bearer, a data radio bearer, and a physical channel. The terminal sends the execution result data to the first network device according to the signaling radio bearer, data radio bearer, or physical channel indicated in the configuration information. Furthermore, the first network device can send the received execution result data to a second network device.

[0099] In the above, the execution result data is at least one of the following:

[0100] The configuration information indicates the data, which is used for training or inference of the intelligent model;

[0101] The training results obtained by training the intelligent model indicated by the configuration information;

[0102] The updated intelligent model indicated by the updated configuration information yields an updated result.

[0103] In the above, the configuration information is sent via RRC signaling, NAS signaling, Media Access Control (MAC) signaling, or Physical Layer signaling. The first network device can send configuration information to the terminal via control; for example, the configuration information can be sent to the terminal via RRC reconfiguration signaling or dedicated configuration information RRC signaling.

[0104] Specifically, the terminal access layer (AS) sends configuration information to the terminal's non-access layer (NAS) and receives execution result data from the NAS layer.

[0105] Figure 3aThe diagram shows the interaction between the terminal, the base station (i.e., the first network device), and the network element device (i.e., the second network device). In the diagram, OAM refers to Operation Administration and Maintenance.

[0106] The base station sends AI-related configuration information (i.e., configuration information) to the terminal and receives AI-related data reported by the terminal.

[0107] AI-related configuration information includes at least one of the following:

[0108] Whether to report the perceived data for AI model training or inference in the big data analysis unit;

[0109] AI training model at the big data analytics unit level;

[0110] Whether it is used in conjunction with the big data analytics unit for AI training and / or for models that require terminal training;

[0111] Perceive the data type or the business type corresponding to the AI ​​training model, such as APP ID.

[0112] The AI-related data (i.e., execution result data) reported by the terminal includes at least one of the following:

[0113] The reported perception data is used for AI model training or inference in the big data analysis unit. The perception data includes: sensor information, such as barometer, altimeter, gyroscope and other information; geographical location information; business-level perception information, such as video version switching times, average throughput, initial playback latency, cache level and other information; wireless related information, such as channel quality information, CSI feedback information and other information.

[0114] Report the model trained on the terminal or the updated AI training model.

[0115] The base station receives AI-related configuration information sent by network element equipment (i.e., big data analysis unit). The network element equipment can be one of the following: core network, network management system, centralized big data platform, edge big data platform, and base station internal functions.

[0116] AI-related configuration information can be either information transmitted and displayed on the interface, or information encapsulated within a container.

[0117] The base station sends the AI-related configuration information to the terminal through control. Specifically, it can send the information to the terminal through Radio Resource Control (RRC) reconfiguration signaling or dedicated AI-related information configuration RRC signaling.

[0118] Optionally, the base station can send the signaling radio bearers (SRB) and data radio bearers (DRB) configuration information for the terminal to report AI-related information to the terminal.

[0119] The base station receives AI-related information from the terminal via SRB2 or a new configuration to the terminal's SRB or DRB.

[0120] The base station sends the AI ​​information fed back by the terminal to the network element equipment.

[0121] From the terminal side, the terminal receives AI-related configuration information sent by the base station and reports AI-related data to the base station;

[0122] The terminal's AS layer sends AI-related configurations to the NAS layer and receives AI information from the NAS layer.

[0123] The terminal sends the terminal AI reporting information through SRB2 or a dedicated SRB or DRB configured by the new base station;

[0124] The terminal reports AI-related support capabilities, including at least one of the following:

[0125] Does it support reporting perception data for AI model training or inference in the big data analysis unit?

[0126] Supported types of perceived data reporting or AI training models;

[0127] Does it support AI applications, such as AI model training or AI inference?

[0128] The information transmission method provided in this application enables a data analysis platform to obtain relevant data from the wireless side and the service side, and based on this data, trains an AI model used by the base station or terminal side to adjust network parameters or replace traditional protocols in the data analysis unit, thereby improving network performance and reducing the complexity of the air interface and protocols. In addition, it can also provide open network capabilities for AI algorithms and models to support applications of low-latency and high-reliability services such as vehicle networking.

[0129] The following provides examples illustrating the application scenarios of the information transmission method provided in this application.

[0130] Scenario 1: When the terminal does not have sufficient memory or computing power, the training or inference of the intelligent model can be carried out in the cloud, including the following process:

[0131] The base station (i.e., the first network device) receives configuration information from the second network device regarding whether to report sensing data (sensing data can be understood as data indicated by configuration information) for training or inference of the AI ​​model at the big data analysis unit. In this application, the AI ​​model refers to an intelligent model.

[0132] The base station sends this configuration information to the terminal, which can be configured to send RRC signaling via RRC reconfiguration signaling or dedicated AI-related information; optionally, a dedicated SRB or DRB can be configured for the terminal.

[0133] The terminal's AS layer sends this configuration information to the terminal's NAS layer;

[0134] The terminal sends the sensing data to the base station. When sending the sensing data, it can do so through SRB2 or through a new dedicated SRB or DRB.

[0135] The base station sends the sensed data to the network element device (which can be understood as a second network device). The network element device can be the core network, network management system, centralized big data platform, edge big data platform, or internal functional module of the base station.

[0136] AI-related configuration information (which can be understood as configuration information) can be either information transmitted and displayed on the interface or information encapsulated in a container.

[0137] Scenario 2: When the terminal can run AI inference, the terminal needs to acquire the AI ​​training model, including the following process:

[0138] The base station sends this configuration information to the terminal. The configuration information includes the AI ​​training model, and the RRC signaling can be configured through RRC reconfiguration signaling or dedicated AI-related information.

[0139] The terminal's AS layer sends this configuration information to the terminal's NAS layer;

[0140] The terminal uses AI training models based on configuration information and performs AI inference using perceptual data.

[0141] Scenario 3: The terminal and the data analysis platform jointly train the AI ​​model, including the following process:

[0142] The base station sends configuration information to the terminal. The configuration information includes whether it needs to cooperate with the big data analysis unit for AI training and / or the model that needs to be trained by the terminal. Optionally, it includes the AI ​​model trained by the big data analysis unit. The RRC signaling can be sent by configuring RRC reconfiguration signaling or dedicated AI-related information.

[0143] The terminal's AS layer sends configuration information to the NAS layer;

[0144] Based on configuration information and the training model from the big data analysis unit, the terminal uses perceived data to update the AI ​​model or generate a terminal-side training model, and reports the updated training model or terminal training model to the base station. These updated intelligent models can be used for joint training with the network-side intelligent model. Optionally, to reduce data transmission volume, if the base station instructs to report enhanced AI training information, only the incremental information relative to the previous report can be reported.

[0145] The terminal can send reporting information via SRB2 or via a new dedicated SRB or DRB;

[0146] The base station sends the AI ​​data reported by the terminal to the network element device.

[0147] Scenario 4: A method for optimizing wireless resource scheduling using neural networks, including the following process:

[0148] The base station (including the first data processing unit) receives configuration information from network devices regarding whether to report sensing data for AI model training or inference at the big data analysis unit (including the second data processing unit); such as... Figure 3b As shown, the terminal can be a terminal used for Augmented Reality (AR) or a terminal used for Virtual Reality (VR).

[0149] The base station sends this configuration information to the terminal, which can configure the RRC signaling through Radio Resource Control (RRC) reconfiguration signaling or dedicated AI-related information.

[0150] Optionally, a dedicated SRB or DRB can be configured for the terminal;

[0151] The terminal AS layer sends all or part of the configuration information to the NAS layer;

[0152] The terminal sends the sensed data to the base station, either via SRB2 or via a new dedicated SRB or DRB;

[0153] The perception data includes: sensor information, such as barometer, altimeter, and gyroscope information; geographic location information; service-level perception information, such as video version switching count, average throughput, initial playback latency, and cache level; wireless-related information, such as channel quality information and channel state information (CSI) feedback information; and service quality of service (QoS) requirements, such as guaranteed rate and latency requirements.

[0154] The base station sends the sensing data to the network element device. The network element device uses this sensing data to train the weights of the deep neural network and sends the AI ​​training model to the base station or terminal. The base station or terminal uses the training model to perform inference based on the real-time sensing data fed back by the terminal as input, and generates parameters for scheduling, including time-frequency domain resources and MCS used for modulation and demodulation.

[0155] like Figure 4 As shown, Figure 4 This is a schematic diagram of the structure of a terminal provided in an embodiment of the present invention, such as... Figure 4 As shown, terminal 400 includes:

[0156] The receiving module 401 is used to receive configuration information sent by the first network device;

[0157] The execution module 402 is used to execute the intelligent-related operations configured in the configuration information.

[0158] Furthermore, the configuration information is configured with at least one of the following:

[0159] Configure the terminal's intelligent model information;

[0160] The terminal is configured to perform reasoning based on the indicated intelligent model information;

[0161] Instructions for configuring the terminal to perform intelligent model training;

[0162] Instructions for intelligent model updates on the configuration terminal;

[0163] Configure the terminal to report the trained or updated intelligent model information;

[0164] Configure the reporting conditions and / or the reported data information for the terminal; the data information is used for training or inference of the intelligent model;

[0165] Transmission resource information configured for the terminal to report data information used for training or inference of intelligent models; and

[0166] Transmission resource information configured for the terminal to report execution result data, wherein the execution result data is the data obtained by the terminal performing the intelligent related operations.

[0167] Furthermore, the updated intelligent model information is described using incremental information; or, the updated intelligent model information is used to cooperate with the network-side intelligent model for joint training.

[0168] Furthermore, the intelligent-related operations include at least one of the following operations:

[0169] A sending operation is used to send the data indicated by the configuration information to a first network device, the data being used for training or inference of an intelligent model;

[0170] Processing operations related to intelligent models.

[0171] Furthermore, the processing operation includes at least one of the following operations:

[0172] The intelligent model indicated by the configuration information is used for inference, training the intelligent model indicated by the configuration information, updating the intelligent model indicated by the configuration information, reporting the trained intelligent model, and reporting the updated intelligent model.

[0173] Furthermore, terminal 400 also includes:

[0174] The first sending module is used to send the intelligent support capability information.

[0175] Furthermore, the support capability information includes at least one of the following:

[0176] Whether it supports sending data, which is used for training or inference of intelligent models;

[0177] Supported data types to send;

[0178] Does it support intelligent applications?

[0179] Supported types of intelligent models.

[0180] Furthermore, terminal 400 also includes:

[0181] The second sending module is used to send the execution result data obtained from performing the intelligent related operations.

[0182] Furthermore, the execution result data is at least one of the following:

[0183] The configuration information indicates the data, which is used for training or inference of the intelligent model;

[0184] The training results obtained by training the intelligent model indicated by the configuration information;

[0185] The updated intelligent model indicated by the updated configuration information yields an updated result.

[0186] Furthermore, the configuration information is also used to indicate the signaling radio bearer, data radio bearer, or physical channel for sending the execution result data.

[0187] Furthermore, the configuration information is sent via RRC signaling, NAS signaling, media access control layer signaling, or physical layer signaling.

[0188] Terminal 400 can achieve Figure 2 The various processes implemented on the terminal in the method embodiment shown can achieve the same technical effect, and will not be described again here to avoid repetition.

[0189] Figure 5 To illustrate the structural diagrams of the terminals in various embodiments of the present invention, the terminal 800 includes, but is not limited to: a transceiver unit (i.e., a transceiver) 801, a network module 802, an audio output unit 803, an input unit 804, a sensor 805, a display unit 806, a user input unit 807, an interface unit 808, a memory 809, a processor 810, and a power supply 88, etc. Those skilled in the art will understand that... Figure 5 The terminal structure shown does not constitute a limitation on the terminal. A terminal may include more or fewer components than shown, or combine certain components, or have different component arrangements. In embodiments of the present invention, the terminal includes, but is not limited to, mobile phones, tablet computers, laptop computers, PDAs, in-vehicle terminals, wearable devices, and pedometers.

[0190] In one embodiment of the present invention, the transceiver unit 801 is used to receive configuration information sent by the first network device;

[0191] The processor 810 is used to execute the intelligent-related operations configured in the configuration information.

[0192] Furthermore, the configuration information is configured with at least one of the following:

[0193] Configure the terminal's intelligent model information;

[0194] The terminal is configured to perform reasoning based on the indicated intelligent model information;

[0195] Instructions for configuring the terminal to perform intelligent model training;

[0196] Instructions for intelligent model updates on the configuration terminal;

[0197] Configure the terminal to report the trained or updated intelligent model information;

[0198] Configure the reporting conditions and / or the reported data information for the terminal; the data information is used for training or inference of the intelligent model;

[0199] Transmission resource information configured for the terminal to report data information, which is used for training or inference of intelligent models;

[0200] Transmission resource information configured for the terminal to report execution result data, wherein the execution result data is the data obtained by the terminal performing the intelligent related operations.

[0201] Furthermore, the updated intelligent model information is described using incremental information; or, the updated intelligent model information is used to cooperate with the network-side intelligent model for joint training.

[0202] Furthermore, the intelligent-related operations include at least one of the following operations:

[0203] A sending operation is used to send the data indicated by the configuration information to a first network device, the data being used for training or inference of an intelligent model;

[0204] Processing operations related to intelligent models.

[0205] Furthermore, the processing operation includes at least one of the following operations:

[0206] The intelligent model indicated by the configuration information is used for inference, training the intelligent model indicated by the configuration information, updating the intelligent model indicated by the configuration information, reporting the trained intelligent model, and reporting the updated intelligent model.

[0207] Furthermore, the transceiver unit 801 is also used to send the intelligent support capability information.

[0208] Furthermore, the support capability information includes at least one of the following:

[0209] Whether it supports sending data, which is used for training or inference of intelligent models;

[0210] Supported data types to send;

[0211] Does it support intelligent applications?

[0212] Supported types of intelligent models.

[0213] Furthermore, the transceiver unit 801 is also used to send the execution result data obtained from performing the intelligent related operations.

[0214] Furthermore, the execution result data is at least one of the following:

[0215] The configuration information indicates the data, which is used for training or inference of the intelligent model;

[0216] The training results obtained by training the intelligent model indicated by the configuration information;

[0217] The updated intelligent model indicated by the updated configuration information yields an updated result.

[0218] Furthermore, the configuration information is also used to indicate the signaling radio bearer, data radio bearer, or physical channel for sending the execution result data.

[0219] Furthermore, the configuration information is sent via Radio Resource Control (RRC) signaling, Non-Access Stratum (NAS) signaling, Media Access Control (MAC) signaling, or Physical Layer signaling.

[0220] Terminal 800 can achieve Figure 2 The various processes implemented on the terminal in the method embodiment shown can achieve the same technical effect, and will not be described again here to avoid repetition.

[0221] It should be understood that, in this embodiment of the invention, the transceiver unit 801 can be used for receiving and sending signals during information transmission or calls. Specifically, it receives downlink data from the base station and processes it with the processor 810; additionally, it sends uplink data to the base station. Typically, the transceiver unit 801 includes, but is not limited to, an antenna, at least one amplifier, a transceiver, a coupler, a low-noise amplifier, a duplexer, etc. Furthermore, the transceiver unit 801 can also communicate with networks and other devices via a wireless communication system.

[0222] Terminal 800 provides users with wireless broadband internet access through network module 802, such as helping users send and receive emails, browse web pages, and access streaming media.

[0223] The audio output unit 803 can convert audio data received by the transceiver unit 801 or the network module 802 or stored in the memory 809 into audio signals and output them as sound. Furthermore, the audio output unit 803 can also provide audio output related to specific functions performed by the terminal 800 (e.g., call signal reception sound, message reception sound, etc.). The audio output unit 803 includes a speaker, a buzzer, and a receiver, etc.

[0224] Input unit 804 is used to receive audio or video signals. Input unit 804 may include a graphics processing unit (GPU) 8041 and a microphone 8042. The GPU 8041 processes image data of still images or videos acquired by an image capture device (such as a camera) in video capture mode or image capture mode. The processed image frames can be displayed on display unit 806. The image frames processed by GPU 8041 can be stored in memory 809 (or other storage media) or transmitted via transceiver unit 801 or network module 802. Microphone 8042 can receive sound and process such sound into audio data. The processed audio data can be converted into a format that can be transmitted to a mobile communication base station via transceiver unit 801 in telephone call mode.

[0225] The terminal 800 also includes at least one sensor 805, such as a light sensor, a motion sensor, and other sensors. Specifically, the light sensor includes an ambient light sensor and a proximity sensor. The ambient light sensor can adjust the brightness of the display panel 8061 according to the ambient light level, and the proximity sensor can turn off the display panel 8061 and / or backlight when the terminal 800 is moved to the ear. As a type of motion sensor, the accelerometer sensor can detect the magnitude of acceleration in various directions (generally three axes). When stationary, it can detect the magnitude and direction of gravity and can be used to identify the terminal's posture (e.g., landscape / portrait switching, related games, magnetometer posture calibration), vibration recognition related functions (e.g., pedometer, tapping), etc. The sensor 805 may also include a fingerprint sensor, pressure sensor, iris sensor, molecular sensor, gyroscope, barometer, hygrometer, thermometer, infrared sensor, etc., which will not be described in detail here.

[0226] The display unit 806 is used to display information input by the user or information provided to the user. The display unit 806 may include a display panel 8061, which may be configured in the form of a liquid crystal display (LCD), an organic light-emitting diode (OLED), or the like.

[0227] User input unit 807 can be used to receive input numerical or character information, and generate key signal inputs related to user settings and function control of the terminal. Specifically, user input unit 807 includes a touch panel 8071 and other input devices 8072. Touch panel 8071, also known as a touch screen, can collect touch operations on or near the user (e.g., operations performed by the user using a finger, stylus, or any suitable object or accessory on or near touch panel 8071). Touch panel 8071 may include two parts: a touch detection device and a touch controller. The touch detection device detects the user's touch position and the signal generated by the touch operation, and transmits the signal to the touch controller; the touch controller receives touch information from the touch detection device, converts it into touch point coordinates, and sends it to processor 810, receiving and executing commands from processor 810. Furthermore, touch panel 8071 can be implemented using various types such as resistive, capacitive, infrared, and surface acoustic wave. In addition to touch panel 8071, user input unit 807 may also include other input devices 8072. Specifically, other input devices 8072 may include, but are not limited to, physical keyboards, function keys (such as volume control buttons, power buttons, etc.), trackballs, mice, joysticks, etc., which will not be described in detail here.

[0228] Furthermore, the touch panel 8071 can cover the display panel 8061. When the touch panel 8071 detects a touch operation on or near it, it transmits the information to the processor 810 to determine the type of touch event. Subsequently, the processor 810 provides corresponding visual output on the display panel 8061 based on the type of touch event. Although in Figure 5 In this embodiment, the touch panel 8071 and the display panel 8061 are two independent components to realize the input and output functions of the terminal. However, in some embodiments, the touch panel 8071 and the display panel 8061 can be integrated to realize the input and output functions of the terminal. The specific implementation is not limited here.

[0229] Interface unit 808 serves as an interface for connecting external devices to terminal 800. For example, external devices may include a wired or wireless headset port, an external power supply (or battery charger) port, a wired or wireless data port, a memory card port, a port for connecting a device with an identification module, an audio input / output (I / O) port, a video I / O port, a headphone port, and so on. Interface unit 808 can be used to receive input from external devices (e.g., data, power, etc.) and transmit the received input to one or more elements within terminal 800, or it can be used to transmit data between terminal 800 and external devices.

[0230] The memory 809 can be used to store software programs and various data. The memory 809 may primarily include a program storage area and a data storage area. The program storage area may store the operating system, applications required for at least one function (such as sound playback, image playback, etc.), etc.; the data storage area may store data created based on the use of the mobile phone (such as audio data, phonebook, etc.). Furthermore, the memory 809 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0231] The processor 810 is the control center of the terminal, connecting various parts of the terminal through various interfaces and lines. It executes software programs and / or modules stored in the memory 809, and calls data stored in the memory 809 to perform various functions and process data, thereby providing overall monitoring of the terminal. The processor 810 may include one or more processing units; preferably, the processor 810 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, user interface, and applications, and the modem processor mainly handles wireless communication. It is understood that the modem processor may not be integrated into the processor 810.

[0232] The terminal 800 may also include a power supply 811 (e.g., a battery) that supplies power to various components. Preferably, the power supply 811 is logically connected to the processor 810 through a power management system, thereby enabling functions such as charging, discharging, and power consumption management through the power management system.

[0233] In addition, terminal 800 includes some functional modules not shown, which will not be described in detail here.

[0234] Preferably, this embodiment of the invention also provides a terminal, including a processor 810, a memory 809, and a computer program stored in the memory 809 and executable on the processor 810, wherein the computer program, when executed by the processor 810, implements the above-described... Figure 2 The various processes of the information transmission method embodiments shown can achieve the same technical effect, and will not be described again here to avoid repetition.

[0235] See Figure 6 , Figure 6 This is a schematic diagram of the structure of a network device provided in an embodiment of the present invention, such as... Figure 6 As shown, network device 600 is the first network device, and network device 600 includes:

[0236] The sending module 601 is used to send configuration information to the terminal, wherein the configuration information is used to configure the terminal to perform intelligent related operations.

[0237] Furthermore, the configuration information is configured with at least one of the following:

[0238] Configure the terminal's intelligent model information;

[0239] The terminal is configured to perform reasoning based on the indicated intelligent model information;

[0240] Instructions for configuring the terminal to perform intelligent model training;

[0241] Instructions for intelligent model updates on the configuration terminal;

[0242] Configure the terminal to report the trained or updated intelligent model information;

[0243] Configure the reporting conditions and / or the reported data information for the terminal; the data information is used for training or inference of the intelligent model;

[0244] Transmission resource information configured for the terminal to report data information, which is used for training or inference of intelligent models;

[0245] Transmission resource information configured for the terminal to report execution result data, wherein the execution result data is the data obtained by the terminal performing the intelligent related operations.

[0246] Furthermore, the updated intelligent model information is described using incremental information; or, the updated intelligent model information is used to cooperate with the network-side intelligent model for joint training.

[0247] Furthermore, the intelligent-related operations include at least one of the following operations:

[0248] A sending operation is used to send the data indicated by the configuration information to a first network device, the data being used for training or inference of an intelligent model;

[0249] Processing operations related to intelligent models.

[0250] Furthermore, the processing operation includes at least one of the following operations:

[0251] The intelligent model indicated by the configuration information is used for inference, training the intelligent model indicated by the configuration information, updating the intelligent model indicated by the configuration information, reporting the trained intelligent model, and reporting the updated intelligent model.

[0252] Furthermore, network equipment 600 also includes:

[0253] The first receiving module is used to receive intelligent support capability information sent by the terminal.

[0254] Furthermore, the support capability information includes at least one of the following:

[0255] Whether it supports sending data, which is used for training or inference of intelligent models;

[0256] Supported data types to send;

[0257] Does it support intelligent applications?

[0258] Supported types of intelligent models.

[0259] Furthermore, network equipment 600 also includes:

[0260] The second receiving module is used to receive the configuration information sent by the second network device.

[0261] Furthermore, the second network device is at least one of an access network element, a network management system, a core network element, and an edge computing node.

[0262] Furthermore, network equipment 600 also includes:

[0263] The third receiving module is used to receive the execution result data obtained by performing the intelligent related operations sent by the terminal.

[0264] Furthermore, the execution result data is at least one of the following:

[0265] The configuration information indicates the data, which is used for training or inference of the intelligent model;

[0266] The training results obtained by training the intelligent model indicated by the configuration information;

[0267] The updated intelligent model indicated by the updated configuration information yields an updated result.

[0268] Furthermore, the configuration information is also used to indicate the signaling radio bearer, data radio bearer, or physical channel for sending the execution result data.

[0269] Furthermore, the configuration information is sent via Radio Resource Control (RRC) signaling, Non-Access Stratum (NAS) signaling, Media Access Control (MAC) signaling, or Physical Layer signaling.

[0270] Network device 600 can achieve Figure 1 The various processes implemented by the first network device in the method embodiment shown, and the same technical effects achieved, will not be repeated here to avoid duplication.

[0271] See Figure 7 , Figure 7 This is a schematic diagram of the structure of a network device provided in an embodiment of the present invention, such as... Figure 7 As shown, it includes a bus 1201, a transceiver 1202, an antenna 1203, a bus interface 1204, a processor 1205, and a memory 1206.

[0272] In one embodiment of the present invention, the network device is a first network device, transceiver 1202, used to send configuration information to the terminal, the configuration information being used to configure the terminal to perform intelligent related operations.

[0273] Furthermore, the configuration information is configured with at least one of the following:

[0274] Configure the terminal's intelligent model information;

[0275] The terminal is configured to perform reasoning based on the indicated intelligent model information;

[0276] Instructions for configuring the terminal to perform intelligent model training;

[0277] Instructions for intelligent model updates on the configuration terminal;

[0278] Configure the terminal to report the trained or updated intelligent model information;

[0279] Configure the reporting conditions and / or the reported data information for the terminal; the data information is used for training or inference of the intelligent model;

[0280] Transmission resource information configured for the terminal to report data information, which is used for training or inference of intelligent models;

[0281] Transmission resource information configured for the terminal to report execution result data, wherein the execution result data is the data obtained by the terminal performing the intelligent related operations.

[0282] Furthermore, the intelligent-related operations include at least one of the following operations:

[0283] A sending operation is used to send the data indicated by the configuration information to a first network device, the data being used for training or inference of an intelligent model;

[0284] Processing operations related to intelligent models.

[0285] Furthermore, the processing operation includes at least one of the following operations:

[0286] The intelligent model indicated by the configuration information is used for inference, training the intelligent model indicated by the configuration information, updating the intelligent model indicated by the configuration information, reporting the trained intelligent model, and reporting the updated intelligent model.

[0287] The transceiver 1202 is also used to receive intelligent support capability information sent by the terminal.

[0288] Furthermore, the support capability information includes at least one of the following:

[0289] Whether it supports sending data, which is used for training or inference of intelligent models;

[0290] Supported data types to send;

[0291] Does it support intelligent applications?

[0292] Supported types of intelligent models.

[0293] Furthermore, the transceiver 1202 is also used to receive the configuration information sent by the second network device.

[0294] Furthermore, the second network device is at least one of an access network element, a network management system, a core network element, and an edge computing node.

[0295] Furthermore, the transceiver 1202 is also used to receive execution result data sent by the terminal from the execution of the intelligent related operations.

[0296] Furthermore, the execution result data is at least one of the following:

[0297] The configuration information indicates the data, which is used for training or inference of the intelligent model;

[0298] The training results obtained by training the intelligent model indicated by the configuration information;

[0299] The updated intelligent model indicated by the updated configuration information yields an updated result.

[0300] Furthermore, the configuration information is also used to indicate the signaling radio bearer, data radio bearer, or physical channel for sending the execution result data.

[0301] Furthermore, the configuration information is sent via Radio Resource Control (RRC) signaling, Non-Access Stratum (NAS) signaling, Media Access Control (MAC) signaling, or Physical Layer signaling.

[0302] The device in this embodiment can achieve Figure 1The various processes implemented by the first network device in the illustrated embodiment achieve the same technical effect, and will not be described in detail here.

[0303] exist Figure 7 In this document, a bus architecture (represented by bus 1201) is used. Bus 1201 may include any number of interconnected buses and bridges, linking various circuits including one or more processors represented by processor 1205 and memory represented by memory 1206. Bus 1201 may also link various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and therefore will not be described further herein. Bus interface 1204 provides an interface between bus 1201 and transceiver 1202. Transceiver 1202 may be a single element or multiple elements, such as multiple receivers and transmitters, providing a unit for communicating with various other devices over a transmission medium. Data processed by processor 1205 is transmitted over a wireless medium via antenna 1203, which further receives data and transmits it to processor 1205.

[0304] Processor 1205 is responsible for managing bus 1201 and general processing, and can also provide various functions, including timing, peripheral interface, voltage regulation, power management, and other control functions. Memory 1206 can be used to store data used by processor 1205 during operation.

[0305] Optionally, the processor 1205 can be a CPU, ASIC, FPGA, or CPLD.

[0306] Preferably, this embodiment of the invention also provides a network device, including a processor 1205, a memory 1206, and a computer program stored in the memory 1206 and executable on the processor 1205, wherein the computer program, when executed by the processor 1205, implements the above-described... Figure 1 The various processes in the information transmission method shown can achieve the same technical effect, and will not be described in detail here to avoid repetition.

[0307] This invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements... Figure 1 The steps in the information transmission method shown, or the steps implemented when the computer program is executed by the processor, are as follows: Figure 2 The steps in the information transmission method shown.

[0308] The computer-readable storage medium mentioned above includes, for example, ROM, RAM, magnetic disk, or optical disk.

[0309] 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. Unless otherwise specified, 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.

[0310] Through 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 software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0311] The embodiments of the present invention have been described above with reference to the accompanying drawings. However, the present invention 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 forms under the guidance of the present invention without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of the present invention.

Claims

1. An information transmission method for a first network device, characterized in that, include: Send configuration information to the terminal, the configuration information being used to configure the terminal to perform intelligent-related operations; The intelligent-related operations include at least one of the following: A sending operation is used to send the data indicated by the configuration information to a first network device, the data being used for training or inference of an intelligent model; Processing operations related to intelligent models; The processing operation includes at least one of the following operations: The intelligent model indicated by the configuration information is used to perform inference, train the intelligent model indicated by the configuration information, update the intelligent model indicated by the configuration information, report the trained intelligent model, and report the updated intelligent model. The configuration information is used to configure the terminal to use the intelligent model to adjust network parameters or replace protocols.

2. The information transmission method according to claim 1, characterized in that, The configuration information is configured with at least one of the following: Configure the terminal's intelligent model information; The terminal is configured to perform reasoning based on the indicated intelligent model information; Instructions for configuring the terminal to perform intelligent model training; Instructions for intelligent model updates on the configuration terminal; Configure the terminal to report the trained or updated intelligent model information; Configure the reporting conditions and / or the reported data information for the terminal; the data information is used for training or inference of the intelligent model; Transmission resource information configured for the terminal to report data information, which is used for training or inference of intelligent models; Transmission resource information configured for the terminal to report execution result data, wherein the execution result data is the data obtained by the terminal performing the intelligent related operations.

3. The information transmission method according to claim 2, characterized in that: The updated intelligent model information is described using incremental information; or The updated intelligent model information is used to perform joint training with the network-side intelligent model.

4. The information transmission method according to claim 1, characterized in that, Also includes: Receive intelligent support capability information sent by the terminal.

5. The information transmission method according to claim 4, characterized in that, The support capability information includes at least one of the following: Whether it supports sending data, which is used for training or inference of intelligent models; Supported data types to send; Does it support intelligent applications? Supported types of intelligent models.

6. The information transmission method according to any one of claims 1-5, characterized in that, Before sending the configuration information to the terminal, the method further includes: Receive the configuration information sent by the second network device.

7. The information transmission method according to claim 6, characterized in that, The second network device is at least one of the following: access network element, network management, core network element, and edge computing node.

8. The information transmission method according to any one of claims 1-5, characterized in that, After sending the configuration information to the terminal, the process also includes: Receive the execution result data obtained from performing the intelligent related operations sent by the terminal.

9. The information transmission method according to claim 8, characterized in that, The execution result data is at least one of the following: The configuration information indicates the data, which is used for training or inference of the intelligent model; The training results obtained by training the intelligent model indicated by the configuration information; The updated intelligent model indicated by the updated configuration information yields an updated result.

10. The information transmission method according to claim 1, characterized in that, The configuration information is sent via Radio Resource Control (RRC) signaling, Non-Access Stratum (NAS) signaling, Media Access Control (MAC) signaling, or Physical Layer signaling.

11. An information transmission method for a terminal, characterized in that, include: Receive configuration information sent by the first network device; Perform the intelligent-related operations configured in the configuration information; The intelligent-related operations include at least one of the following: A sending operation is used to send the data indicated by the configuration information to a first network device, the data being used for training or inference of an intelligent model; Processing operations related to intelligent models; The processing operation includes at least one of the following operations: The intelligent model indicated by the configuration information is used to perform inference, train the intelligent model indicated by the configuration information, update the intelligent model indicated by the configuration information, report the trained intelligent model, and report the updated intelligent model. The configuration information is used to configure the terminal to use the intelligent model to adjust network parameters or replace protocols.

12. The information transmission method according to claim 11, characterized in that, The configuration information is configured with at least one of the following: Configure the terminal's intelligent model information; The terminal is configured to perform reasoning based on the indicated intelligent model information; Instructions for configuring the terminal to perform intelligent model training; Instructions for intelligent model updates on the configuration terminal; Configure the terminal to report the trained or updated intelligent model information; The reporting conditions and / or the reported data information configured for the terminal; the data information is used for training or inference of the intelligent model; Transmission resource information configured for the terminal to report data information, which is used for training or inference of intelligent models; Transmission resource information configured for the terminal to report execution result data, wherein the execution result data is the data obtained by the terminal performing the intelligent related operations.

13. The information transmission method according to claim 12, characterized in that: The updated intelligent model information is described using incremental information; or The updated intelligent model information is used to perform joint training with the network-side intelligent model.

14. The information transmission method according to claim 11, characterized in that, Also includes: Send the aforementioned support capability information related to intelligence.

15. The information transmission method according to claim 14, characterized in that, The support capability information includes at least one of the following: Whether it supports sending data, which is used for training or inference of intelligent models; Supported data types to send; Does it support intelligent applications? Supported types of intelligent models.

16. The information transmission method according to any one of claims 11-15, characterized in that, After executing the intelligent-related operations configured in the configuration information, the method further includes: Send the execution result data obtained from performing the intelligent related operations.

17. The information transmission method according to claim 16, characterized in that, The execution result data is at least one of the following: The configuration information indicates the data information, which is used for training or inference of the intelligent model; The training results obtained by training the intelligent model indicated by the configuration information; The updated intelligent model indicated by the updated configuration information yields an updated result.

18. The information transmission method according to claim 11, characterized in that, The configuration information is sent via Radio Resource Control (RRC) signaling, Non-Access Stratum (NAS) signaling, Media Access Control (MAC) signaling, or Physical Layer signaling.

19. A network device, characterized in that, include: Processor and transceiver; The transceiver is used to send configuration information to the terminal, and the configuration information is used to configure the terminal to perform intelligent-related operations; The intelligent-related operations include at least one of the following: A sending operation is used to send the data indicated by the configuration information to a first network device, the data being used for training or inference of an intelligent model; Processing operations related to intelligent models; The processing operation includes at least one of the following operations: The intelligent model indicated by the configuration information is used to perform inference, train the intelligent model indicated by the configuration information, update the intelligent model indicated by the configuration information, report the trained intelligent model, and report the updated intelligent model. The configuration information is used to configure the terminal to use the intelligent model to adjust network parameters or replace protocols.

20. A terminal, characterized in that, include: Processor and transceiver; The transceiver is used to receive configuration information sent by the first network device; The processor is used to execute the intelligent-related operations configured in the configuration information; The intelligent-related operations include at least one of the following: A sending operation is used to send the data indicated by the configuration information to a first network device, the data being used for training or inference of an intelligent model; Processing operations related to intelligent models; The processing operation includes at least one of the following operations: The intelligent model indicated by the configuration information is used to perform inference, train the intelligent model indicated by the configuration information, update the intelligent model indicated by the configuration information, report the trained intelligent model, and report the updated intelligent model. The configuration information is used to configure the terminal to use the intelligent model to adjust network parameters or replace protocols.

21. A network device, characterized in that, include: The sending module is used to send configuration information to the terminal, wherein the configuration information is used to configure the terminal to perform intelligent-related operations; The intelligent-related operations include at least one of the following: A sending operation is used to send the data indicated by the configuration information to a first network device, the data being used for training or inference of an intelligent model; Processing operations related to intelligent models; The processing operation includes at least one of the following operations: The intelligent model indicated by the configuration information is used to perform inference, train the intelligent model indicated by the configuration information, update the intelligent model indicated by the configuration information, report the trained intelligent model, and report the updated intelligent model. The configuration information is used to configure the terminal to use the intelligent model to adjust network parameters or replace protocols.

22. A terminal, characterized in that, include: The receiving module is used to receive configuration information sent by the first network device; An execution module is used to execute the intelligent-related operations configured in the configuration information; The intelligent-related operations include at least one of the following: A sending operation is used to send the data indicated by the configuration information to a first network device, the data being used for training or inference of an intelligent model; Processing operations related to intelligent models; The processing operation includes at least one of the following operations: The intelligent model indicated by the configuration information is used to perform inference, train the intelligent model indicated by the configuration information, update the intelligent model indicated by the configuration information, report the trained intelligent model, and report the updated intelligent model. The configuration information is used to configure the terminal to use the intelligent model to adjust network parameters or replace protocols.

23. A network device, characterized in that, It includes a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of the information transmission method as described in any one of claims 1-10.

24. A terminal, characterized in that, It includes a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of the information transmission method as described in any one of claims 11 to 18.

25. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the information transmission method as described in any one of claims 1 to 10, or, when executed by a processor, implements the steps of the information transmission method as described in any one of claims 11 to 18.

Images