Model matching method and apparatus

Abstract

A model matching method and an apparatus. The method comprises: a second apparatus sends first information to a first apparatus, and the first apparatus sends information of a first model to the second apparatus on the basis of the first information. The first information comprises one or more of: identification information of a manufacturer to which the second apparatus belongs, model version information, or a first configuration parameter. The first model can be used for communication between the first apparatus and the second apparatus. The content comprised in the first information can be used for the first apparatus and the second apparatus to perform model matching, thereby improving the accuracy of model matching.

Description

A model matching method and apparatus

[0001] Cross-references to related applications

[0002] This application claims priority to Chinese Patent Application No. 202410981371.6, filed on July 19, 2024, entitled "A Model Matching Method and Apparatus", the entire contents of which are incorporated herein by reference. Technical Field

[0003] This application relates to the field of communication technology, and in particular to a model matching method and apparatus. Background Technology

[0004] With the improvement of data storage and computing power, artificial intelligence (AI) technology has been increasingly used. For example, AI can be applied to channel estimation in wireless air interface wireless networks.

[0005] To achieve a certain function, multiple AI models may need to collaborate. If these AI models are deployed on different communication devices, then the models deployed on different communication devices need to be matched so that they can jointly execute a specific task and complete the function. How to match AI models deployed on different communication devices is a problem that urgently needs to be solved. Summary of the Invention

[0006] This application provides a model matching method and apparatus for enabling AI models deployed in different communication devices to match.

[0007] To achieve the above objectives, the embodiments of this application adopt the following technical solutions:

[0008] Firstly, a model matching method is provided, which can be applied to a first device. The first device can be a terminal device or a circuit or chip / chip system (e.g., a modem chip, also known as a baseband chip, or a system-on-chip (SoC) chip containing a modem core, or a system-in-package (SIP) chip) or other functional module within the terminal device; or, the first device can be a logical node, logical module, or software that performs all or part of the terminal's functions. Alternatively, the first device can be a network device or a component within the network device (e.g., a circuit, chip, or chip system); or, the first device is a module or unit used to perform some or all of the functions of the network device, such as a central unit (CU), a distributed unit (DU), or a radio unit (RU).

[0009] The method includes: a first device receiving first information from a second device and sending information about a first model to the second device. The first information includes one or more of the following: identification information of the manufacturer to which the second device belongs, model version information, or first configuration parameters. The first model can be used for communication between the first and second devices.

[0010] In this scheme, the first information can be used to indicate relevant information about the models available to the second device, such as the manufacturer of the second device, the model version, and the applicable configuration parameters (e.g., the first configuration parameters). The first device can determine the first model based on the first information and notify the second device of the information of the first model. In this way, the second device can determine a model that matches the first model (e.g., referred to as the second model) based on the information of the first model. For example, the first model and the second model have the same model version, the same manufacturer, and the same configuration parameters. This scheme improves the accuracy of model matching by performing model matching based on more information (e.g., model version, configuration parameters, and the manufacturer of the device deploying the model).

[0011] In one implementation, when the first information includes the identification information of the manufacturer of the second device, the information of the first model includes model version information and a second configuration parameter, wherein the second configuration parameter is a configuration parameter applicable to the first model. Alternatively, when the first information includes the identification information of the manufacturer of the second device and the first configuration parameter, the information of the first model includes model version information.

[0012] The information from the first model allows the second device to select a second model that matches the first model. In this scheme, the first device does not need to send information already known to the second device, saving signaling overhead. For example, if the first information includes the identification information of the second device's manufacturer, the information from the first model may include model version information and second configuration parameters, but not the identification information of the second device's manufacturer. In this case, the second device will default to the scenario corresponding to the first model being the manufacturer to which the second device belongs.

[0013] In one implementation, the method further includes: a first device receiving second information from a third device, the third device being the manufacturer to which the first device belongs, the second information including association information for at least one model. The at least one model includes a first model, and the association information for the first model includes model version information of the first model, identification information of the manufacturer to which the first device belongs, and configuration parameters applicable to the first model.

[0014] Through this scheme, the first device can obtain at least one usable model from the third device. Optionally, the at least one model can be stored in the first device, and the associated information of the at least one model can also be stored in the first device.

[0015] In one implementation, the model version information of the first model also includes: the launch time of the first model.

[0016] The launch time of the first model can be understood as its deployment / usage time or effective time. When the first device and the second device use the model, the launch time of the model shall prevail. By setting an launch time for the model, the model can be deployed simultaneously on different devices. In this way, there is no need to pay attention to the model version, thus eliminating the need to maintain model version information and reducing the number of models that need to be maintained.

[0017] In one implementation, when the first information includes the identification information of the manufacturer to which the second device belongs, the information of the first model includes the configuration parameters applicable to the first model.

[0018] When the model version information of the first model includes the online time of the first model, the information of the first model fed back by the first device does not need to include the model version information of the first model, which can save signaling overhead.

[0019] Secondly, a model matching method is provided, which can be applied to a second device. The second device can be a terminal device or a circuit or chip / chip system (e.g., a modem chip, also known as a baseband chip, or a SoC chip or SIP chip containing a modem core) or other functional module within the terminal device; or, the first device can be a logical node, logical module, or software that performs all or part of the terminal functions. Alternatively, the first device can be a network device or a component within the network device (e.g., a circuit, chip, or chip system); or, the first device is a module or unit used to perform some or all of the functions of the network device, such as a CU, DU, or RU. The second device and the first device are relative; if the first device is a terminal-side device, then the second device is a network-side device; if the first device is a network-side device, then the second device is a terminal-side device.

[0020] The method includes: a second device sending first information to a first device and receiving information about a first model from the first device. The first information includes one or more of the following: identification information of the manufacturer to which the second device belongs, model version information, or first configuration parameters.

[0021] The first model is used for communication between the second device and the first device.

[0022] In one implementation, when the first information includes the identification information of the manufacturer to which the second device belongs, the information of the first model includes model version information and a second configuration parameter, wherein the second configuration parameter is a configuration parameter applicable to the first model. Alternatively, when the first information includes the identification information of the manufacturer to which the second device belongs and the first configuration parameter, the information of the first model includes model version information.

[0023] In one implementation, the method further includes: a second device receiving third information from a fourth device, the fourth device being the manufacturer to which the second device belongs, the third information including association information for at least one model. The at least one model includes a second model, and the association information for the second model includes model version information of the second model, identification information of the manufacturer to which the second device belongs, and configuration parameters applicable to the second model.

[0024] In one implementation, the model version information of the second model also includes: the launch time of the second model.

[0025] In one implementation, when the first information includes the identification information of the manufacturer to which the second device belongs, the information of the first model includes the configuration parameters applicable to the first model.

[0026] For the beneficial effects of the second aspect and its various implementation methods, please refer to the aforementioned beneficial effects of the second aspect and its various implementation methods; they will not be repeated here.

[0027] Thirdly, a model matching method is provided, which can be applied to a third device. This third device can be from the same vendor as the first device. For example, if the first device is a network-side device, the third device can be collectively referred to as an element management system (EMS). If the first device is a terminal-side device, the third device can be collectively referred to as an over-the-top (OTT) server, generally referring to a vendor's server.

[0028] The method includes: a third device sending a first request message to a fifth device, receiving a first response message from the fifth device, and sending association information of a first model to the first device. The first request message requests the registration of a first model pair, which includes a first model and a second model. The first model is used by the first device, and the second model is used by the second device. The first model pair is trained by the third device, which is the manufacturer to which the first device belongs. The first request message includes registration information for both the first and second models. The registration information for the first model includes model version information, a first identifier of the third device, and applicable configuration parameters for the first model. The registration information for the second model includes model version information, a first identifier of a fourth device, and applicable configuration parameters for the second model. The fourth device is the manufacturer to which the second device belongs. The first response message includes the second identifier of the third device. The association information for the first model includes model version information, the second identifier of the third device, and applicable configuration parameters for the first model.

[0029] In this scheme, the third device, as the manufacturer of the first device, can register the trained model with the fifth device, so that the manufacturer of the second device, namely the fourth device, can obtain the model available to the second device, so as to match it with the model available to the first device in the future.

[0030] In one implementation, the model version information of the first model further includes: the launch time of the first model; and / or, the model version information of the second model further includes: the launch time of the second model.

[0031] Fourthly, a model matching method is provided, which can be applied to a fourth device. This fourth device can be from the same manufacturer as the second device. For example, if the second device is a network-side device, the fourth device can be an EMS (Electronic Services Provider). If the second device is a terminal-side device, the fourth device can be an OTT (Over-The-Top) server. The fourth device and the third device are relative; if the third device is an EMS, then the fourth device is an OTT server; if the third device is an OTT server, then the fourth device is an EMS.

[0032] The method includes: a fourth device sending a second request message to a fifth device, receiving a second response message from the fifth device, and sending third information to the second device. The fifth device manages the models trained by the third device, and the third device is the manufacturer to which the first device belongs. The second request message includes first configuration parameters and first identification information of the fourth device, which is the manufacturer to which the second device belongs. The second response message includes association information for at least one model. The third information includes association information for at least one model, and the at least one model includes a second model. The association information for the second model includes model version information of the second model, second identification information of the fourth device, and configuration parameters applicable to the second model.

[0033] In this scheme, the fourth device, acting as the manufacturer of the second device, can obtain a model usable by the second device from the fifth device and provide the obtained model to the second device. Subsequently, the second device selects a model from this model that matches the model used by the first device.

[0034] In one implementation, the model version information of the second model also includes: the launch time of the second model.

[0035] Fifthly, a model matching method is provided, which can be applied to a fifth device. This fifth device can be used for model registration, management, etc. For example, the fifth device can be a model registry center, which can be collectively referred to as a network management system (NMS) or a cross-domain management system.

[0036] The method includes: a fifth device receiving a first request message from a third device and sending a first response message to the third device. The first request message requests the registration of a first model pair, which includes a first model and a second model. The first model is used by the first device, and the second model is used by the second device. The first model pair is obtained through training by the third device, which is the manufacturer to which the first device belongs. The first request message includes registration information for both the first and second models. The registration information for the first model includes model version information, a first identifier of the third device, and applicable configuration parameters for the first model. The registration information for the second model includes model version information, a first identifier of the fourth device, and applicable configuration parameters for the second model. The first response message includes a second identifier of the third device.

[0037] In one implementation, the first response message also includes the launch time of the first model.

[0038] In one implementation, the method further includes: a fifth device receiving a second request message from a fourth device and sending a second response message to the fourth device. The second request message includes first configuration parameters and first identification information of the fourth device, wherein the fourth device is the manufacturer to which the second device belongs. The second response message includes association information of at least one model, wherein the at least one model includes a second model. The association information of the second model includes model version information of the second model, second identification information of the fourth device, and configuration parameters applicable to the second model, wherein the configuration parameters applicable to the second model include the first configuration parameters.

[0039] In one implementation, the second response message also includes the launch time of the second model.

[0040] The beneficial effects of the fifth aspect and its various implementation methods can be found in the first to fourth aspects and their various implementation methods mentioned above, and will not be repeated here.

[0041] Sixthly, embodiments of this application provide a communication device that has the functionality to implement the behavior in any of the method examples of the first to fifth aspects described above. The beneficial effects can be found in the relevant descriptions of the first to fifth aspects and will not be repeated here. For example, the communication device may be the first device in the first aspect, or it may be a device capable of supporting a terminal device or network device to implement the functions required by the method provided in the first aspect. For example, the communication device may be a chip or chip system in the terminal device or network device. As another example, the communication device may be the second device in the second aspect, or it may be a device capable of supporting a terminal device or network device to implement the functions required by the method provided in the second aspect. For example, the communication device may be a chip or chip system in the terminal device or network device. As yet another example, the communication device may be the aforementioned third, fourth, or fifth device; or it may be a device capable of supporting a network element / device / server to implement the functions required by the method provided in any of the third to fifth aspects.

[0042] In one possible design, the communication device is a terminal device or a network device, which may include a baseband device and a radio frequency device.

[0043] In one possible design, the communication device includes corresponding means, modules, or units for performing the methods of the first or second aspect. These modules, units, or means can be implemented in software, hardware, or a combination of both. For example, the communication device includes a processing unit (sometimes also called a processing module or processor) and / or a transceiver unit (sometimes also called a transceiver module or transceiver). The transceiver unit is capable of both sending and receiving functions. When the transceiver unit performs the sending function, it can be called a sending unit (sometimes also called a sending module), and when it performs the receiving function, it can be called a receiving unit (sometimes also called a receiving module). The sending unit and the receiving unit can be the same functional unit, referred to as the transceiver unit, which performs both sending and receiving functions; or, the sending unit and the receiving unit can be different functional units, with "transceiver unit" being a general term for these functional units. These units (modules) can perform the corresponding functions in the method examples of the first or second aspect described above, as detailed in the method examples, and will not be repeated here.

[0044] In a seventh aspect, embodiments of this application provide a communication device including a processor configured to execute methods from any of the first to fifth aspects and any implementation thereof. Optionally, the communication device further includes a communication interface. Optionally, the communication device also includes a memory for storing computer programs (also referred to as code or instructions), data, etc. The processor is coupled to the memory and the communication interface. When the processor reads the computer program, data, etc., from the memory, it causes the communication device to execute methods from any of the first to fifth aspects and any implementation thereof.

[0045] Eighthly, embodiments of this application provide a communication device including an input / output interface and logic circuitry. The input / output interface is used for inputting and / or outputting information. The input / output interface may be an interface circuit, an output circuit, an input circuit, a pin, or related circuitry, etc. The logic circuitry is used to execute the methods described in any of the first to fifth aspects.

[0046] In one implementation of the eighth aspect, when the communication device is a terminal device, the interface circuit can be a radio frequency processing chip in the terminal device, and the processing circuit can be a baseband processing chip in the terminal device. When the communication device is a network device, the interface circuit can be a radio frequency processing chip in the network device, and the processing circuit can be a baseband processing chip in the network device.

[0047] In one implementation of the eighth aspect, when the communication device is a chip or chip system, the input circuit can be an input pin, the output circuit can be an output pin, and the logic circuit can be a transistor, gate circuit, flip-flop, or various other logic circuits. The input signal received by the input circuit can be received and input by, for example, but not limited to, a receiver; the signal output by the output circuit can be, for example, but not limited to, output to a transmitter and transmitted by the transmitter. Furthermore, the input circuit and the output circuit can be the same circuit, which is used as both the input circuit and the output circuit at different times. This application does not limit the specific implementation of the input / output interface and the logic circuit.

[0048] Ninthly, embodiments of this application provide a communication system, which includes a terminal device and a network device. The terminal device is used to implement the function of the method described in the first aspect, and the network device is used to implement the function of the method described in the second aspect. Alternatively, the network device is used to implement the function of the method described in the first aspect, and the terminal device is used to implement the function of the method described in the second aspect.

[0049] Optionally, the communication system further includes a manufacturer's server for terminal equipment, a manufacturer's server for network equipment, and a network management system. The manufacturer's server for terminal equipment is used to implement the functions described in the third aspect, the manufacturer's server for network equipment is used to implement the functions described in the fourth aspect, and the network management system is used to implement the functions described in the fifth aspect. Alternatively, the manufacturer's server for network equipment is used to implement the functions described in the third aspect, the manufacturer's server for terminal equipment is used to implement the functions described in the fourth aspect, and the network management system is used to implement the functions described in the fifth aspect.

[0050] In a tenth aspect, embodiments of this application provide a computer-readable storage medium for storing a computer program or instructions that, when executed, cause the methods described in any of the first to fifth aspects and any implementation thereof to be implemented.

[0051] In the eleventh aspect, embodiments of this application also provide a computer program product containing instructions that, when run on a computer, cause the methods described in any of the first to fifth aspects and any of their implementations to be implemented.

[0052] The beneficial effects of the sixth to eleventh aspects and their implementation methods can be referenced to the beneficial effects of any aspect of the first to fifth aspects and any implementation method thereof. Attached Figure Description

[0053] Figure 1 is a schematic diagram of the double-ended model;

[0054] Figure 2 shows the network architecture diagram for dual-end model registration and download;

[0055] Figure 3 is a schematic diagram of the communication system applicable to the embodiments of this application;

[0056] Figure 4 is a flowchart illustrating the model matching method 400 provided in an embodiment of this application;

[0057] Figure 5 is a flowchart illustrating the model matching method 500 provided in an embodiment of this application;

[0058] Figure 6 is a flowchart illustrating the model matching method 600 provided in an embodiment of this application;

[0059] Figure 7 is a flowchart illustrating the model matching method 700 provided in an embodiment of this application;

[0060] Figure 8 is a flowchart illustrating the model matching method 800 provided in an embodiment of this application;

[0061] Figure 9 is a schematic diagram of a communication device provided in an embodiment of this application;

[0062] Figure 10 is a schematic diagram of another structure of the communication device provided in an embodiment of this application. Detailed Implementation

[0063] To facilitate understanding of the technical solutions provided in the embodiments of this application, the relevant technical terms involved in the embodiments of this application will be explained below. It should be noted that these explanations are intended to make the embodiments of this application easier to understand and should not be regarded as a limitation on the scope of protection claimed by this application.

[0064] (1) Network equipment

[0065] In this embodiment, network equipment refers to (radio)access network ((R)AN) equipment / RAN node. In this embodiment, (R)AN and RAN are interchangeable. RAN can be a cellular system related to the 3rd generation partnership project (3GPP), such as a 5th generation (5G) mobile communication system / new radio (NR) mobile communication system, or a future-oriented evolution system. RAN can also be an open RAN (O-RAN or ORAN), a cloud radio access network (CRAN), a virtualized RAN (vRAN), a non-terrestrial network (NTN), etc. RAN can also be a communication system that integrates two or more of the above systems. RAN equipment can also be called a RAN node, RAN entity, or access node, etc.

[0066] In one possible scenario, a RAN node can be a base station, an evolved NodeB (eNodeB), an access point (AP), a transmission reception point (TRP), a next-generation NodeB (gNB), or a base station in a future mobile communication system. RAN nodes can also be macro base stations, micro base stations, indoor stations, relay nodes, donor / host nodes, or radio controllers. RAN nodes can also be servers, wearable devices, vehicles, or in-vehicle equipment. For example, in vehicle-to-everything (V2X) technology, the RAN node can be a roadside unit (RSU).

[0067] In another possible scenario, the RAN node can be a module or unit that performs some of the functions of the base station; or multiple RAN nodes can cooperate to assist terminal equipment in achieving wireless access, with different RAN nodes performing some of the functions of the base station. For example, the RAN node can be a CU, DU, or RU. The function of the CU can be implemented by a single entity or by different entities. For example, the function of the CU can be further divided, that is, the control plane and the user plane can be separated and implemented by different entities, namely the control plane CU entity (i.e., CU-control plane (CP) entity) and the user plane CU entity (i.e., CU-user plane (UP) entity). The CU-CP entity and the CU-UP entity can be coupled with the DU to jointly complete the function of the RAN node. The CU and DU can be set up separately or included in the same network element, such as in the baseband unit (BBU). Any of the units among the CU (or CU-CP, CU-UP), DU, and RU in this application can be implemented by software modules, hardware modules, or a combination of software modules and hardware modules.

[0068] In different systems, CU (or CU-CP and CU-UP), DU, or RU may have different names, but those skilled in the art will understand their meaning. For example, in an ORAN system, CU can also be called O-CU (open CU), DU can also be called O-DU, CU-CP can also be called O-CU-CP, CU-UP can also be called O-CU-UP, and RU can also be called O-RU. For ease of description, this application uses CU, CU-CP, CU-UP, DU, and RU as examples.

[0069] The CU and DU can be configured according to the protocol layer functions of the wireless network they implement: for example, the CU can be configured to implement the functions of the Packet Data Convergence Protocol (PDCP) layer and above (such as the Radio Resource Control (RRC) layer and / or the Service Data Adaptation Protocol (SDAP) layer); the DU can be configured to implement the functions of the protocol layers below the PDCP layer (such as the Radio Link Control (RLC) layer, the Media Access Control (MAC) layer, and / or the Physical (PHY) layer). For specific descriptions of the above protocol layers, please refer to the relevant 3GPP technical specifications or the technical specifications of other applicable communication protocols.

[0070] The above division of the processing functions of CU and DU according to protocol layers is merely an example; other division methods are also possible, and this application does not limit this. For example, in one design, CU or DU can be further divided into processing functions with protocol layers. In one design, some functions of the RLC layer and the functions of the protocol layer above the RLC layer are located in the CU, while the remaining functions of the RLC layer and the functions of the protocol layer below the RLC layer are located in the DU.

[0071] In another possible design, the DU and RU collaborate to implement the PHY layer functionality, or, more specifically, a portion of the PHY layer functionality of the DU can be moved to the RU. A DU can be connected to one or more RUs. The functions of the DU and RU can be configured in various ways depending on the design. For example, the DU may be configured to implement baseband functions, and the RU may be configured to implement mid-RF functions. Alternatively, the DU may be configured to implement higher-level functions in the PHY layer, and the RU may be configured to implement lower-level functions in the PHY layer, or both lower-level and RF functions. Higher-level functions in the physical layer may include a portion of the physical layer's functionality closer to the MAC layer, and lower-level functions may include another portion of the physical layer's functionality closer to the mid-RF side. This application does not limit the specific functions of the DU and RU. The interface between the DU and RU can be called a fronthaul interface. In one design, the CU may not have a PDCP layer; for example, the CU may only include an RRC layer. The CU-CP may not have PDCP-C. The CU-UP may not have PDCP-U, or may not have a CU-UP. In one design, the DU may not have an RLC layer; for example, the DU may only have a MAC and a higher PHY layer.

[0072] When the RAN is O-RAN, it can also have AI capabilities. For example, O-RAN includes an intelligent controller. The intelligent controller can be a non-real-time RAN intelligent controller (RIC / non-RT RIC / NRT RIC) or a near-real-time RAN intelligent controller (RIC / near-RT RIC / nRT RIC). A non-real-time RIC can be used to implement non-real-time intelligent management of RAN functions, enabling workflows including model training and model updates, and guiding applications / functions in the nRT RIC based on policies. A near-real-time RIC can be used to implement near-real-time intelligent management of the RAN. Through data collection and related operations on the E2 interface, near-real-time control and optimization of O-RAN modules and resources are achieved.

[0073] (2) Terminal equipment

[0074] In this application embodiment, anything capable of data communication with a base station can be considered a terminal device. Terminal devices are also called terminals, terminal equipment, user equipment (UE), mobile stations, or mobile terminals, etc. Terminal devices can be widely used in various scenarios. For example, terminal devices can be: mobile phones, computers, mobile internet devices (MID), wearable devices, virtual reality (VR) devices, augmented reality (AR) devices, stations (STA), robotic arms, cameras, robots, vehicles, drones, helicopters, airplanes, ships, or smart home devices (such as televisions, air conditioners, robot vacuums, speakers, set-top boxes), relays, customer premises equipment (CPE), etc.

[0075] Furthermore, in this embodiment, the terminal device can also be a terminal device in an Internet of Things (IoT) system, such as a water meter or electricity meter. IoT is an important component of future information technology development, and its main technical characteristic is connecting objects to networks through communication technology, thereby realizing an intelligent network that enables human-machine interconnection and object-to-object interconnection.

[0076] When the terminal device is applied to V2X, it can also be called a V2X device, such as a smart car or intelligent car, a roadside unit (RSU), etc. The various terminal devices described above, if located on a vehicle (e.g., placed / installed inside the vehicle), can all be considered in-vehicle terminal devices. In-vehicle terminal devices can be built into a vehicle's on-board module, on-board unit, on-board component, on-board chip, or on-board unit as one or more components or units. The vehicle can implement the methods of this application through the built-in on-board module, on-board unit, on-board component, on-board chip, or on-board unit. In-vehicle terminal devices can be vehicle equipment, on-board modules, vehicles, on-board units (OBU), RSUs, in-vehicle infotainment systems (or on-board transmitting units) (telematics boxes, T-boxes), chips, or SOCs, etc., and the aforementioned chips or SOCs can be installed in the vehicle, OBU, RSU, or T-box.

[0077] Taking a network device as a base station and a terminal device as a UE as an example, the base station and UE can be fixed or mobile. The base station and UE can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; they can also be deployed on water; and they can also be deployed on airplanes, balloons, and artificial satellites. The embodiments of this application do not limit the application scenarios of the base station and UE.

[0078] (3) AI Model

[0079] AI models, also known as AI algorithms (or AI operators), are algorithms or computer programs that can implement AI functions. An AI model can be understood as a function model that maps an input of a certain dimension to an output of a certain dimension. The parameters of the function model can be obtained through machine learning training. For example, f(x) = ax² + b is a quadratic function model, which can be viewed as an AI model, where a and b are the parameters of this AI model, obtained through machine learning training. The implementation of an AI model can be hardware circuitry, software, or a combination of both; there are no restrictions. Non-restrictive examples of software include: program code, program, subroutine, instruction, instruction set, code, code segment, software module, application program, or software application, etc.

[0080] In this application embodiment, the AI ​​model is simply referred to as a model. The type of model is not limited in this application embodiment. For example, 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 (ML) models, etc. In this application embodiment, the AI ​​model can be used to achieve one or more of the following functions: data collection (collecting training data and / or inference data), data preprocessing, model training (or model learning), model information publishing (configuring model information), model validation, model inference, or publishing inference results. Inference can also be referred to as prediction.

[0081] (4) Two-ended model

[0082] A two-sided model, also known as a two-sided model, collaborative model, or dual model, refers to a model composed of at least two AI models combined in this embodiment. These at least two AI models can be deployed on at least two nodes, and the multiple AI models constituting the two-sided model are mutually matched. Taking two AI models as an example, AI model #1 and AI model #2, their mutual matching means that AI model #1 can understand the output of AI model #2 and can further decode the output of AI model #2 to obtain the desired output.

[0083] As a typical example, an autoencoder (AE) with the encoder and decoder deployed on different nodes is a two-end model. The encoder and decoder of the AE are matched, meaning that the decoder can understand the encoder's output and decode the encoder's output into the desired output.

[0084] For example, please refer to Figure 1, which is a schematic diagram of a two-end model. As shown in Figure 1, AI model #1 is deployed in the encoder, and AI model #2 is deployed in the decoder. For AI model #1 deployed in the encoder, the input of AI model #1 is V, and the output of AI model #1 is Z. For AI model #2 deployed in the decoder, the input of AI model #2 is Z, and the output of AI model #2 is V', where V' is the same as V, or V' can accurately reflect V.

[0085] Typically, the AI ​​models in a dual-end model are trained simultaneously, meaning they are matched to each other. Taking AI model #1 and AI model #2 as examples, AI model #1 and AI model #2 can be trained on the same node and deployed on two separate nodes, or they can be trained in a distributed manner on two separate nodes.

[0086] (5) AI module

[0087] An AI module is a module with machine learning computing capabilities used to acquire (or generate) AI models. In a wireless communication system, an AI module can be a standalone network element entity or deployed within a specific network element. For example, an AI module can be deployed on network devices, terminal devices, or both. Of course, an AI module can also be deployed on other possible network elements; for example, it can be deployed within Operations Administration and Maintenance (OAM). The main function of an AI module in a wireless communication system is to perform a series of AI calculations, such as model building, training approximation, and reinforcement learning, based on input data (in a wireless communication system, input data generally refers to network operation data provided by the RAN side or monitored by OAM, such as network load and channel quality).

[0088] (6) In the embodiments of this application, "transmission" includes "sending" and / or "receiving". "Sending" and "receiving" indicate the direction of signal transmission. For example, "sending information to XX" can be understood as the destination of the information being XX, which may include direct transmission via the air interface or indirect transmission by other units or modules via the air interface. "Receiving information from YY" can be understood as the source of the information being YY, which may include direct reception from YY via the air interface or indirect reception from YY by other units or modules via the air interface. "Sending" can also be understood as the "output" of the chip interface, and "receiving" can also be understood as the "input" of the chip interface. In other words, sending and receiving can occur between devices, such as between access network devices and terminal devices, or within a device, such as between components, modules, chips, software modules, or hardware modules within the device via a bus, wiring, or interface.

[0089] In this application embodiment, the number of nouns, unless otherwise specified, refers to "singular nouns or plural nouns," that is, "one or more." "At least one" means one or more, and "more than one" means two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can mean: A exists alone, A and B exist simultaneously, or B exists alone, where A / B can be singular or plural. The character " / " generally indicates that the related objects before and after are in an "or" relationship. For example, A / B means: A or B. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, and / or c means the following combinations: a exists alone, b exists alone, c exists alone, a and b exist simultaneously, a and c exist simultaneously, b and c exist simultaneously, or a, b, and c exist simultaneously, where a, b, and c can be single or multiple.

[0090] In the embodiments of this application, "when," "if," and "if" all refer to the device taking corresponding actions under certain objective circumstances, and are not time-limited, nor do they require the device to perform a judgment action, nor do they imply any other limitations. Unless otherwise specified, "if" and "if" can be substituted, and "when" and "in the case of" can be substituted. "When" and "if" / "if" can be substituted.

[0091] In the embodiments of this application, the terms "exemplary" or "for example" are used to indicate that something is an example, illustration, or description. Any embodiment or design that is described as "exemplary" or "for example" in this application should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of the terms "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0092] In this application, the ordinal numbers such as "first" and "second" are used to distinguish multiple objects, and are not used to limit the size, content, order, timing, priority, or importance of the multiple objects. For example, "first device" and "second device" refer to two different devices, and do not indicate a difference in priority or importance between the two devices.

[0093] In the embodiments of this application, the solutions in each embodiment can be used in a reasonable combination, and the explanations or descriptions of various terms, similar operations, or steps appearing in the embodiments can be referenced or explained to each other in the embodiments, without limitation.

[0094] Current research proposes applying AI to channel estimation. For example, an AI model can be deployed on the terminal side to compress / encode the collected channel state information (CSI) feedback signal and send the obtained information to the network device. Correspondingly, an AI model is deployed on the network side to decode the information received from the terminal device to recover the CSI feedback signal. Based on the recovered CSI feedback signal, the channel quality is determined, and subsequent beamforming operations are then performed.

[0095] It should be understood that the AI ​​model deployed on the terminal side and the AI ​​model deployed on the network side constitute a dual-end model. This dual-end model, applicable to both terminal and network devices, can be trained by either the terminal device manufacturer or the network device manufacturer. A manufacturer can be considered a vendor server; the manufacturer of the terminal device can be replaced with its vendor server, and the manufacturer of the network device can be replaced with its vendor server. Different terminal devices may belong to the same or different manufacturers; similarly, different network devices may belong to the same or different manufacturers. Therefore, there will be terminal device models from multiple manufacturers, and also network device models from multiple manufacturers. If the manufacturer of the model selected by the terminal device and the manufacturer of the model selected by the network device are different, then the models selected by the terminal device and the network device are mismatched. In this embodiment, the manufacturer of the model is the manufacturer of the device deploying that model.

[0096] To address this, terminal devices and network devices can select models based on vendor, ensuring a match between the chosen models. For example, different vendors can register their trained dual-end models with a central authority, allowing terminal devices or network devices to download matching models from that authority based on their vendor.

[0097] For example, please refer to Figure 2, which shows the network architecture for dual-end model registration and download. Figure 2 illustrates an example where the dual-end model is trained by the vendor of the network device and registered with the registry center.

[0098] Terminal devices can download models from multiple network device vendors from the registry center. After establishing a connection with a network device, the terminal device selects the model corresponding to that vendor (e.g., AI model #1) from the downloaded models, based on the vendor of the network device. The network device then uses AI model #2, and AI model #1 and AI model #2 are jointly used to complete channel estimation. It is understandable that if both end models are trained by the vendor of the terminal device, that vendor will register the trained model with the registry center. Network devices can download models from multiple terminal device vendors from the registry center. After establishing a connection with a terminal device, the network device selects the model corresponding to that vendor (e.g., AI model #1) from the downloaded models, based on the vendor of the terminal device. The network device then uses AI model #2, and AI model #1 and AI model #2 are jointly used to complete channel estimation.

[0099] However, the configuration parameters of the devices deploying the model differ, and the model applicable to that device may also differ. Taking a terminal device as an example, if the terminal device has 4 antennas, model A is applicable; if the terminal device has 8 antennas, model B is applicable. Thus, adapting the dual-end model solely based on the device manufacturer may result in model mismatch, leading to performance loss in channel estimation.

[0100] Therefore, the solution provided in this application embodiment is as follows. In this application embodiment, in addition to the manufacturer to which the device deploying / using the model belongs, other information can also be used to match the dual-end models, thereby improving the matching degree of models deployed in different communication devices. Other information includes, for example, the configuration parameters applicable to the model, the model version, etc.

[0101] The vendor of the equipment that deploys / uses the model can also be referred to as the vendor of the model; unless otherwise specified, the two have the same meaning.

[0102] The configuration parameters applicable to a model can be understood as the configuration parameters used by the device deploying that model. For example, the configuration parameters applicable to the first model can be the configuration parameters of the first device deploying the first model. Taking a terminal device as an example, the configuration parameters applicable to the first model may include one or more of the following: number of antennas, spectrum bandwidth, reference signal configuration, CSI feedback overhead, or subcarrier spacing, etc. There are no restrictions on the specific names of the configuration parameters; for example, configuration parameters are also called communication parameters.

[0103] Model version refers to the version of the model. Under the same configuration parameters, the obtained models may differ depending on performance. Since different models are obtained under the same configuration parameters, it can be considered that there are multiple versions of the model under the same configuration parameters. This application does not limit the specific implementation of the model version. For example, the model version can be an identifier arranged according to the training time of the model, such as V1.0, V1.1, etc. Alternatively, the model version can also be an identifier arranged according to the performance level of the model, such as V1.0.x, V1.0.y, etc., where x and y represent the performance level.

[0104] The solutions provided in the embodiments of this application will be described in detail below with reference to the accompanying drawings.

[0105] The technical solutions provided in the embodiments of this application can be applied to various communication systems, such as Long Term Evolution (LTE) communication systems, 5G / NR communication systems, or future mobile communication systems, or other similar communication systems. Other similar communication systems may include Wireless Fidelity (WIFI), V2X, Internet of Things (IoT) systems, and so on.

[0106] Please refer to Figure 3, which illustrates a communication system applicable to an embodiment of this application. The communication system includes at least one network device and at least one terminal device. Optionally, the communication system may further include a vendor server for the terminal device, a vendor server for the network device, and a model registry center; Figure 3 uses this as an example. AI can be introduced into the network. The AI ​​module can be deployed on the network device, on the terminal device, or both the network device and the terminal device can have AI modules deployed. Alternatively, the vendor server for the network device or the vendor server for the terminal device can deploy the AI ​​module.

[0107] The network architecture shown in Figure 3 is merely illustrative; the number of terminal devices, network devices, terminal device vendor servers, and network device vendor servers may be fewer or more. The communication system described in this application's embodiments is for the purpose of more clearly illustrating the technical solutions of this application's embodiments and does not constitute a limitation on the communication systems to which this application's embodiments are applicable. For example, the communication system may also include other devices, such as wireless relay devices and wireless backhaul devices, which are not shown in Figure 3. Those skilled in the art will understand that, with the evolution of network architectures, the technical solutions provided in this application's embodiments are equally applicable to similar technical problems. When applying the technical solutions of this application's embodiments to other communication systems, the devices, components, and modules in the embodiments can be replaced with corresponding devices, components, and modules in other communication systems without limitation.

[0108] In the following description, the model matching method provided in the embodiments of this application is used as an example, executed by a first device and a second device. Optionally, the model matching method also involves interaction with a third device, a fourth device, and a fifth device. Each of the first to fifth devices is described below.

[0109] The first and second devices are those that need to match models or deploy dual-end models. The third device is the vendor of the first device, the fourth device is the vendor of the second device, and the fifth device is the model registry. The first and second devices are relative, and correspondingly, the third and fourth devices are also relative. For example, the first device can be a network device, the second device can be a terminal device, the third device can be collectively referred to as an element management system (EMS), and the fourth device can be collectively referred to as (over-the-top, OTT), generally referring to the vendor's server; the first device is a terminal device, the second device is a network device, the third device is an OTT, and the fourth device is an EMS. EMS can be used to manage one or more network elements of a certain category. EMS can also be called a domain management system or a single-domain management system.

[0110] It should be understood that the dual-end (i.e., the first and second devices) model can be trained by either the third or fourth device. After obtaining the model, the third or fourth device can register it with the fifth device. The fifth device can be used to manage the models trained by the third device or the models trained by the fourth device. The fifth device can be collectively referred to as a network management system (NMS) or a cross-domain management system, and can be used to be responsible for the operation, management, and maintenance of the network.

[0111] Understandably, in the RAN domain, the EMS can manage network devices. Data / information / models within the network can be transmitted to the OTT via the NMS or Service Management and Orchestration (SMO) functions, allowing the OTT to interact with terminal devices. In the ORAN domain, the SMO can manage various heterogeneous network elements, such as network devices. The SMO's role in the network architecture is similar to that of the NMS, responsible for the operation, management, and maintenance of various network services and orchestration functions. The network elements directly managed by the SMO can be heterogeneous; for example, the SMO can directly manage network devices and core network elements.

[0112] In the embodiments of this application, the steps executed by the first device can be implemented by the first device itself, or by a logic node, logic module, or software that performs some or all of the functions of the first device, or by a component (e.g., a circuit or chip / chip system) in the first device, or by a device that includes the first device. Similarly, the steps executed by the second device can be implemented by the second device itself, or by a logic node, logic module, or software that performs some or all of the functions of the second device, or by a component (e.g., a circuit or chip / chip system) in the second device, or by a device that includes the second device. For example, if the first device is a network device, the steps executed by the first device can be implemented by the network device itself, or by a CU or DU that performs some of the functions of the network device, or by a control subsystem that includes network device functions. The control subsystem that includes network device functions can be a control center in the aforementioned application scenarios such as smart grids, industrial control, intelligent transportation, and smart cities. For example, the first device is a terminal device. The steps performed by the first device can be implemented by the terminal device itself, or by circuits or chip / chip system (e.g., modem chip / baseband chip, or SoC chip or SIP chip containing a modem core) or other functional modules within the terminal device. Similarly, the steps performed by the third / fourth / fifth device can be implemented by the third / fourth / fifth device itself, or by logic nodes, logic modules, or software that perform some or all of the functions of the third / fourth / fifth device, or by components (e.g., circuits or chip / chip system) within the third / fourth / fifth device.

[0113] The model matching method provided in this application will be described in detail below with specific embodiments. The methods mentioned in this embodiment can perform all or some of the steps and do not constitute a limitation.

[0114] Please refer to Figure 4, which is a flowchart illustrating the model matching method 400 provided in this embodiment. The flowchart shown in Figure 4 takes the training of the dual-end model by the manufacturer of the first device (i.e., the third device) as an example. As shown in Figure 4, the flowchart of the model matching method 400 provided in this embodiment includes the following steps.

[0115] S401, the third device sends a first request message to the fifth device, the first request message being used to request the registration of the first model pair.

[0116] The first model pair refers to a two-sided AI model, also known as a two-sided model, which includes multiple models that collaborate to complete a certain function. The first model pair can also be called the first pair of models or the first set of models. It should be understood that the multiple models included in the first model pair are matched with each other. For ease of description, this article uses the example of a first model pair including a first model and a second model. Here, the first model is used in a first device, the second model is used in a second device, and the first and second models are matched.

[0117] The first model pair, comprising the first model and the second model, can be trained by a third device. The third device can register the trained first model pair with a fifth device. For example, the third device can send a first request message to the fifth device, and correspondingly, the fifth device receives the first request message from the third device, which requests the registration of the first model pair. The embodiments of this application do not limit the name of the first request message. For example, the first request message can be called a model registration request message. The fifth device receives the first request message and registers the first model pair according to the content carried in the first request message.

[0118] To improve the accuracy of model matching, embodiments of this application can register multiple pieces of model-related information (e.g., model version information, applicable configuration parameters, etc.) with the fifth device. Thus, during model matching, the first and second devices can refer to more information related to the model to ensure a higher degree of matching. For example, during model matching, the first and second devices can refer to the model's manufacturer, model version, applicable configuration parameters, and the identifier / virtual identifier assigned to the model by the network. Compared to matching only based on the model's manufacturer, this results in a higher degree of model matching.

[0119] For example, the third device can inform the fifth device of model-related information. For instance, the first request message includes registration information for the first model and registration information for the second model. The registration information for the first model may include configuration parameters applicable to the first model, first identification information of the vendor to which the first device belongs (i.e., the third device), and model version information for the first model. The configuration parameters applicable to the first model may be scheduling / operating parameters of the first device. For example, if the first device is a UE, its configuration parameters may include the number of antennas, spectrum bandwidth, etc. The first identification information of the vendor to which the first device belongs (i.e., the third device) may be the domain name, IP address, hostname, network name, etc., of the third device, as long as it can identify the third device. Alternatively, the registration information for the first model may include configuration parameters applicable to the first model, an identifier assigned to the first model by the network, and model version information for the first model. The identifier assigned to the first model by the network includes the identifier assigned to the first model by the NMS, used for matching between the two models. There is no restriction on the specific implementation of the identifier assigned to the first model by the network; for example, the identifier assigned to the first model by the network may be a virtual identifier assigned to the first model by at least one vendor, and the first model is trained by that at least one vendor. Optionally, the network can assign a globally unique identifier to a set of models.

[0120] Similarly, the registration information of the second model may include the configuration parameters applicable to the second model, the first identification information of the vendor to which the second device belongs (i.e., the fourth device), and the model version information of the second model. The configuration parameters applicable to the second model may be the scheduling parameters / operating parameters of the second device. For example, if the second device is a UE, the configuration parameters of the second device may include the number of antennas, spectrum bandwidth, etc. The first identification information of the fourth device may be the domain name, IP address, hostname, network name, etc. of the fourth device, as long as it can identify the fourth device. Alternatively, the registration information of the second model may include the configuration parameters applicable to the second model, the identifier assigned to the second model by the network, and the model version information of the second model. Among them, the identifier assigned to the second model by the network includes the identifier assigned to the second model by the NMS, which is used for matching between the two-end models. There is no restriction on the specific implementation of the identifier assigned to the second model by the network. For example, the identifier assigned to the second model by the network may be a virtual identifier of at least one vendor assigned to the second model by the network, and the second model is trained by at least one vendor.

[0121] It should be noted that the content included in the first request message above is merely an example, and the specific content included in the first request message is not limited in this application embodiment. For example, the first request message may also include the model type. The model type can be divided according to the function implemented by the model; for example, a model used for channel estimation is one type of model, and a model used for image processing is another type of model.

[0122] The fifth device receives the first request message and registers the first model and the second model respectively according to the content carried in the first request message. For example, the fifth device can update the registration information of the first model to the first registry, and the fifth device can update the registration information of the second model to the second registry. The first registry and the second registry can be registries stored locally on the fifth device. The first registry and the second registry can be the same registry, that is, the registration information of the first model and the registration information of the second model are contained in the same registry. Alternatively, the first registry and the second registry can be two independent registries.

[0123] It should be understood that the above only uses the first model pair as an example. In real-world scenarios, the third device can train to obtain more model pairs, and for each model in a model pair, the third device registers it with the fifth device. Thus, the fifth device contains information about the models included in multiple model pairs. The first and second devices can perform model matching based on one or more pieces of information associated with the model to improve model matching accuracy.

[0124] For example, please refer to Table 1, which shows multiple first models and multiple second models, along with their associated information. In Table 1, the first models include model #A1, model #A2, model #A3, and model #A4, and the second models include model #B1, model #B2, model #B3, and model #B4. The version information in Table 1 refers to the model version information.

[0125] Table 1

[0126] As can be seen from Table 1, Model #A3 and Model #B4 have the same number of antennas, spectrum bandwidth, manufacturer identification, and version information. Therefore, Model #A3 and Model #B4 are a match.

[0127] For example, see Table 2, which differs from Table 1 in that the spectral bandwidth is a range.

[0128] Table 2

[0129] As shown in Table 2, models #A3 and #B4 have the same number of antennas, spectrum bandwidth, vendor identifier, and version information. Therefore, models #A3 and #B4 are a match. It should be noted that, for spectrum bandwidth, matching between two models means that their spectrum bandwidths overlap.

[0130] It should be noted that the matching in this application embodiment includes complete matching and partial matching. Complete matching means that multiple pieces of information associated with the first model and the second model match, such as model #A3 and model #B4 in Table 1. Partial matching means that one or more pieces of information associated with the first model and the second model are allowed to be mismatched. For example, if model #A1 and model #B1 in Table 1 have different numbers of antennas associated with them, but their associated spectrum bandwidth, vendor identifier, and version information are the same, then model #A1 and model #B1 are partially matched. In possible scenarios, such as allowing some performance loss, if a completely matching model is not available when the first device and the second device perform model matching, a partially matching model can be selected. The matching of the first model and the second model includes the corresponding parts of the first model and the second model.

[0131] Optionally, considering that the manufacturer to which the model belongs will be referenced during the model matching process between the first and second devices, and that the manufacturer's actual identification information is transmitted over the network, posing a security risk, in this embodiment, after the fifth device obtains the first identification information of the third device, it can reset the identification information for the third device. For example, the fifth device can modify the first identification information to the second identification information. For instance, if the first identification information of the third device is identifier A, the fifth device can modify identifier A to identifier A' (i.e., the second identification information). Compared to the first identification information, the second identification information can be considered virtual identification information. The second identification information is exchanged during the model matching process between the first and second devices to minimize security risks.

[0132] The specific implementation of the second identification information is not limited in the embodiments of this application. For example, the second identification information may be a number set for the third device (e.g., 0001). The association information of the first model may include the configuration parameters applicable to the first model, the second identification information of the third device, and the model version information of the first model.

[0133] Optionally, considering the increasing number of manufacturers owning the second device, the number of models may also increase, making maintenance inconvenient. For example, for manufacturer A, there are models #A1, #A2, #A3, and #A4. Each model may have multiple versions; for instance, based on performance, model #A1 may have versions 1.0, 1.1, 1.2, 1.3, ..., 2.0, 2.1, etc. Similarly, for manufacturer B, there are models #B1, #B2, #B3, and #B4, each of which may also have multiple versions. For ease of management, an online time can be set for the same model. The model's online time can be understood as the model's deployment time, effective time, usage time, or the time when the model is used / deployed, and the time when the model is updated. For the device using the model, the model can only be used / deployed / updated upon reaching its online time. Therefore, the online time for the same model is the same for different devices.

[0134] In one possible implementation, the fifth device can set the model's online time based on the historical request cycles of all models from the fourth device. For example, the online time of the first model could be the sum of the first model's registration time and the longest period during which the fourth device requests the second model. Thus, the same model can be online simultaneously on different devices. When the first and second devices use the model, they use its online time as the standard, without needing to pay attention to the model's version. This eliminates the need to maintain model version information, thereby reducing the number of models that require maintenance.

[0135] S402, the fifth device sends a first response message to the third device, the first response message including the second identification information of the third device.

[0136] In response to the first request message, the fifth device may send a first response message to the third device. This first response message may include the third device's second identification information or an identifier assigned to the first model by the network. Thus, the third device may bind the second identification information to the first model and send it back to the first device. Alternatively, the third device may bind the identifier assigned to the first model by the network to the first model and send it back to the first device.

[0137] S403, the third device sends second information to the first device, the second information including the association information of the first model.

[0138] The third device, upon receiving the first response message, may send information associated with the first model (also known as the association information of the first model) to the first device. For example, the third device may send second information to the first device, which includes the association information of the first model. The association information of the first model may include the model version information of the first model, the second identification information of the third device, and the configuration parameters applicable to the first model. Accordingly, the association information of the first model stored by the first device includes the model version information of the first model, the second identification information of the third device, and the configuration parameters applicable to the first model. Alternatively, the association information of the first model may include the model version information of the first model, the identifier assigned to the first model by the network, and the configuration parameters applicable to the first model. Accordingly, the association information of the first model stored by the first device includes the model version information of the first model, the identifier assigned to the first model by the network, and the configuration parameters applicable to the first model.

[0139] It is understandable that S401-S403, taking the registration of a first model pair by a third device as an example, allows the third device to obtain a usable first model. In practice, the third device can register multiple model pairs with the fifth device, and a process similar to registering a first model pair will be executed for each model pair. Accordingly, S401-S403 can also be seen as a process of providing a usable model to the first device. In the case of multiple model pairs, the third device can send association information of at least one model to the first device. For example, the second information in S403 includes association information of at least one model. After S401-S403, the first device can obtain at least one model suitable for itself. The first device receives the association information of at least one model from the third device and can store the at least one model and its association information. Subsequently, the first device can also select a first model from the stored at least one model that matches the second model used by the second device. Alternatively, the first device can provide the second device with a first model available to it, thereby assisting the second device in selecting a suitable second model from the stored at least one model. It should be noted that the specific implementation of the first device storing at least one model and its association information in this application embodiment is not limited. For example, the first device can store at least one model and its corresponding associated information in the form of a list.

[0140] S404, the fourth device sends a second request message to the fifth device, the second request message including a third configuration parameter for requesting a model applicable to the third configuration parameter.

[0141] The fourth device is from the same manufacturer as the second device and can obtain one or more models applicable to the second device from the fifth device. For example, the fourth device can send a second request message to the fifth device, which can be used to request one or more models. The specific name of the second request message is not limited in this embodiment. For example, the second request message can be called a model request message.

[0142] The second request message may include a third configuration parameter for requesting a model corresponding to the third configuration parameter. If the fourth device requests the model for the second device, the third configuration parameter may be a configuration parameter of the second device, as illustrated in Figure 4. If the fifth device is unaware that the second request message was sent by the fourth device, the second request message may also include the fourth device's first identification information or an identifier assigned by the network to the first model. If the fifth device knows that the second request message was sent by the fourth device, the second request message may not include the fourth device's first identification information. Upon receiving the second request message, the fifth device may provide the fourth device with a model suitable for the second device based on the second request message.

[0143] S405, the fifth device sends a second response message to the fourth device, the second response message including at least one model's association information.

[0144] In response to the second request message, the fifth device sends a second response message to the fourth device. This second response message includes association information for at least one model. It is understood that the at least one model is applicable to the second device, and that the at least one model matches the content included in the second request message. For example, the second request message includes a third configuration parameter (e.g., configuration parameters of the second device), and the configuration parameter corresponding to the at least one model is the same as the third configuration parameter in the second request message. Another example is that the second request message includes first identification information for the fourth device, and the manufacturer corresponding to the at least one model is the manufacturer identified by the first identification information. Similarly, the fifth device sends all model association information matching the content included in the second request message to the fourth device.

[0145] Similar to the first identification information of the third device mentioned above, transmitting the first identification information of the fourth device over the network poses a high security risk. Therefore, the fifth device can also reset the virtual identification information (e.g., the second identification information) for the fourth device to maximize security. The association information for any model sent by the fifth device to the fourth device includes: model version information, the second identification information of the fourth device, and the configuration parameters of the second device. Taking the second model in at least one model as an example, the association information for the second model may include the model version information of the second model, the second identification information of the fourth device, and the applicable configuration parameters for the second model.

[0146] S406, the fourth device sends third information to the second device, the third information including at least one model's association information.

[0147] After obtaining the association information of at least one model from the fifth device, the fourth device can determine at least one model and send the association information of the at least one model to the second device. For example, the fourth device can send third information to the second device, which includes the association information of at least one model. The specific name of the third information is not limited in this embodiment.

[0148] Similar to S401-S403, S404-S406 can be viewed as a process of providing a usable model to the second device. By executing S404-S406, the second device can also obtain at least one model. The second device receives association information of at least one model from the fourth device and can store the at least one model and its association information. This application embodiment does not limit the specific implementation of the second device storing at least one model and its association information. For example, the second device can store at least one model and its corresponding association information in the form of a list. Subsequently, the second device can also select a second model from the stored at least one model that matches the first model used by the first device. Alternatively, the second device can provide the first device with a second model available to it, thereby assisting the first device in selecting a suitable model from the stored at least one model. For example, the model matching process between the first and second devices includes the following S407-S408.

[0149] S407. The second device sends first information to the first device, and correspondingly, the first device receives the first information from the second device.

[0150] The first information can be used to indicate information about the models that the second device can use. For example, the first information may include one or more of the following: the identification information of the manufacturer to which the second device belongs (e.g., the second identification information of the fourth device), the identification assigned by the network to the first model (e.g., the manufacturer virtual identification assigned by the NMS to the first model), model version information, or first configuration parameters.

[0151] The second device may have multiple usable models. The second identification information, network-assigned identifier, model version information, or configuration parameters associated with different models may be the same or different. The second device can indicate to the first device, based on the content contained in the first information, that it can use at least one model. Upon receiving the first information, the first device can select a first model to use from at least one stored model and provide feedback to the second device.

[0152] S408. The first device sends information about the first model to the second device, and correspondingly, the second device receives information about the first model from the first device.

[0153] The first model is the model to be used by the first device. This first model can be determined based on the content carried by the first information. The information of the first model will vary depending on the content carried by the first information. An example is given below.

[0154] (1) The first information includes the identification information of the manufacturer to which the second device belongs.

[0155] The identification information of the manufacturer to which the second device belongs is the second identification information of the fourth device, which can be used to identify the fourth device. For ease of description, the manufacturer identified by the second identification information is referred to as Manufacturer A. When the first information includes the identification information of Manufacturer A, the first device can determine that the manufacturer corresponding to the model available to the second device is Manufacturer A. The first device can select at least one model corresponding to Manufacturer A from at least one stored model. In addition, to improve the model matching accuracy, the first device can also filter at least one model corresponding to the configuration parameters from the selected at least one model according to the configuration parameters of the first device. It should be understood that the first model used by the first device belongs to the last selected at least one model.

[0156] For example, the second identification information indicates manufacturer A, and the first device can select at least one model associated with manufacturer A from at least one stored model. For ease of description, this set of at least one model is called the first model set. Further, the first device selects at least one model corresponding to the configuration parameters of the first device from the first model set. This set of at least one model is called the second model set. It should be understood that the first model belongs to the second model set. The first device can determine the first model from the second model set. For example, the first device can randomly select a model from the second model set as the first model, or the first device can select a model from the second model set as the first model based on certain rules. For example, the first device can select the model with the highest or lowest model version as the first model.

[0157] In this scenario, the information for the first model may include model version information and a second configuration parameter, which is the configuration parameter applicable to the first model. When the first model is the model selected for deployment by the first device, the second configuration parameter may be the configuration parameter of the first device. It can be assumed that the vendor corresponding to the first model selected by the first device is the vendor identified by the second identification information in the first information. Thus, the second device receives the information for the first model and, based on the model version information and the configuration parameter applicable to the first model, determines the second model from at least one stored model. Specifically, the second model matches the first model, meaning the vendor corresponding to the second model is the same as the vendor corresponding to the first model, the model version information of the second model is the same as the model version information of the first model, and the configuration parameters corresponding to the second model are the same as the configuration parameters corresponding to the first model.

[0158] Optionally, if the model version information includes the model's deployment time, then the first device and the second device deploy the model according to the deployment time, thus aligning the model versions between the first device and the second device. In this case, the information for the first model may include the configuration parameters of the first device, but not the model version information of the first model.

[0159] (2) The first information includes the identification information of the manufacturer to which the second device belongs and the first configuration parameters.

[0160] The difference between the first information in (1) and the first information here is that, in addition to the identification information of the manufacturer to which the second device belongs, the first information also includes the first configuration parameters. In this case, it is equivalent to the second device telling the first device the manufacturer and configuration parameters corresponding to the models available to the second device. Thus, the first device determines the first model from at least one stored model based on the identification information of the manufacturer to which the second device belongs and the first configuration parameters. For example, the first device determines a first model set from at least one stored model based on the identification information of the manufacturer to which the second device belongs and the first configuration parameters, and then determines the first model from the first model set. For example, the first device can randomly select a model from the first model set as the first model, or the first device can select a model from the first model set as the first model based on certain rules. For example, the first device can select the model with the highest or lowest model version as the first model.

[0161] In this case, the information of the first model includes model version information. It can be assumed that the manufacturer corresponding to the first model selected by the first device is the manufacturer identified by the second identification information in the first information, and the configuration parameters corresponding to the first model are the first configuration parameters. Thus, the second device receives the information of the first model and determines the second model from at least one stored model based on the model version information. Specifically, the second model matches the first model, meaning the manufacturer corresponding to the second model is the same as the manufacturer corresponding to the first model, the model version information of the second model is the same as the model version information of the first model, and the configuration parameters corresponding to the second model are the same as the configuration parameters corresponding to the first model.

[0162] In (1) and (2) above, the identification information of the manufacturer to which the second device belongs can also be replaced by the identifier assigned by the network to the first model, which can be used to identify the first model and for matching the first model. For example, the identifier assigned by the network to the first model is a virtual identifier of the manufacturer that trained the first model, and the manufacturer identified by this virtual identifier is called manufacturer A. When the first information includes this virtual identifier, the first device can determine that the manufacturer corresponding to the model available to the second device is manufacturer A. The first device can select at least one model corresponding to manufacturer A from at least one model stored in the database. In addition, in order to improve the model matching accuracy, the first device can also filter at least one model corresponding to the configuration parameters from the selected at least one model according to the configuration parameters of the first device. It should be understood that the first model used by the first device belongs to the last selected at least one model.

[0163] It should be noted that in (1) and (2) above, the information of the first model may also include model version information, configuration information of the first device and second identification information of the manufacturer to which the first device belongs, so that the second device determines the second model that matches the first model based on the information of the first model.

[0164] It should be noted that in model matching method 400, steps S401-S403 and / or S404-S406 can be executed in advance. That is, the model available to the first device can be provided to the first device in advance, and the model available to the second device can be provided to the second device in advance. For both the first and second devices, performing model matching only requires executing steps S407-S408. From this perspective, steps S401-S403 and / or S404-S406 are not mandatory steps, and therefore, they are illustrated with dashed boxes in Figure 4.

[0165] In model matching method 400, for dual-end devices, in addition to the manufacturer of the device using the model, model matching can also be performed based on the model version information and the applicable configuration parameters of the model, which can improve the accuracy of model matching.

[0166] Depending on the subject training the dual-end model and the subject requesting the model, the process of the model matching method provided in this application varies. Specific embodiments are described below. Embodiments 1 to 4 below share the same concept as model matching method 400, and the similarities will not be repeated.

[0167] Example 1: The first device is a network device, the second device is a terminal device, the third device is an EMS, the fourth device is an OTT, and the fifth device is an NMS. The dual-end model is trained by the manufacturer to which the network device belongs.

[0168] Please refer to Figure 5, which is a flowchart illustrating the model matching method 500 provided in this embodiment. As shown in Figure 5, the model matching method 500 provided in this embodiment includes the following steps.

[0169] S501, EMS sends a first request message to NMS, which is used to register the first model pair.

[0170] Accordingly, the NMS receives a first request message from the EMS. This first request message may include registration information for each model in the first model pair. For example, if the first model pair includes a first model and a second model, the first request message includes the registration information for both the first and second models. For details regarding the content of the registration information for the first model and the second model, please refer to the relevant description in S401 above; it will not be repeated here.

[0171] S502, NMS sends a first response message to EMS, which includes the second identification information of EMS.

[0172] The NMS registers each model in the first model pair according to the content included in the first request message. For example, the NMS can update the registration information of the first model to the first registry, and the NMS can update the registration information of the second model to the second registry. The first registry stores information associated with the first model, such as the model version information of the first model, the identification information of the EMS to which the first device belongs, and the configuration parameters applicable to the first model; or, for example, the model version information of the first model, the identifier assigned to the first model by the NMS, and the configuration parameters applicable to the first model. Similarly, the second registry stores information associated with the second model, such as the model version information of the second model, the identification information of the OTT to which the second device belongs, and the configuration parameters applicable to the second model; or, for example, the model version information of the second model, the identifier assigned to the second model by the network, and the configuration parameters applicable to the second model.

[0173] To enhance security, the NMS can reset the vendor identification information for the model. For example, the NMS can change the first identification information of the EMS to which the network device belongs to its second identification information, and the identification information of the EMS to which the network device belongs, stored in the first registry, will be the second identification information of the EMS. Similarly, the NMS can change the first identification information of the OTT to which the terminal device belongs to its second identification information, and the identification information of the OTT to which the terminal device belongs, stored in the second registry, will be the second identification information of the OTT. Subsequently, when the network device and the terminal device perform model matching, the second identification information will be used. The NMS also needs to inform the EMS of the EMS's second identification information so that the vendor identification information bound to the model provided by the EMS to the network device is the second identification information.

[0174] S503 and EMS send the association information of the first model to the network device.

[0175] The first model can be used by network devices, and the EMS can inform the network devices of the models that can be used by them. Taking the first model as an example, the EMS can send the associated information of the first model to the network device, such as the model version information of the first model, the second identification information of the EMS, and the applicable configuration parameters; or, for example, the model version information of the first model, the identifier assigned to the first model by the NMS, and the applicable configuration parameters. For details, please refer to the relevant description in S403 above, which will not be repeated here.

[0176] S504, OTT sends a second request message to NMS, which includes the configuration parameters of the terminal device.

[0177] The second request message can be used to request a model suitable for a terminal device. For example, the second request message may carry configuration parameters for the terminal device. In response to the second request message, the NMS can determine at least one model from the registered models that matches the configuration parameters of the terminal device. Alternatively, the second request message may also include the identification information of the OTT or an identifier assigned by the network to the second model; in response, the NMS can determine at least one model from the registered models that matches the OTT. Or, the second request message may include the configuration parameters of the terminal device and the identification information of the OTT (or an identifier assigned by the network to the second model); accordingly, the NMS determines at least one model from the registered models that matches the configuration parameters of the terminal device and the OTT (or the second model).

[0178] S505, NMS sends a second response message to OTT, which includes association information for at least one model.

[0179] The at least one model is a model available to the terminal device. The associated information of any one of the at least one models may include: model version information, OTT second identification information, and applicable configuration parameters; or model version information, an identifier assigned to the model by the network, and applicable configuration parameters.

[0180] S506, OTT sends third information to the terminal device, the third information including at least one model's association information.

[0181] OTT can send the association information of at least one model to the terminal device so that the terminal device can clearly identify the available models and then select the model to be used from the at least one model.

[0182] S507. The network device sends first information to the terminal device, the first information including the second identification information of EMS.

[0183] Upon receiving the first information, the terminal device can determine that the vendor corresponding to the second model used by the network device is the EMS indicated by the second identification information. Therefore, the terminal device also selects the model that matches the second identification information. Optionally, the first information can be carried in a paging message (as shown in Figure 5) or other possible RRC messages.

[0184] Optionally, the first information may also include the network device's configuration parameters. In this case, the terminal device can determine the configuration parameters corresponding to the second model used by the network device as the network device's configuration parameters based on the first information.

[0185] S508, The terminal device determines the first model based on the second identification information of EMS and the configuration parameters of the terminal device.

[0186] Upon receiving the first information, the terminal device can determine the first model from at least one stored model based on the second identification information of the EMS and the configuration parameters of the terminal device. It should be understood that the manufacturer corresponding to the first model matches the EMS identified by the second identification information. See the relevant content in S408 for details, which will not be repeated here.

[0187] S509. The terminal device sends information about the first model to the network device, and the network device receives the information about the first model from the terminal device.

[0188] If the first information includes the second identification information of the EMS, the information of the first model may include the configuration parameters of the terminal device and the model version information of the first model. If the first information includes the second identification information of the EMS and the configuration parameters of the network device, the information of the first model may include the configuration parameters of the terminal device and the model version information of the first model.

[0189] The information in the first model can be carried in the paging response or other RRC messages.

[0190] S510: The network device determines the second model based on the information from the first model.

[0191] The second model is a model that matches the first model. For example, the configuration parameters of the second model are the same as those of the first model, the model version of the second model is the same as that of the first model, and the vendor of the network device deploying the second model is the same as the vendor of the terminal device deploying the first model.

[0192] S507-S510 exemplify the matching of models between a terminal device and a network device based on the second identification information of the EMS. In possible scenarios, the terminal device and network device can also match models based on the identifier assigned to the model by the network. For example, in S507, the first information including the second identification information of the EMS can be replaced with: the first information including the identifier assigned to the second model by the network, such as a virtual identifier of the vendor (e.g., EMS) training the second model. Correspondingly, in S508, the terminal device determining the first model based on the second identification information of the EMS and the terminal device's configuration parameters can be replaced with: the terminal device determining the first model based on the identifier assigned to the second model by the network and the terminal device's configuration parameters. Upon receiving the first information, the terminal device can determine that the vendor corresponding to the second model used by the network device is EMS. Thus, the terminal device also selects a model (e.g., the first model) that matches the identifier assigned to the second model by the network.

[0193] In model matching method 500, the terminal device and the network device are matched based on the model version, applicable configuration parameters and the manufacturer to which the model belongs, which can improve the accuracy of model matching.

[0194] Example 2: The difference from Example 1 is that the model version information includes the model's launch time.

[0195] Please refer to Figure 6, which is a flowchart illustrating the model matching method 600 provided in this embodiment. As shown in Figure 6, the model matching method 600 provided in this embodiment includes the following steps.

[0196] S601, EMS sends a first request message to NMS, which is used to register the first model pair.

[0197] Accordingly, the NMS receives a first request message from the EMS. The contents of the first request message can be found in the relevant description in S401 above, and will not be repeated here.

[0198] S602, NMS sends a first response message to EMS, which includes the second identification information of EMS.

[0199] The NMS registers each model in the first model pair according to the content included in the first request message. To improve security, the first identification information of the EMS to which the NMS network device belongs is modified to the second identification information, and the second identification information of the EMS is informed to the EMS, so that the identifier of the vendor bound to the model provided by the EMS to the network device is the second identification information. Alternatively, the first response message may include the identifier assigned by the network to the first model. For details, please refer to the relevant description in S502 above, which will not be repeated here.

[0200] Additionally, NMS can configure the launch time of the first model in a first model pair, allowing multiple versions of the first model to be retained, with only one version retained. In this case, the registration information for the first model in NMS can also include the launch time of the first model, and the registration information for the second model can also include the launch time of the first model. Correspondingly, the first response message can also include the launch time of the first model.

[0201] S603 and EMS send the association information of the first model to the network device.

[0202] The first model can be used by network devices, and the EMS can inform the network devices of the models that can be used by them. Taking the first model as an example, the EMS can send the associated information of the first model to the network device. For example, the model version information of the first model, the second identification information of the EMS, and the applicable configuration parameters; or, for example, the model version information of the first model, the identifier assigned to the first model by the network, and the applicable configuration parameters, wherein the model version information includes (or is) the online time of the first model. For details, please refer to the relevant description in S403 above, which will not be repeated here.

[0203] S604, OTT sends a second request message to NMS, which includes the configuration parameters of the terminal device.

[0204] S604 can be referred to in the relevant description in the aforementioned S504, and will not be repeated here.

[0205] S605, NMS sends a second response message to OTT, which includes association information for at least one model.

[0206] The at least one model is a model available to the terminal device. The associated information for any one of the at least one models may include: model version information, OTT's second identification information, and applicable configuration parameters; or, model version information, an identifier assigned to the model by the network, and applicable configuration parameters. The model version information includes (or may be) the model's launch time.

[0207] S606, OTT sends third information to the terminal device, the third information including at least one model's association information.

[0208] OTT can send the association information of at least one model to the terminal device so that the terminal device can clearly identify the available models and then select the model to be used from the at least one model.

[0209] S607. The network device sends first information to the terminal device, the first information including the second identification information of EMS.

[0210] Upon receiving the first information, the terminal device can determine that the vendor corresponding to the second model used by the network device is the EMS indicated by the second identification information. Therefore, the terminal device selects the model to use, and also selects the model that matches the second identification information. Optionally, the first information may be carried in a paging message (Figure 6 uses this as an example) or other possible RRC messages.

[0211] Optionally, the first information may also include the network device's configuration parameters. In this case, the terminal device can determine the configuration parameters corresponding to the second model used by the network device as the network device's configuration parameters based on the first information.

[0212] S608. The terminal device determines the first model based on the second identification information of the EMS and the configuration parameters of the terminal device.

[0213] Upon receiving the first information, the terminal device can determine the first model from at least one stored model based on the second identification information of the EMS and the configuration parameters of the terminal device. It should be understood that the manufacturer corresponding to the first model matches the EMS identified by the second identification information. See the relevant content in S408 for details, which will not be repeated here.

[0214] S609. The terminal device sends information about the first model to the network device, and the network device receives the information about the first model from the terminal device.

[0215] The difference from S509 is that the information for the first model can include the configuration parameters of the terminal device, but does not need to include the model version information of the first model. This is because the model's association information includes the model's online time; therefore, the network device can select a second model that matches the first model based on the online time.

[0216] S610, the network device determines the second model based on the information from the first model.

[0217] The second model is a model that matches the first model. For example, the configuration parameters of the second model are the same as those of the first model, the launch time of the second model is the same as that of the first model, and the vendor of the network equipment deploying the second model is the same as the vendor of the terminal equipment deploying the first model.

[0218] S607-S610 exemplify the matching of models between a terminal device and a network device based on the second identification information of the EMS. In possible scenarios, the terminal device and network device can also match models based on the identifier assigned to the model by the network. For example, in S607, the first information including the second identification information of the EMS can be replaced with: the first information including the identifier assigned to the second model by the network, for example, the identifier being a virtual identifier of the vendor (e.g., EMS) training the second model. Correspondingly, in S608, the terminal device determining the first model based on the second identification information of the EMS and the terminal device's configuration parameters can be replaced with: the terminal device determining the first model based on the identifier assigned to the second model by the network and the terminal device's configuration parameters. Upon receiving the first information, the terminal device can determine that the vendor corresponding to the second model used by the network device is EMS. Thus, the terminal device also selects a model (e.g., the first model) that matches the identifier assigned to the second model by the network.

[0219] In model matching method 600, the terminal device and network device are matched based on the model version, applicable configuration parameters, and the manufacturer to which the model belongs, which can improve the accuracy of model matching. In addition, by setting an online time for the model, it is not necessary to maintain multiple versions of the model, which can improve the efficiency of model matching.

[0220] Example 3: The first device is a terminal device, the second device is a network device, the third device is an OTT, the fourth device is an EMS, and the fifth device is an NMS. The dual-end model is trained by the manufacturer to which the terminal device belongs.

[0221] Please refer to Figure 7, which is a flowchart illustrating the model matching method 700 provided in this embodiment. As shown in Figure 7, the model matching method 700 provided in this embodiment includes the following steps.

[0222] S701, OTT sends a first request message to NMS, which is used to register the first model pair.

[0223] Accordingly, the NMS receives a first request message from the OTT. The contents of the first request message can be found in the relevant description in S401 above, and will not be repeated here.

[0224] S702 and NMS send a first response message to the OTT, which includes the OTT's second identification information.

[0225] The NMS registers each model in the first model pair according to the content included in the first request message. To improve security, the NMS modifies the first identification information of the OTT to which the terminal device belongs to the second identification information, and informs the OTT of the second identification information, so that the identifier of the manufacturer bound to the model provided by the OTT to the terminal device is the second identification information. For details, please refer to the relevant description in S502 above, which will not be repeated here.

[0226] S703, OTT sends the association information of the first model to the terminal device.

[0227] The first model can be used by the terminal device, and the OTT can inform the terminal device of the models that can be used by the terminal device. Taking the second model as an example, the EMS can send the associated information of the second model to the terminal device, such as the model version information of the second model, the second identification information of the OTT, and the applicable configuration parameters; or, for example, the model version information of the second model, the identifier assigned to the second model by the network, and the applicable configuration parameters. For details, please refer to the relevant description in S403 above, which will not be repeated here.

[0228] S704, EMS sends a second request message to NMS, which includes the configuration parameters of the terminal device.

[0229] S404 can be referred to in the relevant description in the aforementioned S404, and will not be repeated here.

[0230] S705, NMS sends a second response message to EMS, which includes association information for at least one model.

[0231] The at least one model is a model available to network devices. The associated information of any one of the at least one models may include: model version information, EMS second identification information, and applicable configuration parameters; or, the associated information of any one of the at least one models may include: model version information, an identifier assigned to the model by the network, and applicable configuration parameters.

[0232] S706, EMS sends third information to network devices, which includes association information of at least one model.

[0233] EMS can send the association information of at least one model to the network device so that the network device can clearly identify the available models and then select the model to be used from the at least one model.

[0234] S707. The terminal device sends first information to the network device, the first information including the second identification information of OTT.

[0235] Upon receiving the first information, the network device can determine that the vendor corresponding to the first model used by the terminal device is the OTT indicated by the second identification information. Therefore, the network device selects the model to use, and also selects the model that matches the second identification information. Optionally, the first information can be carried in an RRC message.

[0236] Optionally, the first information may also include the configuration parameters of the terminal device. In this case, the network device can determine the configuration parameters corresponding to the second model used by the terminal device as the configuration parameters of the terminal device based on the first information.

[0237] S708, The network device determines the first model based on the second identification information of the OTT and the configuration parameters of the network device.

[0238] S708 can be referred to in the relevant description in the aforementioned S508, and will not be repeated here.

[0239] S709. The network device sends information about the first model to the terminal device, and the terminal device receives the information about the first model from the network device accordingly.

[0240] If the first information includes the second identification information of the OTT, the information of the first model may include the configuration parameters of the network device and the model version information of the first model. The information of the first model may be carried in an RRC message.

[0241] S710, the terminal device determines the second model based on the information of the first model.

[0242] The second model is a model that matches the first model. For example, the configuration parameters of the second model are the same as those of the first model, the model version of the second model is the same as that of the first model, and the vendor of the network device deploying the second model is the same as the vendor of the terminal device deploying the first model.

[0243] In the process shown in Figure 7, model selection / matching between the two ends is taken as an example based on the identification information of the model's manufacturer. In possible scenarios, the two ends can also match models based on the identifier assigned to the model by the network. Accordingly, in S707 and S708 of the process shown in Figure 7, the second identification information of the OTT can be replaced with the identifier assigned to the first model by the network, as described in the relevant descriptions in S507 and S508 above, which will not be repeated here. Similarly, the first information in S709, including the second identification information of the OTT, can also be replaced with the identifier assigned to the first model by the network.

[0244] In model matching method 700, the terminal device and the network device are matched based on the model version, applicable configuration parameters and the manufacturer to which the model belongs, which can improve the accuracy of model matching.

[0245] Example 4: The difference from Example 1 is that the model version information includes the model's launch time.

[0246] Please refer to Figure 8, which is a flowchart illustrating the model matching method 800 provided in this embodiment. As shown in Figure 8, the model matching method 800 provided in this embodiment includes the following steps.

[0247] S801, OTT sends a first request message to NMS, which is used to register the first model pair.

[0248] Accordingly, the NMS receives a first request message from the OTT. The contents of the first request message can be found in the relevant description in S401 above, and will not be repeated here.

[0249] S802, NMS sends a first response message to OTT, which includes the second identification information of OTT.

[0250] The NMS registers each model in the first model pair according to the content included in the first request message. To improve security, the NMS modifies the first identification information of the OTT to which the terminal device belongs to the second identification information, and informs the OTT of the second identification information, so that the identifier of the manufacturer bound to the model provided by the OTT to the terminal device is the second identification information. For details, please refer to the relevant description in S502 above, which will not be repeated here.

[0251] Additionally, NMS can configure the launch time of the second model in the first model pair, allowing multiple versions of the second model to be retained, with only one version retained. In this case, the registration information for the second model in NMS can also include the launch time of the second model. Correspondingly, the first response message can also include the launch time of the second model.

[0252] S803, OTT sends the association information of the first model to the terminal device.

[0253] The first model can be used by the terminal device, and the OTT can inform the terminal device of the models that can be used by the terminal device. Taking the second model as an example, the EMS can send the associated information of the second model to the terminal device, such as the model version information of the second model, the second identification information of the OTT, and the applicable configuration parameters. The model version information includes (or may be) the launch time of the second model. For details, please refer to the relevant description in S403 above, which will not be repeated here.

[0254] S804, EMS sends a second request message to NMS, which includes the configuration parameters of the terminal device.

[0255] S804 can be referred to in the relevant description in the aforementioned S404, and will not be repeated here.

[0256] S805, NMS sends a second response message to EMS, which includes association information for at least one model.

[0257] The at least one model is a model available to network devices. The associated information for any one of the at least one models may include: model version information, EMS second identification information, and applicable configuration parameters; or, the associated information for any one of the at least one models may include: model version information, an identifier assigned to the model by the network, and applicable configuration parameters. The model version information includes (or may be) the model's deployment time.

[0258] S806, EMS sends third information to the network device, which includes association information of at least one model.

[0259] EMS can send the association information of at least one model to the network device so that the network device can clearly identify the available models and then select the model to be used from the at least one model.

[0260] S807. The terminal device sends first information to the network device, the first information including the second identification information of EMS.

[0261] Upon receiving the first information, the network device can determine that the vendor corresponding to the first model used by the terminal device is the OTT indicated by the second identification information. Therefore, the network device selects the model to use, and also selects the model that matches the second identification information. Optionally, the first information can be carried in an RRC message.

[0262] Optionally, the first information may also include the configuration parameters of the terminal device. In this case, the network device can determine the configuration parameters corresponding to the second model used by the terminal device as the configuration parameters of the terminal device based on the first information.

[0263] S808, the network device determines the first model based on the second identification information of the OTT and the configuration parameters of the network device.

[0264] S808 can be referred to in the relevant description in the aforementioned S508, and will not be repeated here.

[0265] S809. The network device sends the information of the first model to the terminal device, and the terminal device receives the information of the first model from the network device accordingly.

[0266] If the first information includes the second identification information of the OTT, the information of the first model may include the configuration parameters of the network device and the model version information of the first model. The information of the first model may be carried in an RRC message.

[0267] S810, The terminal device determines the second model based on the information of the first model.

[0268] The second model is a model that matches the first model. For example, the configuration parameters of the second model are the same as those of the first model, the model version of the second model is the same as that of the first model, and the vendor of the network device deploying the second model is the same as the vendor of the terminal device deploying the first model.

[0269] In the process shown in Figure 8, model selection / matching between the two ends is taken as an example based on the identification information of the model's manufacturer. In possible scenarios, the two ends can also match models based on the identifier assigned to the model by the network. Accordingly, in S807 and S808 of the process shown in Figure 7, the second identification information of the OTT can be replaced with the identifier assigned to the first model by the network, as described in the relevant descriptions in S507 and S508 above, which will not be repeated here. Similarly, the first information in S809, including the second identification information of the OTT, can also be replaced with the identifier assigned to the first model by the network.

[0270] In model matching method 800, the terminal device and network device are matched based on the model version, applicable configuration parameters, and the manufacturer to which the model belongs, which can improve the accuracy of model matching. In addition, by setting an online time for the model, it is not necessary to maintain multiple versions of the model, which can improve the efficiency of model matching.

[0271] In the embodiments provided above, the methods provided by the embodiments of this application are described using the first device, the second device, the third device, the fourth device, and the fifth device as examples. In this application, each embodiment can be implemented independently or in combination based on certain inherent connections; in each embodiment, different implementation methods can be implemented in combination or independently. To achieve the functions in the methods provided by the embodiments of this application above, each device may include hardware structures and / or software modules, implementing the above functions in the form of hardware structures, software modules, or hardware structures plus software modules. Whether a particular function is implemented in the form of hardware structures, software modules, or hardware structures plus software modules depends on the specific application and design constraints of the technical solution.

[0272] Based on the same inventive concept as the method embodiments, this application provides a communication device. The communication device used to implement the above method in the embodiments of this application is described below with reference to the accompanying drawings. The content above can be used in subsequent embodiments, and repeated content will not be repeated.

[0273] Figure 9 is a schematic block diagram of a communication device 900 provided in an embodiment of this application. The communication device 900 can implement the functions of any of the first to fifth devices in the above embodiments. The communication device 900 may include a processing module 910 and a transceiver module 920. Optionally, it may also include a storage module, which can be used to store instructions (code or program) and / or data. The storage module may be, for example, a memory. The processing module 910 and the transceiver module 920 may be coupled to the storage module. For example, the processing module 910 can read instructions (code or program) and / or data from the storage module to implement a corresponding method. When the communication device 900 is a chip in the first to fifth devices, the storage module may be a storage module within the chip, such as a register, cache, etc. For example, the storage module may also be a storage module located outside the chip in the first to fifth devices, such as a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, such as random access memory (RAM). The above-mentioned units can be set up independently, or they can be partially or fully integrated.

[0274] Processing module 910 may be a processor or controller, such as a general-purpose central processing unit (CPU), a general-purpose processor, a digital signal processing unit (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It may implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. The processor may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc. Transceiver module 920 is a transceiver, interface circuit, bus, pin, or other possible communication interface for receiving signals from other devices. For example, when the device is implemented as a chip, transceiver module 920 is an interface circuit for the chip to receive signals from other chips or devices, or an interface circuit for the chip to send signals to other chips or devices.

[0275] In one implementation, the communication device 900 can correspondingly implement the behavior and functions of the first device in the above method embodiments. The communication device 900 can be a network device or a terminal device, or it can be a chip (system) within the network device or terminal device; or it can be a software module of the network device or terminal device. Alternatively, the communication device 900 can also be a chip or circuit, or a part of a chip or chipset deployed in the network device or terminal device for executing related method functions, or it can be a software module in the first device capable of implementing the above model method, without limitation. For details, please refer to the relevant content of the foregoing method embodiments, which will not be repeated here.

[0276] For example, the transceiver module 920 is used to receive first information from the second device, and the second device sends information about the first model. The first information includes one or more of the following: identification information of the manufacturer of the second device, model version information, or first configuration parameters. The first model can be used for communication between the communication device 900 and the second device. The processing module 910 is used to determine the information of the first model.

[0277] As an optional implementation, when the first information includes the identification information of the manufacturer of the second device, the information of the first model includes model version information and a second configuration parameter, wherein the second configuration parameter is a configuration parameter applicable to the first model. Alternatively, when the first information includes the identification information of the manufacturer of the second device and the first configuration parameter, the information of the first model includes model version information.

[0278] As an optional implementation, the transceiver module 920 is also used to receive second information from a third device, which is the manufacturer to which the communication device 900 belongs. The second information includes association information for at least one model. The at least one model includes a first model, and the association information for the first model includes model version information of the first model, identification information of the manufacturer to which the communication device 900 belongs, and configuration parameters applicable to the first model.

[0279] As an optional implementation, the model version information for the first model also includes: the launch time of the first model.

[0280] As an optional implementation, when the first information includes the identification information of the manufacturer to which the second device belongs, the information of the first model includes the configuration parameters applicable to the first model.

[0281] In one implementation, the communication device 900 can correspondingly implement the behavior and functions of the second device in the above method embodiments. The communication device 900 can be a network device or a terminal device, or it can be a chip (system) within the network device or terminal device; or it can be a software module of the network device or terminal device. Alternatively, the communication device 900 can also be a chip or circuit, or a part of a chip or chipset deployed in the network device or terminal device for executing related method functions, or it can be a software module in the second device capable of implementing the above model matching method; there are no limitations. For details, please refer to the relevant content of the foregoing method embodiments, which will not be repeated here.

[0282] For example, processing module 910 is used to determine first information. Transceiver module 920 is used to send the first information to the first device and receive information about the first model from the first device. The first information includes one or more of the following: identification information of the manufacturer to which the communication device 900 belongs, model version information, or first configuration parameters. The first model is used for communication between the communication device 900 and the first device.

[0283] As an optional implementation, when the first information includes the identification information of the manufacturer to which the communication device 900 belongs, the information of the first model includes model version information and a second configuration parameter, wherein the second configuration parameter is a configuration parameter applicable to the first model. Alternatively, when the first information includes the identification information of the manufacturer to which the communication device 900 belongs and the first configuration parameter, the information of the first model includes model version information.

[0284] As an optional implementation, the transceiver module 920 is also used to receive third information from a fourth device, which is the manufacturer to which the communication device 900 belongs. This third information includes association information for at least one model. The at least one model includes a second model, and the association information for the second model includes model version information, identification information of the manufacturer to which the communication device 900 belongs, and configuration parameters applicable to the second model.

[0285] As an optional implementation, the model version information for the second model also includes: the launch time of the second model.

[0286] As an optional implementation, when the first information includes the identification information of the manufacturer to which the communication device 900 belongs, the information of the first model includes the configuration parameters applicable to the first model.

[0287] In one implementation, the communication device 900 can correspondingly implement the behavior and functions of the third device in the above method embodiments. The communication device 900 can be an EMS or an OTT, or it can be a chip (system) within an EMS or OTT; or it can be a software module of an EMS or OTT. Alternatively, the communication device 900 can also be a chip or circuit, or a part of a chip or chipset deployed in an EMS or OTT for executing related method functions, or it can be a software module in the third device capable of implementing the above model method, without limitation. For details, please refer to the relevant content of the foregoing method embodiments, which will not be repeated here.

[0288] For example, transceiver module 920 is used to send a first request message to a fifth device, receive a first response message from the fifth device, and send association information of the first model to the first device. Processing module 910 is used to determine the association information of the first model. The first request message requests the registration of a first model pair, which includes a first model and a second model. The first model is used by the first device, and the second model is used by the second device. The first model pair is trained by communication device 900, which is the manufacturer to which the first device belongs. The first request message includes registration information of the first model and registration information of the second model. The registration information of the first model includes model version information of the first model, first identification information of communication device 900, and configuration parameters applicable to the first model. The registration information of the second model includes model version information of the second model, first identification information of a fourth device, and configuration parameters applicable to the second model. The fourth device is the manufacturer to which the second device belongs. The first response message includes second identification information of communication device 900. The association information of the first model includes model version information of the first model, second identification information of communication device 900, and configuration parameters applicable to the first model.

[0289] As an optional implementation, the model version information of the first model may also include: the launch time of the first model; and / or, the model version information of the second model may also include: the launch time of the second model.

[0290] In one implementation, the communication device 900 can correspondingly implement the behavior and function of the fourth device in the above method embodiments. The communication device 900 can be an EMS or an OTT, or it can be a chip (system) within an EMS or OTT; or it can be a software module of an EMS or OTT. Alternatively, the communication device 900 can also be a chip or circuit, or a part of a chip or chipset deployed in an EMS or OTT for executing related method functions, or it can be a software module in the fourth device capable of implementing the above model method; there are no limitations. For details, please refer to the relevant content of the foregoing method embodiments, which will not be repeated here.

[0291] For example, transceiver module 920 is used to send a second request message to the fifth device, receive a second response message from the fifth device, and send third information to the second device. Processing module 910 is used to determine the third information. The fifth device is used to manage the model trained by the third device, and the third device is the manufacturer to which the first device belongs. The second request message includes first configuration parameters and first identification information of communication device 900, which is the manufacturer to which the second device belongs. The second response message includes association information for at least one model. The third information includes association information for at least one model, and at least one model includes the second model. The association information for the second model includes model version information of the second model, second identification information of communication device 900, and configuration parameters applicable to the second model.

[0292] As an optional implementation, the model version information for the second model also includes: the launch time of the second model.

[0293] In one implementation, the communication device 900 can correspondingly implement the behavior and functions of the fifth device in the above method embodiments. The communication device 900 can be an NMS, or it can be a chip (system) within the NMS; or it can be a software module of the NMS. Alternatively, the communication device 900 can also be a chip or circuit, or a part of a chip or chipset deployed in the NMS for executing related method functions, or it can be a software module in the fifth device capable of implementing the above model matching method; there are no limitations. For details, please refer to the relevant content of the foregoing method embodiments, which will not be repeated here.

[0294] For example, the transceiver module 920 is used to receive a first request message from a third device and send a first response message to the third device. The processing module 910 is used to determine the first response message. The first request message is used to request the registration of a first model pair, which includes a first model and a second model. The first model is used by the first device, and the second model is used by the second device. The first model pair is obtained by training on the third device, which is the manufacturer to which the first device belongs. The first request message includes the registration information of the first model and the registration information of the second model. The registration information of the first model includes the model version information of the first model, the first identification information of the third device, and the configuration parameters applicable to the first model. The registration information of the second model includes the model version information of the second model, the first identification information of the fourth device, and the configuration parameters applicable to the second model. The first response message includes the second identification information of the third device.

[0295] As an optional implementation, the first response message may also include the launch time of the first model.

[0296] As an optional implementation, the transceiver module 920 is further configured to receive a second request message from the fourth device and send a second response message to the fourth device. The second request message includes first configuration parameters and first identification information of the fourth device, wherein the fourth device is the manufacturer to which the second device belongs. The second response message includes association information of at least one model, wherein the at least one model includes the second model. The association information of the second model includes model version information of the second model, second identification information of the fourth device, and configuration parameters applicable to the second model, wherein the configuration parameters applicable to the second model include the first configuration parameters.

[0297] As an optional implementation, the second response message may also include the launch time of the second model.

[0298] When the communication device 900 is a chip-based device or circuit, the transceiver module can be an input / output circuit and / or a communication interface; the processing module is an integrated processor, microprocessor, or integrated circuit.

[0299] Figure 10 is a schematic block diagram of a communication device 1000 provided in an embodiment of this application. The communication device 1000 can be any of the first to fifth devices in the above embodiments. For example, the communication device 1000 can be the terminal device in Figure 3 or a chip (system) in the terminal device. For example, the communication device 1000 can be the network device in Figure 3 or a chip (system) in the network device. For example, the communication device 1000 can be the vendor server of the network device in Figure 3 or a chip (system) in the vendor server of the network device. For example, the communication device 1000 can be the vendor server of the terminal device in Figure 3 or a chip (system) in the vendor server of the terminal device. For example, the communication device 1000 can be the network management device in Figure 3 or a chip (system) in the network management device. In this embodiment of the application, the chip system can be composed of chips or can include chips and other discrete devices. Specific functions can be found in the descriptions of the above method embodiments. In this embodiment of the application, the chip system can be composed of chips or can include chips and other discrete devices. Specific functions can be found in the descriptions of the above method embodiments.

[0300] The communication device 1000 includes one or more processors 1001, used to implement or support the communication device 1000 in implementing the functions of any of the first to fifth devices in the methods provided in the embodiments of this application. For details, please refer to the detailed description in the method examples, which will not be repeated here. The processor 1001 can also be called a processing unit or processing module, and can implement certain control functions. The processor 1001 can be a general-purpose processor or a dedicated processor, etc. For example, it includes: a baseband processor, a central processing unit, an application processor, a modem processor, a graphics processor, an image signal processor, a digital signal processor, a video codec processor, a controller, a memory, and / or a neural network processor, etc. The baseband processor can be used to process communication protocols and communication data. The central processing unit can be used to control the communication device 1000, execute software programs, and / or process data. Different processors can be independent devices or integrated into one or more processors, for example, integrated on one or more application-specific integrated circuits.

[0301] In one design, processor 1001 may include program 1003 (sometimes also referred to as code or instructions), which can be executed on processor 1001 to cause communication device 1000 to perform the methods described in the embodiments below. In yet another possible design, communication device 1000 includes circuitry (not shown in FIG10) for implementing the functions of any of the first to fifth devices in the above embodiments.

[0302] In one design, the communication device 1000 may include one or more memories 1002 storing a program 1004 (sometimes referred to as code or instructions), which can be run on the processor 1001 to cause the communication device 1000 to perform the methods described in the above method embodiments.

[0303] In one design, the processor 1001 and / or memory 1002 may include an artificial intelligence (AI) module 1007 and an AI module 1008, which are used to implement AI-related functions. The AI ​​modules can be implemented through software, hardware, or a combination of both. For example, the AI ​​module may include a RAN intelligent controller (RIC) module. For example, the AI ​​module may be a near real-time RIC or a non-real-time RIC.

[0304] In one possible design, the processor 1001 and / or memory 1002 may also store data. The processor and memory may be configured separately or integrated together.

[0305] In one possible design, the communication device 1000 may further include a transceiver 1005 and / or an antenna 1006. The processor 1001, sometimes referred to as a processing unit, controls the communication device 1000. The transceiver 1005, sometimes referred to as a transceiver unit, transceiver, transceiver circuit, or transceiver, is used to realize the transmission and reception functions of the communication device 1000 through the antenna 1006.

[0306] In one possible design, the communication device 1000 may further include one or more of the following components: a wireless communication module, an audio module, an external memory interface, internal memory, a universal serial bus (USB) interface, a power management module, an antenna, a speaker, a microphone, an input / output module, a sensor module, a motor, a camera, or a display screen, etc. It is understood that in some embodiments, the communication device 1000 may include more or fewer components, or some components may be integrated, or some components may be separated. These components may be implemented in hardware, software, or a combination of software and hardware.

[0307] The communication device in the above embodiments can be a terminal device, or a chip, circuit, or other combination device or component having the first device described above, applied in a terminal device. Alternatively, the communication device in the above embodiments can be a network device, or a chip, circuit, or other combination device or component having the second device described above, applied in a network device. Alternatively, the communication device in the above embodiments can be an EMS, or a chip, circuit, or other combination device or component having the third device described above, applied in an EMS. Alternatively, the communication device in the above embodiments can be an OTT, or a chip, circuit, or other combination device or component having the fourth device described above, applied in an OTT. Alternatively, the communication device in the above embodiments can be an NMS, or a chip, circuit, or other combination device or component having the fifth device described above, applied in an NMS. When the communication device is a terminal device or a network device, the transceiver module can be a transceiver, which may include an antenna and radio frequency circuits, etc., and the processing module can be a processor, such as a CPU. When the communication device is a system-on-a-chip (SoC), it can be an FPGA, a dedicated ASIC, a SoC, a CPU, a network processor (NP), a DSP, a microcontroller unit (MCU), a programmable logic device (PLD), or other integrated chips. The processing module can be the processor of the SoC. The transceiver module or communication interface can be the input / output interface or interface circuit of the SoC. For example, the interface circuit can be a code / data read / write interface circuit. This interface circuit can be used to receive code instructions (stored in memory, which can be read directly from memory or through other devices) and transmit them to the processor; the processor can then execute the code instructions to perform the methods described in the above method embodiments. As another example, the interface circuit can also be a signal transmission interface circuit between the communication processor and the transceiver.

[0308] This application also provides a communication system, which includes at least one terminal device and at least one network device. The network device is used to implement the functions of the first or second device in the model matching method described above, and the terminal device is also used to implement the functions of the first or second device in the model matching method. The communication system may further include a manufacturer's server for the terminal device, a manufacturer's server for the network device, and a network management device. The manufacturer's server for the terminal device is used to implement the functions of the third or fourth device in the model matching method, the manufacturer's server for the network device is used to implement the functions of the third or fourth device in the model matching method, and the network management device is used to implement the functions of the fifth device in the model matching method.

[0309] This application also provides a computer-readable storage medium including instructions that, when run on a computer, cause the computer to execute the method performed by any one of the first to fifth devices in the above-described model matching method.

[0310] This application also provides a computer program product, including computer program code, which, when executed, causes a computer to perform the method executed by any one of the first to fifth devices in the above-described model matching method.

[0311] This application provides a chip system including a processor and potentially a memory, for implementing the functions of any of the first to fifth devices in the aforementioned model matching method. The chip system can be composed of chips or may include chips and other discrete components.

[0312] To achieve the functions of the communication devices shown in Figures 9 and 10, this application embodiment also provides a chip, including a processor, for supporting the communication device in implementing the functions involved in any of the first to fifth devices in the above method embodiments. In one possible design, the chip is connected to a memory or the chip includes a memory for storing necessary computer programs or instructions and data for the communication device.

[0313] It should be understood that in the various embodiments of this application, the order of the above-mentioned processes does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0314] Those skilled in the art will recognize that the various illustrative logical blocks and steps described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this application.

[0315] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0316] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0317] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0318] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the essential contributing part of the technical solution of this application, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, external hard drives, ROM, RAM, magnetic disks, or optical disks.

[0319] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. A model matching method characterized by, The method comprises: receiving first information from a second device, the first information comprising one or more of: identification information of a vendor to which the second device belongs, an identifier assigned to the first model by a network, model version information, or a first configuration parameter; sending information of the first model to the second device, the first model being used for communication between the second device and the first device.

2. The method of claim 1, wherein, When the first information comprises the identification information of the vendor to which the second device belongs or the identifier assigned to the first model by the network, the information of the first model comprises the model version information and a second configuration parameter, the second configuration parameter being a configuration parameter applicable to the first model; or, When the first information comprises the first configuration parameter and the identification information of the vendor to which the second device belongs, or when the first information comprises the first configuration parameter and the identifier assigned to the first model by the network, the information of the first model comprises the model version information.

3. The method of claim 1 or 2, wherein, The method further comprises: receiving second information from a third device, the third device belonging to a vendor to which the first device belongs, the second information comprising association information of at least one model, wherein the at least one model comprises the first model, the association information of the first model comprising model version information of the first model, identification information of the vendor to which the first device belongs, and a configuration parameter applicable to the first model; or, the association information of the first model comprising model version information of the first model, an identifier assigned to the first model by a network, and a configuration parameter applicable to the first model.

4. The method of claim 3, wherein, The model version information of the first model further comprises: an online time of the first model.

5. The method of claim 4, wherein, When the first information comprises the identification information of the vendor to which the second device belongs or the identifier assigned to the first model by the network, the information of the first model comprises the configuration parameter applicable to the first model.

6. A model matching method characterized by, The method comprises: sending first information to a first device, the first information comprising one or more of: identification information of a first model, model version information, or a first configuration parameter, the identification information of the first model comprising identification information of a vendor to which the second device belongs, or an identifier assigned to the first model by a network; receiving information of the first model from the first device, the first model being used for communication between the second device and the first device.

7. The method of claim 6, wherein, When the first information comprises the identification information of the first model, the information of the first model comprises model version information and a second configuration parameter, the second configuration parameter being a configuration parameter applicable to the first model; or, When the first information comprises the identification information of the first model and the first configuration parameter, the information of the first model comprises model version information.

8. The method of claim 6 or 7, wherein, The method further comprises: receiving third information from a fourth device, the fourth device being a vendor to which the second device belongs, the third information comprising association information of at least one model, wherein the at least one model comprises a second model, the association information of the second model comprising model version information of the second model, identification information of the vendor to which the second device belongs, and configuration parameters applicable to the second model; or the association information of the first model comprising model version information of the first model, an identification allocated to the first model by a network, and configuration parameters applicable to the first model.

9. The method of claim 8, wherein, The model version information of the second model further comprises: an online time of the second model.

10. The method of claim 9, wherein, When the first information comprises the identification information of the vendor to which the second device belongs or the identification allocated to the first model by the network, the information of the first model comprises the configuration parameters applicable to the first model.

11. A model matching method characterized by, Comprising: sending a first request message to a fifth device, the first request message being used to request registration of a first model pair, the first model pair comprising a first model and a second model, the first model being used for a first device, the second model being used for a second device, the first model pair being obtained by training of a third device, the third device being a vendor to which the first device belongs, the first request message comprising registration information of the first model and registration information of the second model; the registration information of the first model comprising model version information of the first model, identification information of the first model, and configuration parameters applicable to the first model, the identification information of the first model comprising first identification information of the third device or an identification allocated to the first model by a network; the registration information of the second model comprising model version information of the second model, identification information of the second model, and configuration parameters applicable to the second model, the identification information of the second model comprising first identification information of a fourth device and an identification allocated to the second model by the network, the fourth device being a vendor to which the second device belongs; receiving a first response message from the fifth device, the first response message comprising second identification information of the third device; sending association information of the first model to the first device, the association information of the first model comprising: model version information of the first model, the second identification information of the third device, and the configuration parameters applicable to the first model; or the association information of the first model comprising: model version information of the first model, the identification allocated to the first model by the network, and the configuration parameters applicable to the first model.

12. The method of claim 11, wherein the model version information of the first model further comprises: an online time of the first model; and / or the model version information of the second model further comprises: an online time of the second model.

13. A model matching method characterized by, Comprising: sending a second request message to a fifth device, the fifth device being configured to manage a model trained by a third device, the third device being a vendor to which the first device belongs, the second request message comprising a first configuration parameter and first identification information of a fourth device, the fourth device being a vendor to which the second device belongs; receiving a second response message from the fifth device, the second response message comprising association information of at least one model; sending third information to the second device, the third information comprising the association information of the at least one model, the at least one model comprising a second model, the association information of the second model comprising model version information of the second model, second identification information of the fourth device and a configuration parameter applicable to the second model, or the association information of the second model comprising the model version information of the second model, an identifier allocated to the second model by a network and the configuration parameter applicable to the second model.

14. The method of claim 13, wherein, The model version information of the second model further comprises an online time of the second model.

15. A model matching method characterized by, The method comprises: receiving a first request message from a third device, the first request message being configured to request registration of a first model pair, the first model pair comprising a first model and a second model, the first model being configured for a first device, the second model being configured for a second device, the first model pair being obtained by training of the third device, the third device being a vendor to which the first device belongs, the first request message comprising registration information of the first model and registration information of the second model; the registration information of the first model comprising model version information of the first model, first identification information of the third device and a configuration parameter applicable to the first model, the registration information of the second model comprising model version information of the second model, first identification information of the fourth device and a configuration parameter applicable to the second model, the fourth device being a vendor to which the second device belongs; or the registration information of the first model comprising model version information of the first model, identification information of the first model and a configuration parameter applicable to the first model, the registration information of the second model comprising model version information of the second model, an identifier allocated to the second model by a network and a configuration parameter applicable to the second model; sending a first response message to the third device, the first response message comprising second identification information of the third device or an identifier allocated to the first model by a network.

16. The method of claim 15, wherein, The first response message further comprises an online time of the first model.

17. The method of claim 15 or 16, wherein, The method further comprises: receiving a second request message from a fourth device, the second request message comprising a first configuration parameter and first identification information of the fourth device, the fourth device being a vendor to which the second device belongs; a second response message to the fourth device, the second response message comprising association information of at least one model, the at least one model comprising a second model, the association information of the second model comprising model version information of the second model, second identification information of the fourth device, and configuration parameters applicable to the second model, or the association information of the second model comprising model version information of the second model, an identification allocated to the second model by a network, and configuration parameters applicable to the second model; and the configuration parameters applicable to the second model comprising the first configuration parameters.

18. The method of claim 17, wherein, The second response message further comprises an online time of the second model.

19. A communications device, characterized by The second response message further comprises an online time of the second model. The transceiver module is configured to receive first information from a second device and send information of a first model to the second device, wherein the first information comprises one or more of the following: identification information of a vendor to which the second device belongs, an identification allocated to the first model by a network, model version information, or first configuration parameters; and the first model is used for communication between the second device and the communication device. The processing module is configured to determine the information of the first model.

20. The apparatus of claim 19, wherein, When the first information comprises the identification information of the vendor to which the second device belongs or the identification allocated to the first model by the network, the information of the first model comprises model version information and second configuration parameters, and the second configuration parameters are configuration parameters applicable to the first model; or When the first information comprises the first configuration parameters and the identification information of the vendor to which the second device belongs, or when the first information comprises the first configuration parameters and the identification allocated to the first model by the network, the information of the first model comprises model version information.

21. The apparatus of claim 19 or 20, wherein, The transceiver module is further configured to receive second information from a third device, the third device belonging to a vendor to which the first device belongs, and the second information comprising association information of at least one model, wherein the at least one model comprises the first model, the association information of the first model comprising model version information of the first model, identification information of the vendor to which the first device belongs, and configuration parameters applicable to the first model; or the association information of the first model comprising model version information of the first model, an identification allocated to the first model by a network, and configuration parameters applicable to the first model.

22. The apparatus of claim 21, wherein, The model version information of the first model further comprises an online time of the first model.

23. The apparatus of claim 22, wherein, When the first information comprises the identification information of the vendor to which the second device belongs or the identification allocated to the first model by the network, the information of the first model comprises configuration parameters applicable to the first model.

24. A communications device, characterized by The second response message further comprises an online time of the second model. The transceiver module is configured to send first information to the first device and receive information of the first model from the first device, wherein the first information comprises one or more of the following: identification information of the first model, model version information, or first configuration parameters; the first model is used for communication between the communication device and the first device; the identification information of the first model comprises identification information of a vendor to which the second device belongs, or an identification allocated to the first model by a network; The processing module is configured to determine the first information.

25. The apparatus of claim 24, wherein, When the first information comprises the identification information of the first model, the information of the first model comprises model version information and second configuration parameters, and the second configuration parameters are configuration parameters applicable to the first model; or When the first information comprises the identification information of the first model and the first configuration parameters, the information of the first model comprises model version information.

26. The apparatus of claim 24 or 25, wherein, The transceiver module is further configured to receive third information from a fourth device, the fourth device being a vendor to which the second device belongs, and the third information comprising association information of at least one model, wherein the at least one model comprises a second model, the association information of the second model comprising model version information of the second model, identification information of the vendor to which the second device belongs, and configuration parameters applicable to the second model; or the association information of the first model comprising model version information of the first model, an identification allocated to the first model by a network, and configuration parameters applicable to the first model.

27. The apparatus of claim 26, wherein, The model version information of the second model further comprises an online time of the second model.

28. The apparatus of claim 27, wherein, When the first information comprises the identification information of the vendor to which the second device belongs or the identification allocated to the first model by the network, the information of the first model comprises configuration parameters applicable to the first model.

29. A communications device, characterized by The transceiver module is configured to send a first request message to a fifth device, receive a first response message from the fifth device, and send association information of a first model to a first device; The processing module is configured to determine the association information of the first model; and The transceiver module is configured to send a first request message to a fifth device, receive a first response message from the fifth device, and send association information of a first model to a first device; The first request message is used for requesting registration of a first model pair, the first model pair includes a first model and a second model, the first model is used for a first device, and the second model is used for a second device; the first model pair is obtained by training of the communication device, the communication device is a manufacturer to which the first device belongs, and the first request message includes registration information of the first model and registration information of the second model; the registration information of the first model includes model version information of the first model, identification information of the first model, and configuration parameters applicable to the first model, and the identification information of the first model includes first identification information of the third device or an identifier allocated to the first model by a network; the registration information of the second model includes model version information of the second model, identification information of the second model, and configuration parameters applicable to the second model, and the identification information of the second model includes first identification information of the fourth device and an identifier allocated to the second model by the network, and the fourth device is a manufacturer to which the second device belongs; The first response message includes second identification information of the communication device; The association information of the first model includes the model version information of the first model, the second identification information of the communication device, and the configuration parameters applicable to the first model; or the association information of the first model includes the model version information of the first model, the identifier allocated to the first model by the network, and the configuration parameters applicable to the first model.

30. The apparatus of claim 29, wherein, The model version information of the first model further includes online time of the first model; and / or The model version information of the second model further includes online time of the second model.

31. A communications device, characterized by Comprise: The transceiver module is configured to send a second request message to a fifth device, receive a second response message from the fifth device, and send third information to a second device; The processing module is configured to determine the third information; The fifth device is configured to manage a model trained by a third device, the third device is a manufacturer to which the first device belongs, the second request message includes first configuration parameters and first identification information of the communication device, and the communication device is a manufacturer to which the second device belongs; The second response message includes association information of at least one model; The third information includes association information of at least one model, and the at least one model includes a second model; the association information of the second model includes model version information of the second model, second identification information of the communication device, and configuration parameters applicable to the second model, or the association information of the second model includes model version information of the second model, an identifier allocated to the second model by a network, and configuration parameters applicable to the second model.

32. The apparatus of claim 31, wherein, The model version information of the second model further includes online time of the second model.

33. A communications device, characterized by Comprise: The transceiver module is configured to receive a first request message from a third device and send a first response message to the third device; The processing module is configured to determine the first response message; The first request message is used for requesting registration of a first model pair, the first model pair includes a first model and a second model, the first model is used for a first device, the second model is used for a second device, the first model pair is obtained by training of a third device, the third device is a vendor to which the first device belongs, and the first request message includes registration information of the first model and registration information of the second model; the registration information of the first model includes model version information of the first model, first identification information of the third device, and configuration parameters applicable to the first model, and the registration information of the second model includes model version information of the second model, first identification information of a fourth device, and configuration parameters applicable to the second model, the fourth device being a vendor to which the second device belongs; or the registration information of the first model includes model version information of the first model, identification information of the first model, and configuration parameters applicable to the first model, and the registration information of the second model includes model version information of the second model, an identification allocated to the second model by a network, and configuration parameters applicable to the second model. The first response message includes second identification information of the third device or an identification allocated to the first model by a network.

34. The apparatus of claim 33, wherein, The transceiver module is further configured to: receive a second request message from a fourth device, the second request message including first configuration parameters and first identification information of the fourth device, the fourth device being a vendor to which the second device belongs; send a second response message to the fourth device, the second response message including association information of at least one model, the at least one model including the second model, the association information of the second model including model version information of the second model, second identification information of the fourth device, and configuration parameters applicable to the second model, or the association information of the second model including model version information of the second model, an identification allocated to the second model by a network, and configuration parameters applicable to the second model, the configuration parameters applicable to the second model including the first configuration parameters.

35. The apparatus of claim 34, wherein, The second response message further includes an online time of the second model.

36. A communications device, characterized by The communication device includes at least one processor configured to execute a computer program, so that the communication device performs the method of any one of claims 1-5, or so that the communication device performs the method of any one of claims 6-10, or so that the communication device performs the method of any one of claims 11-12, or so that the communication device performs the method of any one of claims 13-14, or so that the communication device performs the method of any one of claims 15-18.

37. A computer-readable storage medium, comprising: The computer readable storage medium is configured to store a computer program which, when executed on a computer, causes the computer to perform the method of any one of claims 1-5, or causes the computer to perform the method of any one of claims 6-10, or causes the computer to perform the method of any one of claims 11-12, or causes the computer to perform the method of any one of claims 13-14, or causes the computer to perform the method of any one of claims 15-18.

38. A computer program product, characterised in that, The computer program product comprises a computer program which, when executed on a computer, causes the computer to perform the method of any one of claims 1-5, or causes the computer to perform the method of any one of claims 6-10, or causes the computer to perform the method of any one of claims 11-12, or causes the computer to perform the method of any one of claims 13-14, or causes the computer to perform the method of any one of claims 15-18.

39. A chip or chip system, characterized by The chip or chip system comprises: at least one processor and an interface, the at least one processor being configured to call and run instructions from the interface, when the at least one processor executes the instructions, implement the method of any one of claims 1-5, or implement the method of any one of claims 6-10, or cause the computer to perform the method of any one of claims 11-12, or cause the computer to perform the method of any one of claims 13-14, or cause the computer to perform the method of any one of claims 15-18.

40. A communication system, characterized by comprise a first communication device configured to implement the method of any one of claims 1-5, and a second communication device configured to implement the method of any one of claims 6-10.

41. The system of claim 40, wherein, The communication system further comprises a third communication device configured to implement the method of any one of claims 11-12, a fourth communication device configured to implement the method of any one of claims 13-14, and a fifth communication device configured to implement the method of any one of claims 15-18.

Images