Wireless network failure handling method, apparatus, device, and medium

Abstract

The present disclosure provides a wireless network fault processing method, device, equipment and medium, wherein the method comprises: testing a target terminal based on a test task to obtain cell identification of a service cell corresponding to the test task and number information of the target terminal; obtaining state information of the service cell according to the cell identification, and obtaining control plane signaling and user plane data of the target terminal according to the number information; determining multi-dimensional data information according to the state information, the control plane signaling and the user plane data; processing the multi-dimensional data information based on artificial intelligence (AI) to obtain candidate processing information corresponding to a wireless network fault to be solved; processing the wireless network fault to be solved according to the candidate processing information to obtain a reference processing result, and determining target processing information according to the candidate processing information and the reference processing result, thereby solving the technical problem that the prior art cannot conveniently and quickly determine processing information for solving the wireless network fault, and the quality of the determined processing information is not high.

Description

Technical Field

[0001] This disclosure relates to the field of communication technology, and in particular to a method, apparatus, device and medium for handling wireless network faults. Background Technology

[0002] With the increasing demand for mobile services, ensuring the quality of wireless networks is crucial to meeting this demand. The quality of a wireless network directly impacts the user experience, making the resolution of wireless network quality issues a vital part of ensuring overall network quality. The strategies used to resolve wireless network faults can also be referred to as information processing.

[0003] In related technologies, it is not convenient and quick to determine the processing information used to resolve wireless network faults, and the quality of the determined processing information is not high. Summary of the Invention

[0004] This disclosure aims to at least partially address one of the technical problems in the related art.

[0005] Therefore, this disclosure proposes a wireless network fault handling method, apparatus, electronic device, non-transitory computer-readable storage medium storing computer instructions, and computer program product, which can conveniently and quickly determine the processing information for resolving wireless network faults and improve the quality of the determined processing information.

[0006] The first aspect of this disclosure proposes a wireless network fault handling method, comprising: testing a target terminal based on a test task to obtain test data corresponding to the test task, wherein the test data includes: a cell identifier of a serving cell and number information of the target terminal; obtaining status information of the serving cell based on the cell identifier, and obtaining control plane signaling and user plane data of the target terminal based on the number information; determining multi-dimensional data information based on the status information, control plane signaling, and user plane data, wherein the multi-dimensional data information is used to describe feature data related to each cell grid, the feature data including: first feature data, the first feature data being used to describe the type information of the wireless network fault to be resolved generated by the corresponding cell grid; processing the multi-dimensional data information based on artificial intelligence (AI) to obtain candidate processing information corresponding to the wireless network fault to be resolved; processing the wireless network fault to be resolved based on the candidate processing information to obtain a reference processing result, and determining target processing information based on the candidate processing information and the reference processing result.

[0007] A second aspect of this disclosure provides a wireless network fault handling apparatus, comprising: a testing module for testing a target terminal based on a testing task to obtain test data corresponding to the testing task, wherein the test data includes: a cell identifier of the serving cell and number information of the target terminal; an acquisition module for acquiring status information of the serving cell based on the cell identifier, and acquiring control plane signaling and user plane data of the target terminal based on the number information; a determination module for determining multi-dimensional data information based on the status information, control plane signaling, and user plane data, wherein the multi-dimensional data information describes feature data related to each cell grid, the feature data including: first feature data, the first feature data describing the type information of the wireless network fault to be resolved generated by the corresponding cell grid; a first processing module for processing the multi-dimensional data information based on artificial intelligence (AI) to obtain candidate processing information corresponding to the wireless network fault to be resolved; and a second processing module for processing the wireless network fault to be resolved based on the candidate processing information to obtain a reference processing result, and determining target processing information based on the candidate processing information and the reference processing result.

[0008] A third aspect of this disclosure provides an electronic device, including: a processor and a memory communicatively connected to the processor; the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory to implement the method described above.

[0009] A fourth aspect of this disclosure provides a computer-readable storage medium storing computer-executable instructions that, when executed by a processor, are used to implement the method described above.

[0010] A fifth aspect of this disclosure provides a computer program product including a computer program that, when executed by a processor, implements the method described above.

[0011] The wireless network fault handling method, apparatus, electronic device, non-transitory computer-readable storage medium storing computer instructions, and computer program product provided in this disclosure test a target terminal based on a test task to obtain test data corresponding to the test task. The test data includes: the cell identifier of the serving cell and the number information of the target terminal. Based on the cell identifier, the status information of the serving cell is obtained, and based on the number information, the control plane signaling and user plane data of the target terminal are obtained. Based on the status information, control plane signaling, and user plane data, multi-dimensional data information is determined. This multi-dimensional data information describes feature data related to each cell grid. The feature data includes: first feature data, which describes the type of wireless network fault to be resolved generated by the corresponding cell grid. The multi-dimensional data information is processed based on artificial intelligence (AI) to obtain candidate processing information corresponding to the wireless network fault to be resolved. The wireless network fault to be resolved is processed based on the candidate processing information to obtain a reference processing result. Finally, target processing information is determined based on the candidate processing information and the reference processing result. Because it uses artificial intelligence (AI) to process multi-dimensional data and obtain candidate processing information corresponding to the wireless network fault to be resolved, it can improve the efficiency and accuracy of acquiring candidate processing information. This can effectively guide the handling of wireless network faults. When backtracking tests are performed on wireless network faults based on the candidate processing information determined by AI, and the target processing information is determined based on the reference processing results obtained from the backtracking tests, the accuracy of the target processing information determination can be effectively improved. This allows for convenient and rapid determination of the processing information used to resolve wireless network faults, and also improves the quality of the determined processing information.

[0012] Additional aspects and advantages of this disclosure will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this disclosure. Attached Figure Description

[0013] The above and / or additional aspects and advantages of this disclosure will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, in which:

[0014] Figure 1 This is a flowchart illustrating a wireless network fault handling method provided in an embodiment of the present disclosure.

[0015] Figure 2 This is a schematic diagram of the external device in an embodiment of this disclosure;

[0016] Figure 3 This is a schematic diagram of the external device in an embodiment of this disclosure;

[0017] Figure 4 This is a signaling flowchart for automatically acquiring data in an embodiment of this disclosure;

[0018] Figure 5 This is a schematic diagram of the external device interface in an embodiment of this disclosure;

[0019] Figure 6 This is a flowchart illustrating another wireless network fault handling method provided in an embodiment of the present disclosure;

[0020] Figure 7 This is a schematic diagram of the architecture of the first network and the second network in the embodiments of this disclosure;

[0021] Figure 8 This is a schematic diagram of sample test data in an embodiment of this disclosure;

[0022] Figure 9 This is a schematic diagram of the model training process in an embodiment of this disclosure;

[0023] Figure 10 This is a signaling flowchart of the automatic data reporting in this embodiment of the present disclosure;

[0024] Figure 11 This is a flowchart illustrating the automatic optimization function in an embodiment of this disclosure;

[0025] Figure 12 This is a schematic diagram of the automatic optimization process for wireless networks in an embodiment of this disclosure;

[0026] Figure 13 This is a schematic diagram of the structure of a wireless network fault handling device provided in an embodiment of the present disclosure;

[0027] Figure 14 A block diagram of an exemplary electronic device suitable for implementing embodiments of the present disclosure is shown. Detailed Implementation

[0028] Embodiments of this disclosure are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this disclosure, and should not be construed as limiting this disclosure.

[0029] Figure 1 This is a flowchart illustrating a wireless network fault handling method provided in an embodiment of the present disclosure.

[0030] This embodiment illustrates the example of a wireless network fault handling method configured within a wireless network fault handling device. In this embodiment, the wireless network fault handling method can be configured within a wireless network fault handling device, which can be located in a server or an electronic device, without limitation.

[0031] This embodiment uses the example of a wireless network fault handling method configured in an electronic device. The electronic device includes hardware devices with various operating systems, such as smartphones, tablets, personal digital assistants, and e-readers.

[0032] It should be noted that the execution entity of the embodiments disclosed herein may be, in hardware, a central processing unit (CPU) in a server or electronic device, and in software, a related background service in a server or electronic device, without limitation.

[0033] The wireless network fault handling device in this embodiment can be, for example, a third-party external device. This external device can establish a communication connection with the user terminal and collect the communication data of the user terminal to detect the wireless network quality of the user terminal. Figure 2 As shown, Figure 2 This is a schematic diagram of the external device in an embodiment of this disclosure. The external device can directly collect communication data from the user terminal being tested, providing a more realistic, comprehensive, flexible, and convenient assessment. To ensure that the data collected on-site accurately reflects network problems, the test can be conducted continuously for at least one hour within a 100-meter radius of either the complaint point (a point with poor wireless network quality) or the area center.

[0034] Testers can connect the Universal Serial Bus (USB) interface of an external device to the Micro USB, Type C, or Lightning interface of the target user terminal via a data cable. After configuring the test tasks (including but not limited to upload / download server address, file storage location, upload / download file size, SPEEDTEST (speed test), and PING (ping test)), click "Test" to start collecting data (including but not limited to the target user's Mobile Subscriber International Integrated Service Digital Network (MSISDN), International Mobile Equipment Identity (IMEI), latitude and longitude, Serving Cell Identifier (CELLID), Physical Cell Identifier (PCI), Reference Signal Receiving Power (RSRP), Signal to Interference plus Noise Ratio (SINR), wireless communication events, uplink and downlink rates, Round-Trip Time (RTT), and jitter), and save the log file.

[0035] In this embodiment, for ease of carrying and testing, the external device is equipped with a shoulder strap and an operation knob. The tester carries the external device across their body via the shoulder strap, operating the visual interface with their left hand and the knob and buttons with their right, making on-site testing simple and easy. The external device features one USB 2.0 port and two USB 3.0 ports, supporting Micro, Type-C, or Lightning interfaces for compatibility with various terminal types. It also includes a Universal Subscriber Identity Module (USIM) slot, supporting wide-coverage mobile networks. The communication module has a relatively simple structure and can access mobile communication networks. The external device comes pre-installed with an operating system and automated testing optimization software. Figure 3 As shown, Figure 3This is a schematic diagram of the external device in an embodiment of this disclosure. The external device includes a power module, a storage module, a communication module, a data acquisition module, and a computing module. The power module stores electrical energy for easy portability; the storage module stores and manages data, including but not limited to log files and optimization schemes; the communication module maintains a communication connection with the mobile communication network for end-to-end data interaction; the data acquisition module collects data from the target user terminal and saves log files; and the computing module supports the operation of the external device's built-in software and the processing and analysis of multi-dimensional data.

[0036] like Figure 1 As shown, the wireless network fault handling method includes:

[0037] S101: Test the target terminal based on the test task and obtain test data corresponding to the test task. The test data includes: the cell identifier of the serving cell and the number information of the target terminal.

[0038] In this context, a test task refers to a specific wireless network quality test. For example, an external device can receive test instructions from testers, parse the test configuration information from these instructions, configure the corresponding test task based on the configuration information, and connect the external device to the target terminal to perform the wireless network test on the target terminal. The communication data obtained during the test can be referred to as test data.

[0039] The test data in this embodiment may include: the cell identifier of the serving cell and the number information of the target terminal. The cell identifier can be used to index the status information of the serving cell where the target terminal is located, and the number information can be used to index the communication data of the target terminal.

[0040] In this embodiment of the disclosure, in order to improve the accuracy of test task configuration and the accuracy of the acquired test data, the geographical location of the wireless network fault to be resolved can be determined first, and the test geographical range can be determined according to the geographical location, and configuration information can be obtained, and the test task corresponding to the test geographical range can be configured according to the configuration information.

[0041] The geographical location can be, for example, the location corresponding to the aforementioned complaint point (the location of the complaint point with poor wireless network quality) or the location corresponding to the regional center of the service cell. The test geographical range is determined based on the geographical location, which can be a circle with a radius of 100 meters centered on the geographical location. Then, configuration information entered by the user can be received from an external device, and test tasks corresponding to the test geographical range can be configured based on the configuration information to achieve targeted testing.

[0042] S102: Obtain the status information of the serving cell based on the cell identifier, and obtain the control plane signaling and user plane data of the target terminal based on the number information.

[0043] Among them, status information refers to information used to describe the status of the serving cell. Control plane signaling refers to the control plane signaling data exchanged by the target terminal during communication with network equipment, and user plane data refers to the user plane communication data generated by the target terminal.

[0044] The acquired status information of the serving cell and the control plane signaling and user plane data of the target terminal can be used to determine comprehensive feature data.

[0045] Optionally, in some embodiments, the status information includes at least one of the following: operating status, engineering parameters, wireless configuration parameters, neighbor cell data, performance indicators, device alarm information, uplink interference data, and operating parameters of the base station where the serving cell is located. This allows for a comprehensive and multi-dimensional description of the status of the serving cell where the target terminal is located, supporting improved accuracy in subsequent processing strategies.

[0046] S103: Based on the status information, control plane signaling, and user plane data, determine multi-dimensional data information, wherein the multi-dimensional data information is used to describe the characteristic data associated with each cell grid, and the characteristic data includes: first characteristic data, which is used to describe the type information of the wireless network fault to be resolved generated by the corresponding cell grid.

[0047] After determining the status information, control plane signaling, and user plane data, multi-dimensional data analysis can be performed on the aforementioned data content to form multi-dimensional data information. This multi-dimensional data information can be used to describe the characteristic data related to each cell grid. A cell grid may belong to a serving cell, and each serving cell may contain several cell grids. Based on multi-dimensional data analysis, the characteristic data corresponding to each cell grid can be determined.

[0048] The feature data in this embodiment includes at least first feature data, which can be used to describe the type of wireless network fault to be resolved caused by the corresponding cell grid.

[0049] Therefore, by performing gridded feature analysis on the serving cell, feature data corresponding to each cell grid in the serving cell is formed. This feature data includes at least first feature data, which can be used to describe the type of wireless network fault to be resolved caused by the corresponding cell grid. This enables the acquisition of accurate processing information.

[0050] Optionally, in some embodiments, the feature data may further include: second feature data and third feature data, wherein the second feature data is used to describe the characteristics of the serving cell to which the tested cell grid belongs, and the third feature data is used to describe the characteristics of the neighboring cells related to the corresponding cell grid. This effectively expands the representational dimensions of the feature data, and by analyzing diverse feature data, it can be used to guide the determination of more accurate processing information.

[0051] As shown in Table 1 below, Table 1 illustrates a multidimensional data information diagram. The grid number identifies the corresponding cell grid, the grid latitude and longitude represent the cell grid's location information, feature data 1 is an optional example of the first feature data, feature data 2 is an optional example of the second feature data, and feature data 3 and feature data 4 are optional examples of the third feature data. Feature data 1 describes type information and is a definition of type information. In Table 1, SCell represents the serving cell, and Ncellx represents the x-th neighboring cell. QoS Flow represents the Quality of Service (QoS) flow. OMC entity represents the Operation and Maintenance Center (OMC) entity.

[0052] In this embodiment of the disclosure, when the test data is rasterized, unnecessary optimization operations can be effectively avoided due to low-probability fault issues (an optional example of a wireless network fault to be resolved). Each fault issue (an optional example of type information) within the cell grid can meet the requirements for the total number of samples and the sample ratio. The grid number is used to identify the corresponding cell grid, and the grid number can use a uniformly defined number. The cell grid size is a 50m * 50m area. "STATCAUSExx" represents type information, and the detailed definition of "STATCAUSExx" is shown in Table 2 below:

[0053] Table 1

[0054]

[0055]

[0056] Table 2

[0057]

[0058]

[0059] The samples in Table 2 above can be understood as a set of multi-dimensional data information obtained by testing a target terminal. The network optimization platform refers to a third-party platform that can provide status information of the service cell.

[0060] In this embodiment, the external device can automatically obtain the status information of the serving cell of the target user from the network optimization platform based on the serving cell identifier (CEIIID) of the serving cell in the test data. This information may include, for example, operating status, engineering parameters, radio configuration parameters, neighbor cell data, performance indicators, device alarms, and uplink interference. It can also automatically obtain the control plane signaling and user plane data of the target user from the network optimization platform based on the phone number information. Then, the processing module in the external device parses, correlates, and synthesizes a fixed-format multidimensional data report (an optional example of multidimensional data information). Furthermore, the function of automatically obtaining multidimensional data information can be integrated into the external device's automatic test optimization software, such as... Figure 4 As shown, Figure 4 This is a signaling flowchart for automatically acquiring data in an embodiment of this disclosure.

[0061] In this embodiment of the disclosure, multi-dimensional data information can also be displayed on the interface of an external device, such as... Figure 5 As shown, Figure 5 This is a schematic diagram of the external device interface in an embodiment of this disclosure.

[0062] S104: Based on artificial intelligence (AI) processing of multi-dimensional data information, candidate processing information corresponding to the wireless network fault to be resolved is obtained.

[0063] After obtaining multidimensional data information through computational analysis, the multidimensional data information can be processed based on artificial intelligence (AI) to obtain candidate processing information corresponding to the wireless network fault to be resolved.

[0064] Candidate processing information refers to processing information obtained based on AI analysis and used as a reference. There can be one or more candidate processing information. The better candidate processing information can be selected as the target processing information. The target processing information refers to the processing information that can effectively resolve wireless network faults.

[0065] S105: Process the wireless network fault to be resolved based on the candidate processing information, obtain the reference processing result, and determine the target processing information based on the candidate processing information and the reference processing result.

[0066] In some embodiments, backtracking testing can be performed based on candidate processing information. That is, the wireless network fault to be resolved is processed based on the candidate processing information, and the processing result is used as a reference processing result. If the reference processing result indicates that the wireless network fault has been resolved, the corresponding candidate processing information is used as the target processing information. If the reference processing result indicates that the wireless network fault has not been resolved, the wireless network quality test can be performed again to update the candidate processing information.

[0067] Of course, candidate processing information can also be used to process wireless network faults to be resolved in any other possible way, obtain reference processing results, and determine target processing information based on candidate processing information and reference processing results. There are no restrictions on this.

[0068] In this embodiment, the target terminal is tested based on a test task to obtain test data corresponding to the test task. The test data includes the cell identifier of the serving cell and the number information of the target terminal. Based on the cell identifier, the status information of the serving cell is obtained, and based on the number information, the control plane signaling and user plane data of the target terminal are obtained. Based on the status information, control plane signaling, and user plane data, multi-dimensional data information is determined. The multi-dimensional data information is used to describe the feature data related to each cell grid. The feature data includes: first feature data, which describes the type information of the wireless network fault to be resolved generated by the corresponding cell grid. Based on artificial intelligence (AI), the multi-dimensional data information is processed to obtain candidate processing information corresponding to the wireless network fault to be resolved. The wireless network fault to be resolved is processed according to the candidate processing information to obtain a reference processing result. Based on the candidate processing information and the reference processing result, the target processing information is determined. Because it uses artificial intelligence (AI) to process multi-dimensional data and obtain candidate processing information corresponding to the wireless network fault to be resolved, it can improve the efficiency and accuracy of acquiring candidate processing information. This can effectively guide the handling of wireless network faults. When backtracking tests are performed on wireless network faults based on the candidate processing information determined by AI, and the target processing information is determined based on the reference processing results obtained from the backtracking tests, the accuracy of the target processing information determination can be effectively improved. This allows for convenient and rapid determination of the processing information used to resolve wireless network faults, and also improves the quality of the determined processing information.

[0069] Figure 6 This is a flowchart illustrating another wireless network fault handling method provided in an embodiment of the present disclosure.

[0070] like Figure 6 As shown, the wireless network fault handling method includes:

[0071] S601: Test the target terminal based on the test task and obtain test data corresponding to the test task. The test data includes: the cell identifier of the serving cell and the number information of the target terminal.

[0072] S602: Obtain the status information of the serving cell based on the cell identifier, and obtain the control plane signaling and user plane data of the target terminal based on the number information.

[0073] S603: Based on the status information, control plane signaling, and user plane data, determine multi-dimensional data information, wherein the multi-dimensional data information is used to describe the characteristic data associated with each cell grid, and the characteristic data includes: first characteristic data, which is used to describe the type information of the wireless network fault to be resolved generated by the corresponding cell grid.

[0074] For details regarding S601-S603, please refer to the above embodiments; they will not be repeated here.

[0075] S604: Provide multi-dimensional data information to the processing information generation model in the first network, wherein the processing information generation model is used to process the multi-dimensional data information to obtain initial processing information, which includes: software parameter optimization information and hardware adjustment optimization information. The security level of the first network is higher than that of the second network.

[0076] The security level of the first network is higher than that of the second network. The second network can be, for example, a typical data communication network, specifically a 5G-SA (5th Generation Mobile Communication Technology) standalone (SA) network. Figure 7 As shown, Figure 7This is a schematic diagram of the architecture of the first and second networks in this embodiment of the disclosure. The first network is, for example, an Artificial Intelligence Data Network (AIDN) private network (hereinafter referred to as AIDN private network). The second network includes access network equipment (R)AN, and various network elements in the core network equipment (User Plane Function (UPF) network element, Network Slice Selection Function (NSSF) network element, Network Exposure Function (NEF) network element, Network Repository Function (NRF) network element, Policy Control Function (PCF) network element, Unified Data Management (UDM) network element, Application Function (AF) network element, Authentication Server Function (AUSF) network element, Access and Mobility Management Function (AMF) network element, Session Management Function (SMS) network element, etc.). The network element (SMF) has corresponding interfaces, including: Nnssf, Nnef, Nnrf, Npcf, Nudm, Naf, Nausf, Namf, and Nsmf. The first network connects to the UPF network element via the N6 interface. The first network also includes a gateway. The slice differentiater (SD) of the network slices on the radio side, core network side, and transport side of the first network is the same. The slice and service type (SST) parameters of the network slices on the radio side, core network side, and transport side of the first network are also the same. Figure 7 The system also includes interfaces: N1, N2, N4, N3, N6, N9, and UU, where DN represents the data network. The first network can be configured with a network optimization platform, an OMC entity, and an AI model library (which may include the aforementioned information processing and generation models). Figure 7 The numerical labels in the diagram indicate the data processing flow.

[0077] For example, a new dedicated data network (DNN) with Access Point Name (APN) equal to AIDN can be added to the 5G-SA network architecture (hereinafter referred to as: AIDN private network). The AIDN private network can draw on the network architecture of 5G networks in vertical industry applications to build a dedicated network with automatic and intelligent network optimization. The network slice SD and SST parameters are consistent across the radio, core, and transmission sides of the AIDN private network (e.g., using a 5G network slice with SST=128 & SD=3490001, and configuring 128-3490001 as the default slice in the Universal Subscriber Identity Module (USIM) subscription data of external devices). Entities such as the network optimization platform, OMC, and AI model library within the AIDN private network are connected to the AIDN private network gateway through the transmission network to achieve interconnection. External devices establish communication connections with the network optimization platform, OMC, and AI model library via the 5G New Radio (NR) interface, through the 5G access network, transmission network, core network, AIDN private network gateway, to form a data transmission channel. This architecture ensures that user data and network data do not leave the AIDN private network, effectively protecting user privacy and network security.

[0078] In this embodiment of the disclosure, a communication connection can be established with the operation and maintenance OMC entity and the AI ​​model library in the first network through the second network and the gateway in the first network. The AI ​​model library includes: information processing generation models.

[0079] In this embodiment of the disclosure, based on the established communication connection with the OMC entity and AI model library in the first network, multi-dimensional data information can be provided to the processing information generation model in the AI ​​model library to support the processing information generation model in processing multi-dimensional data information and obtaining initial processing information, wherein the initial processing information includes: software parameter optimization information and hardware adjustment optimization information.

[0080] Information used to optimize software parameters in a wireless network can be referred to as software parameter optimization information. Information used to optimize hardware in a wireless network can be referred to as hardware tuning optimization information.

[0081] Among them, the information generation model has modeled and learned the mapping relationship between multidimensional data information and the initial processed information corresponding to the multidimensional data information.

[0082] Optionally, in some embodiments, the processing information generation model is trained based on the following method: collecting sample data, wherein the sample data includes: sample test data corresponding to each historical wireless network fault, and sample processing information, the sample test data includes: sample features, the sample features include: a first sample feature, a second sample feature, and a third sample feature, the first sample feature is used to describe the type information of each historical wireless network fault, the second sample feature is used to describe the characteristics of the serving cell involved in each historical wireless network fault, and the third sample feature is used to describe the characteristics of the neighboring cells involved in each historical wireless network fault; the initial AI model is trained iteratively at least once based on the sample data until the trained AI model converges, and the trained AI model is used as the processing information generation model. This can effectively improve the processing accuracy of the processing information generation model, and can significantly improve the accuracy of software parameter optimization information and hardware adjustment optimization information, thereby supporting the improvement of wireless network fault handling effects.

[0083] After generating the information generation model, the information generation model can be saved to the AI ​​model library to support online access to the information generation model.

[0084] The training process for information generation models can be illustrated with the following example:

[0085] The network optimization platform collects historical wireless network fault sample test data and corresponding sample processing information (Note: Sample processing information can be processing information that can resolve the corresponding network fault. Historical data includes, but is not limited to, drive test data for network structure optimization, drive test data for handling complaint tickets, historical sample processing information, and operation log data of real-time / non-real-time tickets). Then, based on the aforementioned data, it constructs the data required to train the AI ​​model, such as... Figure 8 As shown, Figure 8 This is a schematic diagram of sample test data in an embodiment of this disclosure. The first sample feature is, for example,... Figure 8 The feature data 1 shown, the second sample feature is, for example, Figure 8 Feature data 2 shown, the third sample feature is, for example, Figure 8 The feature data 3-n shown includes sample processing information such as software parameter optimization schemes and hardware adjustment optimization schemes, which are not restricted.

[0086] Following the principle of uniform distribution of "STATCAUSEx" in "Feature Data 1", the sample test data is divided into a training set (70% of the data) and a test set (30% of the data). An AI algorithm is used to train the model on the training set to obtain the information generation model. Then, the trained information generation model is tested on the test set. After testing, the accuracy of the information generation model's output is evaluated. If the accuracy is <90% (Note: Accuracy of the information generation model = Number of output schemes of the information generation model that match the optimized schemes in the test set / Total number of optimized schemes in the test set * 100%), the training parameters are adjusted and training continues until the accuracy of the information generation model is >= 90%. Figure 9 As shown, Figure 9 This is a schematic diagram of the model training process in an embodiment of this disclosure. It includes the model data construction, model training, model inference, and feedback processes.

[0087] S605: Generates adjustment command scripts based on software parameter optimization information, and generates adjustment execution work orders based on hardware adjustment optimization information.

[0088] The process described above involves generating software parameter optimization information, which can then be processed to generate adjustment command scripts. These scripts can be directly executed to optimize software parameters in the wireless network, thereby addressing software-related faults. Similarly, after generating hardware adjustment and optimization information, this information can be processed to generate adjustment execution work orders. These work orders can serve as a reference for optimizing the wireless network hardware, thus supporting the handling of hardware-related faults in the wireless network.

[0089] S606: Adjust command scripts and adjustment execution work orders will be considered as candidate processing information.

[0090] After obtaining the adjustment command script and adjustment execution work order, these can be used as candidate processing information. Then, wireless network fault optimization is automatically performed.

[0091] Optionally, in some embodiments, during the process of processing the wireless network fault to be resolved based on the candidate processing information and obtaining the reference processing result, an adjustment command script can be sent to the OMC entity in the first network, and an adjustment execution work order can be sent to the operation and maintenance equipment through the first network. The script execution result generated and sent by the OMC based on the adjustment command script can be received, and the work order execution result generated and sent by the operation and maintenance equipment based on the adjustment execution work order can be received. The script execution result and the work order execution result can be used as the reference processing result.

[0092] The result obtained by the OMC entity in processing the adjustment command script can be referred to as the script execution result. The result obtained by the maintenance party in processing the adjustment execution work order can be referred to as the work order execution result.

[0093] S607: Process the wireless network fault to be resolved based on the candidate processing information, obtain the reference processing result, and determine the target processing information based on the candidate processing information and the reference processing result.

[0094] After obtaining the script execution results and work order execution results, the wireless network fault to be resolved can be processed according to the candidate processing information to obtain the reference processing results, and the target processing information can be determined based on the candidate processing information and the reference processing results.

[0095] Optionally, in some embodiments, in the process of processing the wireless network fault to be resolved based on the candidate processing information and obtaining a reference processing result, an adjustment command script may be sent to the OMC entity in the first network, and an adjustment execution work order may be sent to the operation and maintenance equipment through the first network. The system may also receive the script execution result generated and sent by the OMC based on the adjustment command script, and the work order execution result generated and sent by the operation and maintenance equipment based on the adjustment execution work order. The script execution result and the work order execution result are then used as reference processing results. This enables multi-dimensional processing of the wireless network fault to be resolved, ensuring processing effectiveness and providing timely feedback on script execution results and work order execution results, facilitating timely understanding of the wireless network fault processing results and enabling the implementation of subsequent countermeasures.

[0096] Optionally, in some embodiments, the sample data can be updated based on multidimensional data information and target processing information, and the processing information generation model can be iteratively trained based on the updated sample data to obtain a new processing information generation model. This can significantly improve the accuracy of the processing information generation model.

[0097] Optionally, in some embodiments, during the process of determining the target processing information based on candidate processing information and reference processing results, the target terminal can be retested based on the test task according to the reference processing results to obtain retest results. If the retest results meet preset conditions, the candidate processing information corresponding to the reference processing results is used as the target processing information. If the retest results do not meet the preset conditions, new candidate processing information is re-determined based on the retest results, and the reference processing results are re-determined based on the new candidate processing information. This process continues until the new retest results obtained by processing the wireless network fault to be resolved based on the re-determined reference processing results meet the preset conditions, and the new candidate processing information is used as the target processing information. This ensures that wireless network faults can be resolved correctly and effectively.

[0098] The preset conditions could be, for example, that the retest results indicate that the wireless network fault has been resolved and no new wireless network faults have occurred.

[0099] Examples are given below:

[0100] External devices can automatically upload synthesized multidimensional data reports (an optional example of multidimensional data information) to the AI ​​model library via the AIDN private network. This automatic upload functionality can be integrated into the external device's automated testing and optimization software, such as... Figure 10 As shown, Figure 10 This is a signaling flowchart for automatically reporting data in this embodiment. After the AI ​​model obtains the multi-dimensional data report reported by the external device, it outputs a wireless network optimization scheme based on feature data 1 to n. When there are multiple corresponding optimization schemes, the top 3 optimization schemes are output according to priority (optional examples of the top three candidate processing information). After receiving the top 3 optimization schemes, the external device presents the software parameter optimization scheme (an optional example of software parameter optimization information) and the hardware adjustment optimization scheme (an optional example of hardware adjustment optimization information) on the visualization interface. The top 1 scheme is selected by default. Frontline production personnel can select the corresponding scheme according to the specific situation on site using the knob on the external device or the up / down arrows on the touch screen. After clicking OK, a script command is sent to the OMC entity to execute parameter adjustments; the hardware adjustment scheme is sent to the operation and maintenance department in the form of a work order for execution.

[0101] The following is an example of automatically performing wireless network optimization:

[0102] Part 1: Testers select a solution (an optional example of candidate processing information) using the knobs or touchscreen directional keys on an external device, and click "OK" or press a button to confirm the selected solution. The external device automatically converts the software parameter adjustment solution (an optional example of software parameter optimization information) related to the selected solution into a command script (an optional example of an adjustment command script), connects to the OMC entity via the AIDN private network, and transmits the command script to the OMC entity for execution; it also automatically connects to the network optimization platform via the AIDN private network for the hardware adjustment and optimization solution (an optional example of hardware adjustment and optimization information), and dispatches it to the appropriate department for execution in the form of a work order (an optional example of an adjustment execution work order). The automatic optimization function can be integrated into the external device's automatic test optimization software, such as... Figure 11 As shown, Figure 11 This is a flowchart illustrating the automatic optimization function in an embodiment of this disclosure.

[0103] Part Two: Feedback on the Implementation Results of the Wireless Optimization Scheme

[0104] The execution results of the wireless optimization scheme can include: script execution results and work order execution results. Script execution results, for example, are the execution results of software parameter optimization scripts, while work order execution results, for example, are the execution results of hardware adjustment and optimization schemes.

[0105] For example, the OMC entity can feed back the software parameter optimization script execution results to the external device through the AIDN private network. After the hardware adjustment and optimization work order is completed, the network optimization platform feeds back the hardware adjustment and optimization plan execution results (including but not limited to antenna latitude and longitude, mounting height, and attitude photos before and after adjustment) to the external device through the AIDN private network. Testers can view and confirm the results through the external device's visual interface.

[0106] Part Three: Evaluation of the Wireless Optimization Solution

[0107] After the software and hardware optimization plan (including software parameter optimization and hardware adjustment optimization) is executed, frontline production personnel return to the target area with the external device for retesting to verify its effectiveness. If the external device's problem display interface shows no issues after the retest, it indicates that the software and hardware optimization plan has resolved the wireless network fault, and the selected plan is effective. Frontline testers use the effect feedback module in the external device's function menu to feed the pre-optimization multi-dimensional data and the selected software and hardware optimization plan as new sample data to the AI ​​model (e.g., the information generation model). Once the new sample data accumulates for a period or reaches a certain quantity, the AI ​​model is repeatedly retrained to continuously improve its accuracy. Conversely, if the external device's problem display interface shows problems, it indicates that the optimization plan has not resolved the network fault, or although it resolved the pre-test issue, it has introduced new network faults. In this case, the selected software and hardware optimization plan is ineffective or has limited effectiveness, and the entire optimization process can be rolled back. Figure 12 As shown, Figure 12 This is a schematic diagram of the automatic optimization process for wireless networks in an embodiment of this disclosure.

[0108] In this embodiment, since multi-dimensional data information is processed based on artificial intelligence (AI) to obtain candidate processing information corresponding to the wireless network fault to be resolved, the efficiency and accuracy of acquiring candidate processing information can be improved. This effectively guides the handling of wireless network faults. When backtracking tests are performed on the wireless network fault based on the candidate processing information determined by AI, and the target processing information is determined based on the reference processing results obtained from the backtracking tests, the accuracy of determining the target processing information can be effectively improved. This allows for convenient and rapid determination of the processing information used to resolve the wireless network fault, and also improves the quality of the determined processing information. By providing multi-dimensional data information to the processing information generation model in the first network, where the processing information generation model processes multi-dimensional data information to obtain initial processing information, the initial processing information includes: software parameter optimization information and hardware adjustment optimization information. The security level of the first network is higher than that of the second network, thereby effectively ensuring that user data and network data do not leave the first network, effectively protecting user privacy and network security. By generating adjustment command scripts based on software parameter optimization information and adjustment execution work orders based on hardware adjustment optimization information, and using the adjustment command scripts and adjustment execution work orders as candidate processing information, and processing the wireless network faults to be resolved based on the candidate processing information to obtain reference processing results, and determining the target processing information based on the candidate processing information and reference processing results, the comprehensiveness of wireless network fault optimization can be effectively improved, and the success rate of wireless network optimization can be greatly increased.

[0109] The external device provided in this embodiment can detect hidden network problems anytime and anywhere, is simple and flexible to operate, and has a wide range of applications. The information generation model obtained through iterative training using AI algorithms can not only eliminate invalid data but also improve the generation efficiency and accuracy of candidate processing information. Furthermore, an AIDN-dedicated DNN is added to the SA network architecture, allowing for single-point configuration and multi-party sharing. This enables data collection, transmission, storage, and sharing to be completed within the dedicated network, effectively protecting user and network data security. It achieves full automation of the wireless network optimization process, with fully intelligent optimization scheme formulation, resulting in high optimization accuracy and efficiency.

[0110] Figure 13 This is a schematic diagram of the structure of a wireless network fault handling device provided in an embodiment of this disclosure.

[0111] like Figure 3 As shown, the wireless network fault handling device 130 includes:

[0112] The test module 1301 is used to test the target terminal based on the test task and obtain test data corresponding to the test task. The test data includes the cell identifier of the serving cell and the number information of the target terminal.

[0113] The acquisition module 1302 is used to acquire the status information of the serving cell based on the cell identifier, and to acquire the control plane signaling and user plane data of the target terminal based on the number information.

[0114] The determination module 1303 is used to determine multi-dimensional data information based on status information, control plane signaling, and user plane data. The multi-dimensional data information is used to describe the characteristic data associated with each cell grid. The characteristic data includes: first characteristic data, which is used to describe the type information of the wireless network fault to be resolved generated by the corresponding cell grid.

[0115] The first processing module 1304 is used to process multi-dimensional data information based on artificial intelligence (AI) to obtain candidate processing information corresponding to the wireless network fault to be resolved.

[0116] The second processing module 1305 is used to process the wireless network fault to be resolved based on the candidate processing information, obtain the reference processing result, and determine the target processing information based on the candidate processing information and the reference processing result.

[0117] It should be noted that the foregoing explanation of the wireless network fault handling method also applies to the wireless network fault handling device of this embodiment, and will not be repeated here.

[0118] In this embodiment, the target terminal is tested based on a test task to obtain test data corresponding to the test task. The test data includes the cell identifier of the serving cell and the number information of the target terminal. Based on the cell identifier, the status information of the serving cell is obtained, and based on the number information, the control plane signaling and user plane data of the target terminal are obtained. Based on the status information, control plane signaling, and user plane data, multi-dimensional data information is determined. The multi-dimensional data information is used to describe the feature data related to each cell grid. The feature data includes: first feature data, which describes the type information of the wireless network fault to be resolved generated by the corresponding cell grid. Based on artificial intelligence (AI), the multi-dimensional data information is processed to obtain candidate processing information corresponding to the wireless network fault to be resolved. The wireless network fault to be resolved is processed according to the candidate processing information to obtain a reference processing result. Based on the candidate processing information and the reference processing result, the target processing information is determined. Because it uses artificial intelligence (AI) to process multi-dimensional data and obtain candidate processing information corresponding to the wireless network fault to be resolved, it can improve the efficiency and accuracy of acquiring candidate processing information. This can effectively guide the handling of wireless network faults. When backtracking tests are performed on wireless network faults based on the candidate processing information determined by AI, and the target processing information is determined based on the reference processing results obtained from the backtracking tests, the accuracy of the target processing information determination can be effectively improved. This allows for convenient and rapid determination of the processing information used to resolve wireless network faults, and also improves the quality of the determined processing information.

[0119] Figure 14 A block diagram of an exemplary electronic device suitable for implementing embodiments of the present disclosure is shown. Figure 14 The electronic device 12 shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments disclosed herein.

[0120] like Figure 14 As shown, the electronic device 12 is represented in the form of a general-purpose computing device. The components of the electronic device 12 may include, but are not limited to: one or more processors or processing units 16, memory 28, and bus 18 connecting different system components (including memory 28 and processing unit 16).

[0121] Bus 18 represents one or more of several bus architectures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of the various bus architectures. Examples of these architectures include, but are not limited to, the Industry Standard Architecture (ISA) bus, the Micro Channel Architecture (MAC) bus, the Enhanced ISA bus, the Video Electronics Standards Association (VESA) local bus, and the Peripheral Component Interconnect (PCI) bus.

[0122] Electronic device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by electronic device 12, including volatile and non-volatile media, removable and non-removable media.

[0123] Memory 28 may include computer system readable media in the form of volatile memory, such as Random Access Memory (RAM) 30 and / or cache 32. Electronic device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 34 may be used to read and write non-removable, non-volatile magnetic media (… Figure 14 Not shown; usually referred to as a "hard drive".

[0124] although Figure 14Not shown, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk") and an optical disc drive for reading and writing to a removable non-volatile optical disc (e.g., a compact disc read-only memory (CD-ROM), a digital video disc read-only memory (DVD-ROM), or other optical media) may be provided. In these cases, each drive may be connected to bus 18 via one or more data media interfaces. Memory 28 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the embodiments of this disclosure.

[0125] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in memory 28. Such program modules 42 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment. Program modules 42 typically perform the functions and / or methods described in the embodiments of this disclosure.

[0126] Electronic device 12 can also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, etc.), and with one or more devices that enable human interaction with electronic device 12, and / or with any device that enables electronic device 12 to communicate with one or more other computing devices (e.g., network card, modem, etc.). This communication can be performed via input / output (I / O) interface 22. Furthermore, electronic device 12 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 20. As shown, network adapter 20 communicates with other modules of electronic device 12 via bus 18. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with electronic device 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0127] The processing unit 16 executes various functional applications and data processing by running programs stored in the memory 28, such as implementing the wireless network fault handling method mentioned in the foregoing embodiments.

[0128] To implement the above embodiments, this disclosure also proposes an electronic device, including: a processor and a memory communicatively connected to the processor; the memory stores computer execution instructions; the processor executes the computer execution instructions stored in the memory to implement the method provided in the foregoing embodiments.

[0129] To implement the above embodiments, this disclosure also proposes a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the methods provided in the foregoing embodiments.

[0130] To implement the above embodiments, this disclosure also proposes a computer program product, including a computer program that, when executed by a processor, implements the methods provided in the foregoing embodiments.

[0131] The collection, storage, use, processing, transmission, provision, and disclosure of user personal information involved in this disclosure all comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0132] It should be noted that personal information collected from users should be used for legitimate and reasonable purposes and should not be shared or sold outside of these legitimate uses. Furthermore, such collection / sharing should only be conducted after receiving the user's informed consent, including but not limited to notifying the user to read the user agreement / user notice and sign an agreement / authorization that includes authorization of relevant user information before the user uses the function. In addition, any necessary steps must be taken to protect and safeguard access to such personal information data and ensure that others with access to personal information data comply with their privacy policies and procedures.

[0133] This disclosure is intended to provide implementation schemes for users to selectively prevent the use or access to their personal information data. Specifically, this disclosure is intended to provide hardware and / or software to prevent or block access to such personal information data. Once personal information data is no longer needed, risks can be minimized by restricting data collection and deleting data. Furthermore, where applicable, such personal information is de-identified to protect user privacy.

[0134] In the foregoing descriptions of the embodiments, the terms "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of this disclosure. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0135] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this disclosure, "a plurality of" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0136] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing custom logic functions or processes, and the scope of preferred embodiments of this disclosure includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as will be understood by those skilled in the art to which embodiments of this disclosure pertain.

[0137] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0138] It should be understood that various parts of this disclosure can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0139] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0140] Furthermore, the functional units in the various embodiments of this disclosure can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0141] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of the present disclosure have been shown and described above, it is to be understood that the above embodiments are exemplary and should not be construed as limiting the present disclosure. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present disclosure.

Claims

1. A method for handling wireless network faults, characterized in that, Includes the following steps: The target terminal is tested based on the test task to obtain test data corresponding to the test task. The test data includes: the cell identifier of the serving cell and the number information of the target terminal. Based on the cell identifier, obtain the status information of the serving cell, and based on the number information, obtain the control plane signaling and user plane data of the target terminal; Based on the state information, the control plane signaling, and the user plane data, multidimensional data information is determined, wherein the multidimensional data information is used to describe the feature data associated with each cell grid, and the feature data includes: first feature data, second feature data, and third feature data. The first feature data is used to describe the type information of the unresolved wireless network fault generated by the corresponding cell grid, the second feature data is used to describe the characteristics of the serving cell to which the cell grid belongs, obtained from testing, and the third feature data is used to describe the characteristics of the neighboring cells associated with the corresponding cell grid, obtained from testing. Based on artificial intelligence (AI) processing of the multidimensional data information, candidate processing information corresponding to the wireless network fault to be resolved is obtained; The wireless network fault to be resolved is processed according to the candidate processing information to obtain a reference processing result, and the target processing information is determined according to the candidate processing information and the reference processing result. The process of processing the multi-dimensional data information based on artificial intelligence (AI) to obtain candidate processing information corresponding to the wireless network fault to be resolved includes: The multidimensional data information is provided to the processing information generation model in the first network. The processing information generation model is used to process the multidimensional data information to obtain initial processing information, which includes software parameter optimization information and hardware adjustment optimization information. The security level of the first network is higher than that of the second network. The second network includes a User Plane Function (UPF) network element. The first network is connected to the UPF network element through an N6 interface. The first network also includes a gateway. The slice differentials (SDs) of the network slices on the radio side, core network side, and transmission side of the first network are the same. The slice and service type (SST) parameters of the network slices on the radio side, core network side, and transmission side of the first network are the same. Based on the software parameter optimization information, an adjustment command script is generated, and based on the hardware adjustment optimization information, an adjustment execution work order is generated. The adjustment command script and the adjustment execution work order are used as candidate processing information; The method further includes: establishing a communication connection with the operation and maintenance OMC entity and AI model library in the first network through the second network and the gateway in the first network, wherein the AI ​​model library includes the information processing generation model.

2. The method according to claim 1, characterized in that, The status information includes at least one of the following: operating status, engineering parameters, wireless configuration parameters, neighbor cell data, performance indicators, equipment alarm information, uplink interference data, and operating parameters of the base station where the serving cell is located.

3. The method according to claim 1, characterized in that, The step of testing the target terminal based on the test task to obtain test data corresponding to the test task includes: Determine the geographical location where the wireless network fault to be resolved occurred; Based on the aforementioned geographical location, determine the test geographical area; Obtain configuration information and configure test tasks corresponding to the test geographical range based on the configuration information.

4. The method according to claim 1, characterized in that, The information generation model is trained based on the following method: Collect sample data, wherein the sample data includes: sample test data corresponding to each historical wireless network failure, and sample processing information. The sample test data includes: sample features, wherein the sample features include: a first sample feature, a second sample feature, and a third sample feature. The first sample feature is used to describe the type information of each historical wireless network failure. The second sample feature is used to describe the characteristics of the serving cell involved in each historical wireless network failure. The third sample feature is used to describe the characteristics of the neighboring cells involved in each historical wireless network failure. The initial AI model is trained at least once based on the sample data until the trained AI model converges, and the trained AI model is used as the information generation model.

5. The method according to claim 1, characterized in that, The step of processing the unresolved wireless network fault according to the candidate processing information to obtain a reference processing result includes: The adjustment command script is sent to the OMC entity in the first network, and the adjustment execution work order is sent to the maintenance equipment through the first network. Receive the script execution result generated and sent by the OMC based on the adjustment command script, and receive the work order execution result generated and sent by the maintenance equipment based on the adjustment execution work order; The script execution result and the work order execution result are used as the reference processing result.

6. The method according to claim 4, characterized in that, The method further includes: The sample data is updated based on the multidimensional data information and the target processing information; The information generation model is iteratively trained based on the updated sample data to obtain a new information generation model.

7. The method according to any one of claims 1-6, characterized in that, The step of determining the target processing information based on the candidate processing information and the reference processing result includes: Based on the reference processing results, the target terminal is retested according to the test task to obtain the retest results; If the retest result meets the preset conditions, then the candidate processing information corresponding to the reference processing result will be used as the target processing information; If the retest result does not meet the preset conditions, new candidate processing information is re-determined based on the retest result, and a reference processing result is re-determined based on the new candidate processing information, until the new retest result obtained by processing the wireless network fault to be resolved based on the re-determined reference processing result meets the preset conditions, and the new candidate processing information is used as the target processing information.

8. A wireless network fault handling device, characterized in that, include: The testing module is used to test the target terminal based on the testing task and obtain test data corresponding to the testing task. The test data includes: the cell identifier of the serving cell and the number information of the target terminal. The acquisition module is used to acquire the status information of the serving cell based on the cell identifier, and to acquire the control plane signaling and user plane data of the target terminal based on the number information; The determination module is used to determine multi-dimensional data information based on the status information, the control plane signaling, and the user plane data. The multi-dimensional data information describes feature data associated with each cell grid. The feature data includes: first feature data, second feature data, and third feature data. The first feature data describes the type of wireless network fault to be resolved caused by the corresponding cell grid. The second feature data describes the characteristics of the serving cell to which the cell grid belongs, obtained from testing. The third feature data describes the characteristics of neighboring cells associated with the corresponding cell grid, obtained from testing. The first processing module is used to process the multi-dimensional data information based on artificial intelligence (AI) to obtain candidate processing information corresponding to the wireless network fault to be resolved. The second processing module is used to process the wireless network fault to be resolved according to the candidate processing information, obtain a reference processing result, and determine the target processing information according to the candidate processing information and the reference processing result. The process of processing the multi-dimensional data information based on artificial intelligence (AI) to obtain candidate processing information corresponding to the wireless network fault to be resolved includes: The multidimensional data information is provided to the processing information generation model in the first network. The processing information generation model is used to process the multidimensional data information to obtain initial processing information, which includes software parameter optimization information and hardware adjustment optimization information. The security level of the first network is higher than that of the second network. The second network includes a User Plane Function (UPF) network element. The first network is connected to the UPF network element through an N6 interface. The first network also includes a gateway. The slice differentials (SDs) of the network slices on the radio side, core network side, and transmission side of the first network are the same. The slice and service type (SST) parameters of the network slices on the radio side, core network side, and transmission side of the first network are the same. Based on the software parameter optimization information, an adjustment command script is generated, and based on the hardware adjustment optimization information, an adjustment execution work order is generated. The adjustment command script and the adjustment execution work order are used as candidate processing information; A communication connection is established with the operation and maintenance OMC entity and AI model library in the first network through the second network and the gateway in the first network, wherein the AI ​​model library includes the information processing generation model.

9. An electronic device, characterized in that, include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory to implement the method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1-7.

11. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method of any one of claims 1-7.

Images