Task allocation method based on AI model in communication system and related products

Abstract

A task allocation method based on an AI model in a communication system and related products, the method comprising: a terminal / core network element sends first information to an access network device, the first information indicating a first model identifier (ID); wherein the first model ID indicates an AI model deployed by the terminal / core network element. And the terminal / core network element receives second information from the access network equipment, wherein the second information indicates the second model ID. Wherein the second model ID is a model ID in the first model ID, and the second model ID is associated with the first task. And the terminal / core network element executes the first task based on the AI model corresponding to the second model ID. According to the embodiment, alignment of computing power between devices can be achieved, conditions are provided for task segmentation, distributed training is enabled to be achieved, and the overall time delay of reasoning is reduced. The method can be applied to the technical field of AI, the technical field of communication and the like.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of artificial intelligence (AI) and communication technology, in particular to a task allocation method based on an AI model in a communication system and related products. BACKGROUND

[0002] In recent years, AI large models represented by ChatGPT have shown an increasingly popular situation with their outstanding natural language and multi-modal understanding capabilities and the boost to generative AI. However, the ChatGPT-like large model leads to a surge in computing power demand due to its huge parameter quantity and training data, and distributed cluster training becomes a common choice for large models. How to analyze and optimize the training of the network communication characteristics of the distributed training of the large model is the core element to improve the training speed of the large model, reduce the training time and reduce the training cost.

[0003] On the other hand, the training and fine-tuning of AI models rely on real-time data, and how to use distributed terminals to obtain real-time high-quality data is a key problem in the AI field. In addition, considering the trend of cloud-pipeline-end joint deployment of large models, the computing power, real-time state, and willingness to participate in training / inference of the terminal can be coordinated in real time through a wireless network.

[0004] The existing AI mechanism cannot better utilize the computing power of each device (such as a terminal, a base station, a server, etc.) in the communication field, and the computing power of each device cannot be fully released and utilized. SUMMARY

[0005] The present application discloses a communication method, device, storage medium and program product, which can align the computing power between devices, enable distributed training, and reduce the overall latency of inference.

[0006] In a first aspect, an embodiment of the present disclosure provides a communication method. The method can be applied to a terminal side, for example, a terminal or a communication module / processing module in the terminal, or a circuit or chip responsible for communication functions in the terminal (such as a modem chip, also known as a baseband chip, or a system on chip (SoC) chip or system in package (SIP chip) containing a modem core, or a circuit or chip responsible for processing functions in the terminal (such as a graphics processing unit (GPU)), for example, the method is applied to a terminal. In the method, the terminal sends first information, and the first information indicates a first model identification (ID). The first model ID indicates an artificial intelligence (AI) model deployed by the terminal. The terminal also receives second information, and the second information indicates a second model ID. The second model ID is a model ID in the first model ID, and the second model ID is associated with a first task. Then, the terminal performs the first task based on the AI model corresponding to the second model ID.

[0007] By using the above method, the terminal indicates the AI model deployed by the terminal through the first model ID, so that the access network device or the core network device knows the model capability of the terminal, which can align the computing power between devices, fully use the computing power of different devices, and provide conditions for task segmentation (allocation). The terminal performs the first task based on the AI model indicated by the second model ID, which enables distributed training to be implemented, so that the task inference delay is short. Moreover, based on the second model ID, the task decomposition indication overhead can be saved.

[0008] In a possible design, the first model ID corresponds to one or more of the following of the AI model deployed by the first communication device: function, number of input nodes, number of output nodes, version release time, and version number. In this example, by constructing a mapping rule that associates the model ID with the model characteristics, the terminal, the access network device, and the core network element can directly determine the model function and the corresponding function characteristics, and align the model capabilities on different devices by using the model ID generated by the mapping rule with less overhead.

[0009] In a possible design, the first model ID includes a first field and a second field, and the first field and the second field respectively indicate one or more of the function, the number of input nodes, the number of output nodes, the version release time, and the version number. The first field and the second field indicate different contents. In this example, the model ID is displayed based on each field with specific meaning, which can intuitively express the corresponding model characteristics, and the model capabilities of different devices are aligned by using the model ID generated according to the rule with less overhead.

[0010] In a possible design, the first information indicates a first check code, which is generated based on the first model ID. In this example, the check code is used to align the computing power between devices, and based on the indication of the shorter bit overhead, the terminal, the access network device, the core network element, and the like can complete the model capability alignment with less overhead.

[0011] In a possible design, the terminal further receives fourth information indicating a third model ID. The third model ID indicates an AI model deployed by the second communication device. In this example, the terminal can obtain the model capability possessed by the access network device, so as to compare the received model ID with the model capability possessed by the terminal itself, and feed back the capability possessed by the terminal, or supplement the differentiated capability, so that the two devices can align the model capability in a shorter time delay.

[0012] In a possible design, the first model ID includes a model ID in the third model ID. The terminal reports the model ID in the third model ID, so that the access network device can perceive the model capability possessed by the terminal, and the two devices can align the model capability in a shorter time delay, and reduce the time delay of task segmentation.

[0013] In another possible design, the first model ID includes a model ID other than the third model ID. The terminal reports the model ID other than the third model ID, so that the two devices can align the model capability in a shorter time delay, and reduce the time delay of task segmentation.

[0014] In yet another possible design, the first model ID includes a model ID in the third model ID, and a model ID other than the third model ID. The terminal can report not only the model ID in the third model ID, but also the model ID other than the third model ID, so that the devices can fully interact the model capability possessed by each other, and the two devices can align the model capability in a shorter time delay, and reduce the time delay of task segmentation.

[0015] In a possible implementation, the terminal further receives sixth information indicating the number of in-degree and the number of out-degree of a directed acyclic graph (DAG). In this way, the terminal can perceive the demand of the subtask to be executed, and help the access network device to perform part of the computing, so that the terminal can accurately obtain the information related to the subtask to be executed, and assist other devices to complete the task reasoning in a shorter time delay.

[0016] In a second aspect, an embodiment of the present application provides a communication method. The method can be applied to a core network side, for example, a core network element or a module (such as a circuit, a chip or a chip system, etc.) in the core network element, or a logic node, a logic module or software capable of realizing all or part of the function of the core network element. Taking the case where the method is applied to the core network element, in the method, the core network element sends first information, and the first information indicates a first model ID. The first model ID indicates an AI model deployed by the core network element. The core network element also receives second information, and the second information indicates a second model ID. The second model ID is a model ID in the first model ID, and the second model ID is associated with a first task. Further, the core network element performs the first task based on an AI model corresponding to the second model ID.

[0017] By using the above method, the core network element indicates the AI model it deploys through the first model ID, so that the access network device knows its model capability, which can realize the alignment of the computing power between devices and provide conditions for task segmentation (allocation). The core network element performs the first task based on the AI model indicated by the second model ID, which enables distributed training to be implemented, so that the task inference delay is short. Moreover, based on the second model ID indicating the corresponding task, the task decomposition indication overhead can be saved.

[0018] Some possible implementations and beneficial effects of the second aspect can be referred to the above-mentioned first aspect, and will not be repeated here.

[0019] In a possible design, the first task includes a first sub-task and a second sub-task, and the core network element further receives third information, and the third information includes a first data packet and a second data packet. The first data packet and the second data packet have the same service function chaining (SFC) header. The first data packet corresponds to the first sub-task, and the second data packet corresponds to the second sub-task. In this example, the first sub-task and the second sub-task can obtain the same transmission guarantee in the core network, which provides conditions for obtaining a lower inference delay.

[0020] In another possible design, the first task includes a third subtask and a fourth subtask, and the core network network element further sends fifth information indicating a first configuration file and a second configuration file, the first configuration file and the second configuration file being configured with a same 5G QoS identifier (5QI) value, the first configuration file corresponding to the third subtask, and the second configuration file corresponding to the fourth subtask. With this example, the same QoS guarantee can be provided by the access network device when scheduling the third subtask and the fourth subtask, so that the terminal can receive data packets as much as possible at the same time, and a lower inference latency can be obtained.

[0021] In a third aspect, the method can be applied to a network side, for example, an access network device of the network side, a module (for example, a circuit, a chip, or a chip system, etc.) in the access network device, or a logic node, a logic module, or software capable of implementing all or part of the functions of the access network device. Taking the case where the method is applied to the access network device, in the method, the access network device receives first information indicating a first model ID. The first model ID indicates an AI model deployed by a first communication device. The access network device further sends second information indicating a second model ID. The second model ID is a model ID in the first model ID, and the second model ID is associated with a first task.

[0022] Some possible implementations and advantages of the third aspect can refer to the first aspect described above, and will not be repeated.

[0023] In a possible design, the first task includes a first subtask and a second subtask, and the access network device further sends third information including a first data packet and a second data packet, the first data packet and the second data packet having a same SFC header, the first data packet corresponding to the first subtask, and the second data packet corresponding to the second subtask.

[0024] In another possible design, the first task includes a third subtask and a fourth subtask, and the access network device further receives fifth information indicating a first configuration file and a second configuration file, the first configuration file and the second configuration file being configured with a same 5QI value, the first configuration file corresponding to the third subtask, and the second configuration file corresponding to the fourth subtask. In this way, the same QoS guarantee can be provided by the access network device when scheduling the third subtask and the fourth subtask, so that the terminal can receive data packets as much as possible at the same time, and a lower inference latency can be obtained.

[0025] In a possible design, the access network device further sends fourth information, where the fourth information indicates a third model ID, and the third model ID indicates an AI model deployed by the access network device. With this example, the terminal can acquire model capability possessed by the access network device, so as to compare the received model ID with model capability possessed by the terminal itself, and feed back the capability possessed by the terminal itself, or supplement differentiated capability, so that the two devices can align the model capability within a shorter time delay.

[0026] In a fourth aspect, a communication apparatus is provided. The communication apparatus has functions of the first aspect. For example, the communication apparatus includes modules or units or means corresponding to the operations of the first aspect. The modules or units or means can be implemented in software, or in hardware, or in a combination of software and hardware.

[0027] In one implementation, the communication apparatus includes a communication unit, configured to send first information, where the first information indicates a first model ID, and the first model ID indicates an AI model deployed by the terminal.

[0028] The communication unit is further configured to receive second information, where the second information indicates a second model ID, the second model ID is a model ID in the first model ID, and the second model ID is associated with a first task.

[0029] The processing unit is configured to perform the first task based on an AI model corresponding to the second model ID.

[0030] Some possible implementations and advantages of the fourth aspect can refer to the first aspect, and details are not repeated.

[0031] In a fifth aspect, a communication apparatus is provided. The communication apparatus has functions of the second aspect. For example, the communication apparatus includes modules or units or means corresponding to the operations of the second aspect. The modules or units or means can be implemented in software, or in hardware, or in a combination of software and hardware.

[0032] In one implementation, the communication apparatus includes a communication unit, configured to send first information, where the first information indicates a first model ID, and the first model ID indicates an AI model deployed by the core network element.

[0033] The communication unit is further configured to receive second information, where the second information indicates a second model ID, the second model ID is a model ID in the first model ID, and the second model ID is associated with a first task.

[0034] The processing unit is configured to perform the first task based on an AI model corresponding to the second model ID.

[0035] Some possible implementation manners and beneficial effects of the fifth aspect can refer to the first aspect, and will not be repeated.

[0036] In the sixth aspect, the application provides a communication apparatus, which has the function of implementing the third aspect, for example, the communication apparatus includes a module or unit or means corresponding to the operation of the third aspect, which can be implemented by software, or by hardware, or by software and hardware.

[0037] In one implementation, the communication apparatus includes a communication unit configured to receive first information, the first information indicating a first model ID. The first model ID indicates an AI model deployed by the first communication apparatus.

[0038] The communication unit is further configured to send second information, the second information indicating a second model ID. The second model ID is a model ID in the first model ID, and the second model ID is associated with a first task.

[0039] Some possible implementation manners and beneficial effects of the sixth aspect can refer to the first aspect, and will not be repeated.

[0040] In the seventh aspect, the application provides a communication apparatus, which includes an interface circuit and one or more processors. The one or more processors are coupled with a memory. The memory is configured to store part or all of the necessary computer programs or instructions for implementing the functions related to the first aspect. The one or more processors can execute the computer programs or instructions, when the computer programs or instructions are executed, so that the communication apparatus implements the method in any possible design or implementation manner of the first aspect. The interface circuit is configured to implement the communication function within the communication apparatus and / or the communication function of the communication apparatus with other devices or components.

[0041] In one possible design, the processor is configured to communicate with other devices or components through the interface circuit.

[0042] In one possible design, the communication apparatus can further include the memory.

[0043] The communication apparatus can be a terminal, or a communication / processing module in the terminal, or a chip responsible for communication function such as modem chip (also known as baseband chip) or SoC or SIP chip containing modem module in the terminal, or a circuit or chip responsible for processing function (such as GPU) in the terminal.

[0044] In an eighth aspect, the present application provides a communication apparatus, which comprises an interface circuit and one or more processors. The one or more processors are coupled with a memory. The memory is configured to store part or all of the computer programs or instructions necessary for implementing the functions related to the second aspect. The one or more processors can execute the computer programs or instructions, which, when executed, cause the communication apparatus to implement the method in any possible design or implementation manner of the second aspect. The interface circuit is configured to implement the communication function within the communication apparatus and / or the communication function of the communication apparatus with other apparatuses or components.

[0045] In a ninth aspect, the present application provides a communication apparatus, which comprises an interface circuit and one or more processors. The one or more processors are coupled with a memory. The memory is configured to store part or all of the computer programs or instructions necessary for implementing the functions related to the third aspect. The one or more processors can execute the computer programs or instructions, which, when executed, cause the communication apparatus to implement the method in any possible design or implementation manner of the third aspect. The interface circuit is configured to implement the communication function within the communication apparatus and / or the communication function of the communication apparatus with other apparatuses or components.

[0046] In a tenth aspect, the present application provides a communication system, which comprises the communication apparatus of the fourth aspect and the communication apparatus of the sixth aspect. Optionally, the communication system further comprises the communication apparatus of the fifth aspect.

[0047] Alternatively, the communication system comprises the communication apparatus of the fifth aspect and the communication apparatus of the sixth aspect. Optionally, the communication system further comprises the communication apparatus of the fourth aspect.

[0048] Alternatively, the communication system comprises the communication apparatus of the fourth aspect and the communication apparatus of the fifth aspect. Optionally, the communication system further comprises the communication apparatus of the sixth aspect.

[0049] In an eleventh aspect, the present application provides a computer readable storage medium, which stores computer readable instructions. When a computer reads and executes the computer readable instructions, the computer executes the method in any possible design of the first aspect to the third aspect.

[0050] In a twelfth aspect, the present application provides a computer program product, which, when a computer reads and executes the computer program product, causes the computer to execute the method in any one of the first aspect to the third aspect, or any possible design of the first aspect to the third aspect.

[0051] It can be understood that the apparatus provided in the fourth aspect, the apparatus provided in the fifth aspect, the apparatus provided in the sixth aspect, the apparatus provided in the seventh aspect, the apparatus provided in the eighth aspect, the apparatus provided in the ninth aspect, the system provided in the tenth aspect, the computer storage medium provided in the eleventh aspect, or the computer program product provided in the twelfth aspect are all used to execute the method provided in any one of the first aspect, the second aspect or the third aspect. Therefore, the beneficial effects achieved thereby can refer to the beneficial effects in the corresponding method, which will not be described here again. BRIEF DESCRIPTION OF DRAWINGS

[0052] The drawings used in the embodiments of the present application are described below.

[0053] Figure 1 is a schematic diagram of a communication system provided by an embodiment of the present application;

[0054] Figures 2-4 is a schematic diagram of a possible application framework in a communication system provided by an embodiment of the present application;

[0055] Figure 5 is a schematic diagram of a communication method provided by an embodiment of the present application;

[0056] Figure 6 is a schematic diagram of a DAG provided by an embodiment of the present application;

[0057] Figure 7 is a schematic diagram of a communication apparatus provided by an embodiment of the present application;

[0058] Figure 8 is a schematic diagram of a terminal provided by an embodiment of the present application. DETAILED DESCRIPTION

[0059] The embodiments of the present application are described below with reference to the drawings.

[0060] The technology provided by the present application can be applied to various communication systems. For example, the communication system can be a fourth generation (4G) communication system (such as a long term evolution (LTE) system), a fifth generation (5G) communication system, a wireless local area network (WLAN) system, a satellite communication system, a fusion system of multiple systems, or a future communication system. The 5G communication system can also be referred to as a new radio (NR) system.

[0061] In a communication system, a network element can send signals to or receive signals from another network element. These signals can include information, signaling, or data. The term "network element" can also be replaced by an entity, network entity, device, communication equipment, communication module, node, communication node, etc. This application uses a network element as an example for description. For instance, a communication system may include at least one terminal and at least one access network device. The access network device can send downlink signals to the terminal, and / or the terminal can send uplink signals to the access network device. Furthermore, it is understood that if the communication system includes multiple terminals, these terminals can also exchange signals; that is, both the signal-sending network element and the signal-receiving network element can be a terminal.

[0062] Figure 1 This is a schematic diagram illustrating one possible, non-limiting system. For example... Figure 1 As shown, the communication system 10 includes a radio access network (RAN) 100 and a core network (CN) 200. RAN 100 includes at least one RAN node (e.g., ...). Figure 1 110a and 110b (collectively referred to as 110) and at least one terminal (such as Figure 1 RAN 100, denoted as RAN 120a-120j, is collectively referred to as RAN 120. RAN 100 may also include other RAN nodes, such as wireless relay equipment and / or wireless backhaul equipment. Figure 1 (Not shown in the image). Terminal 120 is connected to RAN node 110 wirelessly. RAN node 110 is connected to core network 200 wirelessly or via wired connection. The core network equipment in core network 200 and RAN node 110 in RAN 100 can be different physical devices, or they can be the same physical device integrating core network logical functions and radio access network logical functions.

[0063] RAN 100 can be a cellular system related to the 3rd Generation Partnership Project (3GPP), such as 4G, 5G mobile communication systems, or future-oriented evolution systems. RAN 100 can also be an open access network (O-RAN or ORAN), a cloud radio access network (CRAN), or a wireless fidelity (WiFi) system. RAN 100 can also be a communication system that integrates two or more of the above systems.

[0064] RAN node 110, sometimes also referred to as access network equipment, RAN entity, or access node, constitutes part of the communication system and is used to help terminals achieve wireless access. Multiple RAN nodes 110 in communication system 10 can be of the same type or different types. In some scenarios, the roles of RAN node 110 and terminal 120 are relative, for example... Figure 1 Network element 120i can be a helicopter or a drone, and it can be configured as a mobile base station. For terminals 120j that access RAN 100 through network element 120i, network element 120i is a base station; however, for base station 110a, network element 120i is a terminal. RAN node 110 and terminal 120 are sometimes referred to as communication devices, for example... Figure 1 Network elements 110a and 110b can be understood as communication devices with base station functions, while network elements 120a-120j can be understood as communication devices with terminal functions.

[0065] In one possible scenario, a RAN node can be a base station, an evolved NodeB (eNodeB), an access point (AP), a transmission reception point (TRP), a next-generation NodeB (gNB), a base station in a future mobile communication system, or an access node in a WiFi system, etc. Figure 1 110a), micro base stations or indoor stations (such as Figure 1 The RAN node can be a relay node or donor node (as described in section 110b), or a wireless controller in a CRAN scenario. Optionally, the RAN node can also be a server, wearable device, vehicle, or in-vehicle equipment. For example, the access network equipment in vehicle-to-everything (V2X) technology can be a roadside unit (RSU). All or part of the functions of the RAN node in this application can also be implemented through software functions running on hardware, or through virtualization functions instantiated on a platform (e.g., a cloud platform). The RAN node can also be equipped with communication modules, circuits, or chips that perform corresponding communication functions. The RAN node can also be configured with program instructions for performing corresponding communication functions and corresponding program instructions. The RAN node in this application can also be a logical node, logical module, or software capable of implementing all or part of the RAN node functions.

[0066] In another possible scenario, a terminal is assisted by multiple RAN nodes to implement wireless access, and different RAN nodes respectively implement part of functions of a base station. For example, a RAN node can be a central unit (CU), a distributed unit (DU), a CU-control plane (CP), a CU-user plane (UP), or a radio unit (RU), etc. The CU and the DU can be separately arranged, or can also be included in the same network element, for example, in a baseband unit (BBU). The RU can be included in a radio frequency device or a radio frequency unit, for example, included in a remote radio unit (RRU), an active antenna unit (AAU), or a remote radio head (RRH).

[0067] In different systems, the CU (or CU-CP and CU-UP), DU or RU can also have different names, but those skilled in the art can understand their meanings. For example, in an ORAN system, the CU can also be referred to as an O-CU (open CU), the DU can also be referred to as an O-DU, the CU-CP can also be referred to as an O-CU-CP, the CU-UP can also be referred to as an O-CU-UP, and the RU can also be referred to as an O-RU. For the convenience of description, the CU, CU-CP, CU-UP, DU and RU are taken as examples for description in this application. Any one of the CU (or CU-CP, CU-UP), DU and RU in this application can be implemented by a software module, a hardware module, or a combination of a software module and a hardware module.

[0068] Terminal, which can access the above-mentioned communication system and has corresponding communication functions. The terminal can also be referred to as a terminal device, user equipment (UE), mobile station, mobile terminal, etc. The terminal can be widely used in various scenarios, such as device-to-device (D2D), vehicle-to-everything (V2X) communication, machine-type communication (MTC), internet of things (IOT), virtual reality, augmented reality, industrial control, autonomous driving, remote medical treatment, smart power grid, smart furniture, smart office, smart wear, smart transportation, smart city, etc. The terminal can be a mobile phone, tablet computer, computer with wireless transceiver function, wearable device, vehicle, unmanned aerial vehicle, helicopter, airplane, ship, robot, mechanical arm, smart home device, transport vehicle with wireless communication function, communication module, etc. The embodiments of the present application do not limit the device form of the terminal. The terminal is usually provided with a communication module, circuit or chip for executing corresponding communication functions. The terminal is also configured with program instructions for executing corresponding communication functions.

[0069] The core network 200 is used to complete the three functions of registration, connection and session management, mainly including network exposure function (NEF) network element, policy control function (PCF) network element, application function (AF) network element, access and mobility management function (AMF) network element, session management function (SMF) network element, user plane function (UPF) network element and the like.

[0070] The NEF network element exposes the services and capabilities of the 3GPP network functions to the AF, and also allows the AF to provide information to the 3GPP network functions, and the corresponding interface is N33 interface.

[0071] The PCF network element performs policy management of charging policy and QoS policy.

[0072] The AF network element mainly transmits the demand of the application side to the network side.

[0073] AMF network element: mainly performs mobility management, access authentication / authorization, etc. In addition, it is also responsible for transmitting user policies between UE and PCF; N1 interface is the signaling interface between UE and AMF, since UE cannot directly interact with the core network, it needs to pass through the access network (AN) to transmit non-access layer (NAS) information; N2 interface is the signaling interface for AMF to request AN to allocate resources for protocol data unit (PDU) sessions, etc.

[0074] SMF network element: complete session management functions such as UE IP address allocation, UPF selection, charging and QoS policy control, etc.

[0075] UPF network element: as an interface with a data network, it completes user plane data forwarding, session / stream level-based charging statistics, bandwidth limitation, etc. N3 interface is the interface between RAN and UPF, mainly used for transmitting uplink and downlink user plane data between 5G RAN and UPF.

[0076] Optionally, the communication system 10 further includes an Internet 300. The Internet 300 is in communication connection with the core network 200. And / or, the Internet 300 is in communication connection with the RAN 100.

[0077] In order to support AI technology in the wireless network, AI nodes can also be introduced into the network.

[0078] The AI nodes can be deployed in one or more of the following positions in the communication system: access network nodes (RAN nodes), terminal devices, or core network devices, etc., or the AI nodes can also be deployed separately, for example, in a position other than any of the above devices, such as a host or a cloud server of an over the top (OTT) system. The 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 network elements, etc.

[0079] It can be understood that the present application does not limit the number of AI nodes. For example, when there are multiple AI nodes, the multiple AI nodes can be divided based on functions, such as different AI nodes being responsible for different functions.

[0080] It can also be understood that the AI nodes can be independent devices, can be integrated into the same device to implement different functions, or can be network elements in a hardware device, or can be software functions running on a dedicated hardware, or virtualized functions instantiated on a platform (e.g., a cloud platform), and the present application does not limit the specific form of the AI nodes.

[0081] An AI node can be an AI network element or an AI module.

[0082] Figure 2 An example of a possible application framework in a communication system is shown in FIG. 1. As shown, network elements in the communication system are connected through interfaces (e.g., NG, Xn), or air interface. One or more AI modules are deployed in one or more of the network element nodes, such as a core network device, an access network node (RAN node), a terminal, or one or more devices in operation administration and maintenance (OAM) (for clarity, only one is shown in FIG. 1). The access network node can be a single RAN node or can include multiple RAN nodes, e.g., including a CU and a DU. The CU and / or the DU can also have one or more AI modules deployed therein. The CU can also be split into a CU-CP and a CU-UP, and the CU-CP and / or the CU-UP can have one or more AI modules deployed therein. Figure 2 Figure 2

[0083] An AI module is configured to implement a corresponding AI function. AI modules deployed in different network elements can be the same or different. An AI module can implement different functions according to different parameter configurations. The model of an AI module can be configured based on one or more of the following parameters: a structural parameter (e.g., at least one of a number of layers of a neural network, a width of a neural network, a connection relationship between layers, a weight of a neuron, an activation function of a neuron, or a bias in an activation function), an input parameter (e.g., a type of input parameter and / or a dimension of an input parameter), or an output parameter (e.g., a type of output parameter and / or a dimension of an output parameter). The bias in an activation function can also be referred to as a bias of a neural network.

[0084] In one example, the neural network described above can be a deep neural network (DNN), a convolutional neuron network (CNN), a recurrent neural network (RNN), or a generative adversarial network (GAN).

[0085] A DNN is an artificial neural network architecture that has multiple layers of non-linear transformation units stacked together in a hierarchical structure, forming a deep computational model. Compared with a shallow neural network, a deep neural network has more hidden layers, allowing the network model to capture more complex internal structures of data and high-level abstract features.

[0086] ​​A CNN is a deep neural network with a convolutional structure. A CNN contains a feature extractor consisting of convolutional layers and subsampling layers. This feature extractor can be viewed as a filter, and the convolution process can be seen as performing convolution between a trainable filter and an input image or a convolutional feature map.

[0087] RNN is a type of recursive neural network that takes sequence data as input, recursively moves along the direction of sequence evolution, and connects all nodes (recurrent units) in a chain-like manner.

[0088] GAN is a deep learning model. It consists of a generator and a discriminator, and is trained through adversarial learning. Its purpose is to estimate the potential distribution of data samples and generate new data samples.

[0089] 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.

[0090] Figure 3 This is a schematic diagram illustrating another possible application framework in a communication system. For example... Figure 3 As shown, the communication system includes a RAN intelligent controller (RIC). For example, the RIC can be an AI module 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.

[0091] 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, 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.

[0092] 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, 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.

[0093] 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), while non-real-time RICs can be set in OAM, cloud servers, core network devices, or other network devices.

[0094] Reference Figure 4 The diagram shown is another architectural schematic of a communication system provided in an embodiment of this application. The communication system may include a first communication device 401, a second communication device 402, and a third communication device 403.

[0095] In one possible implementation, the first communication device 401 may be a terminal. The second communication device 402 may be an access network device, such as a base station. The third communication device 403 may be a core network element, such as an AMF element, SMF element, UPF element, etc.

[0096] In another possible implementation, the first communication device 401 can be a core network element, the second communication device 402 can be an access network device, and the third communication device 403 can be a terminal.

[0097] In the example above, the terminal and core network elements communicate with the access network equipment, respectively.

[0098] In another possible implementation, the first communication device can be a terminal, the second communication device 402 can be a core network element, and the third communication device 403 can be an access network device.

[0099] Alternatively, the first communication device may be an access network device, the second communication device 402 may be a core network element, and the third communication device 403 may be a terminal.

[0100] In this example, the terminal and access network equipment communicate with the core network elements respectively.

[0101] Of course, the first communication device can also be an access network device, the second communication device 402 can be a terminal, and the third communication device 403 can be a core network element. Alternatively, the first communication device is a core network element, the second communication device 402 can be a terminal, and the third communication device 403 can be an access network device. That is, the access network device and the core network element respectively communicate with the terminal, and the present solution does not limit this.

[0102] Since the AI mechanism cannot better utilize the computing power of the above devices in the communication field, the computing power of the devices cannot be fully utilized. Based on this, the present application provides a communication method, which can align the computing power between devices, provide conditions for task segmentation (allocation), enable distributed training to be implemented, and reduce the overall latency of inference.

[0103] Based on the architecture of the above communication system, the communication method and device of the present solution will be further introduced below in conjunction with the drawings. It can be understood that the first communication device (terminal or core network element) and the second communication device (access network device) are taken as an example to illustrate the execution subject of the interaction in the present application, but the present application does not limit the execution subject of the interaction. For example, the method executed by the first communication device such as the terminal or the core network element in the present application can also be implemented by a communication / processing module or a circuit or chip (such as a modem chip (also known as a baseband chip), or a SoC chip containing a modem core, or a SIP chip, or a GPU) responsible for communication / processing function in the terminal or the core network element; the method executed by the second communication device such as the access network device in the present application can also be implemented by a module (such as a circuit, a chip or a chip system, etc.), or a logical node, a logical module or software capable of implementing all or part of the function of the access network device.

[0104] Referring to Figure 5 Fig. 1 is a flowchart of a communication method provided by an embodiment of the present application. Optionally, the method can be applied to the communication system described above, for example Figure 1 the communication system shown in Fig. 1. As shown in Figure 5 the communication method can include steps 501-503. Steps 501-503 are as follows:

[0105] 501. The first communication device sends first information to the second communication device, the first information indicating a first model ID, the first model ID indicating an AI model deployed by the first communication device. Correspondingly, the second communication device receives the first information.

[0106] The first communication device can be a terminal or a core network element. The second communication device can be an access network device, such as a base station.

[0107] The AI model may be, for example, an image recognition model, a text generation model, etc.

[0108] The AI model deployed by the first communication device, i.e., the AI model possessed by the first communication device, or the AI model supported by the first communication device. That is, the first communication device can use the AI model corresponding to the first model ID, i.e., the first communication device has the model capability of the AI model corresponding to the first model ID.

[0109] The first model ID will be introduced below.

[0110] In a possible implementation, the first model ID corresponds to one or more of the following of the AI model deployed by the first communication device: function, number of input nodes, number of output nodes, version release time, version number. The function of the AI model, i.e., the purpose of the AI model. The function may be, for example, a picture recognition function (i.e., input a single picture, output the detected object in the picture), a language recognition function (i.e., input a voice, output the text converted by language), etc. The input nodes of the AI model correspond to the input parameters of the AI model. The number of input nodes of the AI model may be, for example, 256. Correspondingly, the AI model corresponds to 256 input parameters. The output nodes of the AI model correspond to the output parameters of the AI model. The number of output nodes of the AI model may be, for example, 64 or 128, etc. Correspondingly, the AI model corresponds to 64 or 128 output parameters. The version release time may be, for example, 202401. The version number may be, for example, 01, 02, etc. The first model ID corresponds to one or more of the function, the number of input nodes, the number of output nodes, the version release time, and the version number of the AI model deployed by the first communication device, which can be understood as that the first model ID is associated with one or more of the above function, the number of input nodes, the number of output nodes, the version release time, and the version number. Alternatively, the first model ID is obtained based on one or more of the above function, the number of input nodes, the number of output nodes, the version release time, and the version number. In this example, by constructing a mapping rule that associates the model ID and the model characteristics, the terminal, the access network device, the core network element, etc. can determine the model function and the corresponding function characteristics in a direct manner, and by using the model ID generated by the mapping rule, the model capability on different devices can be aligned with less overhead.

[0111] The first model ID may be represented by one or more of numbers, letters, symbols, graphics, etc. This scheme does not limit this.

[0112] For example, as shown in Table 1, a mapping table between a model function and a model ID is provided in an embodiment of the present application.

[0113] Table 1

[0114]

[0115] In this example, the model ID corresponds to the model function.

[0116] For another example, the first model ID corresponds to the function, the number of input nodes, the number of output nodes, and the version release time of the AI model deployed by the first communication device. The first model ID can be represented as 0001-256-128-202401, or 0001256128202401. Among them, 0001 indicates the function of the AI model (such as a picture recognition function), 256 indicates the number of input nodes, 128 indicates the number of output nodes, and 202401 indicates the version release time. For another example, the first model ID can be represented as 0005-256-64-202406. Among them, 0005 indicates the function of the AI model (such as a language recognition function), 256 indicates the number of input nodes, 64 indicates the number of output nodes, and 202406 indicates the version release time. It can be understood that the representation of the above first model ID is only an example, and the specific form of the present solution is not limited.

[0117] In a possible implementation, the first model ID includes a first field and a second field, and the first field and the second field respectively indicate one or more of the above function, the number of input nodes, the number of output nodes, the version release time, and the version number. Among them, the contents indicated by the first field and the second field are different.

[0118] Among them, the contents indicated by the first field and the second field are different, which can be understood as that the first field indicates a first part of the above function, the number of input nodes, the number of output nodes, the version release time, and the version number, and the second field indicates a second part of the above function, the number of input nodes, the number of output nodes, the version release time, and the version number. The first part and the second part are completely different. For example, the first field indicates the number of input nodes and the number of output nodes, and the second field indicates the function and the version release time. For another example, the first field indicates the function, and the second field indicates the version number, etc. In this example, the model ID is displayed based on each field with specific meaning, which can intuitively express the corresponding model characteristics. The model ID generated according to the rules is aligned with the model capabilities of different devices with less overhead.

[0119] As shown in Table 2, it is a table of physical meaning of each field in a model ID of an embodiment example of the present application.

[0120] Table 2

[0121]

[0122] The table II is only an example, and the model ID can not include the reserved field #1 and / or the reserved field #2, or include other fields, and the present solution does not limit this.

[0123] In a possible implementation, the first information indicates a first check code, and the first check code is generated based on the first model ID. For example, a cyclic redundancy check (CRC) check code corresponding to the model ID can be generated. For example, the check code f(x) satisfies f(x) = x 8 +x 2 +x+1, where x represents bits of the first model ID. For example, the first model ID is 0001-256-128-20240115, and the check code is 15. In this example, the check code is used to align the computing power between devices, and based on the shorter bit overhead indication, the terminal, the access network device, and the core network element can complete the model capability alignment with less overhead.

[0124] The first model ID is introduced above, and the following describes several possible implementation manners of sending the first information by the first communication device to the second communication device.

[0125] In a possible implementation, the first communication device obtains the first model ID based on a mapping relationship between the model function and the model ID. Then, the first communication device sends the first information to the second communication device.

[0126] The mapping relationship between the model function and the model ID can be predefined, or the mapping relationship is configured by the second communication device (an access network device) or a third communication device. The predefinition includes but is not limited to a predefinition in a protocol, a default configuration when leaving a factory, or a unified regulation based on a region specification or an operation subject. The configuration can be performed by the corresponding communication device through one or more of a radio resource control (RRC) message, downlink control information (DCI), and a media access control (MAC) control element (MAC CE).

[0127] For example, the first communication device receives the mapping relationship between the model function and the model ID from the second communication device or the third communication device. For example, the mapping relationship between the model function and the model ID is the mapping table (e.g., Table 1). The first communication device generates the first model ID based on the mapping table sent by the second communication device or the third communication device. For example, the first communication device is a terminal, and the third communication device is a core network element. Alternatively, the first communication device is a core network element, and the third communication device is a terminal.

[0128] In this example, the first communication device sends the first information to the second communication device, so that the second communication device knows the model capability possessed by the first communication device. In this way, the calculation power of the devices can be aligned, and the task segmentation is provided.

[0129] The implementation of the second communication device interacting with the first communication device about the model capability possessed by the second communication device is described below.

[0130] In a possible implementation, the second communication device further sends fourth information to the first communication device, where the fourth information indicates a third model ID, and the third model ID indicates an AI model deployed by the second communication device.

[0131] That is, the second communication device informs the first communication device about the model capability possessed by the second communication device, so that the terminal can obtain the model capability possessed by the access network device, so as to compare the received model ID with the model capability possessed by the terminal, and then feed back the capability possessed by the terminal, or supplement the differentiated capability, so that the two devices can align the model capability in a short time delay.

[0132] In a possible implementation, the second communication device obtains the third model ID based on the mapping relationship between the model function and the model ID. Further, the second communication device sends the fourth information to the first communication device.

[0133] For example, the mapping relationship between the model function and the model ID can be predefined, or the mapping relationship is configured by the first communication device or the third communication device. For this part, refer to the foregoing description, and details are not described herein.

[0134] For example, the second communication device receives the mapping relationship between the model function and the model ID from the first communication device or the third communication device. For example, the mapping relationship between the model function and the model ID is the mapping table (e.g., Table 1). The second communication device generates the third model ID based on the mapping table indicated by the first communication device or the third communication device. For example, the first communication device is a terminal, and the third communication device is a core network element. Alternatively, the first communication device is a core network element, and the third communication device is a terminal.

[0135] In a possible implementation, the first model ID includes the model ID in the third model ID. That is, the model capability reported by the first communication device is a subset of the model capability of the second communication device. The first communication device reports the model ID in the third model ID, so that the second communication device can perceive the model capability possessed by the first communication device, and enable the two devices to align the model capability in a shorter time delay, and reduce the time delay of task segmentation.

[0136] In another possible implementation, the first model ID includes a model ID other than the third model ID. That is, the model capability reported by the first communication device is a model capability that is not possessed by the second communication device. The first communication device can report a model ID other than the third model ID, so that the two devices can align the model capability in a shorter time delay, and reduce the time delay of task segmentation.

[0137] In yet another possible implementation, the first model ID includes the model ID in the third model ID, and includes a model ID other than the third model ID. That is, the model capability reported by the first communication device includes a model capability in the model capability of the second communication device, and includes a model capability that is not possessed by the second communication device. The first communication device can report not only the model ID in the third model ID, but also a model ID other than the third model ID, so that the devices can fully interact with the model capability possessed by each other, and enable the two devices to align the model capability in a shorter time delay, and reduce the time delay of task segmentation.

[0138] 502. The second communication device sends second information to the first communication device, where the second information indicates a second model ID, the second model ID is a model ID in the first model ID, and the second model ID is associated with the first task. Correspondingly, the first communication device receives the second information.

[0139] The second model ID is a model ID in the first model ID, which can be understood as the second model ID being one or more model IDs in the first model ID. The second model ID is associated with the first task, which can be understood as the first task needing to be performed on a model corresponding to the second model ID. The first task may, for example, be a text-based destination positioning task. Illustratively, the second communication device needs to complete a navigation task (for example, a task that needs to provide real-time video and target instruction text). The model deployed on the second communication device has a video obstacle recognition function, and the model deployed on the first communication device has a text-based destination positioning function. Therefore, the second communication device performs task segmentation on the above-mentioned task to be completed, so that the second communication device performs obstacle recognition in the video, and the first communication device completes the text-based destination positioning task. Through the task segmentation, multiple devices can complete together, so that distributed inference can be implemented, and the task inference time delay is short.

[0140] In this example, the result of the task decomposition is indicated based on the model ID, which can save the overhead of task decomposition indication.

[0141] In a possible implementation, the second information further includes first data. The first data is data required for performing the first task. For example, the first task is a model training task, and the first data is data used for the model training. For another example, the first task is a text-based destination positioning task, and the first data is text data used for destination positioning.

[0142] The second communication device indicates a corresponding model ID to the first communication device based on the model capability reported by the first communication device, so that the first communication device performs a task based on a model corresponding to the model ID.

[0143] In a possible implementation, the second communication device is configured with a mapping relationship between model functions and model IDs. Based on the received first information, the second communication device can know the function of the model deployed by the first communication device through the mapping relationship. Further, the second communication device performs task allocation based on a task requirement. For example, the second communication device needs to complete a speech recognition task, and the first communication device deploys a model with the speech recognition function. Therefore, the second communication device indicates a model ID corresponding to the model with the speech recognition function to the first communication device.

[0144] When the second communication device does not know the mapping relationship between the model functions and the model IDs, in a possible implementation, the first communication device further sends the model function corresponding to the first model ID to the second communication device. Further, the second communication device performs task allocation based on a task requirement.

[0145] In a possible implementation, the first task includes a first subtask and a second subtask. The second communication device further sends third information to the first communication device, where the third information includes a first data packet and a second data packet, and the first data packet and the second data packet have the same service function chain header (SFC header). The first data packet corresponds to the first subtask, and the second data packet corresponds to the second subtask. Correspondingly, the first communication device receives the third information.

[0146] In this example, the first communication device is a core network element. The first task can be a text-based destination positioning task. The first subtask is text-based keyword extraction, such as the text is "find the table in the bathroom", and the keyword extraction of the text is to confirm "table" and "bathroom". The second subtask is keyword-based object positioning, that is, to determine the location of the table according to "table" and "bathroom". The data in the first data packet is data required by the first communication device to perform the first subtask, such as providing similar keyword extraction examples, examples for keyword extraction of the first subtask. The data in the second data packet is data required by the first communication device to perform the second subtask, such as an environmental map in the house, for the first communication device to determine the location corresponding to the keywords. Optionally, the second communication device can only provide data for the first subtask or the second subtask, or not provide data (such as the first communication device already has the corresponding data).

[0147] In this example, the second communication device sends third information to the first communication device, and the first data packet and the second data packet in the third information have the same SFC header, so that the first communication device can provide the same service for different subtasks corresponding to the same task, and the same QoS guarantee can be achieved.

[0148] In another possible implementation, the first task includes a third subtask and a fourth subtask. The second communication device receives fifth information from the first communication device, and the fifth information indicates a first configuration file and a second configuration file, and the first configuration file and the second configuration file are configured with the same 5QI value. The first configuration file corresponds to the third subtask, and the second configuration file corresponds to the fourth subtask.

[0149] In this example, the first communication device is a core network element. The second communication device provides consistent services for the third subtask and the fourth subtask when transmitting data in the downlink based on the same 5QI value indicated by the fifth information, so as to achieve the same QoS guarantee. For the third subtask and the fourth subtask, refer to the description of the first subtask and the second subtask above, which will not be repeated here.

[0150] In a possible implementation, the second communication device further sends sixth information to the first communication device, and the sixth information indicates the number of in-degree and out-degree of the directed acyclic graph (DAG). The in-degree and the out-degree represent the number of input (connection) nodes and the number of output (connection) nodes of a calculation node, respectively. As shown in Figure 6 The number of in-degree of node 4 is 784 (see Figure 6The diagram illustrates a weight w (not showing all nodes), with an out-degree of 1. In this example, the second communication device instructs the first communication device on the in-degree and out-degree of the directed acyclic graph (DAG). This allows the first communication device to perceive the required sub-tasks and assist the second device in performing some computations. This enables the terminal to accurately obtain information related to the sub-tasks and assists other devices in completing task reasoning with less latency. For example, the second communication device instructs the first communication device to calculate a vector with an in-degree of 784 and an out-degree of 1. Upon receiving this instruction, the first communication device performs the calculation based on the data.

[0151] Furthermore, the sixth piece of information also includes raw data. This raw data is data related to the aforementioned sub-tasks (such as the first sub-task, the second sub-task, the third sub-task, or the fourth sub-task). For example, in a navigation task, when the first communication device needs to perform a text-based destination positioning task, it needs to be provided with raw text data information.

[0152] 503. The first communication device executes the first task based on the AI ​​model corresponding to the second model ID.

[0153] The first communication device determines the AI ​​model corresponding to the second model ID, and then performs the first task based on the AI ​​model.

[0154] In one possible implementation, after completing the first task, the first communication device obtains the calculation result. Further, the first communication device sends the calculation result to the second communication device so that the second communication device can perform processing such as summarizing the calculation results.

[0155] In this embodiment, a first communication device sends first information to a second communication device, the first information indicating a first model ID, which in turn indicates an AI model deployed by the first communication device. Then, the second communication device sends second information to the first communication device, the second information indicating a second model ID, which is the model ID within the first model ID and is associated with a first task. Subsequently, the first communication device executes the first task based on the AI ​​model corresponding to the second model ID. In this example, the first communication device indicates its model capabilities to the second communication device via the first model ID, and the second communication device then instructs the first communication device to use the AI ​​model corresponding to the second model ID to execute the first task. This achieves alignment of computing power between devices, provides conditions for task partitioning, enables distributed training, and reduces the overall latency of inference.

[0156] The above Figure 5The embodiments shown take the terminal or the core network element as the first communication device and the access network equipment as the second communication device as an example for introduction. Alternatively, the present application can also take the terminal or the access network equipment as the first communication device and the core network element as the second communication device as an example for illustration. For example, the method performed by the first communication device such as the terminal or the access network equipment in the present application can also be implemented by a communication / processing module or a circuit or chip (such as a modem chip (also known as a baseband chip), or a SoC chip containing a modem core, or a SIP chip, or a GPU) responsible for communication / processing functions in the terminal or the access network equipment; the method performed by the second communication device such as the core network element in the present application can also be implemented by a module (for example, a circuit, a chip or a chip system, etc.), or a logic node, a logic module or software capable of implementing all or part of the core network element functions. Specifically, the communication method can include:

[0157] The access network equipment or the terminal sends first information to the core network element, the first information indicating a first model ID, the first model ID indicating an AI model deployed by the access network equipment or the terminal. Correspondingly, the core network element receives the first information.

[0158] Then, the core network element sends second information to the access network equipment or the terminal, the second information indicating a second model ID, the second model ID being a model ID in the first model ID, the second model ID being associated with the first task. Correspondingly, the access network equipment or the terminal receives the second information.

[0159] Further, the access network equipment or the terminal performs the first task based on the AI model corresponding to the second model ID.

[0160] In another possible implementation, the present application can also take the terminal as the first communication device and the access network equipment or the core network element as the second communication device as an example for illustration. For example, the method performed by the first communication device such as the terminal in the present application can also be implemented by a communication / processing module or a circuit or chip (such as a modem chip (also known as a baseband chip), or a SoC chip containing a modem core, or a SIP chip, or a GPU) responsible for communication / processing functions in the terminal; the method performed by the second communication device such as the access network equipment or the core network element in the present application can also be implemented by a module (for example, a circuit, a chip or a chip system, etc.), or a logic node, a logic module or software capable of implementing all or part of the access network equipment or the core network element functions. Specifically, the communication method can include:

[0161] The access network device or the core network element sends first information to the terminal, the first information indicating a first model ID, the first model ID indicating an AI model deployed by the access network device or the core network element. Correspondingly, the terminal receives the first information.

[0162] Then, the terminal sends second information to the access network device or the core network element, the second information indicating a second model ID, the second model ID being a model ID in the first model ID, the second model ID being associated with the first task. Correspondingly, the access network device or the core network element receives the second information.

[0163] Further, the access network device or the core network element performs the first task based on the AI model corresponding to the second model ID.

[0164] For the introduction of this part, please refer to the description in the embodiments shown in Figure 5 herein.

[0165] The above detailed the method of the embodiments of the present application, the following provides the device of the embodiments of the present application. It can be understood that the division of multiple units or modules in each device embodiment of the present application is only a logical division according to function, and is not as a limitation on the specific structure of the device. In the specific implementation, some of the function modules may be subdivided into more detailed function modules, and some of the function modules may be combined into one function module, but whether the function modules are subdivided or combined, the general flow performed by the device is the same. For example, some devices include a receiving unit and a sending unit. In some designs, the sending unit and the receiving unit can also be integrated into a communication unit, which can realize the functions realized by the receiving unit and the sending unit. Generally, each unit corresponds to its own program code (or program instructions), and the program code corresponding to each unit respectively running on the processor causes the unit to be controlled by the processing unit to execute the corresponding flow to realize the corresponding function.

[0166] The embodiments of the present application also provide a device for implementing any one of the above methods, for example, a communication device including a module (or means) for implementing each step performed by the first communication device or the second communication device in any one of the above methods.

[0167] Figure 7 A possible exemplary block diagram of the communication device involved in the embodiments of the present application is shown. As Figure 7 shown, the communication device 700 can include modules or units for implementing the above-mentioned method embodiments. In one possible design, the communication device 700 includes a processing unit 702 and a communication unit 703. Optionally, the communication device 700 can also include a storage unit 701 for storing device program code and / or data.

[0168] The communication apparatus 700 can be a terminal-side apparatus in the above-described embodiments, for example, a terminal or a communication module in a terminal, or a circuit or a chip responsible for a communication function in a terminal.

[0169] For example, in a possible design, the communication unit 703 is configured to: send first information, where the first information indicates a first model ID, and the first model ID indicates an AI model deployed by the first communication apparatus.

[0170] The communication unit 703 is further configured to: receive second information, where the second information indicates a second model ID, the second model ID is a model ID in the first model ID, and the second model ID is associated with a first task.

[0171] In an embodiment, the processing unit 702 is configured to: perform the first task based on an AI model corresponding to the second model ID.

[0172] In a possible design, the first model ID corresponds to one or more of the following of the AI model deployed by the first communication apparatus:

[0173] a function, a number of input nodes, a number of output nodes, a version release time, and a version number.

[0174] In a possible design, the first model ID includes a first field and a second field, the first field and the second field respectively indicate one or more of the function, the number of input nodes, the number of output nodes, the version release time, and the version number, and the first field and the second field indicate different contents.

[0175] In a possible design, the first information indicates a first check code, and the first check code is generated based on the first model ID.

[0176] In a possible design, the communication unit 703 is further configured to: receive fourth information, where the fourth information indicates a third model ID, and the third model ID indicates an AI model deployed by a second communication apparatus.

[0177] In a possible design, the first model ID includes: a model ID in the third model ID, and / or a model ID other than the third model ID.

[0178] In a possible design, when the communication apparatus 700 is a terminal or a communication module in a terminal, the function of the processing unit 702 can be implemented by one or more processors. Specifically, the processor can include a modem chip, or a system on chip (SoC) chip or a SIP chip including a modem core. The function of the communication unit 703 can be implemented by a transceiver circuit.

[0179] In a possible design, when the communication apparatus 700 is a circuit or a chip responsible for communication functions in a terminal, such as a modem chip or a system on chip (SoC) chip or a SIP chip including a modem core, the function of the processing unit 702 can be implemented by circuitry including one or more processors or processor cores in the chip (for example, the first task is object recognition based on the perceived echo signal, and a baseband chip can participate in performing the steps performed by the processing unit 702). The function of the communication unit 703 can be implemented by interface circuitry or data transceiver circuitry on the chip.

[0180] In a possible design, when the communication apparatus 700 includes a circuit or a chip responsible for communication functions in a terminal, such as a modem chip or a system on chip (SoC) chip or a SIP chip including a modem core, and further includes an AI chip, the function of the processing unit 702 can be implemented by circuitry including one or more processors or processor cores in the AI chip. The function of the communication unit 703 can be implemented by interface circuitry or data transceiver circuitry on the modem chip or the system on chip (SoC) chip or the SIP chip including the modem core.

[0181] In a possible design, when the communication apparatus 700 is a terminal or a processing module in a terminal, the function of the processing unit 702 can be implemented by one or more processors. Specifically, the processor can include a GPU, or a system on chip (SoC) chip or a SIP chip including a GPU. The function of the communication unit 703 can be implemented by transceiver circuitry.

[0182] In a possible design, when the communication apparatus 700 is a circuit or a chip responsible for processing functions in a terminal, such as a GPU or a system on chip (SoC) chip or a SIP chip including a GPU, the function of the processing unit 702 can be implemented by circuitry including one or more processors or processor cores in the chip. The function of the communication unit 703 can be implemented by interface circuitry or data transceiver circuitry on the chip.

[0183] The communication apparatus 700 can be a core network element in the embodiments described above. For example, a module (for example, a circuit, a chip, or a chip system) in the core network element, or a logic node, a logic module, or software capable of implementing all or part of the function of the core network element.

[0184] Some possible implementations of this aspect can refer to the implementation modes of the terminal side described above, and details are not repeated.

[0185] In a possible design, the first task includes a first subtask and a second subtask, and the communication unit 703 is further configured to receive third information, where the third information includes a first data packet and a second data packet, the first data packet and the second data packet have a same service function chain header (SFC header), the first data packet corresponds to the first subtask, and the second data packet corresponds to the second subtask.

[0186] The communication apparatus 700 can be a network side device in the above-described embodiments, for example, a network side access network device, a module (for example, a circuit, a chip, or a chip system, etc.) in the access network device, or a logic node, a logic module, or software capable of implementing all or part of the functions of the access network device.

[0187] For example, in an embodiment, the communication unit 703 is configured to receive first information, where the first information indicates a first model ID, and the first model ID indicates an AI model deployed by the first communication apparatus.

[0188] The communication unit 703 is further configured to send second information, where the second information indicates a second model ID, the second model ID is a model ID in the first model ID, and the second model ID is associated with the first task.

[0189] In a possible design, the first task includes a first subtask and a second subtask, and the communication unit 703 is further configured to send third information, where the third information includes a first data packet and a second data packet, the first data packet and the second data packet have a same service function chain header (SFC header), the first data packet corresponds to the first subtask, and the second data packet corresponds to the second subtask.

[0190] In a possible design, the first task includes a third subtask and a fourth subtask, and the communication unit 703 is further configured to send fifth information, where the fifth information indicates a first configuration file and a second configuration file, the first configuration file and the second configuration file are configured with a same 5QI value, the first configuration file corresponds to the third subtask, and the second configuration file corresponds to the fourth subtask.

[0191] In a possible design, the communication unit 703 is further configured to send fourth information, where the fourth information indicates a third model ID, and the third model ID indicates an AI model deployed by a second communication apparatus.

[0192] It can be understood that the division of units in the above apparatus is only a logical function division, one function unit can correspond to one function, or two or more functions can be integrated into one function unit. In actual implementation, all or part of the units can be integrated into one physical entity, or distributed in different physical entities. In addition, the above function units can be realized in the form of hardware, or in the form of software, or in the form of hardware combined with software. Whether a certain function is executed in the form of hardware or software depends on the specific application and design constraints of the technical scheme. Professional technicians can use different methods to implement the described functions for specific applications, but such implementation should not be considered beyond the scope of the present application.

[0193] In one example, the functional units in any of the above apparatuses can be one or more integrated circuits configured to implement the above methods, such as one or more application specific integrated circuits (ASICs), or one or more central processing units (CPUs), one or more microcontroller units (MCUs), one or more digital signal processors (DSPs), or one or more field programmable gate arrays (FPGAs), or a combination of at least two of these integrated circuit forms.

[0194] In one example, the storage unit 701 can include random access memory, flash memory, read only memory, programmable read only memory, or electrically erasable programmable memory, and / or registers, etc.

[0195] It should be understood that the division of each module in each of the above devices is only a logical functional division, and all or part of the modules can be integrated into one physical entity or physically separated when actually implemented. In addition, the modules in the communication device can be implemented in the form of processor calling software; for example, the communication device includes a processor, the processor is connected with a memory, the memory stores instructions, and the processor calls the instructions stored in the memory to implement any of the above methods or to realize the functions of the modules of the device, wherein the processor is, for example, a general processor such as a central processing unit (CPU) or a microprocessor, and the memory is an internal memory of the device or an external memory of the device. Alternatively, the modules in the device can be implemented in the form of hardware circuit, and the functions of part or all of the units can be realized by the design of the hardware circuit, which can be understood as one or more processors; for example, in one implementation, the hardware circuit is an application-specific integrated circuit (ASIC), and the functions of part or all of the units are realized by the design of the logical relationship between the elements in the circuit; for example, in another implementation, the hardware circuit is a programmable logic device (PLD), and a field programmable gate array (FPGA) is taken as an example, which can include a large number of logic gate circuits, and the connection relationship between the logic gate circuits is configured by a configuration file, so as to realize the functions of part or all of the units. All the modules of the above device can be realized in the form of processor calling software, or all the modules can be realized in the form of hardware circuit, or part of the modules can be realized in the form of processor calling software, and the remaining part can be realized in the form of hardware circuit.

[0196] Reference is made to Figure 8 A structural schematic diagram of a terminal 800 is provided for the embodiments of the present application, and the terminal 800 can correspond to the terminal shown in Figure 1 , and is used to realize the operations of the terminal in the above embodiments. As Figure 8 shown, the terminal includes one or more antennas 810, a radio frequency processing system 820, and a processor system 830.

[0197] In the downlink or sidelink direction, the radio frequency processing system 820 receives a radio frequency signal through the antenna 810, and sends the signal after radio frequency processing to the processor system 830 for further processing. In the uplink or sidelink direction, the processor system 830 performs signal processing on the information on the terminal side, and sends it to the radio frequency processing system 820, which performs radio frequency processing on the signal and transmits it through the antenna 810.

[0198] In one example, the radio frequency processing system 820, as a communication interface for the terminal to communicate with the outside, can include a radio frequency front end 821 (RFFE) and a radio frequency transceiver 822. The RFFE 821 is mainly used for one or more of shaping, passband selection, or gain processing of the RF signals received by the antenna or the RF signals to be sent through the antenna, and can include one or more of radio frequency switches, duplexers, filters, power amplifiers, antenna tuning, and low-noise amplifiers. The RFFE 821 can be circuit system composed of a plurality of discrete devices, or can be integrated and packaged in one or more chips. The radio frequency transceiver 822 is used to process the RF signals received by the RFFE into baseband / intermediate frequency signals for further processing by the processor system 830, and to process the baseband / intermediate frequency signals provided by the processor system 830 into RF signals for sending to the RFFE 821. The baseband / intermediate frequency signals transmitted between the radio frequency transceiver 822 and the processor system 830 can be digital signals or analog signals. The radio frequency transceiver 822 can be implemented by one or more chips, which are usually referred to as radio frequency chips (RFIC).

[0199] In one example, the processor system 830 can include one or more processors for processing signals and executing one or more communication protocols. Optionally, the processor system 830 can also include a memory 836. In one example, the one or more processors include at least one baseband processor 831 (also referred to as a modem processor). The memory 836 is used to store data and / or computer program instructions. Optionally, the processor system 830 can also include one or more application processors 832 for implementing processing of the terminal operating system and the application layer. The application processor 832 can include a GPU, for example. Optionally, the processor system 830 can also include one or more of a voice subsystem 833, a multimedia subsystem 834, or an interface circuit 835. Among them, the voice subsystem 833 is used to process voice signals, the multimedia subsystem 834 is used to process multimedia related operations such as video encoding and decoding, image processing, etc., and the interface circuit 835 is used to implement communication with other terminal components such as a display 840, an input device 850, a memory 860, etc. The above-mentioned components in the processor system 830 can communicate with each other through a bus or a communication interface circuit.

[0200] In one example, the processor system 830 can be packaged into a processor chip, such as a SoC chip or a SIP chip. In one example, the processor system 830 can be a system composed of multiple chips, for example, the baseband processor 831 therein can be packaged into a chip separately, or packaged into a chip together with part or all of the circuit of the radio frequency processing system.

[0201] In one example, the memory 836 can be an on-chip memory, i.e., located on the chip of the processor system 830. In one example, the memory 860 can be an off-chip memory, i.e., located off the chip of the processor system 830.

[0202] In one example, the baseband processor 831 can include one or more processor cores 8311 and an interface circuit 8314. The one or more processor cores 8311 are configured to process signals and perform one or more communication protocols. Optionally, the baseband processor 831 can further include a memory 8312 configured to store at least part of corresponding computer program instructions and / or data. In one example, the one or more processor cores 8311 implement the above-mentioned operations (e.g.,...) in the method embodiments by executing the computer program instructions stored in the memory 8312. In the present disclosure, the memory 8312 configured to store corresponding computer program instructions and / or data can mean that the memory 8312 is configured to store all corresponding computer program instructions and / or data for execution by the processor core 8311; or can mean that the memory 8312 is configured to store part of corresponding computer program instructions and / or data, which includes computer program instructions and / or data currently required for execution by the processor core 8311, and the memory 8312 can store different parts of computer program instructions and / or data for execution by the processor core 8311 multiple times to implement the above-mentioned operations in the method embodiments. The interface circuit 8314 serves as a communication interface to communicate with other components, such as transmitting signals with the radio frequency processing system 820, communicating with other subsystems and related components of the processor system 830 through a bus, such as transmitting data control signals with the application processor 832, and transmitting data or computer program instructions with the memory 836 or the memory 860. Optionally, to reduce the load of the processor core, a baseband signal processing circuit 8313 can be further provided to implement at least part of the processing of baseband signals, including one or more of demodulation, modulation, encoding, or decoding of signals.

[0203] In one example, the communication apparatus provided in the present application can be the terminal 800, including the communication module of the processor system 830 and the radio frequency processing system 820, the processor system 830, or the baseband processor 831.

[0204] The processor, processor system, application processor, baseband processor, processor circuit, or processor core can be collectively referred to as a processor, which can include one or a combination of a central processing unit (CPU), a digital signal processor (DSP), a microprocessor unit (MPU), a microcontroller unit (MCU), a graphics processing unit (GPU), a field programmable gate array (FPGA), an artificial intelligence processor (AI processor), or a neural processing unit (NPU).

[0205] The above memory can include one or more of the following storage media: random access memory (RAM), static RAM (SRAM), dynamic RAM (DRAM), phase-change memory (PCM), resistive RAM (ReRAM), magnetoresistive RAM (MRAM), ferroelectric RAM (FRAM), cache, register, read-only memory (ROM), flash memory, erasable programmable ROM (EPROM), hard disk, etc. In one example, computer program instructions for implementing the above embodiments can be stored on a non-volatile memory, such as at least part of the above memory 860 (e.g., one or more of ROM, flash memory, EPROM, or hard disk). During terminal operation, the corresponding computer program instructions can be loaded in whole or in part into a memory with faster transmission speed to the processor, such as at least part of the above memory 836 and / or memory 8312 (e.g., one or more of RAM, SRAM, DRAM, PCM, RERAM, MRAM, FRAM, cache, or register), for execution by the processor to implement the steps in the above method embodiments.

[0206] In one example, the radio frequency transceiver 822 and the radio frequency front end 821 can also be packaged in one chip. In one example, the radio frequency transceiver 822, the radio frequency front end 821, and the baseband processor 831 can also be packaged in one chip.

[0207] The embodiments of the present application also provide a computer readable storage medium, which stores instructions, and when the instructions run on a computer or processor, the computer or processor executes one or more steps in any of the above methods.

[0208] The embodiments of the present application also provide a computer program product containing instructions. When the computer program product runs on a computer or processor, the computer or processor executes one or more steps in any of the above methods.

[0209] It can be understood that, in this application, "indication" can include direct indication, indirect indication, display indication, and implicit indication. When describing that certain indication information is used to indicate A, it can be understood that the indication information carries A, directly indicates A, or indirectly indicates A. In this application, the information indicated by the indication information is referred to as to-be-indicated information. In the specific implementation process, there are many ways to indicate the to-be-indicated information, for example but not limited to, the to-be-indicated information can be directly indicated, such as the to-be-indicated information itself or an index of the to-be-indicated information, or the to-be-indicated information can be indirectly indicated by indicating other information, where the other information and the to-be-indicated information have an association relationship. It can also be indicated only a part of the to-be-indicated information, and the other part of the to-be-indicated information is known or agreed in advance. For example, the indication of a specific information can also be achieved by means of the arrangement order of each information agreed in advance (for example, a protocol), thereby reducing the indication overhead to a certain extent. The to-be-indicated information can be sent together as a whole, or can be sent separately in multiple sub-information, and the sending period and / or sending occasion of the sub-information can be the same or different. The specific sending method is not limited in this application. The sending period and / or sending occasion of the sub-information can be predefined, for example, predefined according to a protocol, or configured by a transmitting end device to a receiving end device by sending configuration information.

[0210] In this application, "sending information" can be understood as that a device sends information to another device, or can also be understood as that a logical module in a device sends information to another logical module. For example, "the access network device sends information" can be understood as that the access network device sends information to another device (such as a terminal), or can be understood as that a logical module 1 in the access network device sends information to a logical module 2 in the access network device.

[0211] In this application, "receiving information" can be understood as that a device receives information from another device, or can also be understood as that a logical module in a device receives information from another logical module. For example, "the access network device receives information" can be understood as that the access network device receives information from another device (such as a terminal), or can be understood as that a logical module 1 in the access network device receives information from a logical module 2 in the access network device.

[0212] In this application, "sending information to (for example, a terminal)" or related illustrations in the drawings can be understood as that the destination of the information is the terminal. It can include directly or indirectly sending information to the terminal. "Receiving information from (for example, a terminal)" or "receiving information from (for example, a terminal)" or "receiving information sent by (for example, a terminal)", or related illustrations in the drawings can be understood as that the source of the information is the terminal, and can include directly or indirectly receiving information from the terminal. The information can be processed as necessary between the source and the destination of the information, such as format change, etc., but the destination can understand the valid information from the source. Similar expressions in this application can be similarly understood, and will not be repeated here.

[0213] The terms "system" and "network" in the embodiments of the present application can be used interchangeably. "At least one" means one or more, and "multiple" means two or more. "And / or" describes the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B, which can represent the cases of A alone, A and B together, and B alone, where A and B can be singular or plural. The character " / " generally represents an "or" relationship between the associated objects. "At least one of the following" or similar expressions means any combination of these items, including any combination of single or multiple items. For example, "at least one of A, B, or C" includes A, B, C, AB, AC, BC, or ABC, and "at least one of A, B, and C" can also be understood to include A, B, C, AB, AC, BC, or ABC. In addition, unless otherwise specified, the ordinal numbers "first", "second", etc. mentioned in the embodiments of the present application are used to distinguish multiple objects, and are not used to limit the order, time sequence, priority or importance of the multiple objects.

[0214] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer usable storage media (including but not limited to magnetic disk storage, optical storage, etc.) containing computer usable program code.

[0215] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flow or blocks Figure 1 means for functionally implementing the steps listed in the flowchart block or blocks.

[0216] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the function specified in the flowchart block or blocks. Figure 1 one or more flow or blocks Figure 1 means for functionally implementing the steps listed in the flowchart block or blocks.

[0217] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flow or blocks ​ means for functionally implementing the steps listed in the flowchart block or blocks.

[0218] The terms "including", "comprising", "having" and variations thereof in the present description are intended to cover a non-exclusive inclusion. For example, a process, method, system, product, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements but can include other not listed steps or elements, or can further include steps or elements inherent in such process, method, system, product, or apparatus. It is further noted that the use of "a", "an" or "the" in the present description denotes a "one or more" of the referenced item, unless otherwise indicated. It is also noted that the terms "example" and "exemplary" in the present description are used as examples, i.e. of the types of subjects discussed optionally implementable, without necessarily being preferred or advantageous over other methods or designs.

[0219] In several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be implemented in other manners. For example, the division of the units is only a logical function division, and there can be another division manner in actual implementation, for example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. The displayed or discussed mutual couplings between or among the units, or the direct couplings or communication connections between the units, can be indirect couplings or communication connections through some interfaces, devices or units, and can be electrical, mechanical or other forms.

[0220] The units described as separated components can or can not be physically separated, and the components displayed as units can or can not be physical units, i.e., can be located in one place, or can be distributed on multiple network units. Some or all of the units can be selected according to actual needs to achieve the purposes of the embodiments of the present application.

[0221] In the above embodiments, all or part of the embodiments can be implemented by software, hardware, firmware or any combination thereof. When implemented by software, all or part of the embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed by a computer, the computer instructions generate all or part of the processes or functions according to the embodiments of the present application. The computer can be a general-purpose computer, a special-purpose computer, a computer network or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted by the computer-readable storage medium. The computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center through a wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.) manner. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. integrated with one or more available media. The available medium can be a read-only memory (ROM), or a random access memory (RAM), or a magnetic medium, such as a floppy disk, a hard disk, a magnetic tape, a magnetic disk, or an optical medium, such as a digital versatile disc (DVD), or a semiconductor medium, such as a solid state disk (SSD), etc.

[0222] Obviously, many modifications and variations of the present application are possible in light of the above teachings. It is, therefore, to be understood that within the scope of the appended claims and their equivalents, the application can be practiced otherwise than as specifically described.

Claims

1. A communication method, characterized in that, include: Send a first message, the first message indicating a first model identifier ID, the first model ID indicating an artificial intelligence (AI) model deployed on the first communication device; Receive second information, the second information indicating a second model ID, the second model ID being the model ID in the first model ID, and the second model ID being associated with the first task; The first task is executed based on the AI ​​model corresponding to the second model ID.

2. The method according to claim 1, characterized in that, The first model ID corresponds to one or more of the following AI models deployed on the first communication device: Function, number of input nodes, number of output nodes, release date, and version number.

3. The method according to claim 2, characterized in that, The first model ID includes a first field and a second field. The first field and the second field respectively indicate one or more of the following: the function, the number of input nodes, the number of output nodes, the version release time, and the version number. The contents indicated by the first field and the second field are different.

4. The method according to any one of claims 1 to 3, characterized in that, The first information indicates the first verification code, which is generated based on the first model ID.

5. The method according to any one of claims 1 to 4, characterized in that, The first task includes a first subtask and a second subtask, and the method further includes: Receive third information, which includes a first data packet and a second data packet. The first data packet and the second data packet have the same Service Function Chain (SFC) header. The first data packet corresponds to the first subtask, and the second data packet corresponds to the second subtask.

6. The method according to any one of claims 1 to 5, characterized in that, The method further includes: Receive a fourth message, the fourth message indicating a third model ID, the third model ID indicating an AI model deployed by the second communication device.

7. The method according to claim 6, characterized in that, The first model ID includes: the model ID in the third model ID, and / or other model IDs besides the third model ID.

8. A communication device, characterized in that, Includes modules or units for implementing the method as described in any one of claims 1-7.

9. A computer-readable storage medium, characterized in that, The system contains a computer program that, when executed by a processor, causes the method described in any one of claims 1-7 to be implemented.

10. A computer program product comprising instructions that, when run on a processor, cause the method as described in any one of claims 1-7 to be implemented.

Images