Training method and communication apparatus

Abstract

Embodiments of the present application provide a training method and a communication apparatus, aiming to improve the alignment efficiency between multi-module models. The method comprises: receiving training data, and training a first module group on the basis of the training data. The training data is used for training the first module group, the training data is obtained on the basis of a second module group in a second model, the first module group comprises all modules or some cascaded modules in a first model, the second module group comprises all modules or some cascaded modules in the second model, the first module group comprises modules corresponding to modules in the second module group, the first module group comprises target modules, and the target modules are modules in the first model which are not aligned with corresponding modules in the second module group.

Description

Training method and communication device

[0001] This application claims priority to the Chinese patent application filed with the State Intellectual Property Office on December 15, 2023, with application number 202311737078.7 and application name “Training Method and Communication Device”, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The present application relates to the field of communication technology, and in particular to a training method and a communication device. Background Art

[0003] Neural network-based transmitters and receivers, such as encoders and decoders, can be trained using real-world data to optimize transmission signal design and reception performance based on specific scenarios. Neural network transceivers can be used for physical layer signal processing, such as symbol modulation and demodulation, channel coding and decoding, and pilot-channel estimation; they can also be used for data processing, such as channel state information compression and reconstruction.

[0004] The transmitter and receiver neural network models can be jointly optimized to achieve optimal performance. For example, between communicating devices, the transmitter / receiver trained on one end of the communication device can be adapted to the receiver / transmitter trained on the other end of the communication device to achieve end-to-end optimal performance.

[0005] The transmitter neural network model and the receiver neural network model generally include multiple neural network modules, such as a neural network module for symbol modulation / demodulation, a neural network module for channel encoding / decoding, and a neural network module for channel state information compression / reconstruction. Currently, transmitter neural network models and receiver neural network models that include multiple neural network modules suffer from low joint optimization efficiency. Summary of the Invention

[0006] The present application provides a training method and a communication device to improve the efficiency of joint optimization of multi-module models.

[0007] A first aspect provides a training method. The method is performed by a first communication device (which may be a terminal device or a network device), or by a component (e.g., a processor, a chip, or a chip system) in the first communication device. The method may also be implemented by a logic module or software that implements all or part of the functions of the first communication device.

[0008] The method includes receiving training data and then training a first module group based on the training data. The training data is used to train the first module group, and the training data is obtained based on the second module group in the second model. The first module group includes all modules or part of the cascaded modules in the first model, the second module group includes all modules or part of the cascaded modules in the second model, and the first module group includes modules corresponding to the modules in the second module group. The first module group includes a target module, which is a module in the first model that is not aligned with the corresponding module in the second module group. For the target module that is not aligned in the first model, by training the first module group including the target module in units of module groups, the training efficiency can be improved and the communication overhead during the training process can be reduced.

[0009] The first model is a model of a first communication device, and the second model is a model of a second communication device. The first model is, for example, used to implement at least part of the functionality of a transmitter or receiver of the first communication device. The second model is, for example, used to implement at least part of the functionality of a transmitter or receiver of the second communication device. The first model and the second model are related models. In one implementation, the first model and the second model are used to implement mutually inverse functions. For example, the second model is used to perform inverse processing on the output of the first model, i.e., the first model is used to implement at least part of the functionality of the transmitter, and the second model is used to implement at least part of the functionality of the receiver. Alternatively, the first model is used to perform inverse processing on the output of the second model, i.e., the first model is used to implement at least part of the functionality of the receiver, and the second model is used to implement at least part of the functionality of the transmitter. In another implementation, the first model and the second model are used to implement the same functionality. For example, the first model and the second model are both used to implement at least part of the functionality of the transmitter or receiver.

[0010] The first model includes a plurality of modules, and the second model includes a plurality of modules. Each module is used to implement one or more functions in a transmitter or a receiver. The module may be a neural network model. The plurality of modules in the first model have a corresponding relationship with the plurality of modules in the second model. In one implementation, when the first model and the second model are used to implement mutually inverse functions, a pair of modules in the first model and the second model (one of which belongs to the first model and the other belongs to the second model) having a corresponding relationship may be two modules for implementing the mutually inverse function. In another implementation, when the first model and the second model are used to implement the same function, a pair of modules in the first model and the second model having a corresponding relationship may be two modules for the same function.

[0011] The first model consists of multiple modules connected in cascade, i.e., the output of one module can be used as the input of at least one other module, or the input of one module comes from the output of at least one other module. The second model consists of multiple modules connected in cascade, i.e., the output of one module can be used as the input of at least one other module, or the input of one module comes from the output of at least one other module.

[0012] Alignment means that the performance of a pair of modules (module pair) meets the requirements. For example, if a module pair jointly processes a set of data and the loss function value corresponding to the obtained processing result is less than the loss threshold, then the two modules in the module pair are aligned; otherwise, the two modules in the module pair are not aligned. For example, a pair of modules is used to implement mutually inverse functions, that is, one module (module x) is used to implement the function in the transmitter, and the other module (module y) is used to implement the function in the receiver. If the loss function value between the output data of module y and the input data of module x is less than the loss threshold, then module x and module y can be considered aligned. Otherwise, module x and module y can be considered misaligned (misaligned). For another example, if a module pair is used to implement the same function, then for the same input data, if the loss function value between the output data of the two modules is less than the loss threshold, then the two modules in the module pair are considered aligned; otherwise, the two modules in the module pair are considered misaligned (misaligned).

[0013] In one possible implementation, the first module group includes an adaptation module, which is a different module from the target module. The adaptation module is a module used to ensure that the performance of the first module group meets requirements. The adaptation module includes a neural network model, and parameters in the adaptation module can be trained and adjusted to ensure that the performance of the first module group meets requirements, that is, to align the first module group with the second module group, or to adapt the first module group to the second module group. Training the first module group based on training data includes adjusting parameters in the adaptation module based on the training data to align the first module group with the second module group. When training the first module group, the parameters of the adaptation module are adjusted based on the performance of the first module group, without adjusting the parameters of the target module, thereby ensuring the versatility of the target module. Optionally, since the target module is used to implement one or more functions in a receiver or transmitter, and the adaptation module is used to achieve alignment between the first module group and the second module group, the parameters in the adaptation module can generally be fewer than those in the target module, which can reduce the amount of training data required for the training process, reduce training complexity, and improve training efficiency.

[0014] In one possible implementation, the adaptation module can be adjacent to the target module. The adaptation module can be positioned adjacent to the target module, and the adaptation module can be considered a removable network layer of the target module. The parameters of the adaptation module can be adjusted without adjusting the parameters of the target module, thereby preserving the versatility of the target module and improving training efficiency. Alternatively, the adaptation module can be positioned on the output side or input side of the first module group. Alternatively, the adaptation module can be positioned between any two modules in the first module group.

[0015] In a possible implementation, the first module group includes N target modules and N adaptation modules, the N target modules correspond one-to-one to the N adaptation modules, and each adaptation module is adjacent to the corresponding target module; N is an integer greater than or equal to 1.

[0016] In one possible implementation, the first module group includes M target modules and one adaptation module, where M is an integer greater than or equal to 2. That is, when there are multiple unaligned modules, the performance of the first module group can be used as a target, and alignment of the first module group and the second module group can be achieved through one adaptation module. This eliminates the need for independent training and adaptation of each target module, thereby improving the alignment efficiency of the first model and the second model and reducing the communication overhead between the first communication device and the second communication device during the training and adaptation process.

[0017] In one possible implementation, training the first module group based on training data includes adjusting parameters in a target module based on the training data. Specifically, the first module group and the second module group can be aligned by adjusting the parameters in the target module. The first module group can include multiple target modules, and alignment is performed on a per-unit basis within the first module group. Multiple target modules can be tuned and adapted simultaneously, thereby improving alignment efficiency between the first and second module groups.

[0018] In one possible implementation, the training data includes at least one of the following: input data of the second module group and output data of the second module group; a gradient derived based on the input data of the first module group, the output data of the first module group, and the output data of the second module group; the second module group; and the second model. That is, the training data is provided in module groups, and the first module group is trained based on the performance of the module group, thereby improving the alignment efficiency of the first and second module groups.

[0019] In one possible implementation, the method further includes sending or receiving verification data, where the verification data is used to determine a target module. By verifying the module pairs in the first model and the second model, the misaligned target module can be determined, and then the first module group can be determined based on the target module. Training and adaptation are performed based on the first module group, thereby improving the alignment efficiency of the first module group and the second module group.

[0020] In one possible implementation, the verification data includes first verification data used to verify alignment between the third module group and the fourth module group. The third module group includes all modules or a portion of cascaded modules in the first model, and the fourth module group includes modules in the second model that correspond to the modules in the third module group. Verifying alignment between module groups on a module-by-module basis can improve verification efficiency.

[0021] In a possible implementation, the verification data includes second verification data, and the second verification data is used to verify whether the fifth module group and the sixth module group are aligned. The fifth module group is a subset of the third module group, and the sixth module group is a subset of the fourth module group.

[0022] In a possible implementation, the verification data includes third verification data, and the third verification data is used to verify whether the seventh module group and the eighth module group are aligned. The third module group is a subset of the seventh module group, and the fourth module group is a subset of the eighth module group.

[0023] In one possible implementation, the verification data includes fourth verification data, and the fourth verification data is used to verify whether the ninth module group is aligned with the tenth module group. The third module group, the fourth module group, the ninth module group, and the tenth module group each include at least two modules. The modules in the third module group and the ninth module group do not overlap, and the modules in the fourth module group and the tenth module group do not overlap.

[0024] A second aspect provides a training method. The method is performed by a second communication device (which may be a terminal device or a network device), or by a component (e.g., a processor, chip, or chip system) in the second communication device. Alternatively, the method may be implemented by a logic module or software that implements all or part of the functions of the second communication device.

[0025] The method includes: sending training data, the training data is used to train the first module group, the training data is obtained based on the second module group in the second model, the first module group includes all modules in the first model or part of the cascaded modules, the second module group includes all modules in the second model or part of the cascaded modules, the first module group includes modules corresponding to modules in the second module group, the first module group includes a target module, and the target module is a module in the first model that is not aligned with the corresponding module in the second module group.

[0026] In one possible implementation, the training data includes at least one of the following: input data of the second module group and output data of the second module group; a gradient obtained based on the input data of the first module group, the output data of the first module group, and the output data of the second module group; the second module group; and the second model.

[0027] In a possible implementation, the method further includes: sending or receiving verification data, where the verification data is used to determine the target module.

[0028] In one possible implementation, the verification data includes first verification data, which is used to verify whether the third module group is aligned with the fourth module group. The third module group includes all modules in the first model or part of the cascaded modules, and the fourth module group includes modules in the second model corresponding to the modules in the third module group.

[0029] In a possible implementation, the verification data includes second verification data, and the second verification data is used to verify whether the fifth module group and the sixth module group are aligned. The fifth module group is a subset of the third module group, and the sixth module group is a subset of the fourth module group.

[0030] In a possible implementation, the verification data includes third verification data, and the third verification data is used to verify whether the seventh module group and the eighth module group are aligned. The third module group is a subset of the seventh module group, and the fourth module group is a subset of the eighth module group.

[0031] A third aspect provides a communication device. The communication device has the functionality to implement the behavior described in the method example of the first aspect. The beneficial effects can be found in the description of the first aspect and are not further described here. The communication device may be the first communication device described in the first aspect, or it may be a device capable of supporting the first communication device described in the first aspect to implement the functionality required by the method provided in the first aspect, such as a chip or chip system.

[0032] In one possible design, the communication device includes corresponding means or modules for performing the method of the first aspect. For example, the communication device includes a processing unit (sometimes also referred to as a processing module) and / or a transceiver unit (sometimes also referred to as a transceiver module). These units (modules) can perform the corresponding functions in the above-mentioned method example of the first aspect. For details, please refer to the detailed description in the method example, which is not repeated here.

[0033] In a fourth aspect, an embodiment of the present application provides a communication device having the function of implementing the behavior in the method example of the second aspect above. The beneficial effects can be found in the description of the second aspect and are not repeated here. The communication device may be the second communication device in the second aspect, or the communication device may be a device capable of supporting the second communication device in the second aspect to implement the functions required by the method provided in the second aspect, such as a chip or chip system.

[0034] In one possible design, the communication device includes corresponding means or modules for performing the method of the second aspect. For example, the communication device includes a processing unit (sometimes also referred to as a processing module) and / or a transceiver unit (sometimes also referred to as a transceiver module). These units (modules) can perform the corresponding functions in the above-mentioned method example of the second aspect. For details, please refer to the detailed description in the method example, which is not repeated here.

[0035] In a fifth aspect, an embodiment of the present application provides a communication device, which may be the communication device in the third or fourth aspect of the above-mentioned embodiment, or a chip or chip system provided in the communication device in the third or fourth aspect. The communication device includes a communication interface and a processor, and optionally, further includes a memory. The memory is used to store computer programs, instructions, or data, and the processor is coupled to the memory and the communication interface. When the processor reads the computer program, instructions, or data, the communication device executes the method performed by the terminal device or network device in the above-mentioned method embodiment.

[0036] In a sixth aspect, an embodiment of the present application provides a communication device, comprising at least one processor and, optionally, a memory, wherein the at least one processor is coupled to the memory. The at least one processor is configured to execute the method described in the first aspect or the second aspect.

[0037] In a seventh aspect, an embodiment of the present application provides a chip system, which includes a processor and may also include a memory and / or a communication interface, for implementing the method described in the first aspect or the second aspect. In one possible implementation, the chip system also includes a memory for storing program instructions and / or data. The chip system can be composed of a chip, or it can include a chip and other discrete devices.

[0038] In an eighth aspect, an embodiment of the present application provides a communication system, comprising a communication device for executing the method described in the first aspect and a communication device for executing the method described in the second aspect. The communication device for executing the method described in the first aspect is, for example, the first communication device described in the first aspect, and the communication device for executing the method described in the second aspect is, for example, the second communication device described in the second aspect.

[0039] In a ninth aspect, the present application provides a computer-readable storage medium storing a computer program. When the computer program is executed, the method in any one of the first to second aspects described above is implemented.

[0040] In a tenth aspect, a computer program product is provided, comprising: a computer program code, wherein when the computer program code is run, the method in any one of the first to second aspects is executed.

[0041] Among them, the technical effects brought about by any design method in the second to tenth aspects can refer to the technical effects brought about by the different design methods in the above-mentioned first aspect, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] FIG1a is a schematic diagram of a communication system provided by the present application;

[0043] FIG1b is a schematic diagram of another communication system provided by the present application;

[0044] FIG2 is a flow chart of a training method provided by the present application;

[0045] FIG3 is a schematic diagram of a model verification method provided by this application;

[0046] FIG4 is a schematic diagram of another model verification method provided by the present application;

[0047] FIG5 is a schematic structural diagram of a first module group provided by the present application;

[0048] FIG6 is a schematic diagram of an implementation of an adaptation module provided by the present application;

[0049] FIG7 is a schematic diagram of another implementation of an adaptation module provided by the present application;

[0050] FIG8 is a schematic diagram of a communication device provided by the present application;

[0051] FIG9 is another schematic diagram of a communication device provided by the present application;

[0052] FIG10 is another schematic diagram of the communication device provided by the present application;

[0053] FIG11 is another schematic diagram of a communication device provided by the present application;

[0054] FIG12 is another schematic diagram of the communication device provided in this application. DETAILED DESCRIPTION

[0055] First, some of the terms used in the embodiments of the present application are explained to facilitate understanding by those skilled in the art.

[0056] (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.

[0057] 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.

[0058] 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.

[0059] 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.

[0060] 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.

[0061] In an embodiment of the present application, the above-mentioned terminal device may also be a device having an AI model, which can process the data to be sent or the received signal based on the AI ​​model.

[0062] (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.

[0063] 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).

[0064] 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).

[0065] 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.

[0066] 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.

[0067] For the correspondence between network elements in the ORAN system and their achievable protocol layer functions, please refer to Table 1 below.

[0068] Table 1

[0069] 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.

[0070] 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.

[0071] In an embodiment of the present application, the above-mentioned network device may also have a network node of an AI model, which can process data to be sent or received signals based on the AI ​​model.

[0072] 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.

[0073] (3) AI model, also known as AI algorithm (or AI operator), is a general term for mathematical algorithms built based on the principles of artificial intelligence. It is also the basis for using AI to solve specific problems. Depending on the specific methods and / or technologies used to implement artificial intelligence, AI models can also be called machine learning models, deep learning models, or reinforcement learning models. Machine learning is a method of implementing artificial intelligence. The goal of this method is to design and analyze algorithms (also known as models) that allow computers to automatically "learn". The designed algorithms are called machine learning models. Machine learning models are a type of algorithm that automatically analyzes data to obtain patterns and uses these patterns to predict unknown data.

[0074] Currently, the typical structure of a deep learning model is a deep neural network. A neural network is a mathematical or computational model that mimics the structure and function of biological neural networks (the central nervous system of animals, particularly the brain). Neural networks perform computations by connecting a large number of neurons. A neural network can include multiple layers with different functions, each with parameters and computational rules. Different layers within a neural network have different names depending on the computational formula or function. For example, a layer that performs convolution is called a convolutional layer, which is often used to extract features from input signals. A neural network can also be composed of multiple sub-neural networks. Different neural network structures can be applied to different scenarios (such as classification and recognition) or provide different results when used in the same scenario. Differences in neural network structure can include one or more of the following: the number of layers within the neural network, the order of the layers, and the weights, parameters, or computational formulas within each layer. A variety of highly accurate neural networks exist in the industry for applications such as recognition and classification. Some neural networks can be trained with specific datasets and then used independently to complete a task or combined with other neural networks (or other functional modules) to complete a task.

[0075] (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.

[0076] (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.

[0077] 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.

[0078] 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.

[0079] (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.

[0080] 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.

[0081] 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.

[0082] Please refer to Figure 1a, which is a schematic diagram of a communication system provided by the present application. Figure 1a exemplarily shows a network device and two terminal devices. Figure 1a takes the communication system as a cellular communication system and the network device as a base station as an example. The network device can communicate with each terminal device via wireless signals. The network device can send downlink signals to the terminal device, and the terminal device can send uplink signals to the network device. The terminal devices can also send and receive wireless signals via sidelinks (SL).

[0083] Please refer to Figure 1b, which is a schematic diagram of another communication system provided by the present application. Figure 1b shows an example of a network device and a terminal device. Figure 1b takes the communication system as a wireless local area network (WLAN) system and the network device as a wireless access point (AP) as an example. The network device can communicate with each terminal device via wireless signals. The network device can send downlink signals to the terminal device, and the terminal device can send uplink signals to the network device.

[0084] In a wireless communication system (such as the communication system shown in Figure 1a or Figure 1b), the communication node acting as the signal sender can subject the original data to be sent to multiple processing processes, including channel coding, modulation, etc.; correspondingly, the communication node acting as the signal receiver can subject the received signal to other processing processes corresponding to the multiple processing processes, including channel decoding, demodulation, etc., to restore the original data (or obtain an estimate of the original data). These processing processes can improve the reliability of data transmission.

[0085] After more than half a century of development, artificial intelligence (AI) technology has now fully entered the industrialization stage. AI technology has penetrated into various fields and industries, including wireless communications. Specifically, in wireless communication systems, AI models can be incorporated into the transmitter and receiver of devices (network devices or terminal devices). For example, the transmitter can use AI models to perform channel coding and modulation on the data to be transmitted, and the receiver can use AI models to perform channel decoding and demodulation on the received signal, thereby improving system flexibility, spectrum efficiency, and system stability.

[0086] To improve end-to-end performance between communicating parties, the AI ​​models in the transmitter and receiver of both parties can be jointly optimized. Specifically, the trained transmitter / receiver on one side is adapted to the trained receiver / transmitter on the other side. The functions of the transmitter and receiver are complex. For transmitted data, the transmitter must perform encoding, rate matching, scrambling, modulation, layer mapping, precoding, resource element (RE) mapping, digital beamforming (BF), waveform shaping, digital-to-analog conversion, and analog BF. For received wireless signals, the receiver must perform analog BF, analog-to-digital conversion, waveform reception, digital BF, RE demapping, channel equalization, layer demapping, demodulation, descrambling, rate dematching, and decoding. Therefore, the AI ​​models in both the transmitter and receiver often include multiple AI modules, each dedicated to implementing a specific function. Jointly optimizing the AI ​​models of both communicating parties requires multi-module alignment, which is complex and expensive. Therefore, reducing the complexity and overhead of multi-module alignment and improving its efficiency have become pressing challenges.

[0087] To address the above issues, the present application provides the following embodiments to reduce the complexity of multi-module alignment, reduce overhead, and improve alignment efficiency. In general, the present application verifies multiple modules in the models of the communicating parties and screens out modules that are not aligned between the communicating parties. Training is then performed on a module group basis to align the modules, where the module group includes multiple modules, and the multiple modules in the module group include modules that are not aligned. This eliminates the need to perform independent alignment for each module, improving alignment efficiency and reducing implementation complexity and overhead.

[0088] In an embodiment of the present application, the model includes a plurality of cascaded modules for implementing complex signal processing functions in a receiver or transmitter. The plurality of cascaded modules refers to the output of one of the modules, which serves as the input of one or more other modules. Each module in the model is used to implement one or more functions in a receiver or transmitter, such as encoding, modulation or information compression. At least some of the modules in the model may be AI modules. An AI module is a neural network model for implementing one or more functions in a receiver or transmitter, which can be optimized through training. In one possible implementation, all modules in the model are AI modules. In another possible implementation, among the multiple modules of the model, some of the modules may be AI modules and some may be non-AI modules. It should be noted that, unless otherwise specified, the "model" in this application refers to a model including multiple modules, and the "neural network model" corresponds to the module in the "model".

[0089] As shown in Figure 2, Figure 2 is a flow chart of a training method provided by the present application. This method is performed by a first communication device and a second communication device. The first communication device can be the network device / chip in the network device or chip system in Figure 1a / Figure 1b, and the second communication device can be the terminal device / chip in the terminal device or chip system in Figure 1a / Figure 1b. Alternatively, the first communication device can be the terminal device / chip in the terminal device or chip system in Figure 1a / Figure 1b, and the second communication device can be the network device / chip in the network device or chip system in Figure 1a / Figure 1b. This embodiment includes the following steps:

[0090] S201: The first communication device and the second communication device verify whether the modules in the first model and the second model are aligned.

[0091] The first model is a model of the first communication device, and the second model is a model of the second communication device. The first model may be a model in a transmitter, and the second model may be a model in a receiver, where the second model is used to inversely process the data (signal) output by the first model. Alternatively, the first model may be a model in a receiver, and the second model may be a model in a transmitter, where the first model is used to inversely process the data (signal) output by the second model. Alternatively, both the first model and the second model may be models in the transmitter. Alternatively, both the first model and the second model may be models in the receiver.

[0092] The first model includes multiple modules, and the second model includes multiple modules. The multiple modules in the first model have a corresponding relationship with the multiple modules in the second model. In this embodiment, the two modules in the first model and the second model that have a corresponding relationship are referred to as a module pair. Optionally, the multiple modules in the first model have a one-to-one correspondence with the multiple modules in the second model. The two modules in the first model that have a corresponding relationship with the second model are, for example, two modules for performing reciprocal operations, such as a module for modulation in one model and a module for demodulation in another model, a module for information compression in one model and a module for information decompression in another model, a module for encoding in one model and a module for decoding in another model have a corresponding relationship, and so on. Examples are not given here one by one. Alternatively, when the first model and the second model are both models in the transmitter / receiver, the two modules in the first model that have a corresponding relationship with the second model are, for example, two modules used to perform the same operation, for example, a module for modulation in one model has a corresponding relationship with a module for modulation in another model, a module for information compression in one model has a corresponding relationship with a module for information compression in another model, a module for decoding in one model has a corresponding relationship with a module for decoding in another model, and so on. Examples are not given here one by one.

[0093] The first communication device and the second communication device may verify whether each module pair in the first model and the second model is aligned, so as to determine the misaligned module pairs in the plurality of module pairs.

[0094] In one possible implementation, the first model is a model in a transmitter of a first communication device, and the second model is a model in a receiver of a second communication device. The first communication device sends verification data, and the second communication device verifies whether each pair of modules in the first model and the second model are aligned based on the verification data, and feeds back the verification results to the first communication device.

[0095] In another possible implementation, the first model is a model in a receiver of a first communication device, and the second model is a model in a transmitter of a second communication device. The second communication device sends verification data, and the first communication device verifies whether each pair of modules in the first model and the second model are aligned based on the verification data, and feeds back the verification results to the second communication device.

[0096] In another possible implementation, the first model is a model in a transmitter of a first communication device, and the second model is a model in a transmitter of a second communication device. The first communication device may send verification data, and the second communication device may perform verification based on the verification data. Alternatively, the second communication device may send verification data, and the first communication device may perform verification based on the verification data.

[0097] In another possible implementation, the first model is a model in a receiver of a first communication device, and the second model is a model in a receiver of a second communication device. The first communication device may send verification data, and the second communication device may perform verification based on the verification data. Alternatively, the second communication device may send verification data, and the first communication device may perform verification based on the verification data.

[0098] In one possible implementation, the verification data may include a model or module, such as a first model or at least one module in the first model (when the second communication device performs verification), or a second model or at least one module in the second model (when the first communication device performs verification). In another possible implementation, the verification data may include a data set, such as input data and / or output data of the first model.

[0099] There are various methods for verifying whether the modules in the first model and the second model are aligned. For example, each module pair can be verified independently. Another example is that verification can be performed on a module group basis, where the number of modules in the module group being verified can be gradually increasing, or gradually increasing, and so on. These verification methods are described below:

[0100] Verification method 1: verify each module pair independently.

[0101] The modules in the module pair being verified here are all AI modules. Take the example of a first communication device sending verification data to a second communication device, and the second communication device performing verification based on the verification data. The first communication device sends verification data corresponding to each module to the second communication device. The verification data corresponding to the module may include the input data and output data of the module. The second communication device verifies whether the module pair is aligned based on the verification data corresponding to each module and the corresponding module in the second model. When the first model is the model in the transmitter and the second model is the model in the receiver, the second communication device can use the output data of module a (a module in the first model) as the input data of the corresponding module b in the second model to obtain the output data of module b, and then calculate the loss function value based on the input data of module a and the output data of module b. If the loss function value is greater than the threshold, it can be confirmed that module a and module b are not aligned. Otherwise, it can be determined that module a and module b are aligned. When the first model and the second model are both models in the transmitter or receiver, the second communication device can use the input data of module a as the input data of the corresponding module b in the second model to obtain the output data of module b, and then calculate the loss function value based on the output data of module a and the output data of module b. If the loss function value is greater than the threshold, it can be confirmed that module a and module b are not aligned; otherwise, it can be determined that module a and module b are aligned.

[0102] The process in which the second communication device sends verification data to the first communication device and the first communication device performs verification based on the verification data is similar to the process in which the first communication device sends verification data to the second communication device and the second communication device performs verification based on the verification data, so it will not be repeated here.

[0103] Verification method 2 is based on module groups, where the number of modules in the module group decreases from large to small.

[0104] For example, a first communication device sends verification data to a second communication device, and the second communication device performs verification based on the verification data. The first communication device sends verification data corresponding to module group A1 in the first model to the second communication device. Optionally, module group A1 may include all modules in the first model. Of course, module group A1 may also include some modules in the first model. If module group A1 is not aligned with the corresponding module group A2 in the second model, the first communication device sends verification data corresponding to module group B1 in the first model to the second communication device. Module group B1 is a subset of module group A1. If module group B1 is not aligned with module group B2 in the second model, the first communication device sends verification data corresponding to module group C1 in the first model to the second communication device. Module group C1 is a subset of module group B1. This continues in this manner until the module groups in the first model are aligned with the corresponding module groups in the second model, or the number of modules in the module groups is one. The two corresponding module groups in the first and second models include one or more module pairs. That is, the modules in the module group in the first model have a corresponding relationship with the modules in the corresponding module group in the second model.

[0105] The module group may include one or multiple modules in cascade. When the module group verified last time is not aligned, the first communication device reduces the size of the module group to be verified next time to screen out the modules that are not aligned in the first model and the second model. When the first model is a model in a transmitter, the first communication device may shrink the module group toward the output side of the first model, that is, each verified module group includes the module on the output side of the first model, until the verified module group is aligned with the corresponding module group in the second model, or the module group only includes one module on the output side of the first model, and the module group cannot be further shrunk. When the first model is a model in a receiver, the first communication device may shrink the module group toward the input side of the first model, that is, each verified module group includes the module on the input side of the first model, until the verified module group is aligned with the corresponding module group in the second model, or the module group only includes one module on the input side of the first model, and the module group cannot be further shrunk.

[0106] For example, as shown in FIG3 , FIG3 is a schematic diagram of a model verification method provided by the present application. In FIG3 , the first model is the model in the transmitter, the second model is the model in the receiver, the first model includes modules 1, 2, and 3, and the second model includes modules 4, 5, and 6. Modules 1 and 6 form a module pair, modules 2 and 5 form a module pair, and modules 3 and 4 form a module pair. During the first verification, the first communication device sends verification data for module group A1 to the second communication device. Module group A1 includes modules 1, 2, and 3. The verification data for module group A1 includes, for example, input data and output data for module group A1. Based on the verification data for module group A1, the second communication device verifies module group A2 in the second model, which includes modules 4, 5, and 6. If module groups A1 and A2 are misaligned, the second communication device sends a verification result indicating the misalignment to the first communication device. The first communication device sends verification data for module group B1 to the second communication device. Module group B1 includes module 2 and module 3. The verification data for module group B1, for example, includes input data and output data for module group B1. The second communication device verifies module group B2 in the second model based on the verification data for module group B1. Module group B2 includes modules 4 and 5. If module groups B1 and B2 are misaligned, the second communication device sends a verification result indicating misalignment to the first communication device. The first communication device sends verification data for module group C1 to the second communication device. Module group C1 includes module 3. The verification data for module group C1, for example, includes input data and output data for module group C1. The second communication device verifies module group C2 in the second model. Module group C2 includes module 4 based on the verification data for module group C1. If module groups C1 and C2 are misaligned, the second communication device sends a verification result indicating misalignment to the first communication device. The method of verifying whether the module group is aligned based on the verification data corresponding to the module group is similar to the method of verifying whether the modules are aligned based on the verification data corresponding to the modules, so it will not be repeated here.

[0107] Optionally, verification may be stopped when module groups are aligned. For example, if module group A1 is not aligned with module group A2, the first communication device may stop verification when module group B1 is aligned with module group B2, thereby reducing verification overhead and improving verification efficiency.

[0108] Based on the verification result, the first communication device and the second communication device can determine the unaligned module pair. That is, the first communication device can determine the unaligned module in the first model (in this embodiment, the module in the first model that is not aligned with the corresponding module in the second model is called the target module), and the second communication device can determine the unaligned module in the second model. Exemplarily, if module group A1 is not aligned with module group A2, but module group B1 is aligned with module group B2, the unaligned module in the first model is determined to be module 1. For another example, if module group A1 is not aligned with module group A2, module group B1 is not aligned with module group B2, but module group C1 is aligned with module group C2, it is determined that the unaligned modules in the first model include module 2, or, the unaligned modules in the first model include module 1 and module 2.

[0109] The process in which the second communication device sends verification data to the first communication device and the first communication device performs verification according to the verification data is similar to the process in which the second communication device performs verification based on the verification data of the first communication device, so it will not be repeated here.

[0110] By verifying from the whole to the module, the size of the module group can be reduced when the module group is not aligned, and verification can be stopped when the module group is aligned, thereby improving verification efficiency.

[0111] Verification method three is to verify based on module groups, where the number of modules in the module group increases from small to large.

[0112] For example, a first communication device sends verification data to a second communication device, and the second communication device performs verification based on the verification data. The first communication device sends verification data corresponding to module group E1 in the first model to the second communication device. Module group E1, for example, includes one module in the first model. When module group E1 aligns with the corresponding module group E2 in the second model, the first communication device sends verification data corresponding to module group F1 in the first module group to the second communication device. Module group E1 is a subset of module group F1. When module group F1 aligns with module group F2 in the second model, the first communication device sends verification data corresponding to module group G1 in the first module group to the second communication device. Module group F1 is a subset of module group G1. This continues in this manner until the module groups in the first module group are not aligned with the corresponding module groups in the second model, or the module groups include all modules in the first model. Two corresponding module groups in the first and second models include one or more module pairs. That is, a module in a module group in the first model corresponds to a module in a corresponding module group in the second model.

[0113] The module group may include one or multiple modules in cascade. When the module group verified last time is aligned, the first communication device expands the size of the module group to be verified next time to screen out the modules that are not aligned in the first model. When the first model is a model in a transmitter, the first communication device may expand the module group from the output side of the first model to the input side of the first model, that is, the module group verified each time includes the modules on the output side of the first model, until the verified module group is not aligned with the corresponding module group in the second model, or the module group includes all the modules in the first model, and the module group cannot be further expanded. When the first model is a model in a receiver, the first communication device may expand the module group from the input side of the first model to the output side of the first model, that is, the module group verified each time includes the modules on the input side of the first model, until the verified module group is not aligned with the corresponding module group in the second model, or the module group includes all the modules in the first model, and the module group cannot be further expanded.

[0114] For example, as shown in FIG3 , during the first verification, the first communication device sends verification data for module group E1 to the second communication device. Module group E1 includes module 3. The verification data for module group E1, for example, includes input data and output data for module group E1. Based on the verification data for module group E1, the second communication device verifies module group E2 in the second model, which includes module 4. If module groups E1 and E2 are aligned, the second communication device sends a verification result indicating alignment to the first communication device. The first communication device sends verification data for module group F1 to the second communication device. Module group F1 includes modules 2 and 3. The verification data for module group F1, for example, includes input data and output data for module group F1. The second communication device verifies module group F2 in the second model, which includes modules 4 and 5, based on the verification data for module group F1. If module groups F1 and F2 are aligned, the second communication device sends a verification result indicating alignment to the first communication device. The first communication device sends verification data of module group G1 to the second communication device. Module group G1 includes module 1, module 2, and module 3. The verification data of module group G1 includes, for example, input data and output data of module group G1. The second communication device verifies module group G2 in the second model based on the verification data of module group G1, where module group G2 includes module 4, module 5, and module 6. If module group G1 is aligned with module group G2, the second communication device sends a verification result indicating that module group G1 is aligned with module group G2 to the first communication device. The method for verifying whether module groups are aligned based on the verification data corresponding to the module groups is similar to the method for verifying whether modules are aligned based on the verification data corresponding to the modules, and therefore will not be repeated here.

[0115] Optionally, when verification is performed based on verification method three, if the module groups are not aligned, the first communication device may stop verification, thereby reducing verification overhead and improving verification efficiency.

[0116] Based on the verification results, the first communication device and the second communication device can determine the misaligned module pairs. That is, the first communication device can determine the misaligned modules in the first model, and the second communication device can determine the misaligned modules in the second model. For example, if module group E1 and module group E2 are misaligned, it can be determined that module 3 and module 4 are misaligned. For another example, if module group E1 and module group E2 are aligned, and module group F1 and module group F2 are misaligned, it can be determined that the misaligned modules in the first model include module 2, or that the misaligned modules in the first model include module 1 and module 2.

[0117] Verification method 4: verification based on module groups, where the number of modules in the module group is fixed.

[0118] For example, the multiple modules in the first model and the second model can be divided into multiple module groups, with the number of modules in each module group being K, where K is an integer greater than or equal to 2. The multiple modules in the module group are cascaded, so that the module group can be verified as a whole. Optionally, the modules in the module group verified each time do not overlap to improve model verification efficiency. It will be understood that when the number of modules in the first model is not divisible by K, the number of modules in the module group may be less than K.

[0119] For example, as shown in Figure 4, Figure 4 is a schematic diagram of another model verification method provided by the present application. In Figure 4, the first model is the model in the transmitter, the second model is the model in the receiver, the first model includes modules 7, 8, 9 and 10, the second model includes modules 11, 12, 13 and 14, and K=2 is taken as an example. Among them, module 7 and module 14 are a module pair, module 8 and module 13 are a module pair, module 9 and module 12 are a module pair, and module 10 and module 11 are a module pair. The first model includes module group H1 (including module 7 and module 8) and I1 (including module 9 and module 10), and the second model includes module group H2 (including module 11 and module 12) and I2 (including module 13 and module 14). Module group H1 corresponds to module group H2, and module group I1 corresponds to module group I2. The first communication device can send verification data corresponding to module group H1 to the second communication device. The second communication device can verify whether module group H1 is aligned with module group H2 based on the verification data corresponding to module group H1 and module group H2. The first communication device can send verification data corresponding to module group I1 to the second communication device. The second communication device can verify whether module group I1 is aligned with module group I2 based on the verification data corresponding to module group I1 and module group I2. The verification data corresponding to module group H1 and the verification data corresponding to module group I1 can be sent in the same message or in different messages, without limitation.

[0120] Alternatively, if a module group is not aligned, it can be considered that all modules in the module group are not aligned. Similarly, if a module group is aligned, it can be considered that the modules in the module group are aligned.

[0121] Of course, at least two of the above-mentioned verification methods 1 and 4 can be combined. For example, verification method 1 can be combined with verification method 4 to first screen out misaligned module groups using verification method 4, and then determine the misaligned modules using verification method 1. For another example, verification method 2 can be combined with verification method 3. For example, multiple modules in the first model can be divided into two parts, and the modules in each part are cascaded, with one part verified using verification method 2 and the other part verified using verification method 3. For another example, verification method 1 can be combined with verification method 3. If there are still modules that have not been verified when the module group is misaligned, the remaining unverified modules can be verified using verification method 1.

[0122] By using the above verification method, the unaligned target modules in the first model can be determined, and then module alignment can be performed based on the target modules.

[0123] S202: The second communication device sends training data. Correspondingly, the first communication device receives the training data. The training data is used to train a first module group, which includes an unaligned target module.

[0124] The training data is used to train the first module group, and the training data is obtained based on the second module group in the second model. The training data may include a training sample set constructed based on the second module group, and the training sample set may include, for example, input data and output data of the second module group. Alternatively, the training data may include a gradient. Alternatively, the training data may include the second module group. Alternatively, the training data may include the second model.

[0125] The first module group includes all modules or a portion of cascaded modules in the first model, and the second module group includes all modules or a portion of cascaded modules in the second model. The first module group includes modules corresponding to modules in the second module group. The first module group includes a target module, which is a module in the first model that is not aligned with the corresponding module in the second module group. When the first model includes multiple target modules, the first module group may include at least one target module in the first model. The first module group and the second module group are used to implement the same function. Alternatively, the first module group and the second module group are used to implement mutually inverse functions.

[0126] In a possible implementation, the modules in the first module group correspond one-to-one to the modules in the second module group.

[0127] In another possible implementation, the first module group may further include at least one adaptation module. The adaptation module is inserted into the first model after determining the target module in the first model, and the adaptation module is used to align the first module group and the second module group. How to align the first module group and the second module group by the adaptation module will be described in S203. It should be noted that the first module group is trained and adjusted based on the second module group, so the second module group may not include the adaptation module, or the module corresponding to the adaptation module. That is, the modules in the first module group other than the adaptation module correspond one-to-one to the modules in the second module group.

[0128] After determining the misaligned target module, the first communication device may determine a first module group and then request training data corresponding to the second module group from the second communication device. Each module in the first model and the second model, for example, has a corresponding module identifier. In one possible implementation, the module identifiers of the two modules in the module pair may be the same. The module identifiers of each module in the first model may be determined based on the order in which the modules process data, and the module identifiers of each module in the second model may be determined based on the order in which the modules process data. Taking the first and second models in Figure 3 as an example, the module identifiers of modules 1 and 6 may be the same, the module identifiers of modules 2 and 5 may be the same, and the module identifiers of modules 3 and 4 may be the same. In another possible implementation, the module identifiers of the two modules in the module pair may be different, and the first communication device may store a mapping relationship between each module in the first model and each module in the second model. The request for training data sent by the first communication device to the second communication device may carry the module identifiers of the modules in the first module group (excluding the identifier of the adaptation module), or may carry the module identifiers of the modules in the second module group. Thus, the second communication device can send training data for training the first module group to the first communication device.

[0129] Alternatively, after determining the unaligned target module, the second communication device may determine the second module group, send training data corresponding to the second module group to the first communication device, and indicate the modules included in the second module group to the first communication device, so that the first communication device can determine the first module group and use the training data to train the first module group.

[0130] S203: The first communication device trains the first module group according to the training data.

[0131] After verifying the first model and the second model and determining the unaligned target module in the first model, the first model or the module group including the target module can be trained to align the first model with the second model, or to align the target module with the corresponding module in the second model.

[0132] In this embodiment, various training methods are available. To optimize the target score, training can be performed targeting the performance of a single module or multiple modules. To adjust the target score, parameters of the target module or the adaptation module can be adjusted. The adaptation module is distinct from the target module. After the target module is identified, the adaptation module is inserted into the first model for adaptive alignment. Each of the aforementioned training methods is described in detail below.

[0133] Training method 1 adjusts the parameters of the adaptation module with the goal of optimizing the performance of a single module.

[0134] In this training method, the first module group includes a target module and an adaptation module. Correspondingly, the second module group includes a module corresponding to the target module. When training is performed based on this training method, the parameters of the target module are frozen and the parameters of the adaptation module are adjusted so that the performance of the combination of the target module and the adaptation module (the first module group) meets the performance requirements. Whether the first module group and the second module group are aligned can be determined based on the loss function value between the first module group and the second module group. When the first module group and the second module group are aligned, training can be stopped. During inference, the target module and the adaptation module participate in inference as a whole.

[0135] The target module is adjacent to the adapter module, and the target module and the adapter module are cascaded. The adapter module can be set on the input side of the target module. During training, training data is input into the adapter module, processed by the adapter module, and input into the target module. The output data of the target module is used to calculate the loss function value. The adapter module can also be located on the output side of the target module. During training, training data is input into the target module, processed by the target module, and input into the adapter module. The output data of the adapter module is used to calculate the loss function value.

[0136] Since the target module is used to implement one or more functions in the receiver or transmitter, and the adaptation module is used to achieve alignment of the first module group and the second module group, the parameters in the adaptation module can be less than the parameters in the target module, which can reduce the training data required for the training process, reduce the complexity of training, and improve training efficiency. In addition, the adaptation module can adjust the parameters according to different second models or scenarios / tasks / training data, while the target module parameters do not change, which can ensure the versatility of the target module. When the second model / scenario / task / training data is switched, only the adaptation module can be switched without separately training the corresponding target module for each second model / scenario / task / training data.

[0137] Exemplarily, as shown in FIG5 , when the first model includes multiple target modules, a corresponding adaptation module is provided on the input side or the output side of each module, each first module group includes an adaptation module and a target module, and each first module group is trained separately so that the first module group to which each target module belongs is aligned with the corresponding second module group.

[0138] The second training method aims to optimize the performance of multiple modules and adjust the parameters of the target module.

[0139] The first module group may include all modules in the first model. Alternatively, the first module group may include some modules in the first model. The first module group includes multiple modules in the first model. Correspondingly, the second module group includes multiple modules corresponding to the multiple modules in the first module group.

[0140] When the first model includes multiple target modules, the multiple target modules can be trained together. In this case, the first module group can include multiple target modules. For example, taking the first model in Figure 3 as an example, if module 1 and module 2 are target modules and module 3 is an aligned module, the first module group can include module 1 and module 2.

[0141] Optionally, the first module group may further include aligned modules (hereinafter referred to as aligned modules). For example, since the multiple modules in the first model are connected in a cascade manner, when one or more aligned modules are included between the two target modules, the first module group may include these aligned modules. Alternatively, with the goal of optimizing the performance of the first model, the first module group includes all modules in the first model, and the first module group may include aligned modules. During training, the aligned modules in the first module group participate in data processing, but the parameters of the aligned modules will not be adjusted, that is, the parameters of the aligned modules are frozen during the training process. For example, taking the first model in Figure 3 as an example, if modules 1 and 3 are target modules and module 2 is an aligned module, the first module group may include module 1, module 2, and module 3. Alternatively, if modules 1 and 2 are target modules and module 3 is an aligned module, with the goal of first optimizing the performance of the first model, the first module group may include module 1, module 2, and module 3.

[0142] In this training method, the first module group includes multiple target modules. The target modules in the first module group are optimized with the performance of the first module group as the goal. Multiple target modules can be optimized at the same time, which can reduce module alignment overhead and improve alignment efficiency.

[0143] Training method three adjusts the parameters of the adaptation module with the goal of optimizing multi-module performance.

[0144] The first module group may include all modules in the first model. Alternatively, the first module group may include some modules in the first model. When the first model includes multiple target modules, the multiple target modules may be trained together. That is, the first module group may include multiple target modules. Accordingly, the second module group includes multiple modules corresponding to modules other than the adaptation module in the first module group.

[0145] The difference from training method 2 is that, in addition to including multiple target modules and aligned modules (if any), the first module group also includes an adaptation module. For example, taking the first model in Figure 3 as an example, if modules 1 and 2 are target modules and module 3 is an aligned module, the first module group can include module 1, module 2 and at least one adaptation module.

[0146] In one implementation, each target module in the first module group corresponds to an adaptation module. For example, the first module group includes N target modules and N adaptation modules, with each of the N target modules corresponding to each of the N adaptation modules. In training method three, N is an integer greater than or equal to 2. Each adaptation module can be positioned adjacent to the corresponding target module.

[0147] In another implementation, the number of adaptation modules can be one, thereby reducing the complexity of training. For example, the first module group includes M target modules and one adaptation module. M is an integer greater than or equal to 2. The adaptation module can be set at the input side of the first module group, or at the output side of the first module group, or between any two modules in the first module group, without limitation herein.

[0148] When using training data for training, the parameters of the adaptation module are adjusted, and the parameters of the target module and the aligned modules (if any) can be frozen. When the loss function value of the first module group and the second module group is less than the threshold, the training can be completed. When the first model is used for reasoning, the adaptation module participates in the reasoning. By inserting the target module into the first module group, the parameters of the adaptation module are adjusted with the performance of the first module group as the target during training, without adjusting the parameters of each target module, which can reduce the complexity of training and improve the efficiency of training. In addition, joint training of multiple target modules can reduce the number of interactions between the first communication device and the second communication device during training, and reduce the air interface overhead during training.

[0149] In this embodiment, the training data is training data obtained based on the second module group corresponding to the first module group in the second model. The training data, for example, includes input data and output data of the second module group. If the first model and the second model are models for realizing reciprocal functions, when training the first module group, the output data of the second module group can be used as the input data of the first module group to obtain the output data of the first module group, and then the loss function value is calculated based on the input data of the second module group and the output data of the first module group, and the parameters of the target module are adjusted based on the loss function value. If the first model and the second model are models for realizing the same function, when training the first module group, the input data of the second module group can be used as the input data of the first module group to obtain the output data of the first module group, and then the loss function value is calculated based on the output data of the second module group and the output data of the first module group, and the parameters of the target module are adjusted based on the loss function value.

[0150] Alternatively, the training data may include, for example, a gradient obtained based on the second module group. Specifically, the gradient may be obtained based on the input data of the first module group, the output data of the first module group, and the output data of the second module group. The first communication device adjusts the parameters of the target module based on the gradient. Alternatively, the training data may include, for example, the second module group or the second model. Thus, the first communication device may construct a dataset for training based on the second module group and train the first module group based on the dataset.

[0151] In this embodiment, the training method 1, the training method 2 and the training method 3 can be switched adaptively. For example, when the first module group is difficult to converge when training method 3 is used, the training method 1 or the training method 2 can be switched to perform training.

[0152] When the loss function value between the first module group and the corresponding second module group is less than a preset threshold, it can be confirmed that the first module group is aligned with the second module group. The first communication device can associate the first module group and the second module group. The first communication device can configure a first identifier for the first module group, a second identifier for the second module group, and send the second identifier to the second communication module. The first communication device associates the first identifier and the second identifier to associate the first module group and the second module group. Alternatively, the first communication device can determine a third identifier, and the third identifier associates the first module group and the second module group to associate the first module group and the second module group through the third identifier. The first identifier is associated with the second identifier, or the third identifier is associated with the first model and the second model. This association relationship can be used for model selection / switching / activation / monitoring in subsequent processes.

[0153] With the third training method provided in this embodiment, when training different second models or training data, the end-to-end performance of the first and second models can be targeted, and only the parameters of the adaptation module can be adjusted to adapt the first model to the different second models / training data. Different second models or training data are suitable for different scenarios or tasks.

[0154] In one possible implementation, when training is performed for different second models or training data, the structure of the adaptation module remains unchanged, and the parameters of the adaptation module are adjusted for the second model / training data corresponding to each second model or training data, and the parameters of the adaptation module corresponding to the different second models or training data are obtained respectively. The parameters corresponding to the different second models or training data are associated with the second model or scene / task. When the first model is subsequently used for reasoning, the associated parameters are loaded into the adaptation module for reasoning according to the current second model or scene / task. For example, as shown in Figure 6, scene / task 1 corresponds to parameter p1, scene / task 2 corresponds to parameter p2, and scene / task 3 corresponds to parameter p3. When executing task 1, parameter p1 is loaded into the adaptation module for reasoning, when executing task 2, parameter p2 is loaded into the adaptation module for reasoning, and when executing task 3, parameter p3 is loaded into the adaptation module for reasoning.

[0155] In another possible implementation, the adaptation module includes multiple submodules. When training for different second models or scenarios / tasks, the submodules in the adaptation module involved in parameter adjustment can be changed so that different second models or scenarios / tasks correspond to different submodules in the adaptation module. When the second model or scenario / task is relatively complex, more submodules and more parameters can be selected for training to ensure the performance of the first model when applied to the second model / scenario / task. When reasoning for different second models or scenarios / tasks, the corresponding submodules in the target module can be selected for activation. For example, as shown in Figure 7, the target module includes three submodules, w1, w2, and w3. Task 1 corresponds to submodule w3, Task 2 corresponds to submodule w1 and submodule w2, and Task 3 corresponds to submodule w1, submodule w2, and submodule w3. When the first model is used to perform Task 1, only submodule w3 can be activated, while submodule w1 and submodule w2 are not activated. When the first model is used to perform Task 2, submodule w3 and submodule w2 can be activated, while submodule w1 is not activated. When the first model is used to perform task 3, submodule w1, submodule w3, and submodule w2 may be activated.

[0156] The adaptation module shown in Figure 7 can also be applied to training scenarios of different complexities. For example, when there are fewer target modules in the first module group, fewer sub-modules therein can be used for training. When the number of target modules in the first module group is large, more sub-modules therein can be used for training. Exemplarily, taking Figure 7 as an example, if the first module group includes module j and an adaptation module, only sub-module w3 of the adaptation module can be trained. If the first module group includes module i, module j and an adaptation module, sub-module w2 and sub-module w3 of the adaptation module can be trained. If the first module group includes module h, module i, module j and an adaptation module, sub-module w1, sub-module w2 and sub-module w3 of the adaptation module can be trained.

[0157] It can be understood that the models in Figures 3 to 7 are only for illustration and should not be understood as limiting the present application. For example, Figures 3 to 7 take the first model as the model in the transmitter and the second model as the model in the receiver as an example. Of course, the first model can also be the model in the receiver, the second model can also be the model in the transmitter, or the first model and the second model can both be models in the transmitter, or both be models in the receiver, and there is no limitation here. For another example, the number of modules in the first model and the second model is also only for example, and the number of modules in the first model and the second model can also be more or less, and there is no limitation in this application. For another example, the position of the adaptation module in the first model / first module group is also only for illustration, and the adaptation module can be set at the input side of the target module / first module group / first model, or can be set at the output side of the target module / first module group / first model, and there is no limitation here.

[0158] In this embodiment, by verifying the modules in the first model and the second model, the unaligned target modules in the first model and the second model are determined, and then a first module group is determined based on the performance optimization goal and the unaligned target modules. The first module group may include multiple target modules. With the goal of optimizing the performance of the first module group, multiple target modules / adaptation modules can be optimized simultaneously, thereby improving the alignment efficiency of the modules in the first model and the second model and reducing the overhead of aligning the first model.

[0159] Referring to Figure 8 , an embodiment of the present application provides a communication device 800. This communication device 800 can implement the functions of the second communication device or the first communication device in the above-described method embodiment, thereby also achieving the beneficial effects of the above-described method embodiment. In this embodiment of the present application, the communication device 800 can be the first communication device (or the second communication device), or it can be an integrated circuit or component, such as a chip, within the second communication device (or the first communication device).

[0160] 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.

[0161] In one possible implementation, when the device 800 is used to execute the method executed by the first communication device in the aforementioned embodiment, the device 800 includes a processing unit 801 and a transceiver unit 802; the transceiver unit 802 is used to receive training data, and the training data is used to train the first module group. The training data is obtained based on the second module group in the second model, the first module group includes all modules or cascaded partial modules in the first model, the second module group includes modules in the second model corresponding to modules in the first module group, and the first module group includes a target module, which is a module in the first model that is not aligned with the corresponding module in the second module group. The processing unit 801 is used to train the first module group based on the training data.

[0162] In a possible implementation, the first module group includes an adaptation module, and the adaptation module and the target module are different modules. The processing unit 801 is configured to adjust parameters in the adaptation module according to the training data.

[0163] In a possible implementation, the adaptation module is adjacent to the target module; or the adaptation module is disposed on the output side or the input side of the first module group.

[0164] In a possible implementation, the first module group includes N target modules and N adaptation modules, the N target modules correspond one-to-one to the N adaptation modules, and each adaptation module is adjacent to the corresponding target module; N is an integer greater than or equal to 1.

[0165] In a possible implementation, the first module group includes M target modules and 1 adaptation module; M is an integer greater than or equal to 2.

[0166] In a possible implementation, the processing unit 801 is configured to adjust parameters in the target module according to the training data.

[0167] In one possible implementation, the training data includes at least one of the following: input data of the second module group and output data of the second module group; a gradient obtained based on the input data of the first module group, the output data of the first module group, and the output data of the second module group; the second module group; and the second model.

[0168] In a possible implementation, the transceiver unit 802 is configured to send or receive verification data, and the verification data is used to determine the target module.

[0169] In one possible implementation, the verification data includes first verification data, which is used to verify whether the third module group is aligned with the fourth module group. The third module group includes all modules in the first model or part of the cascaded modules, and the fourth module group includes modules in the second model corresponding to the modules in the third module group.

[0170] In a possible implementation, the verification data includes second verification data, and the second verification data is used to verify whether the fifth module group and the sixth module group are aligned. The fifth module group is a subset of the third module group, and the sixth module group is a subset of the fourth module group.

[0171] In a possible implementation, the verification data includes third verification data, and the third verification data is used to verify whether the seventh module group and the eighth module group are aligned. The third module group is a subset of the seventh module group, and the fourth module group is a subset of the eighth module group.

[0172] In one possible implementation, when the device 800 is used to execute the method executed by the second communication device in the aforementioned embodiment, the device 800 includes a processing unit 801 and a transceiver unit 802. The processing unit 801 is used to determine training data. The transceiver unit 802 is used to send training data. The training data is used to train the first module group, and the training data is obtained based on the second module group in the second model. The first module group includes all modules or cascaded partial modules in the first model, and the second module group includes modules in the second model corresponding to the modules in the first module group. The first module group includes a target module, and the target module is a module in the first model that is not aligned with the corresponding module in the second module group.

[0173] In one possible implementation, the training data includes at least one of the following: input data of the second module group and output data of the second module group; a gradient obtained based on the input data of the first module group, the output data of the first module group, and the output data of the second module group; the second module group; and the second model.

[0174] In a possible implementation, the transceiver unit 802 is configured to send or receive verification data, and the verification data is used to determine the target module.

[0175] In one possible implementation, the verification data includes first verification data, which is used to verify whether the third module group is aligned with the fourth module group. The third module group includes all modules in the first model or part of the cascaded modules, and the fourth module group includes modules in the second model corresponding to the modules in the third module group.

[0176] In a possible implementation, the verification data includes second verification data, and the second verification data is used to verify whether the fifth module group and the sixth module group are aligned. The fifth module group is a subset of the third module group, and the sixth module group is a subset of the fourth module group.

[0177] In a possible implementation, the verification data includes third verification data, and the third verification data is used to verify whether the seventh module group and the eighth module group are aligned. The third module group is a subset of the seventh module group, and the fourth module group is a subset of the eighth module group.

[0178] In a possible implementation, the first module group includes an adaptation module, and the adaptation module and the target module are different modules.

[0179] In a possible implementation, the adaptation module is adjacent to the target module; or the adaptation module is disposed on the output side or the input side of the first module group.

[0180] In a possible implementation, the first module group includes N target modules and N adaptation modules, the N target modules correspond one-to-one to the N adaptation modules, and each adaptation module is adjacent to the corresponding target module; N is an integer greater than or equal to 1.

[0181] In a possible implementation, the first module group includes M target modules and 1 adaptation module; M is an integer greater than or equal to 2.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] Optionally, the logic circuit 901 is used to determine first information, where the first information indicates a model alignment mode supported by the first communication device; and the input / output interface 902 is used to send the first information.

[0186] Optionally, the input-output interface 902 is used to receive second information, wherein the second information indicates a target model alignment mode, the target model alignment mode is a model alignment mode supported by the second communication device, and the target alignment mode is a model alignment mode among the model alignment modes supported by the first communication device; the logic circuit 901 is used to perform model alignment based on the target model alignment mode.

[0187] The logic circuit 901 and the input / output interface 902 may also execute other steps executed by the first communication device or the second communication device in any embodiment and achieve corresponding beneficial effects, which will not be described in detail here.

[0188] In a possible implementation, the processing unit 801 shown in FIG. 8 may be the logic circuit 901 in FIG. 9 .

[0189] 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.

[0190] 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.

[0191] 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.

[0192] 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.

[0193] 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).

[0194] 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 .

[0195] 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.

[0196] 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.

[0197] 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.

[0198] 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.

[0199] 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.

[0200] 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.

[0201] 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.

[0202] 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.

[0203] 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.

[0204] 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.

[0205] 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.

[0206] 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.

[0207] 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.

[0208] 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.

[0209] 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 terminal device or network device described above, or a component (such as 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 (such as a RAN node, terminal, or chip, etc.), execute software programs, and process data of software programs.

[0210] 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 ).

[0211] 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.

[0212] 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.

[0213] 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.

[0214] 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.

[0215] 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.

[0216] An embodiment of the present application further 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 methods of the first communication device or the second communication device in the aforementioned embodiment.

[0217] 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 that may be implemented by the above-mentioned first communication device or second communication device.

[0218] 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 communication device or the second communication device in the aforementioned method embodiment.

[0219] An embodiment of the present application further provides a communication system, wherein the network system architecture includes the first communication device and the second communication device in any of the above embodiments.

[0220] 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.

[0221] 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.

[0222] 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 training method, characterized in that: Methods include: Receive training data, the training data is used to train a first module group, the training data is obtained based on a second module group in a second model, the first module group includes all modules or part of cascaded modules in the first model, the second module group includes all modules or part of cascaded modules in the second model, the first module group includes modules corresponding to modules in the second module group, the first module group includes a target module, and the target module is a module in the first model that is not aligned with a corresponding module in the second module group; The first module group is trained according to the training data.

2. The method according to claim 1, characterized in that: The first module group includes an adaptation module, the adaptation module and the target module are different modules, and the training of the first module group according to the training data includes: The parameters of the adaptation module are adjusted according to the training data.

3. The method according to claim 2, characterized in that The adapting module is adjacent to the target module; or the adapting module is arranged at the output side or the input side of the first module group.

4. The method according to claim 2 or 3, characterized in that: The first module group includes N target modules and N adaptation modules, the N target modules correspond to the N adaptation modules one by one, and each adaptation module is adjacent to the corresponding target module; N is an integer greater than or equal to 1.

5. The method according to claim 2 or 3, characterized in that: The first module group includes M target modules and 1 adaptation module; M is an integer greater than or equal to 2.

6. The method according to claim 1, characterized in that The step of training the first module group according to the training data comprises: The parameters of the target module are adjusted according to the training data.

7. The method according to any one of claims 1 to 6, characterized in that The training data includes at least one of the following: input data of the second module group and output data of the second module group; A gradient obtained based on input data of the first module group, output data of the first module group, and output data of the second module group; the second module group; The second model.

8. The method according to any one of claims 1 to 7, characterized in that The method further comprises: Send or receive verification data, where the verification data is used to determine the target module.

9. The method according to claim 8, characterized in that The verification data includes first verification data, which is used to verify whether the third module group is aligned with the fourth module group, the third module group includes all modules in the first model or part of the cascaded modules, and the fourth module group includes modules in the second model corresponding to the modules in the third module group.

10. The method according to claim 9, characterized in that The verification data includes second verification data, and the second verification data is used to verify whether the fifth module group and the sixth module group are aligned, the fifth module group is a subset of the third module group, and the sixth module group is a subset of the fourth module group.

11. The method according to claim 9, characterized in that The verification data includes third verification data, and the third verification data is used to verify whether the seventh module group is aligned with the eighth module group. The third module group is a subset of the seventh module group, and the fourth module group is a subset of the eighth module group.

12. A training method, characterized in that: The method comprises: Send training data, the training data is used to train a first module group, the training data is obtained based on a second module group in a second model, the first module group includes all modules in the first model or part of the cascaded modules, the second module group includes all modules in the second model or part of the cascaded modules, the first module group includes modules corresponding to modules in the second module group, the first module group includes a target module, and the target module is a module in the first model that is not aligned with the corresponding module in the second module group.

13. The method according to claim 12, characterized in that The training data includes at least one of the following: input data of the second module group and output data of the second module group; A gradient obtained based on input data of the first module group, output data of the first module group, and output data of the second module group; the second module group; The second model.

14. The method according to claim 12 or 13, characterized in that The method further comprises: Send or receive verification data, where the verification data is used to determine the target module.

15. The method according to claim 14, characterized in that The verification data includes first verification data, which is used to verify whether the third module group is aligned with the fourth module group, the third module group includes all modules in the first model or part of the cascaded modules, and the fourth module group includes modules in the second model corresponding to the modules in the third module group.

16. The method according to claim 15, characterized in that The verification data includes second verification data, and the second verification data is used to verify whether the fifth module group and the sixth module group are aligned, the fifth module group is a subset of the third module group, and the sixth module group is a subset of the fourth module group.

17. The method according to claim 15, characterized in that The verification data includes third verification data, and the third verification data is used to verify whether the seventh module group is aligned with the eighth module group. The third module group is a subset of the seventh module group, and the fourth module group is a subset of the eighth module group.

18. A communication device, characterized in that: Comprising means for performing the method as claimed in any one of claims 1 to 17.

19. 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 17.

20. The communication device according to claim 19, characterized in that The communication device is a chip or a chip system.

21. A readable storage medium, characterized in that: The storage medium stores a computer program or an instruction, and when the computer program or the instruction is executed by the communication device, the method according to any one of claims 1 to 17 is implemented.

22. 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 17.

Images