Method, device and storage medium for determining mobile communication network complaint issues

Abstract

This application provides a method, apparatus, and storage medium for determining mobile communication network complaint issues, relating to the field of communication technology, and is used to solve the problem of how to determine network problems. The method includes: acquiring network problems of multiple candidate cells and a target factor for each candidate cell, the target factor reflecting the degree of correlation between the candidate cell and the user complaint; for each candidate cell, determining a target score based on the target factor to obtain a target score for each candidate cell, the target score indicating the probability that the candidate cell is the complained-about cell; and based on the target score and network problems of each candidate cell, determining the complained-about cell and its network problem from the multiple candidate cells.

Description

Technical Field

[0001] This application relates to the field of communication technology, and in particular to a method, apparatus and storage medium for determining complaints about mobile communication networks. Background Technology

[0002] Identifying network problems through analysis of complaints is a complex process. Traditional network problem identification workflows often struggle to pinpoint the root cause. For example, it may require conducting on-site testing to simulate user complaint scenarios. Next, it necessitates reviewing statistical data from various backend metrics and detailed signaling records to locate the issue. Finally, targeted testing is required to verify and improve the situation. Due to the complexity of this workflow, complaint handling personnel spend a significant amount of time on the problem identification and troubleshooting stages.

[0003] Therefore, how to identify network problems has become a pressing technical issue that needs to be addressed. Summary of the Invention

[0004] This application provides a method, apparatus, and storage medium for determining mobile communication network complaint issues, used to solve the problem of how to determine network problems.

[0005] To achieve the above objectives, this application adopts the following technical solution:

[0006] Firstly, this application provides a method for determining network issues in mobile communication networks. In this method, network issues of multiple candidate cells and a target factor for each candidate cell are obtained. The target factor reflects the degree of correlation between the candidate cell and the user complaint. For each candidate cell, a target score is determined based on the target factor to obtain the target score for each candidate cell. The target score indicates the probability that the candidate cell is the complained-about cell. Based on the target score and network issues of each candidate cell, the complained-about cell and its network issues are determined from the multiple candidate cells.

[0007] Based on the above technical solution, network problems of multiple candidate cells and target factors for each candidate cell are obtained. This allows for the association of candidate cells with user complaints. For each candidate cell, a target score is determined based on its target factor. By obtaining the target score for each candidate cell, the probability that each candidate cell is the complained-about cell can be calculated. Then, based on the target score and network problems of each candidate cell, the complained-about cell and its network problems are identified from the multiple candidate cells. In this way, by sorting the target scores of each candidate cell, the cell with the highest probability of being complained about can be obtained, enabling precise location of the problem source and improving the accuracy of network problem analysis. Furthermore, this reduces investigation time and improves the efficiency of network problem analysis.

[0008] In one possible design, network issues of multiple candidate cells and a target factor for each candidate cell are obtained. The target factor reflects the correlation between the candidate cell and the user complaint. For each candidate cell, a target score is determined based on the target factor, indicating the probability that the candidate cell is the complained-about cell. Based on the target score and network issues of each candidate cell, the complained-about cell and its network issues are identified from the multiple candidate cells.

[0009] In one possible design, the target factors include at least one of the following: distance factor, dwell time factor, time consistency factor, cell anomaly frequency factor, sampling point factor, and weak coverage grid factor. Based on each target factor of the candidate cell, a score is determined for each target factor. Based on the score corresponding to each target factor and the weight value of each target factor, a target score for the candidate cell is determined.

[0010] In one possible design, the user's complaint time and location are obtained. Based on the complaint time and location, multiple candidate cells are identified.

[0011] In one possible design, based on the complaint time, multiple first cells are identified. These first cells are those the user passed through during a target time period, which is related to the complaint time. Based on the complaint location, multiple second cells are identified. These second cells are those within a preset distance threshold from the complaint location. Multiple candidate cells are then identified; these candidate cells are those where the first and second cells overlap.

[0012] In one possible design, at least one alarm data point from a candidate cell is acquired, with each alarm data point corresponding to an alarm time period. For each alarm data point, if the user's complaint time falls within the corresponding alarm time period, the alarm data point is considered a network problem in the candidate cell.

[0013] In one possible design, if the alarm time period corresponding to at least one alarm data point does not include the complaint time, then the network metrics of the candidate cells are obtained. Based on the network metrics of the candidate cells, the network problems of the candidate cells are determined.

[0014] Secondly, this application provides a device for determining mobile communication network complaint issues, the device including an acquisition module and a processing module.

[0015] The acquisition module acquires network issues from multiple candidate cells, along with a target factor for each candidate cell. The target factor reflects the correlation between the candidate cell and the user complaint. The processing module, for each candidate cell, determines a target score based on its target factor, thus obtaining the target score for each candidate cell. The target score indicates the probability that the candidate cell is the complained-about cell. The processing module also identifies the complained-about cell and its network issues from the multiple candidate cells based on the target score and network issues of each candidate cell.

[0016] In one possible design, the target factors include at least one of the following: distance factor, dwell time factor, time consistency factor, cell anomaly frequency factor, sampling point factor, and weak coverage grid factor. The processing module is used to determine the score corresponding to each target factor based on each target factor of the candidate cell. The processing module is also used to determine the target score of the candidate cell based on the score corresponding to each target factor and the weight value of each target factor.

[0017] In one possible design, an acquisition module is used to acquire the user's complaint time and location. A processing module is used to determine multiple candidate cells based on the complaint time and location.

[0018] In one possible design, the processing module is used to determine multiple first cells based on the complaint time. The first cells are cells the user passed through during a target time period, which is related to the complaint time. The processing module is also used to determine multiple second cells based on the complaint location. The second cells are cells within a preset distance threshold from the complaint location. The processing module is further used to determine multiple candidate cells, which are cells where there is an overlap between the multiple first cells and the multiple second cells.

[0019] In one possible design, an acquisition module is used to acquire at least one alarm data point for a candidate cell, with each alarm data point corresponding to an alarm time period. A processing module is used to, for each alarm data point, if the user's complaint time falls within the corresponding alarm time period, then treat the alarm data as a network problem for a candidate cell.

[0020] In one possible design, an acquisition module is used to acquire network metrics for candidate cells if the alarm time period corresponding to at least one alarm data does not include the complaint time. A processing module is used to determine the network problem of the candidate cells based on their network metrics.

[0021] Thirdly, this application provides a device for determining mobile communication network complaint issues, the device comprising: a processor and a memory; the processor and the memory being coupled; the memory being used to store one or more programs, the one or more programs including computer-executable instructions, wherein when the device for determining mobile communication network complaint issues is running, the processor executes the computer-executable instructions stored in the memory to implement the method as described in the first aspect and any possible implementation thereof.

[0022] Fourthly, this application provides a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform the methods described in the first aspect and any possible implementation thereof.

[0023] Fifthly, this application provides a chip including a processor and a communication interface, the communication interface being coupled to the processor, the processor being used to run computer programs or instructions to implement the methods described in the first aspect and any possible implementation thereof.

[0024] Sixthly, this application provides a computer program product containing instructions that, when executed by a computer, cause the computer to perform the methods described in the first aspect and any possible implementation thereof.

[0025] In the above solution, the technical problems that can be solved and the technical effects that can be achieved by the device for determining mobile communication network complaint problems, computer equipment, computer storage medium, chip or computer program product can be referred to the technical problems and technical effects solved in the first aspect above, and will not be repeated here. Attached Figure Description

[0026] Figure 1 A flowchart illustrating a method for determining mobile communication network complaint issues, provided as an embodiment of this application;

[0027] Figure 2A schematic diagram illustrating an example of scene division provided in this application embodiment;

[0028] Figure 3 A schematic diagram illustrating another scenario division provided in this application embodiment;

[0029] Figure 4 A schematic diagram illustrating an example of a method for determining a grid radius provided in an embodiment of this application;

[0030] Figure 5 A schematic diagram illustrating an example of a cell grid distribution provided in this application embodiment;

[0031] Figure 6 A schematic diagram illustrating another example of cell grid distribution provided in this application embodiment;

[0032] Figure 7 A schematic diagram illustrating another example of cell grid distribution provided in this application embodiment;

[0033] Figure 8 A flowchart illustrating another method for determining mobile communication network complaint issues provided in this application embodiment;

[0034] Figure 9 A schematic diagram illustrating an example of a method for determining a complained-about cell provided in an embodiment of this application;

[0035] Figure 10 A schematic diagram illustrating an example of another method for determining the complained cell provided in this application embodiment;

[0036] Figure 11 A schematic diagram illustrating an example of another method for determining the complained cell provided in this application embodiment;

[0037] Figure 12 A schematic diagram of the structure of a device for determining mobile communication network complaint issues provided in an embodiment of this application;

[0038] Figure 13 A schematic diagram of another device for determining mobile communication network complaint issues provided in an embodiment of this application;

[0039] Figure 14 A conceptual partial view of a computer program product provided for an embodiment of this application. Detailed Implementation

[0040] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0041] The terms “first” and “second” in the specification and claims of this application are used to distinguish different objects, rather than to describe a specific order of objects.

[0042] Furthermore, the terms "comprising" and "having," and any variations thereof, used in the description of this application are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or modules is not limited to the steps or modules listed, but may optionally include other steps or modules not listed, or may optionally include other steps or modules inherent to such process, method, product, or device.

[0043] Furthermore, in the embodiments of this application, the words "exemplary" or "for example" are used to indicate that they are examples, illustrations, or descriptions. Any embodiment or design that is described as "exemplary" or "for example" in this application should not be construed as being more preferred or advantageous than other embodiments or design options. Specifically, the use of the words "exemplary" or "for example" is intended to present concepts in a concrete manner.

[0044] User complaints are a common phenomenon in mobile communication network operation. The main reasons for these complaints include network problems, package issues, tariff issues, terminal problems, service issues, and other related problems. Among these, network problems account for a large proportion of user complaints. Network problems can be further categorized into fault or alarm issues, coverage issues, interference issues, and capacity issues. These problems are classified into maintenance, optimization, and construction issues according to their handling procedures or responsible departments.

[0045] However, since most users are not technical professionals and are influenced by subjective feelings, they may provide incomplete or misleading problem descriptions. For example, they may inaccurately describe the time of the problem and the type of service network, make subjective assessments of signal strength or network speed, or attribute problems with the terminal or subscriber identity module (SIM) card to network issues.

[0046] Furthermore, analyzing network problems requires a certain level of professional expertise. Complaint handlers also need to respond to user complaints within a certain timeframe. For example, the average response time for network problems should be controlled within 24 hours, and should not exceed 72 hours at most. However, because some complaint handlers lack professional-level network analysis skills, they struggle to quickly and accurately identify the network problem when handling complaints.

[0047] In the traditional workflow of analyzing network problem complaints, the process is complex. For example, it requires conducting on-site tests to simulate user complaint scenarios. Then, it necessitates reviewing statistical data from various backend metrics and detailed signaling records to identify problems. Finally, targeted testing is required to verify improvements. Due to the complexity of this workflow, complaint handlers spend a significant amount of time on problem identification and investigation. This makes determining the root cause of mobile communication network complaints even more difficult.

[0048] Currently, AI models can be used to analyze complaints. However, this method is difficult to implement in practice due to factors such as data quality, computing resources, model generalization ability, and lack of interpretability. Furthermore, mobile network complaint analysis results often output multiple possible abnormal cells, making it impossible to directly determine the cell causing the complaint and the network problem within that cell. Some network problem complaint analysis methods focus too much on the complaint phenomenon and lack a comprehensive and in-depth analysis of the network problem. Moreover, they lack methods and measures to address issues such as inaccurate complaint timing and problem descriptions.

[0049] In some embodiments, effectively processing key complaint information output by users can improve the accuracy of information recording, reduce complaint processing time, and enable rapid and effective handling of user complaints.

[0050] However, this approach needs improvement in the accuracy of network problem analysis. If the problem is incorrectly characterized in the initial stage, the corresponding cell for the network problem may also be incorrect. Therefore, the preset model needs to be continuously updated and corrected. As a result, in practical applications, the network problem analysis workflow is lengthy and cumbersome, which not only affects the overall closed-loop processing efficiency but also increases the workload of experts. Furthermore, the cells associated with this method cannot be guaranteed to be cells that users have actually occupied; there is no necessary connection between the cells and the user complaint, and the accuracy of the user complaint handling results cannot be guaranteed.

[0051] To address the technical problems identified in the background section of this application, embodiments of this application provide a method for determining mobile communication network complaint issues. This method involves acquiring network issues from multiple candidate cells and a target factor for each candidate cell. This allows the candidate cells to be associated with user complaints. For each candidate cell, a target score is determined based on its target factor, thus obtaining the target score for each candidate cell. By obtaining the target score for each candidate cell, the probability that each candidate cell is the complained-about cell can be determined. Then, based on the target score and network issues of each candidate cell, the complained-about cell and its network issues are determined from the multiple candidate cells. In this way, by sorting the target scores of each candidate cell, the cell with the highest probability of being complained about is obtained, enabling precise location of the problem source and improving the accuracy of network problem analysis. Furthermore, it reduces investigation time and improves the efficiency of network problem analysis.

[0052] The embodiments of this application will now be described in detail with reference to the accompanying drawings.

[0053] like Figure 1 As shown in the embodiment of this application, a method for determining mobile communication network complaint issues is provided. The method includes:

[0054] S101, Network issues related to obtaining multiple candidate cells.

[0055] Among them, network problems are used to indicate network issues in candidate cells. Network problems include construction-related problems, fault alarm problems, weak grid coverage problems, weak cell coverage problems, strong cell interference problems, and limited cell capacity problems.

[0056] In one possible implementation, the user's complaint time and location are obtained. Based on the complaint time and location, multiple candidate cells are identified.

[0057] In one possible design, multiple first cells are determined based on the complaint time. Multiple second cells are determined based on the complaint location. Then, multiple candidate cells are determined. The first cells are those the user passed through during a target time period, which is related to the complaint time. The second cells are those within a preset distance threshold from the complaint location. The candidate cells are those where there is overlap between the multiple first cells and the multiple second cells.

[0058] The complaint time refers to the time when the complaint was filed and the anomaly was reported.

[0059] For example, the target time period could be 24 hours prior to the time of the complaint.

[0060] In some embodiments, the preset distance threshold includes a first preset distance threshold and a second preset distance threshold, and the second cell includes a first location cell and a second location cell. The first location cell is a candidate cell divided based on the scene where the complaint location is located, and the second location cell is a candidate cell divided based on the grid where the complaint location is located. The first location cell is determined based on the first preset distance threshold, and the second location cell is determined based on the second preset distance threshold.

[0061] In one possible implementation, based on the complaint location, the target scenario where the complaint location is located is determined, thereby determining a first preset distance threshold corresponding to the target scenario. A first location cell is obtained based on the first preset distance threshold. The target scenario is used to indicate the network coverage of the area where the complaint location is located. Target scenarios include urban scenarios, county-level scenarios, township-level scenarios, and rural scenarios.

[0062] In one possible design, the device for determining mobile communication network complaint issues pre-stores a first preset distance threshold corresponding to each target scenario.

[0063] For example, the first preset distance threshold for urban scenes can be 300 meters, the first preset distance threshold for county scenes can be 500 meters, the first preset distance threshold for township scenes can be 800 meters, and the first preset distance threshold for rural scenes can be 1200 meters.

[0064] It's important to note that before determining the target scenario of the complaint location, it's necessary to segment the area where the complaint is located. This involves obtaining regional information, including the urbanization level, population density, network resources, network coverage, and traffic volume of each region. Based on this regional information, the area where the complaint is located is then segmented into scenarios.

[0065] For example, such as Figure 2 The diagram illustrates an example of scene segmentation provided in this application. Urban scene 201 is a single, concentrated black area; county scene 202 consists of three black areas; the remaining black area is township scene 203; and rural scene 204 is a white area. The segmented area of ​​rural scene 204 is larger than that of urban scene 201. The segmentation of urban scene 201 is more concentrated, while that of county scene 202 is more dispersed, and the segmentation of township scene 203 is even more dispersed than that of county scene 202.

[0066] For example, such as Figure 3The diagram illustrates another example of scene division provided in this application. In this diagram, urban scene 301 is a single, concentrated black area; county scene 302 consists of three black areas; the remaining black area is township scene 303; and rural scene 304 is a white area. The rural scene 304 is larger than the urban scene 301. The urban scene 301 is more concentrated, the county scene 302 is more dispersed, and the township scene 303 is more dispersed than the county scene 302. Figure 3 The urban scene in the text is divided into smaller areas than Figure 2 The division of urban scenes into regions. Figure 3 The rural scenes in the text are divided into larger areas than Figure 2 The division of rural scenes in the film into different regions. Figure 3 The county town scene is divided into areas larger than Figure 2 The division of the county town scene in the game.

[0067] In another possible design, the average distance between existing 4G / 5G sites in the target scenario is calculated. Based on the average distance between existing 4G / 5G sites in the target scenario, a first preset distance threshold is obtained for each scenario.

[0068] In another possible implementation, multiple grids exist. Multiple first grids are obtained, centered on the target grid where the complaint location is located. Each first grid is a grid whose center is within a second preset distance threshold from the target grid. The base station cell whose coverage area is within the first grid is designated as the second location cell.

[0069] In one possible design, the grid side length is obtained. Based on the grid side length, a second preset distance threshold is determined.

[0070] In this embodiment of the application, the second preset distance threshold is The value between 2.5 times the grid side length and the grid side length.

[0071] For example, the second preset distance threshold can be 3 times the grid side length.

[0072] For example, if the grid side length is 50 meters, then the second preset distance threshold can be 150.875 meters.

[0073] For example, such as Figure 4 The diagram illustrates an example of a method for determining a grid radius according to an embodiment of this application. The grid side length (d) is obtained. A second preset distance threshold is obtained based on the grid side length. Multiple second grids 402 are obtained, centered on the grid 401 where the complaint location is located, based on the second preset distance threshold. Base station cells covering the second grids 402 are designated as second location cells.

[0074] In one possible design, the base station cells whose coverage area is in the first grid are obtained based on the acquired measurement report (MR) data.

[0075] Optionally, the complaint location can be the location where the complaint was initiated or the location where the anomaly occurred.

[0076] It should be noted that the preset distance threshold obtained again is larger than the preset distance threshold obtained the first time.

[0077] S102. Obtain the target factor for each candidate cell.

[0078] The target factor is used to reflect the degree of correlation between candidate cells and user complaints.

[0079] In one possible implementation, measurement report (MR) data and key performance indicator (KPI) data are acquired, and the target factor for each candidate cell is obtained based on the MR data and KPI data.

[0080] In one possible design, the target factors include at least one of the following: distance factor, dwell time factor, time consistency factor, cell anomaly frequency factor, sampling point factor, and weak coverage grid factor. The distance factor indicates the correlation between the distance between the candidate cell and the complaint location and the user complaint; the dwell time factor indicates the correlation between the user's dwell time in the candidate cell and the user complaint; the time consistency factor indicates the correlation between the difference between the time period of the candidate cell's anomaly and the complaint time, and the user complaint; the cell anomaly frequency factor indicates the correlation between the time period of the candidate cell's anomaly and the user complaint; the sampling point factor indicates the correlation between the candidate cell's coverage network and the user complaint; and the weak coverage grid factor indicates the correlation between the candidate cell's signal strength and the user complaint.

[0081] It's important to note that in mobile communications, wireless signal strength decreases with distance. To ensure communication continuity and quality, users prioritize staying in cells with stronger signals through cell reselection or handover mechanisms. Therefore, cells closer to the user are generally more relevant to their experience. If a user complains about signal or communication quality issues, cells closer to the location of the complaint are likely the root cause. Thus, the distance factor is a crucial indicator for identifying the cell in question.

[0082] It should be noted that a user's prolonged stay in a particular residential area indicates that the network quality of that area has a significant impact on user experience. Therefore, if a residential area with a high percentage of users staying there experiences network problems, it is likely to be the root cause of user complaints. Thus, the dwell time factor is an important reference indicator for identifying the residential areas that have been the subject of complaints.

[0083] It should be noted that if the time of a user complaint highly overlaps with or closely matches the user's dwell time in a particular residential area, the likelihood of that residential area being directly related to the complaint is higher. When an anomaly is found in the indicators of a residential area visited by a user, a time consistency assessment is necessary. Therefore, the time consistency factor is an important reference indicator for identifying the residential area involved in the complaint.

[0084] It should be noted that if a complaining user resides in a particular community at multiple times throughout the day (i.e., 24 hours prior to the time of the complaint), and that community exhibits abnormal indicators for most of the time, then that community is highly likely to be the community being complained about. Therefore, the community anomaly frequency factor is an important reference indicator for identifying the community being complained about.

[0085] It should be noted that within the vicinity of the complaint location, the more sampling points a cell has, the greater its contribution to network coverage and communication services in the area, potentially making it the primary serving cell for that region. Therefore, there is a high correlation between this cell and the user's complaint in the area; that is, the user's complaint is very likely related to the network coverage and service quality provided by this cell. Thus, the sampling point factor is an important reference indicator for identifying the cell being complained about.

[0086] It should be noted that weak coverage grids are grids with poor signal or signal dead zones, and these grids are often high-incidence areas for network problems. For a given cell, the percentage of weak coverage grids is one of the important indicators for evaluating the network coverage quality of the cell. There is a direct correlation between weak coverage grids and complaints, and it is an important basis for identifying the cells being complained about. Therefore, the weak coverage grid factor is an important reference indicator for identifying the cells being complained about.

[0087] S103. For each candidate cell, determine the target score of the candidate cell based on the target factor of the candidate cell, so as to obtain the target score of each candidate cell.

[0088] The target score indicates the probability that a candidate cell is the complained cell.

[0089] In one possible implementation, a score is determined for each target factor based on the candidate cell. The target score for the candidate cell is then determined based on the score for each target factor and the weight value of each target factor.

[0090] For example, the distance between the base station cell and the location of the complaint can satisfy Formula 1.

[0091]

[0092] Where L is the distance between the base station cell and the location of the complaint, R is the average radius of the Earth, lon1 is the longitude of the base station cell, lat1 is the latitude of the base station cell, lon2 is the longitude of the location of the complaint, and lat2 is the latitude of the location of the complaint.

[0093] Alternatively, R is 6,371,393 meters.

[0094] In one possible design, a distance score is obtained by calculating the distance between a first preset distance threshold and the distance between the base station cell and the location of the complaint.

[0095] For example, a score of 100 is awarded if the distance is less than 0.1 times the first preset distance threshold, and 10 points are deducted for every 0.1 times the first preset distance threshold increase in distance, until the score reaches 0. The maximum score range is set to 100 points, and the minimum score is 0 points.

[0096] For example, the distance score can satisfy Formula 2.

[0097]

[0098] Where D1 is the first preset distance threshold, and INT() is the rounding function.

[0099] For example, as shown in Table 1, multiple distance scores are illustrated.

[0100] Table 1

[0101]

[0102] Specifically, in an urban area scenario, with a first preset distance threshold (i.e., coverage radius D1) of 500 meters and 0.1 times the first preset distance threshold of 50 meters, the following distance scores are calculated: 100 for distances between the base station cell and the complaint location (i.e., the distance between the cell and the complaint point) within the range of 0 to 49 meters; 90 for distances between the base station cell and the complaint location within the range of 50 to 99 meters; 80 for distances between the base station cell and the complaint location within the range of 100 to 149 meters; 20 for distances between the base station cell and the complaint location within the range of 400 to 449 meters; 10 for distances between the base station cell and the complaint location within the range of 450 to 499 meters; and 0 for distances greater than 500 meters.

[0103] In one possible design, user trajectory information is obtained based on the time of the user complaint. This trajectory information indicates the duration the user spent in each candidate cell within the 24 hours prior to the complaint. The total user dwell time is summed across all candidate cells. The ratio of the user's dwell time in each candidate cell to the total dwell time is calculated to obtain the dwell time percentage. Candidate cells are then sorted according to their dwell time percentages to obtain a dwell time score for each candidate cell.

[0104] For example, the maximum score for dwell time can be 100 points, and the minimum score can be 0 points. The community with the highest percentage of dwell time is ranked first and scores 100 points. The second-ranked community scores 90 points. The community with the lowest percentage of dwell time is ranked last and scores 0 points. And so on, deducting 10 points for each lower-ranked community, until the score is reduced to 0.

[0105] For example, the dwell time score can satisfy Formula 3.

[0106]

[0107] Where n represents the ranking of the candidate cell by the percentage of dwell time, sorted from high to low according to the percentage of dwell time.

[0108] For example, as shown in Table 2, multiple dwell time scores are presented.

[0109] Table 2

[0110]

[0111] The complaint number is 185xxxx1111, the cell ID is Cell_1, the cell network type is 4G, the cell dwell time is 39313s, and the total user dwell time is 85366s. Ranking first in dwell time, the dwell time score is 100. The complaint number is 185xxxx1111, the cell ID is Cell_2, the cell network type is 4G, the cell dwell time is 14393s, and the total user dwell time is 85366s. Ranking second in dwell time, the dwell time score is 90.

[0112] For an introduction to other length of stay scores in Table 2, please refer to the above introduction to length of stay scores; it will not be repeated here.

[0113] In one possible design, the dwell time period and network metric anomalies are obtained. Based on the complaint time and each time point within the dwell time period (i.e., the dwell time point), multiple first time differences are obtained. Each candidate cell is ranked based on the first time differences and network metric anomalies, resulting in a time consistency score for each candidate cell. The dwell time period is the time the user spends there. The first time difference is the hourly difference between the complaint time and the dwell time point. Network anomalies include normal conditions and network metric anomalies. Network metrics include cell-level metrics, which include weak coverage metrics, strong interference metrics, and capacity-limited metrics.

[0114] For example, the maximum time consistency score is 100 points, and the minimum is 0 points. If the first time difference of a candidate cell at a given time point is 0, and the network metrics are abnormal, then the candidate cell will score 100 points at that time point. For every hour the first time difference increases, the score decreases by 10 points. If the first time difference of a candidate cell is 10 hours, then the candidate cell will score 0 points at that time point.

[0115] It should be noted that when a candidate cell has multiple dwell time points, multiple first time difference scores are obtained for the candidate cell, and the highest score among them is taken as the final score of the candidate cell.

[0116] For example, the time consistency score can satisfy Formula 4.

[0117]

[0118] Where Δt is the first time difference.

[0119] For example, Δt can satisfy Formula 5.

[0120] Δt = |T1 - T2| (Formula 5)

[0121] Where T1 is the time of the complaint and T2 is the time of stay.

[0122] It should be noted that the time consistency score includes weak coverage time consistency score, strong interference time consistency score, and capacity-constrained time consistency score.

[0123] For example, as shown in Table 3, multiple weak coverage time consistency scores are presented, taking the weak coverage index of a cell as an example.

[0124] Table 3

[0125]

[0126] Among them, the complaint number is 185xxxx1111, the cell ID is Cell_1, the complaint time is 21:00 on July 21, 2024, the user's residence time is 01:00 on July 22, 2024, the time difference between the complaint time and the user's residence time is 6 hours, the cell is normal, and the weak coverage time consistency score for this residence time point is not calculated. The complaint number is 185xxxx1111, the cell ID is Cell_1, the complaint time is 21:00 on July 21, 2024, the user's residence time is 21:00 on July 21, 2024, the time difference between the complaint time and the user's residence time is 0, the cell has abnormal weak coverage, and the weak coverage time consistency score for this residence time point is 100. Since this weak coverage time consistency score is the largest among the multiple weak coverage time consistency scores for Cell_1, the weak coverage time consistency score for Cell_1 is 100. The complaint number is 185xxxx1111, the cell ID is Cell_2, the complaint period is 21:00 on July 21, 2024, and the user's dwell time is 01:00 on July 22, 2024. The time difference between the complaint period and the user's dwell time is 4 hours, indicating an anomaly in weak cell coverage. The weak coverage time consistency score at this dwell time point is 60. Since the highest weak coverage time consistency score for Cell_2 is 80, not 60, the weak coverage time consistency score for Cell_2 is 80.

[0127] Table 3 provides an introduction to other time consistency scores. Please refer to the above introduction to time consistency scores for details, which will not be repeated here.

[0128] In one possible design, the cell anomaly frequency is calculated by dividing the total number of dwell time periods (i.e., total dwell time periods) by the number of time periods in which network indicators in the cell are abnormal (i.e., the number of abnormal cell time periods). The abnormal cell frequency is then multiplied by 100 and rounded to the nearest integer to obtain the cell anomaly frequency score. The number of abnormal cell time periods includes the number of periods with weak cell coverage, the number of periods with strong interference, and the number of periods with limited cell capacity.

[0129] For example, the cell anomaly frequency score can satisfy Formula 6.

[0130]

[0131] Optionally, the maximum score for abnormal frequency of a cell is 100 points, and the minimum score is 0 points.

[0132] It should be noted that the abnormal frequency score of a cell includes the abnormal frequency score of a cell with weak coverage, the abnormal frequency score of a cell with strong interference, and the abnormal frequency score of a cell with limited capacity.

[0133] For example, as shown in Table 4, the weak coverage index of a cell is used as an example, which shows the scores of multiple weak coverage anomaly frequencies.

[0134] Table 4

[0135]

[0136] Among them, the complaint number is 185xxxx1111, the cell ID is Cell_1, the complaint time is 21:00 on July 21, 2024, and the total number of time periods is 6. Cell_1 experienced weak coverage issues in 2 time periods, so the cell weak coverage anomaly frequency score is 33.33. The complaint number is 185xxxx1111, the cell ID is Cell_2, the complaint time is 21:00 on July 21, 2024, and the total number of time periods is 6. Cell_2 experienced weak coverage issues in 4 time periods, so the cell weak coverage anomaly frequency score is 66.67.

[0137] In one possible design, a first grid is obtained, and the MR sampling points of all candidate cells falling within the first grid are used as the denominator. For each candidate cell, the MR sampling points falling within the first grid are used as the numerator, yielding the sampling point percentage for each candidate cell. The sampling point percentage is the ratio of the numerator to the denominator. The sampling point percentages of each candidate cell are then sorted from highest to lowest to obtain the sampling point score.

[0138] For example, the maximum score for a sampling point is 100 points, and the minimum score is 0 points. The candidate cell with the largest percentage of sampling points ranks first and scores 100 points. Starting from second place, the score decreases by 10 points for each subsequent ranking, until the score reaches 0 points. The candidate cell with the smallest percentage of sampling points ranks last and scores 0 points.

[0139] For example, the sampling point scores can satisfy Formula 7.

[0140]

[0141] Where n represents the ranking of the percentage of sampling points, sorted from high to low according to the percentage of sampling points.

[0142] In one possible design, the first grid cell is obtained. The total number of grid cells containing all candidate cells in the first grid cell is used as the denominator for coverage calculation. The number of weak coverage grid cells within the total number of grid cells for a candidate cell is used as the numerator for coverage calculation, resulting in the weak coverage grid percentage. The weak coverage grid percentage is the ratio of the coverage numerator to the coverage denominator. The weak coverage grid percentages of each candidate cell are sorted from highest to lowest to obtain the weak coverage grid score.

[0143] For example, the maximum score for a weak coverage raster is 100 points, and the minimum score is 0 points. The candidate cell with the largest proportion of weak coverage raster is ranked first and scores 100 points. Starting from second place, the score decreases by 10 points for each subsequent ranking, until the score reaches 0 points. The candidate cell with the smallest proportion of weak coverage raster is ranked last and scores 0 points.

[0144] For example, such as Figure 5 The diagram shown is an example of a cell grid distribution provided in this application. Within two concentric rings of grids (i.e., 25 grids) around the complaint location with a radius of a second preset distance, there are 14 grids 501 containing Cell_1, of which 7 are weak coverage grids 502.

[0145] For example, such as Figure 6 The diagram shows an example of another cell grid distribution provided in this application. Within two concentric rings of grids (i.e., 25 grids) around the complaint location with a radius of a second preset distance, there are 12 grids 601 containing Cell_2. Among these, 6 are weak coverage grids 602.

[0146] For example, such as Figure 7 The diagram shown is an example of another cell grid distribution provided in this application embodiment. The grid 701 after overlaying Cell_1 cell and Cell_2 cell has 19 cells, and the weak coverage grid 702 has 11 cells.

[0147] For example, the score of a weakly covered raster in Cell_1 can satisfy Equation 8.

[0148]

[0149] For example, the Cell_2 weak coverage raster number score can satisfy Formula 9.

[0150]

[0151] For example, the score of a weakly covered raster can satisfy Equation 10.

[0152]

[0153] Where n represents the ranking of weakly covered raster percentages, sorted from high to low according to the percentage of weakly covered raster.

[0154] In one possible implementation, the weight coefficient of each target factor is obtained, and the target score of each candidate cell is obtained based on the weight coefficient and the score of the target factor.

[0155] In one possible design, based on the network problem of the candidate cells, the corresponding target factors and their weight coefficients are determined. Based on the weight coefficients and scores of the target factors, the target score for each candidate cell is obtained.

[0156] For example, as shown in Table 5, the weight coefficients of the target factors are illustrated.

[0157] Table 5

[0158]

[0159]

[0160] Among them, distance score is a general indicator with a weight of 30%, and dwell time score is a general indicator with a weight of 30%.

[0161] Table 5 provides an introduction to the weight coefficients of other target factors. For details on the weight coefficients of target factors, please refer to the above introduction. It will not be repeated here.

[0162] It should be noted that the data for distance and dwell time metrics are derived from user trajectory data. This data has higher accuracy and refinement compared to grid and cell data, and more directly reflects the user's actual situation. Therefore, a higher weighting coefficient is considered.

[0163] For example, the target score for the candidate cell weak coverage problem can satisfy Formula 11.

[0164] Final total score =

[0165] Distance score × 30% + Dwell time score × 30% + Time consistency score - Weak cell coverage × 20% +

[0166] Indicator Abnormality Frequency Score - Weak Coverage in the Cell × 20% Formula Eleven.

[0167] S104. Based on the target score of each candidate cell and the network problem of each candidate cell, determine the complained cell and the network problem of the complained cell from multiple candidate cells.

[0168] In one possible implementation, multiple candidate cells are ranked based on the target score of each candidate cell. Among the multiple candidate cells, the candidate cell with the highest target score is the complained-about cell. Multiple candidate cells ranked after the complained-about cell, and whose scores are greater than or equal to 60, are then considered as candidate complained-about cells.

[0169] Understandably, this allows for the rapid identification of the network problem in the complained-about community from among multiple candidate communities if the network issue in the complained-about community differs from the network issue reported by the user.

[0170] In some embodiments, after identifying the complained cell and the network problem of the complained cell, a response text is output.

[0171] It should be noted that the device for determining mobile communication network complaint issues stores corresponding response texts for network problems. These response texts include at least one of the following: maintenance response text, construction response text, and optimization response text. If, after re-acquiring the preset distance threshold, multiple candidate cells still cannot be determined, it is determined that a coverage blind spot exists at the location of the complaint, and the network problem at the user's complaint location is classified as a construction problem. A construction response text is then output.

[0172] Based on the above-described scheme, network problems of multiple candidate cells and target factors for each candidate cell are obtained. This allows for the association of candidate cells with user complaints. For each candidate cell, a target score is determined based on its target factor. By obtaining the target score for each candidate cell, the probability that each candidate cell is the complained-about cell can be calculated. Then, based on the target score and network problems of each candidate cell, the complained-about cell and its network problems are identified from the multiple candidate cells. In this way, by sorting the target scores of each candidate cell, the cell with the highest probability of being complained about can be obtained, enabling precise location of the problem source and improving the accuracy of network problem analysis. Furthermore, this reduces investigation time and improves the efficiency of network problem analysis.

[0173] like Figure 8 As shown, this is another method for determining mobile communication network complaint issues provided in an embodiment of this application. In this method, step S101 may include:

[0174] S801. Obtain at least one alarm data from the candidate cell.

[0175] Each alarm data point corresponds to an alarm time period.

[0176] In one possible implementation, at least one alarm data of the candidate cell is obtained by accessing the alarm management module.

[0177] For example, as shown in Table 6, multiple data sources are illustrated.

[0178] Table 6

[0179] Data source Time granularity object granularity Network granularity Fault / Alarm Data real time event Net Element User trajectory data Stay time film user residential area Grid cell-level MR data sky 50-meter grid residential area Community-level MR data Hour Net Element residential area Community-level KPI data Hour Net Element residential area Community-level work parameters sky Net Element residential area

[0180] In this application's embodiments, the data sources include fault / alarm data, user trajectory data, grid cell-level MR data, cell-level MR data, cell-level KPI data, and cell-level operating parameters. The time granularity of fault / alarm data is real-time, the object granularity is event-level, and the network granularity is network element-level. The time granularity of user trajectory data is dwell time slice, the object granularity is user-level, and the network granularity is cell-level.

[0181] Table 6 provides an introduction to other data sources. Please refer to the above introduction to data sources for details, which will not be repeated here.

[0182] Understandably, raster-based cell-level MR data primarily focuses on the spatial dimension, significantly improving spatial accuracy by adding raster positioning attributes. Cell-level MR data, on the other hand, emphasizes the temporal dimension, employing finer granularity to refine the data compared to raster-based cell-level MR data, thus strengthening its connection with the user's time frame. These two types of data complement each other in both the temporal and spatial dimensions, jointly ensuring the accuracy of the analysis results.

[0183] S802. For each alarm data, determine whether the user's complaint time falls within the alarm time period corresponding to the alarm data.

[0184] In some embodiments, if the user's complaint time falls within the alarm time period corresponding to the alarm data, then S803 is executed.

[0185] In other embodiments, if the user's complaint time is not within the alarm time period corresponding to the alarm data, then S804 is executed.

[0186] S803, network problems that use alarm data as candidate cells.

[0187] In one possible implementation, if only one alarm data exists, that alarm data is considered a network problem in a candidate cell.

[0188] In one possible design, the network problem corresponding to the alarm data is a fault alarm problem.

[0189] In another possible implementation, if multiple alarm data exist, the alarm data with the highest priority is selected as the network problem of the candidate cell based on the priority of the alarm data.

[0190] In one possible design, the device for determining mobile communication network complaint issues pre-stores the priority of alarm data.

[0191] In some embodiments, after identifying alarm data as a network problem in a candidate cell, the candidate cell is then identified as the complained-about cell.

[0192] S804. Based on the network indicators of candidate cells, determine the network problems of candidate cells.

[0193] In one possible implementation, network metrics for candidate cells are obtained. Based on these metrics, network issues in the candidate cells are determined. Network metrics also include grid-based metrics.

[0194] In one possible design, grid-based metrics include the percentage of weak coverage grids. The process involves determining if the percentage of weak coverage grids is greater than zero. If it is, the candidate cell's network problem is classified as a weak coverage grid problem. If it is zero, the candidate cell's network problem is determined based on weak coverage metrics, strong interference metrics, and capacity-constrained metrics.

[0195] It should be noted that if the total number of MR sampling points in a cell grid is greater than 30, and the percentage of sampling points with RSRP>=-110 is less than 90%, then the grid is a weak coverage grid.

[0196] It should be noted that weak coverage indicators can identify weak coverage issues in a cell. Strong interference indicators can identify strong interference issues in a cell. Capacity-limited indicators can identify capacity-limited issues in a cell.

[0197] In one possible design, if a candidate cell shows an anomaly in any of the following indicators: weak coverage, strong interference, or limited capacity, then the network problem corresponding to the candidate cell can be identified.

[0198] In another possible design, if a candidate cell exhibits anomalies in at least two of the following categories: weak coverage, strong interference, and limited capacity, then the time consistency score corresponding to each category is summed and compared with the cell anomaly frequency score to obtain the network problem of the candidate cell.

[0199] For example, the sum of the time consistency score and the abnormal frequency score of a cell for weak coverage is A; the sum of the time consistency score and the abnormal frequency score of a cell for strong interference is B; and the sum of the time consistency score and the abnormal frequency score of a cell for capacity-constrained indicators is C. If A is greater than B and A is greater than C, then the network problem of the candidate cell is a weak coverage problem. If B is greater than A and B is greater than C, then the network problem of the candidate cell is a strong interference problem.

[0200] For example, as shown in Table 7, several cell-level network metrics and anomaly thresholds are illustrated.

[0201] Table 7

[0202]

[0203] The indicators are categorized into weak coverage, strong interference, and capacity limitation. The sources of these indicators are MR data and KPI data. The indicator for identifying weak coverage is the percentage of samples with RSRP >= -110. Indicators for identifying strong interference include the percentage of samples with modulo 3 interference (MOD3), the percentage of samples with overlapping coverage, the percentage of samples with a signal-to-interference-plus-noise ratio (SINR) greater than 0, the average interference level per physical resource block (PRB), the average CQI, and the CQI good rate. Indicators for identifying capacity limitation include the number of RRC connection establishment failures, the number of e-Rab establishment congestion caused by limited radio resources, the number of QoSFlow establishment failures, and the cell's downlink PRB utilization rate. The percentage of samples with RSRP >= -110 can determine whether a cell's 4G or 5G network has weak coverage issues; if the percentage is less than 90%, the cell has weak coverage. The average CQI can determine whether a cell's 4G network has strong interference issues, but it cannot determine whether a cell's 5G network has strong interference issues. If the average CQI of a cell is less than or equal to 6, then the cell does not have a strong interference problem.

[0204] In some embodiments, if there are no abnormalities in weak coverage indicators, strong interference indicators, and capacity-limited indicators, it is determined that the candidate cell has no network problems, and an expert analysis request message is sent.

[0205] It should be noted that the target score of candidate cells without network problems is not calculated, and candidate cells without network problems are not ranked.

[0206] Table 7 provides an introduction to other cell-level network metrics and anomaly thresholds. For details on cell-level network metrics and anomaly thresholds, please refer to the above introduction. It will not be repeated here.

[0207] It should be noted that the unique identifier, time period, or date of the candidate cell is obtained. Based on the unique identifier, time period, or date, the corresponding KPI data can be obtained from the KPI indicator database.

[0208] It should be noted that when KPI data can be obtained from the KPI database based on the unique identifier of the cell, time period, or date, cell-level indicators are hourly granular, and consistency of the hourly time period must be ensured. Cell grid indicators are daily granular data, and consistency of the date must be ensured.

[0209] For example, the unique identifier of a cell in a 4G network can be LAC+eNodeBID+CellID, while the unique identifier of a cell in a 5G network can be TAC+gNodeBID+CellID.

[0210] It should be noted that when the total number of MR samples is less than or equal to 30, MR-related indicators are not evaluated. When the number of successful RRC connection establishments is less than or equal to 100, CQI-related indicators are not evaluated.

[0211] It should be noted that the timing of executing S801-S804 is not limited in the embodiments of this application. For example, S801-S804 can be executed before S101. Or, for example, S801-S804 can be executed after S104.

[0212] For example, the device for determining mobile communication network complaint issues may perform S801-S804 before obtaining the target factor for each candidate cell.

[0213] Based on the above scheme, at least one alarm data point from the candidate cell is obtained. For each alarm data point, it is determined whether the user's complaint time falls within the corresponding alarm time period. By associating the alarm data with the network problems reported by the user, network faults can be quickly located, reducing troubleshooting time and improving the efficiency of network problem analysis.

[0214] The embodiments of this application are described below with reference to specific examples. For example, as shown below... Figure 9 The diagram illustrates an example of a method for determining a complained-about cell according to an embodiment of this application. Based on the complaint location, cell operating parameters, and raster MR data, multiple first cells near the complaint location are determined. Based on the complaint number and complaint time, multiple second cells passed by the user within a target time period are determined. Based on the first and second cells, multiple candidate cells are obtained. Candidate cells are cells where there is an intersection between the multiple first cells and multiple second cells. At least one alarm data point for each candidate cell is obtained. For each alarm data point, if the user's complaint time falls within the corresponding alarm time period, the alarm data is considered a network problem for the candidate cell. If none of the alarm time periods corresponding to at least one alarm data point include the complaint time, network metrics for the candidate cell are obtained. Based on the network metrics of the candidate cells, the network problem of the candidate cell is determined. For each candidate cell, a target score is determined based on the target factor and the weight of the target factor. Based on the target score and network problem of each candidate cell, the complained-about cell (i.e., the primary cause cell) and candidate complained-about cells (i.e., secondary cause cells) are determined from the multiple candidate cells. Finally, an analysis of the complained-about cell in terms of maintenance and optimization is output, along with recommendations.

[0215] The embodiments of this application are described below with reference to specific examples. For example, as shown below... Figure 10 The diagram illustrates an example of another method for determining a complained-about cell provided in this application. Based on the complaint location, multiple first cells near the complaint location are determined. Based on the complaint time, multiple second cells passed by the user within a target time period are determined. Based on the first and second cells, multiple candidate cells (i.e., candidate cell A) are obtained. Candidate cells are cells where there is an intersection between the multiple first cells and the multiple second cells. Next, it is determined whether the user's complaint time falls within the alarm time period corresponding to the alarm data. If the user's complaint time falls within the alarm time period corresponding to the alarm data, the alarm data is used as a network problem for the candidate cell, and a construction-related response text is output. If the user's complaint time does not fall within the alarm time period corresponding to the alarm data, the network metrics of the candidate cell are obtained. Based on the network metrics of the candidate cell, the network problem of the candidate cell is determined. It is determined whether the network metrics of the candidate cell are abnormal. If the network metrics are not abnormal, an expert analysis request message is sent. If the network metrics are abnormal, it is determined whether the weak coverage grid percentage index is greater than zero. If the weak coverage grid percentage index is greater than zero, the network problem of the candidate cell is determined to be a grid weak coverage problem. If the weak coverage raster percentage index is zero, then based on cell-level indicators, network problems in candidate cells are determined, and corresponding response text is output. Cell-level indicators include weak coverage indicators, strong interference indicators, and capacity-limited indicators. Based on these indicators, the network problems of candidate cells are identified as weak coverage, strong interference, and capacity-limited issues. Next, for each candidate cell with a network problem (i.e., candidate cell B), a target score is determined based on the target factors and their weights. The target score includes distance score, dwell time score, time consistency score, cell anomaly frequency score, sampling point score, and weak coverage raster score. Based on the target scores of each candidate cell with a network problem, multiple candidate cells are ranked, and the complained cell (i.e., the primary cause cell) and candidate complained cells (i.e., the secondary cause cells) are determined from among them.

[0216] The embodiments of this application are described below with reference to specific examples. For example, as shown below... Figure 11The diagram illustrates an example of another method for determining a complained-about cell provided in this application. The process involves: 1. Determining if the weak coverage grid percentage index is greater than zero. If the weak coverage grid percentage index is greater than zero, the network problem of the candidate cell is determined to be a grid weak coverage problem. 2. If the weak coverage grid percentage index is equal to zero, the network problem of the candidate cell is determined based on weak coverage indicators, strong interference indicators, and capacity-limited indicators. 3. Determining if a cell has a weak coverage problem. If the cell's weak coverage indicators are abnormal, the sum of the time consistency score and the cell's abnormal frequency score for the weak coverage indicators is calculated as A; if the cell's weak coverage indicators are normal, A is set to -1. 4. If the cell's strong interference indicators are abnormal, the sum of the time consistency score and the cell's abnormal frequency score for the strong interference indicators is calculated as B; if the cell's strong interference indicators are normal, B is set to -1. 5. If the cell's capacity-limited indicators are abnormal, the sum of the time consistency score and the cell's abnormal frequency score for the capacity-limited indicators is calculated as C; if the cell's capacity-limited indicators are normal, C is set to -1. 6. Determining if A, B, and C are all -1. If A, B, and C are all -1, then the cell has no network problem. If at least two of A, B, and C are not -1, then the maximum value among A, B, and C is determined. If the maximum value is A, then the cell's network problem is a weak coverage problem. If the maximum value is B, then the cell's network problem is a strong interference problem. If the maximum value is C, then the cell's network problem is a limited capacity problem.

[0217] The foregoing mainly describes the solutions provided by the embodiments of this application from a methodological perspective. It is understood that the mobile communication network complaint determination apparatus, in order to achieve the above functions, includes hardware structures and / or software modules corresponding to the execution of each function. Those skilled in the art should readily recognize that, based on the steps of the mobile communication network complaint determination method described in conjunction with the embodiments disclosed in this application, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0218] This application also provides a device for determining mobile communication network complaint issues. This device can be a server, a CPU within the server, a module within the server for determining mobile communication network complaint issues, or a client within the server for determining network issues.

[0219] This application embodiment can divide the mobile communication network complaint determination device into functional modules or functional units according to the above method example. For example, each function can be divided into a separate functional module or functional unit, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware or in software functional modules or functional units. The module or unit division in this application embodiment is illustrative and only represents one logical functional division; other division methods may be used in actual implementation.

[0220] This application provides an apparatus for determining mobile communication network complaint issues. For example... Figure 12 As shown, the device for determining mobile communication network complaint issues may include: an acquisition module 1201 and a processing module 1202.

[0221] The acquisition module 1201 is used to acquire network problems of multiple candidate cells and target factors for each candidate cell. The target factors are used to reflect the degree of correlation between the candidate cells and user complaints.

[0222] Processing module 1202 is configured to, for each candidate cell, determine a target score for the candidate cell based on the target factor of the candidate cell, thereby obtaining a target score for each candidate cell, wherein the target score is used to indicate the probability that the candidate cell is the complained cell. Processing module 1202 is also configured to, based on the target score of each candidate cell and the network problem of each candidate cell, determine the complained cell and the network problem of the complained cell from multiple candidate cells.

[0223] Figure 13 This is a schematic diagram illustrating the structure of a device for determining mobile communication network complaint issues according to an exemplary embodiment. The device may include a processor 1302, which executes application code to implement the method for determining mobile communication network complaint issues in this application.

[0224] The processor 1302 may be a central processing unit (CPU), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits used to control the execution of the program of the present application.

[0225] like Figure 13 As shown, the device for determining mobile communication network complaint issues may further include a memory 1303. The memory 1303 stores application code that executes the solution of this application, and its execution is controlled by a processor 1302.

[0226] Memory 1303 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto. Memory 1303 may exist independently and be connected to processor 1302 via bus 1304. Memory 1303 may also be integrated with processor 1302.

[0227] like Figure 13 As shown, the device for determining mobile communication network complaint issues may further include a communication interface 1301, wherein the communication interface 1301, processor 1302, and memory 1303 may be coupled to each other, for example, through a bus 1304. The communication interface 1301 is used for information exchange with other devices, for example, supporting information exchange between the device for determining mobile communication network complaint issues and other devices.

[0228] It should be pointed out that, Figure 13 The device structure shown does not constitute a limitation on the device for determining the problem of the mobile communication network complaint, except Figure 13 In addition to the components shown, the device for determining mobile communication network complaint issues may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0229] In actual implementation, the functions implemented by the processing unit can be derived from... Figure 13 The processor 1302 shown calls the program code in memory 1303 to implement this.

[0230] This application also provides a computer-readable storage medium storing instructions that, when executed by a processor of a computer device, enable the computer to perform the method for determining mobile communication network complaint issues provided in the embodiments described above. For example, the computer-readable storage medium may be a memory 1303 including instructions, which may be executed by a processor 1302 of a computer device to complete the method. Optionally, the computer-readable storage medium may be a non-transitory computer-readable storage medium, such as a ROM, RAM, CD-ROM, magnetic tape, floppy disk, or optical data storage device.

[0231] Figure 14 A conceptual partial view of a computer program product provided in an embodiment of this application is shown schematically. The computer program product includes a computer program for executing computer processes on a computing device.

[0232] In one embodiment, a computer program product is provided using a signal bearer medium 1400. The signal bearer medium 1400 may include one or more program instructions that, when executed by one or more processors, can provide the above-mentioned... Figure 1 , Figure 2 The described function or part of the function. Therefore, for example, refer to... Figure 1 In the embodiment shown, one or more features of S101 to S104 can be provided by one or more instructions associated with the signal carrying medium 1400. Furthermore, Figure 14 The program instructions in the document also describe example instructions.

[0233] In some examples, the signal carrying medium 1400 may include a computer-readable medium 1401, such as, but not limited to, a hard disk drive, a compact disc (CD), a digital video disc (DVD), a digital magnetic tape, a memory, a read-only memory (ROM), or a random access memory (RAM), and so on.

[0234] In some implementations, the signal carrying medium 1400 may include a computer recordable medium 1402, such as, but not limited to, a memory, a read / write (R / W) CD, a R / W DVD, and so on.

[0235] In some implementations, the signal carrying medium 1400 may include a communication medium 1403, such as, but not limited to, digital and / or analog communication media (e.g., fiber optic cables, waveguides, wired communication links, wireless communication links, etc.).

[0236] The signal-bearing medium 1400 can be transmitted by a wireless communication medium 1403. One or more program instructions can be, for example, computer-executable instructions or logical implementation instructions.

[0237] In some examples, the means for determining mobile communication network complaint issues can be configured to provide various operations, functions, or actions in response to one or more program instructions in a computer-readable medium 1401, a computer-recordable medium 1402, and / or a communication medium 1403.

[0238] Through the above description of the embodiments, those skilled in the art can clearly understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0239] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another apparatus, or some features may be ignored or not executed. Furthermore, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0240] The units described as separate components may or may not be physically separate. A component shown as a unit can be one or more physical units; that is, it can be located in one place or distributed in multiple different locations. Some or all of the constituent units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0241] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0242] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiments of this application, essentially, or the part that contributes to the prior art, or a complete or partial classification of the technical solution, can be embodied in the form of a software product. This software product is stored in a storage medium and includes several instructions to cause a device (which may be a microcontroller, chip, etc.) or processor to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, ROM, RAM, magnetic disks, or optical disks.

[0243] The above are only specific embodiments of the present application, but the scope of protection of the present application is not limited thereto. Any changes or replacements within the technical scope disclosed in this application should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. A method for determining complaints about mobile communication networks, characterized in that, The method includes: The network problems of multiple candidate cells are obtained, as well as the target factor for each candidate cell, which is used to reflect the degree of correlation between the candidate cell and user complaints; For each candidate cell, a target score is determined based on the target factor of the candidate cell to obtain the target score of each candidate cell, which is used to indicate the probability that the candidate cell is the complained cell; Based on the target score of each candidate cell and the network problem of each candidate cell, the complained cell and the network problem of the complained cell are determined from the plurality of candidate cells; Obtaining the network issues of the candidate cells includes: Obtain at least one alarm data point from the candidate cell, with each alarm data point corresponding to an alarm time period; For each alarm data, if the user's complaint time falls within the alarm time period corresponding to the alarm data, then the alarm data is considered as a network problem in the candidate cell.

2. The method according to claim 1, characterized in that, The target factors include at least one of the following: distance factor, dwell time factor, time consistency factor, cell anomaly frequency factor, sampling point factor, and weak coverage grid factor. Determining the target score of the candidate cell based on the target factor of the candidate cell includes: Based on each target factor of the candidate cells, determine the score corresponding to each target factor; The target score of the candidate cell is determined based on the score corresponding to each target factor and the weight value of each target factor.

3. The method according to claim 1, characterized in that, Before obtaining network issues from multiple candidate cells, the method further includes: Obtain the time and location of the user's complaint; Based on the complaint time and the complaint location, multiple candidate cells are identified.

4. The method according to claim 3, characterized in that, Based on the complaint time and complaint location, multiple candidate cells are determined, including: Based on the complaint time, multiple first communities are identified. The first community is the community that the user passed through during the target time period, and the target time period is related to the complaint time. Based on the location of the complaint, multiple second cells are determined, and the second cells are cells that are within a preset distance threshold from the location of the complaint. The plurality of candidate cells are determined, wherein the candidate cells are the cells that intersect with the plurality of first cells and the plurality of second cells.

5. The method according to claim 1, characterized in that, The method further includes: If the alarm time period corresponding to at least one alarm data does not include the complaint time, then obtain the network metrics of the candidate cell; Based on the network metrics of the candidate cells, the network problems of the candidate cells are determined.

6. A device for determining mobile communication network complaint issues, characterized in that, The device includes an acquisition module and a processing module: The acquisition module is used to acquire network problems of multiple candidate cells and target factors for each candidate cell. The target factors are used to reflect the degree of correlation between the candidate cells and user complaints. The processing module is configured to determine a target score for each candidate cell based on the target factor of the candidate cell, so as to obtain a target score for each candidate cell, wherein the target score is used to indicate the probability that the candidate cell is the complained cell; The processing module is further configured to determine the complained cell and the network problem of the complained cell from the plurality of candidate cells based on the target score of each candidate cell and the network problem of each candidate cell; The acquisition module is also used to acquire at least one alarm data of the candidate cell, and one alarm data corresponds to one alarm time period; The processing module is further configured to, for each alarm data, if the user's complaint time falls within the alarm time period corresponding to the alarm data, then consider the alarm data as a network problem of the candidate cell.

7. A device for determining complaints about mobile communication networks, characterized in that, include: Processor and memory; The processor and the memory are coupled; The memory is used to store one or more programs, the one or more programs including computer execution instructions. When the mobile communication network complaint problem determination device is running, the processor executes the computer execution instructions stored in the memory to cause the mobile communication network complaint problem determination device to perform the method as described in any one of claims 1-5.

8. A computer-readable storage medium storing instructions, characterized in that, When the computer executes the instruction, the computer performs the method as described in any one of claims 1-5.

9. A computer program product containing instructions, characterized in that, When the instruction is executed by the computing device, the computing device performs the method as described in any one of claims 1-5.

Images