Communication method and related device

Abstract

The present application provides a communication method and a related device, which enable the computing power of communication nodes to be used for an artificial intelligence (AI) model processing process of an AI learning system, so as to further realize AI model processing based on AI data feature matching. The method comprises: a first node receives first information, the first information being used for indicating a first AI model; and, on the basis of local data, the first node processes the first AI model to obtain a second AI model, wherein AI data features of the local data are matched with AI data features corresponding to processing requirements of the first AI model.

Description

A communication method and related equipment Technical Field

[0001] The present application relates to the field of communications, and in particular to a communication method and related equipment. Background Art

[0002] Wireless communication can be the transmission communication between two or more communication nodes without propagating through conductors or cables. The communication nodes generally include network devices and terminal devices.

[0003] Currently, in wireless communication systems, communication nodes generally possess both signal transceiver and computing capabilities. For example, network devices with computing capabilities primarily provide computing power to support signal transceiver capabilities (for example, calculating the time and frequency domain resources required to carry signals), enabling communication between the network device and other communication nodes.

[0004] However, in communication networks, communication nodes may have excess computing power beyond just supporting the aforementioned communication tasks. Therefore, how to utilize this computing power is a pressing technical issue.

[0005] Summary of the Invention

[0006] The present application provides a communication method and related equipment for enabling the computing power of communication nodes to be applied to the AI ​​model processing process in an artificial intelligence (AI) learning system, and for realizing AI model processing based on AI data feature matching.

[0007] In a first aspect, the present application provides a communication method, which is executed by a first node, or the method is executed by some components in the first node (such as a processor, a chip or a chip system, etc.), or the method can also be implemented by a logic module or software that can realize all or part of the functions of the first node. In the first aspect and its possible implementation, the method is described as being executed by the first node. For example, the first node can be a communication node such as a terminal device or a network device in a communication system. In this method, the first node receives first information, which is used to indicate a first AI model; the first node processes the first AI model based on local data to obtain a second AI model; wherein the AI ​​data features of the local data meet the AI ​​data features corresponding to the processing requirements of the first AI model.

[0008] Based on the above technical solution, the first information received by the first node is used to indicate the first AI model. Thereafter, the first node processes the first AI model based on local data to obtain a second AI model. The AI ​​data features of the local data of the first node meet the AI ​​data features corresponding to the processing requirements of the first AI model. In other words, the first node acts as a communication node in the communication system, and the AI ​​data features corresponding to the processing requirements of the first AI model processed by the first node match the AI ​​data features of the local data of the first node. Thus, when the communication node in the communication system acts as a node participating in AI model processing, the computing power of the communication node can be applied to the AI ​​model processing process in the AI ​​learning system, in order to realize the AI ​​model processing process in the communication network.

[0009] In addition, the AI ​​data features of the local data of the first node meet the AI ​​data features corresponding to the processing requirements of the first AI model processed by the first node, so that the first node can process the AI ​​model that matches the AI ​​data features of the local data. Correspondingly, the AI ​​model can also be processed by the node that meets the processing requirements, thereby realizing AI model processing based on AI data feature matching.

[0010] In this application, AI model can be replaced by neural network, AI neural network, neural network model, AI neural network model, machine learning model, etc.

[0011] It should be understood that the first information is used to indicate the first AI model, which can be understood as: the first information includes the index of the first AI model, so that the recipient of the first information can obtain the first AI model based on the index; or, the first information includes the first AI model, so that the recipient of the first information can obtain the first AI model from the first information.

[0012] It should be understood that the AI ​​models involved in this application can be applied to AI tasks. In other words, the execution process of an AI task includes the processing of one or more AI models by a communication node. The AI ​​task can be a task that requires the participation of two or more communication nodes, including terminal devices and / or network devices. For example, the AI ​​task can include a federated learning (FL) task, a distributed training task, a distributed learning task, etc.

[0013] Optionally, AI data may refer to data related to AI, and AI data features may be used to indicate characteristics (or properties, or traits, or attributes, or properties) of AI-related data. For example, the AI ​​data features may include at least one of the following: the AI ​​task to which the AI ​​data is applied, the object to which the AI ​​data belongs, the geographic location where the AI ​​data was collected, the time when the AI ​​data was collected, and the number of AI data samples.

[0014] It should be noted that the AI ​​data features of the local data of the first node meet the AI ​​data features corresponding to the processing requirements of the first AI model, which can be understood as at least one of the following: the AI ​​data features corresponding to the processing requirements of the first AI model are a subset of the AI ​​data features of the local data of the first node, the AI ​​data features of the local data of the first node are more than or equal to the AI ​​data features corresponding to the processing requirements of the first AI model, the AI ​​data features of the local data of the first node at least include the AI ​​data features corresponding to the processing requirements of the first AI model, and the AI ​​data features of the local data of the first node match / conform to the AI ​​data features corresponding to the processing requirements of the first AI model.

[0015] In a possible implementation of the first aspect, the first node receiving the first information includes: the first node receiving the first information based on second information, where the second information is used to indicate transmission information of the AI ​​model.

[0016] Based on the above technical solution, the first node can receive first information indicating the first AI model based on the second information, wherein the second information is used to indicate the transmission information of the AI ​​model, so that the first node can realize the transmission of the AI ​​model based on the second information.

[0017] Optionally, the transmission information includes at least one of the following:

[0018] The node identifier of the node that sends the first AI model;

[0019] Receive a node identifier of a node of the second AI model;

[0020] an identifier of the AI ​​task corresponding to the first AI model and / or the second AI model;

[0021] an identifier of the first AI model;

[0022] an identifier of the second AI model;

[0023] The first AI model is processed by at least one of a training process, a distillation process, and a fusion process;

[0024] The second AI model is processed by at least one of a training process, a distillation process, and a fusion process;

[0025] Indication information indicating a non-relay node.

[0026] In a possible implementation manner of the first aspect, the method further includes: the first node receiving the second information.

[0027] Based on the above technical solution, the first node can obtain the second information by receiving the second information, that is, the first node can determine the second information through scheduling instructions from other nodes (such as the central node) to reduce the implementation complexity of the first node.

[0028] Optionally, the other node can serve as a central node (or control node, management node, etc.) in the learning architecture where the first node is located, so that the solution can be adapted to a learning architecture with a central node (or control node, management node, etc.).

[0029] In a possible implementation of the first aspect, the method further includes: the first node receiving one or more neighbor node information, where the one or more neighbor node information is used to indicate AI data features of one or more neighbor nodes; and the first node determining the second information based on the one or more neighbor node information.

[0030] Based on the above technical solution, the first node can receive one or more neighbor node information indicating the AI ​​data characteristics of one or more neighbor nodes, and determine the second information based on the one or more neighbor node information, that is, the first node can locally determine the second information based on the received (or collected) one or more neighbor node information.

[0031] Optionally, the first node can locally determine the transmission information of the AI ​​model, so that the solution can be adapted to a decentralized learning architecture.

[0032] In a possible implementation manner of the first aspect, the method further includes: the first node sending third information based on the second information, where the third information is used to indicate the second AI model.

[0033] Based on the above technical solution, after the first node processes the first AI model based on local data to obtain the second AI model, the first node can also send third information indicating the second AI model based on the second information, so that the recipient of the third information can further process the second AI model.

[0034] In a possible implementation of the first aspect, the method further includes: the first node sending fourth information and / or fifth information, the fourth information being used to indicate AI data features corresponding to the processing requirements of the first AI model, and the fifth information being used to indicate AI data features corresponding to the processing requirements of the second AI model.

[0035] Optionally, the above-mentioned transmission information may further include fourth information and / or fifth information.

[0036] Based on the above technical solution, the first node may further transmit fourth information indicating AI data characteristics corresponding to the processing requirements of the first AI model, and / or the first node may further transmit fifth information indicating AI data characteristics corresponding to the processing requirements of the second AI model. This allows the recipient of the fourth and / or fifth information to clearly identify the AI ​​data characteristics corresponding to the processing requirements of the AI ​​model. Subsequently, the recipient may determine, based on the fourth and / or fifth information, whether the AI ​​data characteristics of the recipient's local data meet the AI ​​data characteristics required for processing by the AI ​​model, and thereby determine whether to process the second AI model.

[0037] In a possible implementation of the first aspect, before the first node processes the first AI model based on local data, the method further includes: the first node receiving fourth information, where the fourth information is used to indicate AI data features corresponding to processing requirements of the first AI model.

[0038] Based on the above technical solution, the first node can also receive fourth information for indicating the AI ​​data characteristics corresponding to the processing requirements of the first AI model, so that the first node can clarify, based on the fourth information, that the AI ​​data characteristics of the local data of the first node meet the AI ​​data characteristics of the processing requirements of the AI ​​model, and then determine to process the second AI model.

[0039] In a possible implementation manner of the first aspect, the method further includes: the first node sending indication information indicating the AI ​​data feature of the local data.

[0040] Based on the above technical solution, the first node can also send indication information indicating the AI ​​data characteristics of the local data of the first node, so that the recipient of the indication information can clearly understand the AI ​​data characteristics of the local data of the first node, and then the recipient can use the indication information as one of the bases for determining the transmission information of the AI ​​model.

[0041] Optionally, the indication information sent by the first node is used to indicate the AI ​​data characteristics of the local data of the first node, which can be understood as indicating the node information of the first node. In other words, the indication information sent by the first node can be called the node information of the first node.

[0042] In a possible implementation of the first aspect, the first node processes the first AI model based on local data to obtain the second AI model, including: the first node performs at least one of training processing, distillation processing, and fusion processing on the first AI model based on the local data to obtain the second AI model.

[0043] Based on the above technical solution, the first node can perform at least one of the above processing on the first AI model based on local data to improve the flexibility of the solution implementation.

[0044] The second aspect of the present application provides a communication method, which is executed by a central node, or the method is executed by some components in the central node (such as a processor, chip or chip system, etc.), or the method can also be implemented by a logic module or software that can realize all or part of the central node function. In the second aspect and its possible implementation, the method is described as being executed by a central node, and the central node can be replaced by a control node, a management node, etc. In this method, the central node receives one or more node information, and the one or more node information is used to indicate the AI ​​data characteristics of one or more nodes; the one or more node information is used to determine the transmission information of the AI ​​model; the central node sends a second information, and the second information is used to indicate the transmission information.

[0045] Based on the above technical solution, the one or more node information received by the central node is used to indicate the AI ​​data characteristics of one or more nodes. The central node can determine the transmission information of the AI ​​model based on the one or more node information. Thereafter, the central node can send second information indicating the transmission information, so that the recipient of the second information can transmit the AI ​​model based on the second information. Therefore, when the communication nodes in the communication system act as nodes participating in AI model processing, the computing power of the communication nodes can be applied to the AI ​​model processing process in the AI ​​learning system, in order to implement the AI ​​model processing process in the communication network.

[0046] In addition, the central node determines the transmission information of the AI ​​model based on the AI ​​data characteristics of one or more nodes, so that the communication node can process the AI ​​model that matches the AI ​​data characteristics of the local data. Correspondingly, the AI ​​model can also be processed by the node that meets the processing requirements, thereby realizing AI model processing based on AI data feature matching.

[0047] It should be understood that the central node can determine the transmission information of the AI ​​model transmitted by the one or more nodes based on the AI ​​data characteristics of the one or more nodes, that is, the second information sent by the central node can be used to instruct the one or more nodes to transmit the transmission information of the AI ​​model. Alternatively, the central node can send one or more second information, and the one or more second information are respectively used to instruct the one or more nodes to transmit the transmission information of the AI ​​model. Accordingly, the recipient of the second information may include the one or more nodes (for example, the one or more nodes may include the first node).

[0048] Optionally, the transmission information includes at least one of the following:

[0049] The node identifier of the node that sends the first AI model;

[0050] Receive a node identifier of a node of the second AI model;

[0051] an identifier of the AI ​​task corresponding to the first AI model and / or the second AI model;

[0052] an identifier of the first AI model;

[0053] an identifier of the second AI model;

[0054] The first AI model is processed by at least one of a training process, a distillation process, and a fusion process;

[0055] The second AI model is processed by at least one of a training process, a distillation process, and a fusion process;

[0056] Indication information indicating a non-relay node.

[0057] Optionally, the AI ​​data feature includes at least one of the following:

[0058] The AI ​​tasks applied to the AI ​​data, the objects to which the AI ​​data belongs, the geographical location information of the AI ​​data collection, the time information of the AI ​​data collection, and the number of AI data samples.

[0059] In a third aspect of the present application, a communication device is provided, which is a first node, or a component of the first node (such as a processor, chip, or chip system), or a logic module or software capable of implementing all or part of the functions of the first node. In the third aspect and its possible implementations, the communication device is described as a first node, and the first node can be a terminal device or a network device.

[0060] The device includes a processing unit and a transceiver unit; the transceiver unit is used to receive first information, where the first information is used to indicate a first artificial intelligence (AI) model; the processing unit is used to process the first AI model based on local data to obtain a second AI model; wherein the AI ​​data features of the local data meet the AI ​​data features corresponding to the processing requirements of the first AI model.

[0061] In a possible implementation of the third aspect, the transceiver unit is used to receive the first information, including: the transceiver unit is specifically used to receive the first information based on second information, and the second information is used to indicate transmission information of the AI ​​model.

[0062] In a possible implementation manner of the third aspect, the transceiver unit is further configured to receive the second information.

[0063] In a possible implementation of the third aspect, the transceiver unit is further used to receive one or more neighbor node information, where the one or more neighbor node information is used to indicate AI data features of one or more neighbor nodes; the processing unit is further used to determine the second information based on the one or more neighbor node information.

[0064] In a possible implementation of the third aspect, the transceiver unit is further used to send third information based on the second information, where the third information is used to indicate the second AI model.

[0065] In a possible implementation of the third aspect, the transceiver unit is further used to send fourth information and / or fifth information, where the fourth information is used to indicate the AI ​​data features corresponding to the processing requirements of the first AI model, and the fifth information is used to indicate the AI ​​data features corresponding to the processing requirements of the second AI model.

[0066] In a possible implementation of the third aspect, the transmission information includes at least one of the following:

[0067] The node identifier of the node that sends the first AI model;

[0068] Receive a node identifier of a node of the second AI model;

[0069] an identifier of the AI ​​task corresponding to the first AI model and / or the second AI model;

[0070] an identifier of the first AI model;

[0071] an identifier of the second AI model;

[0072] The first AI model is processed by at least one of a training process, a distillation process, and a fusion process;

[0073] The second AI model is processed by at least one of a training process, a distillation process, and a fusion process;

[0074] Indication information indicating a non-relay node.

[0075] In a possible implementation of the third aspect, the transceiver unit is further used to receive fourth information, where the fourth information is used to indicate AI data features corresponding to the processing requirements of the first AI model.

[0076] In a possible implementation of the third aspect, the AI ​​data feature includes at least one of the following: the AI ​​task applied to the AI ​​data, the object to which the AI ​​data belongs, the geographic location information for collecting the AI ​​data, the time information for collecting the AI ​​data, and the number of samples of the AI ​​data.

[0077] In a possible implementation manner of the third aspect, the transceiver unit is further configured to send indication information indicating an AI data feature of the local data.

[0078] In a possible implementation of the third aspect, the processing unit is used to process the first AI model based on local data to obtain the second AI model, including: the processing unit is specifically used to perform at least one of training processing, distillation processing, and fusion processing on the first AI model based on the local data to obtain the second AI model.

[0079] In the third aspect of the present application, the constituent modules of the communication device can also be used to execute the steps performed in each possible implementation method of the first aspect and achieve corresponding technical effects. For details, please refer to the first aspect and will not be repeated here.

[0080] In a fourth aspect, the present application provides a communication device, which is a central node, or a component of a central node (such as a processor, chip, or chip system), or a logic module or software capable of implementing all or part of the central node functions. In the eighth aspect and its possible implementations, the communication device is described as a central node, and the central node can be a terminal device or a network device.

[0081] The device includes a processing unit and a transceiver unit; the transceiver unit is used to receive one or more node information, wherein the one or more node information is used to indicate the AI ​​data characteristics of one or more nodes; the one or more node information is used to determine the transmission information of the AI ​​model; the processing unit is used to determine second information, wherein the second information is used to indicate the transmission information; the transceiver unit is also used to send the second information.

[0082] In a possible implementation of the fourth aspect, the transmission information includes at least one of the following:

[0083] The node identifier of the node that sends the first AI model;

[0084] Receive a node identifier of a node of the second AI model;

[0085] an identifier of the AI ​​task corresponding to the first AI model and / or the second AI model;

[0086] an identifier of the first AI model;

[0087] an identifier of the second AI model;

[0088] The first AI model is processed by at least one of a training process, a distillation process, and a fusion process;

[0089] The second AI model is processed by at least one of a training process, a distillation process, and a fusion process;

[0090] Indication information indicating a non-relay node.

[0091] In a possible implementation of the fourth aspect, the AI ​​data feature includes at least one of the following: the AI ​​task applied to the AI ​​data, the object to which the AI ​​data belongs, the geographic location information of collecting the AI ​​data, the time information of collecting the AI ​​data, and the number of samples of the AI ​​data.

[0092] In the fourth aspect of the present application, the constituent modules of the communication device can also be used to execute the steps performed in each possible implementation method of the second aspect and achieve corresponding technical effects. For details, please refer to the second aspect and will not be repeated here.

[0093] In a fifth aspect, the present application provides a communication device, comprising at least one processor coupled to a memory; the memory is used to store programs or instructions; the at least one processor is used to execute the program or instructions so that the device implements the method of the aforementioned first aspect or any possible implementation method of the first aspect.

[0094] In the sixth aspect of the present application, a communication device is provided, comprising at least one processor coupled to a memory; the memory is used to store programs or instructions; the at least one processor is used to execute the program or instructions so that the device implements the aforementioned second aspect or any possible implementation method of the second aspect.

[0095] In a seventh aspect, the present application provides a communication device comprising at least one logic circuit and an input / output interface; the logic circuit is used to execute the method as described in the first aspect or any possible implementation of the first aspect.

[0096] In an eighth aspect, the present application provides a communication device comprising at least one logic circuit and an input / output interface; the logic circuit is used to execute the method as described in the second aspect or any possible implementation of the second aspect.

[0097] In one possible design, the communication device provided in the fifth, sixth, seventh or eighth aspect above may be a chip or a chip system.

[0098] In the ninth aspect of the present application, a computer-readable storage medium is provided, which is used to store one or more computer-executable instructions. When the computer-executable instructions are executed by a processor, the processor executes the method in any possible implementation of any aspect of the first to second aspects above.

[0099] The tenth aspect of the present application provides a computer program product (or computer program). When the computer program product is executed by the processor, the processor executes any possible implementation method of any aspect of the first to second aspects above.

[0100] In the eleventh aspect of the present application, a chip system is provided, which includes at least one processor for supporting a communication device to implement the functions involved in any possible implementation of any one of the first to second aspects above.

[0101] In one possible design, the chip system may further include a memory for storing program instructions and data necessary for the first communication device. The chip system may be composed of a chip or may include a chip and other discrete components. Optionally, the chip system may further include an interface circuit for providing program instructions and / or data to the at least one processor.

[0102] A twelfth aspect of the present application provides a communication system, which includes the first node in any of the above aspects and any of its implementation methods.

[0103] Optionally, the communication system further includes the central node in any of the above aspects and any of its implementations.

[0104] Among them, the technical effects brought about by any design method in the third aspect to the twelfth aspect can refer to the technical effects brought about by the different design methods in the above-mentioned first aspect to the second aspect, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0105] FIG1a is a schematic diagram of a communication system provided by the present application;

[0106] FIG1b is another schematic diagram of the communication system provided by the present application;

[0107] FIG1c is another schematic diagram of the communication system provided by the present application;

[0108] FIG1d is a schematic diagram of the AI ​​processing process involved in this application;

[0109] FIG1e is another schematic diagram of the AI ​​processing process involved in this application;

[0110] FIG2a is another schematic diagram of the AI ​​processing process involved in this application;

[0111] FIG2 b is another schematic diagram of the AI ​​processing process involved in this application;

[0112] FIG2c is another schematic diagram of the AI ​​processing process involved in this application;

[0113] FIG2 d is another schematic diagram of the AI ​​processing process involved in this application;

[0114] FIG2e is another schematic diagram of the AI ​​processing process involved in this application;

[0115] FIG3 is an interactive schematic diagram of the communication method provided by this application;

[0116] FIG4a is a schematic diagram of the AI ​​processing process provided by this application;

[0117] FIG4 b is another schematic diagram of the AI ​​processing process provided by this application;

[0118] FIG5 is another schematic diagram of the AI ​​processing process provided by this application;

[0119] FIG6a is another schematic diagram of the AI ​​processing process provided by this application;

[0120] FIG6 b is another interactive schematic diagram of the communication method provided by the present application;

[0121] FIG7 is another interactive schematic diagram of the communication method provided by this application;

[0122] FIG8 is a schematic diagram of a communication device provided by the present application;

[0123] FIG9 is another schematic diagram of a communication device provided by the present application;

[0124] FIG10 is another schematic diagram of the communication device provided by the present application;

[0125] FIG11 is another schematic diagram of a communication device provided by the present application;

[0126] FIG12 is another schematic diagram of the communication device provided in this application. DETAILED DESCRIPTION

[0127] First, some of the terms used in the embodiments of the present application are explained to facilitate understanding by those skilled in the art.

[0128] (1) Terminal device: It can be a wireless terminal device that can receive network device scheduling and instruction information. The wireless terminal device can be a device that provides voice and / or data connectivity to the user, or a handheld device with wireless connection function, or other processing device connected to a wireless modem.

[0129] Terminal devices can communicate with one or more core networks or the Internet via a radio access network (RAN). Terminal devices can be mobile terminal devices, such as mobile phones (also known as "cellular" phones, mobile phones), computers, and data cards. For example, they can be portable, pocket-sized, handheld, computer-built-in, or vehicle-mounted mobile devices that exchange voice and / or data with the radio access network. Examples include personal communication service (PCS) phones, cordless phones, Session Initiation Protocol (SIP) phones, wireless local loop (WLL) stations, personal digital assistants (PDAs), tablet computers, and computers with wireless transceiver capabilities. Wireless terminal equipment can also be called system, subscriber unit, subscriber station, mobile station, mobile station (MS), remote station, access point (AP), remote terminal equipment (remote terminal), access terminal equipment (access terminal), user terminal equipment (user terminal), user agent, subscriber station (SS), customer premises equipment (CPE), terminal, user equipment (UE), mobile terminal (MT), etc.

[0130] As an example and not a limitation, in the embodiments of the present application, the terminal device may also be a wearable device. Wearable devices may also be referred to as wearable smart devices or smart wearable devices, etc., which are a general term for wearable devices that are intelligently designed and developed using wearable technology for daily wear, such as glasses, gloves, watches, clothing, and shoes. A wearable device is a portable device that is worn directly on the body or integrated into the user's clothes or accessories. Wearable devices are not only hardware devices, but also achieve powerful functions through software support, data interaction, and cloud interaction. Broadly speaking, wearable smart devices include those that are fully functional, large in size, and can achieve complete or partial functions without relying on smartphones, such as smart watches or smart glasses, etc., as well as those that only focus on a certain type of application function and need to be used in conjunction with other devices such as smartphones, such as various smart bracelets, smart helmets, and smart jewelry for vital sign monitoring.

[0131] The terminal may also be a drone, a robot, a terminal in device-to-device (D2D) communication, a terminal in vehicle-to-everything (V2X), a virtual reality (VR) terminal device, an augmented reality (AR) terminal device, a wireless terminal in industrial control, a wireless terminal in self-driving, a wireless terminal in remote medical, a wireless terminal in smart grid, a wireless terminal in transportation safety, a wireless terminal in smart city, a wireless terminal in smart home, etc.

[0132] In addition, the terminal device may also be a terminal device in a communication system that has evolved after the fifth generation (5G) communication system (e.g., a sixth generation (6G) communication system) or a terminal device in a future public land mobile network (PLMN). For example, the 6G network can further expand the form and function of 5G communication terminals. 6G terminals include but are not limited to vehicles, cellular network terminals (with integrated satellite terminal functions), drones, and Internet of Things (IoT) devices.

[0133] In an embodiment of the present application, the terminal device may also obtain AI services provided by the network device. Optionally, the terminal device may also have AI processing capabilities.

[0134] (2) Network equipment: It can be a device in a wireless network. For example, the network equipment can be a RAN node (or device) that connects a terminal device to a wireless network, which can also be called a base station. Currently, some examples of RAN equipment include: base station, evolved NodeB (eNodeB), gNB (gNodeB) in a 5G communication system, transmission reception point (TRP), evolved Node B (eNB), radio network controller (RNC), Node B (NB), home base station (e.g., home evolved Node B, or home Node B, HNB), base band unit (BBU), or wireless fidelity (Wi-Fi) access point AP, etc. In addition, in a network structure, the network equipment can include a centralized unit (CU) node, a distributed unit (DU) node, or a RAN device including a CU node and a DU node.

[0135] Alternatively, a RAN node can be a macro base station, micro base station, indoor base station, relay node, donor node, or a wireless controller in a cloud radio access network (CRAN) scenario. A RAN node can also be a server, wearable device, vehicle, or vehicle-mounted device. For example, the access network device in vehicle-to-everything (V2X) technology can be a roadside unit (RSU).

[0136] In another possible scenario, multiple RAN nodes collaborate to assist the terminal in achieving wireless access, and different RAN nodes respectively implement part of the functions of the base station. For example, the RAN node can be a centralized unit (CU), a distributed unit (DU), a CU-control plane (CP), a CU-user plane (UP), or a radio unit (RU). The CU and DU can be set separately, or they can be included in the same network element, such as a baseband unit (BBU). The RU can be included in a radio frequency device or radio frequency unit, such as a remote radio unit (RRU), an active antenna unit (AAU), or a remote radio head (RRH).

[0137] In different systems, CU (or CU-CP and CU-UP), DU or RU may also have different names, but those skilled in the art can understand their meanings. For example, in an open access network (open RAN, O-RAN or ORAN) system, CU may also be called O-CU (open CU), DU may also be called O-DU, CU-CP may also be called O-CU-CP, CU-UP may also be called O-CU-UP, and RU may also be called O-RU. For the convenience of description, this application takes CU, CU-CP, CU-UP, DU and RU as examples for description. Any unit of CU (or CU-CP, CU-UP), DU and RU in this application can be implemented by a software module, a hardware module, or a combination of a software module and a hardware module.

[0138] The communication between the access network device and the terminal device follows a certain protocol layer structure. The protocol layer may include a control plane protocol layer and a user plane protocol layer. The control plane protocol layer may include at least one of the following: a radio resource control (RRC) layer, a packet data convergence protocol (PDCP) layer, a radio link control (RLC) layer, a media access control (MAC) layer, or a physical (PHY) layer. The user plane protocol layer may include at least one of the following: a service data adaptation protocol (SDAP) layer, a PDCP layer, an RLC layer, a MAC layer, or a physical layer.

[0139] For the correspondence between network elements in the ORAN system and their achievable protocol layer functions, please refer to Table 1 below.

[0140] Table 1

[0141] The network device may be any other device that provides wireless communication functionality to the terminal device. The embodiments of this application do not limit the specific technology and device form used by the network device. For ease of description, the embodiments of this application do not limit this.

[0142] The network equipment may also include core network equipment, which may include, for example, a mobility management entity (MME), a home subscriber server (HSS), a serving gateway (S-GW), a policy and charging rules function (PCRF), and a public data network gateway (PDN gateway, P-GW) in a fourth generation (4G) network; and network elements such as an access and mobility management function (AMF), a user plane function (UPF), or a session management function (SMF) in a 5G network. In addition, the core network equipment may also include other core network equipment in a 5G network and a next generation network of a 5G network.

[0143] In an embodiment of the present application, the above-mentioned network device may also have a network node with AI capabilities, which can provide AI services for terminals or other network devices. For example, it can be an AI node on the network side (access network or core network), a computing power node, a RAN node with AI capabilities, a core network element with AI capabilities, etc.

[0144] In the embodiments of the present application, the apparatus for implementing the function of the network device may be the network device, or may be a device capable of supporting the network device in implementing the function, such as a chip system, which may be installed in the network device. In the technical solutions provided in the embodiments of the present application, the technical solutions provided in the embodiments of the present application are described by taking the network device as an example.

[0145] (3) Configuration and pre-configuration: In this application, configuration and pre-configuration are used simultaneously. Configuration refers to the network device / server sending some parameter configuration information or parameter values ​​to the terminal through messages or signaling, so that the terminal can determine the communication parameters or resources during transmission based on these values ​​or information. Pre-configuration is similar to configuration, and can be parameter information or parameter values ​​pre-negotiated between the network device / server and the terminal device, or parameter information or parameter values ​​used by the base station / network device or terminal device as specified in the standard protocol, or parameter information or parameter values ​​pre-stored in the base station / server or terminal device. This application does not limit this.

[0146] Furthermore, these values ​​and parameters can be changed or updated.

[0147] (4) The terms "system" and "network" in the embodiments of the present application can be used interchangeably. "Multiple" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships can exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, "at least one of A, B and C" includes A, B, C, AB, AC, BC or ABC. In addition, unless otherwise specified, the ordinal numbers such as "first" and "second" mentioned in the embodiments of the present application are used to distinguish multiple objects, and are not used to limit the order, timing, priority or importance of multiple objects.

[0148] (5) “Sending” and “receiving” in the embodiments of the present application indicate the direction of signal transmission. For example, “sending information to XX” can be understood as the destination of the information being XX, which can include direct sending through the air interface, as well as indirect sending through the air interface by other units or modules. “Receiving information from YY” can be understood as the source of the information being YY, which can include direct receiving from YY through the air interface, as well as indirect receiving from YY through the air interface from other units or modules. “Sending” can also be understood as the “output” of the chip interface, and “receiving” can also be understood as the “input” of the chip interface.

[0149] In other words, sending and receiving can be performed between devices, for example, between a network device and a terminal device, or can be performed within a device, for example, sending or receiving between components, modules, chips, software modules or hardware modules within the device through a bus, wiring or interface.

[0150] It is understandable that information may be processed between the source and destination of information transmission, such as coding, modulation, etc., but the destination can understand the valid information from the source. Similar expressions in this application can be understood similarly and will not be repeated.

[0151] (6) In the embodiments of the present application, "indication" may include direct indication and indirect indication, and may also include explicit indication and implicit indication. The information indicated by a certain information (such as the indication information described below) is called information to be indicated. In the specific implementation process, there are many ways to indicate the information to be indicated, such as but not limited to, directly indicating the information to be indicated, such as the information to be indicated itself or the index of the information to be indicated. The information to be indicated may also be indirectly indicated by indicating other information, wherein the other information is associated with the information to be indicated; or only a part of the information to be indicated may be indicated, while the other part of the information to be indicated is known or agreed in advance. For example, the indication of specific information may be achieved by means of the arrangement order of each information agreed in advance (such as predefined by the protocol), thereby reducing the indication overhead to a certain extent. The present application does not limit the specific method of indication. It is understandable that for the sender of the indication information, the indication information can be used to indicate the information to be indicated, and for the receiver of the indication information, the indication information can be used to determine the information to be indicated.

[0152] In this application, unless otherwise specified, the same or similar parts between the various embodiments can refer to each other. In the various embodiments of this application, and the various methods / designs / implementations in each embodiment, if there is no special explanation and logical conflict, the terms and / or descriptions between different embodiments and the various methods / designs / implementations in each embodiment are consistent and can be referenced to each other. The technical features in different embodiments and the various methods / designs / implementations in each embodiment can be combined to form new embodiments, methods, or implementations according to their inherent logical relationships. The following description of the implementation methods of this application does not constitute a limitation on the scope of protection of this application.

[0153] The present application can be applied to a long term evolution (LTE) system, a new radio (NR) system, or a communication system evolved after 5G (such as 6G, etc.). The communication system includes at least one network device and / or at least one terminal device.

[0154] Please refer to Figure 1a, which is a schematic diagram of a communication system in this application. Figure 1a exemplarily illustrates a network device and six terminal devices, namely terminal device 1, terminal device 2, terminal device 3, terminal device 4, terminal device 5, and terminal device 6. In the example shown in Figure 1a, terminal device 1 is a smart teacup, terminal device 2 is a smart air conditioner, terminal device 3 is a smart gas pump, terminal device 4 is a vehicle, terminal device 5 is a mobile phone, and terminal device 6 is a printer.

[0155] As shown in Figure 1a, the AI ​​configuration information sending entity can be a network device. The AI ​​configuration information receiving entity can be terminal devices 1-6. In this case, the network device and terminal devices 1-6 form a communication system. In this communication system, terminal devices 1-6 can send data to the network device, and the network device needs to receive data sent by terminal devices 1-6. At the same time, the network device can send configuration information to terminal devices 1-6.

[0156] For example, in Figure 1a, terminal devices 4 and 6 can also form a communication system. Terminal device 5 serves as a network device, i.e., the AI ​​configuration information sending entity; terminal devices 4 and 6 serve as terminal devices, i.e., the AI ​​configuration information receiving entities. For example, in a connected vehicle system, terminal device 5 sends AI configuration information to terminal devices 4 and 6, respectively, and receives data from them. Correspondingly, terminal devices 4 and 6 receive AI configuration information from terminal device 5 and send data to terminal device 5.

[0157] Taking the communication system shown in Figure 1a as an example, in addition to performing communication-related services, different devices (including between network devices and network devices, between network devices and terminal devices, and / or between terminal devices) may also perform AI-related services. For example, as shown in Figure 1b, taking the network device as a base station as an example, the base station can perform communication-related services and AI-related services with one or more terminal devices, and different terminal devices can also perform communication-related services and AI-related services. For another example, as shown in Figure 1c, taking the terminal devices including a TV and a mobile phone as an example, communication-related services and AI-related services can also be performed between the TV and the mobile phone.

[0158] The technical solution provided in this application can be applied to a wireless communication system (e.g., the system shown in FIG. 1a , FIG. 1b , or FIG. 1c ). For example, an AI network element can be introduced into the communication system provided in this application to implement some or all AI-related operations. The AI ​​network element can also be referred to as an AI node, AI device, AI entity, AI module, AI model, or AI unit, etc. The AI ​​network element can be a network element built into the communication system. For example, the AI ​​network element can be an AI module built into: an access network device, a core network device, a cloud server, or a network management (OAM) to implement AI-related functions. The OAM can be a network management device for a core network device and / or a network management device for an access network device. Alternatively, the AI ​​network element can also be an independently set network element in the communication system. Optionally, the terminal or the chip built into the terminal can also include an AI entity to implement AI-related functions.

[0159] The following is a brief introduction to artificial intelligence (AI) that may be involved in this application.

[0160] Artificial intelligence (AI) can imbue machines with human intelligence. For example, it can enable machines to simulate certain intelligent human behaviors using computer hardware and software. Machine learning methods can be used to achieve AI. In machine learning, a machine uses training data to learn (or train) a model. This model represents the mapping from input to output. The learned model can be used for inference (or prediction), meaning that the model can be used to predict the output corresponding to a given input. This output can also be called an inference result (or prediction result).

[0161] Machine learning can include supervised learning, unsupervised learning, and reinforcement learning. Among them, unsupervised learning can also be called unsupervised learning.

[0162] Supervised learning uses machine learning algorithms to learn the mapping relationship between sample values ​​and sample labels based on collected sample values ​​and sample labels, and then expresses this learned mapping relationship using an AI model. The process of training a machine learning model is the process of learning this mapping relationship. During training, sample values ​​are input into the model to obtain the model's predicted values. The model parameters are optimized by calculating the error between the model's predicted values ​​and the sample labels (ideal values). Once the mapping relationship is learned, the learned mapping can be used to predict new sample labels. The mapping relationship learned by supervised learning can include linear mappings or nonlinear mappings. Based on the type of label, the learning task can be divided into classification tasks and regression tasks.

[0163] Unsupervised learning uses algorithms to discover inherent patterns in collected sample values. One type of unsupervised learning algorithm uses the samples themselves as supervisory signals, meaning the model learns the mapping from one sample to another. This is called self-supervised learning. During training, the model parameters are optimized by calculating the error between the model's predictions and the samples themselves. Self-supervised learning can be used in signal compression and decompression recovery applications. Common algorithms include autoencoders and generative adversarial networks.

[0164] Reinforcement learning, unlike supervised learning, is a type of algorithm that learns problem-solving strategies through interaction with the environment. Unlike supervised and unsupervised learning, reinforcement learning problems lack explicit label data for "correct" actions. Instead, the algorithm must interact with the environment to obtain reward signals from the environment, and then adjust its decision-making actions to maximize the reward signal value. For example, in downlink power control, the reinforcement learning model adjusts the downlink transmit power of each user based on the overall system throughput fed back by the wireless network, hoping to achieve higher system throughput. The goal of reinforcement learning is also to learn the mapping between environmental states and optimal (e.g., optimal) decision-making actions. However, because the labels for "correct actions" cannot be obtained in advance, network optimization cannot be achieved by calculating the error between actions and "correct actions." Reinforcement learning training is achieved through iterative interaction with the environment.

[0165] A neural network (NN) is a specific model in machine learning technology. According to the universal approximation theorem, NNs can theoretically approximate any continuous function, enabling them to learn arbitrary mappings. Traditional communication systems require extensive expert knowledge to design communication modules. However, deep learning communication systems based on neural networks can automatically discover implicit patterns in massive data sets and establish mapping relationships between data, achieving performance superior to traditional modeling methods.

[0166] The idea of ​​a neural network originates from the neuronal structure of the brain. For example, each neuron performs a weighted sum operation on its input values ​​and outputs the result through an activation function. Figure 1d shows a schematic diagram of a neuron structure. Assume that the input of a neuron is x = [x0, x1, ..., x n ], and the weights corresponding to each input are w=[w,w1,…,w n ], where n is a positive integer, w i and x i It can be a decimal, an integer (such as 0, a positive integer or a negative integer, etc.), or a complex number. i As x i The weight of x i Weighted. The bias of the weighted sum of the input values ​​according to the weight is, for example, b. The activation function can take many forms. Assuming that the activation function of a neuron is: y = f(z) = max(0,z), then the output of the neuron is: For another example, if the activation function of a neuron is: y = f(z) = z, then the output of the neuron is: b can be a decimal, an integer (eg, 0, a positive integer, or a negative integer), or a complex number, etc. The activation functions of different neurons in a neural network can be the same or different.

[0167] Furthermore, neural networks generally include multiple layers, each of which may include one or more neurons. Increasing the depth and / or width of a neural network can improve its expressive power, providing more powerful information extraction and abstract modeling capabilities for complex systems. The depth of a neural network can refer to the number of layers it comprises, and the number of neurons in each layer can be referred to as the width of that layer. In one implementation, a neural network includes an input layer and an output layer. The input layer processes the input information received by the neural network through neurons, passing the processing results to the output layer, which then obtains the output of the neural network. In another implementation, a neural network includes an input layer, a hidden layer, and an output layer. The input layer processes the input information received by the neural network through neurons, passing the processing results to an intermediate hidden layer. The hidden layer performs calculations on the received processing results to obtain a calculation result, which is then passed to the output layer or the next adjacent hidden layer, which ultimately obtains the output of the neural network. A neural network can include one hidden layer or multiple hidden layers connected in sequence, without limitation.

[0168] A neural network is, for example, a deep neural network (DNN). Depending on how the network is constructed, a DNN can include a feedforward neural network (FNN), a convolutional neural network (CNN), and a recurrent neural network (RNN).

[0169] A characteristic of FNN networks is that neurons in adjacent layers are fully connected. This characteristic typically requires a large amount of storage space and results in high computational complexity. Figure 1e shows a schematic diagram of an FNN network.

[0170] CNN is a neural network specifically designed to process data with a grid-like structure. For example, time series data (discrete sampling along the time axis) and image data (discrete sampling along two dimensions) can both be considered grid-like data. CNNs do not utilize all input information at once for computation. Instead, they use a fixed-size window to intercept a portion of the information for convolution operations, significantly reducing the computational complexity of model parameters. Furthermore, depending on the type of information intercepted by the window (e.g., people and objects in an image represent different types of information), each window can use a different convolution kernel, enabling CNNs to better extract features from the input data.

[0171] RNNs are a type of DNN that utilizes feedback time series information. Their input consists of a new input value at the current moment and their own output value at the previous moment. RNNs are suitable for capturing temporally correlated sequence features and are particularly well-suited for applications such as speech recognition and channel coding.

[0172] During the machine learning model training process, a loss function can be defined. This function describes the gap or discrepancy between the model's output and the ideal target value. Loss functions can be expressed in various forms, and there are no restrictions on their specific form. The model training process can be viewed as adjusting some or all of the model's parameters to keep the loss function below a threshold or meet the target.

[0173] A model may also be referred to as an AI model, rule, or other name. An AI model can be considered a specific method for implementing an AI function. An AI model represents a mapping relationship or function between the input and output of a model. AI functions may include one or more of the following: data collection, model training (or model learning), model information release, model inference (or model reasoning, inference, or prediction, etc.), model monitoring or model verification, or inference result release, etc. AI functions may also be referred to as AI (related) operations, or AI-related functions.

[0174] The following is an exemplary description of the implementation process of the neural network with reference to the accompanying drawings.

[0175] 1. Fully connected neural network.

[0176] Also known as a multilayer perceptron (MLP), an MLP consists of an input layer (left), an output layer (right), and multiple hidden layers (center). Each layer of the MLP contains several nodes, called neurons. Neurons in adjacent layers are connected to each other.

[0177] Optionally, considering neurons in two adjacent layers, the output h of a neuron in the next layer is the weighted sum of all neurons x connected to it in the previous layer and passes through an activation function, which can be expressed as: h=f(wx+b).

[0178] Among them, w is the weight matrix, b is the bias vector, and f is the activation function.

[0179] Alternatively, the output of the neural network can be recursively expressed as: y = f n (w n f n-1 (…)+b n ).

[0180] Where n is the index of the neural network layer, 1<=n<=N, where N is the total number of neural network layers.

[0181] In other words, a neural network can be understood as a mapping from an input data set to an output data set. Neural networks are typically initialized randomly, and the process of obtaining this mapping from random w and b using existing data is called neural network training.

[0182] Optionally, the specific training method is to use a loss function to evaluate the output of the neural network. As shown in Figure 2b, the error can be backpropagated, and the neural network parameters (including w and b) can be iteratively optimized through gradient descent until the loss function reaches a minimum value, i.e., the "better point (e.g., optimal point)" in Figure 2b. It is understandable that the neural network parameters corresponding to the "better point (e.g., optimal point)" in Figure 2b can be used as the neural network parameters in the trained AI model information.

[0183] Alternatively, the gradient descent process can be expressed as:

[0184] Among them, θ is the parameter to be optimized (including w and b), L is the loss function, and η is the learning rate, which controls the step size of gradient descent. represents the derivative operation, represents the derivative of θ with respect to L.

[0185] Alternatively, the backpropagation process can utilize the chain rule for partial derivatives. As shown in Figure 2c, the gradient of the previous layer parameters can be recursively calculated from the gradient of the next layer parameters, which can be expressed as:

[0186] Among them, w ij is the weight of node j connecting to node i, s i is the weighted sum of the inputs to node i.

[0187] 2. Federated Learning (FL)

[0188] The concept of federated learning effectively addresses the current challenges facing AI development. While fully protecting user data privacy and security, it enables collaboration between edge devices and central servers to efficiently complete model learning tasks. As shown in Figure 2d, the FL architecture is the most widely used training architecture in the FL field. The FedAvg algorithm is the foundation of FL. Its algorithmic process is roughly as follows:

[0189] (1) The center initializes the model to be trained And broadcast it to all client devices.

[0190] (2) In the round t∈[1,T], client k∈[1,K] based on the local dataset For the received global model Perform E epochs of training to obtain local training results Report it to the central node.

[0191] (3) The central node aggregates and collects the local training results from all (or some) clients. Assume that the client set that uploads the local model in round t is The center will use the number of samples of the corresponding client as the weight to perform weighted averaging to obtain a new global model. The specific update rule is: The center then sends the latest version of the global model Broadcast to all client devices for a new round of training.

[0192] (4) Repeat steps (2) and (3) until the model finally converges or the number of training rounds reaches the upper limit.

[0193] In addition to reporting local models You can also use the local gradient of training After reporting, the central node averages the local gradients and updates the global model according to the direction of the average gradient.

[0194] As you can see, in the FL framework, datasets exist on distributed nodes. Distributed nodes collect local datasets, perform local training, and report the local training results (models or gradients) to the central node. The central node itself does not have a dataset; it is only responsible for fusing the training results of distributed nodes to obtain a global model and send it to the distributed nodes.

[0195] 3. Decentralized learning.

[0196] Different from federated learning, another distributed learning architecture, decentralized learning, is shown in Figure 2e. Considering a fully distributed system without a central node, the design goal f(x) of a decentralized learning system is generally the goal f of each node. i The mean of (x), that is Where n is the number of distributed nodes, x is the parameter to be optimized. In machine learning, x is the parameter of the machine learning (such as neural network) model. Each node uses local data and local target f i (x) Calculate local gradient Then it is sent to the neighboring nodes that can be communicated with. After any node receives the gradient information sent by its neighbor, it can update the parameter x of the local model according to the following formula:

[0197] in, represents the parameters of the local model after the k+1th (k is a natural number) update in the i-th node, Represents the parameters of the local model after the kth update in the i-th node (if k is 0, it means is the parameter of the local model of the i-th node that does not participate in the update), α k Represents the tuning coefficient, N i is the set of neighbor nodes of node i, |N i | represents the number of elements in the neighbor node set of node i, that is, the number of neighbor nodes of node i. Through information interaction between nodes, the decentralized learning system will eventually learn a unified model.

[0198] The technical solutions provided in this application can be applied to wireless communication systems (e.g., the systems shown in Figures 1a and 1b). In wireless communication systems, communication nodes generally have both signal transceiver capabilities and computing capabilities. For example, network devices with computing capabilities primarily provide computing power to support signal transceiver capabilities (e.g., calculating the time and frequency domain resources that carry the signal), thereby enabling communication between the network device and other communication nodes.

[0199] However, in communication networks, communication nodes may have excess computing power beyond just supporting the aforementioned communication tasks. Therefore, how to utilize this computing power is a pressing technical issue.

[0200] As an example, to meet the vision of intelligent and inclusive future, intelligence is likely to evolve further at the wireless network architecture level. In future communication systems, AI will likely be further integrated with wireless networks, enabling inherent network intelligence and terminal intelligence. For example, the integration of AI and wireless networks can be applied to the following new demands and scenarios: For example, more flexible and intelligent terminal connectivity, including but not limited to diverse terminal types, the Super Internet of Things (Supper IoT) (e.g., Supper IoT can include IoT, connected vehicles, industrial, and medical), massive connectivity, more flexible terminal connectivity, and terminals with inherent AI capabilities. Another example is inherent network intelligence: in addition to traditional communication connectivity services, the network will also provide computing and AI services to better support inclusive, real-time, and highly secure AI services. These new demands and scenarios will bring about changes in wireless network architecture and communication models.

[0201] Generally, participating nodes in AI learning can include nodes in multiple distributed communication networks, such as terminal devices and network devices. In current learning architectures (such as those shown in Figure 2d or Figure 2e), it is assumed that the learning system has been constructed. That is, all participating nodes are oriented towards the same learning task and jointly train a global machine learning model. However, current research does not discuss the construction of the learning system, that is, how to aggregate nodes oriented towards the same learning task to complete the AI ​​learning task.

[0202] In order to solve the above problems, the present application provides a communication method and related equipment for enabling the computing power of communication nodes to be applied to artificial intelligence (AI) learning, and to realize AI model processing based on AI data feature matching.

[0203] Please refer to FIG3 , which is a schematic diagram of an implementation of the communication method provided in this application. The method includes the following steps.

[0204] It should be noted that, in FIG3 , the method is illustrated by taking the first node and the second node as the execution subjects of the interactive diagram as an example, but the present application does not limit the execution subjects of the interactive diagram. For example, the first node involved in S301 in FIG3 and the corresponding implementation method can also be replaced by a chip, chip system, or processor that supports the first node to implement the method, or a logic module or software that can realize all or part of the functions of the first node. The second node involved in S301 in FIG3 and the corresponding implementation method can also be replaced by a chip, chip system, or processor that supports the second node to implement the method, or a logic module or software that can realize all or part of the functions of the second node. Among them, the first node can be a terminal device or a network device, and the second node can also be a terminal device or a network device.

[0205] S301. A second node sends first information, and a first node receives the first information accordingly, wherein the first information is used to indicate a first AI model.

[0206] In this application, AI model can be replaced by neural network, AI neural network, neural network model, AI neural network model, machine learning model, etc.

[0207] It should be understood that in step S301, the first information received by the first node is used to indicate the first AI model, which can be understood as: the first information includes the index of the first AI model, so that the recipient of the first information (i.e., the first node) can obtain the first AI model based on the index; or, the first information includes the first AI model, so that the recipient of the first information (i.e., the first node) can obtain the first AI model from the first information.

[0208] It should be understood that the AI ​​models involved in this application can be applied to AI tasks. In other words, the execution process of the AI ​​task includes the processing of one or more AI models by a communication node. The AI ​​task can be a task that requires two or more communication nodes (such as a first node and a second node, etc.) to participate in the processing. The communication nodes include terminal devices and / or network devices. For example, the AI ​​task can include a federated learning (FL) task, a distributed training task, a distributed learning task, etc.

[0209] Optionally, the first node and the second node may be communication nodes participating in the AI ​​task, wherein the first node and the second node are neighboring nodes, i.e., the first node and the second node are mutually reachable nodes. In step S301, the second node sends the first information to the first node, i.e., the second node may be the previous hop node of the first node, in other words, the first node may be the next hop node of the second node.

[0210] S302. The first node processes the first AI model based on local data to obtain a second AI model, wherein the AI ​​data features of the local data meet the AI ​​data features corresponding to the processing requirements of the first AI model.

[0211] It should be understood that AI data may refer to data related to AI, and AI data features may be used to indicate characteristics (or properties, characteristics, attributes, or properties) of AI-related data. In step S302, the AI ​​data features of the local data of the first node satisfy the AI ​​data features corresponding to the processing requirements of the first AI model, which can be understood as at least one of the following:

[0212] ①. The AI ​​data features corresponding to the processing requirements of the first AI model are a subset of the AI ​​data features of the local data of the first node;

[0213] ② The AI ​​data features of the local data of the first node are greater than or equal to the AI ​​data features corresponding to the processing requirements of the first AI model;

[0214] ③. The AI ​​data features of the local data of the first node include at least the AI ​​data features corresponding to the processing requirements of the first AI model;

[0215] ④. The AI ​​data features of the local data of the first node match / comply with the AI ​​data features corresponding to the processing requirements of the first AI model.

[0216] Exemplarily, the AI ​​data feature may include at least one of the following features 1 to 5.

[0217] Feature 1. The AI ​​task to which the AI ​​data is applied.

[0218] For feature 1, different AI tasks can be distinguished by different task identifications (IDs), where the task ID can be pre-configured or configured, which is not limited here.

[0219] For example, when the AI ​​data feature includes feature 1, as shown in FIG4a , the local data of node 0 and the local data of node 2 can both be applied to the AI ​​task with task ID 1 (represented as “AI data for task 1” in FIG4a ), and the local data of node 1 can be applied to the AI ​​task with task ID 2 (represented as “AI data for task 2” in FIG4a ). Furthermore, the AI ​​data feature corresponding to the processing requirements of the AI ​​model involved in the model transfer process is the AI ​​data with task ID 1, that is, the AI ​​model involved in the model transfer process can be the AI ​​model involved in the AI ​​task with task ID 1.

[0220] It should be understood that the model transfer process shown in Figure 4a can be an implementation example of step S301, that is, node 1 can determine the first AI model through the model transfer process. In other words, in the example shown in Figure 4a, the first node can be node 1 in the diagram and the second node can be node 0 in the diagram, or the first node can be node 2 in the diagram and the second node can be node 1 in the diagram.

[0221] In the example shown in Figure 4a, for node 0, if node 0 determines that the AI ​​tasks applied to local data include at least the AI ​​tasks corresponding to the processing requirements of the AI ​​model, node 0 can determine that the AI ​​data features of node 0's local data meet the AI ​​data features corresponding to the processing requirements of the AI ​​model (denoted as "AI data feature matching" in the figure). Thus, node 0 can process the received AI model (i.e., the processing process in step S302) and send the processing results to node 1 through the model transfer process.

[0222] In the example shown in Figure 4a, for node 1, if node 1 determines that the AI ​​task applied to the local data is different from the AI ​​task corresponding to the processing requirement of the AI ​​model, node 1 can determine that the AI ​​data characteristics of node 1's local data do not meet the AI ​​data characteristics corresponding to the processing requirement of the AI ​​model (denoted as "AI data characteristic mismatch" in the figure). Therefore, node 1 can discard or ignore the received AI model or transmit it to the next hop node (such as node 2 in Figure 4a).

[0223] Optionally, in the example shown in Figure 4a, node 0 and node 1 are neighbor nodes to each other (i.e., nodes that can communicate with each other), node 1 and node 2 are neighbor nodes to each other (i.e., nodes that can communicate with each other), and node 0 and node 2 are not neighbor nodes to each other (i.e., node 0 and node 2 are not reachable). In other words, node 0 and node 2 can communicate through node 1, and node 1 can be regarded as a relay node for node 0 and node 2. In this case, when node 1 determines that the AI ​​data features do not match, the node 1 may not perform the model processing process. In addition, the node 1 can act as a relay node to perform the model interaction process, that is, forwarding the AI ​​model from node 0 (or indication information for indicating the AI ​​model) to node 2, so that node 2 can obtain the AI ​​model corresponding to the AI ​​data of task 1 through the model transmission process and perform subsequent processing.

[0224] In the example shown in FIG4a , for node 2, after node 2 determines the AI ​​model through the model transfer process, if node 2 determines that the AI ​​tasks applied to the local data include at least the AI ​​tasks corresponding to the processing requirements of the AI ​​model, node 2 can determine that the AI ​​data features of node 2's local data meet the AI ​​data features corresponding to the processing requirements of the AI ​​model (denoted as "AI data feature matching" in the figure). Thus, node 2 can process the received AI model (i.e., the processing process in step S302).

[0225] Optionally, the node 2 may also transmit the processed AI model so that the next hop node of the node 2 determines the processed AI model.

[0226] Feature 2. The object to which AI data belongs.

[0227] For Feature 2, different AI data objects can be distinguished by different object IDs. Object IDs can be pre-configured or configured, and are not limited here. For example, different AI data objects can be distinguished by the different objects to which the AI ​​data corresponds, including AI data for Object 1 and AI data for Object 2. The AI ​​data for Object 1 and the AI ​​data for Object 2 can be AI data from different industries. For example, the AI ​​data for Object 1 and the AI ​​data for Object 2 can be any two different pieces of AI data, such as AI data from the medical industry, AI data from the education industry, or AI data from the financial industry.

[0228] For example, when the AI ​​data feature includes feature 2, as shown in FIG4b , the local data of node 0 and the local data of node 2 may both include data with an object identifier of object 1 (denoted as "AI data of object 1" in FIG4b ), and the local data of node 1 may include data with an object identifier of object 2 (denoted as "AI data of object 2" in FIG4b ). Furthermore, the AI ​​data feature corresponding to the processing requirements of the AI ​​model involved in the model transfer process is the AI ​​data of object 1, that is, the AI ​​model involved in the model transfer process needs to be processed using the AI ​​data of object 1.

[0229] It should be understood that the model transfer process shown in Figure 4b can be an implementation example of step S301, that is, node 1 can determine the first AI model through the model transfer process. In other words, in the example shown in Figure 4b, the first node can be node 1 in the diagram and the second node can be node 0 in the diagram, or the first node can be node 2 in the diagram and the second node can be node 1 in the diagram.

[0230] In the example shown in Figure 4b, for node 0, if node 0 determines that the objects to which the local data belongs include at least the objects corresponding to the processing requirements of the AI ​​model, node 0 can determine that the AI ​​data features of node 0's local data meet the AI ​​data features corresponding to the processing requirements of the AI ​​model (denoted as "AI data feature matching" in the figure). Thus, node 0 can process the received AI model (i.e., the processing process in step S302) and send the processing results to node 1 through the model transfer process.

[0231] In the example shown in Figure 4b, for node 1, if node 1 determines that the object to which the local data belongs is different from the object corresponding to the AI ​​model's processing requirements, node 1 can determine that the AI ​​data characteristics of node 1's local data do not meet the AI ​​data characteristics corresponding to the AI ​​model's processing requirements (denoted as "AI data characteristic mismatch" in the figure). Consequently, node 1 can discard or ignore the received AI model or transmit it to the next hop node (e.g., node 2 in Figure 4b).

[0232] Optionally, in the example shown in Figure 4b, node 0 and node 1 are neighbor nodes to each other (i.e., nodes that can communicate with each other), node 1 and node 2 are neighbor nodes to each other (i.e., nodes that can communicate with each other), and node 0 and node 2 are not neighbor nodes to each other (i.e., node 0 and node 2 are not reachable). In other words, node 0 and node 2 can communicate through node 1, and node 1 can be regarded as a relay node for node 0 and node 2. In this case, when node 1 determines that the AI ​​data features do not match, the node 1 may not perform the model processing process. In addition, the node 1 can act as a relay node to perform the model interaction process, that is, forwarding the AI ​​model from node 0 (or indication information for indicating the AI ​​model) to node 2, so that node 2 can obtain the AI ​​model corresponding to the AI ​​data of type 1 through the model transmission process and perform subsequent processing.

[0233] In the example shown in Figure 4b, for node 2, after determining the AI ​​model through the model transfer process, node 2 determines that the objects to which the local data belongs include at least the objects corresponding to the processing requirements of the AI ​​model. Node 2 can then determine that the AI ​​data features of node 2's local data meet the AI ​​data features corresponding to the processing requirements of the AI ​​model (denoted as "AI data feature matching" in the figure). Consequently, node 2 can process the received AI model (i.e., the processing process in step S302).

[0234] Optionally, the node 2 may also transmit the processed AI model so that the next hop node of the node 2 determines the processed AI model.

[0235] Feature 3. Geographic location information for collecting AI data.

[0236] For Feature 3, different geographic locations for collecting AI data can be distinguished by different geographic location identifiers. These different geographic location identifiers can be pre-configured or configured, and are not limited here. For example, different geographic location identifiers can be distinguished by the different locations where the AI ​​data was collected, including GPS information, indoor / outdoor information, LOS scenario / NLOS scenario information, etc.

[0237] In one implementation example, a possible requirement is to process the AI ​​model based on data from a certain geographic region to obtain an AI model applicable to that region. In this case, the geographic region can be set as feature 3.

[0238] In another implementation example, one possible requirement is to process the AI ​​model based on data from different geographical regions to obtain an AI model with better generalization and applicable to multiple geographical regions. In this case, multiple geographical regions can be set as feature 3.

[0239] Feature 4. Time information of collecting AI data.

[0240] For Feature 4, different time information for collecting AI data can be distinguished by different time information identifiers. The different time information identifiers can be pre-configured or configured, and are not limited here. For example, different time information identifiers can be distinguished by different AI data collection times, including specific time periods, daytime / nighttime, weekdays / holidays, etc.

[0241] In one implementation example, a possible requirement is to process the AI ​​model based on data from a certain time period to obtain an AI model applicable to that time period. In this case, the time period can be set as feature 4.

[0242] In another implementation example, one possible requirement is to process the AI ​​model based on data from different time periods to obtain an AI model with better generalization and applicable to multiple time periods. In this case, multiple time periods can be set as feature 4.

[0243] Feature 5. Number of samples of AI data.

[0244] For feature 5, the number of samples of AI data can be distinguished by different sample number identifiers, where the different sample number identifiers can be pre-configured or configured, which is not limited here.

[0245] It should be noted that two or more of Features 1 to 5 can be used in combination.

[0246] For example, when feature 1 and feature 2 are used in combination, the AI ​​data features of the local data of the first node meet the AI ​​data features corresponding to the processing requirements of the first AI model, including: the AI ​​task applied to the local data of the first node and the AI ​​task corresponding to the processing requirements of the AI ​​model are the same AI task, and the object to which the local data of the first node belongs and the object corresponding to the processing requirements of the AI ​​model are the same object.

[0247] For another example, when feature 1 and feature 5 are combined, the AI ​​data features of the local data of the first node satisfy the AI ​​data features corresponding to the processing requirements of the first AI model, including: the AI ​​tasks applied to the local data of the first node include at least AI tasks corresponding to the processing requirements of the AI ​​model, and the number of samples of the local data of the first node is greater than or equal to the number of samples corresponding to the processing requirements of the AI ​​model.

[0248] In one possible implementation, the first node processes the first AI model based on local data to obtain the second AI model, including: performing at least one of training, distillation, and fusion processing on the first AI model based on the local data to obtain the second AI model. Specifically, the first node may perform at least one of the above processing on the first AI model based on the local data to enhance the flexibility of solution implementation.

[0249] Based on the technical solution shown in Figure 3, the first information received by the first node in step S301 is used to indicate the first AI model. Thereafter, in step S302, the first node processes the first AI model based on local data to obtain a second AI model. The AI ​​data features of the local data of the first node meet the AI ​​data features corresponding to the processing requirements of the first AI model. In other words, the first node acts as a communication node in the communication system, and the AI ​​data features corresponding to the processing requirements of the first AI model processed by the first node match the AI ​​data features of the local data of the first node. Thus, when the communication node in the communication system acts as a node participating in the AI ​​model processing, the computing power of the communication node can be applied to the AI ​​model processing process in the AI ​​learning system, in order to realize the AI ​​model processing process in the communication network.

[0250] In addition, the AI ​​data features of the local data of the first node meet the AI ​​data features corresponding to the processing requirements of the first AI model processed by the first node, so that the first node can process the AI ​​model that matches the AI ​​data features of the local data. Correspondingly, the AI ​​model can also be processed by the node that meets the processing requirements, thereby realizing AI model processing based on AI data feature matching.

[0251] In the technical solution shown in Figure 3, the first node can determine the AI ​​data characteristics corresponding to the processing requirements of the first AI model in a variety of ways, such as through pre-configuration or through instructions from other devices.

[0252] For example, in one possible implementation, before the first node processes the first AI model based on local data in step S302, the method may further include: the first node receiving fourth information, where the fourth information is used to indicate AI data features corresponding to the processing requirements of the first AI model (for example, the fourth information may be used to indicate at least one of features 1 to 5 described above). Specifically, the first node may also receive fourth information indicating the AI ​​data features corresponding to the processing requirements of the first AI model, so that the first node can determine, based on the fourth information, whether the AI ​​data features of the first node's local data meet the AI ​​data features required for processing the AI ​​model, and thereby determine to process the second AI model.

[0253] Optionally, the fourth information may come from the second node, or the fourth information may come from the central node mentioned later, or the fourth information may come from other adjacent nodes of the first node, which is not limited here.

[0254] Optionally, taking the above-mentioned fourth information coming from the second node as an example, the first information in step S301 and the above-mentioned fourth information can be carried in the same message / signaling / information, or in different messages / signaling / information, which is not limited here.

[0255] As an implementation example, taking the example that the first information in step S301 and the fourth information described above can be carried in the same message / signaling / information, as shown in Figure 5, the interaction process between node 0, node 1, and node 2 is still used as an example for explanation. As can be seen from the foregoing description, the first node is the next hop node of the second node, that is, the first node can be node 1 in Figure 5 and the second node can be node 0 in Figure 5, or the first node can be node 2 in Figure 5 and the second node can be node 1 in Figure 5.

[0256] For example, in Figure 5, when node 1 serves as the first node, node 1 can receive first information and fourth information from node 0 through the model interaction process of step ①, where the first information indicates the first AI model, and the fourth information indicates the AI ​​data features corresponding to the processing requirements of the first AI model. Furthermore, if node 1 determines in step ② that the AI ​​data features of node 1's local data do not meet the AI ​​data features corresponding to the processing requirements of the AI ​​model (denoted as "AI data feature mismatch" in the figure), node 1 can determine not to process the first AI model, that is, node 1 may not execute step S302.

[0257] Optionally, in the example shown in Figure 5, node 0 and node 1 are neighbor nodes to each other (i.e., nodes that can communicate with each other), node 1 and node 2 are neighbor nodes to each other (i.e., nodes that can communicate with each other), and node 0 and node 2 are not neighbor nodes to each other (i.e., node 0 and node 2 are not reachable). In other words, node 0 and node 2 can communicate through node 1, and node 1 can be regarded as a relay node for node 0 and node 2. In which case, if node 1 does not execute step S302, node 1 can act as a relay node to execute the model interaction process, that is, forwarding the AI ​​model from node 0 (or indication information for indicating the AI ​​model) to node 2, so that node 2 can obtain the AI ​​model through step ③ and perform subsequent processing.

[0258] For another example, in Figure 5, when node 2 serves as the first node, node 2 can receive first information and fourth information from node 1 through the model interaction process in step ③. The first information indicates the first AI model, and the fourth information indicates the AI ​​data features corresponding to the processing requirements of the first AI model. Furthermore, if node 2 determines in step ④ that the AI ​​data features of node 2's local data meet the AI ​​data features corresponding to the processing requirements of the AI ​​model (denoted as "AI data feature matching" in the figure), node 2 can process the first AI model in step ⑤, that is, node 2 can execute step S302.

[0259] In addition, for the first node, after step S302, the method further includes: the first node sends fourth information and / or fifth information (for example, the fifth information can be used to indicate at least one of the above-mentioned features 1 to 5), the fourth information is used to indicate the AI ​​data features corresponding to the processing requirements of the first AI model, and the fifth information is used to indicate the AI ​​data features corresponding to the processing requirements of the second AI model. Specifically, the first node may also send fourth information for indicating the AI ​​data features corresponding to the processing requirements of the first AI model, and / or the first node may also send fifth information for indicating the AI ​​data features corresponding to the processing requirements of the second AI model. This enables the recipient of the fourth information and / or the fifth information to clearly identify the AI ​​data features corresponding to the processing requirements of the AI ​​model. Subsequently, the recipient can determine whether the AI ​​data features of the recipient's local data meet the AI ​​data features of the processing requirements of the AI ​​model based on the fourth information and / or the fifth information, and then determine whether to process the second AI model.

[0260] In another possible implementation of the technical solution shown in FIG. 3 , in step S301, the process of the first node receiving the first information may include: the first node receiving the first information based on second information, where the second information is used to indicate transmission information of the AI ​​model. Specifically, the first node may receive the first information indicating the first AI model based on the second information, where the second information is used to indicate transmission information of the AI ​​model, so that the first node can implement transmission of the AI ​​model based on the second information.

[0261] Optionally, the transmission information includes at least one of the following:

[0262] Information A: The node identifier of the node sending the first AI model. For the first node, the first AI model comes from the previous-hop node. Therefore, Information A can also be expressed as the node identifier, index, or number of the previous-hop node. In other words, based on Information A, the first node can determine to receive the first information indicating the first AI model from the node corresponding to the node identifier.

[0263] Information B. Node identifier of the node receiving the second AI model. For the first node, after determining the second AI model in step S302, the first node may also send indication information indicating the second AI model (e.g., the third information mentioned below). Accordingly, the recipient of the second AI model is the next-hop node of the first node. Therefore, information B may also be expressed as the node identifier, index, or number of the next-hop node. In other words, based on information B, the first node may determine to send indication information indicating the second AI model to the node corresponding to the node identifier.

[0264] Information C. Identification of the AI ​​task corresponding to the first AI model and / or the second AI model.

[0265] Information D. Identification of the first AI model.

[0266] Information E. Identification of the second AI model.

[0267] Information F: The processing method for processing the first AI model is at least one of training, distillation, and fusion. In other words, the first node may determine the processing method for processing the first AI model in step S302 based on information F.

[0268] Information G. The processing method of processing the second AI model is at least one of training processing, distillation processing and fusion processing.

[0269] Information H. Indication information indicating a non-relay node, or indication information indicating a relay node. Among them, the first node participated in the AI ​​model processing in step S302, and accordingly, the first node is not a relay node, that is, the first node can determine that the node role of the first node is not a relay node based on the information H. Exemplarily, taking Figures 4a and 4b as an example, node 1 determines that the AI ​​data features do not match, but the node 1 can transmit the received AI model to the next hop node. In this case, for node 1, the information H determined by node 1 indicates that node 1 is a relay node, and accordingly, node 1 can transmit the AI ​​model to the next hop node based on the information H.

[0270] Optionally, the above-mentioned transmission information may further include the fourth information and / or fifth information described above.

[0271] In one possible implementation, in the technical solution shown in FIG3 , the method further includes: the first node sending third information based on the second information, where the third information is used to indicate the second AI model. Specifically, after the first node processes the first AI model based on local data to obtain the second AI model, the first node may further send third information indicating the second AI model based on the second information, so that the recipient of the third information (i.e., the first node's next-hop node) can further process the second AI model.

[0272] It should be noted that, for the first node, the first node can determine the second information in a variety of ways, which will be introduced below respectively.

[0273] In implementation example 1, the first node obtains the second information by receiving the second information.

[0274] Specifically, in implementation example 1, the first node may obtain the second information through the implementation process shown in FIG6a , as shown in FIG6a , including the following steps.

[0275] S601. A first node sends its node information, and a central node receives the node information accordingly, wherein the node information is used to indicate AI data features of local data of the first node.

[0276] S602: The central node sends second information, and the first node receives the second information accordingly, wherein the second information is used to indicate the transmission information of the AI ​​model.

[0277] S603. The second node sends the first information, and correspondingly, the first node receives the first information.

[0278] S604. The first node processes the first AI model based on local data to obtain a second AI model.

[0279] The implementation process of step S603 and step S604 may refer to the implementation process of step S301 and step S302 above.

[0280] Based on the technical solution shown in Figure 6, the first node obtains the second information by receiving the second information in step S602, that is, the first node can determine the second information through scheduling instructions from other nodes (such as the central node) to reduce the implementation complexity of the first node.

[0281] Optionally, the other node can serve as a central node (or control node, management node, etc.) in the learning architecture where the first node is located, so that the solution can be adapted to a learning architecture with a central node (or control node, management node, etc.).

[0282] In addition, in the technical solution shown in Figure 6, before step S603, the second node may also send the node information of the second node to the central node (not shown in Figure 6), so that the central node can determine the second information based on the node information of the first node and the node information of the second node. Accordingly, the central node may also send the transmission information of the AI ​​model transmitted by the second node to the second node. In other words, the one or more node information received by the central node is used to indicate the AI ​​data characteristics of one or more nodes. The central node can determine the transmission information of the AI ​​model based on the one or more node information. Thereafter, the central node can send the second information for indicating the transmission information, so that the recipient of the second information can transmit the AI ​​model based on the second information. Thus, the central node determines that the transmission information of the AI ​​model is based on the AI ​​data characteristics of one or more nodes, so that the communication node can process the AI ​​model that matches the AI ​​data characteristics of the local data. Accordingly, the AI ​​model can also be processed by the node that meets the processing requirements, thereby realizing AI model processing based on AI data feature matching.

[0283] As an application example of implementation example 1, as shown in Figure 6b, the interaction process between nodes 0, 1, and 2 is still used as an example for description. As can be seen from the previous description, the first node is the next hop node of the second node, that is, the first node can be node 1 in Figure 6b and the second node can be node 0 in Figure 6b, or the first node can be node 2 in Figure 6b and the second node can be node 1 in Figure 6b.

[0284] In Figure 6b, each distributed node (including node 0, node 1, and node 2) sends node information (i.e., the node information involved in Figure 6a, including the node information of the first node, the node information of the second node, etc.) to the central node in step 1. Thereafter, the central node can send second information to each distributed node in step 2 based on the node information of each distributed node received in step 1. Subsequently, each distributed node can perform model interaction in step 3 based on the second information.

[0285] It should be noted that in Figure 6b, each distributed node reports the AI ​​data features of the local data. The central node selects the node where the AI ​​model is located (for example, node 0 and node 2 in Figure 6b) and determines the model transmission path according to the information reported by each distributed node. When the communication between the two nodes participating in the model processing is unreachable, a relay node is determined for them (such as node 1 in Figure 6b). In other words, in the second information sent by the central node to node 0 and node 2, information H indicates that node 0 and node 2 are not relay nodes; and in the second information sent by the central node to node 1, information H indicates that node 1 is a relay node.

[0286] It should be understood that the central node can determine the transmission information of the one or more nodes transmitting the AI ​​model based on the AI ​​data characteristics of the one or more nodes. The second information sent by the central node can be used to indicate the transmission information of the one or more nodes transmitting the AI ​​model, that is, the second information received by the first node and the second node can be the same information. Alternatively, the central node can send one or more second information, and the one or more second information are respectively used to indicate the transmission information of the one or more nodes transmitting the AI ​​model, that is, the second information received by the first node and the second node can be different information. Accordingly, the recipient of the second information can include the one or more nodes (for example, the one or more nodes can include the first node). The central node can be the central node (or control node, management node, etc.) in the learning architecture where the one or more nodes are located, so that the solution can be adapted to the learning architecture with a central node (or control node, management node, etc.).

[0287] In implementation example 2, the first node obtains the second information by locally determining the second information.

[0288] Specifically, in implementation example 2, the first node may obtain the second information through the implementation process shown in FIG7 , which includes the following steps.

[0289] S701. A second node sends node information of the second node, and correspondingly, a first node receives the node information of the second node, wherein the node information is used to indicate AI data features of local data of the second node.

[0290] S702. The first node determines second information based on node information of neighboring nodes. The second information is used to indicate transmission information of the AI ​​model. In addition, for the first node, the neighboring nodes include at least the second node, that is, before step S702, the first node may also receive one or more neighboring node information, the one or more neighboring node information being used to indicate AI data features of one or more neighboring nodes, the one or more neighboring nodes including at least the second node; thereafter, the first node determines the second information based on the one or more neighboring node information in step S702.

[0291] It should be understood that in the technical solution shown in Figure 7, the first node may also send node information of the first node to the second node, where the node information is used to indicate the AI ​​data characteristics of the first node's local data. In other words, the second node may also receive one or more neighbor node information, where the one or more neighbor node information is used to indicate the AI ​​data characteristics of one or more neighbor nodes, where the one or more neighbor nodes include at least the first node. Thereafter, the second node may determine second information based on the one or more neighbor node information, so that the second node can execute the transmission of the AI ​​model based on the determined second information.

[0292] As an implementation example of step S702, the first node may determine the content shown in the following Table 2 based on the node information of the neighboring nodes.

[0293] Table 2

[0294] It should be understood that in Table 2, the node ID of the second node can be any one of neighbor node ID1 to neighbor node ID1n described above. Among the n nodes corresponding to neighbor node ID1 to neighbor node ID1n, each neighbor node can have one or more local data. Accordingly, the node information of each neighbor node received by the first node can include one or more AI data features corresponding to the one or more local data (e.g., one or more local data have a one-to-one correspondence with one or more AI data features).

[0295] In Table 2, neighbor node ID1 may have k copies of local data, and the k copies of local data respectively correspond to the AI ​​data features corresponding to identifier 1 to the AI ​​data features corresponding to identifier k; neighbor node IDn may have m copies of local data, and the m copies of local data respectively correspond to the AI ​​data features corresponding to identifier 1 to the AI ​​data features corresponding to identifier m. Any identifier in Table 2 (e.g., any identifier from identifier 1 to identifier k corresponding to neighbor node ID1, or any identifier from identifier 1 to identifier m corresponding to neighbor node IDn) may be an identifier of an AI model (e.g., information D and / or E), an identifier of a task applied by the AI ​​model (e.g., information C), a processing method corresponding to the AI ​​model (e.g., information F and / or information G), etc.

[0296] As shown in Table 2, the first node can construct a neighbor information table as shown in Table 2 based on the node information of the neighboring nodes to record the AI ​​data features of the neighboring nodes. Subsequently, when the first node sends or receives an AI model, it can determine the transmission information of the AI ​​model by looking up the table. For example, the first node can determine at least one of information C, information D, information E, information F, and information G based on any identifier in Table 2. For another example, the first node can determine that it can receive the first AI model from the corresponding node (i.e., determine information A - the node identifier of the node sending the first AI model) and determine that it can send the second AI model to the corresponding node (i.e., determine information B - the node identifier of the node receiving the second AI model) based on the AI ​​data features corresponding to each neighbor node ID in Table 2 and the AI ​​data features of the first node's local data.

[0297] Optionally, the first node may determine other information beyond the information included in Table 2 based on the node information of the neighboring nodes. For example, it may also include other neighbor node information of one or more neighboring nodes. Taking the second node as neighbor node ID1 as an example, the node information sent by the second node to the first node may also include node information of neighboring nodes with which the second node can communicate.

[0298] For ease of description, the neighboring nodes that the second node can communicate with include a third node as an example. In the following example, the third node is not a neighboring node of the first node, that is, the communication between the first node and the third node is unreachable, but the two can communicate through a relay node (such as the second node). The second node can send the node information of the third node to the first node, and the node information of the third node is used to indicate the AI ​​data characteristics of the local data of the third node. Thereafter, for the first node, if the first node determines that the AI ​​data characteristics of the n neighboring nodes of the first node (including neighboring node ID1 to neighboring node IDn in Table 2) do not match the AI ​​data characteristics of the first node, the first node may not be able to interact with the AI ​​model of the n neighboring nodes. To this end, the first node can participate in the interaction of the AI ​​model based on the node information of the neighboring nodes that are reachable by the n neighboring nodes. For example, the first node can interact with the AI ​​model of the third node through the second node. At this time, the second node can determine that the second node is a relay node (that is, information H indicates that the second node is a relay node).

[0299] As an implementation example of step S702, the first node may determine the content shown in the following Table 3 based on the node information of the neighboring nodes.

[0300] Table 3

[0301] As shown in Table 3, the first node can construct a model routing table as shown in Table 3 based on the node information of neighboring nodes to record the previous hop node and next hop node information of each target AI model. When the first node receives or sends an AI model, it can determine the transmission information of the AI ​​model based on Table 3 by looking up the table. It should be understood that the implementation process of the first node determining information A to information H based on Table 3 can refer to the implementation process of the first node determining information A to information H based on Table 2 mentioned above.

[0302] S703. The second node sends the first information, and correspondingly, the first node receives the first information.

[0303] S704. The first node processes the first AI model based on local data to obtain a second AI model.

[0304] The implementation process of step S703 and step S704 may refer to the implementation process of step S301 and step S302 above.

[0305] Based on the technical solution shown in Figure 7, the first node can receive one or more neighbor node information indicating AI data characteristics of one or more neighbor nodes, and determine the second information based on the one or more neighbor node information. That is, the first node can locally determine the second information based on the received (or collected) one or more neighbor node information. Optionally, the first node can locally determine the transmission information of the AI ​​model, making the solution adaptable to a decentralized learning architecture.

[0306] Referring to Figure 8, an embodiment of the present application provides a communication device 800, which can implement the functions of the first node or central node (the first node or central node is a terminal device or a network device) in the above method embodiment, and thus can also achieve the beneficial effects possessed by the above method embodiment. In the embodiment of the present application, the communication device 800 can be the first node (or central node), or it can be an integrated circuit or component inside the first node (or central node), such as a chip. The following embodiments are described by taking the communication device 800 as the first node (or central node) as an example.

[0307] It should be noted that the transceiver unit 802 may include a sending unit and a receiving unit, which are respectively used to perform sending and receiving.

[0308] In one possible implementation, when the device 800 is used to execute the method executed by the first node in any of the aforementioned embodiments, the device 800 includes a processing unit 801 and a transceiver unit 802; the transceiver unit 802 is used to receive first information, and the first information is used to indicate a first artificial intelligence AI model; the processing unit 801 is used to process the first AI model based on local data to obtain a second AI model; wherein the AI ​​data features of the local data meet the AI ​​data features corresponding to the processing requirements of the first AI model.

[0309] In one possible implementation, the transceiver unit 802 is used to receive the first information, including: the transceiver unit 802 is specifically used to receive the first information based on second information, and the second information is used to indicate transmission information of the AI ​​model.

[0310] In a possible implementation, the transceiver unit 802 is further configured to receive the second information.

[0311] In one possible implementation, the transceiver unit 802 is further used to receive one or more neighbor node information, where the one or more neighbor node information is used to indicate AI data features of one or more neighbor nodes; the processing unit 801 is further used to determine the second information based on the one or more neighbor node information.

[0312] In a possible implementation, the transceiver unit 802 is further configured to send third information based on the second information, where the third information is configured to indicate the second AI model.

[0313] In one possible implementation, the transceiver unit 802 is further used to send fourth information and / or fifth information, where the fourth information is used to indicate the AI ​​data characteristics corresponding to the processing requirements of the first AI model, and the fifth information is used to indicate the AI ​​data characteristics corresponding to the processing requirements of the second AI model.

[0314] In one possible implementation, the transmission information includes at least one of the following:

[0315] The node identifier of the node that sends the first AI model;

[0316] Receive a node identifier of a node of the second AI model;

[0317] an identifier of the AI ​​task corresponding to the first AI model and / or the second AI model;

[0318] an identifier of the first AI model;

[0319] an identifier of the second AI model;

[0320] The first AI model is processed by at least one of a training process, a distillation process, and a fusion process;

[0321] The second AI model is processed by at least one of a training process, a distillation process, and a fusion process;

[0322] Indication information indicating a non-relay node.

[0323] In a possible implementation, the transceiver unit 802 is further used to receive fourth information, where the fourth information is used to indicate AI data features corresponding to the processing requirements of the first AI model.

[0324] In one possible implementation, the AI ​​data feature includes at least one of the following: the AI ​​task to which the AI ​​data is applied, the object to which the AI ​​data belongs, the geographical location information of where the AI ​​data is collected, the time information of where the AI ​​data is collected, and the number of samples of the AI ​​data.

[0325] In a possible implementation, the transceiver unit 802 is further configured to send indication information indicating an AI data feature of the local data.

[0326] In one possible implementation, the processing unit 801 is used to process the first AI model based on local data to obtain the second AI model, including: the processing unit 801 is specifically used to perform at least one of training processing, distillation processing and fusion processing on the first AI model based on the local data to obtain the second AI model.

[0327] In one possible implementation, when the device 800 is used to execute the method executed by the central node in any of the aforementioned embodiments, the device 800 includes a processing unit 801 and a transceiver unit 802; the transceiver unit 802 is used to receive one or more node information, and the one or more node information is used to indicate the AI ​​data characteristics of one or more nodes; the one or more node information is used to determine the transmission information of the AI ​​model; the processing unit 801 is used to determine the second information, and the second information is used to indicate the transmission information; the transceiver unit 802 is also used to send the second information.

[0328] In one possible implementation, the transmission information includes at least one of the following:

[0329] The node identifier of the node that sends the first AI model;

[0330] Receive a node identifier of a node of the second AI model;

[0331] an identifier of the AI ​​task corresponding to the first AI model and / or the second AI model;

[0332] an identifier of the first AI model;

[0333] an identifier of the second AI model;

[0334] The first AI model is processed by at least one of a training process, a distillation process, and a fusion process;

[0335] The second AI model is processed by at least one of a training process, a distillation process, and a fusion process;

[0336] Indication information indicating a non-relay node.

[0337] In one possible implementation, the AI ​​data feature includes at least one of the following: the AI ​​task to which the AI ​​data is applied, the object to which the AI ​​data belongs, the geographical location information of where the AI ​​data is collected, the time information of where the AI ​​data is collected, and the number of samples of the AI ​​data.

[0338] It should be noted that, for details on the information execution process of the units of the above-mentioned communication device 800, please refer to the description in the method embodiment shown above in this application, and no further details will be given here.

[0339] Please refer to Figure 9, which is another schematic structural diagram of a communication device 900 provided in this application. The communication device 900 includes a logic circuit 901 and an input / output interface 902. The communication device 900 may be a chip or an integrated circuit.

[0340] The transceiver unit 802 shown in FIG8 may be a communication interface, which may be the input / output interface 902 in FIG9 , which may include an input interface and an output interface. Alternatively, the communication interface may be a transceiver circuit, which may include an input interface circuit and an output interface circuit.

[0341] Optionally, the input-output interface 902 is used to receive first information, which is used to indicate a first artificial intelligence (AI) model; the logic circuit 901 is used to process the first AI model based on local data to obtain a second AI model; wherein the AI ​​data features of the local data meet the AI ​​data features corresponding to the processing requirements of the first AI model.

[0342] Optionally, the input-output interface 902 is used to receive one or more node information, where the one or more node information is used to indicate AI data characteristics of one or more nodes; the one or more node information is used to determine transmission information of the AI ​​model; the logic circuit 901 is used to determine second information, where the second information is used to indicate the transmission information; and the input-output interface 902 is also used to send the second information.

[0343] The logic circuit 901 and the input / output interface 902 may also execute other steps executed by the first node or the central node in any embodiment and achieve corresponding beneficial effects, which will not be described in detail here.

[0344] In a possible implementation, the processing unit 801 shown in FIG. 8 may be the logic circuit 901 in FIG. 9 .

[0345] Optionally, the logic circuit 901 may be a processing device, and the functions of the processing device may be partially or entirely implemented by software. The functions of the processing device may be partially or entirely implemented by software.

[0346] Optionally, the processing device may include a memory and a processor, wherein the memory is used to store a computer program, and the processor reads and executes the computer program stored in the memory to perform corresponding processing and / or steps in any one of the method embodiments.

[0347] Alternatively, the processing device may include only a processor. A memory for storing the computer program is located outside the processing device, and the processor is connected to the memory via circuits / wires to read and execute the computer program stored in the memory. The memory and processor may be integrated or physically separate.

[0348] Optionally, the processing device may be one or more chips, or one or more integrated circuits. For example, the processing device may be one or more field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), system-on-chips (SoCs), central processor units (CPUs), network processors (NPs), digital signal processors (DSPs), microcontroller units (MCUs), programmable logic devices (PLDs), or other integrated chips, or any combination of the above chips or processors.

[0349] Please refer to Figure 10, which shows the communication device 1000 involved in the above-mentioned embodiments provided in an embodiment of the present application. The communication device 1000 can specifically be a communication device serving as a terminal device in the above-mentioned embodiments. The example shown in Figure 10 is that the terminal device is implemented through the terminal device (or a component in the terminal device).

[0350] Herein, a possible logical structure diagram of the communication device 1000 is shown. The communication device 1000 may include but is not limited to at least one processor 1001 and a communication port 1002 .

[0351] The transceiver unit 802 shown in FIG8 may be a communication interface, which may be the communication port 1002 in FIG10 , which may include an input interface and an output interface. Alternatively, the communication port 1002 may be a transceiver circuit, which may include an input interface circuit and an output interface circuit.

[0352] Further optionally, the device may also include at least one of a memory 1003 and a bus 1004. In an embodiment of the present application, the at least one processor 1001 is used to control and process the actions of the communication device 1000.

[0353] In addition, the processor 1001 can be a central processing unit, a general-purpose processor, a digital signal processor, an application-specific integrated circuit, a field programmable gate array or other programmable logic device, a transistor logic device, a hardware component, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. The processor can also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a digital signal processor and a microprocessor, and so on. Those skilled in the art will clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0354] It should be noted that the communication device 1000 shown in Figure 10 can be specifically used to implement the steps implemented by the terminal device in the aforementioned method embodiment and achieve the corresponding technical effects of the terminal device. The specific implementation methods of the communication device shown in Figure 10 can refer to the description in the aforementioned method embodiment and will not be repeated here.

[0355] Please refer to Figure 11, which is a structural diagram of the communication device 1100 involved in the above-mentioned embodiments provided in an embodiment of the present application. The communication device 1100 can specifically be a communication device as a network device in the above-mentioned embodiments. The example shown in Figure 11 is that the network device is implemented through the network device (or a component in the network device), wherein the structure of the communication device can refer to the structure shown in Figure 11.

[0356] The communication device 1100 includes at least one processor 1111 and at least one network interface 1114. Further optionally, the communication device also includes at least one memory 1112, at least one transceiver 1113 and one or more antennas 1115. The processor 1111, the memory 1112, the transceiver 1113 and the network interface 1114 are connected, for example, via a bus. In an embodiment of the present application, the connection may include various interfaces, transmission lines or buses, etc., which are not limited in this embodiment. The antenna 1115 is connected to the transceiver 1113. The network interface 1114 is used to enable the communication device to communicate with other communication devices through a communication link. For example, the network interface 1114 may include a network interface between the communication device and the core network device, such as an S1 interface, and the network interface may include a network interface between the communication device and other communication devices (such as other network devices or core network devices), such as an X2 or Xn interface.

[0357] The transceiver unit 802 shown in FIG8 may be a communication interface, which may be the network interface 1114 in FIG11 , which may include an input interface and an output interface. Alternatively, the network interface 1114 may be a transceiver circuit, which may include an input interface circuit and an output interface circuit.

[0358] Processor 1111 is primarily used to process communication protocols and communication data, control the entire communication device, execute software programs, and process software program data, for example, to support the communication device in performing the actions described in the embodiments. The communication device may include a baseband processor and a central processing unit. The baseband processor is primarily used to process communication protocols and communication data, while the central processing unit is primarily used to control the entire terminal device, execute software programs, and process software program data. Processor 1111 in Figure 11 may integrate the functions of both a baseband processor and a central processing unit. Those skilled in the art will appreciate that the baseband processor and the central processing unit may also be independent processors interconnected via a bus or other technology. Those skilled in the art will appreciate that a terminal device may include multiple baseband processors to accommodate different network standards, multiple central processing units to enhance its processing capabilities, and various components of the terminal device may be connected via various buses. The baseband processor may also be referred to as a baseband processing circuit or a baseband processing chip. The central processing unit may also be referred to as a central processing circuit or a central processing chip. The functionality for processing communication protocols and communication data may be built into the processor or stored in memory as a software program, which is executed by the processor to implement the baseband processing functionality.

[0359] The memory is primarily used to store software programs and data. Memory 1112 can exist independently and be connected to processor 1111. Alternatively, memory 1112 can be integrated with processor 1111, for example, within a single chip. Memory 1112 can store program code for executing the technical solutions of the embodiments of the present application, and execution is controlled by processor 1111. The various computer program codes executed can also be considered drivers for processor 1111.

[0360] Figure 11 shows only one memory and one processor. In an actual terminal device, there may be multiple processors and multiple memories. The memory may also be referred to as a storage medium or a storage device. The memory may be a storage element on the same chip as the processor, i.e., an on-chip storage element, or an independent storage element, which is not limited in the present embodiment.

[0361] The transceiver 1113 can be used to support the reception or transmission of radio frequency signals between the communication device and the terminal. The transceiver 1113 can be connected to the antenna 1115. The transceiver 1113 includes a transmitter Tx and a receiver Rx. Specifically, one or more antennas 1115 can receive radio frequency signals. The receiver Rx of the transceiver 1113 is used to receive the radio frequency signal from the antenna, convert the radio frequency signal into a digital baseband signal or a digital intermediate frequency signal, and provide the digital baseband signal or digital intermediate frequency signal to the processor 1111 so that the processor 1111 can further process the digital baseband signal or digital intermediate frequency signal, such as demodulation and decoding. In addition, the transmitter Tx in the transceiver 1113 is also used to receive a modulated digital baseband signal or digital intermediate frequency signal from the processor 1111, convert the modulated digital baseband signal or digital intermediate frequency signal into a radio frequency signal, and transmit the radio frequency signal through one or more antennas 1115. Specifically, the receiver Rx can selectively perform one or more stages of down-mixing and analog-to-digital conversion on the RF signal to obtain a digital baseband signal or a digital intermediate frequency signal. The order of the down-mixing and analog-to-digital conversion processes is adjustable. The transmitter Tx can selectively perform one or more stages of up-mixing and digital-to-analog conversion on the modulated digital baseband signal or digital intermediate frequency signal to obtain a RF signal. The order of the up-mixing and digital-to-analog conversion processes is adjustable. The digital baseband signal and the digital intermediate frequency signal may be collectively referred to as digital signals.

[0362] The transceiver 1113 may also be referred to as a transceiver unit, a transceiver, a transceiver device, etc. Optionally, a device in the transceiver unit that implements a receiving function may be referred to as a receiving unit, and a device in the transceiver unit that implements a transmitting function may be referred to as a transmitting unit. That is, the transceiver unit includes a receiving unit and a transmitting unit. The receiving unit may also be referred to as a receiver, an input port, a receiving circuit, etc., and the transmitting unit may be referred to as a transmitter, a transmitter, or a transmitting circuit, etc.

[0363] It should be noted that the communication device 1100 shown in Figure 11 can be specifically used to implement the steps implemented by the network device in the aforementioned method embodiment, and to achieve the corresponding technical effects of the network device. The specific implementation methods of the communication device 1100 shown in Figure 11 can refer to the description in the aforementioned method embodiment, and will not be repeated here one by one.

[0364] Please refer to FIG12 , which is a schematic structural diagram of the communication device involved in the above-mentioned embodiment provided in an embodiment of the present application.

[0365] It can be understood that the communication device 120 includes, for example, modules, units, elements, circuits, or interfaces, which are appropriately configured together to implement the technical solutions provided in this application. The communication device 120 can be the RAN node, terminal, core network device, or other network device described above, or a component (e.g., a chip) in these devices, used to implement the method described in the following method embodiment. The communication device 120 includes one or more processors 121. The processor 121 can be a general-purpose processor or a dedicated processor. For example, it can be a baseband processor or a central processing unit. The baseband processor can be used to process communication protocols and communication data, and the central processing unit can be used to control the communication device (e.g., RAN node, terminal, or chip), execute software programs, and process data of software programs.

[0366] Optionally, in one design, the processor 121 may include a program 123 (sometimes also referred to as code or instructions), which may be executed on the processor 121 to cause the communication device 120 to perform the methods described in the following embodiments. In yet another possible design, the communication device 120 includes circuitry (not shown in FIG12 ).

[0367] Optionally, the communication device 120 may include one or more memories 122 on which a program 124 (sometimes also referred to as code or instructions) is stored. The program 124 can be run on the processor 121, so that the communication device 120 executes the method described in the above method embodiment.

[0368] Optionally, the processor 121 and / or the memory 122 may include an AI module 127, 128, which is used to implement AI-related functions. The AI ​​module may be implemented through software, hardware, or a combination of software and hardware. For example, the AI ​​module may include a wireless intelligent control (RIC) module. For example, the AI ​​module may be a near real-time RIC or a non-real-time RIC.

[0369] Optionally, data may be stored in the processor 121 and / or the memory 122. The processor and the memory may be provided separately or integrated together.

[0370] Optionally, the communication device 120 may further include a transceiver 125 and / or an antenna 126. The processor 121 may also be sometimes referred to as a processing unit, and controls the communication device (e.g., a RAN node or terminal). The transceiver 125 may also be sometimes referred to as a transceiver unit, a transceiver, a transceiver circuit, or a transceiver, and is configured to implement the transceiver functions of the communication device through the antenna 126.

[0371] The transceiver unit 802 shown in FIG8 may be a communication interface, which may be the transceiver 125 in FIG12 . The transceiver 125 may include an input interface and an output interface. Alternatively, the transceiver 125 may be a transceiver circuit, which may include an input interface circuit and an output interface circuit.

[0372] An embodiment of the present application also provides a computer-readable storage medium, which is used to store one or more computer-executable instructions. When the computer-executable instructions are executed by a processor, the processor executes the method described in the possible implementation method of the first node or the central node in the above embodiment.

[0373] An embodiment of the present application also provides a computer program product (or computer program). When the computer program product is executed by the processor, the processor executes the method of the possible implementation of the above-mentioned first node or central node.

[0374] An embodiment of the present application also provides a chip system, which includes at least one processor for supporting a communication device to implement the functions involved in the possible implementation methods of the above-mentioned communication device. Optionally, the chip system also includes an interface circuit, which provides program instructions and / or data to the at least one processor. In one possible design, the chip system may also include a memory, which is used to store the necessary program instructions and data for the communication device. The chip system can be composed of chips, or it can include chips and other discrete devices, wherein the communication device can specifically be the first node or central node in the aforementioned method embodiment.

[0375] An embodiment of the present application also provides a communication system, which includes a first node and a second node in any of the above embodiments. The first node can be a terminal device or a network device, and the second node can also be a terminal device or a network device.

[0376] Optionally, the communication system may further include a central node, which may also be a terminal device or a network device.

[0377] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0378] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0379] In addition, the functional units in the various embodiments of the present application can be integrated into a processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit. If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the contributing part or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in the various embodiments of the present application. The aforementioned storage medium includes various media that can store program code, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

Claims

1. A communication method, characterized in that: include: Receiving first information, where the first information is used to indicate a first artificial intelligence (AI) model; The first AI model is processed based on local data to obtain a second AI model; wherein AI data features of the local data meet AI data features corresponding to processing requirements of the first AI model.

2. The method according to claim 1, characterized in that The receiving first information comprises: The first information is received based on second information, where the second information is used to indicate transmission information of the AI ​​model.

3. The method according to claim 2, characterized in that The method further comprises: The second information is received.

4. The method according to claim 2, characterized in that: The method further comprises: Receive one or more neighbor node information, where the one or more neighbor node information is used to indicate AI data features of one or more neighbor nodes; The second information is determined based on the one or more neighbor node information.

5. The method according to any one of claims 2 to 4, characterized in that: The method further comprises: Third information is sent based on the second information, where the third information is used to indicate the second AI model.

6. The method according to claim 5, characterized in that The method further comprises: Send fourth information and / or fifth information, the fourth information is used to indicate the AI ​​data characteristics corresponding to the processing requirements of the first AI model, and the fifth information is used to indicate the AI ​​data characteristics corresponding to the processing requirements of the second AI model.

7. The method according to any one of claims 2 to 5, characterized in that: The transmission information includes at least one of the following: Sending a node identifier of a node of the first AI model; Receive a node identifier of a node of the second AI model; an identifier of the AI ​​task corresponding to the first AI model and / or the second AI model; an identifier of the first AI model; an identifier of the second AI model; The processing method of processing the first AI model is at least one of training processing, distillation processing and fusion processing; The processing method of processing the second AI model is at least one of training processing, distillation processing and fusion processing; Indication information indicating a non-relay node.

8. The method according to any one of claims 1 to 7, characterized in that: Before processing the first AI model based on local data, the method further includes: Fourth information is received, where the fourth information is used to indicate AI data features corresponding to the processing requirements of the first AI model.

9. The method according to any one of claims 1 to 8, characterized in that: The AI ​​data features include at least one of the following: The AI ​​tasks applied by the AI ​​data, the objects to which the AI ​​data belongs, the geographical location information of the AI ​​data collection, the time information of the AI ​​data collection, and the number of AI data samples.

10. The method according to any one of claims 1 to 9, characterized in that: The method further comprises: Sending indication information indicating AI data characteristics of the local data.

11. The method according to any one of claims 1 to 10, characterized in that: The processing the first AI model based on the local data to obtain the second AI model includes: Based on the local data, the first AI model is subjected to at least one of training processing, distillation processing and fusion processing to obtain the second AI model.

12. A communication method, characterized in that: include: Receiving one or more node information, wherein the one or more node information is used to indicate AI data features of one or more nodes; The one or more node information is used to determine transmission information of the AI ​​model; Sending second information, where the second information is used to indicate the transmission information.

13. The method according to claim 12, characterized in that The transmission information includes at least one of the following: Sending a node identifier of a node of the first AI model; Receive a node identifier of a node of the second AI model; an identifier of the AI ​​task corresponding to the first AI model and / or the second AI model; an identifier of the first AI model; an identifier of the second AI model; The processing method of processing the first AI model is at least one of training processing, distillation processing and fusion processing; The processing method of processing the second AI model is at least one of training processing, distillation processing and fusion processing; Indication information indicating a non-relay node.

14. The method according to claim 12 or 13, characterized in that The AI ​​data features include at least one of the following: The AI ​​tasks applied by the AI ​​data, the objects to which the AI ​​data belongs, the geographical location information of the AI ​​data collection, the time information of the AI ​​data collection, and the number of AI data samples.

15. A communication device, characterized in that: including a transceiver unit and a processing unit; The transceiver unit is used to receive first information, where the first information is used to indicate a first artificial intelligence AI model; The processing unit is used to process the first AI model based on local data to obtain a second AI model; wherein the AI ​​data features of the local data meet the AI ​​data features corresponding to the processing requirements of the first AI model.

16. The device according to claim 15, characterized in that The transceiver unit is used to receive the first information, including: The transceiver unit is specifically used to receive the first information based on second information, and the second information is used to indicate transmission information of the AI ​​model.

17. The device according to claim 16, characterized in that The transceiver unit is further configured to receive the second information.

18. The device according to claim 16, characterized in that The transceiver unit is further used to receive one or more neighbor node information, where the one or more neighbor node information is used to indicate AI data features of one or more neighbor nodes; The processing unit is further configured to determine the second information based on the one or more neighbor node information.

19. The device according to any one of claims 16 to 18, characterized in that The transceiver unit is further used to send third information based on the second information, where the third information is used to indicate the second AI model.

20. The device according to claim 19, characterized in that The transceiver unit is further used to send fourth information and / or fifth information, the fourth information is used to indicate AI data features corresponding to the processing requirements of the first AI model, and the fifth information is used to indicate AI data features corresponding to the processing requirements of the second AI model.

21. The device according to any one of claims 16 to 20, characterized in that The transmission information includes at least one of the following: Sending a node identifier of a node of the first AI model; Receive a node identifier of a node of the second AI model; an identifier of the AI ​​task corresponding to the first AI model and / or the second AI model; an identifier of the first AI model; an identifier of the second AI model; The processing method of processing the first AI model is at least one of training processing, distillation processing and fusion processing; The processing method of processing the second AI model is at least one of training processing, distillation processing and fusion processing; Indication information indicating a non-relay node.

22. The device according to any one of claims 16 to 21, characterized in that The transceiver unit is further used to receive fourth information, where the fourth information is used to indicate AI data features corresponding to the processing requirements of the first AI model.

23. The device according to any one of claims 16 to 22, characterized in that The AI ​​data features include at least one of the following: The AI ​​tasks applied by the AI ​​data, the objects to which the AI ​​data belongs, the geographical location information of the AI ​​data collection, the time information of the AI ​​data collection, and the number of AI data samples.

24. The device according to any one of claims 16 to 23, characterized in that The transceiver unit is further configured to send indication information indicating AI data features of the local data.

25. The device according to any one of claims 16 to 24, characterized in that The processing unit is used to process the first AI model based on local data to obtain a second AI model, including: The processing unit is specifically used to perform at least one of training processing, distillation processing and fusion processing on the first AI model based on the local data to obtain the second AI model.

26. A communication device, characterized in that: including a transceiver unit and a processing unit; The transceiver unit is used to receive one or more node information, wherein the one or more node information is used to indicate AI data characteristics of one or more nodes; the one or more node information is used to determine transmission information of the AI ​​model; The processing unit is used to determine second information, where the second information is used to indicate the transmission information; The transceiver unit is further configured to send the second information.

27. The device according to claim 26, characterized in that The transmission information includes at least one of the following: Sending a node identifier of a node of the first AI model; Receive a node identifier of a node of the second AI model; an identifier of the AI ​​task corresponding to the first AI model and / or the second AI model; an identifier of the first AI model; an identifier of the second AI model; The processing method of processing the first AI model is at least one of training processing, distillation processing and fusion processing; The processing method of processing the second AI model is at least one of training processing, distillation processing and fusion processing; Indication information indicating a non-relay node.

28. The device according to claim 26 or 27, characterized in that The AI ​​data features include at least one of the following: The AI ​​tasks applied by the AI ​​data, the objects to which the AI ​​data belongs, the geographical location information of the AI ​​data collection, the time information of the AI ​​data collection, and the number of AI data samples.

29. A communication device, characterized in that: The method comprises at least one processor coupled to a memory; the at least one processor is configured to execute the method according to any one of claims 1 to 14.

30. The communication device according to claim 29, characterized in that The communication device is a chip or a chip system.

31. A readable storage medium, characterized in that: The storage medium stores a computer program or an instruction. When the computer program or the instruction is executed by the communication device, the method according to any one of claims 1 to 14 is implemented.

32. A computer program product, characterized in that The method comprises instructions, which, when executed on a computer, cause the computer to perform the method according to any one of claims 1 to 14.

Images