Network information acquisition method, device, equipment, storage medium and product

Abstract

This application provides a method, apparatus, device, storage medium, and product for acquiring network information. The method includes: responding to a received network information acquisition request, performing associated data retrieval based on indication information carried in the network information acquisition request to obtain data retrieval results; then, generating network information corresponding to the network information acquisition request based on the data retrieval results; and finally, returning the network information to the sender of the network information acquisition request. The technical solution of this application, by having core network elements retrieve associated network data and generate network information based on the retrieved data after receiving a request, helps improve the accuracy of network information, thereby improving the accuracy of business processing. Furthermore, utilizing the high-speed data transmission capabilities provided by the core network helps reduce the latency of data retrieval and transmission, improving the real-time performance of acquiring network information, thereby improving the real-time performance of business processing and user experience.

Description

Technical Field

[0001] This application relates to the field of computer technology, specifically to a method, apparatus, device, storage medium, and product for acquiring network information. Background Technology

[0002] With the development of mobile communication technology, the services provided by user equipment (UE) have gradually shifted from voice calls to more diversified applications, such as live video streaming, connected vehicles, and the Internet of Things. Network information is a crucial factor in enabling these diverse applications and making decisions; therefore, acquiring network information has become an important research direction to meet service demands.

[0003] Currently, relevant technologies can analyze data stored by the UE or application server to generate the required network information. However, the accuracy of the network information obtained in this way is relatively low, which may affect business processing and user experience to some extent. Summary of the Invention

[0004] This application provides a method, apparatus, device, storage medium, and product for acquiring network information, which helps to improve the accuracy of the acquired network information and, to a certain extent, improves the accuracy of business processing and user experience.

[0005] In a first aspect, embodiments of this application provide a method for obtaining network information, the method comprising:

[0006] In response to a received network information acquisition request, the system performs associated data retrieval based on the indication information carried in the network information acquisition request to obtain data retrieval results.

[0007] Based on the data retrieval results, generate the network information corresponding to the network information acquisition request;

[0008] The network information is returned to the sender of the network information retrieval request.

[0009] Secondly, embodiments of this application provide a method for obtaining network information, the method comprising:

[0010] The system receives a retrieval request sent by a third core network element, performs a related data retrieval on the indication information in the stored network database, and obtains the data retrieval results. The retrieval request is generated by the third core network element after receiving a network information acquisition request, and the network information acquisition request carries the indication information.

[0011] The data retrieval result is sent to the third core network element, which is used to instruct the third core network element to generate network information corresponding to the network information acquisition request and return the network information to the sender of the network information acquisition request.

[0012] Thirdly, embodiments of this application provide a network information acquisition device, the device comprising:

[0013] The retrieval unit is used to respond to a received network information acquisition request, perform associated data retrieval based on the indication information carried in the network information acquisition request, and obtain data retrieval results;

[0014] The generation unit is used to generate network information corresponding to the network information acquisition request based on the data retrieval results;

[0015] The sending unit is used to return the network information to the sender of the network information acquisition request.

[0016] Fourthly, embodiments of this application provide a network information acquisition device, the device comprising:

[0017] The receiving unit is used to receive a retrieval request sent by a third core network element, perform a related data retrieval on the indication information in the stored network database, and obtain the data retrieval result; the retrieval request is generated by the third core network element after receiving the network information acquisition request, and the network information acquisition request carries the indication information;

[0018] The sending unit is used to send the data retrieval result to the third core network element. The data retrieval result is used to instruct the third core network element to generate network information corresponding to the network information acquisition request and return the network information to the sender of the network information acquisition request.

[0019] Fifthly, embodiments of this application provide an electronic device, which includes one or more processors; and a memory for storing one or more computer programs, which, when executed by the one or more processors, enable the electronic device to implement the network information acquisition method described in the first or second aspect.

[0020] Sixthly, embodiments of this application provide a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform the network information acquisition method described in the first or second aspect.

[0021] In a seventh aspect, embodiments of this application provide a computer program product, which includes a computer program or computer instructions. When the computer program or computer instructions are executed by a processor, they implement the method for obtaining network information as described in the first or second aspect.

[0022] In some embodiments of this application, the network elements in the core network respond to a received network information acquisition request by performing associated data retrieval based on the indication information carried in the request, obtaining data retrieval results, and then generating network information corresponding to the network information acquisition request based on the data retrieval results, so as to return the network information to the sender of the request. It is evident that, on the one hand, by retrieving associated data from the indication information to generate network information, compared to related technologies, the core network elements can analyze network data collected from multiple network elements, which helps improve the accuracy of the generated network information and thus improves the accuracy of service processing. On the other hand, by interacting with each other to retrieve and generate network information, the high-speed data transmission capabilities provided by the core network can be utilized, thereby reducing the latency of generating and feeding back network information, improving the real-time performance of network information, and enhancing the real-time performance of service processing and user experience. Attached Figure Description

[0023] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 This is a schematic diagram of the architecture of a wireless communication system provided in an embodiment of this application;

[0025] Figure 2 This is a schematic diagram of an implementation environment provided in an embodiment of this application;

[0026] Figure 3 This is a flowchart illustrating a method for obtaining network information provided in an embodiment of this application;

[0027] Figure 4 This is a schematic diagram illustrating the interaction between a third core network element and a first core network element, provided in an embodiment of this application.

[0028] Figure 5 This is a timing diagram of a network information acquisition method provided in an embodiment of this application;

[0029] Figure 6 This is another flowchart illustrating a method for obtaining network information provided in an embodiment of this application;

[0030] Figure 7 This is another interactive schematic diagram of a third core network element and a first core network element provided in an embodiment of this application;

[0031] Figure 8 This is another timing diagram of a network information acquisition method provided in an embodiment of this application;

[0032] Figure 9 This is a schematic diagram of the structure of a network information acquisition device provided in an embodiment of this application;

[0033] Figure 10 This is a schematic diagram of another network information acquisition device provided in an embodiment of this application;

[0034] Figure 11 This is a schematic diagram of the structure of a computer system for an electronic device provided in an embodiment of this application. Detailed Implementation

[0035] It should be noted in advance that, in order to enable those skilled in the art to better understand the technical solutions proposed in the embodiments of this application, the embodiments of this application will be described clearly and completely in conjunction with one or more accompanying drawings. Furthermore, the various drawings shown in the embodiments of this application are merely illustrative examples; for example, the execution order of each step in the drawings can be adaptively adjusted according to the actual application scenario. In addition, in the embodiments of this application, the block diagrams shown in the various drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software, or in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0036] In this application embodiment, the terms "module" or "unit" refer to a computer program or part of a computer program that has a predetermined function and works with other related parts to achieve a predetermined goal, and can be implemented wholly or partially using software, hardware (such as processing circuitry or memory), or a combination thereof. Similarly, a processor (or multiple processors or memory) can be used to implement one or more modules or units. Furthermore, each module or unit can be part of an overall module or unit that includes the functionality of that module or unit.

[0037] It should be noted that "multiple" in this article refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone. The character " / " generally indicates that the preceding and following related objects have an "or" relationship.

[0038] With the development of mobile communication technology, the services performed by UEs have gradually shifted from voice calls to more complex and data-intensive services such as live video streaming, connected vehicles, and the Internet of Things. Network information is a crucial factor in these service execution and in the decision-making of UEs or other network devices, playing a vital role in the accuracy of service processing. In related technologies, network information is typically generated by analyzing data stored in the UE or application server to provide service processing for the UE or other network devices. However, this method suffers from relatively low accuracy and real-time performance of the network information, which may negatively impact service processing and user experience to some extent.

[0039] Based on this, this application provides a network information acquisition scheme. After receiving a request for network information, a network element in the core network retrieves information based on the indication information carried in the request and generates the required network information based on the retrieved related data. By having the core network elements retrieve relevant network data from a network database provided by numerous other network elements and generate network information, the accuracy of the network information is improved. Furthermore, by having the core network elements interact with other network elements to construct a network information database and perform retrieval within it to generate network information, the communication capabilities provided by the core network ensure efficient and rapid transmission, which helps improve the generation speed of network information and thus enhances its real-time performance.

[0040] To better understand the solutions of the embodiments of this application, the following is combined with... Figure 1 The relevant terms and concepts that may be involved in the embodiments of this application are introduced.

[0041] Please see Figure 1 , Figure 1 This is a schematic diagram of the architecture of a wireless communication system provided in an embodiment of this application. Figure 1 The 5G network architecture shown may include a UE, access network equipment, and core network equipment. The UE accesses the data network (DN) through the access network equipment and core network equipment. Specifically, the core network equipment involved in the embodiments of this application includes, for example... Figure 1Some or all of the following network elements are shown: Access and Mobility Management Function (AMF) network element, Session Management Function (SMF) network element, Policy Control Function (PCF) network element, User Plane Function (UPF) network element, Application Function (AF) network element, Network Exposure Function (NEF) network element, and Network Data Analytics Function (NWDAF) network element.

[0042] A DN (Network Node) can be used to deploy various services, providing data and / or voice services to terminal devices. It can also provide data services to users on IP Multimedia Service (IMS) networks, the Internet, etc. For example, a DN can be an enterprise's internal office network. Multiple application servers (AS) can be deployed within a DN to provide different application services, such as carrier services and Internet services.

[0043] In some embodiments, the core network equipment may further include Unified Data Repository (UDR) network elements, Unified Data Management (UDM) network elements, Network Repository Function (NRF) network elements, Location Management Function (LMF) network elements, etc. Figure 1 None are shown, and this application does not limit them.

[0044] The following describes the core network equipment involved in the embodiments of this application, namely the network functions (NFs) provided by the core network:

[0045] AMF network elements include functions such as performing mobility management and providing access authentication / authorization. They can be used to manage terminal access to the core network, such as terminal location updates, network registration, access (connection) control, reachability, terminal mobility management, and terminal attachment and detachment. They can provide session management message transmission channels for UE and SMF and are the core network control plane access points for terminals and radio.

[0046] SMF network elements include functions such as session management, execution of PCF-issued control policies, UPF selection, and Internet Protocol (IP) address allocation for terminal devices. They can be used for tunnel maintenance, selecting user plane network elements for terminals, redirecting user plane network elements for terminals, establishing bearers (also known as sessions) between terminals and UPF network elements, modifying and releasing sessions, as well as Quality of Service (QoS) control, billing data collection, roaming, etc.

[0047] PCF network elements include policy control functions such as billing at the session and service flow levels, QoS bandwidth guarantee and mobility management, and terminal device policy decisions. They can be used for a unified policy framework, providing policy rules for control plane functions. Specifically, they can be used to provide policies to AMF and SMF network elements, such as QoS policies and slice selection policies.

[0048] UPF network elements, serving as the interface with the data network, include functions such as user plane data forwarding, session / flow-level billing and statistics, and bandwidth limiting. They can be used for user data transmission, packet routing and forwarding, policy enforcement, traffic reporting, and QoS processing. UPF network elements can be referred to as user plane function network elements, while other network elements in the core network equipment can be referred to as control plane function network elements. These elements are used for authentication, authorization, registration management, session management, mobility management, and policy control to ensure reliable and stable data transmission.

[0049] Specifically, the UPF network element can receive service data from the DN and transmit it to the UE through the access network equipment; the UPF network element can also transmit data through the access network equipment (such as...) Figure 1 The radio access network (RAN) equipment receives user data from the UE and forwards it to the DN. The transmission resources allocated and scheduled by the UPF network element for the terminal are managed and controlled by the SMF network element. The bearer between the UE and the UPF network element can include: the user plane connection between the UPF network element and the RAN equipment, and the establishment of a channel between the RAN equipment and the terminal. The user plane connection enables the establishment of a QoS flow for data transmission between the UPF network element and the RAN equipment.

[0050] AF (Active Front-End) network elements are used to interact with core network elements, supporting application-influenced data routing, accessing network exposure functions, and interacting with PCF (Public Front-End) network elements for policy control. Specifically, they can be used to convey application-side requirements to the network side, such as QoS requirements or user state event subscriptions. AF network elements can implement control plane functions for third-party application servers, specifically through interaction via AF-NEF-PCF or AF-PCF. AF network elements can also act as AS (Application Server), implementing user plane functions for third-party application servers, specifically through interaction via AS-IP transport network-UPF.

[0051] The NEF (Network Element) is located between the 5G core network (5GC) and external third-party AF (Action Filter) or AS (Autonomous System) network elements, and is responsible for managing publicly accessible network data. In other words, external third-party applications need to go through the NEF to access data within the 5GC. The NEF can provide corresponding security guarantees to ensure the security of external applications accessing the 3rd Generation Partnership Project (3GPP) network, and can provide functions such as opening up QoS customization capabilities for external applications, subscription to mobility state events, and distribution of AF requests.

[0052] NWDAF (Network Data Analysis and Automated Support) network elements include functions that provide specific network data analysis services to the network. They can collect data, which may include one or more of the following: UE data, access network device data, core network data, and third-party application device data. This data can be data from the UE, access network device, core network element, or third-party application device itself, or it can be data from the UE on the access network device, core network element, or third-party application device. The NWDAF network element can perform data analysis based on the collected data and output the analysis results for use by the network, network management equipment, and applications in making policy decisions.

[0053] Specifically, NWDAF network elements can utilize machine learning models for data analysis. NWDAF network elements can be divided into training and inference function modules. An NWDAF network element supporting model training can be called an NWDAF supporting the Model Training Logic Function (MTLF), or it can be understood as an NWDAF network element including an MTLF function module. An NWDAF network element supporting model inference can be called an NWDAF supporting the Analysis Logic Function (ANLF), or it can be understood as an NWDAF network element including an ANLF function module. An NWDAF network element can integrate both MTLF and ANLF.

[0054] The ANLF can provide NWDAF service interfaces to external systems, such as the Nnwdaf_AnalyticsSubscription and Nnwdaf_AnalyticsInfo interfaces, which can generate static statistical data and / or dynamic inference results based on requests from consumer network elements. The MTLF can provide trained models to the ANLF; that is, the ANLF is a consumer network element for which the MTLF provides services. For example, the MTLF can train a model based on acquired data to obtain a trained model. Then, the ANLF can input input data into the trained model to obtain analysis results or inference data.

[0055] In some embodiments, an NWDAF network element may refer to a single network element or may be combined with other network elements, such as configuring an NWDAF into a PCF network element or an AMF network element.

[0056] Analytics Data Repository Functional (ADRF) network element ( Figure 1 (Not shown) can be used to store data related to NWDAF network elements, such as model-related data. In the embodiments of this application, the ADRF network element can store a network database. The network data in the network database can be collected by the NWDAF network element so that the NWDAF network element can retrieve and analyze it later. It can also be used to store the analysis results of the NWDAF network element.

[0057] in, Figure 1 The Nnef, Npcf, Namf, Nsmf, Naf, and Nnwdaf shown are the service interfaces provided by NEF, PCF, AMF, SMF, AF, and NWDAF, respectively, used to invoke the corresponding service operations. Specifically, N1, N2, N3, N4, and N6 are interface sequence numbers. N1 is the interface between the AMF network element and the UE; N2 is the interface between the AMF network element and the access network device; N3 is the interface between the access network device and the UPF network element; N4 is the interface between the SMF network element and the UPF network element; and N6 is the interface between the UPF network element and the DN. ANDR can provide the Nadrf interface, which can be used as a service interface for ADRF.

[0058] In some embodiments, there is an N5 interface between the AF network element and the PCF network element, an N7 interface between the PCF network element and the SMF network element, an N11 interface between the SMF network element and the AMF network element, an N15 interface between the PCF network element and the AMF network element, and an N23 interface between the PCF network element and the NWDAF network element, etc. Figure 1 None are shown.

[0059] It should be noted that the aforementioned network element or function can be a network component in a hardware device, a software function running on dedicated hardware, or a virtualization function instantiated on a platform (e.g., a cloud platform). In some embodiments, the aforementioned network element or function can be implemented by one device, multiple devices working together, or a functional module within a single device; this application does not limit this.

[0060] Please refer to the following: Figure 2 , Figure 2 This is a schematic diagram of an implementation environment provided in an embodiment of this application. For example... Figure 2 As shown, this exemplary implementation environment includes a core network (such as 5GC) 201, network devices 202, terminal devices 203, and application servers 204. The core network 201 may include core network devices. Figure 2 The AMF, SMF, PCF, NWDAF, and ADRF network elements are illustrated exemplarily. For a description of each network element, please refer to [link to relevant documentation]. Figure 1 The corresponding descriptions will not be repeated here. Among them, network device 202, terminal device 203, and application server 204 can all interact directly or indirectly with one or more core network devices in core network 201.

[0061] In this context, network device 202 can refer to an entity on the network side used for transmitting or receiving signals, such as a Generation Node B (gNB). Network devices can be devices used to communicate with mobile devices. Network devices can be access points (APs) in Wireless Local Area Networks (WLANs), base stations (BTSs) in Global System for Mobile Communications (GSM) or Code Division Multiple Access (CDMA), base stations (Nodeb, NBs) in Wideband Code Division Multiple Access (WCDMA), relay stations, access points, integrated access and backhaul (IABs), or network devices in vehicle-mounted devices, wearable devices, and future 5G networks, or network devices in future evolved Public Land Mobile Networks (PLMNs), or gnodebs in New Radio (NR) systems, etc.

[0062] Among them, terminal equipment 203 can refer to a device with wireless transceiver capabilities. It can also be referred to as terminal, UE, mobile station (MS), mobile terminal (MT), access terminal equipment, Internet of Things terminal equipment, vehicle-mounted terminal equipment, industrial control terminal equipment, UE unit, UE station, mobile station, remote station, remote terminal equipment, mobile device, UE terminal equipment, wireless communication equipment, UE agent, or UE device, etc. For example, terminal devices can be mobile phones, tablets, desktop computers, laptops, all-in-one computers, in-vehicle terminals, virtual reality (VR) terminal devices, augmented reality (AR) terminal devices, wireless terminals in industrial control, wireless terminals in self-driving, wireless terminals in remote medical surgery, wireless terminals in smart grids, wireless terminals in transportation safety, wireless terminals in smart cities, wireless terminals in smart homes, cellular phones, cordless phones, session initiation protocol (SIP) phones, wireless local loop (WLL) stations, personal digital assistants (PDAs), handheld devices with wireless communication capabilities, computing devices or other processing devices connected to a wireless modem, wearable devices, terminal devices in future mobile communication networks, or terminal devices in future evolved public land mobile networks (PLMNs), etc.

[0063] In some embodiments, the terminal device 203 may have an application (APP) installed. Here, the terminal device 203 may refer to the installed APP, or it may refer to an Internet Protocol (IP) camera, or one or more other terminal software.

[0064] Application server 204 can be an AS capable of providing third-party application services. For example, application server 204 can be a server providing background services for an app installed on terminal device 203. Application server 204 can interact with terminal device 203 to obtain data from terminal device 203. This data can be multimodal data, such as text data and image data. Application server 204 can also be an AF network element in core network 201; for details, please refer to [link to relevant documentation]. Figure 1 The relevant descriptions will not be repeated here.

[0065] In one possible implementation, the network information acquisition method provided in this application can be executed by core network equipment, such as the NWDAF network element and ADRF network element in core network 201. The general process is as follows:

[0066] Both terminal device 202 and application server 204 can send network information retrieval requests to core network 201. For example, terminal device 202 can send a network information retrieval request to NWDAF network element through UPF network element of core network 201, and application server 204 can send a network information retrieval request to NWDAF network element through NEF network element of core network 201. In response to the received network information retrieval request, the NWDAF network element in core network 201 can perform associated data retrieval based on the indication information carried in the network information retrieval request, obtain data retrieval results, and then generate network information corresponding to the network information retrieval request based on the data retrieval results. The network information can then be returned to terminal device 203 or application server 204. Specifically, the NWDAF network element can perform associated data retrieval by sending a retrieval request to ADRF network element in core network 201, so that ADRF network element performs associated data retrieval in its stored network database and returns the data retrieval results.

[0067] The ADRF network element in core network 201 can store a network database. This database is created and updated by the NWDAF network element in core network 201, which collects data from core network devices based on configured data collection rules. For example, if an NWDAF network element wants to collect data from network device 202, it can send a data collection request to network device 202 through the AMF network element to collect specific types of data associated with network device 202. Similarly, if an NWDAF network element wants to collect data from an application running on terminal device 203, it can send a data collection request to application server 204 through the NEF network element to collect data related to the application running on terminal device 203. The NWDAF network element can also send data collection requests to SMF and PCF network elements in core network 201 and receive specific types of data returned by the SMF and PCF network elements, such as session-related and policy-related data.

[0068] As can be seen from the above, in Figure 2 In the illustrated implementation environment, network information retrieval and the construction of the retrieved network database both take place within the core network. Leveraging 5G's ultra-high-speed data transmission and low-latency communication capabilities helps reduce the latency of building the network database, retrieval, and feedback of network information, thereby reducing the response time for network information retrieval requests and improving the real-time performance of business processing. Furthermore, generating network information after retrieving related data allows for the retrieval of relevant network data from multiple network elements, which helps improve the accuracy of network information and thus enhances the accuracy of business processing.

[0069] It is understood that the implementation environment described in the embodiments of this application is for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and does not constitute a limitation on the technical solutions provided in the embodiments of this application. As those skilled in the art will know, with the evolution of system architecture and the emergence of new business scenarios, the technical solutions provided in the embodiments of this application are also applicable to similar technical problems.

[0070] Based on the above implementation environment, this application embodiment provides a method for obtaining network information. This method for obtaining network information can be applied to... Figure 2 The devices in core network 201 shown can be, for example, devices configured as NWDAF network elements. Please refer to... Figure 3 , Figure 3 This is a flowchart illustrating a method for obtaining network information according to an embodiment of this application. The method for obtaining network information includes the following steps S301-S303:

[0071] S301. In response to the received network information acquisition request, perform associated data retrieval based on the indication information carried in the network information acquisition request, and obtain data retrieval results.

[0072] In this application embodiment, a network information acquisition request can refer to a request for obtaining network information, which is information in a specific format that can be parsed and responded to by network elements with network data analysis capabilities. Network information can refer to information reflecting network performance, such as information indicating the network status of the UE's location, which may include throughput, Reference Signal Receiving Power (RSRP), Received Signal Strength Indicator (RSSI), Reference Signal Received Quality (RSRQ), Signal-to-Interference & Noise Ratio (SINR), bit error rate, latency, etc., though this application does not limit this. Network information can also refer to data and information directly related to specific business or application scenarios, including user interaction data, business transaction data, content distribution data, etc. For example, in e-commerce application scenarios, network information may include user browsing history, purchase behavior, product reviews, etc. In video service application scenarios, network information may include viewing duration, video resolution, buffering time, etc. In intelligent driving scenarios, network information can include driving speed, acceleration, steering angle, environmental information collected by cameras and sensors, etc.

[0073] The device receiving network information acquisition requests can be a core network device, specifically a network element (device) in the core network configured with network data analysis capabilities. For ease of description, this network element configured with analysis capabilities will be referred to as a third core network element, such as an NWDAF network element. It should be noted that a third core network element can refer to an independently configured NWDAF network element, multiple NWDAF network elements, or other network elements in the core network. For example, if an NWDAF is configured within an AMF network element, then the third core network element can refer to the AMF network element.

[0074] In one implementation, the network information acquisition request received by the third core network element can originate from the UE. Specifically, a user can send a network information acquisition request through the UE to obtain past, current, or future network information. For example, a network information acquisition request can be used to obtain the network quality of a village 10 kilometers ahead, or to determine whether the current network supports remote driving.

[0075] In another implementation, the network information acquisition request received by the third core network element can originate from a certain NF, such as an AF element or an AS element. Specifically, in order to better provide relevant services to users, the AS can acquire network information related to the UE, and thus send a network information acquisition request. For example, the network information acquisition request can be used to determine whether the network latency in a certain area meets the requirements for live video streaming.

[0076] In some embodiments, a network information acquisition request may be an analysis request sent to a third core network element. This analysis request may be a one-time data query or analysis task initiated by a certain NF (such as an AF element) or UE to obtain certain specific data analysis results, which is suitable for scenarios where specific data analysis results are occasionally required.

[0077] In some embodiments, a network information acquisition request may be a subscription request sent to a third core network element. The subscription request may be a data query or analysis task with a subscription period initiated by a certain NF (such as an AF network element) or UE, in order to periodically or based on trigger conditions to obtain certain specific data analysis results. This is suitable for scenarios that require real-time monitoring or periodic reception of the latest data changes.

[0078] The network information acquisition request can carry indication information, which can be used to specify the specific network information that the UE or AF needs to acquire. For example, it could be a request for network information input by the sender of the request. For instance, the UE could have a smart customer service app related to communication services installed, where the user could input, "Check the network quality of the village 10 kilometers ahead?" The user's input is the indication information, and the UE can then generate a network information acquisition request based on this information and send it to the third core network element. As another example, the AF network element can query network information that might change service processing strategies. The AF network element can generate indication information based on the query content. For instance, if the AF network element is a control server in a remote driving scenario, it can generate indication information based on service information, such as, "Does the XXX area support real-time uploading of high-bitrate video by the vehicle terminal?" The AF network element can then generate a network information acquisition request based on this indication information and send it to the third core network element.

[0079] Specifically, related data retrieval refers to searching network data with a high degree of relevance to the indicated information in a network database. This network database can include data collected by third-party core network elements, specifically data from the UE (User Equipment), network devices (such as base stations), core network elements, and third-party application devices. A network database can be viewed as a knowledge base, integrating relevant external knowledge during the generation of network information to enhance its accuracy. The network data retrieved from this database constitutes the data retrieval result.

[0080] In one possible implementation, a third core network element can interact with a first core network element to perform associated data retrieval based on indication information. Specifically, the third core network element can extract the feature vector corresponding to the indication information and then send a retrieval request to the first core network element. The retrieval request carries the feature vector corresponding to the indication information and instructs the first core network element to calculate the matching degree between the feature vector corresponding to the indication information and the feature vectors of various categories of information stored in the network database of the first core network element. Afterward, the third core network element can receive the data retrieval results sent by the first core network element. The matching degree between the feature vectors corresponding to the category information of the network data in the data retrieval results and the feature vectors corresponding to the indication information is greater than or equal to a set matching degree threshold.

[0081] Correspondingly, the first core network element can receive a retrieval request sent by the third core network element, perform a related data retrieval on the indication information in the stored network database, and obtain the data retrieval results. The network information acquisition request received by the third core network element carries the indication information. This retrieval request is generated by the third core network element after receiving the network information acquisition request, and it carries the feature vector corresponding to the indication information extracted by the third core network element. The first core network element can then calculate the matching degree between the feature vector corresponding to the indication information and the feature vectors of various categories of information in the network database, and then select network data under the category information with a matching degree greater than a set matching degree threshold to obtain the data retrieval results. Afterwards, the first core network element can send the data retrieval results to the third core network element.

[0082] In this interaction process, the feature vector corresponding to the instruction information can refer to the representation of the instruction information converted into a feature vector. For example, if the instruction information is text information, the corresponding feature vector can refer to the vector matrix obtained by converting the text information. It can be a data format that the first core network element can understand, or it can refer to a data format that the network database stored by the first core network element can understand. The third core network element can call a vectorization model to convert the instruction information into the form of a feature vector. This vectorization model can be an embedding model, used to convert high-dimensional data into a low-dimensional embedding (vector) space while maintaining the original data features and semantic information. The first core network element can refer to a network element in the core network that is configured with data storage function, such as an ADRF network element. Specifically, it can refer to an independently configured ADRF network element, or it can refer to other network elements in the core network that are configured with ADRF.

[0083] The retrieval request can be information in a specific format, which can be parsed by network elements with data storage capabilities (such as the first core network element). Alternatively, it can be information in a specific format generated by the third core network element based on the feature vector after extracting the corresponding feature vector. For example, it could be information obtained by combining the specific method of instructing the first core network element to perform the retrieval with the feature vector. This retrieval request can be used to instruct the first core network element to perform retrieval processing.

[0084] In some embodiments, network data in the network database stored in the first core network element can be divided into multiple categories, each corresponding to a category information. For example, the category information may include information indicating the data type of the network data, such as (RSRP, RSSI, RSRQ). The network data under this category information could be the RSRP, RSSI, and RSRQ data of the UE in a certain area at different times. In other words, the network database can store feature vectors for each category of information. These feature vectors can be used to calculate the matching degree between the feature vectors and the indication information, thereby generating network information from the network data most relevant to the indication information.

[0085] The matching degree between the feature vector corresponding to the indication information and the feature vectors of each category can refer to the similarity between vectors, such as the cosine similarity between vectors. The data retrieval results include retrieved network data, which can be network data from multiple categories. The vector matching degree between the category information of each category to which the network data belongs and the indication information is greater than a set matching degree threshold. When the matching degree is similarity, the set matching degree threshold can refer to a predefined similarity threshold. In other words, the third core network element can instruct the first core network element to perform a search in its stored network database through a retrieval request, obtain the similarity between the feature vector corresponding to the indication information and the feature vectors of each category, sort them in descending order of similarity, select network data from at least one category with a similarity greater than or equal to the set similarity threshold as the data retrieval result, and return the data retrieval result.

[0086] In some embodiments, a first core network element may send all network data under category information with a similarity greater than a set similarity threshold as data retrieval results to a third core network element. Alternatively, the first core network element may select a portion of the network data under the category information as data retrieval results and send it to the third core network element. For example, if only one category information has a similarity greater than a set similarity threshold, the first core network element may select a specified number of network data under that category information as data retrieval results.

[0087] Optionally, the first core network element can obtain the time information of the network data under this category of information. This time information may include the collection time, generation time, etc. Then, the first core network element can select the network data collected or generated within a set time period as the data retrieval result, such as selecting the network data collected in the most recent week. The selection method of the first core network element can be configured or indicated by the third core network element in the retrieval request. This application does not limit this method.

[0088] Furthermore, after the third core network element receives the data retrieval results returned by the first core network element in response to the retrieval request, it can generate network information corresponding to the network information acquisition request based on the data retrieval results, and return the generated network information to the sender of the network information acquisition request, so that the sender of the network information acquisition request can make business processing strategy decisions based on the network information.

[0089] In one possible implementation, the third core network element can optimize the indication information during the extraction of the feature vector corresponding to the indication information. This is equivalent to filtering the data to be retrieved, removing irrelevant information, and improving the relevance between the data to be retrieved and the category information in the network database, thereby improving retrieval efficiency and accuracy. Specifically, the third core network element can use two different optimization methods to rewrite the indication information and then extract the rewritten feature vector as the feature vector corresponding to that indication information.

[0090] In one implementation, during the extraction of feature vectors corresponding to indication information, the third core network element can extract keywords from the indication information and filter them according to configured filtering rules to obtain filtered keywords. Then, a keyword rewriting model is invoked to rewrite the filtered keywords, resulting in rewritten target keywords. These target keywords match at least one category of information in the network database. Finally, the third core network element can call a vectorization model to extract feature vectors from the target keywords, thus obtaining the feature vectors corresponding to the indication information.

[0091] The keywords in the instruction information can refer to words with specific meanings and functions, such as nouns. Filtering rules can be used to delete some of the extracted keywords. These rules can include rules indicating parts of speech, or lists of deleted keywords, etc., which are not limited in this application. For example, if the instruction information is "Check the network quality of the village 10 kilometers ahead?", the extracted keywords are "10 kilometers", "village", and "network quality". The filtering rules can be used to filter out "village", which has relatively little help in the search, resulting in the filtered keywords "10 kilometers" and "network quality".

[0092] The keyword rewriting model refers to a machine learning model used to optimize keywords. It can be a Large Language Model (LLM) that converts words into words that match at least one category of information in a network database. In other words, it rewrites words to be closer to the category information in the network database, or rewrites them into words contained within the category information. Specifically, the ANLF in the third core network element can call the model to perform corresponding tasks, such as inputting filtered keywords into the keyword rewriting model to rewrite them and obtain the target keywords output by the model. For example, if the ANLF in the third core network element inputs "10 km" and "network quality" into the keyword rewriting model, the resulting target keywords could be "xxx region," "throughput," "stability," "latency," "RSRP," "RSSI," "RSRQ," etc.

[0093] Furthermore, the ANLF in the third core network element can input the target keywords into the vectorization model, convert the target keywords into feature vectors through the vectorization model, and use them as the feature vectors corresponding to the indication information for subsequent retrieval.

[0094] In another implementation, during the extraction of the feature vector corresponding to the indication information, the third core network element can invoke an indication information rewriting model to rewrite the indication information, obtaining the rewritten target indication information. This target indication information matches at least one category of information in the network database. Subsequently, the third core network element can invoke a vectorization model to extract the feature vector of the target indication information, thus obtaining the feature vector corresponding to the indication information.

[0095] Similar to the previous implementation type, the instruction information rewriting model can refer to a machine learning model used to optimize instruction information. It can also be an LLM (Limited Learning Model) that converts the text content of the instruction information into text content that matches at least one category of information in the network database. This instruction information rewriting model can rewrite the instruction information to be closer to the content of the category information in the network database, or it can rewrite the instruction information to include parts of the category information. Specifically, the ANLF (Application Not Responding) element in the third core network can input the instruction information into the instruction information rewriting model to call the model to rewrite the instruction information, obtaining the rewritten result output by the model, i.e., the target instruction information. For example, if the instruction information is "Check the network quality of the village 10 kilometers ahead?", the rewritten target instruction information would be "What are the network latency, network throughput, and RSRP of region xxx within the time period XX?".

[0096] Furthermore, the ANLF in the third core network element can input the target indication information into the vectorization model. The vectorization model converts the target indication information into a feature vector, which is then sent to the first core network element for retrieval, yielding data retrieval results. It is evident that in both implementation methods, the target keywords or target indication information have a higher degree of matching with the category information in the network database compared to the indication information carried in the network information retrieval request, thereby improving the relevance of the retrieved content.

[0097] S302. Generate the network information corresponding to the above network information acquisition request based on the above data retrieval results.

[0098] In this embodiment, the third core network element can generate the network information indicated by the instruction information in the network information acquisition request based on the network data returned by the first core network element. The network information can be the result obtained by the third core network element through analysis of the network data in the data retrieval results.

[0099] For example, the instruction information might be "Can the XXX area support real-time uploading of high-bitrate video by vehicle-mounted terminals?". The network data included in the data retrieval results received by the third core network element could be, for example, data on the throughput, latency, packet loss rate, RSRP, and RSRQ of the XXX area over the past week. The network information generated by the third core network element based on the data retrieval results could be: "The XXX area can support real-time uploading of high-bitrate video by vehicle-mounted terminals. Based on average data, the uplink throughput is 50Mbps, the network latency is 20 milliseconds, the packet loss rate is less than 0.1%, and the RSRQ is..." P is -85dBm and RSRQ is -10dB, both meeting the requirements for high bitrate video uploads. For example, network information generated by the third core network element based on data retrieval results could be: "The network performance in the XXX area is currently unable to fully support real-time uploading of high bitrate video by the vehicle terminal. Based on average data, the uplink throughput is 20Mbps, network latency is 80 milliseconds, packet loss rate is 1%, RSRP is -100dBm, and RSRQ is -13dB. The following optimization measures are recommended: increase base station density to improve signal coverage, and perform video uploads during off-peak hours."

[0100] In one possible implementation, during the process of generating network information based on data retrieval results, the third core network element can specifically generate prompt words based on configured generation rules and data retrieval results. These prompt words are then input into a large language model (LLM), enabling the LLM to generate network information based on the generation rules and data retrieval results. The generation rules can be rules instructing the LLM to generate network information; they can be pre-configured or generated by the third core network element, and this application does not limit this. A prompt word (Prompt) refers to natural language text input into the LLM to complete the task of generating network information. In this embodiment, the task of generating network information can include two parts: one part is the task of analyzing the data retrieval results based on the prompt information, and the other part is the task of generating network information based on the analyzed data.

[0101] It should be noted that the process by which the third core network element enhances the LLM's generation of network information by retrieving relevant information can refer to the third core network element adopting a retrieval-augmented generation (RAG) hybrid model architecture. This architecture combines two artificial intelligence (AI) technologies: retrieval and generation. By integrating relevant external knowledge during the text generation process, it assists the LLM in generating text content. This allows the LLM to utilize information from the latest or specific domain knowledge bases, enabling it to generate more up-to-date or specific domain text content without retraining the model, thereby improving the quality and accuracy of text generation.

[0102] Specifically, during the process of generating prompt words based on the configured generation rules and data retrieval results, the third core network element can obtain a prompt word template. This prompt word template can include the configured generation rules. The third core network element can fill the prompt word template with the data retrieval results to obtain the generated prompt words. Then, through the ANLF in the third core network element, the generated prompt words are input into the LLM to obtain the network information output by the LLM based on the generation rules in the prompt words and the data retrieval results.

[0103] In some embodiments, the third core network element can generate the prompt word based on generation rules, data retrieval results, and other information. The prompt word template may also include other slots, such as slots for network data type information and network information examples from the data retrieval results. The third core network element can obtain the information corresponding to each slot in the prompt word template and fill it into the slots to obtain the generated prompt word.

[0104] Table 1 is an example of a prompt word template provided in the embodiments of this application.

[0105] Table 1

[0106]

[0107]

[0108] As shown in Table 1, the prompts for the LLM can be written according to the technical concept of the thought chain. They can be used to guide the LLM's thinking process, thereby enhancing the model's logical reasoning ability and generating more accurate network information. The "#requirements" part can be a configured generation rule. At the end of Table 1, multiple slots for filling can be included. It is understood that Table 1 is only an example, and other slots may also be included; this application embodiment does not limit this.

[0109] Please refer to the following: Figure 4 , Figure 4 This is a schematic diagram illustrating the interaction between a third core network element and a first core network element, as provided in an embodiment of this application. Figure 4 As shown in the illustration, this application uses the third core network element as the NWDAF network element and the first core network element as the ADRF network element as an example for explanation. The third core network element can receive network information acquisition requests from a certain NF (from 5GC NF) or UE in the 5GC, which can be an analytics request or a subscription request. A vectorized model (containing an embedding model) can be deployed in the third core network element, which can be used to generate corresponding feature vectors based on the indications carried in the network information acquisition request. Then, it can search relevant knowledge databases, such as sending a search request to the first core network element to search the network database stored in the first core network element. Furthermore, the third core network element can receive the data retrieval results returned by the first core network element, which are network data with a high degree of matching (similarity) with the indication information. Therefore, the third core network element can generate network information based on the received network data.

[0110] S303. Return the aforementioned network information to the sender of the aforementioned network information acquisition request.

[0111] In this embodiment, after generating network information, the third core network element can return it to the sender of the network information acquisition request, such as the UE mentioned in S301 or a certain NF (such as the AF network element, i.e., AS). The specific return path can be the same as the sending path. For example, if the AF network element (AS) sends the network information acquisition request to the third core network element through the NEF network element, then the third core network element can send the network information to the AF network element through the NEF network element. As another example, if the UE sends the network information acquisition request to the third core network element through the UPF network element, then the third core network element can send the network information to the UE through the UPF network element.

[0112] Please refer to the following: Figure 5 , Figure 5 This is a timing diagram illustrating a network information acquisition method provided in an embodiment of this application. Figure 5 Steps 1-8 illustrate the timing of the UE initiating a network information retrieval request, while steps 9-16 illustrate the timing of the AF (Autonomous AF) network element (AS) initiating the same request. Specifically, the UE can send a network information retrieval request to the NWDAF network element via the UPF network element, and the AF network element can send the same request via the NEF network element, as shown in steps 1-2 and 9-10, respectively. After receiving the network information retrieval request, the NWDAF network element's response process may include, for example, 3. sending a retrieval request to the ADRF network element, which instructs the ADRF network element to perform a retrieval and return the data retrieval results; 5. receiving the data retrieval results sent by the ADRF; and 6. generating network information based on the data retrieval results. Steps 11-14 are the same as steps 3-6 and will not be repeated here. Furthermore, the NWDAF network element can return the network information to the UE or the AF network element, for example, in steps 7-8, the NWDAF network element returns the network information to the UE via the UPF network element. For example, in steps 15-16, the NWDAF network element returns network information to the AF network element (AS) through the NEF network element.

[0113] Furthermore, the sender of a network data acquisition request can make decisions and update business processing strategies based on network information. For example, in an intelligent driving scenario, network information can indicate that the area 10 kilometers ahead cannot support real-time uploading of high-bitrate video. The vehicle terminal can then reduce the transmitted video bitrate, or notify the driver that the network quality ahead does not support autonomous driving, suggesting switching to manual driving or pulling over.

[0114] In some embodiments of this application, the core network elements generate network information by retrieving associated data of indication information. Deploying RAG technology on the core network side enhances the core network's decision-making capabilities and improves the accuracy of generated network information, thereby improving the accuracy of service processing and, to a certain extent, promoting the development and innovation of intelligent applications. Furthermore, by interacting with core network elements to retrieve and generate network information, the high-speed, low-latency data transmission capabilities and efficient information processing capabilities provided by the core network can be combined, which helps improve the real-time performance of network information, enhances the real-time performance of service processing, and improves user experience.

[0115] This application also provides a method for obtaining network information, which can be applied to... Figure 2 The devices in the core network 201 shown can be, for example, devices configured as NWDAF network elements. Figure 3 The corresponding embodiment describes the generation of the network database. Please refer to [link / reference]. Figure 6 , Figure 6 This is another schematic flowchart of a method for obtaining network information provided in an embodiment of this application. The method for obtaining network information includes the following steps S601-S602:

[0116] S601. Based on the configured data collection rules, send a data collection request to the second core network element.

[0117] In this embodiment, the data collection rule can be a rule that instructs the collection of different types of network data from different network elements in the core network. For example, it may include the device identifier, communication method, and type of network data being collected, all configured with a second core network element. The second core network element can refer to the NF network element used for collecting network data in the core network, as recorded in the data collection rule, such as SMF, PCF, and AMF network elements. It should be noted that the second core network element can refer to multiple network elements of the same type in the core network, such as multiple AMF network elements in the core network.

[0118] Specifically, a data collection request can be information in a specific format that can be parsed by the second core network element. This request can instruct the second core network element to return a specific type of network data. Network data can refer to one or more of the following: UE data, core network element data, and data from third-party application devices. The specific type is related to the second core network element because the sender of the data collection request may not be able to communicate directly with the data source to be collected, and therefore needs to relay the request through the second core network element. The data type of network data from different data sources is the specific type associated with the second core network element. Specific types can include, for example, throughput, RSRP, RSSI, RSRQ, and cell identifier (ID). Optionally, the network data can be further categorized based on its data source. For example, network data of types RSRP, RSSI, and RSRQ can be further divided into RSRP, RSSI, and RSRQ types on the UE side and RSRP, RSSI, and RSRQ types on the base station side.

[0119] The sender of the data collection request can be a core network device, specifically a network element (device) in the core network configured with network data analysis capabilities. For ease of description, this network element will be referred to as a third core network element, such as an NWDAF network element. It should be noted that a third core network element can refer to an independently configured NWDAF network element, multiple NWDAF network elements, or other network elements in the core network. For example, if NWDAF is configured within an AMF network element, then the third core network element can refer to the AMF network element.

[0120] In one implementation, data collection rules can instruct a third core network element to collect network data reflecting network performance, such as throughput, RSRP, RSSI, RSRQ, and cell ID, from the base station. The third core network element can collect data based on at least one second core network element (such as an AMF element) communicating with the base station. Specifically, the third core network element can generate a data collection request based on one or more of the following: data type (e.g., throughput, RSRP, RSSI), data collection time range, and base station identifier, and send this request to the AMF element to instruct it to collect network data of the type indicated by the request. The AMF element can then send the data collection request to the base station and receive the network data returned by the base station.

[0121] In another implementation, data collection rules can also instruct the third core network element to collect network data reflecting network performance from the AS, such as RSRP, RSSI, RSRQ, and the accessed cell ID from the UE side, as well as data stored in the AS, such as user interaction data. The third core network element can collect data based on the second core network element (such as the NEF element) of the AS communication to be collected. Specifically, the third core network element can generate a data collection request based on data type (such as specific service data, RSRP, RSSI, RSRQ measured by the UE, etc.), the time range of data collection, etc., and send the data collection request to the NEF element to instruct the NEF element to collect network data of the type indicated in the data collection request. The NEF element can then send the data collection request to the indicated AS and receive the network data returned by the AS.

[0122] In some embodiments, the data source for UE-level network data can also be a second core network element in the core network, such as an SMF element or a PCF element. For example, a third core network element can collect network data such as session latency and session interruption rate from an SMF element; similarly, a third core network element can collect network data such as network slicing policies and QoS policies from a PCF element. Specifically, the third core network element can generate data collection requests for different network elements (such as SMF and PCF elements) based on data type and data collection time range, and send these requests to the SMF and PCF elements respectively, instructing them to collect specific types of network data, which are then returned to the third core network element.

[0123] It is understood that the data types collected from different network elements as indicated in the above data collection rules are merely examples and are not limited to them. They may change based on the evolution of the system architecture and the emergence of new business scenarios.

[0124] S602. If network data is received from the second core network element in response to the data collection request, the network data is stored in the first core network element.

[0125] In this embodiment, if the second core network element (such as an AMF element or NEF element) is not a data source, network data from a data source (such as an AS or base station) can be returned to the third core network element. If the second core network element (such as an SMF element or PCF element) is a data source, it can return the network data it has collected to the third core network element. The third core network element can construct a network database based on the collected network data to facilitate the retrieval of relevant network data during the subsequent generation of network information. The first core network element can refer to a network element in the core network configured with data storage capabilities, such as an ADRF element. Specifically, it can refer to an independently configured ADRF element, or other network elements in the core network configured with ADRF.

[0126] In one possible implementation, the third core network element can first preprocess the collected network data, and then store the preprocessed network data in the first core network element to construct a network database within the first core network element. Specifically, the third core network element can extract the data type of each network data point and segment the network data according to the data type indicated by the network information acquisition requirements, obtaining network data under at least two segmentation categories. Furthermore, the third core network element can generate category information for each segmentation category based on the network information acquisition requirements, and call a vectorization model to extract feature vectors for each category. Finally, the feature vectors of each category, along with the network data under each segmentation category, are stored in the first core network element.

[0127] In some embodiments, the network data collected by the third core network element includes network data from the AS related to UE service scenarios or application scenarios, which involves multimodal data such as text data, image data, audio data, and video data. The third core network element can use its modal type as a data type, or it can convert it into text information, for example, extracting text information from an image and determining the data type corresponding to the text information.

[0128] In this context, network information acquisition needs refer to the specific task requirements executed by the network information generated by the third core network elements. This can be understood as the query type of the instruction information carried in the network information acquisition request, such as predicting the future network latency of a certain area, querying the throughput of a certain area, comparing historical data with current data, whether it supports a specific load, whether it will be affected by environmental factors (such as special weather), trajectory prediction, etc. It is understood that the network data analyzed by the third core network elements for different network information acquisition needs can be different. The third core network elements can segment the collected network data according to the data type indicated by the network information acquisition need, that is, divide it into network data under multiple segmentation categories. The network data under each segmentation category can be of multiple data types.

[0129] Furthermore, the third core network element can generate category information for each segmentation category based on network information acquisition requirements. This category information may include the network information acquisition requirements, the data type of network data under that segmentation category, and other content. Specifically, the third core network element can acquire instruction information examples associated with the network information acquisition requirements, and generate category information for each segmentation category based on the network information acquisition requirements, the instruction information examples associated with the network information acquisition requirements, and at least one of the data types of network data under at least two segmentation categories. The instruction information examples can be manually constructed query examples corresponding to the aforementioned network information acquisition requirements, such as "Does the network latency in the area ahead meet the requirements for autonomous driving?".

[0130] Therefore, third core network elements can generate category information for each segmentation based on one or more of the network information acquisition requirements, instruction information examples, and data types. For example, a third core network element can directly use the network information acquisition requirement information, instruction information examples, and data types as the category information for a segmentation, such as the category information being the prediction of future network latency in a certain area (network information acquisition requirement). Another example is the category information being whether the network latency in the area ahead meets the requirements of autonomous driving, or what the network latency in area XXX is (instruction information example). Yet another example is the category information being session latency, wireless interface latency, etc. (data types). Third core network elements can combine one or more of these pieces of information according to their configuration to obtain the category information for each segmentation.

[0131] Optionally, after the third core network elements are combined, key information of the combined information can be extracted and used as category information for each segmentation category.

[0132] In some embodiments, before extracting the data type of network data, the third core network element can perform data cleaning on the collected network data and extract the data type of each cleaned network data. Data cleaning may include data format conversion, such as converting all network data to a uniform format or a format that the third core network element can understand. The third core network element can also remove unrecognizable network data and can perform data formatting processes such as sorting (e.g., sorting by network data generation time, collection time, etc.) and compression according to a configured method. This application does not limit the method of data cleaning.

[0133] Furthermore, the ANLF in the third core network element can call a vectorization model to extract feature vectors for each category of information, that is, to convert the information of each category into a vector matrix. This vectorization model can be an embedding model deployed in the third core network element, or it can be trained using the MTLF in the third core network element. It is understandable that, since the retrieval process compares the matching degree between feature vectors, the quality of the vectorization model used to extract feature vectors directly affects the quality of subsequent retrievals, especially the relevance of the retrieved network data.

[0134] Furthermore, the third core network element can store the network data used to construct the network database, as well as the category information of each segmentation, in the first core network element, so that subsequent retrieval can be performed based on the matching degree between the feature vector corresponding to the indicator information to be retrieved and the feature vector of the category information. If the matching degree between the feature vector corresponding to the indicator information and the feature vector of a certain category information is greater than a set matching degree threshold, then the network data indexed to that segmentation category is used to generate network information.

[0135] In one possible implementation, a third core network element can interact with a first core network element to send data that needs to be stored to the first core network element. Specifically, the third core network element can send a data storage request to the first core network element. This data storage request can be information notifying the first core network element that data storage is required, and it can be generated by the third core network element after receiving network data sent by a second core network element. It may include information indicating the data to be stored. Furthermore, after receiving the data storage request, the first core network element can confirm the storage by sending confirmation information to the third core network element.

[0136] Subsequently, upon receiving the storage confirmation information from the first core network element, the third core network element sends the extracted feature vectors of each category of information, as well as the network data under each segmentation category, to the first core network element. After receiving the feature vectors of each category of information and the network data under each segmentation category from the third core network element in response to the storage confirmation information, the first core network element can perform storage processing, such as storing the feature vectors of each category of information and the network data under each segmentation category (category information) in the network database. This completes the construction of the knowledge base. Optionally, the first core network element can return a notification message to the third core network element indicating that the network database construction is complete.

[0137] In some embodiments, the third core network element may periodically collect network data, determine the segmentation category to which the collected network data belongs, and periodically store the latest network data under each segmentation category in the first core network element.

[0138] Please refer to the following: Figure 7 , Figure 7 This is another interactive diagram of a third core network element and a first core network element provided in an embodiment of this application, such as... Figure 7 As shown in the illustration, this application uses the third core network element as an NWDAF element, the first core network element as an ADRF element, and the second core network element as an NF element in the core network as an example for explanation. The third core network element can collect network data from the second core network element in the 5GC. The third core network element can then segment the collected data to obtain network data under multiple segmentation categories. Afterwards, the third core network element can extract the feature vectors of the category information corresponding to each segmentation category through the deployed vectorized model (Containing Embedding Model), and store the extracted feature vectors of the category information and the network data under each segmentation category in the first core network element (Embedding to Vector and stored in ADRF). Once the feature vectors of each category information and the network data are stored in the first core network element, the network database construction is complete.

[0139] Please refer to the following: Figure 8 , Figure 8 This is another timing diagram of a network information acquisition method provided in an embodiment of this application, such as... Figure 8 As shown, 1. The NWDAF network element can generate data collection requests to be sent to different NF network elements, and then send them to different NF network elements. For example, in steps 2-5, the NWDAF network element sends the data collection requests to the SMF network element, PCF network element, AMF network element, and NEF network element respectively. Steps 2-5 can be performed simultaneously or in a specific order; this application does not limit this. Furthermore, 6. The AMF network element can forward the data collection request to the base station; 7. The NEF network element can forward the data collection request to the AF network element (AS); 8. The AMF network element can receive the network data returned by the base station in response to the data collection request; 9. The NEF network element can receive the network data returned by the AF network element (AS) in response to the data collection request. Thus, different NF network elements can return network data to the NWDAF network element, as shown in steps 10-13. The timing of steps 10-13 is only an example; this application does not limit the order in which different NF network elements return network data.

[0140] Further, 14. The NWDAF network element can send a data storage request to the ADRF network element, and 15. The ADRF network element can return storage confirmation information to the NWDAF network element. 16. The NWDAF network element can segment the collected network data according to network information acquisition requirements and generate category information for different segmentation categories. Then, 17. The NWDAF network element can extract feature vectors of the category information for each segmentation category. 18. The NWDAF network element sends the extracted feature vectors and network data under each segmentation category to the ADRF network element, so that 19. the ADRF network element stores the feature vectors of the category information and the network data under each segmentation category. After storage is completed, 20. The ADRF network element can return a notification message indicating that the NWDAF network element network database construction is complete. Steps 14 and 15 can be executed after steps 16 and 17, or after 16 and before 17; this application does not limit this.

[0141] In some embodiments of this application, a network database is constructed using core network elements to retrieve relevant network data and generate network information. RAG technology is deployed on the core network side, leveraging the high-speed data transmission capabilities provided by the core network to accelerate the construction and retrieval of the network database, thereby improving the timeliness of network information generation. Furthermore, utilizing the low-latency communication capabilities provided by the core network shortens the time required for network database construction and data retrieval, further reducing the time needed to generate network information. This, to a certain extent, ensures the generation of timely and accurate network information for decision-making, thereby improving the accuracy of business processing and user experience.

[0142] The methods of the embodiments of this application have been described in detail above. In order to facilitate better implementation of the above solutions of the embodiments of this application, the apparatus of the embodiments of this application is provided below.

[0143] Please see Figure 9 , Figure 9 This is a schematic diagram of the structure of a network information acquisition device provided in an embodiment of this application. Figure 9 The network information acquisition device shown can be used to perform the above. Figure 3 Some or all of the functionality described in the method embodiments. Please refer to [link / reference]. Figure 9 The network information acquisition device 90 includes:

[0144] The retrieval unit 901 is used to respond to a received network information acquisition request, perform associated data retrieval based on the indication information carried in the network information acquisition request, and obtain data retrieval results;

[0145] The generation unit 902 is used to generate network information corresponding to the network information acquisition request based on the data retrieval results;

[0146] The sending unit 903 is used to return the network information to the sender of the network information acquisition request.

[0147] In some embodiments, the retrieval unit 901 is configured to perform associated data retrieval based on the indication information carried in the network information acquisition request, and obtain data retrieval results, specifically for:

[0148] Extract the feature vector corresponding to the indication information;

[0149] A retrieval request is sent to the first core network element. The retrieval request carries a feature vector corresponding to the indication information. The retrieval request is used to instruct the first core network element to calculate the matching degree between the feature vector corresponding to the indication information and the feature vectors of each category of information stored in the network database of the first core network element.

[0150] The system receives data retrieval results sent by the first core network element, wherein the matching degree between the feature vector corresponding to the category information of the network data contained in the data retrieval results and the feature vector corresponding to the indication information is greater than or equal to a set matching degree threshold.

[0151] In some embodiments, the retrieval unit 901 is used to extract the feature vector corresponding to the indication information, specifically for:

[0152] Extract keywords from the instruction information and filter the keywords according to the configured filtering rules to obtain filtered keywords;

[0153] The filtered keywords are rewritten using a keyword rewriting model to obtain rewritten target keywords, wherein the target keywords have matching information with at least one category of information in the network database.

[0154] The feature vector of the target keyword is extracted by calling a vectorization model, and the feature vector corresponding to the indication information is obtained.

[0155] In some embodiments, the retrieval unit 901 is used to extract the feature vector corresponding to the indication information, specifically for:

[0156] The instruction information is rewritten by calling the instruction information rewriting model to obtain the rewritten target instruction information, and the target instruction information has matching information with at least one category information in the network database;

[0157] The feature vector of the target indication information is extracted by calling the vectorization model, and the feature vector corresponding to the indication information is obtained.

[0158] In some embodiments, the generation unit 902 is used to generate network information corresponding to the network information acquisition request based on the data retrieval results, specifically for:

[0159] Prompt words are generated based on the configured generation rules and the data retrieval results;

[0160] The prompt words are input into a large language model, so that the large language model generates the network information based on the generation rules and the data retrieval results.

[0161] In some embodiments, the sending unit 903 is further configured to send a data collection request to a second core network element based on configured data collection rules, the data collection request being used to instruct the second core network element to collect a specific type of network data;

[0162] Storage unit 904 is used to store network data in the first core network element if it receives network data returned by the second core network element in response to the data collection request.

[0163] In some embodiments, the storage unit 904 is used to store the network data in the first core network element, specifically for:

[0164] Extract the data types of each network data, and segment the network data according to the data types indicated by the network information acquisition requirements to obtain network data under at least two segmentation categories;

[0165] Based on the network information acquisition requirements, category information for each segmentation category is generated, and a vectorization model is called to extract feature vectors for each category.

[0166] The feature vectors of each category of information, as well as the network data under each segmentation category, are stored in the first core network element.

[0167] In some embodiments, the storage unit 904 is used to generate category information for each segmentation based on the network information acquisition requirements, specifically for:

[0168] Obtain an example of indication information associated with the network information acquisition request;

[0169] Based on the network information acquisition requirement, the example of the indication information associated with the network information acquisition requirement, and at least one of the data types of the network data under the at least two segmentation categories, the category information of each segmentation category is generated.

[0170] In some embodiments, the sending unit 903 is further configured to send a data storage request to the first core network element; if it receives a storage confirmation message from the first core network element, it sends the feature vectors of each category of information and the network data under each segmentation category to the first core network element so that the first core network element performs storage processing.

[0171] According to one embodiment of this application, Figure 3 The steps involved in the method shown can be from Figure 9 This is performed by each unit in the network information acquisition device shown. For example, Figure 3 The step S301 shown is by Figure 9 The retrieval unit 901 shown is used to perform the retrieval, and step S302 is performed by... Figure 9 The generation unit 902 shown is used to execute step S303. Figure 9 The sending unit 902 shown is used to perform this operation.

[0172] According to one embodiment of this application, Figure 9 The network information acquisition device 90 shown can be composed of various units, either individually or entirely, into one or more other units. Alternatively, some units can be further divided into functionally smaller units. This achieves the same operation without affecting the technical effects of the embodiments of this application. The units are based on logical function division. In practical applications, the function of one unit can be implemented by multiple units, or the function of multiple units can be implemented by one unit. In other embodiments of this application, the network information acquisition device 90 can also include other units. In practical applications, these functions can be implemented with the assistance of other units, and can be implemented collaboratively by multiple units. According to another embodiment of this application, a general-purpose computing device capable of performing functions such as processing elements (e.g., central processing unit (CPU), random access memory (RAM), read-only memory (ROM)) and storage elements can be run on a general-purpose computer. Figure 3 The computer program (including program code) for each step involved in the corresponding method shown, to construct such... Figure 9 The network information acquisition device 90 shown herein, and the network information acquisition method for implementing the embodiments of this application, are described. The computer program may be recorded on, for example, a computer-readable storage medium, and loaded onto, via the computer-readable storage medium. Figure 2 The NWDAF network element in core network 201 of the implementation environment is shown, and it runs in the environment.

[0173] Please see Figure 10 , Figure 10 This is a schematic diagram of the structure of a network information acquisition device provided in an embodiment of this application. Figure 10The network information acquisition device shown can be used to perform the above. Figure 6 Some or all of the functionality described in the method embodiments. Please refer to [link / reference]. Figure 10 The network information acquisition device 100 includes:

[0174] The receiving unit 1001 is used to receive a retrieval request sent by a third core network element, perform associated data retrieval on the indication information in the stored network database, and obtain data retrieval results; the retrieval request is generated by the third core network element after receiving the network information acquisition request, and the network information acquisition request carries the indication information;

[0175] The sending unit 1002 is used to send the data retrieval result to the third core network element. The data retrieval result is used to instruct the third core network element to generate network information corresponding to the network information acquisition request and return the network information to the sender of the network information acquisition request.

[0176] In some embodiments, the retrieval request carries a feature vector corresponding to the indication information, and the feature vector corresponding to the indication information is extracted by the third core network element; the receiving unit 1001 is used to perform associated data retrieval on the indication information in the stored network database to obtain data retrieval results, specifically for:

[0177] Calculate the matching degree between the feature vector corresponding to the indication information and the feature vectors of each category of information in the network database;

[0178] Network data under category information with a matching degree greater than a set matching degree threshold is selected to obtain the data retrieval results.

[0179] In some embodiments, the sending unit 1002 is further configured to send storage confirmation information to the third core network element in response to receiving a data storage request sent by the third core network element;

[0180] The receiving unit 1001 is further configured to receive the feature vectors of each category of information and the network data under each category of information sent by the third core network element in response to the storage confirmation information, and store the feature vectors of each category of information and the network data under each category of information in the network database.

[0181] According to one embodiment of this application, Figure 6 The steps involved in the method shown can be from Figure 10 This is performed by each unit in the network information acquisition device shown. For example, Figure 6 The step S601 shown is by Figure 10The transmitting unit 1001 shown is responsible for executing step S602. Figure 10 The receiving unit 1002 shown is used to perform this operation.

[0182] According to one embodiment of this application, Figure 10 The network information acquisition device 100 shown can be composed of various units, either individually or entirely, into one or more other units. Alternatively, some units can be further divided into functionally smaller units. This achieves the same operation without affecting the technical effects of the embodiments of this application. The units are based on logical function division. In practical applications, the function of one unit can be implemented by multiple units, or the function of multiple units can be implemented by one unit. In other embodiments of this application, the network information acquisition device 100 may also include other units. In practical applications, these functions can be implemented with the assistance of other units, and can be implemented collaboratively by multiple units. According to another embodiment of this application, a general-purpose computing device capable of performing functions such as processing elements (e.g., a central processing unit (CPU), random access memory (RAM), read-only memory (ROM), etc.) and storage elements can be run on a general-purpose computer. Figure 6 The computer program (including program code) for each step involved in the corresponding method shown, to construct such... Figure 10 The network information acquisition device 100 shown herein, and the network information acquisition method for implementing the embodiments of this application, are described. The computer program may be recorded on, for example, a computer-readable storage medium, and loaded onto the computer-readable storage medium. Figure 2 The ADRF network element in core network 201 of the implementation environment is shown, and it runs in the environment.

[0183] Figure 11 A schematic diagram of a computer system suitable for implementing an electronic device according to embodiments of this application is shown. The electronic device may be... Figure 1 or Figure 2 The network elements or devices shown.

[0184] It should be noted that, Figure 11 The computer system 1100 of the electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0185] like Figure 11As shown, the computer system 1100 includes a Central Processing Unit (CPU) 1101, which can perform various appropriate actions and processes based on a computer program stored in Read-Only Memory (ROM) 1102 or a computer program loaded from storage portion 1108 into Random Access Memory (RAM) 1103, such as executing the business processing methods described in the above embodiments. Various computer programs and data required for system operation are also stored in RAM 1103. The CPU 1101, ROM 1102, and RAM 1103 are interconnected via bus 1104. An input / output (I / O) interface 1105 is also connected to bus 1104.

[0186] In some embodiments, the following components are connected to I / O interface 1105: an input section 1106 including a keyboard, mouse, etc.; an output section 1107 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 1108 including a hard disk, etc.; and a communication section 1109 including a network interface card such as a LAN (Local Area Network) card, modem, etc. The communication section 1109 performs communication processing via a network such as the Internet. A drive 1110 is also connected to I / O interface 1105 as needed. A removable medium 1111, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on drive 1110 as needed so that computer programs read from it can be installed into storage section 1108 as needed.

[0187] In particular, according to embodiments of this application, a computer program implementing the business processing method can be carried on a computer-readable medium, which can be downloaded and installed from a network via the communication section 1109, and / or installed from the removable medium 1111.

[0188] It should be noted that the computer-readable medium shown in the embodiments of this application can be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. For example, a computer-readable storage medium can be an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or at least two wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, portable compact disc read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this application, a computer-readable storage medium can be any tangible medium containing or storing a computer program that can be used by or in conjunction with an instruction execution system, apparatus, or device. Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying a computer-readable computer program. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The computer program contained in the computer-readable medium may be transmitted using any suitable medium, including but not limited to wireless, wired, etc., or any suitable combination thereof.

[0189] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. Each block in a flowchart or block diagram may represent a module, segment, or portion of code, which contains one or at least two executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and a computer program.

[0190] The units described in the embodiments of this application can be implemented in software or hardware, and the described units can also be located in a processor. The names of these units do not necessarily limit the specific unit itself.

[0191] Another aspect of this application provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor of an electronic device, causes the electronic device to implement the image generation method as described above. This computer-readable storage medium may be included in the electronic device described in the above embodiments, or it may exist independently and not assembled into the electronic device.

[0192] Another aspect of this application provides a computer program product, which includes a computer program that, when executed by a processor, implements the image generation methods provided in the various embodiments described above. The computer program can be stored in a computer-readable storage medium. The computer program product can be a computer program as a product, such as an APP (Application), webpage, mini-program, etc.; or, the computer program product can also be a storage medium, device, terminal, virtual machine, etc., containing the computer program.

[0193] The above description is merely a preferred exemplary embodiment of this application and is not intended to limit the implementation of this application. Those skilled in the art can easily make corresponding modifications or alterations based on the main concept and spirit of this application. Therefore, the scope of protection of this application should be determined by the scope of protection claimed in the claims.

Claims

1. A method for acquiring network information, characterized in that, include: In response to a received network information acquisition request, the system performs associated data retrieval based on the indication information carried in the network information acquisition request to obtain data retrieval results. Based on the data retrieval results, generate the network information corresponding to the network information acquisition request; The network information is returned to the sender of the network information retrieval request.

2. The method according to claim 1, characterized in that, The step of performing associated data retrieval based on the indication information carried in the network information retrieval request to obtain data retrieval results includes: Extract the feature vector corresponding to the indication information; A retrieval request is sent to the first core network element. The retrieval request carries a feature vector corresponding to the indication information. The retrieval request is used to instruct the first core network element to calculate the matching degree between the feature vector corresponding to the indication information and the feature vectors of each category of information stored in the network database of the first core network element. The system receives data retrieval results sent by the first core network element, wherein the matching degree between the feature vector corresponding to the category information of the network data contained in the data retrieval results and the feature vector corresponding to the indication information is greater than or equal to a set matching degree threshold.

3. The method according to claim 2, characterized in that, The step of extracting the feature vector corresponding to the indication information includes: Extract keywords from the instruction information and filter the keywords according to the configured filtering rules to obtain filtered keywords; The filtered keywords are rewritten using a keyword rewriting model to obtain rewritten target keywords, wherein the target keywords have matching information with at least one category of information in the network database. The feature vector of the target keyword is extracted by calling a vectorization model, and the feature vector corresponding to the indication information is obtained.

4. The method according to claim 2, characterized in that, The step of extracting the feature vector corresponding to the indication information includes: The instruction information is rewritten by calling the instruction information rewriting model to obtain the rewritten target instruction information, and the target instruction information has matching information with at least one category information in the network database; The feature vector of the target indication information is extracted by calling the vectorization model, and the feature vector corresponding to the indication information is obtained.

5. The method according to claim 1, characterized in that, The process of generating the network information corresponding to the network information acquisition request based on the data retrieval results includes: Prompt words are generated based on the configured generation rules and the data retrieval results; The prompt words are input into a large language model, so that the large language model generates the network information based on the generation rules and the data retrieval results.

6. The method according to claim 2, characterized in that, Before responding to a received network information retrieval request and performing associated data retrieval based on the indication information carried in the network information retrieval request to obtain data retrieval results, the method further includes: Based on the configured data collection rules, a data collection request is sent to the second core network element, the data collection request being used to instruct the second core network element to collect a specific type of network data; If network data is received from the second core network element in response to the data collection request, the network data is stored in the first core network element.

7. The method according to claim 6, characterized in that, The step of storing the network data in the first core network element includes: Extract the data types of each network data, and segment the network data according to the data types indicated by the network information acquisition requirements to obtain network data under at least two segmentation categories; Based on the network information acquisition requirements, category information for each segmentation category is generated, and a vectorization model is called to extract feature vectors for each category. The feature vectors of each category of information, as well as the network data under each segmentation category, are stored in the first core network element.

8. The method according to claim 7, characterized in that, The generation of category information for each segmentation based on the network information acquisition requirements includes: Obtain an example of indication information associated with the network information acquisition request; Based on the network information acquisition requirement, the example of the indication information associated with the network information acquisition requirement, and at least one of the data types of the network data under the at least two segmentation categories, the category information of each segmentation category is generated.

9. The method according to claim 7, characterized in that, Before storing the feature vectors of each category of information and the network data under each segmentation category in the first core network element, the method further includes: Send a data storage request to the first core network element; If a storage confirmation message is received from the first core network element, the feature vectors of each category of information and the network data under each segmentation category are sent to the first core network element so that the first core network element can perform storage processing.

10. A method for acquiring network information, characterized in that, include: It receives retrieval requests sent by third core network elements, performs associated data retrieval on the indication information in the stored network database, and obtains the data retrieval results; The retrieval request is generated by the third core network element after receiving the network information acquisition request, and the network information acquisition request carries the indication information. The data retrieval result is sent to the third core network element, which is used to instruct the third core network element to generate network information corresponding to the network information acquisition request and return the network information to the sender of the network information acquisition request.

11. The method according to claim 10, characterized in that, The retrieval request carries a feature vector corresponding to the indication information, which is extracted by the third core network element; the step of performing associated data retrieval on the indication information in the stored network database to obtain data retrieval results includes: Calculate the matching degree between the feature vector corresponding to the indication information and the feature vectors of each category of information in the network database; Network data under category information with a matching degree greater than a set matching degree threshold is selected to obtain the data retrieval results.

12. The method according to claim 10, characterized in that, Before receiving the retrieval request sent by the third core network element, the method further includes: In response to receiving a data storage request from the third core network element, a storage confirmation message is sent to the third core network element; The third core network element receives the feature vectors of each category of information and the network data under each category of information in response to the storage confirmation information, and stores the feature vectors of each category of information and the network data under each category of information in the network database.

13. A device for acquiring network information, characterized in that, include: The retrieval unit is used to respond to a received network information acquisition request, perform associated data retrieval based on the indication information carried in the network information acquisition request, and obtain data retrieval results; The generation unit is used to generate network information corresponding to the network information acquisition request based on the data retrieval results; The sending unit is used to return the network information to the sender of the network information acquisition request.

14. A device for acquiring network information, characterized in that, include: The receiving unit is used to receive retrieval requests sent by third core network elements, perform associated data retrieval on the indication information in the stored network database, and obtain data retrieval results. The retrieval request is generated by the third core network element after receiving the network information acquisition request, and the network information acquisition request carries the indication information. The sending unit is used to send the data retrieval result to the third core network element. The data retrieval result is used to instruct the third core network element to generate network information corresponding to the network information acquisition request and return the network information to the sender of the network information acquisition request.

15. An electronic device, characterized in that, include: One or more processors; A memory for storing one or more computer programs, which, when executed by one or more processors, cause the electronic device to implement the method for acquiring network information as described in any one of claims 1-12.

16. A computer-readable medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method for acquiring network information as described in any one of claims 1-12.

17. A computer program product, characterized in that, The computer program product includes a computer program stored in a computer-readable storage medium. The processor of the electronic device reads from the computer-readable storage medium and executes the computer program, causing the electronic device to perform the method for acquiring network information as described in any one of claims 1-12.

Images