Voice quality early warning method and device, electronic equipment and storage medium

Abstract

The application discloses a voice quality early warning method and device, electronic equipment and storage medium, and belongs to the field of wireless communication, to improve the early warning efficiency of voice quality, the method comprises the following steps: acquiring at least one first quality difference call data of a preset area in a preset time period; according to the first user position information corresponding to each first quality difference call data, each first quality difference call data is converged to the corresponding element point in the preset quality difference grid, wherein the quality difference grid is obtained by gridding the preset area; the element points in the quality difference grid are clustered to obtain all quality difference problem clusters, and all quality difference problem clusters are displayed in a map tool including the preset area, wherein the position of any quality difference problem cluster in the map tool corresponds to the position of the quality difference problem cluster in the quality difference grid; if it is detected in the map tool that the quality difference problem cluster corresponding to any position point meets the preset early warning condition, voice quality early warning is performed for any position point.

Description

Technical Field

[0001] This application belongs to the field of wireless communication, and specifically relates to a method, device, electronic device and storage medium for early warning of voice quality. Background Technology

[0002] Voice over Long-Term Evolution (VoLTE) is a high-speed wireless communication standard for mobile phones and data terminals. With the rapid growth of VoLTE users, the number of VoLTE voice quality issues has also increased. If a region experiences VoLTE voice quality problems, users in that region will also experience poor call quality. Currently, operators' solutions for locating VoLTE voice quality issues involve manually filtering and correlating various indicators based on the existing network optimization platform when users experience poor call quality. For example, when collecting user voice quality issues (such as call connection failures, dropped calls, handovers, and intermittent single-channel calls), engineers use their experience to match the voice quality issues with other indicators and obtain necessary air interface data to determine network problems and identify the causes of perceived degradation in poor-quality cells. Then, map tools can be used to create cell layers to identify the areas with poor-quality cells, thereby pinpointing the region where the VoLTE voice quality problem is occurring.

[0003] However, the above method is rather vague in defining the range of poor quality locations, and the location of VoLTE voice quality problems is passive and inaccurate, which makes it impossible to provide proactive warnings when voice quality problems occur. Summary of the Invention

[0004] This application provides a method, apparatus, electronic device, and storage medium for early warning of voice quality issues, which can solve the problem of not being able to provide proactive early warning when voice quality problems occur.

[0005] In a first aspect, embodiments of this application provide a voice quality early warning method, the method comprising: acquiring at least one first poor quality call detail record (CDR) data in a preset area within a preset time period, wherein each first poor quality CDR data includes first user location information corresponding to a user, the user being the user corresponding to the first poor quality CDR data; based on the first user location information corresponding to each first poor quality CDR data, aggregating each first poor quality CDR data into a corresponding element point in a preset poor quality grid, wherein the poor quality grid is obtained by rasterizing the preset area, and the element point is a mapping location point of the first user location information in the poor quality grid; performing clustering processing on the element points in the poor quality grid to obtain all poor quality problem clusters, and displaying all the poor quality problem clusters in a map tool including the preset area, wherein the position of any poor quality problem cluster in the map tool corresponds to the position of the poor quality problem cluster in the poor quality grid; if a poor quality problem cluster corresponding to any location point is detected in the map tool to meet preset early warning conditions, then issuing a voice quality early warning for that location point.

[0006] Secondly, embodiments of this application provide a voice quality early warning device, comprising: an acquisition module, configured to acquire at least one first poor quality call detail record (CDR) data within a preset time period and a preset area, wherein each of the first poor quality CDR data includes first user location information corresponding to a user, the user being the user corresponding to the first poor quality CDR data; an aggregation module, configured to aggregate each of the first poor quality CDR data to a corresponding element point in a preset poor quality grid based on the first user location information corresponding to each of the first poor quality CDR data, wherein the poor quality grid is obtained by rasterizing the preset area, and the element point is a mapping location point of the first user location information in the poor quality grid; a clustering module, configured to perform clustering processing on the element points in the poor quality grid to obtain all poor quality problem clusters, and display all the poor quality problem clusters in a map tool including the preset area, wherein the position of any poor quality problem cluster in the map tool corresponds to the position of the poor quality problem cluster in the poor quality grid; and an early warning module, configured to issue a voice quality early warning for any location point if a poor quality problem cluster corresponding to any location point is detected in the map tool and meets preset early warning conditions.

[0007] Thirdly, embodiments of this application provide an electronic device including a processor, a memory, and a program or instructions stored in the memory and executable on the processor, wherein the program or instructions, when executed by the processor, implement the steps of the method described in the first aspect.

[0008] Fourthly, embodiments of this application provide a readable storage medium on which a program or instructions are stored, which, when executed by a processor, implement the steps of the method described in the first aspect.

[0009] In this embodiment, at least one first poor quality call detail record (CDR) data point within a preset time period and a preset area is obtained. Each first poor quality CDR data point includes first user location information corresponding to a user. The user is the user corresponding to the first poor quality CDR data point. Based on the first user location information corresponding to each first poor quality CDR data point, each first poor quality CDR data point is aggregated into a corresponding element point in a preset poor quality grid. The poor quality grid is obtained by rasterizing the preset area, and the element point is the mapping location point of the first user location information in the poor quality grid. Clustering processing is performed on the element points in the poor quality grid to obtain all poor quality problem clusters, and the clusters include the first poor quality CDR data point. The map tool of the region displays all the poor quality problem clusters, wherein the position of any poor quality problem cluster in the map tool corresponds to the position of the poor quality problem cluster in the poor quality grid. If the map tool detects that the poor quality problem cluster corresponding to any location point meets the preset warning conditions, then a voice quality warning is issued for that location point. This method can accurately locate the location point corresponding to the voice quality problem when a voice quality problem occurs, and issue a voice quality warning for location points that meet the preset warning conditions. This solves the problem of not being able to issue an active warning when a voice quality problem occurs, and realizes an active warning for voice quality when a voice quality problem occurs, improving the accuracy and efficiency of the warning. Attached Figure Description

[0010] Figure 1 This is a flowchart illustrating a voice quality early warning method provided in an embodiment of this application;

[0011] Figure 2 This is a schematic diagram of the structure of a voice quality early warning device provided in an embodiment of this application;

[0012] Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0013] 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, 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.

[0014] The terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such use of data can be interchanged where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first," "second," etc., are generally of the same class and the number of objects is not limited; for example, a first object can be one or more. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0015] The following description, in conjunction with the accompanying drawings, details the voice quality early warning method, apparatus, electronic device, and storage medium provided in this application through specific embodiments and application scenarios.

[0016] Figure 1 This illustration shows a voice quality warning method according to an embodiment of the present invention. The method can be executed by an electronic device, which may include a server and / or a terminal device. In other words, the method can be executed by software or hardware installed on the electronic device, and the method includes the following steps:

[0017] Step 102: Obtain at least one first-quality poor call detail record (CDR) data for a preset area within a preset time period.

[0018] Specifically, at least one first poor quality call detail record (CDR) data within a preset time period and preset area can be obtained through a preset user interface. Each first poor quality CDR data includes the first user location information corresponding to the user, and the user is the user corresponding to the first poor quality CDR data.

[0019] Step 104: Based on the first user location information corresponding to each of the first poor quality call detail records, aggregate each of the first poor quality call detail records into the corresponding element point in the preset poor quality grid.

[0020] Specifically, the quality-deterioration grid is obtained by rasterizing a preset area. The preset area can be geographically rasterized using GEO9 raster encoding to obtain the quality-deterioration grid. After obtaining at least one first quality-deterioration call detail record (CDR) data, the element point corresponding to the first user location information in each first quality-deterioration CDR data can be determined in the quality-deterioration grid based on the first user location information in each first quality-deterioration CDR data. The element point corresponding to the first user location information is the mapping location point of the first user location information in the quality-deterioration grid. Each first quality-deterioration CDR data can be aggregated into the corresponding element point.

[0021] Step 106: Perform clustering processing on the element points in the poor quality raster to obtain all poor quality problem clusters, and display all the poor quality problem clusters in the map tool that includes the preset area.

[0022] Specifically, by using an adaptively tuned KANN-DBSCAN clustering algorithm model to cluster all elements in the quality defect raster, all quality defect problem clusters corresponding to the preset region can be obtained. After obtaining all quality defect problem clusters, they can be displayed in a preset map tool that includes the preset region. The position of any quality defect problem cluster in the map tool corresponds to its position in the quality defect raster. In this way, by clustering all elements in the quality defect raster and presenting them in the map tool, speech quality problems can be presented geographically.

[0023] Step 108: If the poor quality cluster corresponding to any location point is detected in the map tool and meets the preset warning conditions, then a voice quality warning is issued for any location point.

[0024] Specifically, if the map tool detects that any location point corresponds to a cluster of poor voice quality issues that meets the preset warning conditions, then a voice quality warning will be issued for that location point. This location point can be a property point that the operator has pre-set in a preset area.

[0025] This invention provides a voice quality early warning method, which acquires at least one first poor quality call detail record (CDR) data set within a preset time period and a preset area. Each first poor quality CDR data set includes first user location information corresponding to a user, where the user is the user corresponding to the first poor quality CDR data set. Based on the first user location information corresponding to each first poor quality CDR data set, each first poor quality CDR data set is aggregated into corresponding element points in a preset poor quality grid. The poor quality grid is obtained by rasterizing a preset area, and the element points are the mapping positions of the first user location information within the poor quality grid. Clustering is then performed on the element points in the poor quality grid. All quality issue clusters are obtained and displayed in a map tool that includes a preset area. The position of any quality issue cluster in the map tool corresponds to its position in the quality issue grid. If a quality issue cluster corresponding to any location point in the map tool meets the preset warning conditions, a voice quality warning is issued for that location point. This method can accurately locate the location point where a voice quality problem occurs and proactively issue a voice quality warning for that location point, solving the problem of not being able to proactively issue warnings when voice quality problems occur and improving the accuracy and efficiency of warnings.

[0026] In one implementation, obtaining at least one first-quality poor call detail record (CDR) from a preset area within a preset time period includes:

[0027] Obtain at least one second-quality call detail record (CDR) from the preset area within the preset time period;

[0028] The second user location information corresponding to each second poor quality call detail record is obtained through a preset positioning correction technology.

[0029] Each second user location information is added to the second poor quality call detail record (CDR) data corresponding to the second user location information to obtain the first poor quality CDR data corresponding to each second poor quality CDR data.

[0030] Specifically, the system can obtain quality data such as call connection, call drop, handover, and intermittent call quality during all calls within a preset time period and area through the operator's preset interface, and obtain all second-quality call detail records within the preset time period and area.

[0031] Standard call detail records (CDRs) for all calls within a preset time period and area can be obtained through the operator's preset interface. Based on the operator's VoLTE end-to-end platform problem delimitation rules, error feature libraries are established by setting signaling error values ​​for each of the four types of perception factors: connection failure, dropped call, intermittent single-channel communication, and handover, using the signaling error fields of their respective interfaces. The voice quality problems are then delimited according to the error feature libraries to determine the type of quality issue.

[0032] When defining the poor quality type, in-depth data signaling analysis is performed on the VoLTE voice call process. Big data mining and analysis techniques are applied to train, evaluate, and iterate the error code feature library to obtain accurate results for delineating the poor quality type.

[0033] After acquiring all the second-quality poor call detail records (CDRs), the user location information obtained from the user terminal can be processed using a preset positioning correction technology to obtain the second user location information corresponding to each second-quality poor CDR. Each second user location information is added to the second-quality poor CDR corresponding to the second user location information to obtain the first-quality poor CDR. If there are second-quality poor CDRs without corresponding second user location information among all the second-quality poor CDRs, the location information corresponding to the second-quality poor CDR without corresponding second user location information can be obtained through a preset base station, and the obtained location information is added to the corresponding second-quality poor CDR to obtain the first-quality poor CDR.

[0034] In this way, by acquiring at least one second poor quality call detail record (CDR) data from a preset area within a preset time period; by using a preset positioning correction technology, obtaining the second user location information corresponding to each second poor quality CDR data; and by adding each second user location information to the second poor quality CDR data corresponding to the second user location information, the first poor quality CDR data corresponding to each second poor quality CDR data can be obtained, thus obtaining the first poor quality CDR data including the first user location information.

[0035] In one implementation, obtaining the second user location information corresponding to each second poor-quality call detail record (CDR) using a preset positioning correction technique includes:

[0036] Obtain the location information of all third users corresponding to all the second poor quality call detail records;

[0037] In at least one preset coordinate system, for any third user location information, determine the distance value between any third user location information and the location information corresponding to the preset primary serving cell in each coordinate system;

[0038] The second user location information is determined based on the third user location information corresponding to the smallest distance value and the coordinate system.

[0039] Specifically, OTT data (HTTP raw stream) can be obtained through the operator's pre-set user interface, and the third-party location information can be parsed out. HTTP requests typically use two common methods: GET or POST. GET requests generally display the third-party location information in plaintext in the URL; POST requests generally report location information in encrypted form. After processing by the server and returning the data, the packets are decompressed, and the third-party location information, which can be latitude and longitude coordinates, can be obtained from the generated downlink payload.

[0040] After obtaining the location information of at least one third user, since the user terminal uses a different coordinate system when judging the location information of the third user, it is necessary to process the location information of the third user through a preset positioning correction technology.

[0041] After obtaining the location information of any third user, the location information of any third user is placed in different preset coordinate systems. In different coordinate systems, the distance value between the location information of the third user and the preset main serving cell is determined. After obtaining all distance values, the location information of the third user and the coordinate system corresponding to the smallest distance value are determined. The location information of the third user in the coordinate system is the location information of the second user.

[0042] In this way, by acquiring all third user location information corresponding to all second-quality poor call detail records; in at least one preset coordinate system, for any third user location information, determining the distance value between any third user location information and the location information corresponding to the preset primary serving cell in each coordinate system; and determining the second user location information based on the third user location information and coordinate system corresponding to the minimum distance value, the system can accurately identify the coordinate system of the third user location information and determine the second user location information by comparing the distances between the third user location information and the primary serving cell in different coordinate systems, thereby improving the accuracy and precision of positioning.

[0043] In one implementation, each of the first poor-quality call detail records (CDRs) further includes a user identifier corresponding to the user. After the method aggregates each of the first poor-quality CDRs to a corresponding element point in a preset poor-quality grid based on the first user location information corresponding to each of the first poor-quality CDRs, the method further includes:

[0044] Determine the total number of first-quality call detail records corresponding to each user identifier from the quality defect grid;

[0045] Arrange the total number of first poor quality call detail records corresponding to each user identifier in descending order, and determine the first M user identifiers in the order.

[0046] If a user-level complaint detail is received corresponding to any of the M user identifiers, then the first user location information corresponding to the user-level complaint detail is determined from the first poor quality call detail data corresponding to any of the user identifiers, where M is a positive integer;

[0047] A voice quality warning is issued for the property management point corresponding to the first user's location information that corresponds to the detailed user-level complaint list.

[0048] The total number of first-quality poor call detail records (CDRs) corresponding to each user identifier is determined from the poor quality grid. These CDRs are then sorted in descending order, and the top M user identifiers are identified. If a user-level complaint detail record corresponding to any of the M user identifiers is received, the first user location information corresponding to the user-level complaint detail record is determined from the first-quality poor quality CDRs corresponding to that user identifier, where M is a positive integer. Voice quality warnings are issued for the property management points corresponding to the first user location information of the user-level complaint detail record. This allows for the geographic location of user-level voice quality issues across the entire network by associating high-frequency users with poor quality output from the poor quality grid terminal with user-level complaint detail records, effectively improving user satisfaction.

[0049] In one implementation, the step of issuing a voice quality warning for any location point if the map tool detects a cluster of poor voice quality issues that meets preset warning conditions includes:

[0050] If the total area of ​​the poor quality problem clusters corresponding to any of the locations detected in the map tool exceeds a preset area threshold, a voice quality warning will be issued for any of the locations.

[0051] If the number of different user identifiers corresponding to any of the locations detected in the map tool exceeds a preset threshold, a voice quality warning will be issued for any of the locations.

[0052] Specifically, if the total area of ​​a cluster of poor-quality issues corresponding to any location point is detected in the map tool to exceed a preset area threshold, a voice quality warning will be issued for that location point, as shown in the table below:

[0053]

[0054] If the preset area threshold is 20000 (m2), and the total area of ​​the poor quality problem cluster of the property site Henan Provincial People's Hospital is 37489.9001, which exceeds the preset area threshold, then a voice quality warning will be issued for Henan Provincial People's Hospital.

[0055] The number of users causing voice quality problems can be determined by the different user identifiers. If the map tool detects that the number of different user identifiers corresponding to any location point exceeds a preset threshold, that is, the number of different users causing voice quality problems corresponding to any location point exceeds the preset threshold, then a voice quality warning will be issued for that location point, as shown in the table below:

[0056] Property Management Number of users Number of quality difference clusters poor quality percentage Henan Provincial People's Hospital 473 5 1.06％ Zhengzhou University First Affiliated Hospital East Campus 307 11 3.58％ The First Affiliated Hospital of Zhengzhou University 276 9 3.26％ The First Affiliated Hospital of Henan University of Traditional Chinese Medicine 116 7 6.03％ Nanyang Central Hospital 93 11 11.83％ Pingdingshan First People's Hospital 65 6 9.23％ Xiangcheng County People's Hospital 55 6 10.91％ Pingyu County People's Hospital 50 5 10.00％ Zhumadian Central Hospital 50 3 6.00％

[0057] For example, if the preset threshold is 200 people, and the number of users with voice quality problems at the property management location Henan Provincial People's Hospital is 473, the number of users with voice quality problems at the property management location Zhengzhou University First Affiliated Hospital East Campus is 307, and the number of users with voice quality problems at Zhengzhou University First Affiliated Hospital is 276, then the number of users (user identifiers) with voice quality problems at the above three property management locations all exceed the preset threshold (200), and a voice quality warning will be issued for the above three property management locations.

[0058] In this way, if the total area of ​​a cluster of quality issues corresponding to any location point detected in the map tool exceeds a preset area threshold, a voice quality warning is issued for that location point; if the number of different user identifiers corresponding to any location point detected in the map tool exceeds a preset number threshold, a voice quality warning is also issued for that location point. This allows for proactive voice quality warnings to be issued for property locations that exceed preset warning thresholds, solving the problem of not being able to proactively issue warnings when voice quality issues occur at property locations.

[0059] In addition, property locations can be marked in the map tool, and electronic devices will push relevant information about the quality problem clusters corresponding to the marked property locations in real time, realizing real-time monitoring of the marked property locations.

[0060] In one implementation, the first poor quality call detail record (CDR) data also includes the type of poor quality problem and the cause of the poor quality problem corresponding to the first poor quality CDR data.

[0061] Specifically, by conducting in-depth data signaling analysis on the VoLTE voice call process and applying big data mining and analysis techniques to train, evaluate, and iterate the error code feature library, accurate results for delineating poor quality types can be obtained.

[0062] After aggregating each first-quality poor call detail record (CDR) into the corresponding element point in the preset poor quality grid, the user terminal external data corresponding to any first-quality poor CDR in the poor quality grid can be obtained. If the user terminal external data corresponding to any first-quality poor CDR is insufficient, it can be supplemented by obtaining data from the network optimization big data platform and network optimization platform of the main serving cell. By linking and jointly analyzing the four data sources of the poor quality grid with user terminal external data, alarms, performance indicators, and communication network, the wireless shortcomings of five dimensions (fault, coverage, interference, capacity, handover) of voice quality problems can be located, and the root causes can be analyzed in depth. The cause of each first-quality poor CDR appearing in the poor quality grid is located in detail, and the cause of the poor quality is marked by a poor quality label (alarm, coverage, interference, etc.) and subdivided poor quality labels (fault outage, performance alarm, over-coverage, weak coverage, etc.).

[0063] In this way, by conducting in-depth data signaling analysis on the VoLTE voice call process, and applying big data mining and analysis techniques to train, evaluate, and iterate the error code feature library, accurate quality defect type delineation results can be obtained. By analyzing the data corresponding to any first-quality defect call detail record, the cause of the voice quality defect problem can be determined.

[0064] It should be noted that the voice quality warning method provided in this application embodiment can be executed by a voice quality warning device or a control module within that voice quality warning device for executing the voice quality warning method. This application embodiment uses the execution of the voice quality warning method by a voice quality warning device as an example to illustrate the voice quality warning device provided in this application embodiment.

[0065] Figure 2 This is a schematic diagram of the structure of a voice quality warning device according to an embodiment of the present invention. Figure 2 As shown, the voice quality warning device 200 includes: an acquisition module 210, a convergence module 220, a clustering module 230, and a warning module 240.

[0066] The acquisition module 210 is used to acquire at least one first poor quality call detail record (CDR) data in a preset area within a preset time period, wherein each first poor quality CDR data includes first user location information corresponding to a user, and the user is the user corresponding to the first poor quality CDR data; the aggregation module 220 is used to aggregate each first poor quality CDR data to a corresponding element point in a preset poor quality grid according to the first user location information corresponding to each first poor quality CDR data, wherein the poor quality grid is obtained by rasterizing the preset area, and the element point is the mapping position point of the first user location information in the poor quality grid; the clustering module 230 is used to perform clustering processing on the element points in the poor quality grid to obtain all poor quality problem clusters, and display all the poor quality problem clusters in a map tool including the preset area, wherein the position of any poor quality problem cluster in the map tool corresponds to the position of the poor quality problem cluster in the poor quality grid; the warning module 240 is used to issue a voice quality warning for any location point if the poor quality problem cluster corresponding to any location point is detected in the map tool and meets the preset warning conditions.

[0067] In one implementation, the acquisition module 210 is used to acquire at least one second poor quality call detail record (CDR) data of the preset area within the preset time period; obtain second user location information corresponding to each second poor quality CDR data through a preset positioning correction technology; add each second user location information to the second poor quality CDR data corresponding to the second user location information to obtain the first poor quality CDR data corresponding to each second poor quality CDR data.

[0068] In one implementation, the acquisition module 210 is used to acquire all third user location information corresponding to all the second poor quality call detail records; in at least one preset coordinate system, for any third user location information, determine the distance value between any third user location information and the location information corresponding to the preset primary serving cell in each coordinate system; and determine the second user location information based on the third user location information corresponding to the smallest distance value and the coordinate system.

[0069] In one implementation, any of the first poor-quality call detail records (CDRs) further includes a user identifier corresponding to the user. The early warning module 240 is further configured to: determine the total number of first poor-quality CDRs corresponding to each user identifier from the poor-quality grid; sort the total number of first poor-quality CDRs corresponding to each user identifier in descending order and determine the top M user identifiers; if a user-level complaint detail corresponding to any of the M user identifiers is received, determine the first user location information corresponding to the user-level complaint detail from the first poor-quality CDRs corresponding to the user identifier, where M is a positive integer; and issue a voice quality warning to the property management point corresponding to the first user location information corresponding to the user-level complaint detail.

[0070] In one implementation, the warning module 240 is configured to issue a voice quality warning for any location if the total area of ​​the poor quality clusters corresponding to any location is detected in the map tool to exceed a preset area threshold; and to issue a voice quality warning for any location if the number of different user identifiers corresponding to any location is detected in the map tool to exceed a preset number threshold.

[0071] In one implementation, the first poor quality call detail record (CDR) data also includes the type of poor quality problem and the cause of the poor quality problem corresponding to the first poor quality CDR data.

[0072] The voice quality warning device in this application embodiment can be a device, or it can be a component, integrated circuit, or chip in a terminal. The device can be a mobile electronic device or a non-mobile electronic device. For example, mobile electronic devices can be mobile phones, tablets, laptops, PDAs, in-vehicle electronic devices, wearable devices, ultra-mobile personal computers (UMPCs), netbooks, or personal digital assistants (PDAs), etc., while non-mobile electronic devices can be servers, network attached storage (NAS), personal computers (PCs), televisions (TVs), ATMs, or self-service machines, etc. This application embodiment does not impose specific limitations.

[0073] The voice quality warning device in this embodiment can be a device with an operating system. This operating system can be Android, iOS, or other possible operating systems; this embodiment does not specifically limit it.

[0074] The voice quality warning device provided in this application embodiment can achieve... Figure 1 The various processes implemented in the method embodiments are not described in detail here to avoid repetition.

[0075] Optionally, such as Figure 3This application embodiment also provides an electronic device 300, including a processor 301 and a memory 302. The memory 302 stores a program or instructions that can run on the processor 301. When the program or instructions are executed by the processor 301, they perform the following: acquiring at least one first poor quality call detail record (CDR) data in a preset area within a preset time period, wherein each of the first poor quality CDR data includes first user location information corresponding to a user, and the user is the user corresponding to the first poor quality CDR data; and according to the first user location information corresponding to each first poor quality CDR data, aggregating each first poor quality CDR data to a preset poor quality grid. The corresponding element points in the grid, wherein the poor quality grid is obtained by rasterizing the preset area, and the element points are the mapping position points of the first user's location information in the poor quality grid; the element points in the poor quality grid are clustered to obtain all poor quality problem clusters, and all poor quality problem clusters are displayed in a map tool that includes the preset area, wherein the position of any poor quality problem cluster in the map tool corresponds to the position of the poor quality problem cluster in the poor quality grid; if the poor quality problem cluster corresponding to any position point is detected in the map tool to meet the preset warning conditions, then a voice quality warning is issued for any position point.

[0076] In one implementation, at least one second poor quality call detail record (CDR) data of the preset area within the preset time period is obtained; second user location information corresponding to each second poor quality CDR data is obtained through a preset positioning correction technology; each second user location information is added to the second poor quality CDR data corresponding to the second user location information to obtain the first poor quality CDR data corresponding to each second poor quality CDR data.

[0077] In one implementation, all third user location information corresponding to all the second poor quality call detail records are obtained; in at least one preset coordinate system, for any third user location information, the distance value between any third user location information and the location information corresponding to the preset primary serving cell in each coordinate system is determined; the second user location information is determined based on the third user location information corresponding to the smallest distance value and the coordinate system.

[0078] In one implementation, any first poor-quality call detail record (CDR) data further includes a user identifier corresponding to the user. After aggregating each first poor-quality CDR data into a corresponding element point in a preset poor-quality grid based on the first user location information corresponding to each first poor-quality CDR data, the total number of first poor-quality CDR data corresponding to each same user identifier is determined from the poor-quality grid. The total number of first poor-quality CDR data corresponding to each same user identifier is sorted in descending order, and the top M user identifiers are determined. If a user-level complaint detail corresponding to any of the M user identifiers is received, the first user location information corresponding to the user-level complaint detail is determined from the first poor-quality CDR data corresponding to any of the user identifiers, where M is a positive integer. A voice quality warning is issued to the property management point corresponding to the first user location information corresponding to the user-level complaint detail.

[0079] In one implementation, if the total area of ​​the poor quality problem clusters corresponding to any location point is detected in the map tool to exceed a preset area threshold, a voice quality warning is issued for any location point; if the number of different user identifiers corresponding to any location point is detected in the map tool to exceed a preset number threshold, a voice quality warning is issued for any location point.

[0080] In one implementation, the first poor quality call detail record (CDR) data also includes the type of poor quality problem and the cause of the poor quality problem corresponding to the first poor quality CDR data.

[0081] The specific execution steps can be found in the various steps of the above-described voice quality warning method embodiment, and can achieve the same technical effect. To avoid repetition, they will not be described again here.

[0082] It should be noted that the electronic devices in the embodiments of this application include: servers, terminals, or other devices besides terminals.

[0083] The above electronic device structure does not constitute a limitation on the electronic device. An electronic device may include more or fewer components than illustrated, or combine certain components, or arrange them differently. For example, an input unit may include a Graphics Processing Unit (GPU) and a microphone, and a display unit may use a liquid crystal display (LCD), organic light-emitting diode (OLED), or other similar display panels. User input units include at least one of a touch panel and other input devices. A touch panel is also called a touchscreen. Other input devices may include, but are not limited to, physical keyboards, function keys (such as volume control buttons, power buttons, etc.), trackballs, mice, and joysticks, which will not be elaborated further here.

[0084] Memory can be used to store software programs and various data. Memory can primarily include a first storage area for storing programs or instructions and a second storage area for storing data. The first storage area can store the operating system, application programs or instructions required for at least one function (such as sound playback, image playback, etc.). Furthermore, memory can include volatile memory or non-volatile memory, or both. Non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory can be random access memory (RAM), static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous linked dynamic random access memory (Synchlink DRAM, SLDRAM), and direct memory bus RAM (DRRAM).

[0085] The processor may include one or more processing units; optionally, the processor integrates an application processor and a modem processor, wherein the application processor mainly handles operations related to the operating system, user interface, and applications, while the modem processor mainly handles wireless communication signals, such as a baseband processor. It is understood that the aforementioned modem processor may also not be integrated into the processor.

[0086] This application also provides a readable storage medium storing a program or instructions. When the program or instructions are executed by a processor, they implement the various processes of the above-described voice quality warning method embodiment and achieve the same technical effect. To avoid repetition, they will not be described again here.

[0087] The processor is the processor in the electronic device described in the above embodiments. The readable storage medium includes computer-readable storage media, such as ROM, RAM, magnetic disk, or optical disk.

[0088] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0089] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a computer software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0090] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of this application without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of this application.

Claims

1. A method for early warning of voice quality, characterized in that, include: Obtain at least one first poor quality call detail record (CDR) data from a preset area within a preset time period, wherein each of the first poor quality CDR data includes first user location information corresponding to the user, and the user is the user corresponding to the first poor quality CDR data; Based on the first user location information corresponding to each first poor quality call detail record (CDR), each first poor quality CDR is aggregated into the corresponding element point in a preset poor quality grid. The poor quality grid is obtained by rasterizing the preset area, and the element point is the mapping position point of the first user location information in the poor quality grid. Clustering is performed on the element points in the quality defect raster to obtain all quality defect clusters, and all quality defect clusters are displayed in a map tool that includes the preset area, wherein the position of any quality defect cluster in the map tool corresponds to the position of the quality defect cluster in the quality defect raster; If any location point is detected in the map tool as having a poor quality cluster that meets the preset warning conditions, then a voice quality warning will be issued for that location point. Each of the first poor quality call detail records (CDRs) further includes a user identifier corresponding to the user. After the method aggregates each first poor quality CDR into a corresponding element point in a preset poor quality grid based on the first user location information corresponding to each first poor quality CDR, the method further includes: Determine the total number of first-quality call detail records corresponding to each user identifier from the quality defect grid; Arrange the total number of first poor quality call detail records corresponding to each user identifier in descending order, and determine the first M user identifiers in the order. If a user-level complaint detail is received corresponding to any of the M user identifiers, then the first user location information corresponding to the user-level complaint detail is determined from the first poor quality call detail data corresponding to any of the user identifiers, where M is a positive integer; A voice quality warning is issued for the property management point corresponding to the first user's location information that corresponds to the detailed user-level complaint list.

2. The early warning method according to claim 1, characterized in that, The step of obtaining at least one first-quality poor call detail record (CDR) data for a preset area within a preset time period includes: Obtain at least one second-quality call detail record (CDR) from the preset area within the preset time period; The second user location information corresponding to each second poor quality call detail record is obtained through a preset positioning correction technology. Each second user location information is added to the second poor quality call detail record (CDR) data corresponding to the second user location information to obtain the first poor quality CDR data corresponding to each second poor quality CDR data.

3. The early warning method according to claim 2, characterized in that, The step of obtaining the second user location information corresponding to each second poor-quality call detail record (CDR) using a preset positioning correction technique includes: Obtain the location information of all third users corresponding to all the second poor quality call detail records; In at least one preset coordinate system, for any third user location information, determine the distance value between any third user location information and the location information corresponding to the preset primary serving cell in each coordinate system; The second user location information is determined based on the third user location information corresponding to the smallest distance value and the coordinate system.

4. The early warning method according to claim 1, characterized in that, If the map tool detects that any location point corresponds to a cluster of poor voice quality issues that meets preset warning conditions, then a voice quality warning is issued for that location point, including: If the total area of ​​the poor quality problem clusters corresponding to any of the locations detected in the map tool exceeds a preset area threshold, a voice quality warning will be issued for any of the locations. If the number of different user identifiers corresponding to any of the locations detected in the map tool exceeds a preset threshold, a voice quality warning will be issued for any of the locations.

5. The early warning method according to claim 1, characterized in that, The first poor quality call detail record (CDR) data also includes the type of poor quality problem and the cause of the poor quality problem corresponding to the first poor quality CDR data.

6. A voice quality warning device, characterized in that, include: The acquisition module is used to acquire at least one first poor quality call detail record (CDR) data in a preset area within a preset time period, wherein each of the first poor quality CDR data includes first user location information corresponding to the user, and the user is the user corresponding to the first poor quality CDR data. The aggregation module is used to aggregate each of the first poor quality call detail records (CDRs) into a corresponding element point in a preset poor quality grid based on the first user location information corresponding to each of the first poor quality CDRs. The poor quality grid is obtained by rasterizing the preset area, and the element point is the mapping position point of the first user location information in the poor quality grid. The clustering module is used to perform clustering processing on the element points in the poor quality raster to obtain all poor quality problem clusters, and to display all the poor quality problem clusters in a map tool that includes the preset area, wherein the position of any poor quality problem cluster in the map tool corresponds to the position of the poor quality problem cluster in the poor quality raster; The early warning module is used to issue a voice quality warning for any location point if the cluster of poor quality issues corresponding to any location point is detected in the map tool and meets the preset early warning conditions. Any of the first poor quality call detail records also includes the user identifier corresponding to the user; Also includes: The first determining module is used to determine the total number of first poor quality call detail records corresponding to the same user identifier from the poor quality grid after the first user location information corresponding to each first poor quality call detail record data is aggregated into the corresponding element point in the preset poor quality grid. The second acquisition module is used to sort the total number of first poor quality call detail records corresponding to each user identifier in descending order, and determine the first M user identifiers in the sorted order. The third determining module is used to determine the first user location information corresponding to the user-level complaint detail from the first poor quality call detail data corresponding to the user-level complaint detail if a user-level complaint detail corresponding to any one of the M user identifiers is received, wherein M is a positive integer; The early warning module is also used to issue voice quality warnings to the property management points corresponding to the first user location information corresponding to the user-level complaint details.

7. The early warning device according to claim 6, characterized in that, The acquisition module is used for: Obtain at least one second-quality call detail record (CDR) from the preset area within the preset time period; The second user location information corresponding to each second poor quality call detail record is obtained through a preset positioning correction technology. Each second user location information is added to the second poor quality call detail record (CDR) data corresponding to the second user location information to obtain the first poor quality CDR data corresponding to each second poor quality CDR data.

8. An electronic device, characterized in that, It includes a processor, a memory, and a program or instructions stored in the memory and executable on the processor, wherein the program or instructions, when executed by the processor, implement the steps of the voice quality warning method as described in any one of claims 1-5.

9. A readable storage medium, characterized in that, The readable storage medium stores a program or instructions that, when executed by a processor, implement the steps of the voice quality warning method as described in any one of claims 1-5.

Images