Communication method, and apparatus

Abstract

A communication method and an apparatus. The method comprises: a terminal reports to a network device environment information of an environment where the terminal is currently located; on the basis of the environment information reported by the terminal, the network device determines an AI model matched with the environment information, and indicates the AI model to the terminal; and the terminal uses the AI model matched with the current environment to execute model reasoning, so as to achieve a corresponding function. The present application improves the AI-based UC performance.

Description

Communication method and device

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to the Chinese patent application filed with the State Intellectual Property Office of the People's Republic of China on December 12, 2023, with application number 202311704622.8 and application name "A Communication Method and Device", the entire contents of which are incorporated by reference into this application. Technical Field

[0003] The embodiments of the present application relate to the field of communication technology, and in particular to a communication method and apparatus. Background Art

[0004] Currently, for air interface-based artificial intelligence (AI) model use cases (UC), the standard discusses designs where the AI ​​model is deployed on the terminal side, the network side, or both. For designs where the AI ​​model is deployed on the terminal side, or both, the terminal faces the challenge of selecting the appropriate AI model from among multiple AI models that implement the desired function. Due to terminal mobility and changes in the surrounding environment, the terminal's environment is time-varying. Determining the AI ​​model that matches the terminal's environment is a research topic. Summary of the Invention

[0005] The embodiments of the present application provide a communication method and apparatus so that a terminal can determine an AI model that matches an environment.

[0006] In a first aspect, a communication method is provided, which is applied to a terminal, and the execution subject of the method is the terminal, or a module (e.g., a chip or circuit) applied to the terminal, comprising: sending a first message to a network device, the first message including first indication information, the first indication information being used to indicate first environmental information of the terminal; and receiving a second message from the network device, the second message including second indication information, the second indication information being used to indicate a first artificial intelligence (AI) model corresponding to the first environmental information. Optionally, the network device may be an access network device, a core network element, an operations management and maintenance (OAM), or other AI node.

[0007] Through the above design, the terminal reports the environmental information of the terminal's current environment to the network device; the network device determines the AI ​​model that matches the environmental information based on the environmental information reported by the terminal, and indicates the AI ​​model to the terminal. The terminal uses the AI ​​model that matches the current environment, performs model reasoning, implements corresponding functions, and improves the performance of AI-based UC.

[0008] In one possible design, sending a first message to the network device includes: receiving a third message from the network device, the third message including first configuration information, the first configuration information being used to configure the terminal to report environmental information to the network device; and sending the first message to the network device according to the first configuration information.

[0009] In one possible design, the second message also includes third indication information and / or fourth indication information, the third indication information is used to indicate the conditions for enabling the first AI model, and the fourth indication information is used to indicate the method for obtaining the first AI model.

[0010] In one possible design, before sending the first message to the network device, it also includes: sending a fourth message to the network device, the fourth message including at least one of the following: fifth indication information, sixth indication information, seventh indication information, eighth indication information or ninth indication information, the fifth indication information is used to indicate the type and content of the environmental information reported by the terminal, the sixth indication information is used to indicate the correspondence between the environmental information and the identifier, the seventh indication information is used to indicate the storage capacity of the terminal, the eighth indication information is used to indicate the performance requirements of the terminal for the AI ​​model under different environmental information, and the ninth indication information is used to indicate the ability of the terminal to obtain the AI ​​model.

[0011] Through the above design, taking the correspondence between the environmental information and the identifier pre-interacted between the network device and the terminal as an example, when the terminal subsequently reports the first environmental information to the access network device, it only needs to directly report the identifier of the type corresponding to the first environmental information to the access network device, without having to report the type of the reported first environmental information to the access network device, thereby saving air interface overhead.

[0012] The second aspect is a contralateral method of the first aspect, and the beneficial effects refer to the description of the first aspect, providing a communication method, which is applied to an access network device, and the execution subject of the method is the access network device, or a module (for example, a chip or circuit, etc.) applied to the access network device, including: receiving a first message from a terminal, the first message including first indication information, and the first indication information is used to indicate first environmental information of the terminal; determining a first artificial intelligence AI model based on the first environmental information; and sending a second message to the terminal, the second message including second indication information, and the second indication information is used to indicate the first AI model.

[0013] In a possible design, it also includes: sending a third message to the terminal, the third message including first configuration information, and the first configuration information is used to configure the terminal to report environmental information to the network device.

[0014] In one possible design, the second message also includes third indication information and / or fourth indication information, the third indication information is used to indicate the conditions for enabling the first AI model, and the fourth indication information is used to indicate the method for obtaining the first AI model.

[0015] In a possible design, before receiving the first message from the terminal, it also includes: receiving a fourth message from the terminal, the fourth message including at least one of the following: fifth indication information, sixth indication information, seventh indication information, eighth indication information or ninth indication information, the fifth indication information is used to indicate the type and content of the environmental information reported by the terminal, the sixth indication information is used to indicate the correspondence between the environmental information and the identifier, the seventh indication information is used to indicate the storage capacity of the terminal, the eighth indication information is used to indicate the performance requirements of the terminal for the AI ​​model under different environmental information, and the ninth indication information is used to indicate the ability of the terminal to obtain the AI ​​model.

[0016] According to a third aspect, a communication method is provided, wherein the execution subject of the method is a terminal, or a module applied in the terminal, and the method includes: receiving a fifth message from a network device, wherein the fifth message includes tenth indication information, and the tenth indication information is used to indicate second environmental information of the network device; and determining a second artificial intelligence AI model based on the second environmental information.

[0017] Through the above design, the access network device provides the terminal with the environmental information that the access network device can obtain. The terminal determines the second AI model that matches the terminal environment based on a comprehensive decision including the environmental information provided by the access network device and the environmental information it can obtain. This avoids the degradation of the terminal's reasoning performance due to the mismatch between the environment and the AI ​​model, and improves the performance of AI-based UC.

[0018] In one possible design, after determining the second AI model, it also includes: sending a sixth message to the network device, the sixth message including eleventh indication information, and the eleventh indication information is used to indicate the second AI model.

[0019] In a possible design, the sixth message also includes: twelfth indication information and / or thirteenth indication information, the twelfth indication information is used to indicate the first condition for the terminal to start the second AI model, and the thirteenth indication information is used to indicate the first method for the terminal to obtain the second AI model.

[0020] In a possible design, it also includes: receiving a seventh message from the network device, the seventh message including at least one of the following: fourteenth indication information, fifteenth indication information, or sixteenth indication information, the fourteenth indication information is used to indicate a third AI model, the third AI model and the second AI model implement the same function, the fifteenth indication information is used to indicate the second method for the terminal to obtain the second AI model, and the sixteenth indication information is used to indicate the second condition for the terminal to start the second AI model.

[0021] In a possible design, it also includes: receiving an eighth message from the network device, the eighth message including at least one of the following: seventeenth indication information, eighteenth indication information, nineteenth indication information or twentieth indication information, the seventeenth indication information is used to indicate the identifier of the AI ​​model that the network device can provide under different environmental information, the eighteenth indication information is used to indicate the transmission method supported when the network device transmits the AI ​​model to the terminal, the nineteenth indication information is used to indicate the type and content included in the environmental information, and the twentieth indication information is used to indicate the mapping relationship between the environmental information and the identifier.

[0022] A fourth aspect. This is the counterpart method of the third aspect. The beneficial effects can be referred to the description of the third aspect. A communication method is provided. The method is applied to an access network device. The execution subject of the method is the access network device, or a module applied to the access network device, and includes: obtaining second environment information of the network device; and sending a fifth message to a terminal, the fifth message including tenth indication information, the tenth indication information being used to indicate the second environment information.

[0023] In a possible design, it also includes: receiving a sixth message from the terminal, the sixth message including eleventh indication information, the eleventh indication information is used to indicate a second artificial intelligence AI model, and the second AI model is determined based on the second environment information.

[0024] In a possible design, the sixth message also includes: twelfth indication information, and / or thirteenth indication information, the twelfth indication information is used to indicate the first condition for the terminal to start the second AI model, and the thirteenth indication information is used to indicate the first method for the terminal to obtain the second AI model.

[0025] In a possible design, it also includes: sending a seventh message to the terminal, the seventh message including at least one of the following: fourteenth indication information, fifteenth indication information, or sixteenth indication information, the fourteenth indication information is used to indicate a third AI model, and the third AI model implements the same function as the second AI model, the fifteenth indication information is used to indicate the second method for the terminal to obtain the second AI model, and the sixteenth indication information is used to indicate the second condition for the terminal to start the second AI model.

[0026] In a possible design, it also includes: sending an eighth message to the terminal, the eighth message including at least one of the following: seventeenth indication information, eighteenth indication information, nineteenth indication information, or twentieth indication information, the seventeenth indication information is used to indicate the identifier of the AI ​​model that the network device can provide under different environmental information, the eighteenth indication information is used to indicate the transmission method supported when the network device transmits the AI ​​model to the terminal, the nineteenth indication information is used to indicate the type and content included in the environmental information, and the twentieth indication information is used to indicate the mapping relationship between the environmental information and the identifier.

[0027] In a fifth aspect, a device is provided that can implement the method of the first or third aspect. For example, the device includes means for executing the corresponding method of the first or third aspect. The device can be implemented through hardware, software, or hardware executing the corresponding software implementation.

[0028] In one possible design, the device includes a unit that performs the first aspect or the third aspect described above.

[0029] In one possible design, the device includes a processor, which is used to execute the method of the first aspect or the third aspect mentioned above.

[0030] In one possible design, the device includes a processor and an interface circuit, the interface circuit is used to receive signals from other devices outside the device and transmit them to the processor or send signals from the processor to other devices outside the device, and the processor is used to implement the method in the first or third aspect above through logic circuits or executing code instructions.

[0031] In one possible design, the device includes a processor and a memory, and the processor is used to execute a computer program or instruction stored in the memory, so that the device implements the method of the first aspect or the third aspect mentioned above.

[0032] Optionally, the device may be the first device, or a module or unit (for example, a chip, or a chip system, or a circuit) in the first device that corresponds one-to-one to executing the method / operation / step / action described in the first aspect or the third aspect, or may be capable of being used in combination with the first device.

[0033] In a sixth aspect, a device is provided that can implement the method of the second or fourth aspect. For example, the device includes means for executing the corresponding method of the second or fourth aspect. The device can be implemented through hardware, software, or hardware executing the corresponding software implementation.

[0034] In one possible design, the apparatus includes a unit for executing the second aspect or the fourth aspect described above.

[0035] In one possible design, the device includes a processor, which is used to execute the method of the second aspect or the fourth aspect above.

[0036] In one possible design, the device includes a processor and an interface circuit, the interface circuit is used to receive signals from other devices outside the device and transmit them to the processor or send signals from the processor to other devices outside the device, and the processor is used to implement the method in the second or fourth aspect above through logic circuits or execution code instructions.

[0037] In one possible design, the device includes a processor and a memory, and the processor is used to execute a computer program or instruction stored in the memory, so that the device implements the method of the second aspect or the fourth aspect above.

[0038] Optionally, the device may be a second device, or a module or unit (for example, a chip, or a chip system, or a circuit) in the second device that corresponds one-to-one to executing the method / operation / step / action described in the second aspect or the fourth aspect, or may be capable of being used in combination with the second device.

[0039] In the seventh aspect, a computer-readable storage medium is provided, which stores a computer program or instruction. When the computer program or instruction is executed on a computer, the computer implements the method of any one of the first to fourth aspects above.

[0040] In an eighth aspect, a computer program product is provided, comprising a computer program or instructions, which enables the method of any one of the above-mentioned first to fourth aspects to be executed when the computer program or instructions are executed by a computer.

[0041] In the ninth aspect, a chip is provided, comprising a processor, wherein the processor is coupled to a memory and is used to execute a computer program or instruction stored in the memory, so that the chip implements the method of any one of the first to fourth aspects above.

[0042] In the tenth aspect, a communication system is provided, comprising: a first communication device and a second communication device; wherein the first communication device is used to implement the method of the first aspect above, and the second communication device is used to implement the method of the second aspect above; or, the first communication device is used to implement the method of the third aspect above, and the second communication device is used to implement the method of the fourth aspect above. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] FIG1 is a schematic diagram of the architecture of a communication system provided in an embodiment of the present application;

[0044] FIG2 is a schematic diagram of the application architecture of the AI ​​model provided in an embodiment of the present application;

[0045] FIG3 is a schematic diagram of a neuron provided in an embodiment of the present application;

[0046] FIG4 is a schematic diagram of a neural network provided in an embodiment of the present application;

[0047] FIG5 is a flow chart of a communication method according to an embodiment of the present application;

[0048] FIG6 is another schematic diagram of a flow chart of a communication method according to an embodiment of the present application;

[0049] FIG7 is a schematic structural diagram of a device provided in an embodiment of the present application;

[0050] FIG8 is another schematic diagram of the structure of the device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0051] In order to make the purpose, technical solutions and advantages of this application more clear, the application will be further described in detail below with reference to the accompanying drawings. The specific operation methods and functional descriptions in the method embodiments can also be applied to the device embodiments or system embodiments.

[0052] The various numbers and terms such as "first" and "second" used in the embodiments of this application are merely for convenience of description and are not intended to limit the scope of the embodiments of this application. The order of the sequence numbers of the above-mentioned processes does not necessarily indicate the order in which they are executed. The order in which the processes are executed should be determined by their functions and internal logic.

[0053] In the embodiments of the present application, the number of nouns, unless otherwise specified, means "singular noun or plural noun", that is, "one or more". "At least one" means one or more, and "plurality" means two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship; "including at least one of A, B or C" can mean: including A; including B; including C; including A and B; including A and C; including B and C; including A, B and C.

[0054] FIG1 shows a possible, non-limiting system diagram. As shown in FIG1 , a communication system 10 includes a radio access network (RAN) 100 and a core network (CN) 200. Optionally, it also includes an operation administration and maintenance (OAM) 300.

[0055] 1. RAN

[0056] The RAN 100 includes at least one RAN node (e.g., 110a and 110b in FIG. 1 , collectively referred to as 110) and at least one terminal (e.g., 120a to 120j in FIG. 1 , collectively referred to as 120). The RAN 100 may also include other RAN nodes, such as wireless relay equipment and / or wireless backhaul equipment (not shown in FIG. 1).

[0057] Terminal 120 can be connected to RAN node 110 wirelessly. RAN node 110 is connected to core network 200 wirelessly or by wire. The core network element in core network 200 and RAN node 110 in RAN 100 can be different physical devices, or they can be a single physical device that integrates the logical functions of the core network element and the logical functions of the radio access network.

[0058] The multiple RAN nodes 110 in the communication system 10 can be nodes of the same type or different types. In some scenarios, the roles of the RAN nodes 110 and the terminals 120 are relative. For example, in FIG1 , the network element 120i can be a helicopter or a drone, which can be configured as a mobile base station. For the terminals 120j accessing the RAN 100 through the network element 120i, the network element 120i is a base station; however, for the base station 110a, the network element 120i is a terminal.

[0059] RAN 100 may be a cellular system related to the Third Generation Partnership Project (3GPP), such as a fourth generation (4G) mobile communication system, a fifth generation (5G) mobile communication system, or a future-oriented evolution system, such as a sixth generation (6G) mobile communication system. RAN 100 may also be an open access network (O-RAN or ORAN), a cloud radio access network (CRAN), or a wireless fidelity (WiFi) system. RAN 100 may also be a communication system that integrates two or more of the above systems.

[0060] 1.1 RAN Node

[0061] In one possible scenario, a RAN node may be a base station, an evolved NodeB (eNodeB), an access point (AP), a transmission reception point (TRP), a next generation NodeB (gNB), a next generation base station in a 6G mobile communication system, a base station in a future mobile communication system, or an access node in a WiFi system. A RAN node may be a macro base station (such as 110a in FIG1 ), a micro base station or an indoor station (such as 110b in FIG1 ), a relay node or a donor node, or a wireless controller in a CRAN scenario. Optionally, a RAN node may also be a server, a wearable device, a vehicle or an onboard device. For example, an access network device in vehicle to everything (V2X) technology may be a road side unit (RSU). All or part of the functions of the RAN node in the embodiments of the present application may also be implemented by software functions running on hardware, or by virtualized functions instantiated on a platform (such as a cloud platform). The RAN node in the embodiments of the present application may also be a logical node, a logical module, or software that can implement all or part of the functions of the RAN node.

[0062] In another possible scenario, multiple RAN nodes collaborate to assist the terminal in achieving wireless access, and different RAN nodes respectively implement part of the functions of the base station. For example, the RAN node can be a centralized unit (CU), a distributed unit (DU), a CU-control plane (CP), a CU-user plane (UP), or a radio unit (RU). The CU and DU can be set separately, or they can be included in the same network element, such as a baseband unit (BBU). The RU can be included in a radio frequency device or radio frequency unit, such as a remote radio unit (RRU), an active antenna unit (AAU), or a remote radio head (RRH).

[0063] In different systems, CU (or CU-CP and CU-UP), DU or RU may also have different names, but those skilled in the art can understand their meanings. For example, in the ORAN system, CU may also be called O-CU (Open CU), DU may also be called O-DU, CU-CP may also be called O-CU-CP, CU-UP may also be called O-CU-UP, and RU may also be called O-RU. For the convenience of description, this application uses CU, CU-CP, CU-UP, DU and RU as examples for description. Any unit of CU (or CU-CP, CU-UP), DU and RU in this application can be implemented by a software module, a hardware module, or a combination of a software module and a hardware module.

[0064] A RAN node, sometimes also referred to as an access network device, RAN entity, or access node, constitutes part of a communication system and helps terminals achieve wireless access. In the subsequent description of this application, unless otherwise specified, the term "access network device" is used for description.

[0065] It is understandable that the access network device can be referred to as a communication device. For example, the access network device can be understood as a device having the function of an access network device. For example, the device for implementing the function of the access network device can be the access network device; or some components in the access network device, such as CU, DU, etc. It can also be a device that can support the access network device to implement the function, such as a chip system, a hardware circuit, a software module, or a hardware circuit plus a software module. The device can be installed in the access network device or can be used in conjunction with the access network device. In the embodiment of the present application, the chip system can be composed of a chip, or it can include a chip and other discrete devices.

[0066] 1.2 Terminal

[0067] A terminal may 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 (VR), augmented reality (AR), industrial control, autonomous driving, telemedicine, smart grid, smart furniture, smart office, smart wearable, smart transportation, smart city, etc. The terminal can be a mobile phone, a head-mounted display device, a tablet computer, a computer with wireless transceiver function, a wearable device, a vehicle, a drone, a helicopter, an airplane, a ship, a robot, a robotic arm, a smart home device, etc. The embodiments of the present application do not limit the device form of the terminal.

[0068] It is understood that a terminal can be referred to as a communication device. For example, a terminal can be understood as a device having terminal functions. For example, a device used to implement the functions of a terminal device can be a terminal device; it can also be a device that supports the terminal device in implementing the functions, such as a chip system, hardware circuit, software module, or hardware circuit and software module, which can be installed in the terminal device or can be used in conjunction with the terminal device.

[0069] 2. CN

[0070] CN200 includes at least one core network element. Taking the 5G communication system as an example, CN200 includes the access and mobility management function (AMF) network element, the session management function (SMF) network element, the user plane function (UPF) network element, the policy control function (PCF) network element, the unified data management (UDM) network element, and the application function (AF) network element.

[0071] It is understood that a core network element can be referred to as a communication device. For example, a core network element can be understood as a device that has core network functions. For example, a device used to implement the functions of a core network element can be a core network element; it can also be a device that supports the core network element in implementing the functions, such as a chip system, hardware circuit, software module, or a hardware circuit and software module. This device can be installed in the core network element or can be used in conjunction with the core network element.

[0072] 3. OAM

[0073] OAM, also known as network management, is used to operate, manage, and maintain access network devices (network management of access network devices) and / or core network elements (network management of core network elements). The OAM for access network devices and the OAM for core network elements can be the same or different, without limitation. For example, the communication system shown in Figure 1 includes a first OAM and a second OAM. The first OAM is the network management of the access network devices, and the second OAM is the network management of the core network elements.

[0074] It is understood that OAM can be referred to as a communication device. For example, OAM can be understood as a device that has OAM functions. For example, the device used to implement OAM functions can be OAM; it can also be a device that supports OAM to implement such functions, such as a chip system, hardware circuit, software module, or a hardware circuit and software module. This device can be installed in OAM or can be used in conjunction with OAM.

[0075] In order to support artificial intelligence (AI) in wireless networks, independent network elements are introduced into the communication system 10 shown in Figure 1, which are called AI network elements (or AI nodes) to implement AI-related operations. The AI ​​network element can be directly connected to the access network device in the communication system 10, or can be connected to the access network device through a third-party network element. Among them, the third-party network element can be a core network network element such as AMF or UPF. Alternatively, at least one of the terminals, access network devices, core network network elements or OAM shown in Figure 1 has a built-in AI module or AI entity for implementing AI-related operations. In this case, the network element that performs AI-related operations is called a network element with built-in AI function.

[0076] For example, an AI model can be deployed within at least one of a terminal, access network device, core network element, or OAM, and the corresponding functionality can be implemented using this AI model. The AI ​​models deployed in different nodes can be the same or different. A different model can refer to at least one of the following: different structural parameters of the model, such as the number of layers and / or weights; different input parameters of the model; or different output parameters of the model. Optionally, the functionality of the access network device can be further split into a CU and a DU. The AI ​​model can be deployed in the CU and / or the DU.

[0077] For example, CU and DU can be understood as the division of access network equipment from a logical functional perspective. CU and DU can be physically separated or deployed together, etc., without limitation. Multiple DUs can be connected to (share) one CU, and one DU can also be connected to multiple CUs. Multiple CUs can be physically set up centrally or separately. The CU and DU can be connected through an interface, for example, the interface can be an F1 interface. CU and DU can be divided according to the protocol layer of the wireless network: for example, the packet data convergence protocol (PDCP) layer and the protocol layers above the PDCP layer are set in the CU. For example, the CU is used to perform the functions of the radio resource control (RRC) layer, the service data adaptation protocol (SDAP) layer, and the PDCP layer. The protocol layers below the PDCP layer are set in the DU. For example, the DU is used to perform the functions of the radio link control (RLC) layer, the media access control (MAC) layer, and the physical layer.

[0078] The above division of the processing functions of CU and DU according to the protocol layer is only an example, and they can also be divided in other ways. For example, the CU or DU can be divided into functions with more protocol layers, and for another example, the CU or DU can be divided into partial processing functions with the protocol layer. For example, some functions of the RLC layer and the functions of the protocol layers above the RLC layer are set in the CU, and the remaining functions of the RLC layer and the functions of the protocol layers below the RLC layer are set in the DU. Alternatively, the functions of the CU or DU can be divided according to the service type or other system requirements, for example, by delay, the functions whose processing time needs to meet the delay requirements are set in the DU, and the functions that do not need to meet the delay requirements are set in the CU, etc. Alternatively, the CU can have one or more functions of the core network. For example, the CU can be set on the network side to facilitate centralized management. The DU can have multiple radio frequency functions, for example, the radio frequency function of the DU is set remotely.

[0079] Furthermore, the CU can be split into the CU-CP and CU-UP. AI models can be deployed in the CU-CP and / or CU-UP.

[0080] For example, the CU's functionality can be further split. For example, the control plane (CP) and user plane (UP) can be separated into the CU control plane (CU-CP) and CU user plane (CU-UP), respectively. Optionally, the CU-CP and CU-UP are implemented by different entities and connected via the E1 interface. The CU-CP and CU-UP can be coupled with the DU to jointly perform the functions of the access network device. The interface between the CU-CP and DU can be F1-C, and the interface between the CU-UP and DU can be F1-D.

[0081] Furthermore, a CU-CP can be split into multiple CU-CPs. For example, a CU-CP can be split into CU-CP1 and CU-CP2. The AI ​​model can be deployed in CP-CP1 and / or CU-CP2.

[0082] For example, the CU-CP functions are further divided into CU-CP1 and CU-CP2. CU-CP1 is used to implement radio resource management functions, while CU-CP2 includes RRC and PDCP control plane functions. For example, CU-CP1 is responsible for AI model reception and model inference, and generates specific interaction instructions, which are then sent to the corresponding network element by CP-CP2.

[0083] It is understandable that when the AI ​​model is deployed in a terminal, access network device, core network element or OAM, the current interface can be reused when the relevant parameters of the AI ​​model are transmitted between different network elements. For example, the communication between OAM and the access network device can reuse the current northbound interface, the communication between the access network device and the terminal can reuse the current Uu interface (air interface), and the communication between the access network device and the access network device can reuse the current Xn interface, etc. When an independent AI network element is introduced and an AI model is deployed in the AI ​​network element, it is necessary to rebuild the communication link between the AI ​​network element and the access network device, core network device and OAM.

[0084]

AI Model

[0085] The AI ​​model is the specific implementation of the AI ​​function. The AI ​​model characterizes the mapping relationship between the input and output of the model. The AI ​​model can be a neural network, a linear regression model, a decision tree model, a support vector machine (SVM), a Bayesian network, a Q learning model, or other machine learning models. AI functions may include one or more of the following: data collection (collecting training data and / or inference data), data preprocessing, model training (model learning), model information release (configuring model information), model verification, model inference, or inference result release, etc.

[0086] As shown in Figure 2, it is a schematic diagram of an application architecture of an AI model. The data source is used to store training data and inference data. The model training host obtains an AI model by analyzing or training the training data provided by the data source, and deploys the AI ​​model in the model inference host. Optionally, the model training node can also update the AI ​​model deployed on the model inference node. The model inference node can also feedback relevant information of the deployed model to the model training node, so that the model training node can optimize or update the deployed AI model.

[0087] Among them, the AI ​​model is obtained by learning the model training node, which is equivalent to the mapping relationship between the input and output of the model obtained by the model training node using the training data. The model inference node uses the AI ​​model to perform inference based on the inference data provided by the data source to obtain the inference result. The method can also be described as: the model inference node inputs the inference data into the AI ​​model, and obtains the output through the AI ​​model, and the output is the inference result. The inference result can indicate: the configuration parameters used (executed) by the execution object, and / or the operation performed by the execution object. The inference result can be uniformly planned by the execution (actor) entity and sent to one or more execution objects (for example, network entities) for execution. Optionally, the execution entity or execution object can feed back the measurement results of the parameters or measurement quantities it collects to the data source. This process can be called performance feedback, and the parameters fed back can be used as training data or inference data. Optionally, feedback information related to the model performance can be determined based on the inference results output by the model inference node, and the feedback information can be fed back to the model inference node. The model inference node can feed back the performance information of the model to the model training node based on the feedback information, so that the model training node can optimize or update the deployed AI model, etc. This process can be called model feedback.

[0088] AI models can be neural networks or other machine learning models. For example, neural networks are a specific implementation of machine learning technology. According to the universal approximation theorem, neural networks can theoretically approximate any continuous function, enabling them to learn arbitrary mappings. Therefore, neural networks can accurately abstractly model complex, high-dimensional problems.

[0089] The idea of ​​a neural network originates from the neuron structure of the brain. Each neuron performs a weighted sum operation on its input values ​​and generates an output through an activation function. Figure 3 shows a schematic diagram of the neuron structure. Assume that the input of a neuron is x = [x0, x1, ..., x n ], and the weights corresponding to each input are w=[w,w1,…,w n ], the bias of the weighted sum is b. The activation function can be diversified. Assume that the activation function of a neuron is: y = f(z) = max(0,z), the output of the neuron is: For example, the activation function of a neuron is: y = f(z) = z, and the output of the neuron is: x i 、w i , and b can take various possible values, such as decimals, integers (including 0, positive integers or negative integers), or complex numbers. The activation functions of different neurons in a neural network can be the same or different.

[0090] A neural network generally comprises a multi-layer structure, with each layer comprising one or more neurons. Increasing the depth and / or width of a neural network can improve its expressive power, providing more powerful information extraction and abstract modeling capabilities for complex systems. The depth of a neural network can refer to the number of layers it comprises, and the number of neurons in each layer can be referred to as the width of that layer. Figure 4 shows a schematic diagram of the layer relationships of a neural network. For example, a neural network comprises an input layer and an output layer. The input layer of the neural network processes the input received by the neurons and then passes the result to the output layer, which then obtains the output of the neural network. Alternatively, a neural network may comprise an input layer, a hidden layer, and an output layer. The input layer of the neural network processes the input received by the neurons and then passes the result to an intermediate hidden layer. The hidden layer then passes the calculation result to the output layer or an adjacent hidden layer, and finally the output layer obtains the output of the neural network. A neural network can comprise one or more sequentially connected hidden layers, without limitation. During the training process of a neural network, a loss function can be defined. The loss function describes the gap or difference between the output value of the neural network and the ideal target value. The embodiments of this application do not limit the specific form of the loss function. The training process of a neural network is to adjust the neural network parameters, such as the number of neural network layers, width, neuron weights, and / or parameters in the neuron activation function, so that the value of the loss function is less than the threshold value or meets the target requirements.

[0091] The terminal can realize the corresponding functions by using the AI ​​model. For example, when the terminal performs model inference, it can select an AI model from multiple AI models with the same function. Because in different environments, even AI models that realize the same function can achieve different performance. For example, AI model 1, AI model 2 and AI model 3 can all realize the function of predicting the load of access network equipment. In a specific environment, the load prediction accuracy of AI model 1 is 98%, the load prediction accuracy of AI model 2 is 95%, and the load prediction accuracy of AI model 3 is 90%. How to select an AI model that matches the current environment of the terminal based on the current environmental information of the terminal is a technical problem to be solved in the embodiments of the present application.

[0092] For current AI-based use cases (UC) over the air interface, the standard discusses deploying AI models on the terminal side, the network side, or both the terminal and the NW. For example, for certain functions, the terminal and the NW collaborate to complete them. For example, to reduce the overhead of the terminal feeding back downlink data channel information to the access network equipment, a channel state information (CSI) compression model can be deployed on the terminal side. The terminal measures the downlink reference signal, determines the downlink data channel matrix H, and inputs H into the CSI compression model to obtain compressed CSI. The terminal feeds back the compressed CSI to the access network equipment. The access network equipment deploys a CSI decompression model, which inputs the received compressed CSI into the CSI decompression model to obtain the recovered downlink data channel matrix H. The access network equipment can perform operations such as precoding the downlink data based on the recovered downlink data channel matrix H. For designs where the AI ​​model is deployed on the terminal side, or where the AI ​​model is deployed on both the terminal and the NW side, the terminal faces the problem of selecting the appropriate (e.g., optimal) AI model from among the multiple AI models that implement the function.

[0093] In one possible implementation, the network device may indicate the identifier of the AI ​​model it uses to the terminal, and the terminal selects the corresponding AI model based on the indication of the network device. Due to factors such as the movement of the terminal and changes in the surrounding environment, the environment in which the terminal is located changes in real time. Therefore, it is necessary to dynamically adjust the AI ​​model used by the terminal according to the different environments in which the terminal is located. For the above-mentioned solution in which the network device indicates the AI ​​model used by the terminal to the terminal, since the network device cannot obtain the actual environmental information of the terminal at any time, the AI ​​model configured by the network device for the terminal may not match the current environment of the terminal, thereby affecting the performance of the AI-based UC.

[0094] In view of this, an embodiment of the present application provides a communication method and device, which includes: the terminal reports environmental information of the terminal's current environment to a network device; the network device determines an AI model that matches the environmental information based on the environmental information reported by the terminal, and indicates the AI ​​model to the terminal. The terminal uses the AI ​​model that matches the current environment, performs model reasoning, implements corresponding functions, and improves the performance of AI-based UC.

[0095] It is understandable that the network device may be a node that has the ability to configure an AI model for the terminal and requires the terminal to provide environmental information for assistance. The network device may be referred to as NW for short. For example, the network device may be an access network device, a CU in an access network device, a CU-CP in an access network device, a core network element, an OAM, or other third-party nodes, etc. In the following process description, the network device is described as an access network device. It is understandable that when the network device is an OAM or a core network element, the network device and the terminal may exchange related messages through the data plane bearer or the non-access stratum (NAS) message of the control plane. For example, the terminal sends a NAS message to the OAM or core network element through the access network device, and the NAS message includes the first message below. The OAM or core network element sends a NAS message to the terminal through the access network device, and the NAS message includes the second message below, etc.

[0096] As shown in FIG5 , a schematic diagram of a process method is provided, including:

[0097] Step 510: The access network device sends a third message to the terminal, and the terminal receives the third message from the access network device.

[0098] For example, the third message includes first configuration information, and the first configuration information is used to configure the terminal to report environmental information to the access network device. For example, the first configuration information is used to configure the type and content of environmental information reported by the terminal to the access network device. For example, environmental information includes five types, namely:

[0099] 1. Macroscopic physical properties of the terminal.

[0100] For example, the terminal's moving speed, moving direction, geographical location, and altitude.

[0101] 2. Software and / or hardware attributes of the terminal.

[0102] For example, the terminal's effective power, computing power, storage space, supported AI model compilation environment, etc.

[0103] 3. The channel environment in which the terminal is located.

[0104] For example, the channel environment in which the terminal is located may be an urban macro environment, an urban micro environment, or an indoor hotspot.

[0105] 4. Communication configuration of terminals and access network equipment.

[0106] For example, the communication configuration includes a downlink communication configuration and / or an uplink communication configuration. For example, the downlink communication configuration includes the number of receiving antennas and receiving ports of the terminal, and the number of transmitting antennas and transmitting ports of the access network device. The uplink communication configuration includes the number of transmitting antennas and transmitting ports of the terminal, and the number of receiving antennas and receiving ports of the access network device.

[0107] 5. Time and frequency domain resources for terminal air interface communication.

[0108] For example, the carrier frequency, subcarrier spacing, or bandwidth of terminal communication.

[0109] The access network device can configure the terminal to report one or more of the five types of environmental information listed above. For each type of environmental information, the access network device can also configure the specific content of the environmental information reported by the terminal. For example, for one type of environmental information, such as the terminal's macroscopic physical attributes, the access network device can configure the terminal to report specific environmental information, namely the terminal's movement speed.

[0110] For example, the access network device determines the type and content of the environmental information reported by the terminal, and configures it to the terminal through the first configuration information. The terminal reports the environmental information to the access network device according to the configuration. In one possible implementation, the terminal and the access network device can exchange the type and content of the environmental information reported by the terminal in advance. One type of environmental information can be called a combination of environmental information. For example, an environmental information combination includes: mobile speed (a macroscopic physical attribute of the terminal), the channel environment to which the terminal belongs, and the carrier frequency of the terminal communication (a time-frequency domain resource of the terminal communication). The environmental information combination is also called an environmental information pattern. Furthermore, the terminal and the access network device can also exchange the correspondence between environmental information and identifiers. For example, the correspondence between environmental information and identifiers can be one-to-one or one-to-many, without limitation. For example, the correspondence between environmental information and identifiers includes: environmental information 1 corresponds to identifier A, and environmental information 2 corresponds to identifier B. In one possible implementation, the access network device can select one type of environmental information from multiple types of environmental information and determine the identifier corresponding to the environmental information. When configuring a terminal to report environmental information, the access network device may indicate to the terminal the identifier corresponding to the environmental information. For example, the third message may include the identifier of the environmental information. Upon receiving the third message, the terminal obtains the identifier of the environmental information from the third message and, based on the correspondence between the environmental information and the identifier, determines the type and content of the environmental information to be reported. Alternatively, the access network device may directly instruct the terminal to report the type and content of the environmental information, with the first configuration information specifically including the type and content of the environmental information to be reported by the terminal. For example, the access network device may instruct the terminal to report its channel environment. Alternatively, the type and content of the environmental information to be reported by the terminal are preset, and the terminal reports the environmental information according to the preset method. Alternatively, the terminal determines the type and content of the environmental information to be reported, and reports the environmental information to the access network device based on the content it determines. It can be seen that in addition to the method configured by the access network device, the terminal may also report environmental information to the access network device according to a preset method or a method determined by the terminal itself. Therefore, step 510 described above is optional.

[0111] Optionally, the first configuration information is also used to configure the way in which the terminal reports environmental information to the access network device. For example, the terminal is configured to periodically report environmental information to the access network device, or to report environmental information to the access network device based on conditional triggering. Different environmental information has different corresponding triggering conditions. For example, a speed threshold can be configured, and when the terminal's moving speed is greater than or equal to the speed threshold, the terminal is triggered to report environmental information. Or, when the terminal's environmental information changes relative to the last reporting of environmental information, the terminal is triggered to report the next environmental information. For example, the terminal performs environmental information reporting for the first time according to the configuration of the access network device. When the detected environmental information changes relative to the environmental information reported for the first time, the terminal is triggered to report the environmental information for the second time. Similarly, when the detected environmental information changes relative to the environmental information reported for the second time, the terminal is triggered to report the environmental information for the third time.

[0112] Step 520: The terminal sends a first message to the access network device, and the access network device receives the first message from the terminal.

[0113] The first message includes first indication information, which is used to indicate first environmental information of the terminal. For example, in a method where the access network device configures the terminal to report environmental information using first configuration information, the terminal reports the environmental information to the access network device according to the configuration of the access network device. For example, the terminal sends the first message to the access network device based on the first configuration information. For example, based on the configuration of the access network device, when a reporting period is reached or a trigger condition is met, the terminal reports the first environmental information to the access network device.

[0114] It is understandable that the first environmental information can be determined based on the environment in which the terminal is located in real time. For example, when the reporting period is reached or the trigger condition is met, the terminal can detect the environment in which the terminal is located in real time; based on the environment in which the terminal is located, the first environmental information is generated. Alternatively, the first environmental information can be the environmental information of the terminal over a period of time. For example, the access network device can also configure the terminal to report environmental information for a period of time, for example, by configuring the terminal through the first configuration information. Specifically, it may include: the start time of a period of time, the duration of a period of time, etc. Based on the configuration, the terminal continuously detects the environment over a period of time and generates environmental information (i.e., the first environmental information) over a period of time. When the reporting period is reached or the trigger condition is met, the environmental information over a period of time is reported.

[0115] Optionally, the first environmental information may be environmental information based on a specific cell or beam. For example, the access network device may configure the terminal to report environmental information for at least one cell or at least one beam. For example, this may be configured using first configuration information. For example, the first environmental information reported by the terminal may be represented as: Cell 1 - Identifier A corresponding to Environmental Information 1.

[0116] For example, in a scheme in which the terminal reports the first environmental information to the access network device according to the configuration of the access network device, in addition to reporting the type and content of the environmental information configured by the access network device to the access network device, the terminal also reports other environmental information to the access network device. For example, the access network device and the terminal pre-exchange the types and content of a type of environmental information. The access network device instructs the terminal to report the above-mentioned type of environmental information. The above-mentioned type of environmental information does not include configurations such as the terminal's moving speed and the channel environment in which the terminal is located. In addition to reporting the types and content of the above-mentioned type of environmental information, the access network device also additionally reports that the terminal's moving speed is high speed, the channel environment in which the terminal is located is an indoor hotspot, etc. Optionally, the terminal believes that the environmental information such as "high speed and indoor hotspot" reported by it has an impact on the access network device configuring the AI ​​model for it.

[0117] Furthermore, if the terminal's method and / or capabilities for acquiring the AI ​​model are updated, the terminal reports the updated acquisition method and / or capabilities to the access network device. It is understood that information such as "the terminal's updated acquisition method and / or capabilities" is reported to the access network device via a first message, or the terminal creates a new message to report information such as "the terminal's updated acquisition method and / or capabilities" via the new message.

[0118] Step 530: The access network device determines the first AI model based on the first environment information.

[0119] The AI ​​model may be simply referred to as a model. In one possible implementation, the access network device may obtain a correspondence between environmental information and the AI ​​model. This correspondence may also be referred to as an association relationship, a mapping relationship, or the like. The access network device may query the correspondence between environmental information and AI models to determine the AI ​​model corresponding to the first environmental information. The AI ​​model corresponding to the first environmental information is referred to as the first AI model.

[0120] For example, the access network device may instruct the terminal to detect the AI ​​model corresponding to each piece of environmental information. The terminal reports the correspondence between the detected environmental information and the AI ​​model to the access network device. The access network device stores the correspondence between the environmental information and the AI ​​model. For example, when the terminal is in a certain environment, the environmental information corresponding to that environment is referred to as environmental information 1. AI models 1 through 3 perform the same function. In the current environment, the terminal collects inference data. This inference data is sequentially input into AI models 1 through 3. Based on the outputs of AI models 1 through 3, three results are obtained. The gaps or differences between these three results and the ideal target results are measured, and these gaps or differences are referred to as measurement results. The AI ​​model corresponding to the smallest measurement result is referred to as the AI ​​model corresponding to the current environmental information 1. In this case, one piece of environmental information corresponds to one AI model, and this AI model can be referred to as the optimal AI model corresponding to that environmental information. Alternatively, the AI ​​model whose measurement result is less than or equal to a threshold is referred to as the AI ​​model corresponding to the current environmental information 1. In this case, one piece of environmental information can correspond to multiple AI models.

[0121] It is understandable that, in the correspondence between environmental information and AI models, one piece of environmental information may correspond to one AI model or multiple AI models. The first environmental information reported by the terminal may correspond to one AI model or multiple AI models. The first AI model may include one or more AI models. In one possible implementation, the second indication information sent by the access network device to the terminal indicates an AI model list, where the AI ​​model list includes the first AI model. When the first AI model includes one AI model, the AI ​​model list includes one AI model. When the first AI model includes multiple AI models, the AI ​​model list includes multiple AI models.

[0122] In another possible implementation, when the access network device receives the first environment information reported by the terminal, the access network device determines the first environment of the terminal based on the first environment information. For example, the environment of the terminal can be classified as follows: high-speed outdoor and low-speed indoor. There is a correspondence between the terminal environment and the AI ​​model. For example, high-speed outdoor corresponds to AI model X, and low-speed indoor corresponds to AI model Y. The access network device determines the AI ​​model corresponding to the first environment based on the correspondence between the terminal environment and the AI ​​model, which is called the first AI model. For example, the access network device may instruct the terminal to detect the correspondence between different environments and AI models. For the process of the terminal detecting the correspondence between different environments and AI models, refer to the terminal detecting the correspondence between different environmental information and AI models. The terminal reports the correspondence between the detected different environments and AI models to the access network device, and the access network device stores the correspondence between different environments and AI models.

[0123] Optionally, when determining the first AI model, the access network device may consider the environmental information of the access network device in addition to the first environmental information reported by the terminal. In one possible implementation, the access network device may determine the first AI model based on the first environmental information and the environmental information of the access network device. For example, the access network device determines one or more AI models based on the first environmental information. Further, the access network device selects one or more AIs that match the environmental information of the access network device from the one or more AI models, and the one or more AI models are referred to as the first AI model. Similar to the principle on the terminal side, the access network device determines the correspondence between the environmental information of the access network device and the AI ​​model through detection. The environmental information of the access network device may be information that the access network device can obtain and that has an impact on the terminal model configuration, such as weighted information of the access network device's transmit beam, antenna downtilt angle, channel environment of the access network device (for example, whether the access network device is located indoors or outdoors), etc.

[0124] Step 540: The access network device sends a second message to the terminal, and the terminal receives the second message from the access network device.

[0125] The second message includes second indication information, which is used to indicate the first AI model or execute the function of the first AI model. For example, the first AI model is represented by an identifier or index, such as the second message including the identifier or index of the first AI model. When the first AI model includes a single AI model (for example, an AI model is included in an AI model list sent by the access network device to the terminal), the terminal may use the AI ​​model indicated by the access network device to perform model inference and implement the corresponding function. For example, when the terminal collects inference data and inputs the inference data into the AI ​​model, it determines the inference result based on the output of the AI ​​model. Alternatively, when the first AI model includes multiple AI models (for example, multiple AI models are included in an AI model list sent by the access network device to the terminal), the terminal may further select an AI model from the multiple AI models to perform model inference. For example, the terminal may select an AI model based on other information. For example, based on the performance requirements of the AI ​​model in the current environment, the terminal may select an AI model that meets the performance requirements from the multiple AI models. Alternatively, when the terminal obtains the multiple AI models from other devices, the terminal can select an AI model that occupies the smallest storage space, or the terminal can select an AI model with the fastest transmission rate, etc., without restriction.

[0126] Optionally, the second message also includes third indication information and / or fourth indication information, where the third indication information is used to indicate the conditions for enabling the first AI model. For example, the conditions for enabling the first AI model include time information for starting the first AI model, that is, enabling the first AI model within a certain time. The fourth indication information is used to indicate a method for obtaining the first AI model. It is understandable that in an embodiment of the present application, when the first AI model is stored internally in the terminal, the terminal directly uses the first AI model to perform model reasoning and implement the corresponding function. Alternatively, the terminal needs to obtain the first AI model from other nodes, for example, the terminal downloads the first AI model from other nodes. The other nodes may be access network devices, core network network elements, OAM, AI nodes that implement AI functions, such as over the top (OTT) servers, etc. In this case, the access network device instructs the terminal on how to obtain the first AI model through the fourth indication information. For example, the access network device may instruct the terminal to obtain the first AI model from the CP / UP of the access network device, or instruct the terminal to obtain the first AI model from the core network element through the CP / UP of the access network device, or instruct the terminal to obtain the first AI model from the OAM, or instruct the terminal to obtain the first AI model from the OTT service, or instruct the terminal to obtain the first AI model using a combination of the above methods, etc. Optionally, the access network device may also indicate to the terminal a deadline or completion time for obtaining the first AI model, for example, by indicating it in a second message. For example, the terminal may be instructed to obtain the first AI model from other nodes within the deadline; after the deadline, the terminal will no longer obtain the first AI model from other nodes. Alternatively, the terminal may be instructed to obtain the first AI model from other nodes within the completion time. Optionally, the access network device may also indicate to the terminal the reason for obtaining the first AI model, for example, by indicating it in a second message. The reason may be matching the first environment information, etc.

[0127] In one possible implementation, the access network device may set priorities for different model acquisition methods. For example, a terminal may have the highest priority for obtaining an AI model from the access network device, followed by obtaining an AI model from a core network element, and then obtaining an AI model from an OTT server. For example, when the access network device determines that it cannot transmit a first AI model to a terminal while meeting latency requirements, the access network device may use fourth indication information in the second message to instruct the terminal to obtain the first AI model from a node other than the access network device. For example, the access network device may instruct the terminal to obtain the first AI model from a core network element or OTT server with lower priority. Optionally, the access network device may indicate the reason for the terminal obtaining the first AI model from another node, for example, through a second message. This reason may be that the access network device cannot transmit the first AI model to the terminal while meeting latency requirements due to factors such as limited air interface resources and channel conditions on the access network device, and therefore the first AI model is obtained from another node. Furthermore, during the process of obtaining the first model from other nodes, that is, during the transmission of the first AI model, the terminal can send an indication to the access network device to indicate the transmission progress of the first AI model, and / or after the terminal completes obtaining the first AI model from other nodes, that is, after the transmission of the first AI model is completed, the terminal can send an indication to the access network device to indicate the end of transmission of the first AI model.

[0128] For example, the first environmental information corresponds to one or more AI models, and the one or more AI models include an AI model stored inside the terminal. If the access network device determines that the performance of the AI ​​model stored inside the terminal is poor (for example, the generalization performance is poor), the access network device may configure the terminal to obtain the AI ​​model from other nodes, and the first AI model indicated by the access network device to the terminal does not include the AI ​​model stored inside the terminal. Furthermore, in the scheme where the terminal obtains the first AI model from the access network device, the access network device may configure a high-priority quality of service (QoS) flow for the terminal, and the access network device uses the high-priority QoS flow to transmit the first AI model to the terminal.

[0129] Optionally, before step 510, the method further includes:

[0130] Step 500: The terminal performs pre-interaction with the access network device.

[0131] The pre-interaction process can be initiated by the terminal or the access network device, without limitation. Through the pre-interaction process, the terminal and the access network device can exchange the following information:

[0132] Each type of environmental information includes the type and content, the correspondence between environmental information and identification, the storage capacity of the terminal, the performance requirements of the AI ​​model for different environmental information of the terminal, or the ability of the terminal to obtain the AI ​​model.

[0133] For example, the types and contents of each type of environmental information, as well as the correspondence between the environmental information and the identifier, can be determined by the terminal. The terminal reports the determined information to the access network device. The access network device can agree or refuse. If the access network device agrees, the access network device stores the types and contents of each type of environmental information, as well as the correspondence between the environmental information and the identifier. Afterwards, the access network device can instruct the terminal to report a certain type of environmental information. The terminal reports the corresponding type of environmental information based on the above-mentioned pre-interaction. Alternatively, the types and contents of each type of environmental information, as well as the correspondence between the environmental information and the identifier, can be determined by the access network device, and the access network device configures the determined information to the terminal. Afterwards, the access network device can instruct the terminal to report a certain type of environmental information, and the terminal reports the corresponding type of environmental information based on the above-mentioned configuration.

[0134] The terminal reports information about its storage capacity, its performance requirements for AI models in different environments, and its ability to acquire AI models to the access network device. Taking the example of a terminal reporting its storage capacity, in one possible implementation, the terminal reports a storage capacity list to the access network device. This storage capacity list includes storage capacity information for one or more functionalities. It is understood that a function corresponds to at least one AI model, and all of these AI models can implement the function. The at least one AI model may be stored internally in the terminal, or a portion of the at least one AI model may be stored internally, while the remaining portion may need to be downloaded from other nodes, or all of the at least one AI model may need to be downloaded from other nodes. For a function, the storage capacity information reported by the terminal includes at least one of the following: the amount of storage space available for storing all AI models corresponding to the function, the number of AI models available for storing the function, the amount of storage space available for storing AI models corresponding to the function, the number of AI models available for storing the function, the amount of storage space available for future AI models allocated to the function, or the number of AI models available for future AI models allocated to the function.

[0135] It is understandable that in the scenario where the terminal reports the storage capacity of the terminal to the access network device, the access network device can consider the storage capacity of the terminal when determining the first AI model. For example, the first environment information reported by the terminal corresponds to multiple AI models, and the access network device can select some AI models from the multiple AI models based on the storage capacity of the terminal. For example, select an AI model whose storage space can meet the storage capacity requirements of the terminal.

[0136] In one possible implementation, taking a function as an example, the performance requirements of the terminal for the AI ​​model under different environmental information include: the performance requirements for the AI ​​model under different environmental information. For example, the performance requirements of the AI ​​model include: the applicable model, throughput, or other performance indicators under the corresponding environmental information. For example, when the AI ​​model is used for prediction, the above-mentioned other performance indicators include: the accuracy of the AI ​​model's prediction results, the ability to provide prediction results (for example, based on periodic provision of prediction results), or the degree of accuracy of the prediction results (for example, the minimum error of the prediction results, etc.). Optionally, the performance requirement information of the terminal for the AI ​​model can be simply referred to as the performance requirement information of the AI ​​model. The performance requirement information of the AI ​​model can be determined by the access network device and configured to the terminal by the access network device, or determined by the terminal itself and reported to the access network device, or can be determined by the access network device and the terminal after discussion. Therefore, the performance requirement information of the AI ​​model can also be called the performance requirement information of the access network device for the AI ​​model, or the performance requirement information of the terminal and the access network device for the AI ​​model, etc.

[0137] It is understood that in scenarios where a terminal reports AI model performance requirements to an access network device, the access network device may consider the terminal's AI model performance requirements under the first environment information reported by the terminal when determining the first AI model. For example, if the first environment information corresponds to multiple AI models, the terminal may select an AI model from the multiple AI models whose performance requirements meet the terminal's requirements.

[0138] In one possible implementation, the terminal's ability to obtain AI models primarily refers to the terminal's ability to obtain AI models from various nodes, such as access network devices, core network elements, OAM, or OTT servers. The ability to obtain AI models may include obtaining the AI ​​model's identifier (or index), obtaining the AI ​​model's size, obtaining the AI ​​model's rate, and the estimated time to obtain the AI ​​model.

[0139] It is understood that in scenarios where a terminal reports its AI model acquisition capabilities to an access network device, the access network device may consider the terminal's AI model acquisition capabilities when determining the first AI model. For example, the access network device may prioritize AI models with strong terminal acquisition capabilities and configure them for the terminal.

[0140] For example, the terminal reports to the access network device in one message or in multiple messages the type and content of the environmental information, the correspondence between the environmental information and the identifier, the storage capacity of the terminal, the performance requirements of the terminal for the AI ​​model in different environmental information, or the ability of the terminal to obtain the AI ​​model. Taking the terminal reporting the above information in one message as an example: the terminal sends a fourth message to the access network device, and the access network device receives the fourth message from the terminal, and the fourth message includes at least one of the following indication information: fifth indication information, sixth indication information, seventh indication information, eighth indication information, or ninth indication information;

[0141] Among them, the fifth indication information is used to indicate the type and content of environmental information reported by the terminal, the sixth indication information is used to indicate the correspondence between the environmental information and the identifier, the seventh indication information is used to indicate the storage capacity of the terminal, the eighth indication information is used to indicate the performance requirements of the terminal for the AI ​​model under different environmental information, and the ninth indication information is used to indicate the terminal's ability to obtain the AI ​​model.

[0142] For example, the terminal is located on an urban road and switches from high speed to low speed. The terminal reports environmental information related to the low-speed environment to the access network device. Based on the environmental information reported by the terminal, the access network device can determine the first AI model and instruct the terminal to obtain the first AI model from other nodes. When the terminal requests the first AI model from other nodes, it can indicate the reason for the request to the other nodes. For example, in the above example, the reason why the terminal requests the first AI model is: the terminal switches from high speed to low speed, and therefore needs an AI model adapted to low-speed scenarios.

[0143] With this design, the terminal reports its first environment information to the access network device. Based on the first environment information, the access network device determines a first AI model that matches the first environment information and indicates the first AI model to the terminal. The terminal then uses the first AI model that matches the current environment to perform model inference and implement the corresponding functions. This prevents degradation in terminal inference performance due to a mismatch between the environment and the AI ​​model, thereby improving the performance of AI-based UC.

[0144] An embodiment of the present application also provides a communication method and apparatus, which differs from the aforementioned method in that: a network device sends second environmental information that the network device can obtain to a terminal, and the terminal determines a second AI model that matches the terminal's environment based on the second environmental information, so that the terminal can use the AI ​​model that matches the current environment, perform model reasoning, implement corresponding functions, and improve the performance of AI-based UC.

[0145] Taking the network device as an access network device as an example, as shown in FIG6 , a process of a communication method is provided, including:

[0146] Step 610: The access network device sends a fifth message to the terminal, and the terminal receives the fifth message from the access network device.

[0147] For example, the fifth message includes tenth indication information, and the tenth indication information is used to indicate the second environmental information of the access network device. The second environmental information is any environmental information that can be obtained by the access network device and has an impact on the terminal AI model configuration. There is no restriction on the type and content of the environmental information included in the second environmental information. For example, one type of second environmental information includes: transmit beam weighting information of the access network device, antenna downtilt angle information of the access network device, and channel environment of the access network device (for example, whether the access network device is located indoors or outdoors, etc.).

[0148] In one possible implementation, the access network device and the terminal may discuss and determine one or more types of environmental information through pre-interaction or other means, and the types and / or contents of environmental information included in different types of environmental information are different. Furthermore, the access network device and the terminal may also determine the correspondence between different types of environmental information and identifiers through pre-interaction or other means. For example, the access network device selects one type of environmental information from the one or more types of environmental information determined. According to the type and content included in the environmental information of this type, the environment is detected and the second environmental information is generated. It is understandable that the fifth message also includes indication information of the type corresponding to the second environmental information. The access network device determines the identifier of the type corresponding to the second environmental information based on the stored correspondence between different types of environmental information and identifiers, and notifies the terminal of the identifier, for example, the identifier is carried in the fifth message to notify the terminal.

[0149] It is understood that the access network device can send the second environment information to the terminal periodically or based on event triggering. Specifically, the method by which the access network device reports the second environment information can be preset, determined by the access network device, or determined through pre-interaction between the access network device and the terminal. The second environment information reported by the access network device can be environment information that the access network device can obtain in real time. For example, when a period is reached or when conditions such as an event trigger are met, the access network device collects environment information in real time and generates the second environment information. Alternatively, the access network device can report environment information for a period of time, and the environment information for this period of time is referred to as the second environment information.

[0150] Optionally, the second environment information has a validity period. For example, the validity period may refer to the validity start time and validity duration of the second environment information, or the validity end time of the second environment information, or the second environment information remains valid until the terminal receives new environment information notified by the access network device. Furthermore, the access network device may notify the terminal of the validity period of the second environment information. For example, the fifth message may carry information indicating the validity period.

[0151] Step 620: The terminal determines a second AI model based on the second environment information.

[0152] In one possible implementation, the terminal can determine the correspondence between environmental information and AI models through detection. Unlike the process of Figure 5 above, the environmental information in Figure 6 refers to environmental information that can be obtained by the access network device and has an impact on the configuration of the terminal AI model. For example, the access network device performs detection in an environment and obtains the corresponding environmental information. The access network device sends the environmental information to the terminal. For multiple AI models that implement the same function, the terminal uses the environmental information as input and inputs it into the multiple AI models respectively; based on the outputs of the multiple AI models, multiple output results are obtained; the difference between the multiple output results and the ideal target results is measured respectively to obtain multiple measurement results. Based on the multiple measurement results, the correspondence between the environmental information and the AI ​​model is determined.

[0153] It can be understood that, in the correspondence between environmental information and AI models, one piece of environmental information may correspond to one AI model, or one piece of environmental information may correspond to multiple AI models. In one possible implementation, the terminal may determine the model corresponding to the second environmental information based on the correspondence between the environmental information and the AI ​​model, and the model is referred to as the second AI model. The second AI model includes one or more AI models. In another possible implementation, in addition to considering the influence of the factors of the second environmental information, the terminal also considers other factors to determine the second AI model. For example, the terminal also considers at least one of: the environmental information detected by the terminal, the model storage capacity of the terminal itself, the ability of the terminal to obtain the AI ​​model, or the performance requirements for the AI ​​model. The terminal determines the AI ​​model that meets the above conditions among the multiple AI models corresponding to the second environmental information, and the AI ​​model is referred to as the second AI model.

[0154] In one possible implementation, step 620 may be replaced by: the terminal determines the second AI model based on the detected third environmental information. For example, the terminal may detect the environment and generate the third environmental information. Based on the correspondence between the environmental information and the AI ​​model, the terminal determines the AI ​​model corresponding to the third environmental information. This AI model is referred to as the second AI model. Furthermore, when determining the second AI model, the terminal may also consider other factors, such as the terminal's own AI model storage capacity, the terminal's ability to obtain AI models, or the performance requirements for the AI ​​model. Alternatively, the terminal may obtain the correspondence between environments and AI models, for example, environment 1 (high-speed outdoor) corresponds to AI model X, and environment 2 (low-speed indoor) corresponds to AI model Y. The terminal may determine the terminal's environment based on the detected third environmental information and determine the second AI model based on the correspondence between the environment and the AI ​​model. It will be understood that the correspondence between the environment and the AI ​​model may be determined by the terminal, configured for the terminal by the access network device, or predefined. Optionally, in a possible implementation, the access network device may send indication information to the terminal, where the indication information is used to instruct the terminal to directly enable the corresponding AI model based on the detected environmental information.

[0155] After determining the second AI model, the terminal can directly use the second AI model for reasoning to implement the corresponding function. Alternatively, the terminal reports the second AI model to the access network device and performs the corresponding operation after receiving the instruction from the access network device. In this case, optionally, the process in Figure 6 also includes:

[0156] Step 630: The terminal sends a sixth message to the access network device, and the access network device receives the sixth message from the terminal.

[0157] The sixth message includes eleventh indication information, which is used to indicate the second AI model or to execute the function of the second AI model. In one possible implementation, the sixth message includes an AI model list, which includes one or more AI models. In this embodiment of the present application, the AI ​​models included in the AI ​​model list are referred to as second AI models.

[0158] For example, when the access network device receives the sixth message, it determines the second AI model based on the eleventh indication information included in the sixth message. When the access network device determines that the second AI model does not match the environmental information of the terminal, the access network device may send indication information to the terminal to instruct the terminal to switch the AI ​​model. Optionally, the access network device also indicates to the terminal the reason for switching the AI ​​model, for example, the reason is that the terminal's environment does not match the second AI model. Further, the access network device may also indicate to the terminal the reason for the mismatch, for example, the reason for the mismatch is: the second AI model requested by the terminal is applicable to an outdoor channel environment, and the access network device determines that the terminal is actually in an indoor channel environment. Furthermore, the access network device may also send to the terminal an AI model that the access network device believes is more suitable for the terminal (which may be called a third AI model), or the access network device may recommend a better AI model (which may be called a third AI model) to the terminal, but whether to use the AI ​​model to implement the corresponding function is ultimately decided by the terminal.

[0159] In one possible implementation, the terminal may determine a first condition for activating the second AI model and / or a first method for the terminal to obtain the second AI model. For example, the terminal may determine the first condition for activating the second AI model and / or the first method for the terminal to obtain the second AI model based on at least one of the second environment information indicated by the access network device, the environment information detected by the terminal, the performance requirements for the AI ​​model, the model storage capability of the terminal, or the AI ​​model acquisition capability of the terminal.

[0160] Optionally, the terminal may further report the first condition for enabling the second AI model and / or the first method for the terminal to obtain the second AI model to the access network device. For example, the terminal reports via a sixth message, wherein the sixth message further includes: twelfth indication information and / or thirteenth indication information, wherein the twelfth indication information is used to indicate the first condition for enabling the second AI model, and the thirteenth indication information is used to indicate the first method for the terminal to obtain the second AI model.

[0161] For example, when the access network device receives the sixth message, it obtains the twelfth indication information and / or the thirteenth indication information in the sixth message. The access network device determines the first condition for the terminal to start the second model and / or the first method for the terminal to obtain the second AI model based on the twelfth indication information and / or the thirteenth indication information. The access network device can determine whether the first condition for the terminal to start the second AI model and / or the first method for obtaining the second AI model are reasonable. If not, the access network device can recommend or suggest better startup conditions and / or methods for obtaining the second AI model (which may be referred to as second conditions and / or second methods, respectively) to the terminal.

[0162] Step 640: The access network device sends the seventh message to the terminal, and the terminal receives the seventh message from the access network device.

[0163] For example, the seventh message includes at least one of the following: fourteenth indication information, fifteenth indication information, or sixteenth indication information. The fourteenth indication information is used to indicate a third AI model or to execute the function of the third AI model. The third AI model implements the same function as the second AI model. The third AI model may include one or more AI models. For example, the fourteenth indication information is used to indicate an AI model list, which includes one or more AI models. The AI ​​models included in the AI ​​model list are referred to as the third AI model. It is understood that the third AI model is the AI ​​model recommended or suggested by the access network device to the terminal. Optionally, the terminal can decide whether to adopt the third AI model to implement the corresponding function. In other words, the terminal can accept or reject the model recommended by the access network device, etc., without limitation. In one possible implementation, if the terminal accepts the third AI model recommended by the access network device, if the third AI model includes multiple AI models, the terminal further selects one AI model from the multiple AI models to implement the corresponding function.

[0164] The fifteenth indication information is used to instruct the terminal on a second method for acquiring the second AI model. It is understood that the second method is a method for acquiring the second AI model recommended or suggested by the access network device to the terminal. Similarly, the terminal can accept or reject the method suggested by the access network device without limitation. The sixteenth indication information is used to instruct the terminal on a second condition for starting the second AI model. It is understood that the second condition is a condition for starting the second AI model recommended or suggested by the access network device to the terminal. Similarly, the terminal can accept or reject the condition established by the access network device.

[0165] For example, the terminal may obtain the second AI model by acquiring the second AI model from the access network device. The access network device may transmit the second AI model to the terminal using a corresponding transmission method. For example, the access network device may transmit the second AI model to the terminal based on air interface resources. Alternatively, when RRC air interface resources are limited but the terminal requests transmission of the second AI model via the CP, the second AI model may be transmitted to the terminal via the UP. In this case, the access network device may also indicate to the terminal that the reason for switching the transmission method is that RRC air interface resources are limited.

[0166] Optionally, before step 610, the method further includes:

[0167] Step 600: Preliminary interaction between the terminal and the access network device.

[0168] The pre-interaction process can be initiated by the terminal or the access network device, without limitation. For information on the specific interaction between the terminal and the access network device, please refer to the description of step 500. The difference is that the access network device can indicate to the terminal the capability information of the AI ​​model that the access network device can provide, for example: for a function, the identifier (or index) of the AI ​​model that the access network device can provide under different environmental information, the transmission mode supported by the access network device when transmitting the AI ​​model to the terminal (for example, the transmission rate supported by the access network device, the transmission duration and the size of the transmitted AI model, etc.)

[0169] In one possible implementation, the access network device sends an eighth message to the terminal, and the terminal receives the eighth message from the access network device. The eighth message includes at least one of the following: seventeenth indication information, eighteenth indication information, nineteenth indication information, or twentieth indication information, wherein the seventeenth indication information is used to indicate the identifier (or index) of the AI ​​model that the access network device can provide under different environmental information, the eighteenth indication information is used to indicate the transmission mode supported by the access network device when transmitting the AI ​​model to the terminal, the nineteenth indication information is used to indicate the type and content of the environmental information, and the twentieth indication information is used to indicate the mapping relationship between the environmental information and the identifier.

[0170] Through the above design, the access network device provides the terminal with the environmental information that the access network device can obtain. The terminal determines the second AI model that matches the terminal environment based on a comprehensive decision including the environmental information provided by the access network device and the environmental information it can obtain. This avoids the degradation of the terminal's reasoning performance due to the mismatch between the environment and the AI ​​model, and improves the performance of AI-based UC.

[0171] It is understood that in the description of the embodiments of the present application:

[0172] 1. In addition to focusing on describing the differences between different processes, the descriptions of different processes can refer to each other.

[0173] 2. In each process, the order of different steps is not limited. In addition, each process may include fewer steps or more steps than the flowchart or text description.

[0174] 3. The processes in Figures 5 and 6 are described using the terminal and access network device as examples. It is understood that in each process, the terminal's functions can be implemented by the terminal itself, or by a module (e.g., a chip or circuit) within the terminal. The functions of the access network device can be implemented by the access network device itself, or by a module (e.g., a chip or circuit) within the access network device, or by a logical node (e.g., CU, DU, etc.), logical module, or software that fully or partially implements the functions of the access network device.

[0175] 4. In the embodiments of the present application, "(e.g., a terminal) receives information from (e.g., an access network device)" can be understood to mean that the source of the information is the access network device and the destination is the terminal, which may include the terminal directly or indirectly receiving information from the access network device. The information may undergo necessary processing between the source and destination, such as format changes, but the destination can still understand the valid information from the source. Similar expressions in this application should be understood similarly and will not be repeated here.

[0176] In the embodiments provided above, the methods provided in the embodiments of the present application are described from the perspectives of a terminal and an access network device, respectively. In order to implement the various functions in the methods provided in the embodiments of the present application, the terminal or access network device, etc., may include a hardware structure and / or a software module, and implement the above functions in the form of a hardware structure, a software module, or a hardware structure plus a software module. Whether a particular function of the above functions is executed in the form of a hardware structure, a software module, or a hardware structure plus a software module depends on the design constraints of the specific application of the technical solution.

[0177] Figures 7 and 8 are schematic diagrams of the structures of possible communication devices provided in embodiments of the present application. These communication devices can implement one or more corresponding functions in the above-mentioned method embodiments. For example, the functions implemented by a terminal or a network device, etc., may therefore achieve the beneficial effects possessed by the above-mentioned method embodiments. In an embodiment of the present application, the communication device may be a terminal or a network device, the network device may be an access network device, or a core network element, or an OAM, or other AI node, etc., or the communication device may be a module (such as a chip) applied to a terminal or a network device.

[0178] As shown in Figure 7, a communication device 700 includes a processing unit 710 and a transceiver unit 720. The communication device 700 is used to implement the functions of the terminal or access network device in the method embodiment of Figure 5 or Figure 6.

[0179] Optionally, the transceiver unit 720 may also be referred to as an output unit, an interface unit, or a communication unit. In one possible implementation, the transceiver unit 720 includes at least one of a transmitting unit and a receiving unit. The transmitting unit and the receiving unit may be integrated together or may be two independent units.

[0180] When the communication device 700 is used to implement the functions of the terminal in Figure 5, specifically: the processing unit 710 is used to generate a first message; the transceiver unit 720 is used to send a first message to the network device, the first message includes first indication information, and the first indication information is used to indicate the first environmental information of the terminal; the transceiver unit 720 is also used to receive a second message from the network device, the second message includes second indication information, and the second indication information is used to indicate the first artificial intelligence AI model corresponding to the first environmental information.

[0181] In one possible design, when the transceiver unit 720 sends a first message to a network device, it is specifically used to: receive a third message from the network device, the third message including first configuration information, the first configuration information being used to configure the terminal to report environmental information to the network device; and send the first message to the network device according to the first configuration information.

[0182] In one possible design, the second message also includes third indication information and / or fourth indication information, the third indication information is used to indicate the conditions for enabling the first AI model, and the fourth indication information is used to indicate the method for obtaining the first AI model.

[0183] In one possible design, before sending the first message to the network device, the transceiver unit 720 is further used to: send a fourth message to the network device, the fourth message including at least one of the following: fifth indication information, sixth indication information, seventh indication information, eighth indication information or ninth indication information, the fifth indication information is used to indicate the type and content of the environmental information reported by the terminal, the sixth indication information is used to indicate the correspondence between the environmental information and the identifier, the seventh indication information is used to indicate the storage capacity of the terminal, the eighth indication information is used to indicate the performance requirements of the terminal for the AI ​​model under different environmental information, and the ninth indication information is used to indicate the ability of the terminal to obtain the AI ​​model.

[0184] When the communication device 700 is used to implement the function of the access network device in Figure 5, specifically: the transceiver unit 720 is used to receive a first message from the terminal, the first message includes first indication information, and the first indication information is used to indicate the first environmental information of the terminal; the processing unit 710 is used to determine the first artificial intelligence AI model based on the first environmental information; the transceiver unit 720 is also used to send a second message to the terminal, the second message includes second indication information, and the second indication information is used to indicate the first AI model.

[0185] In one possible design, the transceiver unit 720 is further used to send a third message to the terminal, where the third message includes first configuration information, and the first configuration information is used to configure the terminal to report environmental information to the network device.

[0186] In one possible design, the second message also includes third indication information and / or fourth indication information, the third indication information is used to indicate the conditions for enabling the first AI model, and the fourth indication information is used to indicate the method for obtaining the first AI model.

[0187] In one possible design, before receiving the first message from the terminal, the transceiver unit 720 is further used to receive a fourth message from the terminal, where the fourth message includes at least one of the following: fifth indication information, sixth indication information, seventh indication information, eighth indication information or ninth indication information, where the fifth indication information is used to indicate the type and content of the environmental information reported by the terminal, the sixth indication information is used to indicate the correspondence between the environmental information and the identifier, the seventh indication information is used to indicate the storage capacity of the terminal, the eighth indication information is used to indicate the performance requirements of the terminal for the AI ​​model under different environmental information, and the ninth indication information is used to indicate the ability of the terminal to obtain the AI ​​model.

[0188] When the communication device 700 is used to implement the function of the terminal in Figure 6, specifically: the transceiver unit 720 is used to receive a fifth message from the network device, the fifth message includes tenth indication information, and the tenth indication information is used to indicate the second environmental information of the network device; the processing unit 710 is used to determine the second artificial intelligence AI model based on the second environmental information.

[0189] In one possible design, after determining the second AI model, the transceiver unit 720 is further used to send a sixth message to the network device, where the sixth message includes eleventh indication information, and the eleventh indication information is used to indicate the second AI model.

[0190] In a possible design, the sixth message also includes: twelfth indication information and / or thirteenth indication information, the twelfth indication information is used to indicate the first condition for the terminal to start the second AI model, and the thirteenth indication information is used to indicate the first method for the terminal to obtain the second AI model.

[0191] In one possible design, the transceiver unit 720 is further used to receive a seventh message from the network device, where the seventh message includes at least one of the following: fourteenth indication information, fifteenth indication information, or sixteenth indication information, where the fourteenth indication information is used to indicate a third AI model, and the third AI model implements the same function as the second AI model. The fifteenth indication information is used to indicate a second method for the terminal to obtain the second AI model, and the sixteenth indication information is used to indicate a second condition for the terminal to start the second AI model.

[0192] In one possible design, the transceiver unit 720 is further used to receive an eighth message from the network device, where the eighth message includes at least one of the following: seventeenth indication information, eighteenth indication information, nineteenth indication information, or twentieth indication information, where the seventeenth indication information is used to indicate the identifier of the AI ​​model that the network device can provide under different environmental information, the eighteenth indication information is used to indicate the transmission method supported when the network device transmits the AI ​​model to the terminal, the nineteenth indication information is used to indicate the type and content of the environmental information, and the twentieth indication information is used to indicate the mapping relationship between the environmental information and the identifier.

[0193] When the communication device 700 is used to implement the function of the access network device in Figure 6: the processing unit 710 is used to obtain the second environmental information of the network device; the transceiver unit 720 is used to send a fifth message to the terminal, and the fifth message includes tenth indication information, and the tenth indication information is used to indicate the second environmental information.

[0194] In one possible design, the transceiver unit 720 is further used to receive a sixth message from the terminal, where the sixth message includes eleventh indication information, and the eleventh indication information is used to indicate a second artificial intelligence AI model, where the second AI model is determined based on the second environmental information.

[0195] In a possible design, the sixth message also includes: twelfth indication information, and / or thirteenth indication information, the twelfth indication information is used to indicate the first condition for the terminal to start the second AI model, and the thirteenth indication information is used to indicate the first method for the terminal to obtain the second AI model.

[0196] In one possible design, the transceiver unit 720 is further used to send a seventh message to the terminal, where the seventh message includes at least one of the following: fourteenth indication information, fifteenth indication information, or sixteenth indication information, where the fourteenth indication information is used to indicate a third AI model, and the third AI model implements the same function as the second AI model. The fifteenth indication information is used to indicate a second method for the terminal to obtain the second AI model, and the sixteenth indication information is used to indicate a second condition for the terminal to start the second AI model.

[0197] In one possible design, the transceiver unit 720 is further used to send an eighth message to the terminal, and the eighth message includes at least one of the following: seventeenth indication information, eighteenth indication information, nineteenth indication information, or twentieth indication information, the seventeenth indication information is used to indicate the identifier of the AI ​​model that the network device can provide under different environmental information, the eighteenth indication information is used to indicate the transmission method supported when the network device transmits the AI ​​model to the terminal, the nineteenth indication information is used to indicate the type and content included in the environmental information, and the twentieth indication information is used to indicate the mapping relationship between the environmental information and the identifier.

[0198] For a more detailed description of the processing unit 710 and the transceiver unit 720, reference may be made to the description in FIG. 5 or FIG. 6 in the above method embodiment, which will not be repeated here.

[0199] In one possible implementation, when the access network device adopts the O-RAN architecture, the processing unit 710 may be located on the O-CU entity, and the transceiver unit 720 may be located on the O-DU or O-RU entity. Optionally, when the O-CU entity includes an O-CU-CP entity, the processing unit 710 may be located on the O-CU-CP entity. Alternatively, the processing unit 710 is located on the O-DU entity, and the transceiver unit 720 is located on the O-RU entity. Alternatively, both the processing unit 710 and the transceiver unit 720 are located on the O-DU entity or the O-RU entity, etc., without limitation.

[0200] It is understood that the division of units in the embodiments of the present application is schematic and is only a logical functional division. In actual implementation, there may be other division methods. In addition, the various functional units in the embodiments of the present application can be integrated into a physical device (for example, a processor), or each functional unit can be a separate physical device, or two or more units can be integrated into a unit for implementation. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional modules.

[0201] As shown in Figure 8, communication device 800 includes a processor 810 and an interface circuit 820. Processor 810 and interface circuit 820 are coupled to each other. It will be appreciated that interface circuit 820 may be a transceiver or an input / output interface. Optionally, communication device 800 may further include a memory 830 for storing instructions executed by processor 810, input data required by processor 810 to execute instructions, or data generated after processor 810 executes instructions.

[0202] When the communication device 800 is used to implement the method shown in FIG. 5 or FIG. 6 , the processor 810 is used to implement the functions of the processing unit 710 , and the interface circuit 820 is used to implement the functions of the transceiver unit 720 .

[0203] When the communication device is a chip used in a terminal, the chip implements the terminal functions described in the method embodiments. The chip receives information sent by the access network device to the terminal through other modules in the terminal (such as a radio frequency module or antenna); alternatively, the chip sends information to other modules in the terminal (such as a radio frequency module or antenna), and the information is sent by the terminal to the access network device.

[0204] When the above-mentioned communication device is a module applied to an access network device, the module implements the functions of the access network device in the above-mentioned method embodiments. The module receives information from other modules in the access network device (such as a radio frequency module or antenna), and the information is sent by the terminal to the access network device; or the module sends information to other modules in the access network device (such as a radio frequency module or antenna), and the information is sent by the access network device to the terminal.

[0205] It is understood that the processor in the embodiments of the present application may be a central processing unit (CPU), or may be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field programmable gate arrays (FPGA), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. The general-purpose processor may be a microprocessor or any conventional processor.

[0206] The memory in the embodiments of the present application can be a random access memory (RAM), a flash memory, a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a register, a hard disk, a mobile hard disk, a CD-ROM, or any other form of storage medium known in the art.

[0207] The method steps in the embodiments of the present application can be implemented in hardware or in software instructions that can be executed by a processor. The software instructions can be composed of corresponding software modules, and the software modules can be stored in random access memory, flash memory, read-only memory, programmable read-only memory, erasable programmable read-only memory, electrically erasable programmable read-only memory, registers, hard disk, mobile hard disk, CD-ROM or any other form of storage medium well known in the art. An exemplary storage medium is coupled to the processor so that the processor can read information from the storage medium and write information to the storage medium. The storage medium can also be an integral part of the processor. The processor and the storage medium can be located in an ASIC.

[0208] An embodiment of the present application also provides a communication device, which includes a processor and a memory, the processor and the memory are coupled, and the processor is used to implement the functions of the access network device or terminal in Figure 5 or Figure 6.

[0209] An embodiment of the present application also provides a communication device, including a processor, which is used to implement the functions of the access network device or terminal in Figure 5 or Figure 6.

[0210] The present application also provides a computer-readable storage medium storing instructions, which may also be referred to as a computer program, computer program code, etc. The instructions are executed on a computer, causing the computer to perform the functions of the access network device or terminal in FIG. 5 or FIG. 6 in the above method embodiment.

[0211] An embodiment of the present application further provides a computer program product, including a computer program or instructions. When the computer program or instructions are executed on a computer, the method of the access network device or terminal in FIG. 5 or FIG. 6 is implemented.

[0212] An embodiment of the present application also provides a chip, which includes a processor coupled to a memory, and the processor is used to execute computer programs or instructions stored in the memory, so that the functions of the access network device or terminal in Figure 5 or Figure 6 are implemented.

[0213] The present application also provides a communication system including a first communication device and a second communication device. The first communication device and the second communication device can be used to implement the functions of the access network device and the terminal in Figure 5, or the first communication device and the second communication device can be used to implement the functions of the access network device and the terminal in Figure 6, respectively.

[0214] In the above embodiments, all or part of the embodiments may be implemented using software, hardware, firmware, or any combination thereof. When implemented using software, all or part of the embodiments may be implemented in the form of a computer program product. The computer program product includes one or more computer programs or instructions. When the computer program or instructions are loaded and executed on a computer, the processes or functions described in the embodiments of the present application are performed in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, a network device, a user device, or other programmable device. The computer program or instructions may be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another. For example, the computer program or instructions may be transferred from one website, computer, server, or data center to another website, computer, server, or data center via wired or wireless means. The computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server or data center that integrates one or more available media. The available medium may be a magnetic medium, such as a floppy disk, hard disk, or magnetic tape; an optical medium, such as a digital video disk; or a semiconductor medium, such as a solid-state drive. The computer-readable storage medium may be a volatile or nonvolatile storage medium, or may include both volatile and nonvolatile types of storage media.

[0215] In the various embodiments of the present application, unless otherwise specified or there is a logical conflict, the terms and / or descriptions between different embodiments are consistent and can be referenced by each other. The technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationships.

Claims

1. A communication method, characterized in that: include: Sending a first message to a network device, where the first message includes first indication information, where the first indication information is used to indicate first environment information of a terminal; Receive a second message from the network device, where the second message includes second indication information, and the second indication information is used to indicate a first artificial intelligence (AI) model corresponding to the first environmental information or to execute a function of the first AI model.

2. The method according to claim 1, characterized in that The sending a first message to the network device includes: receiving a third message from the network device, the third message including first configuration information, the first configuration information being used to configure the terminal to report environmental information to the network device; According to the first configuration information, the first message is sent to the network device.

3. The method according to claim 1 or 2, characterized in that The second message also includes third indication information and / or fourth indication information, the third indication information is used to indicate a condition for enabling the first AI model, and the fourth indication information is used to indicate a method for obtaining the first AI model.

4. The method according to any one of claims 1 to 3, characterized in that Before sending the first message to the network device, the method further includes: A fourth message is sent to the network device, wherein the fourth message includes at least one of the following: fifth indication information, sixth indication information, seventh indication information, eighth indication information or ninth indication information, wherein the fifth indication information is used to indicate the type and content of environmental information reported by the terminal, the sixth indication information is used to indicate the correspondence between the environmental information and the identifier, the seventh indication information is used to indicate the storage capacity of the terminal, the eighth indication information is used to indicate the performance requirements of the terminal for the AI ​​model under different environmental information, and the ninth indication information is used to indicate the ability of the terminal to obtain the AI ​​model.

5. A communication method, characterized in that: include: receiving a first message from a terminal, where the first message includes first indication information, and the first indication information is used to indicate first environment information of the terminal; Determine a first artificial intelligence AI model according to the first environment information; Send a second message to the terminal, where the second message includes second indication information, and the second indication information is used to indicate the first AI model or execute a function of the first AI model.

6. The method according to claim 5, characterized in that Also includes: A third message is sent to the terminal, where the third message includes first configuration information, where the first configuration information is used to configure the terminal to report environmental information to a network device.

7. The method according to claim 5 or 6, characterized in that The second message also includes third indication information and / or fourth indication information, the third indication information is used to indicate a condition for enabling the first AI model, and the fourth indication information is used to indicate a method for obtaining the first AI model.

8. The method according to any one of claims 5 to 7, characterized in that Before receiving the first message from the terminal, the method further includes: Receive a fourth message from the terminal, the fourth message including at least one of the following: fifth indication information, sixth indication information, seventh indication information, eighth indication information or ninth indication information, the fifth indication information is used to indicate the type and content of environmental information reported by the terminal, the sixth indication information is used to indicate the correspondence between the environmental information and the identifier, the seventh indication information is used to indicate the storage capacity of the terminal, the eighth indication information is used to indicate the performance requirements of the terminal for the AI ​​model under different environmental information, and the ninth indication information is used to indicate the ability of the terminal to obtain the AI ​​model.

9. A communication method, characterized in that: include: receiving a fifth message from a network device, the fifth message including tenth indication information, the tenth indication information being used to indicate second environment information of the network device; Determine a second artificial intelligence AI model based on the second environmental information.

10. The method according to claim 9, characterized in that After determining the second AI model, the method further includes: Send a sixth message to the network device, where the sixth message includes eleventh indication information, where the eleventh indication information is used to indicate the second AI model or execute a function of the second AI model.

11. The method according to claim 10, characterized in that The sixth message also includes: twelfth indication information and / or thirteenth indication information, the twelfth indication information is used to indicate the first condition for the terminal to start the second AI model, and the thirteenth indication information is used to indicate the first method for the terminal to obtain the second AI model.

12. The method according to claim 10 or 11, characterized in that Also includes: Receive a seventh message from the network device, the seventh message including at least one of the following: fourteenth indication information, fifteenth indication information, or sixteenth indication information, the fourteenth indication information is used to indicate a third AI model or execute a function of the third AI model, the third AI model and the second AI model implement the same function, the fifteenth indication information is used to indicate a second way for the terminal to obtain the second AI model, and the sixteenth indication information is used to indicate a second condition for the terminal to start the second AI model.

13. The method according to any one of claims 9 to 12, characterized in that Also includes: Receive an eighth message from the network device, the eighth message including at least one of the following: seventeenth indication information, eighteenth indication information, nineteenth indication information or twentieth indication information, the seventeenth indication information is used to indicate the identifier of the AI ​​model that the network device can provide under different environmental information, the eighteenth indication information is used to indicate the transmission mode supported by the network device when transmitting the AI ​​model to the terminal, the nineteenth indication information is used to indicate the type and content included in the environmental information, and the twentieth indication information is used to indicate the mapping relationship between the environmental information and the identifier.

14. A communication method, characterized in that: include: Acquire second environment information of the network device; A fifth message is sent to the terminal, where the fifth message includes tenth indication information, and the tenth indication information is used to indicate the second environment information.

15. The method according to claim 14, characterized in that Also includes: A sixth message is received from the terminal, where the sixth message includes eleventh indication information, where the eleventh indication information is used to indicate a second artificial intelligence (AI) model or to execute a function of a second AI model, where the second AI model is determined according to the second environment information.

16. The method according to claim 15, characterized in that The sixth message also includes: twelfth indication information, and / or thirteenth indication information, the twelfth indication information is used to indicate a first condition for the terminal to start the second AI model, and the thirteenth indication information is used to indicate a first method for the terminal to obtain the second AI model.

17. The method according to claim 15 or 16, characterized in that Also includes: Sending a seventh message to the terminal, the seventh message including at least one of the following: fourteenth indication information, fifteenth indication information, or sixteenth indication information, the fourteenth indication information is used to indicate a third AI model or execute a function of a third AI model, the third AI model and the second AI model implement the same function, the fifteenth indication information is used to indicate a second way for the terminal to obtain the second AI model, and the sixteenth indication information is used to indicate a second condition for the terminal to start the second AI model.

18. The method according to any one of claims 14 to 17, characterized in that Also includes: An eighth message is sent to the terminal, wherein the eighth message includes at least one of the following: seventeenth indication information, eighteenth indication information, nineteenth indication information, or twentieth indication information, wherein the seventeenth indication information is used to indicate the identifier of the AI ​​model that the network device can provide under different environmental information, the eighteenth indication information is used to indicate the transmission mode supported when the network device transmits the AI ​​model to the terminal, the nineteenth indication information is used to indicate the type and content included in the environmental information, and the twentieth indication information is used to indicate the mapping relationship between the environmental information and the identifier.

19. A communication device, characterized in that: The method comprises a unit for implementing the method according to any one of claims 1 to 4, or a unit for implementing the method according to any one of claims 9 to 13.

20. A communication device, characterized in that: The method comprises a processor and a memory, wherein the processor and the memory are coupled, and the processor is used to implement the method according to any one of claims 1 to 4, or the method according to any one of claims 9 to 13.

21. A communication device, characterized in that: The invention comprises a processor and an interface circuit, wherein the interface circuit is used to receive a signal from another device outside the device and transmit it to the processor or send a signal from the processor to another device outside the device, and the processor is used to implement the method according to any one of claims 1 to 4 or the method according to any one of claims 9 to 13 through a logic circuit or executing code instructions.

22. A communication device, characterized in that: The method comprises a unit for implementing the method according to any one of claims 5 to 8 or a unit for implementing the method according to any one of claims 14 to 18.

23. A communication device, characterized in that: The method comprises a processor and a memory, wherein the processor and the memory are coupled, and the processor is used to implement the method according to any one of claims 5 to 8, or the method according to any one of claims 14 to 18.

24. A device, characterized in that: The invention comprises a processor and an interface circuit, wherein the interface circuit is used to receive a signal from another device outside the device and transmit it to the processor or send a signal from the processor to another device outside the device, and the processor is used to implement the method as claimed in any one of claims 5 to 8 or the method as claimed in any one of claims 14 to 18 through a logic circuit or executing code instructions.

25. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions, which are executed on a computer so that the computer executes the method according to any one of claims 1 to 4, or the method according to any one of claims 5 to 8, or the method according to any one of claims 9 to 13, or the method according to any one of claims 14 to 18.

26. A computer program product, characterized in that The method comprises a computer program or an instruction, which, when executed by the device, causes the method according to any one of claims 1 to 4 to be executed, or the method according to any one of claims 5 to 8 to be executed, or the method according to any one of claims 9 to 13 to be executed, or the method according to any one of claims 14 to 18 to be executed.

27. A chip, characterized in that: The invention comprises a processor coupled to a memory and configured to execute a computer program or instruction stored in the memory, so that the chip implements the method as claimed in any one of claims 1 to 4, or implements the method as claimed in any one of claims 5 to 8, or the method as claimed in any one of claims 9 to 13, or the method as claimed in any one of claims 14 to 18.

28. A communication system, characterized in that: include: The first communication device is used to perform the method according to any one of claims 1 to 4; The second communication device is used to perform the method according to any one of claims 5 to 8; or, The first communication device is used to execute the method according to any one of claims 9 to 13; the second communication device is used to execute the method according to any one of claims 14 to 18.

Images