Communication method and related apparatus

Abstract

Provided in the present application are a communication method and a related apparatus. The method may be executed by means of a first communication apparatus. The method comprises: a first communication apparatus receiving first indication information sent by a second communication apparatus, wherein the first indication information is used for determining the transmission integrity of at least one first parameter segment sent by the second communication apparatus, and each first parameter segment comprises some parameters of an artificial intelligence (AI) model; and then, on the basis of the first indication information, the first communication apparatus determining whether the at least one first parameter segment is completely received. In the method, the integrity of AI model parameter transmission can be determined by means of indication information. The preparation status of models on both a terminal side and a network side can be evaluated, so as to be used for inference, thereby cooperatively improving the performance of wireless communication; in addition, a condition for requiring a request for retransmission can be determined more accurately, thereby reducing signaling redundancy caused by repeated requests and improving the system transmission efficiency.

Description

A communication method and related apparatus

[0001] This application claims priority to Chinese Patent Application No. 202510370564.2, filed with the State Intellectual Property Office of China on March 26, 2025, entitled "A Communication Method and Related Device", the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to the field of wireless communication, and more particularly to a communication method, apparatus, communication system, computer storage medium, and computer program product. Background Technology

[0003] Currently, artificial intelligence (AI) technology is being introduced into wireless communication systems. AI technology can be used for wireless channel information compression and reconstruction, beam management, and positioning enhancement, and trained AI models can be used to improve the performance of wireless communication.

[0004] AI-based radio access networks (RANs) can deploy AI models on both the terminal (e.g., user equipment, UE) and the network side to collaboratively complete wireless communication. Model training can be performed on one side, with parameters transmitted to the other via the radio interface. For example, a UE can request the network side to send the trained model parameters for inference and other tasks.

[0005] However, related technologies struggle to ensure the completeness of model parameter transmission, making it difficult for communication systems to determine whether all required parameters have been received and whether retransmission is necessary. On one hand, incomplete parameter reception may affect model updates on the receiving side, thus impacting communication performance. On the other hand, the receiving side may misjudge incomplete model parameter transmission, unnecessarily requesting retransmission, causing signaling redundancy and affecting system transmission efficiency. Summary of the Invention

[0006] This application provides a communication method to solve the problem of difficulty in ensuring the integrity of model parameter transmission in related technologies.

[0007] In a first aspect, this application provides a communication method, which can be executed by a first communication device, the method comprising:

[0008] A first communication device receives a first instruction message sent by a second communication device. The first instruction message is used to determine the transmission integrity of at least one first parameter segment sent by the second communication device, where each first parameter segment contains partial parameters of an artificial intelligence (AI) model. Then, the first communication device determines, based on the first instruction message, whether at least one first parameter segment has been fully received.

[0009] This method can determine the integrity of AI model parameter transmission through indication information. On the one hand, it can assess the readiness of the models on both the terminal and the network so that they can be used for inference and collaboratively improve the performance of wireless communication. On the other hand, it can more accurately determine the conditions for requesting retransmission, reduce signaling redundancy caused by repeated requests, and improve system transmission efficiency.

[0010] In some possible implementations, the first communication device may further receive at least one second parameter segment from the second communication device, wherein the at least one second parameter segment is included in at least one first parameter segment. Then, the first communication device can determine whether at least one first parameter segment has been fully received based on the first indication information. Specifically, if the number of first parameter segments indicated by the first indication information is the same as the number of received second parameter segments, or if the identifier of the first parameter segment indicated by the first indication information is the same as the identifier of the second parameter segment, the first communication device can determine that at least one first parameter segment has been fully received; if the number of first parameter segments indicated by the first indication information is different from the number of received second parameter segments, or if the identifier of the first parameter segment indicated by the first indication information is different from the identifier of the second parameter segment, the first communication device can determine that at least one first parameter segment has not been fully received. Thus, the first communication device can directly determine whether the transmitted first parameter segments have been fully received by comparing the differences in quantity or identifier, which is relatively simple to implement.

[0011] In some possible implementations, the first indication information is also used to indicate the end-of-transmission identifier of the first parameter segment. The identifier of the first parameter segment includes the number of the first parameter segment sent. If the numbers of at least one second parameter segment are consecutive and the first communication device receives the end-of-transmission identifier, the first communication device can determine that at least one first parameter segment has been fully received. If the numbers of at least one second parameter segment are not consecutive or the first communication device does not receive the end-of-transmission identifier, the first communication device can determine that at least one first parameter segment has not been fully received. In this way, the first communication device can determine whether the parameter segment has been fully received by the continuity of the numbers of the sent parameter segments. When the numbers are not consecutive, the parameter segment can be directly determined to be lost in real time without waiting for all parameter segments to be transmitted, which is highly efficient.

[0012] In some possible implementations, if the first parameter segment is not fully received, the first communication device can also send a first retransmission request to the second communication device. The first retransmission request instructs the retransmission of all the first parameter segments sent by the second communication device, or the retransmission of the unreceived first parameter segments. This allows for model updates based on the obtained retransmission parameter segments, improving the performance of the wireless communication system. Simultaneously, requesting the retransmission of the unreceived first parameter segments makes the retransmission process more efficient and reduces signaling overhead.

[0013] In some possible implementations, each first parameter segment corresponds to a layer of the AI ​​model, and the parameters in each first parameter segment are used to update the parameters of the corresponding layer of the AI ​​model. Simultaneously, the first and second communication devices can pre-determine this correspondence, thus linking the parameter segments to the layers of the model, facilitating model recovery and updating.

[0014] For example, in some possible implementations, the first parameter segment can correspond one-to-one with the layers of the AI ​​model, thus making it easier to segment the parameter segment using the existing model structure.

[0015] For example, in some possible implementations, the first parameter segment sent can correspond one-to-one with the packets to be transmitted in the AI ​​model. Each packet to be transmitted in the AI ​​model corresponds to at least one layer or a portion of the parameters within a layer that requires parameter transmission. This allows for a more flexible determination of the number of parameters in a parameter segment. For instance, when the model structure is complex and the data volume is large, a layer of the model can correspond to multiple packets to be transmitted or the first parameter segment; when the model structure is simple and the data volume is small, multiple layers of the model can be mapped to a single packet to be transmitted or the first parameter segment, thus reducing the number of transmissions and saving signaling overhead.

[0016] In some possible implementations, the first indication information is transmitted through the Radio Resource Control (RRC) layer. It should be noted that the first indication information can be transmitted directly through the RRC layer, or it can be added to a new AI layer, and then transmitted transparently or after parsing by the RRC layer.

[0017] Secondly, this application provides a communication method, which can be executed by a first communication device, the method comprising:

[0018] The first communication device receives a second indication message sent by the second communication device. This second indication message is used to determine the transmission integrity of at least one third parameter segment received by the second communication device. Each third parameter segment includes partial parameters of an artificial intelligence (AI) model. Then, the first communication device can determine, based on the second indication message, whether at least one third parameter segment represents all the parameter segments sent by the first communication device. Thus, the first communication device, as the sender of model parameters, can determine the integrity of the AI ​​model parameter transmission through the second indication message, thereby understanding the readiness status of the model receiver, more accurately determining whether retransmission of model parameters is necessary, reducing signaling redundancy caused by repeated transmissions, and improving system transmission efficiency.

[0019] In some possible implementations, the first communication device may also send at least one first parameter segment to the second communication device.

[0020] In some possible implementations, if the number of third parameter segments indicated by the second indication information is the same as the number of first parameter segments, or if the identifier of the third parameter segment indicated by the second indication information is the same as the identifier of the first parameter segment, the first communication device can determine that at least one third parameter segment is all the parameter segments sent by the first communication device. If the number of third parameter segments indicated by the second indication information is different from the number of first parameter segments, or if the identifier of the third parameter segment indicated by the second indication information is different from the identifier of the first parameter segment, the first communication device can determine that at least one third parameter segment is not all the parameter segments sent by the first communication device. Thus, the first communication device can directly determine whether the sent first parameter segments have been completely received by comparing the differences in quantity or identifier, which is relatively simple to implement.

[0021] In some possible implementations, the first communication device may also send a third indication message to the second communication device. This third indication message indicates to the second communication device whether at least one third parameter segment is part of all parameter segments sent by the first communication device. The third indication message also indicates whether the second communication device can request a retransmission. Thus, the second communication device, as the parameter receiver, can determine the integrity of the parameter segment transmission and whether it can request a retransmission of the parameter segment from the sender based on the third indication message.

[0022] In some possible implementations, the first communication device can also receive a second retransmission request sent by the second communication device, and transmit all the first parameter segments sent by the first communication device or the first parameter segments not received by the second communication device according to the second retransmission request. This allows the second communication device to update the model parameters based on the retransmitted data, improving the performance and efficiency of wireless communication.

[0023] In some possible implementations, each first parameter segment corresponds to a layer of the AI ​​model, and the parameters in each first parameter segment are used to update the parameters of the corresponding layer of the AI ​​model. Simultaneously, the first and second communication devices can pre-determine this correspondence, thus linking the parameter segments to the layers of the model, facilitating model recovery and updating.

[0024] For example, in some possible implementations, the first parameter segment can correspond one-to-one with the layers of the AI ​​model, thus making it easier to segment the parameter segment using the existing model structure.

[0025] For example, in some possible implementations, the first parameter segment sent can correspond one-to-one with the packets to be transmitted in the AI ​​model. Each packet to be transmitted in the AI ​​model corresponds to at least one layer or a portion of the parameters within a layer that requires parameter transmission. This allows for a more flexible determination of the number of parameters in a parameter segment. For instance, when the model structure is complex and the data volume is large, a layer of the model can correspond to multiple packets to be transmitted or the first parameter segment; when the model structure is simple and the data volume is small, multiple layers of the model can be mapped to a single packet to be transmitted or the first parameter segment, thus reducing the number of transmissions and saving signaling overhead.

[0026] Thirdly, this application provides a communication method that can be executed by a second communication device, the method comprising:

[0027] The second communication device sends a first indication message to the first communication device. This first indication message is used to determine the transmission integrity of at least one first parameter segment sent by the second communication device. Each first parameter segment includes partial parameters of an artificial intelligence (AI) model. Thus, the first communication device can determine the integrity of the parameter transmission based on the first indication message, and subsequently determine whether to request parameter retransmission, ensuring the smooth progress of model updates.

[0028] In some possible implementations, the second communication device may also receive a first retransmission request sent by the first communication device, and retransmit all of the first parameter segments according to the first retransmission request, or retransmit the first parameter segments that the first communication device has not received.

[0029] Fourthly, this application provides a communication method that can be executed by a second communication device, the method comprising:

[0030] The second communication device sends a second indication message to the first communication device. This second indication message is used to determine the transmission integrity of at least one third parameter segment received by the second communication device. Each third parameter segment includes partial parameters of the artificial intelligence (AI) model. Thus, the first communication device can determine the integrity of the parameter transmission based on the second indication message, and subsequently determine whether to request parameter retransmission, ensuring the smooth progress of model updates.

[0031] In some possible implementations, the second communication device may also receive at least one first parameter segment sent by the first communication device.

[0032] In some possible implementations, the second communication device may also receive third indication information sent by the first communication device. The third indication information is used to indicate whether at least one third parameter segment is all the parameter segments sent by the first communication device. The third indication information is also used to indicate whether the second communication device may request retransmission.

[0033] In some possible implementations, the second communication device may also send a second retransmission request to the first communication device when at least one third parameter segment is not all the parameter segments sent by the first communication device. The second retransmission request is used to instruct the retransmission of all first parameter segments or the retransmission of the first parameter segments that were not received.

[0034] Fifthly, this application provides a communication device that has the functions of implementing the first or second aspect described above. For example, the communication device includes modules, units, or means corresponding to the operations involved in the first or second aspect described above. These modules, units, or means can be implemented by software, hardware, or a combination of software and hardware.

[0035] Sixthly, this application provides a communication device that has the functions of implementing the third or fourth aspects mentioned above. For example, the communication device includes modules, units, or means corresponding to the operations involved in the third or fourth aspects mentioned above. These modules, units, or means can be implemented by software, hardware, or a combination of software and hardware.

[0036] In a seventh aspect, this application provides a communication device including an interface circuit and one or more processors. The one or more processors are coupled to a memory. The memory stores part or all of the necessary computer programs or instructions for implementing the functions described in the first or second aspect. The one or more processors are executable to carry out the computer programs or instructions, which, when executed, cause the communication device to implement the methods in any possible design or implementation of the first or second aspect. The interface circuit is used to implement communication functions within the communication device and / or communication functions between the communication device and other devices or components.

[0037] In some possible implementations, the processor is used to communicate with other devices or components through the interface circuit.

[0038] In some possible implementations, the communication device may also include the memory.

[0039] The aforementioned communication device may be a terminal, or a communication and / or computing module in a terminal, or a chip in a terminal responsible for communication functions such as a modem chip (also known as a baseband chip) or a SoC or SIP chip containing a modem module, or a circuit or chip in a terminal responsible for communication and / or computing functions (such as a GPU, AI processor, or ASIC), or a logical node or logical module capable of implementing all or part of the terminal functions.

[0040] Eighthly, this application provides a communication device including an interface circuit and one or more processors. The one or more processors are coupled to a memory. The memory stores part or all of the necessary computer program or instructions for implementing the functions described in the third or fourth aspect above. The one or more processors are executable to the computer program or instructions, which, when executed, cause the communication device to implement the methods in any possible design or implementation of the third or fourth aspect above. The interface circuit is used to implement the communication functions within the communication device and / or the communication functions between the communication device and other devices or components.

[0041] In some possible implementations, the processor is used to communicate with other devices or components through the interface circuit.

[0042] In one possible implementation, the communication device may also include the memory.

[0043] The aforementioned communication device may be an access network device, or a module (e.g., a circuit, chip, or chip system) in the access network device, or a circuit or chip (e.g., a GPU, AI processor, or ASIC) in the access network device that is responsible for communication and / or computing functions, or a logical node or logical module that can implement all or part of the functions of the access network device.

[0044] Ninthly, this application provides a communication system, which includes a first communication device and a second communication device. The first communication device is used to implement the functions of the first or second aspect described above, and the second communication device is used to implement the functions of the third or fourth aspect described above.

[0045] In a tenth aspect, this application provides a computer-readable storage medium storing computer-readable instructions that, when read and executed by a computer, cause the computer to perform any of the possible designs in the first to fourth aspects described above.

[0046] In one aspect, this application provides a computer program product that, when read and executed by a computer, causes the computer to perform any of the possible designs in the first to fourth aspects described above.

[0047] The effects of the solutions provided in any of the third to eleventh aspects above can be referenced to the corresponding descriptions in the first or second aspects.

[0048] Based on the implementation methods provided in the above aspects, this application can be further combined to provide more implementation methods. Attached Figure Description

[0049] Figure 1 is a schematic diagram of the application framework of a communication system provided in an embodiment of this application;

[0050] Figure 2 is a schematic diagram of the application framework of another communication system provided in an embodiment of this application;

[0051] Figure 3 is a flowchart of a communication method provided in an embodiment of this application;

[0052] Figure 4 is a schematic diagram of a parameter segmentation method in a model provided by an embodiment of this application;

[0053] Figure 5 is a schematic diagram of a parameter segmentation method in a model provided by an embodiment of this application;

[0054] Figures 6A and 6B are schematic diagrams of parameter segmentation methods in a set of models provided in the embodiments of this application;

[0055] Figures 7A and 7B are schematic diagrams of parameter segmentation methods in another set of models provided in the embodiments of this application;

[0056] Figures 8A and 8B are schematic diagrams of parameter segmentation methods in another set of models provided in the embodiments of this application;

[0057] Figure 9 is a schematic diagram of a communication method provided in an embodiment of this application;

[0058] Figure 10 is a schematic diagram of a communication method under an open RAN architecture provided in an embodiment of this application;

[0059] Figure 11 is a schematic diagram of the structure of a first communication device provided in an embodiment of this application;

[0060] Figure 12 is a schematic diagram of the structure of a second communication device provided in an embodiment of this application;

[0061] Figure 13 is a schematic diagram of the structure of a terminal device provided in an embodiment of this application;

[0062] Figure 14 is a schematic diagram of the structure of a network device provided in an embodiment of this application. Detailed Implementation

[0063] The technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments.

[0064] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a particular order or sequence. It should be understood that such terms are interchangeable where appropriate so that the embodiments described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0065] It should be understood that the term "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, where A and B can be single or multiple. Additionally, the character " / " in this document generally indicates that the preceding and following related objects are in an "or" relationship. Furthermore, "at least one of the following" or similar expressions in this document are used to represent any combination of the listed items; for example, at least one of A, B, and / or C can represent the following six situations: A alone, B alone, C alone, A and B simultaneously, B and C simultaneously, A and C simultaneously, and A, B, and C simultaneously, where A, B, and C can be single or multiple.

[0066] It is understood that in this application, "instruction" can include direct instruction, indirect instruction, explicit instruction, and implicit instruction. When describing a certain instruction information to indicate A, it can be understood that the instruction information carries A, directly indicates A, or indirectly indicates A.

[0067] In this application, the information indicated by the instruction information is called the information to be instructed. In specific implementations, there are many ways to instruct the information to be instructed, such as, but not limited to, directly instructing the information to be instructed, such as the information to be instructed itself or its index; indirectly instructing the information to be instructed by instructing other information, where there is a relationship between the other information and the information to be instructed; or instructing only a part of the information to be instructed, while the other parts are known or pre-agreed upon. For example, the instruction of specific information can be achieved by using a pre-agreed (e.g., protocol-defined) arrangement of various pieces of information, thereby reducing instruction overhead to some extent.

[0068] The information to be instructed can be sent as a whole or divided into multiple sub-information messages, and the sending period and / or timing of these sub-information messages can be the same or different. This application does not limit the specific sending method. The sending period and / or timing of these sub-information messages can be predefined, for example, according to a protocol, or configured by the transmitting device by sending configuration information to the receiving device.

[0069] It is understood that "send" and "receive" in this application refer to the direction of signal transmission. For example, "send information to XX" can be understood as the destination of the information being XX, which can include direct transmission via the air interface or indirect transmission via the air interface from other units or modules. "Receive information from YY" can be understood as the source of the information being YY, which can include direct reception from YY via the air interface or indirect reception from YY via the air interface from 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.

[0070] 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.

[0071] 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.

[0072] First, the communication system involved in the embodiments of this application is introduced. The technical solution of this application can be applied to cellular communication systems related to the 3rd Generation Partnership Project (3GPP). For example, fourth-generation (4G) communication systems, 5G communication systems, and communication systems after the fifth generation. For example, future communication systems. For example, the fourth-generation communication system may include the Long Term Evolution (LTE) communication system. The fifth-generation communication system may include the New Radio (NR) communication system. The technical solution of this application can also be applied to wireless fidelity (WiFi) systems, communication systems supporting the convergence of multiple wireless technologies, device-to-device (D2D) systems, or vehicle-to-everything (V2X) communication systems.

[0073] The communication systems to which this application applies include terminal equipment and network equipment. Terminal equipment and network equipment are described below.

[0074] Terminal equipment, also known as user equipment (UE), mobile station (MS), mobile terminal (MT), fixed wireless access (FWA), customer premises equipment (CPE), etc., refers to devices that include wireless communication capabilities (providing voice / data connectivity to users). Examples include handheld devices with wireless connectivity, in-vehicle devices, and machine-type communication (MTC) terminals. Currently, terminal devices can include: mobile phones, tablets, laptops, PDAs, mobile internet devices (MIDs), wearable devices, virtual reality (VR) devices, augmented reality (AR) devices, wireless terminals in industrial control, wireless terminals in self-driving (e.g., drones, vehicles), wireless terminals in remote medical surgery, wireless terminals in smart grids, wireless terminals in transportation safety, wireless terminals in smart cities, and wireless terminals in smart homes. For example, wireless terminals in self-driving can be drones, helicopters, or airplanes. For example, wireless terminals in vehicle-to-everything (V2X) can be in-vehicle equipment, vehicle-mounted equipment, in-vehicle modules, vehicles, or ships. Wireless terminals in industrial control can be cameras, robots, or robotic arms. Wireless terminals in smart homes can be televisions, air conditioners, robot vacuums, speakers, or set-top boxes. The terminal device can also be a device or module that is connected to the communication system shown above and has corresponding communication functions. The terminal device usually contains a communication module, circuit or chip that performs the corresponding communication function, and the terminal device is also configured with program instructions for performing the corresponding communication function.

[0075] It should be noted that the terminal device can be a device or apparatus with a chip, or a device or apparatus with integrated circuitry, or a chip, chip system, module, or control unit in the device or apparatus shown above; the specific application is not limited to any particular type. It should also be noted that in this application, when referring to a terminal device, it can refer to the terminal device itself, or to the chip, functional module, or integrated circuit within the terminal device that performs the method provided in this application; the specific application is not limited to any particular type.

[0076] A network device is a device deployed in a radio access network to provide wireless communication functions for terminal devices. Network devices may also be referred to as radio access network (RAN) entities, access nodes, network nodes, access network equipment, or communication devices, etc.

[0077] Specifically, the network equipment can be access network equipment for cellular systems related to the 3rd Generation Partnership Project (3GPP). For example, fourth-generation (4G) mobile communication systems, 5G mobile communication systems, or future mobile communication systems. The network equipment can also be access network equipment in open RAN (O-RAN or ORAN) or cloud radio access network (CRAN). Alternatively, the network equipment can also be access network equipment in a communication system resulting from the integration of two or more of the above communication systems.

[0078] Network equipment includes, but is not limited to: evolved Node B (eNB), radio network controller (RNC), Node B (NB), base station controller (BSC), base transceiver station (BTS), home base station (e.g., home evolved Node B, or home Node B, HNB), baseband unit (BBU), access point (AP) in wireless fidelity (WIFI) systems, macro base station, micro base station, wireless relay node, donor node, radio controller in CRAN scenarios, wireless backhaul node, transmission point (TP), or transmission and receiving point (TRP). Network equipment can also be access network equipment in 5G mobile communication systems. For example, a next-generation NodeB (gNB) in a new radio (NR) system, a transmission and reception point (TRP), a TP, or one or more antenna panels (including multiple antenna panels) of a base station in a 5G mobile communication system. Alternatively, network equipment can also be network nodes constituting a gNB or transmission point. Examples include a centralized unit (CU), a distributed unit (DU), a CU-control plane (CP), a CU-user plane (UP), or a radio unit (RU). CUs and DUs can be separate or included in the same network element. For example, a BBU. RUs can be included in radio equipment or radio units. For example, in a remote radio unit (RRU), an active antenna unit (AAU), or a remote radio head (RRH). Alternatively, network equipment can also be a server, wearable device, vehicle, or in-vehicle equipment. For example, in V2X technology, network devices can be roadside units (RSUs).

[0079] To support artificial intelligence (AI) technology in wireless networks, AI nodes may be introduced into the network. AI nodes can be AI network elements or AI modules.

[0080] AI nodes can be deployed in one or more of the following locations within the communication system: access network nodes (RAN nodes), terminal devices, or core network devices. Alternatively, AI nodes can be deployed independently, for example, in a location other than any of the aforementioned devices, such as in the host or cloud server of an over-the-top (OTT) system. AI nodes can communicate with other devices in the communication system, which can be one or more of the following: network devices, terminal devices, or core network elements.

[0081] It is understood that this application does not limit the number of AI nodes. For example, when there are multiple AI nodes, these nodes can be divided based on function, such as different AI nodes being responsible for different functions.

[0082] It can also be understood that AI nodes can be independent devices, or they can be integrated into the same device to achieve different functions. Alternatively, they can be network elements in hardware devices, software functions running on dedicated hardware, or virtualization functions instantiated on a platform (e.g., a cloud platform). This application does not limit the specific form of the aforementioned AI nodes.

[0083] Figure 1 is a schematic diagram of a possible application framework in a communication system. As shown in Figure 1, the communication system includes an example diagram of an open RAN architecture (CU-DU decoupled architecture), which may include other components besides those shown in the figure.

[0084] In a communication system, network elements are connected via interfaces or air interfaces. These network element nodes, such as core network equipment, access network nodes (RAN nodes), and one or more devices in the terminal, may also be equipped with one or more AI modules (only one is shown in the figure for clarity). The access network node can be a single RAN node or can include multiple RAN nodes, for example, including CU and DU. The CU and / or DU may also be equipped with one or more AI modules.

[0085] Optionally, the CU can be further divided into CU-CP and CU-UP. One or more AI models are configured in CU-CP and / or CU-UP. The AI ​​modules are used to implement corresponding AI functions. AI modules deployed in different network elements can be the same or different. Depending on the parameter configuration, the AI ​​module can implement different functions. An AI module can have one or more models. A model can infer an output, which includes one or more parameters. The learning, training, or inference processes of different models can be deployed on different nodes or devices, or they can be deployed on the same node or device.

[0086] Figure 2 illustrates a possible application framework in a communication system. As shown in Figure 2, the communication system includes a RAN intelligent controller (RIC). For example, the RIC can be the AI ​​module shown in Figure 1, used to implement AI-related functions. RICs include near-real-time RICs (near-RT RICs) and non-real-time RICs (non-RT RICs). Non-real-time RICs primarily process non-real-time information, such as data that is not sensitive to latency, with latency in the order of seconds. Real-time RICs primarily process near-real-time information, such as data that is relatively sensitive to latency, with latency in the order of tens of milliseconds.

[0087] Near real-time (NRT) RICs are used for model training and inference. For example, they are used to train AI models and then use those models for inference. NRT RICs can obtain network-side and / or terminal-side information from RAN nodes (e.g., CUs, CU-CPs, CU-UPs, DUs, compute nodes, and / or RUs) and / or terminals. This information can be used as training data or inference data. NRT RICs can deliver inference results to RAN nodes and / or terminals. Inference results can be exchanged between CUs and DUs, and / or between DUs and RUs. For example, a NRT RIC delivers an inference result to a DU, which then forwards it to an RU.

[0088] Non-real-time RICs are also used for model training and inference. For example, they are used to train AI models and then use those models for inference. Non-real-time RICs can obtain network-side and / or terminal-side information from RAN nodes (e.g., CUs, CU-CPs, CU-UPs, DUs, compute nodes, and / or RUs) and / or terminals. This information can be used as training data or inference data, and the inference results can be delivered to RAN nodes and / or terminals. Inference results can be exchanged between CUs and DUs, and / or between DUs and RUs; for example, a non-real-time RIC delivers inference results to a DU, which then forwards them to an RU.

[0089] Near real-time RICs and non-real-time RICs can also be configured as separate network elements. Near real-time RICs and non-real-time RICs can also be part of other devices. For example, near real-time RICs can be set in RAN nodes (e.g., CU, DU, compute nodes), while non-real-time RICs can be set in OAM, cloud servers, core network devices, or other network devices.

[0090] 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).

[0091] This document explains some basic concepts in the field of AI, which does not limit the scope of protection of the embodiments of this application.

[0092] (1) Machine learning (ML):

[0093] Machine learning is a crucial technological approach to achieving AI. AI endows machines with human-like intelligence, using computer hardware and software to simulate certain intelligent human behaviors, including machine learning and other methods. Machine learning refers to learning models or rules from raw data, such as neural networks, decision trees, and support vector machines. Machine learning can be categorized into supervised learning, unsupervised learning, and reinforcement learning.

[0094] Supervised learning, based on collected sample values ​​and labels, uses machine learning algorithms to learn the mapping relationship between sample values ​​and labels, and expresses this learned mapping relationship using a machine learning model. The process of training the machine learning model is the process of learning this mapping relationship. For example, in signal detection, the noisy received signal is the sample, and the corresponding real constellation point is the label. Machine learning aims to learn the mapping relationship between samples and labels through training, that is, to enable the machine learning model to learn a signal detector. During training, the model parameters are optimized by calculating the error between the model's predicted values ​​and the real labels. Once the mapping relationship is learned, it can be used to predict the sample label of each new sample. The mapping relationship learned in supervised learning can include linear mappings and nonlinear mappings. Based on the type of label, the learning task can be divided into classification tasks and regression tasks.

[0095] Unsupervised learning relies solely on collected sample values, using algorithms to discover inherent patterns within the samples. One type of unsupervised learning algorithm uses the samples themselves as supervisory signals; that is, the model learns the mapping relationship from sample to sample, which 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.

[0096] 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 terminal device 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 the 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.

[0097] Deep neural networks (DNNs) are a specific implementation of machine learning. 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 DNN-based deep learning communication systems can automatically discover hidden pattern structures from large datasets, establish mapping relationships between data, and achieve performance superior to traditional modeling methods.

[0098] Based on their construction method, DNNs can be divided into feedforward neural networks (FNNs), convolutional neural networks (CNNs), and recurrent neural networks (RNNs). FNNs can be neural networks where neurons in adjacent layers are completely connected pairwise, which makes FNNs typically require a large amount of storage space and have high computational complexity.

[0099] CNNs are neural networks specifically designed to process data with a grid-like structure. For example, time-series data (discrete sampling along the time axis) and image data (two-dimensional discrete sampling) can both be considered grid-like data. CNNs do not use all the input information at once for computation; instead, they use a fixed-size window to extract a portion of the information for convolution operations, which significantly reduces the computational cost of model parameters. Furthermore, depending on the type of information extracted by the window (such as people and objects in an image representing different types of information), each window can use different convolution kernels, allowing CNNs to better extract features from the input data.

[0100] Recurrent Neural Networks (RNNs) are a type of distributed neural network (DNN) that utilizes feedback time-series information. Their input includes the current input value and their own output value from the previous time step. RNNs are well-suited for acquiring temporally correlated sequence features, and are particularly applicable to applications such as speech recognition and channel coding / decoding.

[0101] AI models refer to function models that map a certain-dimensional input to a certain-dimensional output, and their parameters can be obtained through machine learning training. For example, f(X) = aX² + b is a quadratic function model, which can be viewed as an AI model. a and b correspond to the model's parameters and can be obtained through machine learning training. Data used for model training, validation, and / or testing in machine learning can form datasets or training datasets. The quantity and / or quality of data in these datasets or training datasets will affect the effectiveness of machine learning. Model training involves selecting an appropriate loss function (which measures the difference between the model's predictions and the true values) and using optimization algorithms to train the model parameters to minimize the loss function value. Model testing involves evaluating the model's performance using test data after training. Model application involves using the trained model to solve real-world problems.

[0102] A neural network, or artificial neural network, is a mathematical model that mimics the behavioral characteristics of animal neural networks to perform distributed parallel information processing. It is a special form of AI model.

[0103] (2) Model training:

[0104] Model training involves selecting an appropriate function (such as a loss function) and using optimization algorithms to train the model parameters so that the difference between the model's predicted values ​​and the ground truth (or target values, labels) tends to be minimized.

[0105] For example, model training methods include, but are not limited to, supervised learning, self-supervised learning, and knowledge distillation.

[0106] (3) Model file and model parameters:

[0107] Model files and / or model parameters can be used to determine the model. Optionally, the model in this application may refer to the model itself, or it may refer to the model files and / or model parameters used to determine the model.

[0108] The model file can be used to indicate the model structure, which may include, but is not limited to, FNN, CNN, or RNN. The model file can have a fixed format, such as a standard predefined format, or a format pre-negotiated by both ends of the interface. Model parameters can refer to parameters in the neural network model, such as, but not limited to, the number of layers in the neural network, the type and weights of neurons in each layer, etc. This application does not limit the method of distributing model parameters.

[0109] Take DNN as an example. The idea behind DNN comes from the neuronal structure of the brain. Each neuron can perform a weighted summation operation on its inputs and then use the result of the weighted summation operation to generate the output through a non-linear function. For example, the input of a neuron is x = [x0, x1, ..., x...]. N-1 The weights corresponding to the inputs are w = [w0, w1, ..., w] N-1 The bias of the weighted summation is b. The nonlinear function f() can take many forms; for example, the nonlinear function f() can be the maximum value function max{0, x}. Then the effect of a neuron's execution is... Where N is a positive integer, and n is a positive integer greater than or equal to 0 and less than or equal to (N-1). The weights of the weighted summation operation of neurons in a neural network and the nonlinear function are called the parameters of the neural network. The parameters of all neurons in a neural network constitute the parameters of the neural network.

[0110] A typical DNN has multiple neural network layers, including an input layer, one or more hidden layers, and an output layer. Generally, the first layer is the input layer, the last layer is the output layer, and the layers in between are hidden layers. Each layer contains multiple neurons. Layers are fully connected; that is, any neuron in the i-th layer is connected to any neuron in the (i+1)-th layer. The input layer processes the received values ​​(i.e., the DNN's input) through neurons and then passes them to the hidden layers. Similarly, the hidden layers pass the computation results to the final output layer, producing the DNN's output.

[0111] Currently, AI technology is being introduced into wireless communication systems. AI technology can be used for wireless channel information compression and reconstruction, beam management, and positioning enhancement, improving wireless communication performance based on trained AI models. In different application scenarios, terminals, such as user equipment (UE), network devices, and core network elements, can possess AI capabilities and be configured with AI models or functions for inference. These AI models or functions can be trained internally by nodes or transmitted from external nodes. That is, one of the model structure or model parameters in the communication system can be predefined, while the other can be sent by the parameter sender (e.g., the network side); alternatively, both the model structure and model parameters can be sent by the parameter sender (e.g., the network side). Sending the model can refer to sending the model file and / or model parameters, and receiving the model can refer to receiving the model file and / or model parameters. This application does not limit the structure and parameters used by the AI ​​model.

[0112] Both the UE and network equipment can deploy AI models to collaboratively achieve wireless communication functions. During deployment, to ensure smooth transmission, the UE and network equipment can transmit a model structure known and supported by both parties in an open format. This allows for the deployment of AI models with the same structure on both sides, facilitating parameter updates. Then, to save training costs, model training can be performed on one side, with parameters transmitted to the other via the wireless interface. For example, the UE can request the network side to send the trained model parameters for inference and other tasks.

[0113] However, related technologies struggle to ensure the completeness of model parameter transmission, making it difficult for communication systems to determine whether all required parameters have been received and whether parameter retransmission is necessary. To conserve resources, AI models with the same structure may implement different communication functions based on parameter updates. Alternatively, the same AI model may implement different communication functions based on specific layers and their corresponding parameters. The parameter sender can then selectively send parameters to update parameters in specific layers for the desired communication function. In this scenario, when the parameter receiver receives only partial parameters, it becomes difficult to determine whether the sender only sent parameters from a portion of the layers or whether the parameters were lost during transmission. Thus, on the one hand, incomplete parameter reception may affect the receiver's model updates, impacting communication performance; on the other hand, the parameter receiver may misjudge incomplete parameter transmission, unnecessarily requesting parameter retransmission, causing signaling redundancy and affecting system transmission efficiency.

[0114] In view of this, this application provides a communication method to solve the problem that the receiver has difficulty determining whether it has completely received the parameters during the above-mentioned model parameter transmission process. Specifically, the method can be executed by a first communication device, and the method includes: the first communication device receiving first indication information sent by a second communication device, wherein the first indication information is used to determine the transmission integrity of at least one first parameter segment sent by the second communication device, and each first parameter segment includes partial parameters of an artificial intelligence (AI) model configured on the first and second communication devices. Then, the first communication device determines, according to the first indication information, whether at least one first parameter segment has been fully received.

[0115] This method can determine the integrity of AI model parameter transmission through indication information. On the one hand, it can assess the readiness of the models on both the terminal and the network so that they can be used for inference and collaboratively improve the performance of wireless communication. On the other hand, it can more accurately determine the conditions for requesting retransmission, reduce signaling redundancy caused by repeated requests, and improve system transmission efficiency.

[0116] To make the technical solution of this application clearer and easier to understand, the communication method of this application is described below with reference to embodiments. In the embodiments of this application, the first communication device refers to a communication device used to determine whether the model parameters have been transmitted completely, and the second communication device transmits AI model parameters between the first communication device and the second communication device.

[0117] It is understood that this application uses network devices and terminals as examples to illustrate the execution of the interaction, but this application does not limit the execution subject of the interaction. The first communication device and the second communication device can be access network devices (also known as network devices) or terminal devices (also known as UEs). In addition, the method executed by the access network device in this application can also be implemented by modules (e.g., circuits, chips, or chip systems) in the access network device, or by logical nodes, logical modules, or software that can implement all or part of the functions of the access network device, or by circuits or chips (such as GPUs, AI processors, or ASICs) in the access network device that are responsible for computing functions. The method executed by the terminal in this application can also be implemented by communication / computing modules in the terminal or by circuits or chips (such as modem chips (also known as baseband chips), or SoC chips / SIP chips containing modem cores, or GPUs / AI processors / ASICs) in the terminal that are responsible for communication / computing functions, or by logical nodes, logical modules, or software that can implement all or part of the functions of the terminal.

[0118] Referring to the flowchart of a communication method shown in Figure 3, the method includes the following steps:

[0119] S302: The first communication device receives a first instruction message and at least one first parameter segment sent by the second communication device.

[0120] Both the first and second communication devices are equipped with AI models of the same structure for collaborative wireless communication. For example, the AI ​​model in the communication device can be used for sending or receiving information. During information transmission, the AI ​​model can be used for channel state information (CSI) compression, channel coding, symbol modulation, resource mapping, waveform modulation, and RF processing, etc. Correspondingly, during information reception, the AI ​​model can be used for CSI reconstruction, channel decoding, symbol demodulation, resource mapping de-mapping, waveform demodulation, or RF processing, etc. Of course, the AI ​​model may also be used in other processes in wireless communication to achieve other functions, such as beam management and mobility management (e.g., positioning, handover), etc. This application embodiment does not impose any limitations on these aspects.

[0121] The AI ​​models deployed on the first and second communication devices can be sent by a third-party device (such as a server) to the first and second communication devices respectively, or they can be pre-deployed on one side, such as the first communication device, and then the first communication device sends the model structure to the second communication device, thereby deploying the models on both devices. It should be noted that the AI ​​models deployed on the first and second communication devices have the same structure, but this application embodiment does not impose any limitations on the specific structure of the AI ​​models.

[0122] To save training costs, model training can be performed on one side, with parameters transmitted to the other side wirelessly. Taking the network device having the trained model parameters as an example, the network device can proactively send model parameters to the UE based on a pre-agreed protocol, or it can send the trained model parameters to the UE in response to a model parameter request. In this way, the UE can update or restore the corresponding AI model based on the received model parameters and the known model structure, thus enabling more efficient wireless communication in collaboration with the network device based on the trained AI model.

[0123] In this context, AI models with the same structure may implement different communication functions based on parameter updates. Alternatively, the same AI model may implement different communication functions based on certain layers and their corresponding parameters. The sender (e.g., a network device) can selectively send parameters to update the parameters in certain layers of the model for the target communication function, such as by sending delta parameters through the radio resource control (RRC) layer. This can save transmission costs and improve transmission efficiency.

[0124] In some possible implementations, the parameters sent by the parameter sender can be segmented according to their hierarchical sequence number within the model. The parameter sender (e.g., a network device) can independently segment and send the model's parameters, or it can receive segmentation information from a third party (e.g., a server) and send the transmitted parameters to the parameter receiver in at least one parameter segment based on this segmentation information. The segmentation of model parameters can occur at the RRC layer or in a newly added AI layer. The new AI layer can be parallel to the RRC layer, exchanging information through a service access point (SAP). When the model parameter segmentation occurs at the RRC layer, the parameter sender can directly transmit parameter segments through the RRC layer, for example, via RRC Connection Setup or RRC Reconfiguration messages, sending the model's parameter segments as signaling fields, with one RRC message corresponding to one parameter segment. When model parameters are segmented in the newly added AI layer, the parameter sender can interact with the RRC layer through the AI ​​layer and use the RRC layer to transmit parameter segments to the parameter receiver. The RRC layer can either parse and repackage information from the AI ​​layer or perform transparent transmission of information from the AI ​​layer.

[0125] Figures 4 to 8B are schematic diagrams illustrating parameter segmentation methods in a series of models provided in the embodiments of this application. It should be noted that the following implementation methods are only illustrative examples. In actual applications, the parameters in the model may be segmented in other ways, and the embodiments of this application do not limit this.

[0126] In some possible implementations, all the parameter segments that can be transmitted in the AI ​​model can correspond one-to-one with the hierarchical sequence number of the AI ​​model.

[0127] Referring to Figure 4, a schematic diagram of parameter segmentation in a model is shown. In this method, the parameters in the model are segmented according to their hierarchical sequence, with one segment for each layer. That is, the first parameter segment corresponds one-to-one with a layer in the AI ​​model. The first parameter segment refers to one of at least one parameter segment from all transmittable parameters in the AI ​​model, divided according to a preset rule. In the parameter segment diagram in Figure 4, the shaded area represents the first parameter segment that has not been sent. When transmitting parameters, the parameter sender will transmit them consecutively according to the number of the first parameter segment or the hierarchical sequence of the model. As shown, the parameter sender can send first parameter segments numbered 0, 1, 2, and 3, but chooses not to send first parameter segments numbered 4 and 5; the parameter sender will not choose to send first parameter segments numbered 0, 1, and 3 sequentially. That is, if the parameter receiver receives parameter segments with non-consecutive numbers, it indicates that information loss occurred during transmission. Thus, this one-to-one, continuous transmission segmentation method is simple to implement, simplifies the segmentation configuration process, and improves system efficiency.

[0128] In some possible implementations, all the parameter segments available for transmission in the AI ​​model can correspond one-to-one with the grouping of parameter segments actually transmitted.

[0129] In the first possible implementation, see Figure 5, which illustrates a parameter segmentation method in a model. In this method, the first parameter segment corresponds one-to-one with the layer of the AI ​​model, and also one-to-one with the group to be transmitted in the AI ​​model. That is, one parameter segment actually used for transmission corresponds to one first parameter segment and one layer of parameters in the AI ​​model. Here, the No number represents the initial number of the first parameter segment, the Seg number represents the group number of the parameter segment actually used for transmission (i.e., the first parameter segment sent), and the shaded part and the parameters corresponding to the " / " symbol are not sent. In the parameter segment diagram shown in Figure 5, when transmitting parameters, the parameter sender can transmit the initial number of the first parameter segment or the layer number of the model discontinuously. That is, as shown in the figure, among the parameter segments actually sent by the parameter sender, the parameter segment with group number 1 corresponds to the initial number of the first parameter segment being 1 and the model layer number being 2, and the parameter segment with group number 2 corresponds to the initial number of the first parameter segment being 4 and the model layer number being 5. In this way, the parameters in the model can be selected for transmission more flexibly, avoiding the transmission of unnecessary parameters due to continuous transmission, thus reducing the transmission burden.

[0130] In the second possible implementation, refer to the schematic diagram of parameter segmentation in the model shown in Figures 6A and 6B. Here, the No number represents the initial number of the first parameter segment, the Seg number represents the group number of the parameter segment actually used for transmission (i.e., the first parameter segment sent), the shaded area, and the parameters corresponding to the " / " symbol are not sent. The first parameter segment corresponds one-to-one with the packets to be transmitted in the AI ​​model, but the relationship between the first parameter segment and the layers of the AI ​​model is not one-to-one. Specifically, each packet to be transmitted or the first parameter segment corresponds to multiple layers of parameters that can be used for transmission in the AI ​​model (two layers in Figures 6A and 6B). In this way, the number of groups can be reduced when the amount of AI model parameter data is small, thereby reducing transmission overhead and transmission latency.

[0131] When parameters are transmitted sequentially, as shown in Figure 6A, the sender can send the packet number to be transmitted and the parameter segment with initial numbers 0 and 1 for the first parameter segment, and corresponding hierarchical numbers 1, 2, 3, and 4. Alternatively, the sender can choose not to send the packet number to be transmitted and the parameter segment with initial number 2 for the first parameter segment, and corresponding hierarchical numbers 5 and 6. When parameters are transmitted discontinuously, as shown in Figure 6B, the sender can send the packet number to be transmitted with initial numbers 0 and 1 for the first parameter segment, and initial numbers 0 and 2 for the first parameter segment, and corresponding hierarchical numbers 1, 2, 5, and 6. Alternatively, the sender can choose not to send the parameter segment with initial number 2 for the first parameter segment, and corresponding hierarchical numbers 3 and 4.

[0132] In the third possible implementation, refer to the schematic diagrams of parameter segmentation in the models shown in Figures 7A and 7B. Here, the No number represents the initial number of the first parameter segment, and the Seg number represents the group number of the parameter segment actually used for transmission (i.e., the first parameter segment sent). The shaded areas and the parameters corresponding to the " / " symbol are not sent. The first parameter segment corresponds one-to-one with the groups to be transmitted in the AI ​​model. However, the first parameter segment does not correspond one-to-one with the layers of the AI ​​model. Each group to be transmitted or the first parameter segment corresponds to N layers of parameters that can be transmitted in the AI ​​model, where N is a non-integer greater than 1 (1.5 layers in Figures 7A and 7B). Figure 7A represents the case where parameters are sent continuously, and Figure 7B represents the case where parameters are sent discontinuously; please refer to the description above for details. This approach can balance reducing transmission overhead and improving the positioning accuracy of parameters within layers based on the non-integer layer division.

[0133] In the fourth possible implementation, refer to the schematic diagrams of parameter segmentation in the models shown in Figures 8A and 8B. Here, the No number represents the initial number of the first parameter segment, and the Seg number represents the group number of the parameter segment actually used for transmission (i.e., the first parameter segment sent). The shaded areas and the parameters corresponding to the " / " symbol are not sent. The first parameter segment corresponds one-to-one with the groups to be transmitted in the AI ​​model. However, the first parameter segment does not correspond one-to-one with the layers of the AI ​​model. Each layer of the AI ​​model has at least two groups to be transmitted or first parameter segments (six in Figures 8A and 8B). Figure 8A represents the case where parameters are sent continuously, and Figure 8B represents the case where parameters are sent discontinuously; please refer to the description above for details. In this way, the number of groups can be increased when the model parameter data volume is large, thereby improving the accurate location of data in each layer.

[0134] To avoid the difficulty in determining whether the parameter sender only sent parameters from a portion of the layers or whether the parameters were lost during transmission when the parameter receiver receives only some of the model's parameters, indication information can be added during parameter transmission to determine the transmission integrity of at least one first parameter segment sent by the parameter sender.

[0135] In some possible implementations, the first communication device can be the receiver of the parameters, and determine the integrity of the parameter segment transmission by receiving the first indication information sent by the second communication device.

[0136] The following section provides a detailed description of the part of S302 concerning the first communication device receiving the first instruction information sent by the second communication device.

[0137] In some possible implementations, the first indication information can indicate to the second communication device, i.e., the parameter sender, the number of first parameter segments transmitted. Taking the parameter segmentation method shown in Figure 4 as an example, the first indication information may include the number of first parameter segments transmitted as 4. In this way, by indicating the number of first parameter segments transmitted, information confirming the integrity of the transmission parameters can be provided to the first communication device from the perspective of the overall transmitted data.

[0138] In some possible implementations, the first indication information can indicate the identifier of the first parameter segment sent by the parameter sender, such as the number of the packet to be transmitted corresponding to the first parameter segment and the initial number of the first parameter segment. Taking the parameter segmentation method shown in Figure 4 as an example, the first indication information may include the initial number of the first parameter segment: 0, 1, 2, 3. Taking the parameter segmentation method shown in Figure 6B as an example, the first indication information may include the number of the packet to be transmitted (Seg number): 0 and 1, and the initial number of the corresponding first parameter segment (No number): 0 and 2. In this way, by indicating the specific attribute information of each first parameter segment sent, information for determining the integrity of the transmission parameters can be provided to the first communication device.

[0139] In some possible implementations, the first indication information may further include the initial number of the first parameter segment to be sent and / or the number of the packet to be transmitted, as well as the information of the corresponding parameter's hierarchical sequence number. Taking the parameter segmentation method shown in Figure 4 as an example, the first indication information may include the hierarchical sequence number corresponding to the first parameter segment to be sent: 1, 2, 3, 4. Taking the parameter segmentation method shown in Figure 6B as an example, the first indication information may include the hierarchical sequence number corresponding to the first parameter segment to be sent: 1, 2, 5, 6. In this way, the information of the sent parameters can be specified down to the corresponding hierarchical level, which helps the parameter receiver to more accurately locate the received parameters, thereby facilitating model updates or recovery.

[0140] In some possible implementations, the first indication information may also indicate a transmission end identifier. For example, the first indication information may include a field or character indicating the end of transmission, or it may include the number (including at least one of No number, Seg number, or hierarchical sequence number) corresponding to the last first parameter segment sent by the second communication device (parameter sender), or it may include transmission data length indication information and transmission time indication information, etc. In this way, the integrity of parameter transmission can be implicitly indicated through the transmission end identifier.

[0141] In some possible implementations, the first and second communication devices may deploy multiple models, which may be deployed at different protocol layers of the communication devices, such as the physical layer, media access control (MAC) layer, or application layer. In this case, the first indication information may also include the model's identifier. For example, when the second communication device transmits parameters of multiple models in parallel, the first indication information may be sent in the following form:

[0142] First instruction information {

[0143] Model identifier sequence {model identifier 1, model identifier 2, ..., model identifier N}

[0144] The first parameter to be sent is the sequence {number1, number2, ..., numberN}.

[0145] The first parameter segment identifier sent is sequence {(parameter segment identifier 1), (parameter segment identifier 2) ... (parameter segment identifier N)}

[0146] }

[0147] Alternatively, you can send it in the following format:

[0148] First instruction information {

[0149] sequence{(model identifier 1, quantity 1 (parameter segment identifier 1)), (model identifier 2, quantity 2 (parameter segment identifier 2))……(model identifier N, quantity N (parameter segment identifier N))}

[0150] }

[0151] Here, `sequence` represents an array, and the quantity information and parameter segment identifier are optional, with at least one of them. Each parameter segment identifier corresponds to the number of the first parameter segment sent in different models (including at least one of the initial number, the number of the packet to be transmitted, or the hierarchical sequence number). In this way, the integrity of the transmission of the first parameter segment in each model can be determined according to the different transmission model identifiers in the first indication information.

[0152] S304: The first communication device determines, based on the first instruction information, whether at least one first parameter segment has been fully received.

[0153] In some possible implementations, when the first indication information indicates the number of first parameter segments sent, the first communication device can compare the number of second parameter segments received with the number of first parameter segments indicated by the first indication information. If the number of first parameter segments indicated by the first indication information is the same as the number of second parameter segments received, it is determined that at least one first parameter segment has been fully received; if the number of first parameter segments indicated by the first indication information is different from the number of second parameter segments received, it is determined that at least one first parameter segment has not been fully received. Taking the parameter segmentation method shown in Figure 4 as an example, the first indication information may include a number of first parameter segments sent of 4. If the number of second parameter segments received by the first communication device is equal to 4, it indicates that at least one first parameter segment has been fully received, and the parameter transmission is complete; if the number of second parameter segments received is less than 4, it indicates that at least one first parameter segment has not been fully received, and the parameter transmission is incomplete.

[0154] In some possible implementations, the first indication information may indicate the identifier of the first parameter segment sent by the parameter sender, such as the number of the packet to be transmitted corresponding to the first parameter segment and the initial number of the first parameter segment. The first communication device may compare whether the identifier of the received second parameter segment is the same as the identifier in the first indication information, thereby determining the integrity of the parameter transmission. Taking the parameter segmentation method shown in Figure 4 as an example, the first indication information may include the initial number of the first parameter segment sent: 0, 1, 2, 3. The first communication device may correspondingly compare whether the initial number of the received second parameter segment is 0, 1, 2, 3. Taking the parameter segmentation method shown in Figure 6B as an example, the first indication information may include the number of the packet to be transmitted (Seg number): 0 and 1, and the corresponding initial number of the first parameter segment (No number): 0 and 2. The first communication device may correspondingly compare whether the number of the packet to be transmitted (Seg number) of the received second parameter segment is 0 and 1, and / or whether the initial number of the received second parameter segment (No number) is 0 and 2. If the identifier of the received second parameter segment is the same as the identifier in the first indication information, it is determined that at least one first parameter segment has been fully received, and the parameter transmission is complete; otherwise, at least one first parameter segment has not been fully received, and the parameter transmission is incomplete. In this way, the first communication device can directly determine whether the transmitted first parameter segment has been fully received by comparing the differences in quantity or identifier, which is relatively simple to implement.

[0155] In some possible implementations, the first indication information may further include the initial number of the first parameter segment to be sent and / or the number of the packet to be transmitted, and the information of the hierarchical sequence number of the corresponding parameter. The first communication device may also compare whether the hierarchical sequence number information of the corresponding received second parameter segment is the same as that in the first indication information, thereby determining the integrity of the parameter transmission.

[0156] In some possible implementations, the first indication information may also indicate a transmission end identifier. If the first indication information includes an identifier indicating the end of transmission and the number of the packet to be transmitted (Seg number), the first communication device can determine the integrity of the parameter transmission by whether the number of the packet to be transmitted is consecutive. Specifically, if the number of the packet to be transmitted for at least one second parameter segment is consecutive and the first communication device receives the transmission end identifier, it can be determined that at least one first parameter segment has been fully received and the parameter transmission is complete; if the number of at least one second parameter segment is not consecutive or the first communication device does not receive the transmission end identifier, it can be determined that at least one first parameter segment has not been fully received and the parameter transmission is incomplete. In this way, the first communication device can determine whether the parameter segment has been fully received by the continuity of the number of the transmitted parameter segments. When the number is not consecutive, it can directly determine in real time that the parameter segment is lost without waiting for all parameter segments to be transmitted, which is highly efficient.

[0157] It should be noted that the first indication information may also include the initial number of the first parameter segment. When the parameter transmission is complete and the numbers of the packets to be transmitted in the received second parameter segment are consecutive, the initial number (No number) of the received second parameter segment may not be consecutive. As shown in Figure 6B, in a parameter segmentation method, if the numbers of the packets to be transmitted in the received second parameter segment (Seg number) are consecutive (0 and 1), and the initial number (No number) of the received second parameter segment is 0 and 2 (not consecutive), the first communication device can still determine that the parameter transmission is complete.

[0158] In some possible implementations, after confirming the integrity of parameter transmission, the first communication device can also request the second communication device to retransmit parameter segments if the parameter transmission is incomplete. The first communication device can send a retransmission request to the second communication device, which instructs the retransmission of all first parameter segments sent by the second communication device, thereby restoring the model update.

[0159] In some possible implementations, the first communication device may also request the second communication device to retransmit the specific parameter segment that was not received. For example, when the first indication information includes the number of the first parameter segment (including at least one of the initial number, the packet number to be transmitted, or the hierarchical sequence number), the first communication device can determine the parameter segment that was not successfully received based on the aforementioned numbering information and request a retransmission from the second communication device accordingly. This makes the retransmission process more efficient and reduces signaling overhead.

[0160] Based on the above description, in the communication method of this application embodiment, the first communication device, as the receiver of model parameters, can determine the integrity of the AI ​​model parameter transmission through the first indication information. On the one hand, it can determine the recovery and update status of its own deployed AI model so that it can be used for inference and improve the performance of wireless communication; on the other hand, it can more accurately determine the conditions for requesting retransmission, reduce the signaling redundancy caused by repeated requests, and improve the system transmission efficiency.

[0161] The above describes a specific implementation method where the first communication device, as the receiver of model parameters, determines the integrity of parameter segment transmission based on the first indication information. In some possible implementations, the first communication device may also be the sender of model parameters; that is, the sender of model parameters determines the integrity of the parameter segment. This is because model training is typically performed on devices with high computing power and performance. Therefore, the sender of model parameters is generally considered to have stronger computing power or other performance characteristics and can undertake more computational tasks than the receiver, such as determining parameter integrity. Based on this, the following describes a scenario where the first communication device is the sender of parameters, and the sender determines the integrity of parameter transmission based on the second indication information.

[0162] Referring to Figure 9, a schematic diagram of a communication method is shown. Specifically, a first communication device sends at least one first parameter segment to a second communication device and receives second indication information sent by the second communication device. Then, based on the second indication information, it is determined whether at least one third parameter segment is one of all the parameter segments sent by the first communication device. Here, the third parameter segment refers to at least one parameter segment actually received by the second communication device (parameter receiver). A detailed description follows.

[0163] S902: The first communication device sends at least one first parameter segment to the second communication device, and the second communication device sends second instruction information to the first communication device based on the received third parameter segment.

[0164] In some possible implementations, the second indication information can indicate the number of third parameter segments received by the second communication device, i.e., the parameter receiver. Thus, by indicating the number of received third parameter segments, information confirming the integrity of the transmission parameters can be provided to the first communication device from the perspective of the overall transmitted data.

[0165] In some possible implementations, the second indication information may indicate the identifier of the first parameter segment received by the parameter receiver, such as the initial number of the received third parameter segment and the corresponding packet number to be transmitted. Thus, by indicating the specific attribute information of each first parameter segment sent, information determining the integrity of the transmission parameters can be provided to the second communication device.

[0166] In some possible implementations, the second indication information may further include the initial number of the received third parameter segment and / or the number of the packet to be transmitted, as well as the information of the corresponding parameter hierarchy number. This allows the received parameter information to be specified down to the corresponding hierarchy, enabling the parameter sender to more accurately locate the parameters received by the second communication device.

[0167] In some possible implementations, the first communication device may also send feedback indication information to the second communication device. This feedback indication information instructs the second communication device to send second indication information to the first communication device. For example, the feedback indication information may instruct the second communication device to provide feedback to the first communication device on the number of received third parameter segments and / or the identifier of the received third parameter segments. The feedback indication information may be sent to the second communication device along with the first parameter segments, or it may be pre-sent by the first communication device to the second communication device. For instance, when the parameters of the AI ​​model are periodically updated, the first communication device may send the feedback indication information only within one cycle, while the second communication device is instructed to send the second indication information in every subsequent transmission cycle.

[0168] S904: The first communication device determines, based on the second instruction information, whether at least one third parameter segment is one of all parameter segments sent by the first communication device.

[0169] In some possible implementations, the second indication information can indicate the number of third parameter segments received by the second communication device, i.e., the parameter receiver. The first communication device can compare the number of third parameter segments indicated by the second indication information with the number of first parameter segments sent. If the number of third parameter segments indicated by the second indication information is the same as the number of first parameter segments sent, then at least one third parameter segment is determined to be all the parameter segments sent by the first communication device; if the number of third parameter segments indicated by the second indication information is different from the number of first parameter segments sent, then at least one third parameter segment is determined not to be all the parameter segments sent by the first communication device. Taking the parameter segmentation method shown in Figure 4 as an example, if the number of third parameter segments indicated by the second indication information is equal to 4, it means that at least one third parameter segment is all the parameter segments sent by the first communication device, at least one first parameter segment has been fully received, and the parameter transmission is complete; if the number of third parameter segments indicated by the second indication information is less than 4, it means that at least one third parameter segment is not all the parameter segments sent by the first communication device, at least one first parameter segment has not been fully received, and the parameter transmission is incomplete.

[0170] In some possible implementations, the second indication information may indicate the identifier of the third parameter segment received by the parameter receiver, such as the initial number of the received third parameter segment and the corresponding packet number to be transmitted. The first communication device may compare whether the identifier in the second indication information is the same as the identifier of the transmitted first parameter segment, thereby determining the integrity of the parameter transmission. Taking the parameter segmentation method shown in Figure 4 as an example, the second indication information may include the initial number (No number) of the received third parameter segment, and the first communication device may correspondingly compare whether the initial number of the third parameter segment in the second indication information is 0, 1, 2, or 3. Taking the parameter segmentation method shown in Figure 6B as an example, the second indication information may include the packet number to be transmitted (Seg number) of the second parameter terminal and the corresponding initial number (No number) of the third parameter segment, and the first communication device may correspondingly compare whether the packet number to be transmitted (Seg number) of the first parameter segment is 0 and 1, and / or whether the initial number (No number) of the first parameter segment is 0 and 2. If the identifier in the second indication information is the same as the identifier of the first parameter segment sent, then it is determined that at least one third parameter segment is all the parameter segments sent by the first communication device, at least one first parameter segment is fully received, and the parameter transmission is complete; otherwise, it indicates that at least one third parameter segment is not all the parameter segments sent by the first communication device, at least one first parameter segment is not fully received, and the parameter transmission is incomplete.

[0171] In some possible implementations, the second indication information may further include the initial number of the received third parameter segment and / or the number of the packet to be transmitted, as well as information on the hierarchical sequence number of the corresponding parameter. The first communication device may also compare whether the hierarchical sequence number information in the received second indication information is the same as that in the sent first parameter segment, thereby determining the integrity of the parameter transmission.

[0172] S906: The first communication device sends a third instruction message to the second communication device.

[0173] In some possible implementations, the first communication device may also send a third indication message to the second communication device. The third indication message may include parameter feedback information and retransmission indication information. The parameter feedback information is used to indicate whether at least one third parameter segment received by the second communication device is all the parameter segments sent by the first communication device, and the retransmission indication information is used to indicate whether the second communication device can request a retransmission.

[0174] In some possible implementations, when the parameter feedback information indicates that the parameter segment received by the second communication device is incomplete, the retransmission instruction information can instruct the second communication device to send a retransmission request to the first communication device. Specifically, the retransmission instruction information can instruct the second communication device to send a retransmission request to retransmit all the first parameter segments; when the second instruction information includes an identifier of the third parameter segment (including at least one of the initial number, the packet number to be transmitted, or the hierarchical sequence number), the first communication device can also determine the missing parameter segment of the second communication device and inform the second communication device through the retransmission instruction information, so that the second retransmission device can send a request to retransmit the missing parameter segment.

[0175] S908: The first communication device retransmits the parameter segment to the second communication device.

[0176] In some possible implementations, the first communication device may also retransmit the parameter segment to the second communication device. Specifically, the first communication device may directly send all or all missing parameter segments to the second communication device after determining that the parameter transmission is incomplete; alternatively, it may send all or all parameter segments to the second communication device based on a retransmission request.

[0177] Based on the above description, in the communication method of this application embodiment, the first communication device, as the sender of model parameters, can determine the integrity of AI model parameter transmission through the second indication information, thereby knowing the preparation status of the model receiving side, more accurately determining whether model parameters need to be retransmitted, reducing signaling redundancy caused by repeated transmission, and improving system transmission efficiency.

[0178] The following describes a specific implementation scenario of the embodiments of this application under an open RAN architecture. Referring to Figure 10, which illustrates a scenario of a communication method under an open RAN architecture, the first communication device is the receiver of model parameters. The method includes:

[0179] S1002: The CU sends segmentation information of the model parameters to the DU.

[0180] The CU can obtain segmentation information of model parameters from third-party devices, the AI ​​layer, or the RRC layer, and transmit this segmentation information to the DU. For example, the CU can send the segmentation method of the first parameter segment to the DU, as well as the correspondence between the first parameter segment and the layer sequence number of the AI ​​model and / or the packet to be transmitted.

[0181] S1004: DU determines the first parameter segment to be sent and sends the first parameter segment to be sent to CU.

[0182] The DU can determine the transmission of some parameter information, and send the segments of the parameters to be transmitted to the CU according to the segmentation information of the first parameter segment sent by the CU.

[0183] S1006a: The first communication device sends a model parameter request to the CU.

[0184] In some possible implementations, the first communication device (the receiver of model parameters) can directly interact with the CU and request the CU to send model parameters in order to update the parameters of the model it deploys.

[0185] S1006b: The first communication device sends a model parameter request to the DU, and the DU forwards the model parameter request to the CU.

[0186] In some possible implementations, the first communication device can request model parameters from the CU via the DU.

[0187] S1008: The CU sends at least one first parameter segment and first indication information to the first communication device.

[0188] The CU can send at least one first parameter segment to the first communication device based on the partial parameters that need to be transmitted as determined by the DU. At the same time, in order to enable the first communication device to determine the integrity of the parameter transmission, the CU can send first indication information to the first communication device. The first indication information may include the number of the first parameter segments to be transmitted and an identifier, wherein the identifier may include the number corresponding to the first parameter segment (including at least one of No number, Seg number or hierarchical number).

[0189] S1010a: The first communication device sends a retransmission request to the CU.

[0190] In some possible implementations, the first communication device can directly interact with the CU, send a retransmission request to the CU to receive the first parameter segment that was not received in the aforementioned steps, and update the parameters of the model it deploys.

[0191] S1010b: The first communication device sends a retransmission request to the DU, and the DU forwards the retransmission request to the CU.

[0192] In some possible implementations, the first communication device can send a retransmission request to the CU via the DU in order to receive the retransmitted parameter segment.

[0193] S1012: The CU retransmits the first parameter segment or the first parameter segment that was not received to the first communication device.

[0194] The specific details of the above steps are similar to those of the method corresponding to Figure 3, and will not be repeated here.

[0195] The first communication device provided in the embodiments of this application will now be described. Please refer to FIG11, which is a schematic structural diagram of the first communication device according to an embodiment of this application. The first communication device 1100 can be used to execute the above-described method embodiments. The first communication device 1100 includes a transceiver module 1101 and a processing module 1102.

[0196] The processing module 1102 is used for data processing. The transceiver module 1101 can implement the corresponding communication functions. The transceiver module 1101 can also be called a communication interface or a communication module.

[0197] In some possible implementations, the first communication device 1100 may further include a storage module, which can be used to store program code, program instructions and / or data. The processing module 1102 can read the instructions and / or data in the storage module so that the first communication device 1100 can implement the aforementioned method embodiments.

[0198] The first communication device 1100 can be used to perform the actions performed by the first communication device in the above method embodiments. The first communication device 1100 can be a terminal device, a network device, or a component that can be configured on a terminal device or a network device. The processing module 1102 is used to perform processing-related operations on the first communication device side in the above method embodiments. The transceiver module 1101 is used to perform receiving-related operations on the first communication device side in the above method embodiments.

[0199] In some possible implementations, the transceiver module 1101 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.

[0200] It should be noted that the first communication device 1100 may include a transmitting module but not a receiving module. Alternatively, the first communication device 1100 may include a receiving module but not a transmitting module. Specifically, it depends on whether the above-described scheme executed by the first communication device 1100 includes both transmitting and receiving actions.

[0201] For example, the first communication device 1100 is used to execute the following scheme:

[0202] The transceiver module 1101 is used to receive first indication information sent by the second communication device, wherein the first indication information is used to determine the transmission integrity of at least one first parameter segment sent by the second communication device, and each first parameter segment includes partial parameters of an artificial intelligence (AI) model configured on the first and second communication devices.

[0203] The processing module 1102 is used to determine, based on the first indication information, whether at least one first parameter segment has been fully received.

[0204] In some possible implementations, the transceiver module 1101 is further configured to receive at least one second parameter segment from the second communication device, wherein the at least one second parameter segment is included in at least one first parameter segment. In this case, the processing module 1102 is specifically configured to determine that at least one first parameter segment has been fully received when the number of first parameter segments indicated by the first indication information is the same as the number of second parameter segments received, or when the identifier of the first parameter segment indicated by the first indication information is the same as the identifier of the second parameter segment; and to determine that at least one first parameter segment has not been fully received when the number of first parameter segments indicated by the first indication information is not the same as the number of second parameter segments received, or when the identifier of the first parameter segment indicated by the first indication information is not the same as the identifier of the second parameter segment.

[0205] In some possible implementations, the first indication information is also used to indicate the end-of-transmission identifier of the first parameter segment, the identifier of the first parameter segment including the number of the first parameter segment sent. In this case, the processing module 1102 is specifically used to determine that at least one first parameter segment has been fully received when the numbers of at least one second parameter segment are consecutive and the first communication device receives the end-of-transmission identifier; and to determine that at least one first parameter segment has not been fully received when the numbers of at least one second parameter segment are not consecutive or the first communication device does not receive the end-of-transmission identifier.

[0206] In some possible implementations, the transceiver module 1101 is further configured to send a first retransmission request to the second communication device when the first parameter segment is not fully received. The first retransmission request is used to instruct the retransmission of all the first parameter segments sent by the second communication device, or to retransmit the first parameter segments that were not received.

[0207] For example, the first communication device 1100 is also used to execute the following scheme:

[0208] The transceiver module 1101 is used to receive second indication information sent by the second communication device. The second indication information is used to determine the transmission integrity of at least one third parameter segment received by the second communication device. Each third parameter segment includes some parameters of the artificial intelligence (AI) model configured on the first and second communication devices.

[0209] The processing module 1102 is used to determine, based on the second indication information, whether at least one third parameter segment is one of all parameter segments sent by the first communication device.

[0210] In some possible implementations, the transceiver module 1101 is further configured to send at least one first parameter segment to the second communication device, and the processing module 1102 is specifically configured to determine that at least one third parameter segment is all the parameter segments sent by the first communication device when the number of third parameter segments indicated by the second indication information is the same as the number of first parameter segments, or when the identifier of the third parameter segment indicated by the second indication information is the same as the identifier of the first parameter segment; and to determine that at least one third parameter segment is not all the parameter segments sent by the first communication device when the number of third parameter segments indicated by the second indication information is not the same as the number of first parameter segments, or when the identifier of the third parameter segment indicated by the second indication information is not the same as the identifier of the first parameter segment.

[0211] In some possible implementations, the transceiver module 1101 is further configured to send a third indication information to the second communication device. The third indication information is used to indicate to the second communication device whether at least one third parameter segment is all the parameter segments sent by the first communication device. The third indication information is also used to indicate whether the second communication device can request a retransmission.

[0212] In some possible implementations, the transceiver module 1101 is also used to receive a second retransmission request sent by the second communication device, and to transmit all the first parameter segments sent by the first communication device or the first parameter segments not received by the second communication device according to the second retransmission request.

[0213] 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.

[0214] The processing module 1102 in the above embodiments can be implemented by at least one processor or processor-related circuitry. The transceiver module 1101 can be implemented by a transceiver or transceiver-related circuitry. The transceiver module 1101 can also be referred to as a communication module or communication interface. The storage module can be implemented by at least one memory.

[0215] The following is a schematic diagram of a second communication device according to an embodiment of this application. Referring to FIG12, the second communication device 1200 can be used to perform the above-described method embodiment. The second communication device 1200 includes a transceiver module 1201 and a processing module 1202.

[0216] The processing module 1202 is used for data processing. The transceiver module 1201 can implement the corresponding communication functions. The transceiver module 1201 can also be called a communication interface or a communication module.

[0217] In some possible implementations, the second communication device 1200 may further include a storage module, which can be used to store program code, program instructions and / or data. The processing module 1202 can read the instructions and / or data in the storage module so that the second communication device 1200 can implement the aforementioned method embodiments.

[0218] The second communication device 1200 can be used to perform the actions performed by the second communication device in the above method embodiments. The second communication device 1200 can be a terminal device, a network device, or a component that can be configured on a terminal device or a network device. The processing module 1202 is used to perform processing-related operations on the second communication device side in the above method embodiments. The transceiver module 1201 is used to perform receiving-related operations on the second communication device side in the above method embodiments.

[0219] In some possible implementations, the transceiver module 1201 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.

[0220] It should be noted that the second communication device 1200 may include a transmitting module but not a receiving module. Alternatively, the second communication device 1200 may include a receiving module but not a transmitting module. Specifically, it depends on whether the above-described scheme executed by the second communication device 1200 includes both transmitting and receiving actions.

[0221] For example, the second communication device 1200 is used to execute the following scheme:

[0222] The transceiver module 1201 is used to send first indication information to the first communication device. The first indication information is used to determine the transmission integrity of at least one first parameter segment sent by the second communication device. Each first parameter segment includes some parameters of the artificial intelligence (AI) model configured on the first and second communication devices.

[0223] In some possible implementations, the transceiver module 1201 is also configured to receive a first retransmission request sent by the first communication device, and retransmit all the first parameter segments according to the first retransmission request, or retransmit the first parameter segments that the first communication device has not received.

[0224] For example, the second communication device 1200 is used to execute the following scheme:

[0225] The transceiver module 1201 is used to send second indication information to the first communication device. The second indication information is used to determine the transmission integrity of at least one third parameter segment received by the second communication device. Each third parameter segment includes some parameters of the artificial intelligence (AI) model configured on the first and second communication devices.

[0226] In some possible implementations, the transceiver module 1201 is also used to receive at least one first parameter segment sent by the first communication device.

[0227] In some possible implementations, the transceiver module 1201 is also used to receive third indication information sent by the first communication device. The third indication information is used to indicate whether at least one third parameter segment is all the parameter segments sent by the first communication device. The third indication information is also used to indicate whether the second communication device can request retransmission.

[0228] In some possible implementations, the transceiver module 1201 is further configured to send a second retransmission request to the first communication device when at least one third parameter segment is not all the parameter segments sent by the first communication device. The second retransmission request is used to instruct the retransmission of all first parameter segments or the retransmission of the first parameter segments that were not received.

[0229] 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.

[0230] The processing module 1202 in the above embodiments can be implemented by at least one processor or processor-related circuitry. The transceiver module 1201 can be implemented by a transceiver or transceiver-related circuitry. The transceiver module 1201 can also be referred to as a communication module or communication interface. The storage module can be implemented by at least one memory.

[0231] This application also provides an apparatus 1300, which may be a terminal device, a processor in the terminal device, or a chip. The apparatus 1300 can be used to perform the operations performed by the first communication device or the second communication device in the above method embodiments.

[0232] When device 1300 is a terminal device, Figure 13 shows a simplified structural diagram of the terminal device. As shown in Figure 13, the terminal device includes a processor, a memory, and a transceiver. The memory can store computer program code, and the transceiver includes a transmitter 1331, a receiver 1332, radio frequency circuitry (not shown in the figure), an antenna 1333, and input / output devices (not shown in the figure).

[0233] The processor is mainly used to process communication protocols and communication data; control terminal devices; execute software programs; and process data from software programs.

[0234] Memory is mainly used to store software programs and data.

[0235] Radio frequency (RF) circuits are mainly used for the conversion between baseband signals and RF signals, as well as for the processing of RF signals.

[0236] Antennas are primarily used for transmitting and receiving radio frequency signals in the form of electromagnetic waves.

[0237] Input / output devices can include touchscreens, displays, or keyboards. They are primarily used to receive user input and output data to the user. It should be noted that some types of terminal devices may not have input / output devices.

[0238] When data needs to be transmitted, the processor performs baseband processing on the data to be transmitted and outputs a baseband signal to the radio frequency (RF) circuit. The RF circuit then processes the baseband signal and transmits it outwards via an antenna as electromagnetic waves. When data is sent to the terminal device, the RF circuit receives the RF signal through the antenna. The RF circuit converts the RF signal back into a baseband signal and outputs it to the processor. The processor converts the baseband signal back into data and processes the data. For ease of explanation, Figure 13 only shows one memory, processor, and transceiver. In actual terminal device products, there may be one or more processors and one or more memories. Memory can also be called storage medium or storage device, etc. Memory can be independent of the processor or integrated with the processor; this embodiment does not limit this.

[0239] In this embodiment, the antenna and radio frequency circuit with transceiver function can be regarded as the transceiver module of the terminal device, and the processor with processing function can be regarded as the processing module of the terminal device.

[0240] As shown in Figure 13, the terminal device includes a processor 1310, a memory 1320, and a transceiver 1330. The processor 1310 may also be referred to as a processing unit, processing board, processing module, or processing device, etc. The transceiver 1330 may also be referred to as a transceiver unit, transceiver, or transceiver device, etc.

[0241] In some possible implementations, the devices in transceiver 1330 used for receiving can be considered as receiving modules, and the devices in transceiver 1330 used for transmitting can be considered as transmitting modules. That is, transceiver 1330 includes a receiver and a transmitter. A transceiver is sometimes also called a transceiver unit, transceiver module, or transceiver circuit. A receiver is sometimes also called a receiver unit, receiver module, or receiver circuit. A transmitter is sometimes also called a transmitter, transmitter module, or transmitter circuit.

[0242] The processor 1310 is used to execute the processing actions on the side of the first communication device or the second communication device in the above embodiments. The transceiver 1330 is used to execute the transmission and reception actions on the side of the first communication device or the second communication device in the above embodiments.

[0243] It should be understood that Figure 13 is merely an example and not a limitation, and the terminal device described above, including the transceiver module and the processing module, may not depend on the structure shown in Figures 11, 12 or 13.

[0244] When device 1300 is a chip, the chip includes a processor, a memory, and a transceiver. The transceiver can be an input / output circuit or a communication interface. The processor can be a processing module integrated on the chip, a microprocessor, or an integrated circuit. In the above method embodiments, the transmitting operation of the first or second communication device can be understood as the chip's output, and the receiving operation of the first or second communication device in the above method embodiments can be understood as the chip's input.

[0245] This application also provides an apparatus 1400, which can be a network device or a chip. The apparatus 1400 can be used to perform the operations performed by the first communication device or the second communication device in the above embodiments.

[0246] When device 1400 is a network device, such as a base station, Figure 14 shows a simplified schematic diagram of a base station structure. The base station includes parts 1410, 1420, and 1430.

[0247] Part 1410 is mainly used for baseband processing and controlling the base station; Part 1410 is usually the control center of the base station, which can be called a processor, and is used to control the base station to perform the processing operations of the first communication device or the second communication device in the above method embodiments.

[0248] Section 1420 is primarily used to store computer program code and data.

[0249] Section 1430 is primarily used for transmitting and receiving radio frequency (RF) signals, as well as converting RF signals to baseband signals. Section 1430 is commonly referred to as a transceiver module, transceiver, transceiver circuit, or transceiver unit. The transceiver module of section 1430, also called a transceiver or transceiver unit, includes antenna 1433 and RF circuitry (not shown in the figure), where the RF circuitry is mainly used for RF processing. In some possible implementations, the device in section 1430 that performs the receiving function can be considered a receiver, and the device that performs the transmitting function can be considered a transmitter; that is, section 1430 includes receiver 1432 and transmitter 1431. The receiver can also be called a receiving module, receiver circuit, or receiving circuit, and the transmitter can be called a transmitting module, transmitter, or transmitting circuit.

[0250] Sections 1410 and 1420 may include one or more circuit boards, each of which may include one or more processors and one or more memories. The processors are used to read and execute programs in the memories to implement baseband processing functions and control the base station. If multiple circuit boards exist, they can be interconnected to enhance processing capabilities. As an alternative implementation, multiple circuit boards may share one or more processors, multiple circuit boards may share one or more memories, or multiple circuit boards may simultaneously share one or more processors.

[0251] For example, in some possible implementations, the transceiver module of section 1430 is used to execute the transceiver-related processes performed by the first or second communication device in the above embodiments. The processor of section 1410 is used to execute the processing-related processes performed by the first or second communication device in the above embodiments.

[0252] It should be understood that Figure 14 is merely an example and not a limitation, and the network device described above, including the processor, memory, and transceiver, may not depend on the structure shown in Figures 11, 12, or 14.

[0253] When device 1400 is a chip, the chip includes a transceiver, a memory, and a processor. The transceiver can be an input / output circuit or a communication interface; the processor can be a processor integrated on the chip, a microprocessor, or an integrated circuit. In the above method embodiments, the transmitting operation of the first or second communication device can be understood as the chip's output, and the receiving operation of the first or second communication device in the above method embodiments can be understood as the chip's input.

[0254] This application also provides a computer-readable storage medium storing computer instructions for implementing the methods executed by the first communication device or the second communication device in the above method embodiments.

[0255] For example, when the computer program is executed by a computer, it enables the computer to implement the method performed by the first communication device or the second communication device in the above method embodiments.

[0256] This application also provides a computer program product containing instructions that, when executed by a computer, cause the computer to perform the method described in the above method embodiments, executed by the first communication device or the second communication device.

[0257] This application also provides a communication system, which includes a first communication device and a second communication device. The first communication device is used to perform some or all of the operations performed by the first communication device in the above embodiments, and the second communication device is used to perform some or all of the operations performed by the second communication device in the above embodiments.

[0258] This application also provides a chip device, including a processor, for calling computer programs or computer instructions stored in the memory to cause the processor to execute the method provided in the above embodiments.

[0259] In some possible implementations, the input of the chip device corresponds to the receive operation in any of the above embodiments, and the output of the chip device corresponds to the send operation in any of the above embodiments.

[0260] In some possible implementations, the processor is coupled to the memory via an interface.

[0261] In some possible implementations, the chip device also includes a memory that stores computer programs or computer instructions.

[0262] In the embodiments of this application, the processor can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), graphics processing units (GPUs), neural network processing units (NPUs), artificial intelligence processors, or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. A general-purpose processor can be a microprocessor, any conventional processor, or one or more integrated circuits used to control the execution of a program for controlling the method provided in any of the above embodiments. The memory mentioned above can be read-only memory (ROM) or other types of static storage devices capable of storing static information and instructions, random access memory (RAM), etc. Some or all steps of the communication method in the embodiments of this application can be implemented by a GPU or NPU, or by a GPU or NPU in conjunction with other processors.

[0263] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the explanations and beneficial effects of the relevant contents in any of the above-mentioned devices can be referred to the corresponding method embodiments provided above, and will not be repeated here.

[0264] 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.

[0265] 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.

[0266] 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.

[0267] 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 essential contribution of the technical solution of this application, 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, ROM, RAM, magnetic disks, or optical disks.

[0268] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit it. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.

Claims

1. A communication method characterized by comprising: Applied to a first communication device, the method includes: The system receives a first indication message sent by a second communication device, the first indication message being used to determine the transmission integrity of at least one first parameter segment sent by the second communication device, each first parameter segment including partial parameters of an artificial intelligence (AI) model; Based on the first indication information, determine whether the at least one first parameter segment has been fully received.

2. The method of claim 1, wherein, The method further includes: Receive at least one second parameter segment from the second communication device, the at least one second parameter segment being included in the at least one first parameter segment; The first indication information includes the number of the first parameter segments and / or the identifier of the first parameter segments. Determining whether all of the at least one first parameter segment has been received based on the first indication information includes: If the number of first parameter segments indicated by the first indication information is the same as the number of second parameter segments received, or if the identifier of the first parameter segment indicated by the first indication information is the same as the identifier of the second parameter segment, then it is determined that at least one first parameter segment has been fully received. If the number of first parameter segments indicated by the first indication information is different from the number of second parameter segments received, or if the identifier of the first parameter segment indicated by the first indication information is different from the identifier of the second parameter segment, then it is determined that at least one first parameter segment has not been fully received.

3. The method of claim 2, wherein, The first indication information is further used to indicate the end-of-transmission identifier of the first parameter segment, wherein the identifier of the first parameter segment includes the number of the transmitted first parameter segment, and determining whether the at least one first parameter segment has been fully received according to the first indication information includes: If the at least one second parameter segment is numbered consecutively and the first communication device receives the transmission end identifier, then it is determined that the at least one first parameter segment has been fully received. If the numbering of the at least one second parameter segment is not consecutive or the first communication device does not receive the transmission end identifier, then it is determined that the at least one first parameter segment has not been fully received.

4. The method according to any one of claims 1 to 3, characterized in that, The method further includes: If the first parameter segment is not fully received, a first retransmission request is sent to the second communication device. The first retransmission request is used to instruct the retransmission of all the first parameter segments sent by the second communication device, or to retransmit the first parameter segments that were not received.

5. The method according to any one of claims 1 to 4, characterized in that, Each of the first parameter segments corresponds to a layer of the AI ​​model, and the parameters in each first parameter segment are used to update the parameters of the corresponding layer of the AI ​​model.

6. The method of claim 5, wherein, The first parameter segment corresponds one-to-one with the layer of the AI ​​model.

7. The method of claim 5, wherein, The first parameter segment sent corresponds one-to-one with the packet to be transmitted in the AI ​​model. Each packet to be transmitted in the AI ​​model corresponds to at least one layer or a portion of the parameters within a layer in the AI ​​model that need to be transmitted.

8. The method according to any one of claims 1 to 7, characterized in that, The first indication information is transmitted through the Radio Resource Control (RRC) layer.

9. A communication method characterized by comprising: Applied to a first communication device, the method includes: The system receives a second indication message sent by a second communication device, the second indication message being used to determine the transmission integrity of at least one third parameter segment received by the second communication device, each of the third parameter segments including partial parameters of an artificial intelligence (AI) model; Based on the second indication information, determine whether the at least one third parameter segment is all the parameter segments sent by the first communication device.

10. The method of claim 9, wherein, The method further includes: Send the at least one first parameter segment to the second communication device; The second indication information includes the number of the first parameter segments and / or the identifier of the first parameter segments. Determining whether the at least one third parameter segment is one of all parameter segments sent by the first communication device, based on the second indication information, includes: If the number of the third parameter segments indicated by the second indication information is the same as the number of the first parameter segments, or if the identifier of the third parameter segment indicated by the second indication information is the same as the identifier of the first parameter segment, then it is determined that the at least one third parameter segment is all the parameter segments sent by the first communication device. If the number of third parameter segments indicated by the second indication information is different from the number of first parameter segments, or if the identifier of the third parameter segment indicated by the second indication information is different from the identifier of the first parameter segment, then it is determined that the at least one third parameter segment is not one of the total number of parameter segments sent by the first communication device.

11. The method of claim 10, wherein, The method further includes: A third indication message is sent to the second communication device. The third indication message is used to indicate to the second communication device whether the at least one third parameter segment is all the parameter segments sent by the first communication device. The third indication message is also used to indicate whether the second communication device can request a retransmission.

12. The method of claim 11, wherein, The method further includes: Receive the second retransmission request sent by the second communication device; According to the second retransmission request, transmit all the first parameter segments sent by the first communication device or the first parameter segments not received by the second communication device.

13. The method according to any one of claims 10 to 12, characterized in that, Each of the first parameter segments corresponds to a layer of the AI ​​model, and the parameters in each first parameter segment are used to update the parameters of the corresponding layer of the AI ​​model.

14. The method of claim 13, wherein, The first parameter segment corresponds one-to-one with the layer of the AI ​​model.

15. The method of claim 13, wherein, The first parameter segment sent corresponds one-to-one with the packet to be transmitted in the AI ​​model. Each packet to be transmitted in the AI ​​model corresponds to at least one layer or a portion of the parameters within a layer in the AI ​​model that need to be transmitted.

16. The method according to any one of claims 9 to 15, characterized in that, The second indication information is transmitted through the Radio Resource Control (RRC) layer.

17. A method of communication, comprising: Applied to a second communication device, the method includes: Send a first indication message to a first communication device, the first indication message being used to determine the transmission integrity of at least one first parameter segment sent by the second communication device, each first parameter segment including partial parameters of an artificial intelligence (AI) model.

18. The method of claim 17, wherein, The method further includes: Receive the first retransmission request sent by the first communication device; Retransmit all of the first parameter segments according to the first retransmission request, or retransmit the first parameter segments that the first communication device did not receive.

19. A method of communication, comprising: Applied to a second communication device, the method includes: Send a second indication message to the first communication device, the second indication message being used to determine the transmission integrity of at least one third parameter segment received by the second communication device, each of the third parameter segments including partial parameters of an artificial intelligence (AI) model.

20. The method of claim 19, wherein, The method further includes: Receive the at least one first parameter segment sent by the first communication device.

21. The method of claim 20, wherein, The method further includes: The second communication device receives a third indication message sent by the first communication device. The third indication message is used to indicate whether the at least one third parameter segment is all the parameter segments sent by the first communication device. The third indication message is also used to indicate whether the second communication device can request a retransmission.

22. The method of claim 21, wherein, The method further includes: If the at least one third parameter segment is not all the parameter segments sent by the first communication device, a second retransmission request is sent to the first communication device. The second retransmission request is used to instruct the retransmission of all the first parameter segments, or the retransmission of the first parameter segments that were not received.

23. A communication device, characterized in that, The communication device includes: A unit for performing the method as described in any one of claims 1 to 8, or a unit for performing the method as described in any one of claims 9 to 16.

24. A communication device, characterized in that, The communication device includes: A unit for performing the method as described in any one of claims 17 or 18, or a unit for performing the method as described in any one of claims 19 to 22.

25. A communication system, characterized in that, The system includes a first communication device and a second communication device, the first communication device being used to perform the method as described in any one of claims 1 to 8, or to perform the method as described in any one of claims 9 to 16, and the second communication device being used to perform the method as described in any one of claims 17 or 18, or to perform the method as described in any one of claims 19 to 22.

26. A computer storage medium, characterized in that, The computer storage medium is used to store a computer program, which, when executed, is used to implement the method of any one of claims 1 to 22.

27. A computer program product, characterized in that, When the computer program product is run on a computer, the method as described in any one of claims 1 to 22 is implemented.

Images