Communication method, communication apparatus, and storage medium

Abstract

Disclosed in the embodiments of the present application are a communication method, a communication apparatus, and a storage medium, which are applied to the technical field of wireless communications, and are used for specifying acquisition manners for AI models of different versions. The method in the embodiments of the present application comprises: sending a request message, wherein the request message is used for requesting a first AI model of a first version, the first AI model of the first version is a model obtained after updating the first AI model of a second version, and the first version and the second version belong to the same version branch; and receiving the first AI model of the first version. In the embodiments of the present application, the procedure in which a first apparatus requests a first AI model of a first version is specified, such that the manner in which the first apparatus acquires the first AI model of the first version is defined, thereby enabling the first apparatus to acquire an updated first AI model on the basis of a request message.

Description

Communication methods, communication devices and storage media

[0001] This application claims priority to Chinese Patent Application No. 202510197094.4, filed on February 20, 2025, entitled "Communication Method, Communication Device and Storage Medium", the entire contents of which are incorporated herein by reference. Technical Field

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

[0003] Artificial intelligence (AI) and machine learning (ML) can be used for various wireless tasks, such as time-frequency domain channel estimation, prediction, and beam prediction related to wireless channels. AI / ML models for specific tasks require data collection, model training, selection, switching, and retraining based on applicable conditions.

[0004] During model updates, the same model may generate different versions. For example, for a transformer structure model, there can be different numbers of layers, different numbers of attention heads, etc. Different numbers of layers can correspond to different versions, and different numbers of attention heads can also correspond to different versions.

[0005] Therefore, how to manage different versions of AI models has become an urgent problem to be solved. Summary of the Invention

[0006] This application provides a communication method, communication device, and storage medium for clarifying the acquisition methods of different versions of AI models.

[0007] This application provides a communication method, optionally executed by a first device. The first device can be a terminal device, a component or device applied to the terminal device (e.g., a processor, circuit, chip, or chip system), or a logic module or software capable of implementing all or part of the terminal device's functions. The first device can also be a network device, a component or device applied to the network device (e.g., a processor, circuit, chip, or chip system), or a logic module or software capable of implementing all or part of the network device's functions (e.g., a central unit (CU), a distributed unit (DU), or a radio unit (RU)). In this method, the first device sends a request message requesting a first version of a first AI model. The first version of the first AI model is an updated model of a second version of the first AI model, and the first and second versions belong to the same version branch. The first device receives the first version of the first AI model.

[0008] Based on the first aspect of this application, by clarifying the process of the first device requesting the first version of the first AI model, the method by which the first device obtains the first version of the first AI model is defined, so that the first device can obtain the updated first AI model based on the request message.

[0009] In some possible implementations, the request message includes indication information for indicating a first version.

[0010] By instructing the recipient of the request message to determine the first AI model of the first version based on the instruction information, the first device is able to obtain the first AI model of the first version from the recipient of the request message.

[0011] In some possible implementations, the indication information includes a first model identifier and a first version identifier, wherein the first model identifier is used to indicate a first AI model and the first version identifier is used to indicate a first version.

[0012] By defining a first version identifier, different versions of the first AI model can be indicated by the version identifier, thereby enabling the first device to request the first version of the first AI model based on the first model identifier and the first version identifier.

[0013] In some possible implementations, the indication information includes a second model identifier, which is used to indicate the first AI model of the first version.

[0014] By defining a second model identifier, different versions of the first AI model can be indicated by the model identifier, thereby enabling the first device to request the first version of the first AI model based on the second model identifier.

[0015] In some possible implementations, the second model identifier includes at least two bits of information, wherein the first bit of the at least two bits is used to indicate the first AI model, and the second bit of the at least two bits is used to indicate the first version.

[0016] By defining the content of the second model identifier, the method by which the first device requests the first version of the first AI model based on the second model identifier is clarified.

[0017] In some possible implementations, the instruction information is also used to indicate a second version.

[0018] In some possible implementations, the request message includes indication information for indicating a second version.

[0019] By instructing the recipient of the second version, the recipient of the request message is able to determine the updated model version based on the instruction information, thereby enabling the first device to obtain the first AI model of the first version from the recipient of the request message.

[0020] In some possible implementations, the indication information includes a first model identifier and a second version identifier, wherein the first model identifier is used to indicate a first AI model and the second version identifier is used to indicate a second version.

[0021] By defining a second version identifier, different versions of the first AI model can be indicated by the version identifier, thereby enabling the first device to request the first version of the first AI model based on the first model identifier and the second version identifier.

[0022] In some possible implementations, the indication information includes a third model identifier, which is used to indicate the first AI model in the second version.

[0023] By defining a second model identifier, different versions of the first AI model can be indicated by the model identifier, thereby enabling the first device to request the first version of the first AI model based on the third model identifier.

[0024] In some possible implementations, the third model identifier includes at least two bits of information, the third bit of which is used to indicate the first AI model, and the fourth bit of which is used to indicate the second version.

[0025] By defining the content of the third model identifier, the method by which the first device requests the first version of the first AI model based on the third model identifier is clarified.

[0026] In some possible implementations, the first device may also receive model version information, which is used to indicate the first version of the first AI model.

[0027] Since the first device can receive model version information, it can request the first version of the first AI model from the recipient of the request message based on the model version information.

[0028] In some possible implementations, the first version corresponds to any one of the first model parameter quantization accuracy, the first model parameter quantity, and the first model performance, and the second version corresponds to any one of the second model parameter quantization accuracy, the second model parameter quantity, and the second model performance.

[0029] A second aspect of this application provides a communication method. Optionally, the execution subject of this method may be a second device, which may be a network device, a component or device applied to the network device (e.g., a processor, circuit, chip, or chip system), or a logic module or software (e.g., CU, DU, or RU) capable of implementing all or part of the functions of the network device. In this method, the second device receives a request message, which requests a first version of a first AI model. The first version of the first AI model is an updated model of the second version of the first AI model, and the first and second versions belong to the same version branch. The second device then sends the first version of the first AI model.

[0030] In some possible implementations, the request message includes indication information for indicating a first version.

[0031] In some possible implementations, the indication information includes a first model identifier and a first version identifier, wherein the first model identifier is used to indicate a first AI model and the first version identifier is used to indicate a first version.

[0032] In some possible implementations, the indication information includes a second model identifier, which is used to indicate the first AI model of the first version.

[0033] In some possible implementations, the second model identifier includes at least two bits of information, wherein the first bit of the at least two bits is used to indicate the first AI model, and the second bit of the at least two bits is used to indicate the first version.

[0034] In some possible implementations, the instruction information is also used to indicate a second version.

[0035] In some possible implementations, the request message includes indication information for indicating a second version.

[0036] In some possible implementations, the indication information includes a first model identifier and a second version identifier, wherein the first model identifier is used to indicate a first AI model and the second version identifier is used to indicate a second version.

[0037] In some possible implementations, the indication information includes a third model identifier, which is used to indicate the first AI model in the second version.

[0038] In some possible implementations, the third model identifier includes at least two bits of information, the third bit of which is used to indicate the first AI model, and the fourth bit of which is used to indicate the second version.

[0039] In some possible implementations, the second device may also send model version information, which is used to indicate the first version of the first AI model.

[0040] In some possible implementations, the first version corresponds to any one of the first model parameter quantization accuracy, the first model parameter quantity, and the first model performance, and the second version corresponds to any one of the second model parameter quantization accuracy, the second model parameter quantity, and the second model performance.

[0041] A third aspect of this application provides a communication device, which may be the first device described above. The communication device includes modules or units for performing the methods described in the first aspect and any possible implementation thereof.

[0042] A fourth aspect of this application provides a communication device, which may be the second device described above. The communication device includes modules or units for performing the methods described in the second aspect and any possible implementation thereof.

[0043] A fifth aspect of this application provides a communication device, which may be a first device or a second device, or a component applied to the first device or the second device (e.g., a processor, circuit, chip, or chip system), or a logic module or software (e.g., CU, DU, or RU) capable of implementing all or part of the functions of the first device or the second device. The communication device includes:

[0044] A processor for executing a program that causes the communication device to perform the method as described in the first or second aspect and any possible implementation thereof.

[0045] Optionally, the communication device further includes a memory, and the processor is coupled to the memory; the memory is used to store programs.

[0046] The sixth aspect of this application provides a chip or chip system including at least one processor and a communication interface, the communication interface and at least one processor being interconnected via a line, the at least one processor being used to run computer programs or instructions to perform the communication method described in any of the possible implementations of the first or second aspect.

[0047] The communication interface in the chip can be an input / output interface, pins, or circuits.

[0048] In one possible implementation, the chip or chip system described above in this application further includes at least one memory storing instructions. The memory can be an internal storage unit of the chip, such as a register or cache, or it can be a storage unit of the chip itself, such as a read-only memory or random access memory.

[0049] The seventh aspect of this application provides a communication system, including a communication device that performs the first aspect and any possible implementation thereof, and a communication device that performs the second aspect and any possible implementation thereof.

[0050] An eighth aspect of this application provides a computer-readable storage medium including instructions that, when executed on a computer, cause the computer to perform the method described in the first aspect above, or cause the computer to perform the method described in the second aspect above.

[0051] The ninth aspect of this application provides a computer program product containing instructions that, when run on a computer, cause the computer to perform the method described in the first aspect above, or cause the computer to perform the method described in the second aspect above. Attached Figure Description

[0052] Figures 1a to 1c are schematic diagrams of the communication system provided in this application;

[0053] Figure 2 is a schematic diagram of the AI ​​model lifecycle management provided in this application;

[0054] Figures 3 and 4 are schematic diagrams of the deployment of the model provided in this application;

[0055] Figure 5 is an interactive schematic diagram of the communication method provided in this application;

[0056] Figures 6 to 8 are schematic diagrams of the communication device provided in this application. Detailed Implementation

[0057] First, some terms used in the embodiments of this application will be explained to facilitate understanding by those skilled in the art.

[0058] (1) Terminal device: 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.

[0059] 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 (or "cellular" phones), computers, and data cards. For example, they can be portable, pocket-sized, handheld, computer-embedded, or vehicle-mounted mobile devices that exchange voice and / or data with the RAN. Examples include personal communication service (PCS) phones, cordless phones, session initiation protocol (SIP) phones, wireless local loop (WLL) stations, personal digital assistants (PDAs), tablets, and computers with wireless transceiver capabilities. Wireless terminal equipment can also be called subscriber unit, subscriber station, mobile station (MS), remote station, access point (AP), remote terminal, access terminal, user terminal, user agent, subscriber station (SS), customer premises equipment (CPE), terminal, user equipment (UE), mobile terminal (MT), etc.

[0060] By way of example and not limitation, in this embodiment, the terminal device can also be a wearable device. Wearable devices, also known as wearable smart devices or smart wearable devices, are a general term for devices that utilize wearable technology to intelligently design and develop everyday wearables, such as glasses, gloves, watches, clothing, and shoes. Wearable devices are portable devices that are worn directly on the body or integrated into the user's clothing or accessories. Wearable devices are not merely hardware devices, but also achieve powerful functions through software support, data interaction, and cloud interaction. Broadly speaking, wearable smart devices include those that are feature-rich, large in size, and can achieve complete or partial functions without relying on a smartphone, such as smartwatches or smart glasses, as well as those that focus on a specific type of application function and require the use of other devices such as smartphones, such as various smart bracelets, smart helmets, and smart jewelry for vital sign monitoring.

[0061] Terminals can also be drones, robots, devices in device-to-device (D2D) communication, vehicles to everything (V2X) communication, virtual reality (VR) terminal devices, augmented reality (AR) terminal devices, wireless terminals in industrial control, wireless terminals in self-driving, wireless terminals in telemedicine or telehealth services, wireless terminals in smart grids, wireless terminals in transportation safety, wireless terminals in smart cities, wireless terminals in smart homes, etc.

[0062] Furthermore, the terminal device can also be a terminal device in a future communication system after the 5th generation (5G) communication system, or a terminal device in a future evolved public land mobile network (PLMN). Exemplary terminals include, but are not limited to, vehicles, cellular network terminals (integrated with satellite terminal functions), drones, and Internet of Things (IoT) devices.

[0063] In this embodiment, the terminal device can also obtain AI services provided by the network device. Optionally, the terminal device can also have AI processing capabilities.

[0064] (2) Network equipment: This can be equipment within a wireless network. For example, network equipment can be a RAN node (or device) that connects terminal devices to the wireless network, and can also be called a base station. Currently, some examples of RAN equipment include: base station, evolved NodeB (eNodeB), gNB (gNodeB) in 5G communication systems, 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 architecture, network equipment can include central unit (CU) nodes, distributed unit (DU) nodes, or RAN equipment including both CU and DU nodes.

[0065] Optionally, RAN nodes can also be macro base stations, micro base stations, indoor stations, relay nodes, donor nodes, or radio controllers in cloud radio access network (CRAN) scenarios. RAN nodes can also be servers, wearable devices, vehicles, or in-vehicle equipment. For example, the access network equipment in vehicle-to-everything (V2X) technology can be a roadside unit (RSU).

[0066] In another possible scenario, multiple RAN nodes collaborate to assist the terminal in achieving wireless access, with different RAN nodes each implementing some of the base station's functions. For example, RAN nodes can be CUs, DUs, CUs (control plane, CP), CUs (user plane, UP), or radio units (RUs). CUs and DUs can be configured separately or included in the same network element, such as a baseband unit (BBU). RUs can be included in radio equipment or radio units, such as remote radio units (RRUs), active antenna units (AAUs), radio heads (RHs), or remote radio heads (RRHs).

[0067] 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 open access network (open RAN, O-RAN, or 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 modules and hardware modules.

[0068] Network devices can be other devices that provide wireless communication functions for terminal devices. The embodiments of this application do not limit the specific technology or form of the network device. For ease of description, the embodiments of this application are not limited.

[0069] Network equipment may also include core network equipment.

[0070] In this embodiment of the application, the network device may also have network nodes with AI capabilities, which can provide AI services to terminals or other network devices. For example, it may be an AI node, computing node, RAN node with AI capabilities, or core network element with AI capabilities on the network side (access network or core network).

[0071] In this application embodiment, the device for implementing the function of the network device can be the network device itself, or it can be a device capable of supporting the network device in implementing the function, such as a chip system. This device can be disposed within the network device. In the technical solutions provided in this application embodiment, the example of a network device being used to implement the function of the network device is used to describe the technical solutions provided in this application embodiment.

[0072] (3) Configuration and Pre-configuration: In this application, both configuration and pre-configuration are used. Configuration refers to the network device / server sending configuration information or parameter values ​​to the terminal via messages or signaling, so that the terminal can determine communication parameters or transmission resources based on these values ​​or information. Pre-configuration is similar to configuration; it can be parameter information or parameter values ​​negotiated in advance between the network device / server and the terminal device, or it can be parameter information or parameter values ​​used by the base station / network device or terminal device as specified in standard protocols, or it can be parameter information or parameter values ​​pre-stored in the base station / server or terminal device. This application does not limit this.

[0073] Furthermore, these values ​​and parameters can be changed or updated.

[0074] (4) The terms "system" and "network" in the embodiments of this application can be used interchangeably. "Multiple" refers to two or more. "And / or" describes the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist simultaneously, or B exists alone, where A and B can be singular or plural. The character " / " generally indicates that the related objects before and after are in an "or" relationship. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, "at least one of A, B and C" includes A, B, C, AB, AC, BC or ABC. And, unless otherwise specified, the ordinal numbers such as "first" and "second" mentioned in the embodiments of this application are used to distinguish multiple objects and are not used to limit the order, sequence, priority or importance of multiple objects.

[0075] (5) In the embodiments of this application, "send" and "receive" indicate the direction of signal transmission. For example, "send information to XX" can be understood as the destination of the information being XX, which may include sending directly through the air interface or sending indirectly through the air interface by other units or modules. "Receive information from YY" can be understood as the source of the information being YY, which may include receiving directly from YY through the air interface or receiving indirectly from YY through the air interface by other units or modules. "Send" can also be understood as the "output" of the chip interface, and "receive" can also be understood as the "input" of the chip interface.

[0076] In other words, sending and receiving can occur between devices, such as between network devices and terminal devices, or within a device, such as between components, modules, chips, software modules, or hardware modules within the device via buses, wiring, or interfaces.

[0077] It is understandable that information may undergo necessary processing, such as encoding and modulation, between the source and destination, but the destination can understand the valid information from the source. Similar statements in this application can be interpreted in a similar way and will not be elaborated further.

[0078] (6) In the embodiments of this application, "instruction" may include direct instruction and indirect instruction, as well as explicit instruction and implicit instruction. The information indicated by a certain piece of information (as described below, the instruction information) is called the information to be instructed. In the specific implementation process, there are many ways to indicate the information to be instructed, such as, but not limited to, directly indicating the information to be instructed, such as the information to be instructed itself or its index. It can also indirectly indicate the information to be instructed by indicating other information, where there is an association between the other information and the information to be instructed; or it can only indicate a part of the information to be instructed, while the other parts of the information to be instructed are known or pre-agreed upon. For example, the instruction can be implemented by using a pre-agreed (e.g., protocol predefined) arrangement order of various information, thereby reducing the instruction overhead to a certain extent. This application does not limit the specific method of instruction. It is understood that for the sender of the instruction information, the instruction information can be used to indicate the information to be instructed, and for the receiver of the instruction information, the instruction information can be used to determine the information to be instructed.

[0079] In this application, unless otherwise specified, the same or similar parts between the various embodiments can be referred to each other. In the various embodiments of this application, and in the various methods / designs / implementations within each embodiment, unless otherwise specified or logically conflicting, the terminology and / or descriptions between different embodiments and between the various methods / designs / implementations within each embodiment are consistent and can be mutually referenced. The technical features in different embodiments and the various methods / designs / implementations within each embodiment can be combined to form new embodiments, methods, or implementations based on their inherent logical relationships. The following descriptions of the embodiments of this application do not constitute a limitation on the scope of protection of this application.

[0080] This application can be applied to long-term evolution (LTE) systems, new radio (NR) systems, or future communication systems beyond 5G. These communication systems include at least one network device and / or at least one terminal device.

[0081] Please refer to Figure 1a, which is a schematic diagram of the architecture of the communication system 1000 used in the embodiments of this application. As shown in Figure 1a, the communication system may include a radio access network (RAN) 100. Optionally, the communication system 1000 may also include a core network 200 and an Internet 300. The RAN 100 includes at least one RAN node (110a and 110b in Figure 1a, collectively referred to as 110) and at least one terminal (120a-120j in Figure 1a, collectively referred to as 120). The RAN 100 may also include other RAN nodes, such as wireless relay devices and / or wireless backhaul devices (not shown in Figure 1a). The terminal 120 is wirelessly connected to the RAN node 110, and the RAN node 110 is wirelessly or wiredly connected to the core network 200. The core network equipment in the core network 200 and the RAN node 110 in the RAN 100 may be independent and different physical devices, or they may be the same physical device integrating the logical functions of the core network equipment and the logical functions of the RAN node. Terminals can be connected to each other, as can RAN nodes, via wired or wireless means.

[0082] Taking the communication system shown in Figure 1a as an example, in addition to performing communication-related services, different devices (including network devices and network devices, network devices and terminal devices, and / or terminal devices and terminal devices) may also perform AI-related services.

[0083] As shown in Figure 1b, taking a network device as a base station as an example, the base station can perform communication-related services and AI-related services with one or more terminal devices, and different terminal devices can also perform communication-related services and AI-related services.

[0084] As shown in Figure 1c, taking terminal devices including televisions and mobile phones as an example, communication-related services and AI-related services can also be performed between televisions and mobile phones.

[0085] The technical solutions provided in this application can be applied to wireless communication systems (such as the systems shown in Figures 1a, 1b, or 1c). For example, AI network elements can be introduced into the communication system provided in this application to realize some or all AI-related operations. AI network elements can also be called AI nodes, AI devices, AI entities, AI modules, AI models, or AI units, etc. The AI ​​network element can be built into a network element within the communication system. For example, the AI ​​network element can be an AI module built into: access network equipment, core network equipment, cloud server, or operation, administration, and maintenance (OAM) to realize AI-related functions. The OAM can act as the network management system for the core network equipment and / or the access network equipment. Alternatively, the AI ​​network element can also be an independently set network element in the communication system. Optionally, the terminal or its built-in chip can also include an AI entity to realize AI-related functions.

[0086] Optionally, in communication systems, AI application cases may include, but are not limited to: channel state information (CSI) feedback enhancement, beam management enhancement, positioning accuracy enhancement, network energy saving, load balancing, and mobility optimization. These will be explained below.

[0087] 1. Enhanced CSI feedback:

[0088] Channel quality information (CSI) is the channel attribute of a communication link, reported by the terminal device to the network device. By reporting this information, the terminal device can select an appropriate modulation and coding scheme (MCS) to adapt to changing wireless channels. For example, the terminal device might perform channel estimation based on the received channel state information-reference signal (CSI-RS) and then feed back the CSI-RS to the network device. This information serves as input to the network device's model, enabling AI model training. Applying AI to CSI feedback enhancement can reduce overhead, improve accuracy, and enhance predictive capabilities.

[0089] CSI-RS feedback enhancement may include at least one sub-function, such as: CSI compression, CSI prediction, and CSI-RS configuration signaling reduction. CSI compression may further include CSI compression in at least one domain: spatial, time, and frequency.

[0090] 2. Enhanced beam management.

[0091] Enhanced beam management primarily aims to discover the strongest transmit / receive beam pairs. AI-based sparse beam prediction can improve accuracy. This can be achieved through both network-side and terminal-side AI sparse beam prediction, based on AI training and inference. Taking terminal-side AI sparse beam prediction as an example, the pre-trained AI model on the terminal device can be provided by the network or pre-stored on the terminal device. During training, the network device scans all possible beams and then reports the transmit beam pattern to the terminal device. Once training is complete, the network device only needs to scan a small subset of beams, and the terminal device then feeds back the inference results. AI-based beam management can achieve beam prediction in, for example, the temporal and / or spatial domains, reducing overhead and latency and improving beam selection accuracy.

[0092] Beam management enhancements may include at least one sub-function, such as: beam scan matrix prediction and optimal (or better) beam prediction.

[0093] 3. Enhanced positioning accuracy:

[0094] In line-of-sight (LOS) or non-line-of-sight (NLOS) scenarios, AI-based positioning can improve positioning accuracy with a smaller number of TRP antennas. Positioning enhancement can include at least one sub-function, such as: positioning enhancement based on access network devices, positioning enhancement based on positioning management function network elements, and positioning enhancement based on terminal devices.

[0095] 4. Network energy saving:

[0096] Network energy conservation can be achieved through cell activation / deactivation, load reduction, coverage improvement, or other RAN setting adjustments. AI technology can be used to optimize energy-saving decisions by leveraging data collected within the RAN network. AI algorithms can predict energy efficiency and load status for the next cycle, which can be used to assist in cell activation / deactivation decisions to save energy. Based on the predicted load, the system can dynamically configure energy-saving strategies to maintain a balance between system performance and energy efficiency, and reduce energy consumption.

[0097] 5. Load balancing:

[0098] Load balancing can distribute the load evenly between cells and across different areas within a cell, or transfer some traffic from congested cells, or offload users across a single cell, carrier, or access standard, thereby improving network performance. Using AI models to enhance load balancing performance—such as inputting various measurements and feedback from terminal devices and network nodes, as well as historical data—can provide a higher quality user experience and increase system capacity.

[0099] 6. Mobility Management:

[0100] Mobility management is a solution that ensures service continuity for mobile devices by minimizing dropped calls, radio link failures (RLFs), unnecessary handovers, and ping-pong effects. AI can enhance mobility management by, for example, reducing the probability of unexpected events, predicting device location / mobility / performance, and routing traffic.

[0101] It should be understood that the definitions of the above technical terms are merely illustrative. For example, as technology continues to develop, the scope of the above definitions may also change, and the embodiments of this application are not intended to limit the scope.

[0102] It should be understood that the definitions of the above technical terms are merely illustrative. For example, as technology continues to develop, the scope of the above definitions may also change, and the embodiments of this application are not intended to limit the scope.

[0103] For example, an AI function may include multiple AI sub-functions.

[0104] Optionally, AI application cases are also called AI application scenarios or AI functions.

[0105] As described above regarding AI application examples, AI can be widely used to improve network performance in areas such as CSI feedback enhancement, beam management, positioning accuracy enhancement, energy saving, mobility enhancement, and load balancing. AI models can typically be deployed on the network side and / or the terminal device side. The training of AI models relies on the collection of training data, which can come from measurements and feedback from the terminal devices.

[0106] The following is a brief introduction to the concepts that may be involved in this application.

[0107] AI can endow machines with human-like intelligence, for example, allowing them to use computer hardware and software to simulate certain intelligent human behaviors. To achieve artificial intelligence, machine learning methods can be employed. In machine learning, machines learn (or train) a model using training data. This model represents the mapping between inputs and outputs. The learned model can be used for reasoning (or prediction), that is, it can be used to predict the output corresponding to a given input. This output can also be called the reasoning result (or prediction result).

[0108] Machine learning (ML) can include supervised learning, unsupervised learning, and reinforcement learning. Unsupervised learning can also be called learning without supervision.

[0109] Supervised learning, based on collected sample values ​​and labels, uses machine learning algorithms to learn the mapping relationship between sample values ​​and labels, and then expresses this learned mapping relationship using an AI model. The process of training the machine learning model is the process of learning this mapping relationship. During training, sample values ​​are input into the model to obtain the model's predicted values, and the model parameters are optimized by calculating the error between the model's predicted values ​​and the sample labels (ideal values). After the mapping relationship is learned, it can be used to predict new sample labels. The mapping relationship learned in supervised learning can include linear or non-linear mappings. Based on the type of label, the learning task can be divided into classification tasks and regression tasks.

[0110] Unsupervised learning relies on collected sample values ​​to discover inherent patterns within the samples themselves. One type of unsupervised learning algorithm uses the samples themselves as supervisory signals, meaning the model learns the mapping relationship from sample to sample; this is called self-supervised learning. During training, model parameters are optimized by calculating the error between the model's predictions and the samples themselves. Self-supervised learning can be used for signal compression and decompression recovery applications; common algorithms include autoencoders and generative adversarial networks.

[0111] Reinforcement learning, unlike supervised learning, is a type of algorithm that learns problem-solving strategies through interaction with the environment. Unlike supervised and unsupervised learning, reinforcement learning problems do not have explicit "correct" action labels. The algorithm needs to interact with the environment to obtain reward signals from the environment, and then adjust its decision actions to obtain a larger reward signal value. For example, in downlink power control, the reinforcement learning model adjusts the downlink transmission power of each user based on the total system throughput feedback from the wireless network, aiming to achieve a higher system throughput. The goal of reinforcement learning is also to learn the mapping relationship between the environment state and a better (e.g., optimal) decision action. However, because the label of the "correct action" cannot be obtained in advance, the network cannot be optimized by calculating the error between the action and the "correct action." Reinforcement learning training is achieved through iterative interaction with the environment.

[0112] Neural networks (NNs) are a specific model in machine learning techniques. According to the general approximation theorem, neural networks can theoretically approximate any continuous function, thus enabling them to learn arbitrary mappings. Traditional communication systems rely on extensive expert knowledge to design communication modules, while deep learning communication systems based on neural networks can automatically discover hidden pattern structures from large datasets, establish mapping relationships between data, and achieve performance superior to traditional modeling methods.

[0113] The idea behind neural networks comes from the neuronal structure of the brain. For example, each neuron performs a weighted summation of its input values ​​and outputs the result through an activation function.

[0114] Furthermore, neural networks generally consist of multiple layers, each of which may include one or more neurons. Increasing the depth and / or width of a neural network can improve its expressive power, providing more powerful information extraction and abstract modeling capabilities for complex systems. The depth of a neural network can refer to the number of layers it includes, and the number of neurons in each layer can be called the width of that layer. In one implementation, a neural network includes an input layer and an output layer. The input layer processes the received input information through neurons and passes the processing result to the output layer, which then obtains the output of the neural network. In another implementation, a neural network includes an input layer, hidden layers, and an output layer. The input layer processes the received input information through neurons and passes the processing result to the hidden layer. The hidden layer calculates the received processing result and passes the calculation result to the output layer or the next adjacent hidden layer, ultimately obtaining the output of the neural network. A neural network may include one hidden layer or multiple sequentially connected hidden layers, without limitation.

[0115] Neural networks, for example, are deep neural networks (DNNs). Depending on how the network is constructed, DNNs can include feedforward neural networks (FNNs), convolutional neural networks (CNNs), and recurrent neural networks (RNNs).

[0116] A model can also be called an AI model, a rule, or other names. An AI model can be considered a specific method for implementing AI functions. An AI model represents the mapping relationship or function between the model's input and output. AI functions can include one or more of the following: data collection, model training (or model learning), model information dissemination, model inference (or model reasoning, inference, or prediction, etc.), model monitoring or model validation, or inference result publication, etc. AI functions can also be called AI (related) operations or AI-related functions.

[0117] Figure 2 illustrates AI model lifecycle management (LCM). LCM encompasses multiple stages, including data collection, model training, model storage, model inference, and model management. As shown in Figure 3, the overall framework includes the following:

[0118] Data collection is a function that provides input data for model training, management, and inference.

[0119] - Training data: The data required as input for training AI / ML models.

[0120] - Monitoring data: Data required as input for AI / ML model or AI / ML function management.

[0121] - Inference data: The data required as input for AI / ML inference functions.

[0122] Model training is a function that performs AI / ML model training, validation, and testing, and may generate model performance metrics that can be used as part of the model testing process. The model training function can also be responsible for data preparation (e.g., data preprocessing and cleaning, formatting, and transformation) based on the training data provided by the data collection function.

[0123] - Trained / Updated Models: If a model storage function is available, this function is used to deliver trained, validated, and tested AI / ML models to the model storage function, or to deliver updated versions of the model to the model storage function.

[0124] Management is a function responsible for overseeing the operation of AI / ML models or AI / ML functions (e.g., selection / (deactivation) / toggle / rollback) and monitoring (e.g., performance). This function is also responsible for making decisions based on data received from data collection and inference functions to ensure the correctness of inference operations.

[0125] - Management Instructions: Manage the input information required for the inference function. This information may include selecting / disabling / switching an AI / ML model or AI / ML-based function, reverting to non-AI / ML operations (i.e., operations independent of the inference process), etc.

[0126] - Model Transfer / Delivery Request: Used to request a model from the model storage function.

[0127] -Performance Feedback / Retraining Request: Information required as input to the model training function, such as for the purpose of (re)training or updating the model.

[0128] Model inference is a function that uses data provided by the data collection function (i.e., inference data) as input, applies AI / ML models or AI / ML functions, and provides output. The inference function is also responsible for data preparation (e.g., data preprocessing and cleaning, formatting, and transformation) based on the inference data provided by the data collection function, if necessary.

[0129] -Inference Output: Management functions use data to monitor the performance of AI / ML models or AI / ML functions.

[0130] Model storage is a function responsible for storing the trained / updated models that can be used to perform inference functions.

[0131] - Model Transfer / Delivery: Used to deliver AI / ML models to inference functions.

[0132] Figure 3 illustrates a possible model transmission method. In this method, terminal devices are used to train the model. Multiple terminal devices under the same terminal server can upload their trained models to the terminal server for aggregation, and the terminal server then transmits them to the network side for storage. Terminal devices can request models from the network side.

[0133] Figure 4 illustrates another possible model transmission method. In this method, the network side is responsible for training the model, and the trained model is stored by the network side. The terminal device can request the model from the network side.

[0134] During model updates, the same model may generate different versions. For example, for a transformer structure model, there can be different numbers of layers, different numbers of attention heads, etc. Different numbers of layers can correspond to different versions, and different numbers of attention heads can also correspond to different versions. However, the current model identifiers are only used to indicate the functionality of the model and cannot indicate different versions of the model.

[0135] Based on this, this application provides a method. Please refer to Figure 5, which is a schematic diagram of the communication method provided in this application. The method shown in Figure 5 is executed interactively by a first device and a second device. The first device can be a terminal device, or a component or device applied to a terminal device (e.g., a processor, circuit, chip, or chip system), or a logic module or software capable of implementing all or part of the functions of the terminal device. The first device can also be a network device, or a component or device applied to a network device (e.g., a processor, circuit, chip, or chip system), or a logic module or software capable of implementing all or part of the functions of the network device (e.g., CU, DU, or RU). The second device can be a network device, or a component or device applied to a network device (e.g., a processor, circuit, chip, or chip system), or a logic module or software capable of implementing all or part of the functions of the network device (e.g., CU, DU, or RU). The model is deployed on the second device, and the first device requests the model from the second device by sending a request message.

[0136] In one possible scenario, the first device is a terminal device, and the second device is an access network device. The terminal device can request a model from the access network device.

[0137] In another possible scenario, the first device is an access network device and the second device is a core network device. The access network device can request a model from the core network device.

[0138] In another possible scenario, the first device is a terminal device, and the second device is a third-party service (over-the-top, OTT) network element. The terminal device can request the model from the OTT network element.

[0139] The method includes:

[0140] 501. The first device sends a request message to the second device. Correspondingly, the second device receives the request message from the first device.

[0141] The request message is used to request the first AI model of the first version. The first version is an updated version of the second version. The first version and the second version belong to the same version branch. The first AI model of the second version is deployed on the first device.

[0142] In the embodiments of this application, the first AI model can be an AI / ML model or an AI / ML function, and the specific is not limited here.

[0143] Different features of the first AI model correspond to different version branches. Within the model parameter quantization precision branch of the first AI model, different quantization precisions correspond to different versions. For example, if the model parameter quantization precision of the first AI model is 4-bit integer (INT4), then the first AI model is called the second version of the first AI model. If the model parameter quantization precision of the first AI model is 8-bit integer (INT8), then the first AI model is called the first version of the first AI model.

[0144] The request information includes instruction information, which allows the second device to determine the version of the first AI model to be sent to the first device.

[0145] In one possible implementation, the indication information is used to indicate the first version. It should be noted that the first device may, after obtaining the model version information, carry the indication information for indicating the first version in the request message. See step 500c below for details.

[0146] Optionally, the indication information includes a first model identifier and a first version identifier, or more specifically, a first model ID and a first version ID. The first model identifier indicates the first AI model, and the first version identifier indicates the first version. For example, if the first AI model is a transformer architecture model, then the first model identifier indicates the transformer architecture model, and the first version identifier indicates that the model parameter quantization precision is INT8. Table 1 below illustrates one possible implementation of the indication information:

[0147] Table 1: Instruction Information

[0148] As shown in Table 1, the first device may only indicate the first model identifier and the first version identifier to the second device. The second device determines the first AI model based on the first model identifier and determines the first version of the first AI model based on the first version identifier.

[0149] It should be noted that in this application, the model identifier corresponds to the structure / function of the AI ​​model. That is, the model identifier is used to indicate a class of AI models that have a certain model structure or function. For example, the first model identifier is used to indicate a class of AI models with a transformer architecture. Another example is the first model identifier used to indicate a CSI compressed feedback model. Specific limitations are not specified here.

[0150] The correspondence between model identifiers and the functions / structures of AI models, as well as the correspondence between version identifiers and versions, can be predefined, preconfigured, or configured. Therefore, the first device does not need to indicate a specific model or version to the second device, thus saving indication overhead. For example, the correspondence between model identifiers and model structures is shown in Table 2 below:

[0151] Table 2: Correspondence between model identifiers and model structures

[0152] As shown in Table 2, model identifier 1 corresponds to the AI ​​model of the transformer architecture, model identifier 2 corresponds to the AI ​​model of the encoder-decoder architecture, model identifier 3 corresponds to the AI ​​model of the generative adversarial network, and model identifier 4 corresponds to the convolutional neural network (CNN) / recurrent neural network (RNN) / multi-layer perceptron (MLP) architecture.

[0153] The above model structure is only an example. In practical applications, other model structures are also possible, but no specific limitations are made here.

[0154] It should be noted that when the model structure is a two-end model, the AI ​​model requested by the first device is the model of one end (e.g., the sending end model or the receiving end model). For example, when the second device is a network device and the first device is a terminal device, the network device can send different versions of the AI ​​model corresponding to the terminal device in the two-end model to the terminal device.

[0155] It is understandable that one version identifier can correspond to multiple model features, and one model identifier can correspond to multiple version identifiers. For example, Table 3 below shows the correspondence between model identifiers and multiple version identifiers. Table 3 uses the model parameter quantization precision and transformer layer number of the transformer architecture corresponding to the version identifier as an example.

[0156] Table 3: Correspondence between model identifiers and multiple version identifiers

[0157] As shown in Table 3, each version identifier corresponds to two model features: the quantization precision of the model parameters and the number of model parameters, where FP16 represents half-precision floating-point numbers. For example, version identifiers 1, 2, and 3 correspond to the same number of model parameters but different quantization precisions. Version identifiers 1, 4, and 7 correspond to the same quantization precision but different number of model parameters.

[0158] In the examples shown in Table 3, the larger the version number, the higher the quantization accuracy of the model parameters or the more model parameters. This can be understood as follows: the first AI model in a version with lower quantization accuracy is an updated version of the first AI model in a version with lower quantization accuracy; or, the first AI model in a version with more model parameters is an updated version of the first AI model in a version with fewer model parameters.

[0159] In other words, the first AI model corresponding to version 2 can be understood as the updated AI model of the first AI model corresponding to version 1.

[0160] Assume that the AI ​​model currently deployed in the first device is a first AI model with a model parameter quantization precision of INT6 and a model parameter layer of 6.

[0161] As an example, the first device carries version identifier 8 in the instruction information to request a first AI model with more model parameters at the same model parameter quantization precision.

[0162] As another example, the first device carries version identifier 6 in the instruction information to request a first AI model with higher model parameter quantization accuracy under the same number of model parameters.

[0163] As another example, the first device carries version identifier 9 in the instruction information to request a first AI model with higher model parameter quantization accuracy and more model parameters.

[0164] It should be noted that Table 3 only uses two model features as examples. In practical applications, version identifiers can also correspond to model features such as model performance. For example, in the channel compression feedback use case, generalized cosine similarity (GCS) or square generalized cosine similarity (SGCS) is used to measure performance. An example is shown in Table 4 below. Table 4 uses the version identifier corresponding to the SGCS of the transformer architecture as an example.

[0165] Table 4: Correspondence between model identifiers and multiple version identifiers

[0166] As shown in Table 4, SGCS measures performance by calculating the square of the cosine similarity between the compressed and recovered channel and the original channel. The value of SGCS ranges from [0,1]. The closer the value is to 1, the more similar the compressed and recovered channel is to the original channel, and the better the performance.

[0167] The above model features are merely examples. In practical applications, the indication information may also include other model features, which are not limited here.

[0168] Optionally, the indication information includes a second model identifier, which is used to indicate the first AI model of the first version. That is, a single identifier can indicate both the model and the version.

[0169] For example, the second model identifier can be represented as ABCD, where different values ​​of A correspond to different AI models; different values ​​of B correspond to different model parameter quantization precision; different values ​​of C correspond to different model parameter quantities; and different values ​​of D correspond to different model performance.

[0170] Optionally, the second model identifier may include at least two bits of information, wherein the first bit of the at least two bits of information is used to indicate the first AI model, and the second bit of the at least two bits of information is used to indicate the first version.

[0171] For example, if the second model is identified as 01.01.01.01, it means that the first AI model is a transformer architecture model with a model parameter quantization precision of INT4, a transformer layer number of 4, and an SGCS of 0.7.

[0172] For example, if the second model is identified as 01.10.11.10, it means that the first AI model is a transformer architecture model with a model parameter quantization precision of INT8, a transformer layer number of 8, and an SGCS of 0.8.

[0173] Optionally, the instruction information can also be used to indicate a second version. That is, the first device can also report a second version of the locally deployed first AI model to the second device.

[0174] At this time, the instruction information also includes a second version identifier or a third model identifier. The implementation method of the second version identifier can refer to the implementation method of the first version identifier mentioned above, and the implementation method of the third model identifier can refer to the implementation method of the second model identifier mentioned above. The specific details will not be repeated here.

[0175] Optionally, the third model identifier may include at least two bits of information, wherein the third bit of the at least two bits is used to indicate the first AI model, and the fourth bit of the at least two bits is used to indicate the second version.

[0176] For example, if the third model is identified as 01.01.01.01, it means that the first AI model is a transformer architecture model with a model parameter quantization precision of INT4, a transformer layer number of 4, and an MMSE of 1.0.

[0177] For example, if the third model is identified as 01.10.11.10, it means that the first AI model is a transformer architecture model with a model parameter quantization precision of INT6, a transformer layer number of 8, and an MMSE of 0.1.

[0178] In another possible implementation, the instruction information is used to indicate a second version. That is, the first device indicates the version of the currently deployed first AI model to the second device, so that the second device can determine the updated version based on the version currently deployed by the first device.

[0179] Optionally, the indication information includes a first model identifier and a second version identifier. A description of the first model identifier and the second version identifier can be found in the foregoing embodiments, and will not be repeated here.

[0180] Optionally, the indication information includes a third model identifier. A description of the third model identifier can be found in the foregoing embodiments, and will not be repeated here.

[0181] 502. The second device performs model matching.

[0182] Specifically, the second device searches for the updated model in the stored models based on the instruction information sent by the first device.

[0183] In one possible implementation, the indication information is used to indicate the first AI model of the first version, and the second device can then search in the stored models whether the first AI model of the first version exists based on the indication information.

[0184] In another possible implementation, the indication information is used to indicate the first AI model of the second version, and the second device can determine one or more of the first AI models updated to the second version based on the indication information.

[0185] It should be noted that the second device executes step 503 only if the stored model includes the first version of the first AI model.

[0186] 503. The second device sends a first version of the first AI model to the first device. Correspondingly, the first device receives the first version of the first AI model from the second device.

[0187] In one possible implementation, the second device sends the first version of the first AI model to the first device if it matches the first version of the first AI model.

[0188] In another possible implementation, the instruction information is used to indicate the second version of the first AI model, then the second device can send one or more second version updated first AI models to the first device, the one or more first AI models including the first version of the first AI model.

[0189] Optionally, the embodiment shown in FIG5 further includes step 500a. Step 500a may be performed before step 501.

[0190] 500a, Second device acquires model.

[0191] The second device acquires multiple AI models, which can be trained on the network (NW) side, obtained by receiving AI models from the terminal server, or obtained by receiving AI models from the NW side server.

[0192] Optionally, the embodiment shown in Figure 5 further includes step 500b. Step 500b may be performed before step 501.

[0193] 500b, The second device performs branch management on the model.

[0194] Different features of an AI model correspond to different version branches, and a version branch includes different versions corresponding to that feature. Here, a model feature of an AI model can be understood as the factors that influence the AI ​​model. For example, the features of an AI model include model parameter quantization precision, model parameter count, and model performance. Each of these three aspects corresponds to a version branch, and within the model parameter quantization precision branch, different levels of precision correspond to different versions.

[0195] Optionally, the embodiment shown in Figure 5 further includes step 500c. Step 500c may be performed before step 501.

[0196] 500c. The second device sends model version information to the first device. Correspondingly, the first device receives the model version information from the second device.

[0197] The second device can send the latest versions after the second version to the first device via model version information.

[0198] For example, the model version information includes a first model identifier and a first version identifier, enabling the first device to request the first version of the first AI model from the second device based on the first model identifier and the first version identifier.

[0199] For example, the model version information includes a second model identifier, enabling the first device to request the first version of the first AI model from the second device based on the second model identifier.

[0200] The communication method in the embodiments of this application has been described above. The communication device in the embodiments of this application is described below. Referring to Figure 6, in one possible implementation, the communication device 600 can be used to execute the process performed by the first device in the embodiment shown in Figure 5. For details, please refer to the relevant descriptions in the foregoing method embodiments. The communication device 600 can be a terminal device, or a component or device applied to a terminal device (e.g., a processor, circuit, chip, or chip system), or a logic module or software capable of implementing all or part of the functions of the terminal device. The communication device 600 can also be a network device, or a component or device applied to a network device (e.g., a processor, circuit, chip, or chip system), or a logic module or software capable of implementing all or part of the functions of the network device.

[0201] The communication device 600 includes an interface module 601 and a processing module 602.

[0202] The processing module 602 is used for data processing. The interface module 601 can implement corresponding communication functions. The interface module 601 can also be called a communication interface or a communication module.

[0203] Optionally, the communication device 600 may further include a storage module, which can be used to store program code, program instructions and / or data. The processing module 602 can read the instructions and / or data in the storage module so that the communication device 600 can implement the aforementioned method embodiments.

[0204] The communication device 600 can be used to perform the actions performed by the first device in the above method embodiments. For example, it can be the first device, a communication module within the first device, or a circuit or chip in the first device responsible for communication functions. The communication device 600 can be the first device or a component configurable within the first device. The processing module 602 is used to perform processing-related operations on the first device side in the above method embodiments. The interface module 601 is used to perform receiving-related operations on the first device side in the above method embodiments.

[0205] Optionally, interface module 601 may include a sending module and a receiving module. The sending module is used to perform the sending operation in the above method embodiments. The receiving module is used to perform the receiving operation in the above method embodiments.

[0206] It should be noted that the communication device 600 may include a transmitting module but not a receiving module. Alternatively, the communication device 600 may include a receiving module but not a transmitting module. Specifically, it depends on whether the above-described scheme performed by the communication device 600 includes both transmitting and receiving actions. For example, the communication device 600 is used to perform the actions performed by the first device in the embodiment shown in FIG. 5. For details, please refer to the relevant descriptions in the embodiment shown in FIG. 5; they will not be elaborated upon here.

[0207] For example, the communication device 600 is used to execute the following scheme:

[0208] Processing module 602 is used to generate request messages;

[0209] Interface module 601 is used to send request messages. The request messages are used to request the first AI model of the first version. The first AI model of the first version is the updated model of the first AI model of the second version. The first version and the second version belong to the same version branch.

[0210] Interface module 601 is also used to receive the first version of the first AI model.

[0211] In another possible implementation, the communication device 600 can be used to execute the process performed by the second device in the embodiment shown in FIG5, as detailed in the relevant descriptions in the foregoing method embodiments.

[0212] For example, the communication device 600 is used to execute the following scheme:

[0213] Interface module 601 is used to receive request messages. The request messages are used to request the first AI model of the first version. The first AI model of the first version is the updated model of the first AI model of the second version. The first version and the second version belong to the same version branch.

[0214] Processing module 602 is used for model matching;

[0215] Interface module 601 is also used to send the first version of the first AI model.

[0216] It should be understood that the specific procedures for each module to perform the above-mentioned corresponding processes have been described in detail in the above method embodiments, and will not be repeated here for the sake of brevity.

[0217] Optionally, when the communication device 600 is a terminal device or a communication module within a terminal device, the processing module 602 in the above embodiments can be implemented by at least one processor or processor-related circuitry. Specifically, the processor may include a modem chip, or a system-on-chip (SoC) chip containing a modem core, or a system-in-package (SIP) chip. The interface module 601 can be implemented by a transceiver or transceiver-related circuitry. The interface module 601 may also be referred to as a communication module or communication interface. The storage module can be implemented by at least one memory.

[0218] Optionally, when the communication device 600 is a circuit or chip in a terminal device responsible for communication functions, such as a modem chip or a SoC chip or SIP chip containing a modem core, the function of the processing module 602 can be implemented by a circuit system in the aforementioned chip that includes one or more processors or processing cores. The function of the interface module 601 can be implemented by the interface circuit or data transceiver circuit on the aforementioned chip.

[0219] The following describes a communication device provided in an embodiment of this application. Please refer to Figure 7, which is a schematic diagram of the structure of a communication device provided in an embodiment of this application. The communication device may be the first device or the second device in the above method embodiments, or it may be a chip, chip system, or processor that supports the first device or the second device in implementing the above methods. This communication device can be used to implement the methods described in the above method embodiments, and for details, please refer to the description in the above method embodiments.

[0220] The communication device may include one or more processors 701, which are connected to a memory 702, an input / output unit 703, and a bus 704. The processor 701 may be a general-purpose processor or a dedicated processor, such as a baseband processor or a central processing unit (CPU). The baseband processor can be used to process communication protocols and communication data, while the CPU can be used to control the communication device (e.g., base station, baseband chip, terminal, terminal chip, DU or CU, etc.), execute software programs, and process data from the software programs.

[0221] Optionally, the communication device may include one or more memories 702, which may store instructions that can be executed on the processor 701, causing the communication device to perform the methods described in the above method embodiments. Optionally, the memories 702 may also store data. The processor 701 and the memories 702 may be provided separately or integrated together.

[0222] Optionally, the communication device may also include a transceiver and an antenna. A transceiver, also called a transceiver unit, transceiver, or transceiver circuit, is used to implement transmission and reception functions. A transceiver may include a receiver and a transmitter; the receiver, also called a receiver circuit, is used to implement the receiving function; the transmitter, also called a transmitter or transmitting circuit, is used to implement the transmitting function.

[0223] In another possible design, the processor 701 may include a transceiver for implementing receive and transmit functions. For example, the transceiver may be a transceiver circuit, an interface, or an interface circuit. The transceiver circuit, interface, or interface circuit for implementing receive and transmit functions may be separate or integrated. The aforementioned transceiver circuit, interface, or interface circuit can be used for reading and writing code / data, or it can be used for transmitting or relaying signals.

[0224] In another possible design, the processor 701 may optionally store instructions that, when executed, cause the communication device to perform the methods described in the above method embodiments. The instructions may be stored in the processor 701; in this case, the processor 701 may be implemented in hardware.

[0225] In another possible design, the communication device may include a circuit that can perform the transmitting or receiving or communication functions of the first or second device in the aforementioned method embodiments. The processor and transceiver described in this application embodiment can be implemented on integrated circuits (ICs), analog ICs, radio frequency integrated circuits (RFICs), mixed-signal ICs, application-specific integrated circuits (ASICs), printed circuit boards (PCBs), electronic devices, etc. The processor and transceiver can also be manufactured using various IC process technologies, such as complementary metal oxide semiconductors (CMOS), n-type metal-oxide-semiconductor (NMOS), p-type metal oxide semiconductors (PMOS), bipolar junction transistors (BJTs), bipolar CMOS (BiCMOS), silicon germanium (SiGe), gallium arsenide (GaAs), etc.

[0226] The communication device described in the above embodiments may be a first device or a second device, but the scope of the communication device described in the embodiments of this application is not limited thereto, and the structure of the communication device may not be limited to FIG. 7. The communication device may be a standalone device or part of a larger device. For example, the communication device may be:

[0227] (1) Independent integrated circuit IC, or chip, or chip system or subsystem;

[0228] (2) A collection of one or more ICs, optionally including a storage component for storing data and instructions;

[0229] (3) ASIC, such as modem;

[0230] (4) Modules that can be embedded in other devices;

[0231] (5) Receivers, terminals, smart terminals, cellular phones, wireless devices, handheld devices, mobile units, vehicle-mounted devices, network devices, cloud devices, artificial intelligence devices, etc.

[0232] (6) Others, etc.

[0233] For communication devices that can be chips or chip systems, please refer to the schematic diagram of the chip structure shown in Figure 8. The chip 800 shown in Figure 8 includes a processor 801 and an interface 802. Optionally, it may also include a memory 803. The number of processors 801 can be one or more, and the number of interfaces 802 can be multiple.

[0234] For cases where the chip is used to implement the functions of the first or second device in the embodiments of this application:

[0235] The interface 802 is used to receive or output signals;

[0236] The processor 801 is used to perform data processing operations of the first device or the second device.

[0237] It is understood that some optional features in the embodiments of this application can be implemented independently in certain scenarios without relying on other features, such as the current solution on which they are based, to solve the corresponding technical problems and achieve the corresponding effects. Alternatively, they can be combined with other features as needed in certain scenarios. Correspondingly, the communication device given in the embodiments of this application can also implement these features or functions, which will not be elaborated here.

[0238] It should be understood that the processor in the embodiments of this application can be an integrated circuit chip with signal processing capabilities. In implementation, the steps of the above method embodiments can be completed by integrated logic circuits in the processor's hardware or by instructions in software form. The processor described above can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0239] It is understood that the memory in the embodiments of this application can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAK are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous linked dynamic random access memory (SLDRAM), and direct rambus RAM (DR RAM). It should be noted that the memory used in the systems and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0240] This application also provides a computer-readable storage medium including instructions that, when executed on a computer, cause the computer to perform the methods described in the foregoing embodiments. The computer-readable storage medium may be a non-volatile storage medium.

[0241] This application also provides a computer program product containing instructions that, when run on a computer, cause the computer to perform the methods described in the foregoing embodiments.

[0242] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0243] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of 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 system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection between apparatuses or units through some interfaces, and may be electrical, mechanical, or other forms.

[0244] The units described as separate components may or may not be physically separate. 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 the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0245] 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.

[0246] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0247] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions. When the computer instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium accessible to a computer or a data storage device such as a server or data center that integrates one or more available media. The available media may be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., high-density digital video discs (DVDs)), or semiconductor media (e.g., solid-state disks (SSDs)).

[0248] The embodiments described in this application are merely some, not all, of the embodiments described herein. All other embodiments obtained by those skilled in the art based on the embodiments described herein without inventive effort are within the scope of protection of this application.

[0249] References to "one embodiment" or "some embodiments" as described in this application mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0250] In the description of this application, unless otherwise stated, " / " means "or". For example, A / B can mean A or B. "And / or" in this document is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, and B alone. Furthermore, "at least one" means one or more, and "multiple" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or multiple items. For example, at least one of a, b, or c can represent: a, b, c; a and b; a and c; b and c; or a and b and c. Where a, b, and c can be single or multiple.

Claims

1. A communication method, characterized in that, The method includes: Send a request message, the request message being used to request the first AI model of the first version, the first AI model of the first version being an updated model of the first AI model of the second version, the first version and the second version belonging to the same version branch; Receive the first AI model of the first version.

2. The method according to claim 1, characterized in that, The request message includes indication information, which is used to indicate the first version.

3. The method according to claim 2, characterized in that, The indication information includes a first model identifier and a first version identifier, wherein the first model identifier is used to indicate the first AI model and the first version identifier is used to indicate the first version.

4. The method according to claim 2, characterized in that, The indication information includes a second model identifier, which is used to indicate the first AI model of the first version.

5. The method according to claim 4, characterized in that, The second model identifier includes at least two bits, wherein the first bit of the at least two bits is used to indicate the first AI model, and the second bit of the at least two bits is used to indicate the first version.

6. The method according to any one of claims 2 to 5, characterized in that, The instruction information is also used to indicate the second version.

7. The method according to claim 1, characterized in that, The request message includes indication information, which is used to indicate the second version.

8. The method according to claim 6 or 7, characterized in that, The indication information includes a first model identifier and a second version identifier, wherein the first model identifier is used to indicate the first AI model and the second version identifier is used to indicate the second version.

9. The method according to claim 6 or 7, characterized in that, The indication information includes a third model identifier, which is used to indicate the first AI model of the second version.

10. The method according to claim 9, characterized in that, The third model identifier includes at least two bits of information, wherein the third bit of the at least two bits is used to indicate the first AI model, and the fourth bit of the at least two bits is used to indicate the second version.

11. The method according to any one of claims 1 to 10, characterized in that, The method further includes: Receive model version information, which is used to indicate the first version of the first AI model.

12. The method according to any one of claims 1 to 11, characterized in that, The first version corresponds to any one of the following: the quantization accuracy of the first model parameters, the number of first model parameters, and the performance of the first model. The second version corresponds to any one of the following: the quantization accuracy of the second model parameters, the number of second model parameters, and the performance of the second model.

13. A communication method, characterized in that, The method includes: Receive a request message, the request message is used to request the first AI model of the first version, the first AI model of the first version is the updated model of the first AI model of the second version, and the first version and the second version belong to the same version branch; Send the first version of the first AI model.

14. The method according to claim 13, characterized in that, The request message includes indication information, which is used to indicate the first version.

15. The method according to claim 14, characterized in that, The indication information includes a first model identifier and a first version identifier, wherein the first model identifier is used to indicate the first AI model and the first version identifier is used to indicate the first version.

16. The method according to claim 14, characterized in that, The indication information includes a second model identifier, which is used to indicate the first AI model of the first version.

17. The method according to claim 16, characterized in that, The second model identifier includes at least two bits, wherein the first bit of the at least two bits is used to indicate the first AI model, and the second bit of the at least two bits is used to indicate the first version.

18. The method according to any one of claims 14 to 17, characterized in that, The instruction information is also used to indicate the second version.

19. The method according to claim 13, characterized in that, The request message includes indication information, which is used to indicate the second version.

20. The method according to claim 18 or 19, characterized in that, The indication information includes a first model identifier and a second version identifier, wherein the first model identifier is used to indicate the first AI model and the second version identifier is used to indicate the second version.

21. The method according to claim 18 or 19, characterized in that, The indication information includes a third model identifier, which is used to indicate the first AI model of the second version.

22. The method according to claim 21, characterized in that, The third model identifier includes at least two bits of information, wherein the third bit of the at least two bits is used to indicate the first AI model, and the fourth bit of the at least two bits is used to indicate the second version.

23. The method according to any one of claims 13 to 22, characterized in that, The method further includes: Send model version information, which is used to indicate the first version of the first AI model.

24. The method according to any one of claims 13 to 23, characterized in that, The first version corresponds to any one of the following: the quantization accuracy of the first model parameters, the number of first model parameters, and the performance of the first model. The second version corresponds to any one of the following: the quantization accuracy of the second model parameters, the number of second model parameters, and the performance of the second model.

25. A communication device, characterized in that, Includes modules or units for performing the method as described in any one of claims 1 to 12, or for performing the method as described in any one of claims 13 to 24.

26. A communication device, characterized in that, include: A processor for executing a program that causes the communication device to perform the method as described in any one of claims 1 to 12, or causes the communication device to perform the method as described in any one of claims 13 to 24.

27. A computer-readable storage medium, characterized in that, Includes instructions that, when executed on a computer, cause the computer to perform the method as claimed in any one of claims 1 to 12, or cause the computer to perform the method as claimed in any one of claims 13 to 24.

28. A computer program product containing instructions, characterized in that, When it is run on a computer, it causes the computer to perform the method as described in any one of claims 1 to 12, or causes the computer to perform the method as described in any one of claims 13 to 24.

29. A chip, characterized in that, The chip includes a processor and a communication interface, the communication interface being used to receive data and transmit it to the processor, or to send data from the processor to another chip; The processor is configured to perform the processing-related steps as described in any one of claims 1 to 12, or to perform the processing-related steps as described in any one of claims 13 to 24; The communication interface is used to perform the transmission and reception related steps as described in any one of claims 1 to 12, or to perform the transmission and reception related steps as described in any one of claims 13 to 24.

Images