Communication method and apparatus

Abstract

The present application relates to the technical field of communications. Provided are a communication method and apparatus, which are used for reducing the transmission overhead incurred by model exchange between apparatuses and improving the communication efficiency. The method comprises: receiving first indication information which is used for indicating an association relationship between a first model and a second model; and determining the first model on the basis of the first indication information.

Description

A communication method and apparatus

[0001] This application claims priority to Chinese Patent Application No. 202410697321.5, filed with the State Intellectual Property Office of China on May 30, 2024, entitled “A Communication Method and Apparatus”, the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to the field of communication technology, and in particular to a communication method and apparatus. Background Technology

[0003] As wireless communication networks become more complex, service demands become more diverse, and service experiences become more personalized, artificial intelligence (AI) or machine learning (ML) models and algorithms will be more widely used in wireless communication scenarios. For example, AI or ML algorithms can be applied to scenarios such as channel prediction, network resource scheduling, or location calculation to improve data processing efficiency.

[0004] In this context, AL / ML models can have a modular structure, such as being composed of multiple sub-models or including multiple component modules. For example, an AL / ML model may include modules such as a backbone, neck, and head. When communication devices exchange this model, the sending end needs to transmit the structure of the model and the relevant parameters of each module to the receiving end, resulting in significant transmission overhead. Furthermore, for services with high real-time requirements, the transmission latency of the model is substantial, impacting communication efficiency. Summary of the Invention

[0005] This application provides a communication method and apparatus for reducing the transmission overhead of interaction models between different devices and improving communication efficiency.

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

[0007] In a first aspect, a communication method is provided, which can be executed by a first device, the first device being a functional module (such as a chip or circuit), for example, the first device being a terminal. The method includes: receiving first indication information for indicating an association relationship between a first model and a second model; and determining the first model based on the first indication information.

[0008] In the above embodiments, different devices can improve communication efficiency by indicating the association between different models, thereby saving the transmission overhead of interactive models, reducing transmission latency, and improving communication efficiency. For example, the first device can obtain the association between the first model and the second model based on the first indication information sent by the second device, and then determine part or all of the first model based on the association and some or all of the model parameters of the second model, saving the transmission overhead of the second device sending the first model to the first device.

[0009] In one implementation, the first indication information is used to indicate that a first module is shared with a first model and a second model; determining the first model according to the first indication information includes: determining the first module in the first model according to the first module in the second model; wherein, the first model includes the first module and the second model includes the first module. That is, if the first indication information indicates that the first model and the second model share part or all of the model structure or model parameters, such as sharing the first module, then the first device can determine the first module included in the first model according to the sharing information indicated by the first indication information, thereby saving the transmission overhead of the second device sending the first module to the first device.

[0010] In one implementation, the first indication information includes the name and / or index number of the first module. This can be achieved by predefining or preconfiguring names or index numbers corresponding to different modules, allowing the first indication information to carry the name or index number of the corresponding module, thus indicating related module information and saving signaling overhead.

[0011] In one implementation, the first indication information includes the name and / or index number of the second model. This can be achieved by predefining or preconfiguring names or index numbers corresponding to different models, allowing the first indication information to carry the name or index number of the corresponding model, thus indicating related model information and saving signaling overhead.

[0012] In one implementation, the association relationship is a quasi-co-addressable (QCL) relationship. That is, the association relationship between different models can be represented as a QCL relationship, thereby determining some or all of the target model's information based on the QCL relationship, improving model transmission efficiency.

[0013] In one embodiment, the method further includes: obtaining configuration information, the configuration information including at least one of the following: a correspondence between I models and I model index numbers; a correspondence between J modules and J module index numbers, wherein a model includes at least one module; or, a correspondence between M1 association information and M index numbers, wherein the association information indicates that at least two different models share at least one module; I, J, M1, and M are positive integers, and M1 is greater than or equal to M.

[0014] In the above embodiments, by predefining or preconfiguring model index numbers corresponding to different models, module index numbers corresponding to different modules, or index numbers corresponding to different relationships, the first indication information can be used to indicate the models, modules, or relationships that have relationships by carrying the index numbers, thereby saving the signaling overhead of the indication information.

[0015] In one embodiment, before receiving the first indication information, the method further includes: receiving second indication information for indicating the activation of N related information among M1 related information, wherein M is greater than N, and M and N are positive integers; the first indication information is used to indicate at least one of the N related relationships.

[0016] In the above embodiments, a few of the multiple associations can be activated first by the second instruction information, and then further indicated by the first instruction information, thereby reducing the instruction overhead of the first instruction information.

[0017] In one implementation, the first module includes at least one of the following information: part or all of the model structure, model parameters, model hyperparameters, and relevant parameters for model training or inference. That is, different devices can use the first indication information to indicate the relationships between part or all of the model structure, model parameters, model hyperparameters, and relevant parameters for model training or inference between two or more models, thereby saving the overhead of model transmission, updating, or storage and improving communication efficiency.

[0018] It should be noted that the first module in this application may be one or more sub-models, model parts, subsets of AIML parameters, model blocks, or subsets of model structures, etc.

[0019] Secondly, a communication method is provided, which can be executed by a second device, which may be a functional module (such as a chip or circuit), for example, a network device. The method includes: sending first indication information to a first device to indicate the association relationship between a first model and a second model.

[0020] In one implementation, the first indication information is used to indicate that the first module is shared with the first model and the second model; wherein the first model includes the first module and the second model includes the first module.

[0021] In one implementation, the first indication information includes the name and / or index number of the first module.

[0022] In one implementation, the first indication information includes the name and / or index number of the second model.

[0023] In one implementation, the association relationship is a quasi-co-addressable (QCL) relationship.

[0024] In one embodiment, the method further includes: sending configuration information to a first device, the configuration information including at least one of the following: a correspondence between I models and I model index numbers; a correspondence between J modules and J module index numbers, wherein a model includes at least one module; or, a correspondence between M1 association information and M index numbers, wherein the association information indicates that at least two different models share at least one module; I, J, M1, and M are positive integers, and M1 is greater than or equal to M.

[0025] In one embodiment, before sending the first indication information to the first device, the method further includes: sending the second indication information to the first device to indicate the activation of N related information among M1 related information, wherein M is greater than N, and M and N are positive integers; the first indication information is used to indicate at least one of the N related relationships.

[0026] In one implementation, the first module includes at least one of the following: part or all of the model structure, model parameters, model hyperparameters, and relevant parameters for model training or model inference.

[0027] Thirdly, a communication device is provided for implementing the above-described method. This communication device may be the first device in the first aspect, or the second device in the second aspect, or a node or device containing the first or second device, or a functional module having the first or second device, such as a chip, chip system, or circuit, or a logic node, logic module, or software capable of implementing some or all of the functions. For example, the first device may be a terminal or a network device, and the second device may be a terminal or a network device. This application can be applied to communication between terminals, communication between a terminal and a network device, or communication between network devices.

[0028] The communication device includes modules, units, or means that implement the methods described above. These modules, units, or means can be implemented in hardware, software, or by hardware executing corresponding software. The hardware or software includes one or more modules or units corresponding to the functions described above.

[0029] In conjunction with the third aspect described above, in one possible implementation, the communication device may include a processing module and a transceiver module. The processing module can be used to implement the processing functions in any of the above aspects and any possible implementations thereof. The processing module may be, for example, a processor. The transceiver module, also referred to as a transceiver unit, is used to implement the sending and / or receiving functions in any of the above aspects and any possible implementations thereof. The transceiver module may consist of a transceiver circuit, a transceiver, a transceiver unit, or a communication interface.

[0030] In conjunction with the third aspect mentioned above, in one possible implementation, the transceiver module includes a sending module and a receiving module, which are used to implement the sending and receiving functions in any of the above aspects and any possible implementations.

[0031] Fourthly, a communication device is provided, comprising: a processor; the processor being coupled to a memory, reading instructions from the memory, and executing the method described in any of the preceding aspects according to the instructions. The communication device may be a first device as described in the first aspect, or a second device as described in the second aspect, or a node or device comprising the first or second device, or a module of the first or second device, such as a chip, chip system, or circuit, or a logic node, logic module, or software capable of implementing some or all of the functions.

[0032] In conjunction with the fourth aspect above, in one possible implementation, the communication device further includes a memory for storing necessary program instructions and data.

[0033] In conjunction with the fourth aspect above, in one possible implementation, the communication device is a chip or a chip system. Optionally, when the communication device is a chip system, it can be composed of chips or may include chips and other discrete components.

[0034] Fifthly, a communication device is provided, comprising: a processor and an interface circuit; the interface circuit is configured to receive a computer program or instructions and transmit them to the processor; the processor is configured to execute the computer program or instructions to cause the communication device to perform the method described in any of the preceding aspects. The communication device may be the first device of the first aspect or the second device of the second aspect, or a node or device comprising the first or second device, or a module of the first or second device, such as a chip, chip system, or circuit, or a logic node, logic module, or software capable of implementing some or all of the functions.

[0035] In conjunction with the fifth aspect above, in one possible implementation, the communication device is a chip or a chip system. Optionally, when the communication device is a chip system, it can be composed of chips or may include chips and other discrete components.

[0036] In a sixth aspect, a computer-readable storage medium is provided that stores a computer program or instructions that, when executed on a computer, enable the computer to perform the methods described in any of the preceding aspects.

[0037] In a seventh aspect, a computer program product comprising a computer program or instructions is provided, which, when run on a computer, enables the computer to perform the methods described in any of the preceding aspects.

[0038] The technical effects of any of the possible implementations of aspects two through seven can be found in the technical effects of the different possible implementations of aspect one above, and will not be repeated here.

[0039] Understandably, provided that the solutions do not contradict each other, the solutions in the above aspects can be combined. Attached Figure Description

[0040] Figure 1 is a schematic diagram of the architecture of a communication system provided in an embodiment of this application;

[0041] Figure 2 is a schematic diagram of the architecture of a communication device provided in an embodiment of this application;

[0042] Figure 3 is a flowchart illustrating a communication method provided in an embodiment of this application;

[0043] Figure 4 is a schematic diagram of the structure of a model provided in an embodiment of this application;

[0044] Figure 5 is a schematic diagram of a sharing relationship between models provided in an embodiment of this application;

[0045] Figure 6 is a schematic diagram of the architecture of another communication device provided in an embodiment of this application. Detailed Implementation

[0046] Hereinafter, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this embodiment, unless otherwise stated, "multiple" means two or more. "At least one" means "one or more".

[0047] It should be noted that, in this application, the terms "exemplary" or "for example" are used to indicate that something is being described as an example, illustration, or illustration. Any embodiment or design described as "exemplary" or "for example" in this application should not be construed as being more preferred or advantageous than other embodiments or design solutions. Specifically, the use of terms such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0048] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0049] First, a brief introduction will be given to the implementation environment and application scenarios of the embodiments of this application.

[0050] This application can be applied to scenarios involving communication between network devices, between network devices and terminals, and between terminals. For example, network devices may include base stations, which provide wireless access services to terminals. Base stations can communicate with each other via backhaul links, which can be wired (e.g., fiber optic, copper cable) or wireless (e.g., microwave). Terminals can communicate with their corresponding base stations via wireless links. Terminals can also communicate with each other via sidelinks.

[0051] In this embodiment, a network device is a means deployed in a radio access network to provide wireless communication functions for terminal devices. Network devices can include various forms of macro network devices, micro network devices (also known as small cells), relay stations, access points, etc. In systems employing different radio access technologies, the name of the network device may differ, such as a base transceiver station (BTS) in a Global System for Mobile Communication (GSM) or Code Division Multiple Access (CDMA) network, an NB (NodeB) in Wideband Code Division Multiple Access (WCDMA), or an eNB or eNodeB (evolutionary NodeB) in Long Term Evolution (LTE). A network device can also be a radio controller in a cloud radio access network (CRAN) scenario. A network device can also be a network device in a future fifth-generation mobile communication network or a network device in a future evolved public land mobile network (PLMN). A network device can also be a wearable device or an in-vehicle device. Network devices can also be transmission reception points (TRPs). Network devices can also be core network elements, dedicated nodes, or network management components, such as those used for operation, administration, maintenance (OAM).

[0052] Figure 1 is a schematic diagram illustrating a possible, non-limiting system. The communication method provided in this application embodiment can be applied to the network architecture shown in Figure 1. As shown in Figure 1, the communication system 10 includes a radio access network (RAN) 100 and a core network (CN) 200. RAN 100 includes at least one RAN node (110a and 110b in Figure 1, collectively referred to as 110) and at least one terminal (120a-120j in Figure 1, collectively referred to as 120). RAN 100 may also include other RAN nodes, such as wireless relay devices and / or wireless backhaul devices (not shown in Figure 1). Terminal 120 is wirelessly connected to RAN node 110. RAN node 110 is wirelessly or wired connected to core network 200. The core network device in core network 200 and RAN node 110 in RAN 100 can be different physical devices, or they can be the same physical device integrating core network logical functions and radio access network logical functions.

[0053] RAN 100 can be a cellular system related to the 3rd Generation Partnership Project (3GPP), such as 4G, 5G mobile communication systems, or future-oriented evolution systems (such as 6G mobile communication systems). RAN 100 can also be an open access network (open RAN, O-RAN or ORAN), a cloud radio access network (CRAN), or a wireless fidelity (WiFi) system. RAN 100 can also be a communication system that integrates two or more of the above systems.

[0054] RAN node 110, sometimes also referred to as access network equipment, RAN entity, or access node, constitutes part of the communication system and is used to help terminals achieve wireless access. Multiple RAN nodes 110 in communication system 10 can be of the same type or different types. In some scenarios, the roles of RAN node 110 and terminal 120 are relative. For example, network element 120i in Figure 1 can be a helicopter or drone, which can be configured as a mobile base station. For terminals 120j accessing RAN 100 through network element 120i, network element 120i is a base station; but for base station 110a, network element 120i is a terminal. RAN node 110 and terminal 120 are sometimes both referred to as communication devices. For example, network elements 110a and 110b in Figure 1 can be understood as communication devices with base station functions, and network elements 120a-120j can be understood as communication devices with terminal functions.

[0055] In one possible scenario, the RAN node can be a base station, an evolved NodeB (eNodeB), an access point (AP), a TRP, a next-generation NodeB (gNB), a next-generation base station in a 6th-generation (6G) mobile communication system, a base station in a future mobile communication system, or an access node in a WiFi system. The RAN node can be a macro base station (as shown in Figure 1, 110a), a micro base station or indoor station (as shown in Figure 1, 110b), a relay node or donor node, or a radio controller in a CRAN scenario. Optionally, the RAN node can also be a server, wearable device, vehicle, or in-vehicle equipment. For example, the access network equipment in vehicle-to-everything (V2X) technology can be a roadside unit (RSU). All or part of the functions of the RAN node in this application can also be implemented through software functions running on hardware, or through virtualization functions instantiated on a platform (e.g., a cloud platform). The RAN node in this application can also be a logical node, logical module, or software capable of implementing all or part of the RAN node functions.

[0056] In another possible scenario, multiple RAN nodes collaborate to assist the terminal in achieving wireless access, with each RAN node performing a portion of the base station's functions. For example, RAN nodes can be central units (CUs), distributed units (DUs), CU-control plane (CPs), CU-user plane (UPs), or radio units (RUs), etc. CUs and DUs can be separate entities or included in the same network element, such as a baseband unit (BBU). RUs can be included in radio frequency equipment or radio frequency units, such as remote radio units (RRUs), active antenna units (AAUs), or remote radio heads (RRHs).

[0057] In different systems, CU (or CU-CP and CU-UP), DU, or RU may have different names, but those skilled in the art will understand their meaning. For example, in an ORAN system, CU can also be called O-CU (open CU), DU can also be called O-DU, CU-CP can also be called O-CU-CP, CU-UP can also be called O-CU-UP, and RU can also be called O-RU. For ease of description, this application uses CU, CU-CP, CU-UP, DU, and RU as examples. Any of the units among CU (or CU-CP, CU-UP), DU, and RU in this application can be implemented through software modules, hardware modules, or a combination of software and hardware modules.

[0058] A terminal can also be called a terminal device, user equipment (UE), mobile station, mobile terminal, etc. Terminals can be widely used in various scenarios, such as device-to-device (D2D), vehicle-to-everything (V2X) communication, machine-type communication (MTC), Internet of Things (IoT), virtual reality, augmented reality, industrial control, autonomous driving, telemedicine, smart grids, smart furniture, smart offices, smart wearables, smart transportation, smart cities, etc. Terminals can be mobile phones, tablets, computers with wireless transceiver capabilities, wearable devices, vehicles, drones, helicopters, airplanes, ships, robots, robotic arms, smart home devices, etc. The embodiments of this application do not limit the device form of the terminal.

[0059] In addition, the terminal can also be a virtual reality (VR) terminal, an augmented reality (AR) terminal, or a mixed reality (MR) terminal. VR terminals, AR terminals, and MR terminals can all be called extended reality terminals. XR terminals can be, for example, head-mounted devices (such as helmets, head-mounted displays (HMDs), or glasses), all-in-one devices, as well as televisions, monitors, cars, in-vehicle devices, tablets, or smart screens. XR terminals can access the network wirelessly or via wired means, such as through WiFi or 5G systems. XR terminals can present XR data to users, allowing users to experience diverse XR services by wearing or using XR terminals.

[0060] The functions of the other network elements included in Figure 1 can be found in the relevant descriptions in conventional technologies, and will not be repeated here.

[0061] The communication system 10 shown in Figure 1 is for illustrative purposes only and is not intended to limit the technical solutions of this application. Those skilled in the art should understand that in specific implementations, the communication system 10 may also include other devices, and the number of RAN nodes and terminals may be determined according to specific needs without limitation.

[0062] Optionally, each network element or device (such as a RAN node or terminal) in Figure 1 of this application may also be referred to as a communication device, which may be a general-purpose device or a special-purpose device. This application does not make any specific limitation on this.

[0063] Optionally, the functions of each network element or device (e.g., RAN node or terminal) in Figure 1 of this application can be implemented by one device, multiple devices working together, or one or more functional modules within a single device. This application does not impose specific limitations on these functions. It is understood that the aforementioned functions can be network elements in hardware devices, software functions running on dedicated hardware, a combination of hardware and software, or virtualization functions instantiated on a platform (e.g., a cloud platform).

[0064] It is understood that the devices or network elements in Figure 1 above can communicate directly or through forwarding by other devices. This application embodiment does not specifically limit this.

[0065] It is understood that Figure 1 above is merely a schematic diagram and does not constitute a limitation on the applicable scenarios of the technical solutions provided in this application. Those skilled in the art should understand that in specific implementation processes, the communication system may include fewer devices or network elements than shown in Figure 1, or the communication system may also include other devices or other network elements, and the number of devices or network elements in the communication system can be determined according to specific needs.

[0066] It should be noted that the communication system shown in Figure 1 is for illustrative purposes only and is not intended to limit the technical solutions of this application. Those skilled in the art should understand that in specific implementations, the communication system may also include other devices or network elements, and the number of each network element may be determined according to specific needs.

[0067] Optionally, each network element in Figure 1 of this application embodiment can be a functional module within a device. It is understood that the above functions can be network elements in hardware devices, such as communication chips in mobile phones, or software functions running on dedicated hardware, or virtualization functions instantiated on a platform (e.g., cloud platform).

[0068] For example, each network element in Figure 1 can be implemented using the communication device 20 in Figure 2. Figure 2 shows a schematic diagram of the hardware structure of a communication device applicable to embodiments of this application. The communication device 20 includes at least one processor 201, a communication line 202, a memory 203, and at least one communication interface 204.

[0069] The processor 201 may be a general-purpose central processing unit (CPU), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits used to control the execution of the program of the present application.

[0070] Communication line 202 may include a path for transmitting information between the aforementioned components, such as a bus.

[0071] Communication interface 204 uses any transceiver-like device for communicating with other devices or communication networks, such as Ethernet interface, RAN interface, wireless local area network (WLAN) interface, etc.

[0072] The memory 203 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto. The memory may exist independently and be connected to the processor via communication line 202. The memory may also be integrated with the processor. The memory provided in this application embodiment is generally non-volatile. The memory 203 is used to store computer execution instructions involved in the scheme of this application and is controlled by the processor 201 for execution. The processor 201 is used to execute computer execution instructions stored in the memory 203, thereby implementing the method provided in the embodiments of this application.

[0073] Optionally, the computer execution instructions in the embodiments of this application may also be referred to as application code, and the embodiments of this application do not specifically limit this.

[0074] In a specific implementation, as one example, processor 201 may include one or more CPUs, such as CPU0 and CPU1 in FIG2.

[0075] In a specific implementation, as one embodiment, the communication device 20 may include multiple processors, such as processor 201 and processor 207 in FIG. 2. Each of these processors may be a single-core (single-CPU) processor or a multi-core (multi-CPU) processor. Here, a processor may refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0076] In a specific implementation, as one embodiment, the communication device 20 may further include an output device 205 and an input device 206. The output device 205 communicates with the processor 201 and can display information in various ways. For example, the output device 205 may be a liquid crystal display (LCD), a light-emitting diode (LED) display device, a cathode ray tube (CRT) display device, or a projector, etc. The input device 206 communicates with the processor 201 and can receive user input in various ways. For example, the input device 206 may be a mouse, keyboard, touchscreen device, or sensing device, etc.

[0077] The communication device 20 described above can be a general-purpose device or a dedicated device. In specific implementations, the communication device 20 can be a portable computer, a web server, a handheld digital assistant (PDA), a mobile phone, a tablet computer, a wireless terminal device, an embedded device, or a device with a similar structure to that shown in Figure 2. This application does not limit the type of communication device 20.

[0078] The communication method provided in the embodiments of this application will be described in detail below.

[0079] It should be noted that the message names between network elements or the names of parameters in the messages in the following embodiments of this application are just examples. Other names may be used in the specific implementation. This application does not limit them in this respect.

[0080] Furthermore, in this application, "sending information to...(terminal)" can be understood as the destination of the information being the terminal. This can include sending information to the terminal directly or indirectly. "Receiving information from...(terminal)" can be understood as the source of the information being the terminal, and can include receiving information from the terminal directly or indirectly. Information may undergo necessary processing between the source and destination, such as format changes, but the destination can understand the valid information from the source. Similar expressions in this application can be interpreted similarly, and will not be elaborated further here.

[0081] It is understood that some or all of the steps in the embodiments of this application are merely examples, and other steps or variations thereof may also be performed in the embodiments of this application. Furthermore, the steps may be performed in different orders as presented in the embodiments of this application, and it is not necessary to perform all the steps in the embodiments of this application.

[0082] This application provides a communication method in which the sending end indicates the relationship between at least two models to the receiving end, enabling the receiving end to determine the target model, such as the model structure, model components, or model-related parameters. This eliminates the need for the sending and receiving ends to transmit complete model structures and related parameters, thereby reducing the transmission overhead of interactive models between devices, reducing transmission latency, and improving communication efficiency.

[0083] For example, the following embodiments of this application describe the application of this application to a first device and a second device. The first device or the second device can be a network device or terminal, such as any network element shown in Figure 1, or a device, module, or chip within any network element. The embodiments of this application can also be used between any two AI devices that need to communicate.

[0084] As shown in Figure 3, the method may include the following steps.

[0085] 301: The second device sends a first instruction message to the first device, indicating the association between the first model and the second model.

[0086] For example, the first and / or second models can be AI or ML models. An AL / ML model can be understood as a data-driven algorithm that uses AI / ML technology to generate a set of outputs based on a set of inputs. An AL / ML model can also be understood as learning patterns and rules from a training dataset, and then using these patterns or rules for prediction, supervision, or inference. In practical applications, AI or ML models can be applied to AI4NET scenarios such as channel prediction, intelligent signal generation, network state tracking, network resource scheduling, or location calculation to improve communication processing efficiency. AI or ML models can also be applied to NET4AI scenarios to improve the processing efficiency of AI / ML and other services.

[0087] Different models can be obtained by training on different training datasets. There may be some correlation between two or more different models.

[0088] In the embodiments of this application, indication information can be used to indicate the association relationship between two or more different models to other communication devices. For example, the indication information can be used to indicate that some or all of the parameters of one model can be obtained from some of the structure or parameters of another model, and / or, the indication information can be used to indicate that a sub-model (and / or model structure and / or model parameters) is applicable to one or more models, for example, multiple models can share the sub-model (and / or model structure and / or model parameters).

[0089] For example, the first indication information can be used to indicate the relationship between the first model and the second model. That is, some or all of the parameters of the first model can be obtained from some of the structure and / or parameters of the second model.

[0090] In one implementation, the relationships between models may include one or more of the following: the models have some or all of the same model structure, the same model parameters, the same model hyperparameters, or the same parameters related to model training or model inference. For example, the first model and the second model have some of the same model structure, such as including the same convolutional layers; or they include the same parameters; or some or all of the modules included in the models are the same; or the sub-models of the two models are the same, etc.

[0091] For example, model parameters may include: the number of layers in the neural network, the number of neurons in each layer, the activation function of each layer, the configuration of the normalized layers, or the special connection relationships between layers, etc.

[0092] For example, the model can be a convolutional neural network (CNN). The model parameters of a CNN can include: kernel size, stride, and padding of the convolutional layers, and / or kernel size and stride of the pooling layers.

[0093] For example, the model parameters of the Transformer architecture in deep learning models may include: the number of encoder and decoder layers, the dimension of the hidden layers, the number of parallel heads in the self-attention mechanism, the dimension of the hidden layers inside the feedforward network, the dropout probability of the regularization technique, the number of samples in each training batch, and / or the key-value pairs used to save the previous layer in the acceleration strategy of the inference stage.

[0094] For example, model hyperparameters refer to parameters that are manually set or predefined in the model, such as the number of model layers or step size.

[0095] In one implementation, as shown in Figure 4, the model may include modules such as a backbone network, a neck, and a head.

[0096] The backbone module is the main component of the model, responsible for extracting features from the input dataset for subsequent data processing and analysis. Typically, the backbone can be a convolutional neural network (CNN) or a residual neural network (ResNet), etc.

[0097] The neck module is the intermediate layer connecting the backbone and the head. The main function of the neck is to reduce or adjust the dimensionality of the data features from the backbone to better utilize those features and adapt them to task requirements. The neck can employ attention mechanisms, convolutional layers, or pooling layers, among others.

[0098] The head module can be the last layer of the model, typically providing classification and localization functions. Features processed by the neck are passed through the head to generate the final output, such as a softmax layer or a fully connected layer.

[0099] It should be understood that this application does not specifically limit the type, structure, or parameters of the models involved, and the description of the structure or parameters of the above models is only for illustrative purposes.

[0100] Correspondingly, the first device receives first instruction information from the second device and obtains the association relationship between the first model and the second model.

[0101] 302: The first device determines the first model based on the first instruction information.

[0102] Specifically, the first device can determine the target model, i.e., the first model, based on the relationship between the first model and the second model, combined with the model structure or model parameters of the second model.

[0103] In one implementation, the first indication information can be used to indicate that the first module is shared by the first model and the second model. That is, the first indication information indicates that the first model includes the first module and the second model also includes the first module; or the first indication information indicates that the first module is applicable to both the first model and the second model.

[0104] For example, the first module may include at least one of the following: part or all of the model structure, model parameters, model hyperparameters, and parameters related to model training or model inference.

[0105] For example, the first module can be one of the partial model structures included in the model, such as backbone, neck, or head.

[0106] For example, the first module can be a backbone, the first model is model 1, the second model is model 2, and the first indication information can be used to indicate the relationship between model 1 and model 2 as follows: model 1 and model 2 include the same backbone.

[0107] In this implementation, the first device determines the first model based on the first instruction information. Specifically, the first device can determine the first module in the first model based on the first module in the second model. That is, if the first device locally stores the second model, or if the first device obtains the first module included in the second model, it can obtain the first module included in the first model based on the first instruction information.

[0108] In the above embodiments, devices can improve communication efficiency by indicating the association between different models, thereby saving transmission overhead and reducing transmission latency. As in the aforementioned embodiments, the second device indicates a first model to the first device. If the first model includes a backbone, neck, or head, then according to the prior art, the second device needs to send the related structures and parameters of the backbone, neck, and head, resulting in significant transmission overhead. However, in the embodiments of this application, the second device indicates the association between the first and second models to the first device, and also indicates part of the model structure or parameters. For example, the first and second models share the same backbone and neck parts, and the second device sends the model parameters of the head part to the second device. This allows the first device to determine the first model, saving transmission overhead and latency.

[0109] In one implementation, the first indication information includes the name and / or index number of at least one second model. That is, the first indication information may carry the name and / or index number of one or more models that are associated with the target model storage.

[0110] Further optionally, the first indication information may also include the name and / or index number of the first model, which is used to indicate the target model.

[0111] In one implementation, the first instruction information may include the name and / or index number of the first module. That is, the first instruction information may carry the name or index number of a module or parameter shared by two or more related models.

[0112] For example, firstly, the base station can send to the terminal: (1) the name or identifier (ID) of model 1, (2) the model parameters of model 1, such as the backbone of model 1; and the neck1 of model 1, for example, a transformer encoder structure including 6 layers; and the head1 of model 1, for example, a transformer decoder structure including 6 layers. Correspondingly, the terminal can obtain model 1 based on the received (1) and (2) above.

[0113] Then, the base station can send the following to the terminal: (1) the name or ID of model 2; (2) the association between model 1 and model 2, such as indicating that model 1 and model 2 share the same backbone; (3) the model parameters of model 2, such as the neck2 of model 2, which may be a transformer encoder structure with 8 layers; and the head2 of model 2, which may be a transformer decoder structure with 8 layers. Correspondingly, the terminal can obtain model 2 based on the received (1), (2), and (3) and the backbone of model 1 obtained in the aforementioned steps.

[0114] For example, as shown in Figure 5, different models can share different modules. These modules include backbone, neck1, neck2, head1, and head2. Models 1, 2, 3, and 4 can all share the same backbone. Model 1 consists of backbone, neck1, and head1; Model 2 consists of backbone, neck1, and head2; Model 3 consists of backbone, neck2, and head1; and Model 4 consists of backbone, neck2, and head2. By transmitting the relationships between these models and some model parameters, the transmission overhead of each model can be reduced, and communication efficiency can be improved.

[0115] In one implementation, the association between the different models can be indicated as a share type relationship, a consistency relationship, or a quasi co-location (QCL) type relationship, etc.

[0116] In antenna technology, if the wireless channel attributes of one antenna port can be deduced from the wireless channel attributes of the other, or if the large-scale channel characteristic parameters of two antenna ports are the same (or similar), then these two antenna ports can be considered quasi-co-located, and the relationship between them can be indicated by QCL (Quasi-Co-located Channel Parameters). In other words, the QCL relationship can be used to indicate that the wireless channel attributes of two antenna ports are the same or similar. For example, large-scale channel characteristic parameters may include one or more of the following: Doppler shift, Doppler spread, average delay, delay spread, or spatial receiver parameters.

[0117] In this application, QCL relationships can be used to indicate the association between two or more models, and to indicate that some or all of the model parameters of another model can be obtained through some or all of the model parameters of one model.

[0118] The following section will introduce the method of indicating the first instruction information with specific examples.

[0119] For example, the following examples only use QCL (Quality-Coherent Class) as the indication of the relationship between models, and the model structure includes modules such as backbone, neck, and head as examples. More exemplarily, the backbone module may include a CNN or ResNet structure, the neck module may include a Transformer encoder structure, and the head module may include a Transformer decoder structure, etc. The above examples do not constitute a limitation on this application, and this application does not limit the specific structure or parameters of the model.

[0120] In one implementation, the names of model parameters or modules (or sub-models) included in the model can be predefined by the protocol, as well as the relationship between the names and numbers, so that the numbers of shared model parameters or modules can be indicated in the QCL relationship.

[0121] For example, the correspondence between predefined modules and module index numbers can be shown in Table 1 below.

[0122] Table 1. Correspondence between modules and index numbers

[0123] The first indication information may include the index number of the shared module, which is used to indicate that at least two models share the module structure and / or model parameters corresponding to the index number.

[0124] For example, the correspondence between predefined model parameters and index numbers can be shown in Table 2 below.

[0125] Table 2. Correspondence between model parameters and index numbers

[0126] For example, the correspondence between predefined model parameters and index numbers can also be shown in Table 3 below.

[0127] Table 3. Correspondence between model parameters and index numbers

[0128] The first indication information may include the index number corresponding to the above model parameters, which is used to indicate that at least two models share the model parameters corresponding to the index number.

[0129] In one implementation, the QCL relationships between models can be predefined through the protocol, such as predefined QCL relationships X1, X2, X3, X4, etc., which respectively represent the following association relationships:

[0130] QCL relationship X1{backbone}: QCL type X1 indicates a shared backbone.

[0131] QCL relation X2{backbone,neck}: QCL type X2 indicates that the backbone and neck are shared.

[0132] QCL relationship X3{backbone, neck, head}: QCL type X3 indicates that the backbone, neck, and head are shared.

[0133] QCL relationship X4{backbone, head}: QCL type X4 indicates that the backbone and head are shared.

[0134] QCL relationship X5{neck, head}: QCL type X5 indicates that the neck and head are shared.

[0135] QCL relationship X6{backbone,neck}: QCL type X6 indicates that the backbone and neck are shared.

[0136] QCL relationship X7{neck}: QCL type X7 indicates a shared neck.

[0137] QCL relation X8{head}: QCL type X8 indicates shared head.

[0138] ...

[0139] It should be noted that among the predefined multiple QCL relations, X1, X2, or X3, etc., used to distinguish different QCL relations, can also be represented by other numbers or letters, such as A, B, C, D, E, F, etc. For example, the predefined QCL relation E{backbone}: QCL type E indicates a shared backbone. This application does not impose restrictions on the naming of QCL relations.

[0140] For example, by predefining the QCL relationships between models through the protocol, multiple association relationships and their corresponding index numbers can be predefined, as shown in Table 4 below. The association information indicates that at least two different models share at least one module.

[0141] Table 4. Predefined or configured QCL relationships

[0142] The first indication information may include the index number corresponding to the above QCL relationship, which is used to indicate that the association between at least two models can be the QCL relationship corresponding to the index number, and to indicate that part or all of the structure of a model can be obtained from other models.

[0143] For example, the first indication information includes the identifier of the target model and the identifier of the model that is related to the target model. For example, the target model is model 2 and the model that is related to model 2 is model 1. The first indication information can indicate index number 1 in table 4, that is, indicate the QCL relationship X1 in the above table 4. Configure the QCL relationship between model 2 and model 1 as follows: model 2 and model 1 share the backbone structure, indicating that the backbone-related parameters of model 2 can be obtained from model 1.

[0144] In another example, the first indication information includes the ID of model 2, and the model identifier that is related to the target model. For example, the target model is model 2, the model that is related to model 2 is model 1, and the QCL relationship between model 2 and model 1 is configured as: QCL relationship X2{backbone and neck}, indicating that the backbone and neck related parameters of model 2 can be obtained from model 1.

[0145] In one implementation, the parameters of a model can be obtained from multiple other models. For example, the first indication information can indicate the association relationship between the target model and multiple other models, or the association relationship between the target model and multiple other models can be indicated by sending multiple first indication information.

[0146] For example, the first indication information includes the ID of the target model (Model 3), and also indicates the IDs of related models, such as Model 1 and Model 2. The QCL relationship between Model 3 and Model 2 is configured as: QCL relationship X7 {neck}, and the QCL relationship between Model 3 and Model 1 is configured as: QCL type X4 {backbone and head}. That is, the backbone and head parameters of Model 3 can be obtained from Model 1, and the neck parameters can be obtained from Model 2.

[0147] In one implementation, the correspondence between index numbers and one or more QCL relationships can be predefined or configured, as shown in Table 5 or Table 6 below. For example, index number 10 corresponds to two QCL relationships, where QCL relationship 1 indicates the association between the target model and model ID-1, and QCL relationship 2 indicates the association between the target model and model ID-2.

[0148] Table 5. Predefined or configured QCL relationships

[0149] Alternatively, the meaning of QCL relationships can be predefined through the protocol, and then the index number corresponding to different QCL relationships and the model ID associated with the QCL relationship can be configured through higher-level signaling. For example, the protocol predefines the meaning of QCL relationships X1, X2, X3, and X4, and then configures the correspondence between QCL relationships, associated model IDs, and index numbers as shown in Table 6 below.

[0150] Table 6. Predefined or configured QCL relationships

[0151] It should be understood that, in the embodiments of this application, the model ID included in the association relationship can also be a task ID or a goal ID, etc. This application does not limit the naming of the model ID.

[0152] In summary, in order to save the overhead of instruction signaling (such as the first instruction information), configuration information can be sent through protocol predefinition or higher-level signaling, so that both communicating parties, such as the first device and the second device, can obtain the configuration information and thus determine the specific instruction content of the first instruction information based on the configuration information.

[0153] In one embodiment, the communication method further includes: a first device and / or a second device acquiring configuration information, the configuration information including at least one of the following: a correspondence between I models and I model index numbers; a correspondence between J modules and J module index numbers, wherein each model includes at least one module; or, a correspondence between M1 association information and M index numbers, wherein the association information indicates that at least two different models share at least one module; I, J, M1, and M are positive integers, and M1 is greater than or equal to M. The configuration information can be predefined by the protocol or configured by higher-layer signaling.

[0154] In one possible configuration, the configuration information may include a correspondence between J module index numbers and J1 module index numbers, where J is greater than J1. That is, one module index number can correspond to multiple modules, thereby reducing the overhead of instruction signaling.

[0155] In another possible configuration, the configuration information may include a correspondence between I models and I1 model index numbers, where I is greater than I1. That is, one model index number can correspond to multiple models, thereby reducing the overhead of instruction signaling.

[0156] One possible example is that configuration information can be predefined through the protocol, or multiple shared states can be configured through higher-level signaling, such as obtaining configuration information through higher-level signaling. The configuration information may include the definition of the aforementioned QCL relationship, as well as the index number corresponding to the QCL relationship, with each index number corresponding to the shared information of one or more models.

[0157] Then, the first indication information can be indicated via physical layer signaling, that is, specifying one or more QCL relationships. For example, the first indication information can be carried in downlink control information (DCI), sidelink control information (SCI), or uplink control information (UCI). Alternatively, the first indication information can also be indicated via higher layer signaling, such as by carrying it in the medium access control control element (MAC CE).

[0158] In another possible implementation, the devices may predefine configuration information or obtain it from a higher layer, configuring M1 associations. Optionally, one index number may correspond to one or more associations; therefore, the M1 associations may correspond to M index numbers. Before the first device receives the first indication information, the system may further include: the second device can activate N associations among the configured M1 associations by sending second indication information to the first device. For example, the second indication information may be carried in a MAC CE.

[0159] Then, the second device can send a first indication message to the first device, which can use log2(N) bits to indicate one of the N associations. Here, M1 ≥ M > N, and M1, M, and N are all positive integers. For example, the first indication message can be carried in downlink control information (DCI), sidelink control information (SCI), or uplink control information (UCI).

[0160] It should be noted that the association relationship between models in the above embodiments uses QCL relationship as an example. The association relationship in the embodiments of this application can also be represented in other forms, such as share type, consistency relationship, etc. This application does not limit the specific name of the association relationship.

[0161] For example, the second device sends a first instruction message to the first device, indicating shared information between models, which indicates that some or all of the parameters of one model can be obtained from one or more other models.

[0162] For example, the base station can send a first indication message to the terminal to indicate that the target model (such as model 1) can be obtained through model 2, that is, the first indication message indicates that some model parameters of model 1 can be obtained from model 2.

[0163] For example, the protocol can predefine the following sharing relationships:

[0164] Shared relationship 1{backbone}: indicates sharing the backbone.

[0165] Shared relationship 2{backbone,neck}: indicates sharing the backbone and neck.

[0166] Shared relationship 3 {backbone, neck, head}: indicates sharing of backbone, neck, and head.

[0167] Shared relationship 4{backbone, head}: indicates sharing backbone and head.

[0168] The shared relationship 5{neck, head} indicates that the neck and head are shared.

[0169] Shared relationship 6{backbone,neck}: indicates sharing the backbone and neck.

[0170] Shared relation 7{neck}: indicates a shared neck.

[0171] The shared relationship 8{head} indicates that the head is shared.

[0172] Alternatively, the protocol can be predefined as shown in Table 7 below to configure one or more sharing relationships that exist between different models.

[0173] Table 7. Predefined or configured sharing relationships

[0174] In addition, models can share one or more sub-models (sub-model 1), one possible definition of which is as follows:

[0175] Shared relationship (Share type) X1{sub-model 1}

[0176] Shared relationship (Share type) X2 {sub-model 1, sub-model 2}

[0177] Shared relationship (Share type) X3{sub-model1, sub-model3}

[0178] Shared relationship (Share type) X4{sub-model2}.

[0179] Additionally, a mapping between sub-models and their corresponding sub-model numbers (index numbers) can be predefined via a protocol, as shown in Table 8 below. Thus, the first indication information can carry the corresponding number of the sub-model, used to indicate sub-models shared among models.

[0180] Table 8. Numbering of predefined or configured sub-models

[0181] Alternatively, as an example, the predefined correspondence between sub-models and index numbers can also be shown in Table 9 below.

[0182] Table 9. Numbering of predefined or configured sub-models

[0183] Alternatively, for example, the correspondence between predefined sub-models and index numbers can also be shown in Table 10 below.

[0184] Table 10. Numbering of predefined or configured sub-models

[0185] For example, if a model includes one or more sub-models, the first indication information can be given in the following way:

[0186] Model 2sub-model 1 means that sub-model 1 can be obtained from model 2;

[0187] Model 2ENUMERATED{sub-model 1} means that sub-model 1 can be obtained from model 2;

[0188] Model 2{sub-model 1} means that sub-model 1 can be obtained from model 2; or,

[0189] Model 2|{sub-model 1} means that sub-model 1 can be obtained from model 2. This application does not limit the form of the instruction.

[0190] Alternatively, the communication device can indicate predefined sharing relationships through physical layer signaling, as shown in Table 11-13 below.

[0191] Table 11. Predefined or configured sharing relationships

[0192] or

[0193] Table 12. Predefined or configured sharing relationships

[0194] For example, the predefined or configured sharing relationships shown in Table 12 can be represented solely by shared sub-models or modules, without needing to define names for multiple sharing relationships. For instance, index number 00 indicates that the target model and model 1 can share the sub-model1.

[0195] Alternatively, the predefined sharing relationships are shown in Table 13 below.

[0196] Table 13. Predefined or configured sharing relationships

[0197] Through the above implementation methods, multiple models can share sub-models of a model. By indicating the sharing relationship of sub-models and the known sub-models, the structure and parameters of the target model can be obtained, thereby reducing the overhead of model transmission, storage and / or updating.

[0198] It should be noted that the sub-model in the above embodiments can also be referred to as a model part, a subset of AIML parameters, a model block, or a subset of model structure, etc. This application does not limit the specific composition or structural name of the model.

[0199] It should be understood that the above implementation method is applicable to scenarios where it is not necessary to transmit model parameters of all models between devices. For example, the base station obtains four models through data training. When the terminal needs to obtain the target model, the base station can only indicate the correlation of the target model to the terminal, such as indicating the QCL relationship between model 1 and other models. Thus, the terminal can obtain the relevant structure and parameters of model 1 through other models.

[0200] In another possible implementation scenario, the devices need to transmit model parameters for all models. For example, the base station may train four models using data, while the terminal may have a large storage space and high requirements for model updates. In this case, the base station can transmit all four models to the terminal in a unified manner.

[0201] In this implementation, the first indication information can be used to indicate that the first module (or sub-model) is applicable to one or more models, that is, to indicate that multiple models can share the first module (or sub-model).

[0202] Similar to the aforementioned implementation, for example, the first indication information may include the name of the first module and / or the index number corresponding to the module.

[0203] For example, the first indication information may include the name of the model with an association relationship, and / or the index number corresponding to the model.

[0204] For example, taking a model that includes the backbone, neck, and head, the first indication information could specifically indicate:

[0205] backbone|QCL relation1{model 1,2,3,4}: used to indicate that model 1, model 2, model 3 and model 4 share the same backbone;

[0206] neck|QCL relation 2{model 1,2},QCL relation 3{model 3,4}: used to indicate that model 1 and model 2 share the same neck (e.g., neck1), and model 3 and model 4 share the same neck (e.g., neck2);

[0207] head|QCL relation 4{model 1,3}, QCL relation 5{model 2,4}: used to indicate that model 1 and model 3 share the same head (e.g., head1), and model 2 and model 4 share the same head (e.g., head2).

[0208] For example, one possible way to indicate the first indication information is as follows:

[0209] Model configInfo::=SEQUENCE{

[0210] backbone ENUMERATED{model 1, model2, model3, model4}

[0211] neck ENUMERATED{model 1, model2}

[0212] head ENUMERATED{model 1, model3}

[0213] }

[0214] Similar to the aforementioned implementation method, the above indication method can also be configured in advance by pre-defining the protocol to pre-configure the correspondence between each QCL relationship and the index number. The first indication information can indicate one or more index numbers to indicate the sharing relationship between models, thereby saving signaling overhead.

[0215] It should be understood that the relationships involved in the above embodiments of this application are not limited to QCL relationships, and can also be represented by other relationships, such as sharing relationships or other indication methods, which are not limited in this application.

[0216] The various embodiments mentioned above in this application can be combined without contradiction, and no limitation is imposed.

[0217] The above primarily describes the solution provided in this application from the perspective of interaction between various network devices. Accordingly, this application also provides a communication device, which can be the first device in the above method embodiments, or a component such as a chip that can be used in the first device; or it can be the second device in the above embodiments, or a component such as a chip that can be used in the second device. For example, the first device or the second device can be a terminal or a network device.

[0218] It is understood that, in order to achieve the aforementioned functions, the communication device includes hardware structures and / or software modules corresponding to the execution of each function. Those skilled in the art should readily recognize that, based on the unit and algorithm operations of the examples described in conjunction with the embodiments disclosed herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0219] It should be understood that the above description of the interaction between various network elements only uses terminals or network devices as examples. In reality, the processing performed by the terminals is not limited to being performed by a single network element, and the processing performed by the network devices is not limited to being performed by a single network element.

[0220] This application can divide the communication device into functional modules based on the above method examples. For example, each function can be divided into its own functional modules, or two or more functions can be integrated into one processing module. The integrated modules can be implemented in hardware or as software functional modules. It is understood that the module division in this application is illustrative and only represents one logical functional division; other division methods may be used in actual implementation.

[0221] For example, when the functional modules are divided in an integrated manner, Figure 6 shows a schematic diagram of the structure of a communication device 600. The communication device 600 includes an interface module 601 and a processing module 602.

[0222] In some embodiments, the communication device 600 may further include a storage module (not shown in FIG. 6) for storing program instructions and data.

[0223] For example, the communication device 600 can be used to implement the function of the first device in the above embodiments. The communication device 600 is, for example, the first device described in the various embodiments of FIG3 above.

[0224] The interface module 601 can be used to receive first indication information, which indicates the association between the first model and the second model.

[0225] The processing module 602 can be used to determine the first model based on the first instruction information.

[0226] In one implementation, the first indication information is used to indicate that the first module is shared with both the first model and the second model; the processing module 602 can be used to determine the first module in the first model based on the first module in the second model; wherein, the first model includes the first module and the second model includes the first module. That is, if the first indication information indicates that the first model and the second model share part or all of the model structure or model parameters, such as sharing the first module, then the first device can determine the first module included in the first model based on the sharing information indicated by the first indication information, thereby saving the transmission overhead of the second device sending the first module to the first device.

[0227] In one implementation, the first indication information includes the name and / or index number of the first module. This can be achieved by predefining or preconfiguring names or index numbers corresponding to different modules, allowing the first indication information to carry the name or index number of the corresponding module, thus indicating related module information and saving signaling overhead.

[0228] In one implementation, the first indication information includes the name and / or index number of the second model. This can be achieved by predefining or preconfiguring names or index numbers corresponding to different models, allowing the first indication information to carry the name or index number of the corresponding model, thus indicating related model information and saving signaling overhead.

[0229] In one implementation, the association relationship is a quasi-co-addressable (QCL) relationship. That is, the association relationship between different models can be represented as a QCL relationship, thereby determining some or all of the target model's information based on the QCL relationship, improving model transmission efficiency.

[0230] In one embodiment, the interface module 601 is further configured to obtain configuration information, the configuration information including at least one of the following: a correspondence between I models and I model index numbers; a correspondence between J modules and J module index numbers, wherein a model includes at least one module; or, a correspondence between M1 association information and M index numbers, wherein the association information indicates that at least two different models share at least one module; I, J, M1, and M are positive integers, and M1 is greater than or equal to M.

[0231] In one embodiment, the interface module 601 is further configured to receive second indication information, which indicates the activation of N association information among M1 association information, wherein M is greater than N, and M and N are positive integers; the first indication information is used to indicate at least one of the N association relationships.

[0232] In one implementation, the first module includes at least one of the following: part or all of the model structure, model parameters, model hyperparameters, and relevant parameters for model training or model inference.

[0233] Additionally, the communication device 600 can be used to implement the functions of the second device in the above embodiments. The communication device 600 is, for example, the second device described in the various embodiments of FIG3, and may be a RAN node, such as a base station.

[0234] The interface module 601 can be used to send first instruction information to the first device to indicate the association between the first model and the second model.

[0235] In one implementation, the first indication information is used to indicate that the first module is shared with the first model and the second model; wherein the first model includes the first module and the second model includes the first module.

[0236] In one implementation, the first indication information includes the name and / or index number of the first module.

[0237] In one implementation, the first indication information includes the name and / or index number of the second model.

[0238] In one implementation, the association relationship is a quasi-co-addressable (QCL) relationship.

[0239] In one embodiment, the interface module 601 can be used to send configuration information to the first device, the configuration information including at least one of the following: a correspondence between I models and I model index numbers; a correspondence between J modules and J module index numbers, wherein a model includes at least one module; or, a correspondence between M1 association information and M index numbers, wherein the association information indicates that at least two different models share at least one module; I, J, M1 and M are positive integers, and M1 is greater than or equal to M.

[0240] In one embodiment, the interface module 601 can be used to send a second indication information to the first device to indicate the activation of N association information among M1 association information, wherein M is greater than N, and M and N are positive integers; the first indication information is used to indicate at least one of the N association relationships.

[0241] In one implementation, the first module includes at least one of the following: part or all of the model structure, model parameters, model hyperparameters, and relevant parameters for model training or model inference.

[0242] In summary, when the communication device 600 is used to implement the functions performed by the first device or the second device in the above embodiments, other functions that the communication device 600 can implement can be referred to the relevant descriptions of any of the embodiments shown above, and will not be elaborated further.

[0243] In a simplified embodiment, those skilled in the art will recognize that the communication device 600 can take the form shown in FIG2. For example, the processor 201 in FIG2 can invoke computer execution instructions stored in memory 203 to cause the communication device 20 to perform the methods described in the above-described method embodiments.

[0244] For example, the function / implementation process of the processing module 602 in FIG6 can be implemented by the processor 201 in FIG2.

[0245] For example, the function / implementation process of the interface module 601 in Figure 6 can be implemented through the communication interface 204 in Figure 2.

[0246] It is understood that one or more of the above modules or units can be implemented by software, hardware, or a combination of both. When any of the above modules or units are implemented by software, the software exists as computer program instructions and is stored in memory. The processor can be used to execute the program instructions and implement the above method flow. The processor can be built into a SoC (System-on-Chip) or ASIC, or it can be a separate semiconductor chip. In addition to the core that executes software instructions for computation or processing, the processor may further include necessary hardware accelerators, such as field-programmable gate arrays (FPGAs), programmable logic devices (PLDs), or logic circuits that implement dedicated logic operations.

[0247] When the above modules or units are implemented in hardware, the hardware can be any one or any combination of a CPU, microprocessor, digital signal processing (DSP) chip, microcontroller unit (MCU), artificial intelligence processor, ASIC, SoC, FPGA, PLD, application-specific digital circuit, hardware accelerator, or non-integrated discrete device, which can run the necessary software or perform the above method flow independently of software.

[0248] Optionally, this application also provides a chip system, including: at least one processor and an interface, wherein the at least one processor is coupled to a memory via the interface, and when the at least one processor executes a computer program or instructions in the memory, the method in any of the above method embodiments is executed. In one possible implementation, the chip system further includes a memory. Optionally, the chip system may be composed of chips or may include chips and other discrete devices; this application does not specifically limit this.

[0249] Optionally, this application also provides a computer-readable storage medium. All or part of the processes in the above method embodiments can be implemented by a computer program instructing related hardware. This program can be stored in the aforementioned computer-readable storage medium. When executed, the program can include the processes described in the above method embodiments. The computer-readable storage medium can be an internal storage unit of the communication device in any of the foregoing embodiments, such as the hard disk or memory of the communication device. The aforementioned computer-readable storage medium can also be an external storage device of the communication device, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the communication device. Further, the aforementioned computer-readable storage medium can include both internal storage units and external storage devices of the communication device. The aforementioned computer-readable storage medium is used to store the aforementioned computer program and other programs and data required by the communication device. The aforementioned computer-readable storage medium can also be used to temporarily store data that has been output or will be output.

[0250] Optionally, this application also provides a computer program product. All or part of the processes in the above method embodiments can be executed by a computer program instructing related hardware. This program can be stored in the above computer program product, and when executed, it can include the processes described in the above method embodiments.

[0251] Optionally, this application also provides computer instructions. All or part of the processes in the above method embodiments can be executed by computer instructions instructing related hardware (such as a computer, processor, network device, or terminal device). The program can be stored in the aforementioned computer-readable storage medium or the aforementioned computer program product.

[0252] Optionally, this application also provides a communication system, including: the first device and the second device in the above embodiments. For example, the first device may be a terminal or a network device, and the second device may be a terminal or a network device.

[0253] Through the above description of the embodiments, those skilled in the art can clearly understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0254] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0255] The units described as separate components may or may not be physically separate. A component shown as a unit can be one or more physical units; that is, it can be located in one place or distributed in multiple different locations. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0256] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0257] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A communication method characterized by comprising: Applied to a first device, the method includes: Receive first indication information, which is used to indicate the association relationship between the first model and the second model; The first model is determined based on the first instruction information.

2. The method according to claim 1, characterized in that, The first model includes a first module, and the second model includes the first module; The first indication information, used to indicate the association between the first model and the second model, includes: The first indication information is used to indicate that the first module is shared with the first model and the second model; Determining the first model based on the first indication information includes: The first module in the first model is determined based on the first module in the second model.

3. The method of claim 2, wherein, The first indication information includes the name and / or index number of the first module.

4. The method according to claim 1 or 2, characterized in that, The first indication information includes the name and / or index number of the second model.

5. The method according to any one of claims 1 to 4, characterized in that, The association relationship is a quasi-co-addressable (QCL) relationship.

6. The method according to any one of claims 1 to 5, characterized in that, The method further includes: Obtain configuration information, which includes at least one of the following: The correspondence between I models and I model index numbers; The model contains J modules and their corresponding index numbers, where each module includes at least one module; or, The correspondence between M1 related information and M index numbers, wherein the related information indicates that at least two different models share at least one module; I, J, M1 and M are positive integers, and M1 is greater than or equal to M.

7. The method of claim 6, wherein, Before receiving the first indication information, the method further includes: Receive second indication information, which is used to indicate the activation of N associated information out of M1 associated information, where M is greater than N, and M and N are positive integers; The first indication information is used to indicate at least one of the N associations.

8. The method of claim 2 or 3, wherein, The first module includes at least one of the following: The model's partial or complete structure, parameters, hyperparameters, and parameters related to model training or inference.

9. A communication method characterized by comprising: Applied to a second device, the method includes: Send a first instruction message to the first device, the first instruction message being used to indicate the association relationship between the first model and the second model.

10. The method according to claim 9, characterized in that, The first model includes the first module and the second model includes the first module; The first indication information, used to indicate the association between the first model and the second model, includes: The first indication information is used to indicate that the first module shares the first model and the second model.

11. The method according to claim 10, characterized in that, The first indication information includes the name and / or index number of the first module.

12. The method according to claim 9 or 10, characterized in that, The first indication information includes the name and / or index number of the second model.

13. The method according to any one of claims 9-12, characterized in that, The association relationship is a quasi-co-addressable (QCL) relationship.

14. The method according to any one of claims 9-13, characterized in that, The method further includes: Send configuration information to the first device, the configuration information including at least one of the following: The correspondence between I models and I model index numbers; The model contains J modules and their corresponding index numbers, where each module includes at least one module; or, The correspondence between M1 related information and M index numbers, wherein the related information indicates that at least two different models share at least one module; I, J, M1 and M are positive integers, and M1 is greater than or equal to M.

15. The method according to claim 14, characterized in that, Before receiving the first indication information, the method further includes: Receive second indication information, which is used to indicate the activation of N associated information out of M1 associated information, where M is greater than N, and M and N are positive integers; The first indication information is used to indicate at least one of the N associations.

16. The method according to claim 10 or 11, characterized in that, The first module includes at least one of the following: The model's partial or complete structure, parameters, hyperparameters, and parameters related to model training or inference.

17. A communication device, characterized in that, The communication device is used to implement the method as described in any one of claims 1-16.

18. A communication device, characterized in that, Includes a processor for running computer programs or instructions to cause the communication device to perform the method as described in any one of claims 1-16.

19. The communication device according to claim 18, characterized in that, The communication device further includes a memory coupled to the processor, the memory being used to store the computer program or instructions.

20. A computer-readable storage medium having a computer program or instructions stored thereon, characterized in that, When the computer program or instructions are executed, the method as described in any one of claims 1-16 is performed.

21. A computer program product, said computer program product comprising computer program code, characterized in that, When the computer program code is run on a computer, the method as described in any one of claims 1-16 is performed.

22. A chip, characterized in that, Includes a processor configured to perform the method as described in any one of claims 1-16.

Images