Self-updating method, device and equipment for sensing integrated sensing algorithm

Abstract

The embodiment of the invention provides a self-updating method, device and equipment for a communication and sensing integrated sensing algorithm. According to the method, a first response message sent by a target NWDAF is acquired through an SF, an initial model algorithm is deployed according to the first response message, sensing information is analyzed and processed by using the initial model algorithm to obtain sensing data, the sensing information is information reported by a base station, a first request message is generated according to the sensing data, and the first request message is sent to the target NWDAF. And obtaining a second response message sent by the target NWDAF, wherein the second response message is used for indicating a processing mode of the initial model algorithm. And updating and storing the initial model algorithm according to the second response message to obtain a target model algorithm. According to the method, the sensing data and the correct data are simultaneously sent to the NWDAF through interaction of the SF and the NWDAF, so that the NWDAF can perform self-updating and optimization on the model algorithm according to the data, and the optimization and updating efficiency of the model algorithm is improved.

Description

Technical Field

[0001] The present application relates to the technical field of integrated communication and perception, and in particular to a self-updating method, device and equipment for a synaesthesia integrated perception algorithm. Background Art

[0002] 5G-A (5G Advanced), as an evolutionary version of 5G technology, is leading a new round of changes in the communications field. Among them, the network mode of inter-sensory integration has become a research hotspot. This mode uses 5G base stations to perform real-time signal scanning of objects within the service range, obtain information such as the type, location, speed and route of the objects, and provide strong support for emerging fields such as low-altitude economy and smart cities.

[0003] In the 5G-A inter-sensory network, the 5G base station on the wireless network side transmits the sensing information to the newly added sensing function network element (Sensing Function, referred to as SF). SF is responsible for receiving and processing this information, and performing calculations and outputs according to application requirements. At present, the analysis and computing capabilities are mainly updated and optimized through one-time deployment and subsequent upgrades to achieve algorithm model updates.

[0004] However, the current synaesthesia technology has shortcomings in the update and optimization of algorithm models. Since performance optimization needs to be performed frequently in the early stages of technology development, the existing manual model upgrade method is not flexible and convenient enough. This upgrade method not only increases operation and maintenance costs, but may also affect the stability and reliability of the system. Therefore, how to more efficiently update and optimize the algorithm model has become a key issue that needs to be solved in the development of 5G-A synaesthesia technology. Summary of the invention

[0005] The embodiments of the present application provide a self-updating method, device and equipment for a synaesthesia perception algorithm to achieve self-learning and self-optimization of the algorithm model.

[0006] In a first aspect, an embodiment of the present application provides a self-updating method of a synaesthesia perception algorithm, which is applied to SF, and includes:

[0007] Acquire a first response message sent by a target NWDAF, where the first response message includes a model algorithm that meets the requirements of the SF;

[0008] deploying an initial model algorithm according to the first response message, and analyzing and processing the perception information using the initial model algorithm to obtain perception data, where the perception information is information reported by the base station;

[0009] Generate a first request message according to the perception data, and send the first request message to the target NWDAF, where the first request message includes the perception data;

[0010] Obtain the second response message sent by the target NWDAF, where the second response message is used to indicate the processing method of the initial model algorithm;

[0011] Update and save the initial model algorithm according to the second response message to obtain a target model algorithm.

[0012] Optionally, before obtaining the first response message sent by the target NWDAF, the method further includes:

[0013] Send a second request message to the NRF, where the second request message is used to instruct the NRF to query NWDAFs that meet the SF sensing requirements;

[0014] Obtain a third response message sent by the NRF, where the third response message includes information of multiple NWDAFs that meet the SF requirements;

[0015] Determine a target NWDAF according to the third response message and its own configuration, and send a third request message to the target NWDAF, where the third request message includes multiple requirements of the model algorithm.

[0016] Optionally, the using the initial model algorithm to analyze and process the sensing information to obtain sensing data includes:

[0017] Obtain the sensing information uploaded by the base station;

[0018] Perform algorithm analysis and processing on the sensing information according to the initial model algorithm to obtain a sensing target and motion data of the sensing target;

[0019] Obtain the real data of the sensing target sent by the application platform, where the application platform is a system that receives and stores motion information of the sensing target;

[0020] Determine whether the real data is consistent with the motion data;

[0021] If the real data is consistent with the motion data, generate first sensing data, where the first sensing data is used to indicate that the model algorithm meets the sensing requirements;

[0022] If the real data is inconsistent with the motion data, generate second sensing data, where the first sensing data is used to indicate that the model algorithm does not meet the sensing requirements.

[0023] Optionally, the updating and saving the initial model algorithm according to the second response message to obtain a target sensing algorithm includes:

[0024] Perform parsing processing on the second response message to obtain the indication information of the second response message;

[0025] When the indication information is confirmation information, confirm the current model algorithm as the target perception algorithm and save the target perception algorithm;

[0026] When the indication information is a model algorithm, update and optimize the initial model algorithm according to the model algorithm to obtain a second model algorithm;

[0027] Use the second model algorithm to analyze and process the perception information, resend the first request message and obtain a second response message until the indication information of the second response message is confirmation information.

[0028] In a second aspect, an embodiment of the present application provides a self-update method for a communication-sensing integrated perception algorithm, which is applied to NWDAF and includes:

[0029] After obtaining a third request message sent by the SF, determine a model algorithm that conforms to the SF and send the model algorithm to the SF as a first response message;

[0030] After obtaining the first request message sent by the SF, determine the corresponding perception data according to the first request message;

[0031] When the perception data is first perception data, perform a mapping process on the current model algorithm to obtain confirmation information;

[0032] When the perception data is second perception data, update the current model algorithm according to the second perception data to obtain a processing result, and the processing result includes the updated model algorithm;

[0033] Generate a second response message according to the confirmation information or the processing result and send the second response message to the SF.

[0034] Optionally, the performing a mapping process on the current model algorithm to obtain confirmation information includes:

[0035] According to the first perception data, determine the current model algorithm and the current service requirement, where the current model algorithm is the model algorithm that generates the first perception data, and the current service requirement is the specific information of the second request message sent by the SF;

[0036] Construct a mapping relationship between the current model algorithm and the current service requirement, and perform a storage process on the mapping relationship to obtain confirmation information, where the confirmation information is used to indicate that the model algorithm has been confirmed and stored.

[0037] In a third aspect, an embodiment of the present application provides a self-update device for a communication-sensing integrated perception algorithm, which is applied to the SF and includes:

[0038] An acquisition module, configured to acquire a first response message sent by a target NWDAF, where the first response message includes a model algorithm that meets the SF requirements;

[0039] A processing module, configured to deploy an initial model algorithm according to the first response message, and analyze and process sensing information by using the initial model algorithm to obtain sensing data, where the sensing information is information reported by a base station;

[0040] A generation module, configured to generate a first request message according to the sensing data, and send the first request message to the target NWDAF, where the first request message includes the sensing data;

[0041] The acquisition module is further configured to acquire a second response message sent by the target NWDAF, where the second response message is used to indicate a processing method of the initial model algorithm;

[0042] The processing module is further configured to perform an update and save process on the initial model algorithm according to the second response message to obtain a target model algorithm.

[0043] Optionally, the apparatus further includes: a sending module, a confirmation module;

[0044] The sending module is configured to send a second request message to an NRF, where the second request message is used to instruct the NRF to query a NWDAF that meets the SF sensing requirements;

[0045] The acquisition module is further configured to acquire a third response message sent by the NRF, where the third response message includes information of multiple NWDAFs that meet the SF requirements;

[0046] The confirmation module is configured to determine a target NWDAF according to the third response message and its own configuration, and send a third request message to the target NWDAF, where the third request message includes multiple requirements of the model algorithm.

[0047] Optionally, the apparatus further includes: a judgment module;

[0048] The acquisition module is further configured to acquire sensing information uploaded by a base station;

[0049] The processing module is further configured to perform algorithm analysis and processing on the sensing information according to the initial model algorithm to obtain a sensing target and motion data of the sensing target;

[0050] The acquisition module is further configured to acquire real data of the sensing target sent by an application platform, where the application platform is a system that receives and stores motion information of the sensing target;

[0051] The determination module is used to determine whether the real data is consistent with the motion data;

[0052] The generation module is further used to generate first perception data if the real data is consistent with the motion data, and the first perception data is used to indicate that the model algorithm meets the perception requirements;

[0053] The generation module is further used to generate second perception data if the real data is inconsistent with the motion data, and the first perception data is used to indicate that the model algorithm does not meet the perception requirements.

[0054] Optionally, the processing module is further used to parse and process the second response message to obtain the indication information of the second response message;

[0055] The confirmation module is further used to confirm the current model algorithm as the target perception algorithm and save the target perception algorithm when the indication information is confirmation information;

[0056] The processing module is further used to update and optimize the initial model algorithm according to the model algorithm to obtain a second model algorithm when the indication information is the model algorithm;

[0057] The processing module is further used to analyze and process the perception information by using the second model algorithm, resend the first request message and obtain a second response message until the indication information of the second response message is confirmation information.

[0058] Fourthly, an embodiment of the present application provides a self-updating device for a communication-sensing integrated perception algorithm, which is applied to NWDAF and includes:

[0059] A determination module, configured to determine a model algorithm that meets the SF after obtaining a third request message sent by the SF, and send the model algorithm to the SF as a first response message;

[0060] The determination module is further used to determine corresponding perception data according to the first request message after obtaining the first request message sent by the SF;

[0061] A processing module, configured to perform a mapping process on the current model algorithm to obtain confirmation information when the perception data is the first perception data;

[0062] The processing module is further used to update the current model algorithm according to the second perception data to obtain a processing result when the perception data is the second perception data, and the processing result includes the updated model algorithm;

[0063] A generation module, configured to generate a second response message according to the confirmation information or processing result, and send the second response message to the SF.

[0064] Optionally, the determination module is further configured to determine a current model algorithm and a current service requirement according to the first sensing data, where the current model algorithm is the model algorithm for generating the first sensing data, and the current service requirement is the specific information of the second request message sent by the SF;

[0065] The processing module is further configured to construct a mapping relationship between the current model algorithm and the current service requirement, and perform storage processing on the mapping relationship to obtain confirmation information, where the confirmation information is used to indicate that the model algorithm has been confirmed and stored.

[0066] In a fifth aspect, an embodiment of the present application provides a self-updating device for a communication and sensing integrated sensing algorithm, including: a memory, a processor;

[0067] The memory stores computer-executable instructions;

[0068] The processor executes the computer-executable instructions stored in the memory, so that the processor executes the above first aspect, second aspect and / or various possible implementation manners of the first aspect and the second aspect.

[0069] In a sixth aspect, an embodiment of the present application provides a computer-readable storage medium, in which computer-executable instructions are stored, and when the computer-executable instructions are executed by a processor, they are used to implement the above first aspect, second aspect and / or various possible implementation manners of the first aspect and the second aspect.

[0070] In a seventh aspect, an embodiment of the present application provides a computer program product, including a computer program, and when the computer program is executed by a processor, it implements the above first aspect, second aspect and / or various possible implementation manners of the first aspect and the second aspect.

[0071] The self-updating method, device and equipment for the communication and sensing integrated sensing algorithm provided by the embodiments of the present application are applied to an intelligent network sensing and optimization system. The NWDAF first receives a third request message from the SF, determines a model algorithm that meets the SF, and sends it to the SF; the SF deploys the initial model algorithm accordingly, uses it to determine sensing data and then sends it to the NWDAF; the NWDAF processes the sensing data to obtain confirmation information or a processing result and feeds it back to the SF; finally, the SF updates and saves the initial model algorithm according to the feedback from the NWDAF to obtain a target model algorithm. This method realizes the dynamic determination, deployment, verification and update of the model algorithm through the interaction between the NWDAF and the SF, effectively improves the accuracy of network sensing and the optimization efficiency, and promotes the continuous optimization of the performance of the intelligent network. BRIEF DESCRIPTION OF THE DRAWINGS

[0072] The accompanying drawings herein are incorporated into and constitute a part of this specification, showing embodiments consistent with the present application, and are used together with the specification to explain the principles of the present application.

[0073] Figure 1 It is a schematic structural diagram of the intelligent network perception and optimization system shown for the present application;

[0074] Figure 2 It is a flowchart of a self - updating method for a joint communication and sensing perception algorithm provided by the present application Figure 1 ;

[0075] Figure 3 It is a signaling interaction diagram of a self - updating method for a joint communication and sensing perception algorithm provided by the present application Figure 1 ;

[0076] Figure 4 It is a signaling interaction diagram of a self - updating method for a joint communication and sensing perception algorithm provided by the present application Figure 2 ;

[0077] Figure 5 It is a flowchart of a self - updating method for a joint communication and sensing perception algorithm provided by the present application Figure 2 ;

[0078] Figure 6 It is a flowchart of a self - updating method for a joint communication and sensing perception algorithm provided by the present application Figure 3 ;

[0079] Figure 7 It is a flowchart of a self - updating method for a joint communication and sensing perception algorithm provided by the present application Figure 4 ;

[0080] Figure 8 It is a schematic structural diagram of a self - updating device for a joint communication and sensing perception algorithm provided by the present application Figure 1 ;

[0081] Figure 9 It is a schematic structural diagram of a self - updating device for a joint communication and sensing perception algorithm provided by the present application Figure 2 ;

[0082] Figure 10 It is a schematic structural diagram of a self - updating device for a joint communication and sensing perception algorithm provided by the present application.

[0083] Through the above - mentioned accompanying drawings, specific embodiments of the present application have been shown, and there will be more detailed descriptions hereinafter. These drawings and textual descriptions are not intended to limit the scope of the concept of the present application in any way, but to explain the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0084] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0085] With the rapid development of 5G technology, 5G-A, as an evolutionary version of 5G, is gradually becoming a research hotspot in the field of communications. 5G-A not only inherits the characteristics of 5G such as high speed, large capacity and low latency, but also further explores the integration of communication and perception, and proposes a network model of synaesthesia. This model aims to utilize the technical advantages of 5G base stations themselves, such as massive MIMO (massive multiple input multiple output), to achieve radar-like perception functions, thereby expanding the application scenarios of 5G networks and supporting the development of emerging fields such as low-altitude economy, traffic management, campus management, intrusion detection and smart cities. Synaesthesia technology perceives objects in a connectionless way, without the need for the perceived objects to interact with the network, providing a new solution for the integration of communication and perception.

[0086] In the 5G-A inter-sensory network mode, the 5G base station on the wireless network side plays a core role. The base station uses its own communication technology to perform real-time signal scanning on objects within the service range, and receives the signal reflected by the object to obtain information such as the type, location, speed and route of the object. This information is then passed to the newly added perception function network element (SF). SF is responsible for receiving and processing the perception information fed back by the base station, and calculating and outputting the information of the perceived object according to application requirements. The deployment method of SF is flexible and diverse. It can be an independent network element or co-located with other network elements, and supports centralized or distributed deployment. In the current 5G-A inter-sensory device, the analysis and computing capabilities are mainly deployed in the base station's BBU (baseband processing unit) perception board and SF. These devices are deployed once and upgraded later to achieve the update and optimization of the algorithm model.

[0087] Although the current 5G-A synaesthesia technology has made significant progress in achieving the integration of communication and perception, it still faces some technical problems. Especially in the early stages of technology development, due to the need for frequent technical performance optimization, the existing method of manually upgrading models is not flexible and convenient enough. This upgrade method not only increases the operation and maintenance costs, but may also affect the stability and reliability of the system. Therefore, how to more efficiently update and optimize the algorithm model has become a key issue that needs to be solved in the current development of 5G-A synaesthesia technology.

[0088] In view of the above problems, the present application proposes a self-update method for a joint sensing and communication perception algorithm. The SF determines whether the model algorithm it uses meets the current service requirements through feedback interaction with the base station. If it does not meet the current service requirements, it sends a model algorithm update request to the NWDAF, enabling the NWDAF to update the model algorithm according to the update request. This method automatically upgrades and optimizes the sensing ability by continuously self-learning and self-optimizing the algorithm model in the actual sensing service, and automatically and conveniently improves the sensing ability and accuracy.

[0089] Figure 1 FIG. shows the structural schematic diagram of the intelligent network sensing and optimization system shown in the present application. The following will be combined with Figure 1 to describe the structure of the intelligent network sensing and optimization system in detail.

[0090] As Figure 1 shown, the system integrates a sensing function (Sensing Function, abbreviated as SF), a network data analytics function (Network Data Analytics Function, abbreviated as NWDAF), and a network repository function (Network Repository Function, abbreviated as NRF).

[0091] The SF is responsible for the execution of actual sensing services, such as data collection, preprocessing, etc., and provides real-time performance data of the sensing model through feedback interaction with the NWDAF. The NWDAF is responsible for processing and analyzing the data collected from the SF and other network functions, deeply analyzing the data using the algorithm model, generating optimization suggestions, and continuously optimizing the algorithm model according to the real-time performance data through feedback interaction with the SF. The NRF stores and manages various functional entities in the network, such as the SF, NWDAF, etc., supports the deployment of the SF and the registration of network elements, and ensures the correct connection and interoperability of network functions. This system can automatically deploy the SF and complete the network element registration to ensure that the newly added SF can quickly integrate into the network. The system supports the interoperability between different network functions to ensure the smooth flow and sharing of data. By optimizing the network configuration and protocols, the efficient operation of the network and the rapid recovery of faults are achieved.

[0092] The following will specifically describe the technical solution of the present application and how the technical solution of the present application solves the above technical problems with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below with reference to the accompanying drawings.

[0093] Figure 2 FIG. shows the flow diagram of a self-update method for a joint sensing and communication perception algorithm provided by an embodiment of the present applicationFigure 1 , applied to SF, such as Figure 2 shown, the method includes:

[0094] S101: Obtain the first response message sent by the target NWDAF.

[0095] Among them, the first response message includes a model algorithm that meets the SF requirements.

[0096] It can be understood that before obtaining, SF actively initiates a request to NWDAF, aiming to obtain a model algorithm that can meet the specific needs of SF. As the core component of network data analysis, NWDAF can provide corresponding algorithm support according to the request of SF. The first response message is the response of NWDAF to the request of SF, which contains carefully selected and configured model algorithms, and these algorithms are matched according to the specific requirements of SF (such as data processing ability, accuracy requirements, real-time performance, etc.). In this way, SF can obtain an initial model algorithm that not only meets its business needs but also can operate efficiently.

[0097] S102: Deploy the initial model algorithm according to the first response message, and use the initial model algorithm to analyze and process the sensing information to obtain sensing data.

[0098] Among them, the sensing information is the information reported by the base station.

[0099] It can be understood that after receiving the first response message containing the model algorithm sent by NWDAF, SF immediately starts to deploy this initial model algorithm. After the deployment is completed, SF starts to use this algorithm to analyze and process the sensing information from the base station. Through the processing of the initial model algorithm, the original sensing information from the base station is transformed into valuable sensing data, providing a basis for subsequent network optimization, decision support, etc.

[0100] S103: Generate a first request message according to the sensing data, and send the first request message to the target NWDAF. The first request message includes the sensing data.

[0101] It can be understood that after obtaining the sensing data, SF will generate a new request message based on these data, that is, the first request message. The main purpose of this request message is to feedback the sensing data to NWDAF so that NWDAF can further analyze these data and evaluate and adjust the initial model algorithm according to the analysis results. By sending the first request message containing the sensing data to NWDAF, SF realizes data sharing and collaborative work with NWDAF, jointly promoting the improvement of network intelligence level.

[0102] S104: Obtain the second response message sent by the target NWDAF.

[0103] Among them, the second response message is used to indicate the processing method of the initial model algorithm.

[0104] It can be understood that after receiving the first request message containing sensing data sent by the SF, the NWDAF will deeply analyze these data and put forward specific suggestions on the processing method of the initial model algorithm according to the analysis results. These suggestions are encapsulated in the second response message and sent back to the SF. The second response message not only contains the evaluation results of the performance of the initial model algorithm, but may also put forward optimization suggestions or new processing strategies. By receiving and interpreting the second response message, the SF can understand the performance of the initial model algorithm in actual applications and make corresponding adjustments accordingly.

[0105] S105: Update and save the initial model algorithm according to the second response message to obtain the target model algorithm.

[0106] Finally, the SF updates and optimizes the initial model algorithm according to the suggestions or strategies put forward in the second response message sent by the NWDAF. This step may involve adjusting algorithm parameters, optimizing algorithm structures, or introducing new algorithm components, etc. After the update process, the SF will obtain a more perfect and better-performing target model algorithm. This target model algorithm will be saved and play an important role in subsequent network analysis and optimization work.

[0107] The self-update method of the integrated sensing and communication sensing algorithm provided by the embodiment of the present application is applied to the SF. The SF obtains the first response message sent by the target NWDAF, deploys the initial model algorithm according to the first response message, and uses the initial model algorithm to analyze and process the sensing information to obtain sensing data. The sensing information is the information reported by the base station. According to the sensing data, a first request message is generated and sent to the target NWDAF. Obtain the second response message sent by the target NWDAF. The second response message is used to indicate the processing method of the initial model algorithm. Update and save the initial model algorithm according to the second response message to obtain the target model algorithm. Through the interaction with the NWDAF, this method sends the sensing data and correct data to the NWDAF at the same time, enabling the NWDAF to self-update and optimize the model algorithm according to the data, and improving the optimization and update efficiency of the model algorithm.

[0108] Figure 3 It is a signaling interaction diagram of a self-update method of an integrated sensing and communication sensing algorithm provided by an embodiment of the present application Figure 1 , as Figure 3 shown. On the basis of the Figure 2 embodiment, the interaction process between the SF and the NWDAF is described in detail. The method includes:

[0109] S201: After the NWDAF obtains the third request message sent by the SF, it determines a model algorithm that conforms to the SF.

[0110] S202: The NWDAF sends the model algorithm as the first response message to the SF.

[0111] It can be understood that the main task of the NWDAF in this step is to receive and analyze the third request message sent by the SF to determine a model algorithm that meets the specific requirements and business scenarios of the SF. The NWDAF uses its powerful data processing and analysis capabilities to parse and evaluate the information in the request message, and then selects the most suitable model algorithm and sends it back to the SF as the first response message.

[0112] S203: The SF deploys the initial model algorithm according to the first response information and uses the initial model algorithm to determine the sensed data.

[0113] S204: The SF sends the sensed data as the first request message to the NWDAF.

[0114] Among them, steps S203 - S204 are similar to steps S102 - S103, and will not be elaborated here.

[0115] S205: The NWDAF determines the corresponding sensed data according to the first request message, processes the sensed data, and obtains a confirmation message or a processing result.

[0116] S206: The NWDAF sends the confirmation message or the processing result as the second response message to the SF.

[0117] It can be understood that in this step, the main task of the NWDAF is to receive the first request message sent by the SF and determine the sensed data according to this message. Subsequently, the NWDAF conducts detailed processing and analysis on these sensed data. If the sensed data contains an indication that the algorithm is correct, the NWDAF will generate a confirmation message; if the sensed data is incorrect, the current model algorithm will be updated and the updated model algorithm will be used as the processing result. Finally, the NWDAF sends this confirmation message or processing result back to the SF as the second response message, thereby ensuring the accuracy and integrity of the algorithm or providing corrected and optimized information.

[0118] S207: The SF performs an update and save process on the initial model algorithm according to the second response message to obtain the target model algorithm.

[0119] Among them, step S207 is similar to step S105, and will not be elaborated here.

[0120] A self - updating method for a communication - sensing integrated perception algorithm provided by an embodiment of the present application is applied to an intelligent network perception and optimization system. Through the interaction between NWDAF and SF, the dynamic determination, deployment, verification, and update of the model algorithm are realized, effectively improving the accuracy of network perception and the optimization efficiency, and promoting the continuous optimization of the performance of the intelligent network.

[0121] Figure 4 Signaling interaction schematic for a self - updating method of a communication - sensing integrated perception algorithm provided by an embodiment of the present application Figure 2 , such as Figure 4 shown. Based on the Figure 2 embodiment, the process of SF and NRF determining the target NWDAF is described in detail. The method includes:

[0122] S301: The SF sends a second request message to the NRF.

[0123] Among them, the second request message is used to instruct the NRF to query the NWDAF that meets the SF perception requirements.

[0124] It can be understood that the SF, according to its own service requirements or perception ability requirements, needs to find one or more network data analysis function (NWDAF) instances that can meet these requirements. To achieve this goal, the SF constructs a second request message, which clearly contains the specific perception requirements of the SF for the NWDAF, such as data processing ability, response speed, geographical location preference, etc. Subsequently, the SF sends this request message to the NRF, requesting the NRF to help query and return the NWDAF information that meets these conditions.

[0125] S302: The NRF searches for multiple NWDAF information that meets the SF requirements according to the second request message.

[0126] It can be understood that after receiving the second request message from the SF, the NRF starts to search for NWDAF instances that meet the conditions in the network function registration information library it maintains. This process may involve the matching analysis of multiple dimensions such as the ability description, current load, and geographical location of the NWDAF instance. Finally, the NRF filters out the information of multiple NWDAF instances that meet the SF requirements, and this information may include key data such as the identifier, address, and supported interface protocols of the NWDAF.

[0127] S303: The NRF sends the multiple NWDAF information as a third response message to the SF.

[0128] It can be understood that after successfully finding the NWDAF instance information that meets the SF requirements, the NRF will encapsulate this information into a third response message and send it to the SF via the network. This response message contains the detailed information of all eligible NWDAF instances found by the NRF, enabling the SF to comprehensively understand the capabilities and status of these NWDAF instances. This step is a direct response from the NRF to the SF's request and also the basis for the SF to select the target NWDAF subsequently.

[0129] S304: The SF determines the target NWDAF based on the third response message and its own configuration.

[0130] It can be understood that after receiving the third response message from the NRF, the SF will conduct further analysis and evaluation based on the NWDAF instance information provided in the message, combined with factors such as its own business logic, performance requirements, and cost considerations. This process may involve comprehensive considerations of multiple aspects such as the response time, data processing ability, reliability, and geographical location of the NWDAF instance. Finally, the SF will select one or more optimal NWDAF instances as the target NWDAF for subsequent data analysis and processing tasks.

[0131] S305: The SF sends a third request message to the target NWDAF.

[0132] Among them, the third request message includes multiple requirements for the model algorithm.

[0133] It can be understood that after determining the target NWDAF, the SF will construct a third request message according to the specific business requirements. This message details the specific requirements of the model algorithm that needs to be executed by the target NWDAF. These requirements may include key information such as the type of algorithm, the format of the input data, the expected output result, and the processing time requirement. Subsequently, the SF sends this request message to the target NWDAF, requesting it to perform data analysis and processing according to these requirements. This step marks the official start of business interaction and data flow between the SF and the target NWDAF.

[0134] An auto-update method for a communication-sensing integrated perception algorithm provided by an embodiment of the present application is applied to an intelligent network perception and optimization system. By the SF requesting and determining the NWDAF that meets its perception requirements from the NRF, and then the SF sending a request containing model algorithm requirements to the selected NWDAF, it realizes the efficient matching and distribution of model algorithm requirements in the intelligent network perception and optimization system. This process optimizes resource allocation, improves the flexibility and accuracy of network perception, and accelerates the formulation and execution of network optimization decisions.

[0135] Figure 5 It is a flowchart illustration of an auto-update method for a communication-sensing integrated perception algorithm provided by an embodiment of the present applicationFigure 2 , as Figure 5 shown, this embodiment is applied to SF. Based on the Figure 2 embodiment, the process of determining the sensing data for SF will be described in detail. The method includes:

[0136] S401: Obtain the sensing information uploaded by the base station.

[0137] It can be understood that the sensing information uploaded by the base station refers to the data collected by the base station (usually a device deployed at a specific location for wireless communication and / or sensing) and reported to the system center or data processing unit. The sensing information usually includes information such as signal strength and signal characteristics. This information is uploaded to the data processing center by the base station, providing the original material for subsequent analysis and processing.

[0138] S402: Perform algorithm analysis and processing on the sensing information according to the initial model algorithm to obtain the sensing target and the motion data of the sensing target.

[0139] It can be understood that performing algorithm analysis and processing on the sensing information according to the initial model algorithm is a key step in extracting valuable information. In this step, the preset model algorithm will deeply mine and intelligently analyze the sensing information uploaded by the base station, so as to identify the sensing target (such as a specific user or object) and its motion data (such as trajectory, speed change, etc.). This process relies on advanced algorithm technology and computing power to achieve efficient and accurate information extraction.

[0140] S403: Obtain the real data of the sensing target sent by the application platform.

[0141] Among them, the application platform is a system that receives and stores the motion information of the sensing target.

[0142] It can be understood that obtaining the real data of the sensing target sent by the application platform is to verify the accuracy of the algorithm analysis result. As a system specifically used to receive and store the motion information of the sensing target, the application platform can provide the actual motion data of the sensing target. These data, as the "gold standard", are used to compare with the motion data obtained by algorithm analysis to evaluate the accuracy and reliability of the algorithm.

[0143] S404: Determine whether the real data is consistent with the motion data. If so, execute step S405; if not, execute step S406.

[0144] It is understandable that the step of determining whether the real data is consistent with the motion data is a key link to ensure the algorithm performance. By comparing the real data with the motion data obtained through algorithm analysis, the performance of the algorithm can be intuitively evaluated. If the two are consistent, it indicates that the algorithm can accurately reflect the actual motion of the perceived target; if not, it means that there are errors or deficiencies in the algorithm and further improvement and optimization are needed.

[0145] S405: Generate the first sensing data, which is used to indicate that the model algorithm meets the sensing requirements.

[0146] It is understandable that when the motion data obtained through algorithm analysis is consistent with the real data, it indicates that the current model algorithm can effectively process the sensing information and accurately extract valuable data. These first sensing data not only prove the effectiveness of the algorithm but also provide reliable data support for subsequent business applications.

[0147] S406: Generate the second sensing data, which is used to indicate that the model algorithm does not meet the sensing requirements.

[0148] It is understandable that when the motion data obtained through algorithm analysis is inconsistent with the real data, these inconsistent data are classified as the second sensing data. These data reveal the problems and deficiencies of the algorithm and provide valuable feedback for subsequent algorithm optimization. These data will be sent to systems such as the Network Data Analytics Function (NWDAF) so that the algorithm can be adjusted and improved based on these data, thereby enhancing the accuracy and reliability of the algorithm.

[0149] A self-update method for a communication-sensing integrated sensing algorithm provided by an embodiment of the present application is applied to the SF. By obtaining the sensing information uploaded by the base station, the sensing information is processed through algorithm analysis according to the initial model algorithm to obtain the perceived target and the motion data of the perceived target. Obtain the real data of the perceived target sent by the application platform, where the application platform is a system that receives and stores the motion information of the perceived target. Determine whether the real data is consistent with the motion data. If so, generate the first sensing data, which is used to indicate that the model algorithm meets the sensing requirements. If not, generate the second sensing data, which is used to indicate that the model algorithm does not meet the sensing requirements. This method efficiently obtains and analyzes the sensing information uploaded by the base station, combines the real data of the application platform for verification, accurately determines whether the model algorithm meets the sensing requirements, and thus quickly generates accurate sensing data, effectively improving the intelligent level and accuracy of network sensing.

[0150] Figure 6 For the flow diagram of a self-update method for a communication-sensing integrated sensing algorithm provided by an embodiment of the present application Figure 3 , as Figure 6 shown, this embodiment is in Figure 2Based on the embodiments, the process of the SF determining the target perception algorithm is described in detail. The method includes:

[0151] S501: Parse and process the second response message to obtain the indication information of the second response message.

[0152] It can be understood that after receiving the second response message from the NWDAF, the SF will first perform a detailed parsing and processing on it. This step aims to extract key indication information from the response message. The indication information in the second response message is mainly divided into two categories: one is the confirmation information, indicating that the currently submitted model algorithm has been confirmed and saved by the NWDAF, which means that this algorithm can be directly called when encountering the same business requirements in the future without having to submit it again; the other is the processing result, which usually refers to the result after updating or optimizing the model algorithm, such as an updated and completed model algorithm. Such a design aims to improve the efficiency and flexibility of algorithm usage.

[0153] S502: Determine whether the indication information is confirmation information. If so, execute step S503; if not, execute step S504.

[0154] It can be understood that after successfully parsing the indication information in the second response message, the SF will make the next judgment. It first checks whether the indication information is confirmation information. If it is the information indicating that the algorithm has been confirmed and saved, then this means that the currently submitted model algorithm meets the requirements of the NWDAF and can be regarded as a valid target perception algorithm. Next, the SF will execute step S503. If the indication information is not confirmation information but the processing result indicating that the model algorithm needs further optimization or update, then the SF will turn to execute step S504.

[0155] S503: Confirm the current model algorithm as the target perception algorithm and save the target perception algorithm.

[0156] It can be understood that when the confirmation information indicates that the current model algorithm has been accepted and saved by the NWDAF, the SF will officially confirm this algorithm as the target perception algorithm. This step is an important link in the algorithm life cycle, indicating that the algorithm has passed the necessary verification and review and can be officially used in business processing. At the same time, the SF is also responsible for saving this target perception algorithm to ensure that it can be quickly called when needed to meet business requirements. The saving method may include storing the algorithm in a local database or a remote server for quick access.

[0157] S504: Update and optimize the initial model algorithm according to the model algorithm to obtain the second model algorithm.

[0158] It is understandable that if the indication information in the second response message indicates that the model algorithm needs to be updated and optimized, the SF will initiate an update and optimization processing flow. This step may involve various technologies and methods, such as tuning machine learning algorithms, adjusting parameters, feature selection, etc., aiming to improve its performance or adaptability by improving the algorithm. After this series of optimization processes, the SF will obtain a new and improved second model algorithm. This algorithm should theoretically be more efficient or accurate than the previous one and can better meet the business requirements.

[0159] S505: Analyze and process the sensing information using the second model algorithm, resend the first request message, and obtain the second response message until the indication information in the second response message is confirmation information.

[0160] It is understandable that after obtaining the updated second model algorithm, the SF will use this new algorithm to analyze and process the sensing information. This step is a key link in verifying the performance of the new algorithm and an important step in ensuring that the algorithm can play a role in actual business. After processing the sensing information, the SF may resend the first request message to the NWDAF according to the analysis results to obtain new response messages and indication information. This process may be repeated multiple times until the indication information returned by the NWDAF indicates that the current algorithm has been confirmed and saved. This cyclic process ensures that the algorithm can be continuously optimized and improved to adapt to the current business requirements and environmental conditions.

[0161] A self-update method for a communication-sensing integrated sensing algorithm provided by an embodiment of the present application is applied to the SF. By parsing and processing the second response message, the indication information of the second response message is obtained. It is judged whether the indication information is confirmation information. If so, the current model algorithm is confirmed as the target sensing algorithm and the target sensing algorithm is saved. If not, the initial model algorithm is updated and optimized according to the model algorithm to obtain a second model algorithm. The second model algorithm is used to analyze and process the sensing information, and the first request message is resent and the second response message is obtained until the indication information in the second response message is confirmation information. This method analyzes the messages transmitted by the NWDAF to determine whether the current model algorithm needs to be updated, ensuring the real-time accuracy of the algorithm model.

[0162] Figure 7 It is a flowchart of a self-update method for a communication-sensing integrated sensing algorithm provided by an embodiment of the present application Figure 4 , such as Figure 7 shown. On the basis of the Figure 3 embodiment, the process of the NWDAF processing the model algorithm according to the sensing data is described in detail. The method includes:

[0163] S601: After receiving the first request message sent by the SF, determine the corresponding sensing data according to the first request message.

[0164] It can be understood that in the working process of the NWDAF, once the first request message from the SF is successfully captured, this step marks the start of the data processing flow. The NWDAF first parses the request message and extracts key information from it, which is used to locate and obtain the corresponding sensing data. Sensing data is important information during network operation and is crucial for subsequent analysis and decision-making.

[0165] S602: Determine whether the sensing data is the first sensing data. If so, execute step S603; if not, execute step S605.

[0166] It can be understood that after obtaining the sensing data, the NWDAF will further determine the specific type of the sensing data and perform the next operation according to the specific type of the sensing data.

[0167] S603: Determine the current model algorithm and the current business requirements according to the first sensing data.

[0168] Among them, the current model algorithm is the model algorithm that generates the first sensing data, and the current business requirement is the specific information of the second request message sent by the SF.

[0169] It can be understood that for the first sensing data, the NWDAF will determine the currently used model algorithm and the current business requirements that match it according to the characteristics and content of the data. The current model algorithm here refers to the algorithm that generates these sensing data, and the current business requirement is obtained by parsing the second request message sent by the SF, which contains specific business requirements and expected analysis results.

[0170] S604: Construct the mapping relationship between the current model algorithm and the current business requirements, and perform storage processing on the mapping relationship to obtain a confirmation message.

[0171] Among them, the confirmation message is used to indicate that the model algorithm has been confirmed and stored.

[0172] It can be understood that after determining the current model algorithm and the current business requirements, the NWDAF will construct the mapping relationship between the two and perform storage processing on this mapping relationship. The purpose of this step is to ensure that the corresponding model algorithm can be quickly found according to the business requirements in the future, thereby improving the efficiency of data processing and analysis. For example, when the SF request with the same business requirements next time determines the model algorithm, the algorithm model can be sent first. After the storage processing is completed, the NWDAF will generate a confirmation message, which is used to indicate that the model algorithm has been confirmed and successfully stored, providing a basis for subsequent data processing and analysis.

[0173] S605: Update the current model algorithm according to the second sensing data to obtain a processing result.

[0174] The processing result includes the updated model algorithm.

[0175] It can be understood that if the sensing data is not the first sensing data but the second sensing data, and the second sensing data includes motion data and the difference data between the motion data and the real data, NWDAF will update the current model algorithm according to these sensing data and difference data. The update process may include adjusting model parameters, optimizing the algorithm structure or introducing new algorithms, etc., to obtain better data processing and analysis effects. After the processing is completed, NWDAF will generate a processing result containing the updated model algorithm.

[0176] S606: Generate a second response message according to the confirmation information or the processing result, and send the second response message to the SF.

[0177] It can be understood that finally, NWDAF will construct a second response message according to the confirmation information or the processing result generated in the previous steps and send the message back to the SF. This response message contains the final result or status information of NWDAF's data processing, such as the confirmation information of the model algorithm, the updated model algorithm, etc. In this way, the SF can understand the progress and result of NWDAF's data processing according to this response message, and thus make corresponding decisions or adjustments.

[0178] A self - updating method for a communication - sensing integrated sensing algorithm provided by an embodiment of the present application is applied to NWDAF. By determining the corresponding sensing data according to the first request message, it is judged whether the sensing data is the first sensing data. If so, according to the first sensing data, the current model algorithm and the current service requirement are determined. The current model algorithm is the model algorithm for generating the first sensing data, and the current service requirement is the specific information of the second request message sent by the SF. A mapping relationship between the current model algorithm and the current service requirement is constructed and stored to obtain confirmation information, and the confirmation information is used to indicate that the model algorithm has been confirmed and stored. If not, the current model algorithm is updated according to the second sensing data to obtain a processing result, and the processing result includes the updated model algorithm. A second response message is generated according to the confirmation information or the processing result and sent to the SF. This method determines the accuracy of the model algorithm by analyzing the sensing data. When the model algorithm is inaccurate, it is optimized according to the sensing data, and when the model algorithm is accurate, it is saved, realizing the self - learning and self - optimization of the sensing ability and saving labor costs.

[0179] Figure 8Structural schematic of a self - updating device for a synesthesia - integrated perception algorithm provided by this application Figure 1 , applied to SF, such as Figure 8 As shown, the self - updating device 70 for the synesthesia - integrated perception algorithm provided in this embodiment includes:

[0180] An acquisition module 701, configured to acquire a first response message sent by a target NWDAF, where the first response message includes a model algorithm that meets the requirements of the SF;

[0181] A processing module 702, configured to deploy an initial model algorithm according to the first response message, and analyze and process perception information by using the initial model algorithm to obtain perception data, where the perception information is the information reported by the base station;

[0182] A generation module 703, configured to generate a first request message according to the perception data, and send the first request message to the target NWDAF, where the first request message includes the perception data;

[0183] The acquisition module 701 is further configured to acquire a second response message sent by the target NWDAF, where the second response message is used to indicate the processing method of the initial model algorithm;

[0184] The processing module 702 is further configured to perform update and save processing on the initial model algorithm according to the second response message to obtain a target model algorithm.

[0185] Optionally, the device further includes: a sending module 704, a confirmation module 705;

[0186] The sending module 704 is configured to send a second request message to the NRF, where the second request message is used to instruct the NRF to query NWDAFs that meet the SF perception requirements;

[0187] The acquisition module 701 is further configured to acquire a third response message sent by the NRF, where the third response message includes information of multiple NWDAFs that meet the SF requirements;

[0188] The confirmation module 705 is configured to determine a target NWDAF according to the third response message and its own configuration, and send a third request message to the target NWDAF, where the third request message includes multiple requirements of the model algorithm.

[0189] Optionally, the device further includes: a judgment module 706;

[0190] The acquisition module 701 is further configured to acquire the perception information uploaded by the base station;

[0191] The processing module 702 is further configured to perform algorithm analysis and processing on the perception information according to the initial model algorithm to obtain a perception target and motion data of the perception target;

[0192] The obtaining module 701 is further configured to obtain the real data of the perception target sent by the application platform, where the application platform is a system for receiving and storing motion information of the perception target;

[0193] The judging module 706 is configured to judge whether the real data is consistent with the motion data;

[0194] The generating module 703 is further configured to generate first perception data if the real data is consistent with the motion data, where the first perception data is used to indicate that the model algorithm meets the perception requirements;

[0195] The generating module 703 is further configured to generate second perception data if the real data is inconsistent with the motion data, where the first perception data is used to indicate that the model algorithm does not meet the perception requirements.

[0196] Optionally, the processing module 702 is further configured to parse and process the second response message to obtain the indication information of the second response message;

[0197] The confirmation module 705 is further configured to confirm the current model algorithm as the target perception algorithm and save the target perception algorithm when the indication information is confirmation information;

[0198] The processing module 702 is further configured to update and optimize the initial model algorithm according to the model algorithm to obtain a second model algorithm when the indication information is the model algorithm;

[0199] The processing module 702 is further configured to analyze and process the perception information by using the second model algorithm, resend the first request message, and obtain a second response message until the indication information of the second response message is confirmation information.

[0200] The self-updating device for the integrated communication and sensing algorithm provided in this embodiment can execute the method provided in the above method embodiment, and its implementation principle and technical effect are similar, which will not be elaborated here in this embodiment.

[0201] Figure 9 The structural schematic of a self-updating device for the integrated communication and sensing algorithm provided in this application Figure 2 , applied to NWDAF, as Figure 9 shown, the self-updating device 80 for the integrated communication and sensing algorithm provided in this embodiment includes:

[0202] A determination module 801, configured to determine a model algorithm that conforms to the SF after receiving a third request message sent by the SF, and send the model algorithm to the SF as a first response message;

[0203] The determination module 801 is further configured to determine corresponding sensing data according to the first request message after receiving the first request message sent by the SF;

[0204] A processing module 802, configured to perform mapping processing on the current model algorithm when the sensing data is first sensing data to obtain a confirmation message;

[0205] The processing module 802 is further configured to perform update processing on the current model algorithm according to the second sensing data when the sensing data is second sensing data to obtain a processing result, where the processing result includes the updated model algorithm;

[0206] A generation module 803, configured to generate a second response message according to the confirmation message or the processing result, and send the second response message to the SF.

[0207] Optionally, the determination module 801 is further configured to determine a current model algorithm and a current service requirement according to the first sensing data, where the current model algorithm is the model algorithm that generates the first sensing data, and the current service requirement is the specific information of the second request message sent by the SF;

[0208] The processing module 802 is further configured to construct a mapping relationship between the current model algorithm and the current service requirement, and perform storage processing on the mapping relationship to obtain a confirmation message, where the confirmation message is used to indicate that the model algorithm has been confirmed and stored.

[0209] The self-update device for the integrated sensing and communication algorithm provided in this embodiment can execute the method provided in the above method embodiment, and its implementation principle and technical effect are similar, which will not be elaborated here in this embodiment.

[0210] Figure 10 This is a schematic structural diagram of a self-update device for an integrated sensing and communication algorithm provided in the present application. As Figure 10 shown, the electronic device 90 provided in this embodiment includes: at least one processor 901 and a memory 902. Optionally, the device 90 further includes a communication component 903. Among them, the processor 901, the memory 902, and the communication component 903 are connected through a bus 904.

[0211] In a specific implementation process, at least one processor 901 executes computer execution instructions stored in the memory 902, so that at least one processor 901 executes the above method.

[0212] For the specific implementation process of the processor 901, reference may be made to the above method embodiments. Their implementation principles and technical effects are similar, and will not be elaborated here in this embodiment.

[0213] In the above embodiments, it should be understood that the processor may be a central processing unit (English: Central Processing Unit, abbreviated as: CPU), or may also be other general-purpose processors, digital signal processors (English: Digital Signal Processor, abbreviated as: DSP), application specific integrated circuits (English: Application Specific Integrated Circuit, abbreviated as: ASIC), etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in combination with the invention can be directly embodied as being executed and completed by a hardware processor, or can be executed and completed by a combination of hardware and software modules in the processor.

[0214] The memory may include a high-speed memory (Random Access Memory, RAM), and may also include a non-volatile memory (Non-volatile Memory, NVM), such as at least one disk memory.

[0215] The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of convenience in representation, the buses in the drawings of this application are not limited to only one bus or one type of bus.

[0216] This application also provides a computer program product, including a computer program, which implements the above method when executed by a processor.

[0217] This application also provides a computer-readable storage medium, in which computer-executable instructions are stored, and when the processor executes the computer-executable instructions, the above method is implemented.

[0218] The above-readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The readable storage medium can be any available medium accessible by a general-purpose or special-purpose computer.

[0219] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (ASIC). Of course, the processor and the readable storage medium can also exist as discrete components in a device.

[0220] The division of units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection between each other can be an indirect coupling or communication connection through some interfaces, devices or units, and can be in electrical, mechanical or other forms.

[0221] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0222] In addition, in each embodiment of the present invention, the functional units can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit.

[0223] If a function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or a part of this 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 for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods of various embodiments of the present invention. The aforementioned storage medium includes: USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs and other various media that can store program codes.

[0224] Those of ordinary skill in the art can understand that all or part of the steps for implementing the above method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When this program is executed, it executes the steps including the above method embodiments; and the aforementioned storage medium includes: ROMs, RAMs, magnetic disks, or optical discs and other various media that can store program codes.

[0225] Finally, it should be noted that: After considering the specification and practicing the invention disclosed herein, those skilled in the art will readily think of other implementation manners of the present invention. The present invention is intended to cover any variations, uses, or adaptations of the present invention. These variations, uses, or adaptations follow the general principles of the present invention and include the common general knowledge or conventional technical means in the technical field not disclosed in the present invention. It is not limited to the exact structures described above and shown in the drawings, and various modifications and changes can be made without departing from its scope. The scope of the present invention is only limited by the appended claims.

Claims

1. A self-updating method for a synaesthesia perception algorithm, characterized in that: Applied to SF, including: Acquire a first response message sent by a target NWDAF, where the first response message includes a model algorithm that meets the requirements of the SF; deploying an initial model algorithm according to the first response message, and analyzing and processing the perception information using the initial model algorithm to obtain perception data, where the perception information is information reported by the base station; Generate a first request message according to the perception data, and send the first request message to the target NWDAF, where the first request message includes the perception data; Obtaining a second response message sent by the target NWDAF, where the second response message is used to indicate a processing method of the initial model algorithm; The initial model algorithm is updated and saved according to the second response message to obtain a target model algorithm.

2. The method according to claim 1, characterized in that Before obtaining the first response message sent by the target NWDAF, the method further includes: Sending a second request message to the NRF, where the second request message is used to instruct the NRF to query the NWDAF that meets the SF perception requirements; Obtain a third response message sent by the NRF, where the third response message includes multiple NWDAF information that meets the requirements of the SF; According to the third response message and its own configuration, a target NWDAF is determined, and a third request message is sent to the target NWDAF, where the third request message includes multiple requirements of the model algorithm.

3. The method according to claim 1, characterized in that The using the initial model algorithm to analyze and process the perception information to obtain the perception data includes: Obtain the perception information uploaded by the base station; Performing algorithmic analysis and processing on the perception information according to the initial model algorithm to obtain a perception target and motion data of the perception target; Acquire real data of the perceived target sent by an application platform, wherein the application platform is a system for receiving and storing motion information of the perceived target; Determining whether the real data is consistent with the motion data; If the real data is consistent with the motion data, first perception data is generated, where the first perception data is used to indicate that the model algorithm meets the perception requirement; If the real data is inconsistent with the motion data, second perception data is generated, and the first perception data is used to indicate that the model algorithm does not meet the perception requirements.

4. The method according to claim 1, characterized in that: The updating and saving processing of the initial model algorithm according to the second response message to obtain a target perception algorithm includes: Parsing the second response message to obtain indication information of the second response message; When the indication information is confirmation information, confirming the current model algorithm as the target perception algorithm and saving the target perception algorithm; When the indication information is a model algorithm, updating and optimizing the initial model algorithm according to the model algorithm to obtain a second model algorithm; The perception information is analyzed and processed using the second model algorithm, and the first request message is resent and the second response message is obtained until the indication information of the second response message is confirmation information.

5. A self-updating method for a synaesthesia perception algorithm, characterized in that: Applied to NWDAF, including: After acquiring the third request message sent by the SF, determining a model algorithm that conforms to the SF, and sending the model algorithm to the SF as a first response message; After acquiring the first request message sent by the SF, determining corresponding perception data according to the first request message; When the perception data is the first perception data, mapping processing is performed on the current model algorithm to obtain confirmation information; When the perception data is second perception data, updating the current model algorithm according to the second perception data to obtain a processing result, wherein the processing result includes an updated model algorithm; A second response message is generated according to the confirmation information or the processing result, and the second response message is sent to the SF.

6. The method according to claim 5, characterized in that The mapping process is performed on the current model algorithm to obtain confirmation information, including: Determine a current model algorithm and a current service requirement according to the first perception data, where the current model algorithm is a model algorithm for generating the first perception data, and the current service requirement is specific information of a second request message sent by the SF; A mapping relationship between the current model algorithm and the current business demand is constructed, and the mapping relationship is stored to obtain confirmation information, where the confirmation information is used to indicate that the model algorithm has been confirmed and stored.

7. A self-updating device for a synaesthesia perception algorithm, characterized in that: Applied to SF, including: An acquisition module, configured to acquire a first response message sent by a target NWDAF, wherein the first response message includes a model algorithm that meets the requirements of the SF; a processing module, configured to deploy an initial model algorithm according to the first response message, and use the initial model algorithm to analyze and process the perception information to obtain perception data, where the perception information is information reported by the base station; A generating module, configured to generate a first request message according to the perception data, and send the first request message to the target NWDAF, where the first request message includes the perception data; The acquisition module is further used to acquire a second response message sent by the target NWDAF, where the second response message is used to indicate a processing method of the initial model algorithm; The processing module is further used to update and save the initial model algorithm according to the second response message to obtain a target model algorithm.

8. A self-updating device for a synaesthesia perception algorithm, characterized in that: Applied to NWDAF, including: a determination module, configured to determine a model algorithm that conforms to the SF after acquiring the third request message sent by the SF, and send the model algorithm to the SF as a first response message; The determining module is further configured to determine corresponding perception data according to the first request message sent by the SF after acquiring the first request message; A processing module, used for performing mapping processing on the current model algorithm to obtain confirmation information when the perception data is the first perception data; The processing module is further configured to update the current model algorithm according to the second perception data to obtain a processing result when the perception data is the second perception data, and the processing result includes the updated model algorithm; A generating module is used to generate a second response message according to the confirmation information or the processing result, and send the second response message to the SF.

9. A self-updating device for a synaesthesia perception algorithm, characterized in that: include: Memory, processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory, so that the processor performs the method according to any one of claims 1 to 4, 5 to 6.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 4, 5 to 6 when executed by a processor.

11. A computer program product, characterized in that The invention comprises a computer program, which implements the method according to any one of claims 1 to 4, 5 to 6 when being executed by a processor.

Images