Communication method, apparatus and system

Abstract

A communication method, apparatus and system, which relate to the field of communications, so as to reduce the energy consumption of a terminal apparatus in an AI scenario. The method comprises: a first device acquiring data of a first terminal apparatus, and training a first model on the basis of the data of the first terminal apparatus. Correspondingly, the first terminal apparatus receives the first model from the first device, and / or, data obtained by performing inference on the basis of the first model. The first device comprises a first resource allocated to the first terminal apparatus. The data of the first terminal apparatus that is acquired by the first device is stored in the first resource. The solutions of the present application can be widely applied to the technical field of communications, and fields such as artificial intelligence, the Internet of Vehicles, and smart home networking.

Description

A communication method, apparatus and system

[0001] This application claims priority to Chinese Patent Application No. 202410807618.2, filed on June 20, 2024, entitled "A Communication Method, Apparatus and System", the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to the field of communications, and more particularly to a communication method, apparatus, and system. Background Technology

[0003] In recent years, with the rapid development of artificial intelligence (AI) technology, leveraging AI to improve the network performance of 5G mobile communication systems and future communication systems has become a research hotspot in the mobile communications field. Numerous research results demonstrate that AI technology can enhance various aspects of existing 5G network designs at multiple levels, thereby improving system efficiency and user experience. In particular, the introduction of AI-based designs into several wireless air interface technologies will bring about fundamental changes in wireless network design and is a key direction for future network design.

[0004] The introduction of AI-based designs into various wireless air interface technologies places high demands on the hardware of terminal devices. For example, the hardware of these devices needs to perform one or more of the following: measure large amounts of data to train AI models, process large amounts of data to obtain AI models or data obtained from AI model inference, and support large-capacity energy storage devices to ensure the training of AI models. Therefore, in AI-based design scenarios, reducing the energy consumption or processing complexity of terminal devices has become an urgent problem to be solved. Summary of the Invention

[0005] This application provides a communication method, apparatus, and system to reduce the energy consumption or processing complexity of terminal devices in AI scenarios.

[0006] To achieve the above objectives, this application adopts the following technical solution:

[0007] In a first aspect, embodiments of this application provide a communication method. This method can be executed by a first device, which may be a first equipment or a functional module or chip within the first device. Taking execution by the first device as an example, the method includes: the first device acquiring data from a first terminal device, and training a first model based on the data from the first terminal device. The first device includes first resources, and the data of the first terminal device is stored in the first device within the first resources allocated to the first terminal device.

[0008] Based on the method described in the first aspect, in an AI scenario, the first device acquires data from the first terminal device to train an AI model. This eliminates the need for the first terminal device to expend significant resources training the AI ​​model, thereby reducing its energy consumption. Simultaneously, the data from the first terminal device is stored in the first resources allocated to it by the first device, enhancing the data security of the first terminal device.

[0009] In one possible design, the first device sends data inferred from the first model, and / or sends the first model. Based on this possible design, the device receiving the first model and / or data inferred from the first model, such as a first terminal device, no longer needs to expend significant resources, such as computing power and storage resources, thus reducing its own energy consumption.

[0010] In one possible design, the first device sending data inferred based on a first model and / or sending the first model may include: the first device receiving first information; and in response to the first information, the first device sending data inferred based on the first model and / or sending the first model. The first information is used to request the acquisition of the first model and / or the data inferred based on the first model.

[0011] Based on this possible design, the first device can trigger the sending of the first model and / or data inferred from the first model, thereby enabling on-demand sending of the first model and / or data inferred from the first model and improving its own performance.

[0012] In one possible design, the first device sends second information. The second information is used to indicate information about the first model, which includes one or more of the following: the applicable scenario of the first model, whether the first model has been trained or updated, the performance of the first model, the identifier of the first model, and the type of the first model.

[0013] Based on this possible design, the first device can send second information to the receiving device (e.g., the first terminal device) if it does not obtain information about the first model, so that the receiving device (e.g., the first terminal device) can obtain the first model in a scenario applicable to the first model.

[0014] In one possible design, the first device acquiring data from the first terminal device may include: the first device receiving data from the first terminal device of the network device; and / or, the first device receiving data from the first terminal device of the first terminal device.

[0015] Based on this possible design, the first device can acquire data from a variety of first terminal devices to fully utilize the data of the first terminal devices and improve the performance of the first terminal devices.

[0016] In one possible design, the data of the first terminal device includes one or more of the following: data measured by a chip in the first terminal device, data measured by a sensor in the first terminal device, application data of the first terminal device, location data of the first terminal device, data about the first terminal device measured or stored by a network device, and data about the first terminal device measured by other devices; the other devices are not deployed in the first terminal device and the network device.

[0017] Based on this possible design, the data from the first terminal device can correspond to different data for different communication scenarios, thus improving the applicability of this solution.

[0018] In one possible design, the information stored in the first resource is dedicated to the first terminal device; or, the information stored in the first resource is available to devices other than the first terminal device.

[0019] Based on this possible design, the first device can determine whether the information stored in the first resource can be shared based on whether the information is dedicated to the first terminal device. If the information stored in the first resource is dedicated to the first terminal device, then the information stored in the first resource cannot be shared. If the information stored in the first resource is available to devices other than the first terminal device, then the information stored in the first resource can be shared.

[0020] In one possible design, a first device sends a license request and, in response to the license request, receives a response message. The license request is used to request sharing of information stored in the first resource, and the response message indicates permission to share the information stored in the first resource.

[0021] Based on this possible design, when the first device needs to share information stored in the first resource, it needs to share the information stored in the first resource based on the instruction of the response message, thereby improving the security of the information stored in the first resource.

[0022] In one possible design, the first device receives a first request message for requesting training or updating a first model. Based on this possible design, the first device can implement triggered training or updating of the first model, achieving on-demand training or updating of the first model and improving its own performance.

[0023] In one possible design, the first device receives third information. This third information instructs the first device to acquire data from the first terminal device. Based on this design, the first device can acquire data from the first terminal device in a triggered manner, enabling on-demand acquisition of data and improving its own performance.

[0024] In one possible design, the first device receives the fourth information. Alternatively, the first device sends the fourth information. The fourth information is used to indicate configuration information for the data of the first terminal device.

[0025] Based on this possible design, the first device can flexibly obtain the configuration information of the first terminal device, which improves the applicability of this solution.

[0026] In one possible design, the configuration information of the data of the first terminal device includes one or more of the following: the content of the data of the first terminal device, the format of the data of the first terminal device, the reporting type of the data of the first terminal device, the reporting conditions of the data of the first terminal device, and the reporting termination conditions of the data of the first terminal device.

[0027] Based on this possible design, the configuration information of the data of the first terminal device can correspond to different information for different communication scenarios, which improves the applicability of this solution.

[0028] Secondly, embodiments of this application provide a communication method, which can be executed by a first terminal device. The first terminal device can be a terminal equipment or a functional module or chip within a terminal equipment. Taking execution by the first terminal device as an example, the method includes: the first terminal device receiving data from the first device based on inference from a first model. And / or, the first terminal device receiving a first model from the first device. Wherein, the first model is trained based on data from the first terminal device; the data of the first terminal device is stored in a first resource allocated to the first terminal device within the first device.

[0029] Based on the method described in the second aspect, in AI scenarios, the first terminal device no longer needs to expend significant resources training the AI ​​model, thus reducing the energy consumption of the first terminal device. Simultaneously, the data stored in the first terminal device is stored in the first resource allocated to it within the first device, enhancing the data security of the first terminal device.

[0030] In one possible design, the first terminal device receives a first model from the first device, and further includes: the first terminal device acquiring data obtained by reasoning from the first model based on the first model.

[0031] Based on this possible design, the first terminal device, upon receiving the first model, can acquire the data obtained from the inference of the first model in order to obtain the gain of the first model.

[0032] In one possible design, the first terminal device sends first information, which is used to request the acquisition of a first model and / or data obtained by reasoning based on the first model.

[0033] Based on this possible design, the first terminal device can acquire the first model and / or data obtained by reasoning based on the first model on demand, thereby improving its own performance.

[0034] In one possible design, the first terminal device receives second information. The second information is used to indicate information about the first model, which includes one or more of the following: the applicable scenario of the first model, whether the first model has been trained or updated, the performance of the first model, the identifier of the first model, and the type of the first model.

[0035] Based on this possible design, the first terminal device can obtain the information of the first model through the second information even when the information of the first model is not available locally, so as to obtain the first model in a scenario applicable to the first model.

[0036] In one possible design, the first terminal device sends its data to the first device; and / or, the first terminal device sends its data to the network device.

[0037] Based on this possible design, the first device can acquire data from the first terminal device through different devices, thus improving the applicability of this solution.

[0038] In one possible design, the data of the first terminal device includes one or more of the following: data measured by a chip in the first terminal device, data measured by a sensor in the first terminal device, application data of the first terminal device, location data of the first terminal device, data about the first terminal device measured or stored by a network device, and data about the first terminal device measured by other devices; the other devices are not deployed in the first terminal device and the network device.

[0039] Based on this possible design, the data from the first terminal device can correspond to different data for different communication scenarios, thus improving the applicability of this solution.

[0040] In one possible design, the information stored in the first resource is dedicated to the first terminal device; or, the information stored in the first resource is available to devices other than the first terminal device.

[0041] Based on this possible design, the first device can determine whether the information stored in the first resource can be shared based on whether the information is dedicated to the first terminal device. If the information stored in the first resource is dedicated to the first terminal device, then the information stored in the first resource cannot be shared. If the information stored in the first resource is available to devices other than the first terminal device, then the information stored in the first resource can be shared.

[0042] In one possible design, the first terminal device receives a license request and, in response to the license request, sends a response message. The license request is used to request sharing of information stored in the first resource, and the response message is used to indicate permission to share the information stored in the first resource.

[0043] Based on this possible design, when the first device needs to share the information stored in the first resource, it can share the information stored in the first resource based on the instructions of the first terminal device, thereby improving the security of the information stored in the first resource.

[0044] In one possible design, the first terminal device sends a first request message to request training or updating of the first model. Based on this possible design, the first device can train or update the first model on demand, thereby improving its own performance.

[0045] In one possible design, the first terminal device sends third information. This third information instructs the first device to acquire data from the first terminal device. Based on this possible design, the first device can acquire data from the first terminal device on demand, thereby improving its own performance.

[0046] In one possible design, the first terminal device sends fourth information; or, the first terminal device receives fourth information. The fourth information is used to indicate configuration information for the data of the first terminal device.

[0047] Based on this possible design, the first device can flexibly obtain the configuration information of the first terminal device, thereby improving the applicability of this solution.

[0048] In one possible design, the configuration information of the data of the first terminal device includes one or more of the following: the content of the data of the first terminal device, the format of the data of the first terminal device, the reporting type of the data of the first terminal device, the reporting conditions of the data of the first model, and the reporting termination conditions of the data of the first terminal device.

[0049] Based on this possible design, the configuration information of the data of the first terminal device can correspond to different information for different communication scenarios, which improves the applicability of this solution.

[0050] Thirdly, this application provides a first device, which can be a first device or a chip or system-on-a-chip within the first device, or a functional module within the first device for implementing the first aspect or any possible design of the first aspect. This first device can implement the functions performed by the first device in the aforementioned first aspect or possible designs of the first aspect, and these functions can be implemented by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the aforementioned functions. For example, the first device may include a transceiver unit and a processing unit.

[0051] A transceiver unit is used to acquire data from a first terminal device; the data of the first terminal device is stored in a first device and allocated to a first resource; the first device includes the first resource.

[0052] The processing unit is used to train the first model based on the data from the first terminal device.

[0053] Specifically, the execution actions of each unit of the first device can be referred to in the first aspect or any possible design of the first aspect, and will not be repeated here.

[0054] Fourthly, this application provides a first terminal device, which can be a terminal device or a chip or system-on-a-chip in a terminal device, or a functional module in the first terminal device for implementing the second aspect or any possible design of the second aspect. The first terminal device can implement the functions performed by the first terminal device in the aforementioned second aspect or possible design of the second aspect, and these functions can be implemented by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the aforementioned functions. For example, the first terminal device may include a transceiver unit.

[0055] The transceiver unit is configured to receive data from the first device obtained based on the first model inference; and / or receive the first model from the first device; the first model is trained based on the data from the first terminal device; the data of the first terminal device is stored in the first device in the first resources allocated to the first terminal device.

[0056] Specifically, the execution actions of each unit of the first terminal device can be referred to in the second aspect or any possible design of the second aspect, and will not be repeated here.

[0057] Fifthly, this application provides a communication device, which can be the first device or the first terminal device described above. In one possible design, the communication device includes a processor. The processor is configured to support the communication device in executing the communication method described in the first aspect or any possible design of the first aspect, or the processor is configured to support the communication device in executing the communication method described in the second aspect or any possible design of the second aspect. In yet another possible design, the communication device may further include a memory for storing instructions and / or data. When the communication device is running, the processor executes the computer execution instructions stored in the memory to cause the communication device to execute the communication method described in the first aspect or any possible design of the first aspect, or to cause the communication device to execute the communication method described in the second aspect or any possible design of the second aspect.

[0058] Sixthly, this application provides a communication system, which includes a first device provided in the third aspect and a first terminal device provided in the fourth aspect.

[0059] In a seventh aspect, this application provides a computer-readable storage medium that stores computer instructions that, when executed on a computer, cause the computer to perform the communication method of the first aspect or any possible design of the first aspect; or cause the computer to perform the communication method of the second aspect or any possible design of the second aspect.

[0060] Eighthly, this application provides a computer program product comprising computer instructions that, when executed on a computer, cause the computer to perform the communication method of the first aspect or any possible design of the first aspect; or cause the computer to perform the communication method of the second aspect or any possible design of the second aspect. Attached Figure Description

[0061] Figure 1 is a schematic diagram of a terminal device acquiring an AI-CSI model;

[0062] Figure 2 is a schematic diagram of the process of a terminal device acquiring an AI-BM model in scenario A;

[0063] Figure 3a is a schematic diagram of the spatial relationship between SetA and SetB of network device configuration in scenario A.

[0064] Figure 3b is a schematic diagram of the spatial relationship between SetA and SetB of network device configuration in scenario B;

[0065] Figure 4a is a schematic diagram of the beam configuration of network devices in scenario C;

[0066] Figure 4b is a schematic diagram of the beam configuration of network devices in scenario D;

[0067] Figure 5 is a schematic diagram of a communication system provided in an embodiment of this application;

[0068] Figure 6 is a flowchart illustrating a communication method provided in an embodiment of this application;

[0069] Figure 7 is a flowchart illustrating a communication method provided in an embodiment of this application;

[0070] Figure 8 is a schematic diagram of the structure of a chip server provided in an embodiment of this application.

[0071] Figure 9 is a flowchart illustrating a communication method provided in an embodiment of this application;

[0072] Figure 10 is a schematic diagram of the path by which a chip server receives data from a first terminal of an access network device, according to an embodiment of this application.

[0073] Figure 11 is a schematic diagram of the structure of a first device provided in an embodiment of this application;

[0074] Figure 12 is a schematic diagram of the structure of a first terminal device provided in an embodiment of this application;

[0075] Figure 13 is a schematic diagram of the structure of a communication device provided in an embodiment of this application. Detailed Implementation

[0076] Before introducing the embodiments of this application, some technical terms involved in the embodiments of this application will be explained. It should be noted that the following explanations are for the purpose of making the embodiments of this application easier to understand, and should not be regarded as a limitation on the scope of protection claimed by the embodiments of this application.

[0077] In wireless communication research, with the introduction of 5G mobile communication systems and their evolutions, and the rapid development of various future communication networks, physical layer technologies will undoubtedly become increasingly complex. As the significant advantages of AI technologies based on machine learning (ML), deep learning (DL), and reinforcement learning (RL) in solving highly complex and difficult-to-model and solve problems are widely recognized, the academic and industrial communities have reached an increasingly clear consensus on using AI to solve complex physical layer problems in future wireless communication. AI is also being increasingly applied to the research and development of various air interface technologies.

[0078] As an example, taking the application of AI in channel state information (CSI) compression and reporting as an example, Figure 1 shows a schematic diagram of the process by which a terminal device obtains an AI-CSI model and uses the AI-CSI model to obtain inference data. As shown in Figure 1, this process includes:

[0079] S101: The terminal device measures and stores a large amount of CSI data.

[0080] CSI data can be used to assess and describe the characteristics of communication channels to help the sender (e.g., terminal device) and receiver (e.g., network device) make intelligent adjustments and decisions during communication.

[0081] S102: The terminal device trains the AI-CSI model based on CSI data.

[0082] The AI-CSI model is used to compress CSI data in order to send compressed CSI data to network devices.

[0083] The input data (or input label) of the AI-CSI model can be the original channel matrix or the feature vector after preprocessing the channel matrix, and the output data (or output label) can be the compressed CSI, which is usually a bit sequence with a value of 0 or 1.

[0084] S103: The terminal device sends data obtained based on AI-CSI model inference to the network device.

[0085] S104: The network device determines the precoding method based on the data obtained by inference based on the AI-CSI model.

[0086] Among them, the network equipment is equipped with an AI model for recovering data obtained from terminal devices based on AI-CSI model inference.

[0087] Specifically, the network device uses a configured AI model to recover the compressed CSI sent by the terminal device. Based on the recovered CSI, it selects a precoding method that conforms to the current channel environment and sends downlink data to the terminal device based on the selected precoding method. This enables the terminal device to more accurately parse the downlink data after receiving it, thereby improving throughput.

[0088] Another example, taking the application of AI in beam management, is illustrated in Figure 2, which shows a flowchart of a terminal device acquiring an AI-BM model in scenario A. The terminal device determines the optimal beam for transmitting data using the AI-BM model. The terminal device uses the optimal beam to transmit data, minimizing path loss. As shown in Figure 2, this method may include:

[0089] S201: The terminal device sends a request message to the network device.

[0090] The request message is used to request beam information from the network device. The beam information of the network device can be used to indicate the spatial relationship between the configured beam set SetA and beam set SetB of the network device, the beams contained in SetA, and the beams contained in SetB.

[0091] S202: In response to the request message, the network device sends a notification message to the terminal device, and the terminal device receives the notification message.

[0092] The notification message may include an ID identifier. The ID identifier is used to indicate the spatial relationship between SetA and SetB configured on the network device.

[0093] For example, Figure 3a is a schematic diagram of the spatial relationship between SetA and SetB of a network device configuration in scenario A. As shown in Figure 3a, the beams included in SetA of the network device configuration in scenario A are A′1-A′8, and the beams included in SetB are B′1-B′3.

[0094] S203: The network device sends the beams contained in SetA and SetB to the terminal device, and the terminal device receives the beams contained in SetA and SetB.

[0095] S204: The terminal device trains the AI-BM model corresponding to the ID identifier based on the beams contained in SetA and SetB.

[0096] Specifically, the terminal device measures the reference signal receiving power (RSRP) of the beam contained in SetA and the RSRP of the beam contained in SetB. The RSRP of the beam contained in SetB is used as the input variable of the AI-BM model, and the RSRP of the beam contained in SetA is used as the output variable to train the AI-BM model corresponding to the ID identifier.

[0097] The AI-BM model corresponding to the ID identifier can be used to predict the RSRP of the beams contained in SetA based on the RSRP of the beams contained in SetB, provided that the spatial relationship between SetA and SetB configured in the network device conforms to the ID identifier.

[0098] S205: The terminal device sends information to the network device that the AI-BM model corresponding to the ID identifier has completed training, and the network device receives the information that the AI-BM model corresponding to the ID identifier has completed training.

[0099] It should be understood that after receiving information that the AI-BM model corresponding to the ID identifier has been trained, the network device can instruct the terminal to transpose and activate the AI-BM model if the applicable scenario of the model is met, so that the terminal device can quickly activate the AI-BM model in the future.

[0100] S206: The network device sends the beam contained in SetB to the terminal device, and the terminal device receives the beam contained in SetB.

[0101] S207: The terminal device performs inference of the AI-BM model corresponding to the ID identifier based on the beam contained in the SetB.

[0102] Specifically, the terminal device measures the RSRP corresponding to the beams contained in the current SetB, uses it as the input variable of the AI-BM model corresponding to the ID identifier, and infers the RSRP corresponding to the beams contained in the current SetA. Furthermore, the beam corresponding to the maximum RSRP value is taken as the optimal beam in SetA, and the data is transmitted using the optimal beam.

[0103] Figure 3b shows a schematic diagram of the spatial relationship between SetA and SetB of the network devices configured in scenario B. Comparing Figures 3a and 3b, it can be seen that in scenario B, SetA contains beams A1-A8, and SetB contains beams B1-B3. The spatial relationship between SetA and SetB of the network devices configured in scenario A is different from that in scenario B, causing the AI-BM model trained by the terminal device in scenario A to be unsuitable for scenario B. Therefore, the terminal device needs to re-execute S201-S207 to obtain the AI-BM model in scenario B.

[0104] Another example is the application of AI to beam management. The beam configuration of the network device in scenario C is shown in Figure 4a, and the beam configuration of the network device in scenario D is shown in Figure 4b. Comparing Figures 4a and 4b, it can be seen that in both scenarios C and D, the beam numbers of SetA and SetB configured by the network device are 1-16, and SetB includes beams corresponding to numbers 1, 4, 7, and 10, while SetA includes beams corresponding to the remaining numbers. However, the positions and orientations of beams with the same number differ between scenarios C and D. For example, in scenario C, the beam corresponding to number 1 is horizontal and oriented to the left, but in scenario D, the beam corresponding to number 1 is not horizontal and is oriented to the lower left. Therefore, the AI-BM model trained based on beams 1, 4, 7, and 10 in scenario C is not applicable to scenario D. To obtain the AI-BM model for scenario D, the terminal device needs to re-execute steps S201-S207.

[0105] As the above analysis shows, due to differences in one or more of the beam shape, beam number, and beam order of network devices in different scenarios, the AI-BM model trained by the terminal device for beam management lacks generalization ability. Therefore, the terminal device needs to measure and store different training data for different communication scenarios, and train the AI-BM model based on different training data. This results in the terminal device needing to use a large amount of resources (e.g., computing power, energy consumption) to train a large number of AI-BM models for beam management.

[0106] As seen from the applications of AI in CSI and beam management, the application of AI in air interface technology requires terminal devices to perform operations related to acquiring AI models. These operations include acquiring the data needed to train the AI ​​model (e.g., training data and inference data), training the AI ​​model, inferring the AI ​​model, and updating the AI ​​model. This places high demands on the hardware configuration of the terminal device. For example, the measurement module needs to support the ability to measure large amounts of data to provide training and inference data for the AI ​​model; the processing module (e.g., modem) needs to support the ability to process large amounts of data to acquire the AI ​​inference model; and the power supply module needs to provide a large capacity of power to address the high energy consumption associated with measuring training and inference data, as well as the training and inference of the AI ​​model.

[0107] To reduce the energy consumption of terminal devices in AI scenarios, this application provides a communication method. The method includes: a first device acquiring data from a first terminal device and training a first model based on the data. The first device includes a first resource allocated to the first terminal device. The data acquired by the first device from the first terminal device is stored in the first resource. Correspondingly, the first terminal device receives the first model from the first device and / or data obtained through inference based on the first model. Thus, in AI scenarios, the first device acquires the data from the first terminal device to train the AI ​​model, eliminating the need for the first terminal device to expend significant resources training the AI ​​model, thereby reducing the energy consumption of the first terminal device. Simultaneously, the data of the first terminal device is stored in the first resource allocated to the first terminal device, improving the security of the data on the first terminal device.

[0108] The communication method provided in the embodiments of this application will be described below with reference to the accompanying drawings.

[0109] The technical methods of this application embodiment can be used in various communication systems in AI scenarios. These communication systems can be third-generation partnership project (3GPP) communication systems, such as long-term evolution (LTE) systems, fifth-generation (5G) mobile communication systems, new radio (NR) systems, vehicle-to-everything (NR V2X) systems, LTE and 5G hybrid networking systems, wireless fidelity (WiFi) systems, device-to-device (D2D) communication systems, machine-to-machine (M2M) communication systems, integrated access and backhaul (IBA) communication systems, Internet of Things (IoT) systems, and other future communication systems. They can also be non-3GPP communication systems, without limitation.

[0110] The technical solutions of this application can be applied to various communication scenarios, such as one or more of the following communication scenarios: enhanced mobile broadband (eMBB), ultra-reliable low latency communication (URLLC), machine type communication (MTC), massive machine type communications (mMTC), D2D, V2X, and IoT communication scenarios.

[0111] Figure 5 is a structural diagram of a communication system provided in an embodiment of this application. As shown in Figure 5, the communication system may include an AI node, a first terminal device, and a first equipment. The first equipment can provide services to the terminal device.

[0112] Optionally, the first device can be a server, which can be a single server or a server cluster consisting of multiple servers. In some embodiments, the server cluster can also be a distributed cluster. The server can provide services to the chip, and therefore can also be called a chip server. Alternatively, the first device can be a first network element in the core network. The first device can allocate dedicated resources to the terminal devices it serves, and can also load the trained or updated AI model into the chip of the terminal device in real time. Taking the allocation of dedicated resources by the first network element to the terminal device as an example, the first device can allocate dedicated first resources to the first terminal device.

[0113] It should be understood that the resources described in this application may include, but are not limited to, at least one of storage resources, computing resources, and network resources. The first resource may be used to perform one or more of the following: storing information of the first terminal device, processing related operations corresponding to the first terminal device. The size of the first resource may be predefined by the protocol, or determined by the first terminal device.

[0114] In this application, the information of the first terminal device may include, but is not limited to, the data of the first terminal device and the first model trained based on the data of the first terminal device. The allocation of dedicated first resources by the first device to the first terminal device can be understood as the first resource being dedicated to the first terminal device, and other terminal devices besides the first terminal device cannot use the first resource and / or the information stored in the first resource; or, the information stored in the first resource can be used not only by the first terminal device but also by other terminal devices besides the first terminal device, that is, the information stored in the first resource can be shared by multiple terminal devices including the first terminal device, or, it can be understood as the information stored in the first resource being allowed by the first terminal device to be used by other terminal devices.

[0115] Optionally, this application does not limit the number of terminal devices included in the communication system shown in FIG. 5. As shown in FIG. 5, the system may also include a second terminal device. In this case, the first device may also include a second resource allocated to the second terminal device. If the information stored in the first resource is dedicated to the first terminal device, the second terminal device cannot access the information stored in the first resource. If the information stored in the first resource is available to devices other than the first terminal device, the second terminal device can access the information stored in the first resource.

[0116] Optionally, the first device in Figure 5 may also include a third resource. The third resource is used to collect, store, and process public data in the first device. The third resource may also be used to send the first model to the first terminal device. The third resource may also be referred to as a public resource or a central node.

[0117] Optionally, the communication system shown in Figure 5 may include network devices. Network devices can be any type of device deployed in the access network capable of wirelessly communicating with terminal devices (e.g., a first terminal device, a second terminal device). They can also be chips or chip systems that can be configured in the aforementioned devices, logical nodes or logical modules, or functions implemented in software. They are primarily responsible for functions such as air interface-side wireless physical control, resource scheduling, wireless resource management, quality of service management, data compression and encryption, wireless access control, and mobility management. Specifically, network devices can be devices that support wired access or devices that support wireless access.

[0118] For example, a network device may consist of one or more access network (AN) / radio access network (RAN) nodes. AN / RAN nodes can be various types of base stations, such as: satellite base stations, evolved Node Bs (gNBs), transmission reception points (TRPs), evolved Node Bs (eNBs), radio network controllers (RNCs), Node Bs (NBs), base station controllers (BSCs), base transceiver stations (BTSs), home base stations (e.g., home evolved Node Bs, or home Node Bs (HNBs), macro base stations, micro base stations, pico base stations, small cells, relay stations, balloon stations, unmanned aerial vehicle (UAV) stations, wireless backhaul nodes, base band units (BBUs), or wireless fidelity (Wi-Fi) access points (APs), or grant nodes (G nodes) in satellite constellations, etc. It is understood that network equipment can be either ground-based or non-ground-based (such as satellites, drones, high-altitude communication equipment, etc.). Furthermore, the names of network equipment with base station functionality may differ in communication systems employing different wireless access technologies; this application does not impose any restrictions on this.

[0119] In another example, the network equipment may include a BBU and a remote radio unit (RRU). The BBU and RRU can be located in different places; for example, the RRU can be moved remotely to a high-traffic area, while the BBU is located in the central equipment room. The BBU and RRU can also be located in the same equipment room. The BBU and RRU can also be different components under the same rack.

[0120] In another example, the network device can be a device that includes centralized unit (CU) nodes, distributed unit (DU) nodes, or both CU and DU nodes. For instance, the network device can be logically divided into CUs and DUs, with some protocol layer functions centrally controlled by the CU, and the remaining partial or complete protocol layer functions distributed in the DU, which is centrally controlled by the CU. The CU and DU can be separate entities or included in the same network element, such as a BBU. Furthermore, the centralized unit (CU) can be further divided into a control plane (CU-CP) and a user plane (CU-UP).

[0121] In another example, the network device may also be a device that includes a radio unit (RU), or a device that includes a CU, a DU, and a RU. The RU may be included in a radio frequency device or radio frequency unit, such as an RRU, an active antenna unit (AAU), or a remote radio head (RRH).

[0122] It is understood that CU (or CU-CP and CU-UP), DU, or RU may have different names in different systems, but those skilled in the art will understand their meaning. For example, in an open radio access network (O-RAN) system, CU can also be called O-CU (open CU), DU can also be called O-DU, CU-CP can also be called O-CU-CP, CU-UP can also be called O-CU-UP, and RU can also be called O-RU. For ease of description, this application uses CU, CU-CP, CU-UP, DU, and RU as examples. Any of the units among CU (or CU-CP, CU-UP), DU, and RU in this application can be implemented through software modules, hardware modules, or a combination of software modules and hardware modules.

[0123] Optionally, the network device in Figure 5 can also be a core network device or a functional module / chip in a core network device, such as the access and mobility management function (AMF) or a functional module / chip in the AMF, which is responsible for the central point of most control plane function interactions and is mainly used for various functions related to registration management, connection management, access management, mobility management, security and access management, and authorization.

[0124] The first terminal device in Figure 5 can be a device with wireless transceiver capabilities or a chip or chip system that can be installed in the device. It allows users to access the network and is used to provide voice and / or data connectivity to users. The first terminal device can also be referred to as a first terminal equipment, user equipment (UE), subscriber unit, terminal, mobile station (MS), or mobile terminal (MT), etc.

[0125] For example, the first terminal device may be a mobile phone, a tablet computer, or a computer with wireless transceiver capabilities. The first terminal device can also be a user station, mobile station, remote station, remote terminal equipment, mobile terminal equipment, user terminal equipment, wireless communication equipment, user agent, user equipment, cellular phone, cordless phone, session initiation protocol (SIP) phone, wireless local loop (WLL) station, personal digital assistant (PDA), handheld device with wireless communication capabilities, computing device, processing device connected to a wireless modem, in-vehicle equipment, wearable device, terminal device in the Internet of Things (IoT), home appliance, virtual reality (VR) terminal, augmented reality (AR) terminal, wireless terminal in industrial control, wireless terminal in autonomous driving, wireless terminal in telemedicine, wireless terminal in smart grid, wireless terminal in smart city, wireless terminal in smart home, vehicle with vehicle-to-vehicle (V2V) communication capability, intelligent connected vehicle, or UAV-to-UAV communication. Unrestricted applications include unmanned aerial vehicles (UAVs) with U2U communication capabilities, terminal devices in future networks, terminal devices in future evolved public land mobile networks (PLMNs), Wi-Fi stations (STAs), or terminal nodes (T-nodes) in satellite navigation. It is understood that the first terminal device and the mobile user can be completely independent. All user-related information can be stored in a subscriber identity module (SIM) card, which can be used on the terminal device. The first terminal device can interact with network-side equipment by transmitting and / or receiving signals over the air interface.

[0126] In Figure 5, the AI ​​node is used to support the use of AI technology in AI scenarios.

[0127] Optionally, the AI ​​node can be deployed in one or more of the following locations in the communication system shown in Figure 5: network equipment, first terminal device, second terminal device, first device, etc. Alternatively, the AI ​​node can be deployed independently, for example, in a location other than any of the above-mentioned devices, such as in the host or cloud server of an over-the-top (OTT) system.

[0128] It is understood that this application does not limit the number of AI nodes. For example, when there are multiple AI nodes, these nodes can be divided based on function, such as different AI nodes being responsible for different functions.

[0129] It can also be understood that AI nodes can be independent devices, or they can be integrated into the same device to achieve different functions. Alternatively, they can be network elements in hardware devices, software functions running on dedicated hardware, or virtualization functions instantiated on a platform (e.g., a cloud platform). This application does not limit the specific form of the aforementioned AI nodes.

[0130] AI nodes can be AI network elements or AI modules.

[0131] It is understood that Figure 5 above is merely a schematic diagram and does not constitute a limitation on the applicable scenarios of the technical solutions provided in this application. Those skilled in the art should understand that in specific implementation processes, the communication system shown in Figure 5 may include fewer devices than those shown in Figure 5, or the communication system shown in Figure 5 may also include other devices. At the same time, the number of devices in the communication system shown in Figure 5 can be determined according to specific needs and is not limited.

[0132] Optionally, the devices in Figure 5, such as the first device, the first terminal device, the network device, and the second terminal device, can also be referred to as communication devices. They can be general-purpose devices or special-purpose devices. This application embodiment does not specifically limit them in this regard.

[0133] Optionally, the functions of each device in Figure 5 of this application can be implemented by one device, multiple devices working together, or one or more functional modules within a single device. This application does not specifically limit these functions. It is understood that the aforementioned functions can be network elements in hardware devices, software functions running on dedicated hardware, a combination of hardware and software, or virtualization functions instantiated on a platform (e.g., a cloud platform).

[0134] The communication method provided in the embodiments of this application will be described below with reference to the communication system shown in Figure 5. The actions, terms and other information involved in the following embodiments can be referred to each other. The message names or parameter names in the messages between devices in each embodiment are just examples, and other names can be used in specific implementations. For example, "corresponding" in the following embodiments can be replaced by "associating", etc., and "sending" in the following embodiments can be replaced by "transmitting", etc.

[0135] Figure 6 is a flowchart illustrating a communication method provided in an embodiment of this application. As shown in Figure 6, it may include:

[0136] S601: The first device acquires data from the first terminal device.

[0137] The first device can be the first device in Figure 5, and the first terminal device can be the first terminal device in Figure 5. The descriptions of the first device and the first terminal device in Figure 5 can be found in the above descriptions and will not be repeated here.

[0138] The first device may include a first resource. The first resource is the resource allocated to the first terminal device within the first device.

[0139] In this application, the first resource can be used to perform one or more of the following: storing information of the first terminal device (e.g., data of the first terminal device, a first model trained based on the data of the first terminal device (e.g., an AI model), data obtained by inference from the first model, etc.), processing related operations corresponding to the first terminal device, such as training the first model based on the data of the first terminal device, inferring the first model based on the data of the first terminal device, updating the first model corresponding to the first terminal device, etc.

[0140] In one example, the size and / or data access permissions of the first resource in this application can be predefined by the protocol (as specified by the standard). For example, the first device can be the factory configuration of the first terminal device, in which case the size and / or data access permissions of the first resource have already been set at the factory of the first terminal device. Alternatively, when a user of the first terminal device purchases the first terminal device, the size and / or data access permissions of the first resource can be determined through the "purchase agreement," and the size and / or data access permissions of the first resource can be loaded onto the first device according to the agreement. Alternatively, when the first terminal device accesses a wireless network, the first device sets the size and data access permissions of the first resource in accordance with the predefined protocol or standard specifications.

[0141] In another example, the size and / or data access permissions of the first resource can be determined by the first terminal device. For instance, the first terminal device may be configured with an application (APP) corresponding to the first resource, and a user of the first terminal device can configure the size and / or data access permissions of the first resource through the APP. The first terminal device determines the size and / or data access permissions of the first resource in response to the user's configuration operation.

[0142] In this application, the data access permission of the first resource can be used to indicate that the information stored in the first resource is dedicated to the first terminal device, or it can be used to indicate that the information stored in the first resource is available to devices other than the first terminal device.

[0143] When the data access permission instruction of the first resource indicates that "the information stored in the first resource is available to devices other than the first terminal device", the first device may send a permission request to the first terminal device to request sharing the information stored in the first resource. If the first device receives a response message from the first terminal device indicating that sharing the information stored in the first resource is permitted, then the first device may share the information stored in the first resource with devices other than the first device. If the first device does not receive a response message from the first terminal device, then the first device may not share the information stored in the first resource with devices other than the first device.

[0144] Thus, if the information stored in the first resource is available to devices other than the first terminal device, then if a device other than the first terminal device obtains the information stored in the first resource, the permission of the user of the first terminal device is required, thereby improving the data security of the first terminal device.

[0145] In S601, the first device acquiring data from the first terminal device may include receiving data from the first terminal device of the network device, and / or receiving data from the first terminal device of the first terminal device.

[0146] In this application, the data of the first terminal device may include, but is not limited to, one or more of the following: data measured by a chip in the first terminal device, data measured by sensors in the first terminal device, application data of the first terminal device, location data of the first terminal device, data about the first terminal device measured or stored by a network device, and data about the first terminal device measured or stored by other devices. Other devices are not deployed in the first terminal device and the network device. For example, other devices may be positioning modules.

[0147] The data from the first terminal device of the network device may include, but is not limited to, one or more of the following: data received by the network device from the first terminal device, data generated by the network device from the first terminal device, data stored by the network device from the first terminal device, data received by the network device from a device other than the first terminal device from the first terminal device, and data received by the network device from a device other than the first terminal device from the first terminal device stored by the first terminal device. In this application, the device other than the first terminal device may be a positioning module, which is not deployed in the first terminal device or the network device, and can be used to provide location data for the first terminal device.

[0148] S602: The first device trains the first model based on the data from the first terminal device.

[0149] The first model can include AI models that need to be trained in the AI ​​scenario. For example, AI-CSI model and AI-BM model.

[0150] The first device trains a first model based on data from the first terminal device, which may include: the first resource in the first device trains the first model based on data from the first terminal device.

[0151] S603: The first device sends the second information to the first terminal device, and the first terminal device receives the second information.

[0152] In this application, the second information is used to indicate information about the first model, which may include one or more of the following: the applicable scenario of the first model, whether the first model has been trained or updated, the performance of the first model, the identifier of the first model, and the type of the first model.

[0153] The applicable scenarios for the first model may include one or more of the following: communication environment information to which the first model applies (e.g., channel conditions), terminal device information to which the first model applies (e.g., battery level, power consumption, storage capacity, or motion trends of the terminal device), and network device information to which the first model applies (e.g., network device configuration).

[0154] The second piece of information is that the first model has been trained or updated. This allows the first device to notify the first terminal device or network device that the first model has been trained or updated when the first device has completed the training or update of the first model. This enables the first terminal or network device to obtain the first model when it needs to use the first model.

[0155] In this application, updating the first model by the first device can include: the first device updating the first model triggered by a specific event, or the first device updating the first model proactively. For example, a network device or terminal device determines that the first model needs to be updated and sends a request message to the first device to request the first device to update the first model, thus achieving a triggered update of the first model. Alternatively, the first device may update the first model periodically, thus achieving a proactive update of the first model; or, the terminal device or network device may periodically send the performance data of the first model to the first device, and if the performance data of the first model is less than a preset threshold, the first device proactively updates the first model.

[0156] The performance of the first model can indicate the accuracy achievable by the first model, or it can indicate the system performance after using the first model. This application does not limit the performance metrics of the first model.

[0157] For example, the performance of the first model indicates the accuracy it can achieve. In scenarios where the first model is used for channel recovery, its performance can be measured by the accuracy of channel recovery; the higher the accuracy, the higher the accuracy achieved by the first model. In scenarios where the first model is used for location determination, its performance can be measured by the location error value; the lower the location error value, the higher the accuracy achieved by the first model.

[0158] For example, the performance of the first model indicates the system's performance after using the first model. The performance metrics for the first model can be the system's throughput or bit error rate after using it. Throughput reflects the amount of information the system can process per unit of time. The higher the throughput, the better the performance of the first model. The bit error rate reflects the accuracy of data transmission within a specified time. The lower the bit error rate, the better the performance of the first model.

[0159] The identifier for the first model can be used to identify the first model. This application does not limit the content of the identifier for the first model.

[0160] For example, if the mapping relationship between the first model and numbers is pre-configured or specified by the protocol, the identifier of the first model can be a number, and the first model can be determined through the number and the mapping relationship between the first model and the number.

[0161] For example, if the mapping relationship between the first model and the bit sequence is pre-configured or specified by the protocol, the identifier of the first model can be a bit sequence. The first model can be determined by the bit sequence and the mapping relationship between the first model and the bit sequence.

[0162] In this application, the identifier of the first model may also be assigned by the first terminal device or network device.

[0163] In this application, there is no restriction on the timing of assigning the identifier of the first model.

[0164] For example, if the identifier of the first model is assigned by the first terminal device or network device, the first terminal device or network device sends a first request message to the first device. The first request message is used to request training or updating of the first model. If the first request message includes the identifier of the first model, the identifier of the first model can be assigned by the first terminal device or network device before sending the first request message. If the first request message does not include the identifier of the first model, the identifier of the first model can be assigned by the first terminal device or network device after receiving the first model from the first device.

[0165] For example, if the identifier of the first model is assigned by the first device, the first device receives a request message from a first terminal device or network device. The request message requests training or updating of the first model. In response to the request message, the first device trains or updates the first model and assigns an identifier to the first model. Alternatively, after training or updating the first model, the first device assigns an identifier to the first model and includes the identifier in the aforementioned second information.

[0166] The type of the first model can indicate the air interface technology applied to the first model. For example, the type of the first model may include one of the following: beam management, CSI, positioning, or mobility enhancement.

[0167] When the first device updates the first model, it does not need to reacquire the data from the first terminal. For example, if the first device optimizes the first model (e.g., adds a hidden layer to the first model to improve its performance), the data from the first terminal required to update the first model remains unchanged, and in this case, it is not necessary to reacquire the data from the first terminal.

[0168] S603 is an optional execution step. If the first terminal device has not obtained information about the first model, S603 is executed, allowing the first terminal device to subsequently obtain the first model in a scenario applicable to it. If the first terminal device has already determined the information about the first model, S603 is not executed.

[0169] S604: The first device sends the first model and / or data obtained by reasoning based on the first model, and the first terminal device receives the first model and / or data obtained by reasoning based on the first model from the first device.

[0170] The first device sending the first model and / or data inferred based on the first model may include: the first device sending the first model and / or data inferred based on the first model to a network device, the first device sending the first model and / or data inferred based on the first model to a first terminal device, and the first device sending the first model and / or data inferred based on the first model to other devices.

[0171] In this application, other devices may include devices other than network devices and the first terminal device, such as a second terminal device. These other devices are not deployed in the first terminal device and the network devices.

[0172] The first terminal device receiving a first model and / or data inferred from the first device may include: the first terminal device receiving a first model and / or data inferred from the first device; or the first terminal device receiving data forwarded from the first device by devices other than the first terminal device, which is also derived from the first model and / or data inferred from the first device. Devices other than the first terminal device may include network devices or other devices.

[0173] S604 is an optional execution step. It is executed when the first device needs to send the first model and / or data inferred from the first model. For example, the first device receives first information requesting the acquisition of the first model and / or data inferred from the first model; in response to the first information, the first device sends the first model and / or data inferred from the first model. If the first device does not need to send the first model and / or data inferred from the first model, S604 is not executed.

[0174] This application does not limit the manner in which the first device sends the first model and / or data inferred based on the first model. For example, the first device may periodically send the first model and / or data inferred based on the first model. Alternatively, the first device may trigger the sending of the first model and / or data inferred based on the first model.

[0175] Based on the communication method shown in Figure 6, the first terminal device no longer needs to expend significant resources training the first model (e.g., an AI model), thus reducing the power consumption of the first terminal device. Simultaneously, the data of the first terminal device is stored in the first resources allocated to the terminal device within the first device, enhancing the data security of the first terminal device.

[0176] Optionally, before the first device acquires data from the first terminal device, it may send configuration information for the first terminal device's data to instruct the first terminal device to send its data according to the configuration information. In this case, the communication method shown in Figure 6 may further include:

[0177] S600: The first device sends the fourth information to the first terminal device, and the first terminal device receives the fourth information.

[0178] The fourth piece of information is used to indicate the configuration information of the data of the first terminal device.

[0179] In this application, the configuration information of the data of the first terminal device may include one or more of the following: the content of the data of the first terminal device, the format of the data of the first terminal device, the reporting type of the data of the first terminal device, the reporting conditions of the data of the first model, and the reporting termination conditions of the data of the first terminal device.

[0180] The content of the data from the first terminal device can indicate the specific content of the data. For example, when the first model is the AI-CSI model, the content of the data from the first terminal device may include one or more of the following: CSI, the terminal's motion speed. When the first model is the AI-BM model, the content of the data from the first terminal device may include one or more of the following: reference signal receiving power (RSRP), spatial information identifier of the beam, beamwidth of any beam in Set A, beamwidth of any beam in Set B, the number corresponding to any beam in Set A, the beam number corresponding to any beam in Set B, the orientation of any beam in Set A, and the orientation of any beam in Set B.

[0181] The format of the data from the first terminal device can indicate the specific format of the data. For example, if the first model is an AI-CSI model, the data from the first terminal device is CSI, and the format of the data from the first terminal device can be a channel matrix or an eigenvector.

[0182] The data reporting type of the first terminal device can be used to indicate that the data of the first terminal device is reported periodically, or it can indicate that the data of the first terminal device is reported event-triggered.

[0183] The data reporting conditions of the first terminal device may include a periodic value if the reporting type of the first terminal device indicates that the data of the first terminal device is periodically reported; and may include triggering a reporting event of the first terminal device if the reporting type of the first terminal device indicates that the data of the first terminal device is event-triggered reporting.

[0184] The data reporting termination condition of the first terminal device may include the termination condition of the event if the reporting type of the first terminal device indicates that the data of the first terminal device is an event-triggered report.

[0185] The following discussion, using the communication system shown in Figure 5, which includes a first device, a first terminal device, and a second terminal device, takes the direct communication between the first device and the first terminal device as an example. Here, the first device is a chip server, the first terminal device is the first terminal, and the second terminal device is the second terminal. The communication method shown in Figure 6 will now be described in conjunction with Figure 7.

[0186] Figure 7 is a flowchart illustrating a communication method provided in an embodiment of this application. As shown in Figure 7, the method may include:

[0187] S701: The first terminal sends a first request message to the chip server, and the chip server receives the first request message.

[0188] The chip server may include a first resource, a second resource, and a third resource. The first resource is the resource allocated to the first terminal in the chip server. The second resource is the resource allocated to the second terminal in the chip server. The third resource is the resource in the chip server used for collecting, storing, and processing public data. A schematic diagram of the chip server structure is shown in Figure 8.

[0189] In this application, the chip server serves the terminal device, and the chip server may have one or more of the following characteristics: allocating dedicated resources to the terminal device it serves, loading the trained or updated AI model into the chip of the terminal device it serves in real time, using the chip to execute the inference of the AI ​​model, and acquiring the data of the terminal device it serves in real time.

[0190] The first request message is used to request training or updating of the first model. Sending the first request message from the first terminal to the chip server can include: the first terminal sending the first request message to the chip server when it needs to train or update the first model. For example, if the first terminal detects that there is no AI model suitable for the current scenario locally, it sends the first request message to the chip server to request the chip server to train an AI model suitable for the current scenario. Another example is if, based on model monitoring results, the first terminal determines that the performance of the local AI model suitable for the current scenario is no longer higher than a preset threshold, it sends the first request message to the chip server to request the chip server to update the AI ​​model suitable for the current scenario, so that the performance of the AI ​​model is higher than the preset threshold.

[0191] Model monitoring can be used to determine model management strategies. For example, based on model monitoring results, it can determine whether to perform any of the following operations: train the model, update the model, activate the model, deactivate the model, infer the model, or switch the model.

[0192] This application does not restrict the path through which the first terminal sends the first request message to the chip server. For example, the first terminal can send the first request message directly to the chip server, or it can send it indirectly. For instance, the user plane (UP) of the first terminal sends the first request message to the chip server. Alternatively, the control plane (CP) of the first terminal sends the first request message to the CP or UP of the network device, which then forwards the first request message to the chip server.

[0193] Optionally, the first request message may include an identifier for the first model. The identifier for the first model is described above and will not be repeated here.

[0194] S702: The first terminal sends third information to the chip server, and the chip server receives the third information.

[0195] The third piece of information is used to instruct the first device to obtain data from the first terminal.

[0196] This application does not restrict the path through which the first terminal sends third information to the chip server. For example, the first terminal can send third information directly to the chip server, or the first terminal can send third information indirectly to the chip server.

[0197] S703: The first terminal sends the fourth information to the chip server, and the chip server receives the fourth information.

[0198] The fourth piece of information is described in S600 and will not be repeated here.

[0199] S703 is an optional execution step. S703 is executed when the configuration information of the data of the first terminal is determined by the first terminal; S703 is not executed when the configuration information of the data of the first terminal is determined by a device other than the first terminal.

[0200] S704: The first terminal sends data from the first terminal to the chip server, and the chip server receives the data from the first terminal.

[0201] It should be understood that the first terminal is an example of a first terminal device, and therefore the data of the first terminal can be referred to the data-related description of the first terminal device in S601, which will not be repeated here.

[0202] It should be understood that when the first terminal executes S703, the first terminal can send the data of the first terminal according to the configuration information of the first terminal's data in the fourth information.

[0203] S705: The chip server sends a license request to the first terminal, and the first terminal receives the license request.

[0204] The permission request is used to request the sharing of information stored in the first resource.

[0205] The process of the chip server sending a license request to the first terminal may include: the second resource needs to obtain information stored in the first resource, triggering the chip server to send a license request to the first terminal.

[0206] It should be understood that the second resource needs to obtain the information stored in the first resource, and can also trigger the chip server to send a license request to the second terminal. In this case, S705 can be alternatively described as: the chip server sends a license request to the second terminal, the second terminal receives the license request, and sends a license request to the first terminal.

[0207] It should be understood that the prerequisite for the chip server to execute S705 may include that the information stored in the first resource is available to devices other than the first terminal.

[0208] S706: In response to the license request, the first terminal sends a response message to the chip server, and the chip server receives the response message.

[0209] The response message is used to indicate permission to share information stored in the first resource.

[0210] S707: The chip server shares the information stored in the first resource.

[0211] The information stored in the first resource shared by the chip server may include: in response to a response message, the first resource sharing the information stored in the first resource with the second resource.

[0212] This application does not restrict the path through which the first resource shares the information stored in the first resource with the second resource. For example, the first resource can directly share the information stored in the first resource with the second resource, or the first resource can share the information stored in the first resource with the third resource, and the third resource can then share the information stored in the first resource.

[0213] In one possible design, where data interaction between resources in a pre-configured or protocol-predefined chip server is impossible, the chip server shares information stored in a first resource. This could include: in response to a response message, the chip server shares the information stored in the first resource with a first terminal; the first terminal then sends the information stored in the first resource to a second terminal; further, the second terminal sends the information stored in the first resource to the chip server, enabling the second resource to access the information stored in the first resource. The second resource is the resource allocated to the second terminal within the chip server.

[0214] It should be understood that S705-S707 are optional execution steps. S705-S707 are executed when the second resource in the chip server needs to obtain the information stored in the first resource; S705-S707 are not executed when the second resource in the chip server does not need to obtain the information stored in the first resource, or when the second terminal is pre-configured (predefined by the protocol) to share the data of the first terminal.

[0215] S708: The chip server trains the first model based on the data from the first terminal.

[0216] The first model can be referred to in the relevant description in S602, and will not be repeated here.

[0217] The chip server trains a first model based on the data from the first terminal, which may include: the first resource in the chip server trains the first model based on the data from the first terminal.

[0218] S709: The chip server sends the second information to the first terminal, and the first terminal receives the second information.

[0219] The second piece of information can be found in the relevant description in S603, and will not be repeated here.

[0220] S710: The first terminal sends a second request message to the chip server, and the chip server receives the second request message.

[0221] The second request message can be used to request the sending of the first model or data obtained by reasoning based on the first model.

[0222] The first terminal sends a second request message to the chip server, which may include: the first terminal sensing that the currently required AI model matches the information of the first model in the second information, and sending the second request message to the chip server. For example, the first terminal senses that the AI ​​model currently needed for positioning, and the second information in S709 indicates that the type of the first model is positioning accuracy, the first terminal senses that the required AI model for positioning matches the type of the first model in the second information, and sends the second request message to the chip server.

[0223] S711: The chip server sends the first model or data obtained by inference based on the first model to the first terminal, and the first terminal receives the first model or data obtained by inference based on the first model.

[0224] If the chip server in S711 sends data obtained from inference based on the first model to the first terminal, after the chip server completes the training of the first model, it still needs to perform inference based on the data of the first terminal and the first model in order to send the data obtained from inference based on the first model to the first terminal.

[0225] If the chip server in S711 sends the first model to the first terminal, the first terminal executes step S712.

[0226] S712: The first terminal performs inference based on the first model.

[0227] The first terminal, based on the first model, performs inference based on the first model, which may include: the first terminal performing inference based on the data of the first terminal and the first model to obtain data obtained by inference based on the first model.

[0228] It should be noted that steps S705-S707 and S708 described above are merely illustrative descriptions of the communication method shown in Figure 7. The execution order of steps S705-S707 and S708 is not limited. For example, steps S705-S707 may be executed before step S708; or steps S705-S707 may be executed after step S708; or steps S705-S707 may be executed simultaneously with step S708.

[0229] Based on the method shown in Figure 7, the first terminal and the chip server can communicate directly, and the chip server possesses one or more of the following characteristics: allocating dedicated resources (e.g., first resources) to the first terminal; loading the trained or updated first model (e.g., an AI model) into the chip of the first terminal in real time; and acquiring data from the first terminal in real time. This allows the chip server to acquire data from the first terminal in real time while ensuring the data security of the first terminal. Simultaneously, the chip server trains the first model based on the data from the first terminal, eliminating the need for the first terminal to consume significant resources for training the first model and reducing the energy consumption of the first terminal.

[0230] The following example illustrates the communication system shown in Figure 5, which includes a first device, a first terminal device, a second terminal device, and network equipment. The network equipment comprises access network equipment and core network equipment, and the first device can directly communicate with the access network equipment within the network equipment. Here, the first device is a chip server, the first terminal device is a first terminal, and the second terminal device is a second terminal. The communication method shown in Figure 6 will now be described in conjunction with Figure 9.

[0231] Figure 9 is a flowchart illustrating a communication method provided in an embodiment of this application. As shown in Figure 9, the method may include:

[0232] S901: The access network device sends a first request message to the chip server, and the chip server receives the first request message.

[0233] The chip server and the first request message can be found in the relevant description in S701, and will not be repeated here.

[0234] The sending of a first request message from the access network device to the chip server may include: the access network device sending a first request message to the chip server when it needs to train or update a first model. This application does not limit the path through which the access network device sends the first request message to the chip server. For example, the access network device (e.g., the CP of the access network device, the UP of the access network device) may directly send the first request message to the chip server, or the access network device may indirectly send the first request message to the chip server. In this application, the path through which the access network device indirectly sends any information (e.g., a first request message, third information, fourth information, or a second request message) to the chip server may include any of the following: the CP of the access network device sends any information to the UP of the first terminal, and the UP of the first terminal sends any information to the chip server. Or, the access network device sends any information to the core network device, and the core network device sends any information to the chip server. Or, the CP of the access network device sends any information to the CoP of the first terminal, and the UP or CoP of the access network device sends any information to the chip server. CoP (container) is a data transmission method of CP. It only defines the CP plane signaling used for data transmission and does not define the data transmission format. The first terminal and chip server can parse its content, but network devices do not parse its content.

[0235] S902: The access network device sends third information to the chip server, and the chip server receives the third information.

[0236] The third piece of information can be found in the relevant description in S702, and will not be repeated here.

[0237] This application does not restrict the path through which the access network device sends third information to the chip server. For example, the access network device (e.g., the CP of the access network device, the UP of the access network device) can send third information directly to the chip server, or the access network device can send third information indirectly to the chip server.

[0238] S903: The access network device sends the fourth information to the chip server, and the chip server receives the fourth information.

[0239] The fourth piece of information is described in S600 and will not be repeated here.

[0240] S903 is an optional execution step. S903 is executed when the configuration information of the first terminal's data is determined by the access network device; S903 is not executed when the configuration information of the first terminal's data is determined by a device other than the access network device.

[0241] S904: The access network device sends data from the first terminal to the chip server, and the chip server receives the data from the first terminal of the access network device.

[0242] It should be understood that the access network device is an example of a network device, and the first terminal is an example of a first terminal device. Therefore, the data from the first terminal of the access network device can be referred to the relevant description of the data from the first terminal device of the network device in S601, which will not be repeated here.

[0243] For example, Figure 10 is a schematic diagram of the path through which a chip server receives data from a first terminal of an access network device. As shown in Figure 10, the network device includes an access network device and a core network device. The access network device provides services to a first terminal and a second terminal, and the core network device provides services to the access network device. The chip server includes a first resource and a second resource. The first resource is the resource allocated in the chip server for the first terminal, and the second resource is the resource allocated in the chip server for the second terminal. The chip server can receive data from the first terminal of the access network device via any of the following paths:

[0244] (1) If the data from the first terminal of the access network device is the data sent from the first terminal of the access network device to the first terminal of the access network device, then the path for the chip server to receive the data from the first terminal of the access network device can be path A, which includes: first terminal -> access network device -> chip server.

[0245] (2) If the data from the first terminal of the access network device is the data of the first terminal stored in the access network device, then the path for the chip server to receive the data from the first terminal of the access network device can be path B, which includes: access network device -> chip server.

[0246] (3) If the data from the first terminal of the access network device is the data configured for the first terminal of the access network device, and the data is the data required by the core network device, then the path for the chip server to receive the data from the first terminal of the access network device can be path C, which includes: access network device -> core network device -> chip server.

[0247] (4) If the data from the first terminal of the access network device is the data measured by the second terminal of the first terminal, and there is no direct path between the second terminal and the chip server, then the path for the chip server to receive the data from the first terminal of the access network device can be path D, which includes: second terminal -> access network device -> chip server. It should be understood that when the access network device executes S903, the access network device can send the data of the first terminal according to the configuration information of the first terminal's data in the fourth information.

[0248] S905: The chip server sends a license request to the first terminal, and the first terminal receives the license request.

[0249] The license request and the chip server sending the license request to the first terminal are described in S705 and will not be repeated here.

[0250] This application does not limit the path for transmitting information (e.g., license requests, response messages) between the chip server and the first terminal. For example, the chip server can transmit information to the first terminal directly or indirectly. For example, if the chip server and the first terminal can communicate directly, the chip server can directly send a license request to the first terminal. For example, if the chip server and network devices can communicate directly, the chip server can send a license request to the first terminal via core network devices and access network devices.

[0251] S906: In response to the license request, the first terminal sends a response message to the chip server, and the chip server receives the response message.

[0252] The response message is used to indicate permission to share information stored in the first resource.

[0253] S907: The chip server shares the information stored in the first resource.

[0254] The relevant descriptions in S907 can be found in the relevant descriptions in S707, and will not be repeated here.

[0255] S908: The chip server trains the first model based on the data from the first terminal.

[0256] The first model can be referred to in the relevant description in S602, and will not be repeated here.

[0257] The chip server trains a first model based on data from the first terminal, which may include: the first resource in the chip server trains the first model based on data from the first terminal of the access network device.

[0258] S909: The access network device sends a second request message to the chip server, and the chip server receives the second request message.

[0259] The second request message can be used to request the sending of the first model or data obtained by reasoning based on the first model.

[0260] S910: The chip server sends the second information to the access network device, and the access network device receives the second information.

[0261] The second piece of information can be found in the relevant description in S603, and will not be repeated here.

[0262] The sending of second information by the chip server to the access network device can include: the chip server sending the second information directly to the access network device, or the chip server sending the second information indirectly to the access network device. For example, the chip server sends the second information to the access network device via the core network device.

[0263] S911: The chip server sends the first model to the access network device, and the access network device receives the first model.

[0264] The process of the chip server sending the first model to the access network device can include: the chip server sending the first model directly to the access network device, or the chip server sending the first model indirectly to the access network device. For example, the chip server sends the first model to the access network device via the core network device.

[0265] The process of the access network device receiving the first model may include: the access network device receiving the first model and storing it locally. This allows the first terminal to obtain the first model through the access network device.

[0266] S912: The access network device sends an instruction message to the first terminal, and the first terminal receives the instruction message.

[0267] The instruction information can be used to instruct the activation of the first model. The instruction information may include one or more of the following: the applicable scenario of the first model, the performance of the first model, the identifier of the first model, and the type of the first model.

[0268] The process of the access network device sending instruction information to the first terminal may include: the access network device sensing that the AI ​​model currently required by the first terminal matches the information of the first model in the second information, and sending instruction information to the first terminal.

[0269] S913: The first terminal sends a model request message to the access network device, and the access network device receives the model request message.

[0270] The model request message can be used to request the sending of the first model or data obtained by inference based on the first model.

[0271] S914: The access network device sends a first model and / or data inferred based on the first model to the first terminal, and the first terminal receives the first model and / or data inferred based on the first model.

[0272] S915: The first terminal performs inference based on the first model.

[0273] The relevant descriptions of S914-S915 can be found in the relevant descriptions of S711-S712, and will not be repeated here.

[0274] Based on the method shown in Figure 9, the network device and the chip server can communicate directly. When the chip server needs to obtain data from the first terminal of the network device, or when the network device also needs to obtain the data obtained by the chip server from the first terminal, the chip server can directly obtain the data from the network device, avoiding the first terminal from repeatedly sending the data and reducing the energy consumption of the first terminal. Simultaneously, the introduction of the chip server allows the chip server to train the first model based on the data from the first terminal, while ensuring the data security of the first terminal. This eliminates the need for the first terminal to consume significant resources for training the first model, further reducing the energy consumption of the first terminal.

[0275] The foregoing mainly describes the solutions provided by the embodiments of this application from the perspective of interaction between various devices. It is understood that each device, such as the first device and the first terminal device, includes corresponding hardware structures and / or software modules to perform the aforementioned functions. Those skilled in the art should readily recognize that, in conjunction with the algorithm steps of the examples described in the embodiments disclosed herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed by hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0276] This application embodiment can group the first device, first terminal device, etc., into functional modules according to the above method example. For example, each functional group can correspond to a functional module, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware or as a software functional module. It should be noted that the grouping of modules in this application embodiment is illustrative and only represents one logical functional grouping. In actual implementation, there may be other grouping methods.

[0277] Figure 11 shows a structural diagram of a first device 1100, which can be used to perform the functions of the first device involved in the above embodiments. As one possible implementation, the first device 1100 shown in Figure 11 includes: a transceiver unit 1101 and a processing unit 1102;

[0278] The transceiver unit 1101 is used to acquire data from the first terminal device; the data of the first terminal device is stored in a first device and allocated to a first resource; the first device includes the first resource. For example, the transceiver unit 1101 may support the first device 1100 in executing S704, or it may support the first device 1100 in executing S902.

[0279] The processing unit 1102 is used to train a first model based on data from the first terminal device.

[0280] The relevant descriptions of the data, first resources, and first model of the first terminal device can be referred to in the above method embodiments.

[0281] Specifically, all relevant content of each step involved in the chip server in the method embodiments shown in Figures 7 and 9 can be referenced from the functional description of the corresponding functional module, and will not be repeated here. The first device 1100 is used to perform the function of the chip server in the communication method shown in Figure 7 or Figure 9, and thus can achieve the same effect as the above-described communication method.

[0282] Figure 12 shows a structural diagram of a first terminal device 1200, which can be used to perform the functions of the first terminal device involved in the above embodiments. As one possible implementation, the first terminal device 1200 shown in Figure 12 includes: a transceiver unit 1201;

[0283] The transceiver unit 1201 is configured to receive data obtained from the first device based on a first model inference; and / or, receive the first model from the first device. The first model is trained based on data from the first terminal device; the data from the first terminal device is stored in a first resource allocated to the first terminal device within the first device. For example, the transceiver unit 1201 may be configured to support the first terminal device 1200 in executing S711, or to support the first terminal device 1200 in executing S914.

[0284] The relevant descriptions of the data, first resources, and first model of the first terminal device can be referred to in the above method embodiments.

[0285] Specifically, all relevant content of each step involved in the first terminal in the method embodiments shown in Figures 7 and 9 can be referenced from the functional description of the corresponding functional module, and will not be repeated here. The first terminal device 1200 is used to perform the function of the first terminal in the communication method shown in Figure 7 or Figure 9, and therefore can achieve the same effect as the above-mentioned communication method.

[0286] The processing unit mentioned above can be a processing module, a processor, or a controller. It can implement or execute various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. A processor can also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc. A transceiver unit can be a communication module, a transceiver circuit, or a communication interface, etc. Any of the communication devices mentioned above can also include a storage unit for storing the program code and data of any communication device. The storage unit can be a storage module or a memory. When the processing module is a processor, the communication module is a communication interface, and the storage module is a memory, the first device 1100 and the first terminal device 1200 involved in the embodiments of this application can be the communication device 1300 shown in FIG. 13. For example, the first terminal and chip server mentioned above can adopt the composition structure shown in FIG. 13 or include the components shown in FIG. 13. Figure 13 is a schematic diagram of the composition of a communication device 1300 provided in an embodiment of this application. As shown in Figure 13, the communication device 1300 may include a processor 1301, and optionally, may also include a communication line 1302 and a communication interface 1303.

[0287] Furthermore, the communication device 1300 may also include a memory 1304. The processor 1301, the memory 1304, and the communication interface 1303 can be connected via a communication line 1302.

[0288] The processor 1301 can be a central processing unit (CPU), a network processor (NP), a digital signal processor (DSP), a microprocessor, a microcontroller, a programmable logic device (PLD), or any combination thereof. The processor 1301 can also be other communication devices with processing capabilities, such as circuits, devices, or software modules.

[0289] Communication line 1302 is used to transmit information between the components included in communication device 1300.

[0290] Communication interface 1303 is used for communication with other devices or other communication networks. These other communication networks can be Ethernet, radio access network (RAN), wireless local area network (WLAN), etc. Communication interface 1303 can be a radio frequency module, transceiver, or any communication device capable of communication. This application embodiment uses a radio frequency module as an example to illustrate communication interface 1303. The radio frequency module can include an antenna, radio frequency circuitry, etc., and the radio frequency circuitry can include a radio frequency integrated chip, a power amplifier, etc.

[0291] Memory 1304 is used to store instructions. These instructions can be computer programs.

[0292] The memory 1304 can be a read-only memory (ROM) or other type of static storage device that can store static information and / or instructions; it can also be a random access memory (RAM) or other type of dynamic storage device that can store information and / or instructions; it can also be an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage, magnetic disk storage medium or other magnetic storage device. Optical disc storage includes compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.

[0293] It should be noted that the memory 1304 can exist independently of the processor 1301, or it can be integrated with the processor 1301. The memory 1304 can be used to store instructions, program code, or some data, etc. The memory 1304 can be located inside or outside the communication device 1300, without limitation. The processor 1301 is used to execute the instructions stored in the memory 1304 to implement the random access procedure preamble transmission method provided in the following embodiments of this application.

[0294] In one example, processor 1301 may include one or more CPUs, such as CPU0 and CPU1 in Figure 13.

[0295] As an optional implementation, the communication device 1300 may include multiple processors, for example, in addition to the processor 1301 in FIG13, it may also include a processor 1307.

[0296] As an optional implementation, the communication device 1300 also includes an output device 1305 and an input device 1306. The input device 1306 is a keyboard, mouse, microphone, or joystick, etc., and the output device 1305 is a display screen, speaker, etc.

[0297] It should be noted that the communication device 1300 can be a desktop computer, a portable computer, a web server, a mobile phone, a tablet computer, a wireless terminal, an embedded device, a chip system, or a device with a similar structure to that shown in Figure 13. Furthermore, the composition shown in Figure 13 does not constitute a limitation on the communication device. In addition to the components shown in Figure 13, the communication device may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0298] In this embodiment of the application, the chip system may be composed of chips or may include chips and other discrete devices.

[0299] This application also provides a computer-readable storage medium. All or part of the processes in the above method embodiments can be implemented by a computer program instructing related hardware. This program can be stored in the computer-readable storage medium, and when executed, it can include the processes of the above method embodiments. The computer-readable storage medium can be a terminal device of any of the foregoing embodiments, such as an internal storage unit including a data transmission end and / or a data receiving end, like a hard disk or memory of the terminal device. The computer-readable storage medium can also be an external storage device of the terminal device, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the terminal device. Further, the computer-readable storage medium can include both internal storage units and external storage devices of the terminal device. The computer-readable storage medium is used to store the computer program and other programs and data required by the terminal device. The computer-readable storage medium can also be used to temporarily store data that has been output or will be output.

[0300] It should be understood that the collection, storage, use, processing, transmission, provision, and disclosure of user personal information involved in the technical solution of this application all comply with relevant laws and regulations and do not violate public order and good morals. For example, in the technical solution of this application, the processing of user personal information is carried out with the user's authorization, and this will not be repeated hereafter.

[0301] It should be noted that the terms "first" and "second," etc., in the specification, claims, and drawings of this application are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or apparatuses.

[0302] It should be understood that in this application, "at least one (item)" means one or more, "more than one" means two or more, "at least two (items)" means two or three or more, and "and / or" is used to describe the relationship between related objects, indicating that there can be three relationships. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the related objects before and after are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0303] It should be understood that in the embodiments of this application, "B corresponding to A" means that B is associated with A. For example, B can be determined based on A. It should also be understood that determining B based on A does not mean that B is determined solely based on A; B can also be determined based on A and / or other information. Furthermore, the term "connection" in the embodiments of this application refers to various connection methods, such as direct connection or indirect connection, to achieve communication between devices, and the embodiments of this application do not impose any limitations on this.

[0304] Unless otherwise specified, the term "transmission" in the embodiments of this application refers to bidirectional transmission, encompassing the actions of sending and / or receiving. Specifically, "transmission" in the embodiments of this application includes sending data, receiving data, or both sending and receiving data. In other words, data transmission here includes uplink and / or downlink data transmission. Data may include channels and / or signals; uplink data transmission refers to uplink channel and / or uplink signal transmission, and downlink data transmission refers to downlink channel and / or downlink signal transmission. The terms "network" and "system" in the embodiments of this application refer to the same concept; a communication system is a communication network.

[0305] Through the above description of the embodiments, those skilled in the art can clearly understand that, for the sake of convenience and brevity, only the grouping of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0306] In the several embodiments provided in this application, it should be understood that the disclosed communication devices and methods can be implemented in other ways. For example, the communication device embodiments described above are merely illustrative. For instance, the grouping of modules or units is only a logical functional grouping, and in actual implementation, there may be other grouping methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, or indirect coupling or communication connection between devices or units, and may be electrical, mechanical, or other forms.

[0307] The units described as separate components may or may not be physically separate. A component shown as a unit can be one or more physical units; that is, it can be located in one place or distributed in multiple different locations. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0308] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0309] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solutions of the embodiments of this application, essentially, or the parts that contribute to the prior art, or all or part of the technical solutions, can be embodied in the form of a software product. This software product is stored in a storage medium and includes several instructions to cause a device, such as a microcontroller, chip, or processor, to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media for storing program code, such as USB flash drives, portable hard drives, ROM, RAM, magnetic disks, or optical disks.

[0310] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A communication method characterized by comprising: The method is applied to a first device, the first device comprising a first resource; the method comprising: obtaining data of a first terminal device; the data of the first terminal device being stored in the first resource allocated to the first terminal device in the first device; training the first model based on the data of the first terminal device.

2. The method of claim 1, wherein, The method further comprises: sending data inferred based on the first model; and / or, sending the first model.

3. The method of claim 2, wherein, The sending of the first model and / or the sending of data inferred based on the first model comprises: receiving first information, the first information being used to request obtaining the first model and / or data inferred based on the first model; in response to the first information, sending the first model and / or data inferred based on the first model.

4. The method according to any one of claims 1 to 3, characterized in that, The method further comprises: sending second information, the second information being used to indicate information of the first model, the information of the first model comprising one or more of the following: a scenario applicable to the first model, the first model having completed training or updating, performance of the first model, an identifier of the first model, and a type of the first model.

5. The method according to any one of claims 1 to 4, characterized in that, The obtaining of the data of the first terminal device comprises: receiving the data of the first terminal device from a network device; and / or, receiving the data of the first terminal device from the first terminal device.

6. The method according to any one of claims 1 to 5, characterized in that, The data of the first terminal device comprises one or more of the following: data measured by a chip in the first terminal device, data measured by a sensor in the first terminal device, application data of the first terminal device, location data of the first terminal device, data about the first terminal device measured or stored by a network device, and data about the first terminal device measured by another device; the another device is not deployed in the first terminal device and the network device.

7. The method according to any one of claims 1-6, wherein: the information stored in the first resource is specific to the first terminal device; or the information stored in the first resource is available to devices other than the first terminal device.

8. The method of claim 7, wherein, The method further comprises: sending a permission request; the permission request being used to request sharing of the information stored in the first resource; receiving a response message, the response message being used to indicate permission to share the information stored in the first resource.

9. The method according to any one of claims 1 to 8, characterized in that, The method further comprises: receiving a first request message, the first request message being used to request training or updating of the first model.

10. The method according to any one of claims 1 to 9, characterized in that, The method further comprises: receiving third information, the third information being used to indicate that the first device obtains the data of the first terminal device.

11. The method according to any one of claims 1 to 10, characterized in that, The method further comprises: receiving fourth information; or sending the fourth information; the fourth information being used to indicate configuration information of the data of the first terminal device.

12. The method of claim 11, wherein, The configuration information of the data of the first terminal device comprises one or more of the following: content of the data of the first terminal device, format of the data of the first terminal device, reporting type of the data of the first terminal device, reporting condition of the data of the first terminal device, and reporting termination condition of the data of the first terminal device.

13. A communication method characterized by comprising: The method is applied to a first terminal device, and the method comprises: receiving data inferred based on a first model from a first device; and / or, receiving the first model from the first device; the first model being trained based on data of the first terminal device; the data of the first terminal device being stored in a first resource allocated to the first terminal device in the first device.

14. The method of claim 13, wherein, The receiving the first model from the first device further comprises: obtaining data inferred based on the first model.

15. The method of claim 13, wherein, The method further comprises: sending first information, the first information being used to request obtaining the first model and / or data inferred based on the first model.

16. The method according to any one of claims 13-15, characterized in that, The method further comprises: receiving second information, the second information being used to indicate information of the first model, the information of the first model comprising one or more of the following: applicable scenario of the first model, completion of training or updating of the first model, performance of the first model, identification of the first model, and type of the first model.

17. The method according to any one of claims 13-16, characterized by, The method further comprises: sending data of the first terminal device to the first device; and / or, sending the data of the first terminal device to a network device.

18. The method of claim 17, wherein, The data of the first terminal device comprises one or more of the following: data measured by a chip in the first terminal device, data measured by a sensor in the first terminal device, application data of the first terminal device, location data of the first terminal device, data about the first terminal device measured or stored by a network device, and data about the first terminal device measured by another device; the another device not being deployed in the first terminal device and the network device.

19. The method of any one of claims 13-18, wherein: the information stored in the first resource is specific to the first terminal device; or the information stored in the first resource is available to devices other than the first terminal device.

20. The method of claim 19, wherein, The method further comprises: receiving a permission request, the permission request being used to request sharing the information stored in the first resource; sending a response message, the response message being used to indicate permission to share the information stored in the first resource.

21. The method according to any one of claims 13-20, characterized in that, The method further comprises: sending a first request message, the first request message being used to request training or updating the first model.

22. The method according to any one of claims 13-21, characterized by, The method further comprises: sending third information, the third information being used to indicate the first device to obtain the data of the first terminal device.

23. The method according to any one of claims 13-22, characterized in that, The method further comprises: sending fourth information; or receiving the fourth information, the fourth information being used to indicate configuration information of the data of the first terminal device.

24. The method of claim 23, wherein, The configuration information of the data of the first terminal device comprises one or more of the following: content of the data of the first terminal device, format of the data of the first terminal device, reporting type of the data of the first terminal device, reporting condition of the data of the first model, reporting termination condition of the data of the first terminal device.

25. A first apparatus, comprising: The first device is configured to support performing the communication method according to any one of claims 1-12.

26. A first terminal device, the device comprising: The first terminal device is configured to support performing the communication method according to any one of claims 13-24.

27. A communications device, characterized by The communication device comprises a processor configured to support the communication device to perform the communication method according to any one of claims 1-12, or to perform the method according to any one of claims 13-24.

28. A communication system, characterized by The communication system comprises the first device according to claim 25, and the first terminal device according to claim 26.

29. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer instructions which, when executed on a computer, cause the computer to perform the method according to any one of claims 1-12, or cause the computer to perform the method according to any one of claims 13-24.

30. A computer program product, characterised in that, The computer program product comprises computer instructions which, when executed on a computer, cause the computer to perform the method according to any one of claims 1-12, or cause the computer to perform the method according to any one of claims 13-24.

Images