Method, device and equipment for determining a poor-quality area and a medium

Abstract

The application discloses a quality difference area determination method, device and equipment and a medium. The method comprises the following steps: determining complaint location longitude and latitude according to complaint work order data of a communication service; determining a first neighborhood radius, determining a first neighborhood of the complaint location longitude and latitude according to the first neighborhood radius, and determining a first type cluster according to each complaint location longitude and latitude and the complaint location longitude and latitude in the corresponding first neighborhood; determining a second neighborhood radius according to the first neighborhood radius, determining a second neighborhood of the complaint location longitude and latitude in the first type cluster according to the second neighborhood radius, and determining a second type cluster according to each complaint location longitude and latitude in the first type cluster and the complaint location longitude and latitude in the corresponding second neighborhood; and determining a quality difference area where the communication service fails according to the second type cluster. The application improves the accuracy of the determined quality difference area where the communication service fails.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a method, apparatus, device, and medium for determining poor quality regions. Background Technology

[0002] Currently, in network operations and maintenance responding to user complaints, the primary method is to determine whether a fault alarm has occurred at a relevant base station based on alarms from the network management OMC device. For example, based on the geographical location of the user complaint, the system checks whether there are fault alarms such as those related to hosting or service outage at the base station in that location; it then contacts the relevant regional maintenance personnel to go to the site to handle the fault; and after the fault is restored, it contacts the customer and provides feedback on the situation.

[0003] However, there are many problems in determining whether a base station has a fault alarm based on alarms from the network management OMC device. For example, it is impossible to accurately determine the location of the complaint based on individual user complaints and fault handling, and it is impossible to identify poor-quality geographical areas where user complaints are concentrated and faults occur frequently. Summary of the Invention

[0004] The main objective of this invention is to provide a method, apparatus, device, and medium for determining poor quality areas, aiming to solve the problem of how to accurately determine poor quality areas reported by users.

[0005] To achieve the above objectives, the present invention provides a method for determining a region of poor quality, the method comprising the following steps:

[0006] Based on the complaint ticket data for communication services, determine the latitude and longitude of the complaint location;

[0007] Determine the first neighborhood radius, determine the first neighborhood of the complaint location's latitude and longitude based on the first neighborhood radius, and determine the first cluster based on the latitude and longitude of each complaint location and the latitude and longitude of the complaint locations within the corresponding first neighborhood;

[0008] The second neighborhood radius is determined based on the first neighborhood radius, the second neighborhood of the complaint location latitude and longitude in the first cluster is determined based on the second neighborhood radius, and the second cluster is determined based on the complaint location latitude and longitude in each of the first clusters and the complaint location latitude and longitude in the corresponding second neighborhood;

[0009] The poor-quality region where the communication service malfunctions is determined based on the second cluster type.

[0010] In one embodiment, the step of determining the first cluster based on the latitude and longitude of each of the complaint locations and the latitude and longitude of the corresponding complaint locations within the first neighborhood includes:

[0011] Select one of the latitude and longitude coordinates of the location of the complaint as the first core latitude and longitude coordinate;

[0012] Determine the latitude and longitude of all complaint locations within the first neighborhood of the first core latitude and longitude, and add all the latitude and longitude of the complaint locations to the first cluster;

[0013] Among the latitude and longitude of the complaint locations within the first neighborhood of the first core latitude and longitude, a first target latitude and longitude is determined, wherein the first number of the latitude and longitude of the complaint locations within the first neighborhood of the first target latitude and longitude is greater than a preset threshold, and the first target latitude and longitude does not correspond to the first cluster.

[0014] Add all the latitude and longitude of the complaint locations in the first neighborhood of the first target latitude and longitude to the first cluster.

[0015] In one embodiment, the step of selecting a latitude and longitude of the complaint location as the first core latitude and longitude includes:

[0016] Choose any one of the latitude and longitude coordinates of the complaint location as the first latitude and longitude coordinate to be determined;

[0017] Determine a first number of complaint locations within the first neighborhood of the first latitude and longitude to be determined;

[0018] If the first quantity is greater than a preset threshold, and the first latitude and longitude to be determined does not correspond to the first cluster, then the first latitude and longitude to be determined is taken as the first core latitude and longitude.

[0019] In one embodiment, the step of determining the second cluster based on the latitude and longitude of the complaint location in each of the first clusters and the latitude and longitude of the complaint location in the corresponding second neighborhood includes:

[0020] Select one of the latitude and longitude coordinates of the complaint location from the first cluster as the second core latitude and longitude coordinate;

[0021] Determine the latitude and longitude of all complaint locations within the second neighborhood of the second core latitude and longitude, and add all the latitude and longitude of the complaint locations to the second cluster;

[0022] In the latitude and longitude of the complaint location within the second neighborhood of the second core latitude and longitude, a second target latitude and longitude is determined, wherein the second number of the latitude and longitude of the complaint location within the second neighborhood of the second target latitude and longitude is greater than a preset threshold, and the second target latitude and longitude does not correspond to the second cluster;

[0023] Add all the latitude and longitude of the complaint locations in the second neighborhood of the second target latitude and longitude to the second cluster.

[0024] In one embodiment, the step of selecting a latitude and longitude coordinate of the complaint location within the first cluster as the second core latitude and longitude coordinate includes:

[0025] Choose any one of the latitude and longitude coordinates of the complaint location in the first cluster as the second latitude and longitude coordinate to be determined;

[0026] Determine a second number of complaint locations' latitude and longitude coordinates within the second neighborhood of the second latitude and longitude coordinates to be determined;

[0027] If the second quantity is greater than or equal to a preset threshold, and the second latitude and longitude to be determined does not correspond to the second cluster, then the second latitude and longitude to be determined is determined as the second core latitude and longitude.

[0028] In one embodiment, the step of determining the first neighborhood radius includes:

[0029] Determine the Manhattan distance between the latitude and longitude of each pair of the stated complaint locations;

[0030] The first neighborhood radius is determined based on the average of the various Manhattan distances.

[0031] In one embodiment, the step of determining the second neighborhood radius based on the first neighborhood radius includes:

[0032] Determine a third number of latitude and longitude coordinates of the complaint locations within the first cluster;

[0033] The second neighborhood radius is determined based on a preset threshold, the first neighborhood radius, and the third quantity.

[0034] To achieve the above objectives, the present invention also provides an apparatus for determining a region of poor quality, the apparatus comprising:

[0035] The acquisition module is used to determine the latitude and longitude of the complaint location based on the complaint work order data of the communication service;

[0036] The first calculation module is used to determine a first neighborhood radius, determine a first neighborhood of the latitude and longitude of the complaint location based on the first neighborhood radius, and determine a first cluster based on the latitude and longitude of each complaint location and the latitude and longitude of the complaint locations in the corresponding first neighborhood.

[0037] The second calculation module is used to determine the second neighborhood radius based on the first neighborhood radius, determine the second neighborhood of the latitude and longitude of the complaint location in the first cluster based on the second neighborhood radius, and determine the second cluster based on the latitude and longitude of the complaint location in each of the first clusters and the latitude and longitude of the complaint location in the corresponding second neighborhood;

[0038] The determination module is used to determine the poor quality area where the communication service has failed based on the second cluster.

[0039] To achieve the above objectives, the present invention also provides a device for determining poor quality regions. The device for determining poor quality regions includes a memory, a processor, and a program for determining poor quality regions stored in the memory and executable on the processor. When the program for determining poor quality regions is executed by the processor, it implements the various steps of the method for determining poor quality regions as described above.

[0040] To achieve the above objectives, the present invention also provides a computer-readable storage medium storing a program for determining poor quality regions, wherein when the program for determining poor quality regions is executed by a processor, it implements the various steps of the method for determining poor quality regions as described above.

[0041] This invention provides a method, apparatus, device, and medium for determining poor-quality areas. Based on complaint work order data for communication services, the method determines the latitude and longitude of the complaint location; determines a first neighborhood radius; determines a first neighborhood of the complaint location's latitude and longitude based on the first neighborhood radius; determines a first cluster based on the latitude and longitude of each complaint location and the latitude and longitude of the corresponding complaint locations within the first neighborhood; determines a second neighborhood radius based on the first neighborhood radius; determines a second neighborhood of the complaint location's latitude and longitude within the first cluster based on the second neighborhood radius; determines a second cluster based on the latitude and longitude of each complaint location within the first cluster and the latitude and longitude of the corresponding complaint locations within the second neighborhood; and determines the poor-quality area where the communication service is malfunctioning based on the second cluster. By determining the first cluster and then determining the second cluster based on the latitude and longitude of the complaint location within the first cluster, and finally determining the poor-quality area based on the second cluster, the accuracy of determining the poor-quality area where the communication service is malfunctioning is improved. Attached Figure Description

[0042] Figure 1 This is a schematic diagram of the hardware structure of the device for determining the poor quality region according to an embodiment of the present invention;

[0043] Figure 2 This is a flowchart illustrating the first embodiment of the method for determining poor quality regions according to the present invention.

[0044] Figure 3 This is a detailed flowchart of step S20 of the second embodiment of the method for determining the poor quality region of the present invention;

[0045] Figure 4 This is a detailed flowchart of step S30 of the third embodiment of the method for determining the poor quality region of the present invention.

[0046] Figure 5 This is a schematic diagram of the logic structure of the device for determining the poor quality region of the present invention.

[0047] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0048] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0049] The main solution of this invention is as follows: Based on complaint work order data for communication services, determine the latitude and longitude of the complaint location; determine a first neighborhood radius; determine a first neighborhood of the complaint location's latitude and longitude based on the first neighborhood radius; determine a first cluster based on the latitude and longitude of each complaint location and the latitude and longitude of the corresponding complaint locations within the first neighborhood; determine a second neighborhood radius based on the first neighborhood radius; determine a second neighborhood of the complaint location's latitude and longitude within the first cluster based on the second neighborhood radius; determine a second cluster based on the latitude and longitude of each complaint location within the first cluster and the latitude and longitude of the corresponding complaint locations within the second neighborhood; and determine the poor-quality area where the communication service malfunctions based on the second cluster.

[0050] By identifying the first cluster and then determining the second cluster based on the latitude and longitude of the complaint location of the first cluster, the accuracy of identifying the poor quality areas where communication services are malfunctioning can be improved.

[0051] As one implementation method, the device for determining the poor quality area can be as follows: Figure 1 As shown.

[0052] The embodiments of the present invention relate to a device for determining poor quality regions. This device includes: a processor 101, such as a CPU; a memory 102; and a communication bus 103. The communication bus 103 is used to establish communication between these components.

[0053] Memory 102 can be high-speed RAM or stable memory (non-volatile memory), such as disk storage. Figure 1 As shown, the memory 102, which is a computer-readable storage medium, may include a program for determining poor-quality regions; and the processor 101 may be used to call the program for determining poor-quality regions stored in the memory 102 and perform the following operations:

[0054] Based on the complaint ticket data for communication services, determine the latitude and longitude of the complaint location;

[0055] Determine the first neighborhood radius, determine the first neighborhood of the complaint location's latitude and longitude based on the first neighborhood radius, and determine the first cluster based on the latitude and longitude of each complaint location and the latitude and longitude of the complaint locations within the corresponding first neighborhood;

[0056] The second neighborhood radius is determined based on the first neighborhood radius, the second neighborhood of the complaint location latitude and longitude in the first cluster is determined based on the second neighborhood radius, and the second cluster is determined based on the complaint location latitude and longitude in each of the first clusters and the complaint location latitude and longitude in the corresponding second neighborhood;

[0057] The poor-quality region where the communication service malfunctions is determined based on the second cluster type.

[0058] In one embodiment, the processor 101 can be used to call a program for determining poor-quality regions stored in the memory 102, and perform the following operations:

[0059] Select one of the latitude and longitude coordinates of the location of the complaint as the first core latitude and longitude coordinate;

[0060] Determine the latitude and longitude of all complaint locations within the first neighborhood of the first core latitude and longitude, and add all the latitude and longitude of the complaint locations to the first cluster;

[0061] Among the latitude and longitude of the complaint locations within the first neighborhood of the first core latitude and longitude, a first target latitude and longitude is determined, wherein the first number of the latitude and longitude of the complaint locations within the first neighborhood of the first target latitude and longitude is greater than a preset threshold, and the first target latitude and longitude does not correspond to the first cluster.

[0062] Add all the latitude and longitude of the complaint locations in the first neighborhood of the first target latitude and longitude to the first cluster.

[0063] In one embodiment, the processor 101 can be used to call a program for determining poor-quality regions stored in the memory 102 and perform the following operations:

[0064] Choose any one of the latitude and longitude coordinates of the complaint location as the first latitude and longitude coordinate to be determined;

[0065] Determine a first number of complaint locations within the first neighborhood of the first latitude and longitude to be determined;

[0066] If the first quantity is greater than a preset threshold, and the first latitude and longitude to be determined does not correspond to the first cluster, then the first latitude and longitude to be determined is taken as the first core latitude and longitude.

[0067] In one embodiment, the processor 101 can be used to call a program for determining poor-quality regions stored in the memory 102, and perform the following operations:

[0068] Select one of the latitude and longitude coordinates of the complaint location from the first cluster as the second core latitude and longitude coordinate;

[0069] Determine the latitude and longitude of all complaint locations within the second neighborhood of the second core latitude and longitude, and add all the latitude and longitude of the complaint locations to the second cluster;

[0070] In the latitude and longitude of the complaint location within the second neighborhood of the second core latitude and longitude, a second target latitude and longitude is determined, wherein the second number of the latitude and longitude of the complaint location within the second neighborhood of the second target latitude and longitude is greater than a preset threshold, and the second target latitude and longitude does not correspond to the second cluster;

[0071] Add all the latitude and longitude of the complaint locations in the second neighborhood of the second target latitude and longitude to the second cluster.

[0072] In one embodiment, the processor 101 can be used to call a program for determining poor-quality regions stored in the memory 102, and perform the following operations:

[0073] Choose any one of the latitude and longitude coordinates of the complaint location in the first cluster as the second latitude and longitude coordinate to be determined;

[0074] Determine a second number of complaint locations' latitude and longitude coordinates within the second neighborhood of the second latitude and longitude coordinates to be determined;

[0075] If the second quantity is greater than or equal to a preset threshold, and the second latitude and longitude to be determined does not correspond to the second cluster, then the second latitude and longitude to be determined is determined as the second core latitude and longitude.

[0076] In one embodiment, the processor 101 can be used to call a program for determining poor-quality regions stored in the memory 102, and perform the following operations:

[0077] Determine the Manhattan distance between the latitude and longitude of each pair of the stated complaint locations;

[0078] The first neighborhood radius is determined based on the average of the various Manhattan distances.

[0079] In one embodiment, the processor 101 can be used to call a program for determining poor-quality regions stored in the memory 102, and perform the following operations:

[0080] Determine a third number of latitude and longitude coordinates of the complaint locations within the first cluster;

[0081] The second neighborhood radius is determined based on a preset threshold, the first neighborhood radius, and the third quantity.

[0082] Based on the hardware architecture of the above-mentioned device for determining poor quality regions, an embodiment of the method for determining poor quality regions of the present invention is proposed.

[0083] Reference Figure 2 , Figure 2 This is a first embodiment of the method for determining the poor quality region of the present invention, the method comprising the following steps:

[0084] Step S10: Determine the latitude and longitude of the complaint location based on the complaint work order data of the communication service.

[0085] Specifically, a complaint ticket is a management tool used to record user complaint information. Complaint tickets can obtain communication service data at certain intervals. The complaint ticket data includes user identification, complaint time, complaint location name, and complaint location latitude and longitude, among which the complaint location latitude and longitude is the latitude and longitude information of the user when complaining about the communication service.

[0086] Step S20: Determine the first neighborhood radius, determine the first neighborhood of the complaint location's latitude and longitude based on the first neighborhood radius, and determine the first cluster based on the latitude and longitude of each complaint location and the latitude and longitude of the complaint locations within the corresponding first neighborhood.

[0087] Specifically, the first neighborhood radius is determined. Optionally, the neighborhood radius selected or input by the user can be used as the first neighborhood radius. Optionally, the Euclidean distance between the latitude and longitude of each pair of complaint locations is determined, and the first neighborhood radius is determined based on the average of these Euclidean distances. The Euclidean distance between the latitude and longitude of two complaint locations is shown in the following formula:

[0088]

[0089] Among them, C O This represents the Euclidean distance between the latitude and longitude of the two complaint locations; the latitude and longitude of the two complaint locations are (x1, y1) and (x2, y2), respectively.

[0090] Optionally, determine the Manhattan distance between the latitude and longitude of every two complaint locations, and determine the first neighborhood radius based on the average of these Manhattan distances. The Manhattan distance between the latitude and longitude of two complaint locations is shown in the following formula:

[0091] C M =|x3-x4|+|y3-y4|;

[0092] Among them, C M This represents the Manhattan distance between the latitude and longitude of two complaint locations; the latitude and longitude of the two complaint locations are (x3, y3) and (x4, y4) respectively. Compared to Euclidean distance, the calculation of Manhattan distance is simpler and can greatly improve computational efficiency. Compared to straight-line distance, the calculation of Manhattan distance is more consistent with the user's movement trajectory in real life and is closer to the movement distance between the two complaint locations on the map.

[0093] The first neighborhood of the complaint location's latitude and longitude is determined based on the radius of the first neighborhood. The first neighborhood is a circular area centered on the complaint location's latitude and longitude, with the radius of the first neighborhood as its radius. Each complaint location's latitude and longitude corresponds to a first neighborhood. A first cluster is determined based on each complaint location's latitude and longitude and the corresponding complaint location's latitude and longitude within its first neighborhood. The first cluster includes multiple complaint location latitudes and longitudes. For example, a core latitude and longitude can be selected. If the number of complaint location latitudes and longitudes within the core latitude and longitude's first neighborhood exceeds a preset threshold, all complaint location latitudes and longitudes within the core latitude and longitude's first neighborhood are added to the first cluster.

[0094] Step S30: Determine the second neighborhood radius based on the first neighborhood radius; determine the second neighborhood of the complaint location latitude and longitude in the first cluster based on the second neighborhood radius; determine the second cluster based on the complaint location latitude and longitude in each of the first clusters and the complaint location latitude and longitude in the corresponding second neighborhood.

[0095] Specifically, the second neighborhood radius is determined based on the first neighborhood radius. Optionally, the second neighborhood radius is a preset multiple of the first neighborhood radius. Optionally, a third number of latitude and longitude coordinates of the complaint locations in the first cluster is determined, and the second neighborhood radius is determined based on a preset threshold, the first neighborhood radius, and the third number. For example, the second neighborhood radius is shown in the following formula:

[0096]

[0097] Where, ε i ' represents the second neighborhood radius; ε represents the first neighborhood radius; MinPts represents the preset threshold; M i This indicates the third number of latitude and longitude coordinates of the complaint location within the first cluster.

[0098] The second neighborhood of the complaint location's latitude and longitude in the first cluster is determined based on the second neighborhood radius. The second neighborhood is a circular area centered on the complaint location's latitude and longitude in the first cluster, with the radius of the second neighborhood as its radius. Each complaint location's latitude and longitude in the first cluster corresponds to a second neighborhood. The second cluster is determined based on the complaint location's latitude and longitude in each first cluster and the corresponding complaint location's latitude and longitude within its second neighborhood. For example, a core latitude and longitude can be selected. If the number of complaint location's latitude and longitude within the core latitude and longitude's second neighborhood exceeds a preset threshold, all complaint location's latitude and longitude within the core latitude and longitude's second neighborhood are added to the second cluster.

[0099] Step S40: Determine the poor quality area where the communication service malfunctions based on the second cluster.

[0100] Specifically, the poor-quality area is the geographical area where user complaints are concentrated. The poor-quality area where communication service failures occur is determined based on the second type of cluster, which includes the latitude and longitude of multiple complaint locations. Optionally, boundary latitude and longitude coordinates are determined from the complaint location latitude and longitude coordinates of the second type of cluster, and the poor-quality area is delineated based on these boundary coordinates. Determining the poor-quality area where communication service failures occur based on the second type of cluster facilitates subsequent fault tracking and focused attention, and improves the response speed of communication service complaint handling. Compared to spherical clustering algorithms, the poor-quality area determined based on the second type of cluster is closer to actual geographical conditions and can better identify special shapes such as roads, railway lines, parks, and buildings.

[0101] In this embodiment, the latitude and longitude of the complaint location are determined based on the complaint work order data of the communication service; a first neighborhood radius is determined, and a first neighborhood of the complaint location's latitude and longitude is determined based on the first neighborhood radius; a first cluster is determined based on the latitude and longitude of each complaint location and the latitude and longitude of the corresponding complaint locations within the first neighborhood; a second neighborhood radius is determined based on the first neighborhood radius, and a second neighborhood of the complaint location's latitude and longitude within the first cluster is determined based on the second neighborhood radius; a second cluster is determined based on the latitude and longitude of each complaint location within the first cluster and the latitude and longitude of the corresponding complaint locations within the second neighborhood; and a poor-quality area where the communication service malfunctions is determined based on the second cluster. By determining the first cluster and then determining the second cluster based on the latitude and longitude of the complaint location within the first cluster, and finally determining the poor-quality area based on the second cluster, the accuracy of the determined poor-quality area where the communication service malfunctions is located is improved.

[0102] Reference Figure 3 , Figure 3 This is a second embodiment of the method for determining poor quality regions of the present invention. Based on the first embodiment, step S20 includes:

[0103] Step S21: Select a latitude and longitude of the complaint location as the first core latitude and longitude.

[0104] Step S22: Determine the latitude and longitude of all complaint locations within the first neighborhood of the first core latitude and longitude, and add all the latitude and longitude of the complaint locations to the first cluster;

[0105] Step S23: Among the latitude and longitude of the complaint locations within the first neighborhood of the first core latitude and longitude, determine the first target latitude and longitude, wherein the first number of the latitude and longitude of the complaint locations within the first neighborhood of the first target latitude and longitude is greater than a preset threshold, and the first target latitude and longitude does not correspond to the first cluster.

[0106] Step S24: Add all the latitude and longitude of the complaint locations in the first neighborhood of the first target latitude and longitude to the first cluster.

[0107] Specifically, a complaint location's latitude and longitude are selected as the first core latitude and longitude p. Alternatively, any complaint location's latitude and longitude can be selected as the first latitude and longitude to be determined. If the first latitude and longitude to be determined does not correspond to a first type of cluster C... i Then, the first latitude and longitude to be determined is determined as the first core latitude and longitude p. Optionally, any latitude and longitude of the complaint location can be selected as the first latitude and longitude to be determined, and a first number of complaint location latitude and longitude within the first neighborhood of the first latitude and longitude to be determined can be determined; if the first number is greater than a preset threshold, and the first latitude and longitude to be determined does not correspond to a first cluster C. i If the first number is less than or equal to a preset threshold, then the first latitude and longitude to be determined is taken as the first core latitude and longitude p. If the first number is less than or equal to a preset threshold, then the first latitude and longitude to be determined is taken as noise latitude and longitude and deleted. Deleting noise latitude and longitude can remove malicious complaints from individual users and make it easier to locate and discover common problems.

[0108] Determine the latitude and longitude of all complaint locations within the first neighborhood of the first core latitude and longitude p, and add all complaint location latitude and longitude to the first cluster C. i .

[0109] Among multiple complaint location latitudes and longitudes within the first neighborhood of the first core latitude and longitude p, a first target latitude and longitude is determined, wherein the first number of complaint location latitudes and longitudes within the first neighborhood of the first target latitude and longitude is greater than a preset threshold, and the first target latitude and longitude does not correspond to a first cluster C. i Add the latitude and longitude of all complaint locations in the first neighborhood of the first target's latitude and longitude to the first cluster C. i If, within the first neighborhood of a first core latitude and longitude coordinate p, the number of latitude and longitude coordinates of a complaint location is less than or equal to a preset threshold, then the complaint location latitude and longitude coordinate is considered noise latitude and longitude coordinate and deleted. Deleting noise latitude and longitude coordinates can eliminate malicious complaints from individual users, making it easier to centrally locate and discover common problems.

[0110] In this embodiment, a complaint location's latitude and longitude is selected as the first core latitude and longitude. All complaint location latitudes and longitudes within the first neighborhood of the first core latitude and longitude are determined and added to a first cluster. Among the complaint location latitudes and longitudes within the first neighborhood of the first core latitude and longitude, a first target latitude and longitude is determined. The first target latitude and longitude is further defined if the number of complaint location latitudes and longitudes within the first neighborhood exceeds a preset threshold and if the first target latitude and longitude does not correspond to a first cluster. All complaint location latitudes and longitudes within the first neighborhood of the first target latitude and longitude are added to the first cluster. By clustering the complaint location latitudes and longitudes to obtain the first cluster, the range of the poor-quality area is initially determined, facilitating the subsequent determination of the second cluster. Based on the second cluster, the poor-quality area is determined, improving the accuracy of identifying the poor-quality area where communication services have failed.

[0111] Reference Figure 4 , Figure 4 In a third embodiment of the method for determining poor-quality regions of the present invention, based on the first or second embodiment, step S30 includes:

[0112] Step S31: Select a latitude and longitude of the complaint location from the first cluster as the second core latitude and longitude.

[0113] Step S32: Determine all the latitude and longitude of the complaint locations within the second neighborhood of the second core latitude and longitude, and add all the latitude and longitude of the complaint locations to the second cluster;

[0114] Step S33: In the latitude and longitude of the complaint location within the second neighborhood of the second core latitude and longitude, determine the second target latitude and longitude, wherein the second number of the latitude and longitude of the complaint location within the second neighborhood of the second target latitude and longitude is greater than a preset threshold, and the second target latitude and longitude does not correspond to the second cluster;

[0115] Step S34: Add all the latitude and longitude of the complaint locations in the second neighborhood of the second target latitude and longitude to the second cluster.

[0116] Specifically, in the first type of cluster C i Select the latitude and longitude of the complaint location as the second core latitude and longitude q. Optionally, any first-class cluster C can be selected. i The latitude and longitude of the complaint location are used as the second set of latitude and longitude to be determined; if the second set of latitude and longitude to be determined does not correspond to a second cluster C i If ', then the second undetermined latitude and longitude is determined as the second core latitude and longitude q. Optionally, any first-class cluster C can be selected. i The latitude and longitude of the complaint location are used as the second latitude and longitude to be determined; a second number of complaint location latitude and longitude within the second neighborhood of the second latitude and longitude to be determined is determined; if the second number is greater than or equal to a preset threshold, and the second latitude and longitude to be determined does not correspond to a second cluster C. i If the second undetermined latitude and longitude is determined, then the second core latitude and longitude q is identified. If the second number is less than or equal to a preset threshold, then the second undetermined latitude and longitude is treated as noise latitude and longitude and deleted. Deleting noise latitude and longitude can eliminate malicious complaints from individual users, making it easier to centrally locate and discover common problems.

[0117] Determine the latitude and longitude of all complaint locations within the second neighborhood of the second core latitude and longitude q, and add all complaint location latitude and longitude to the second cluster C. i ';

[0118] Among multiple complaint location latitudes and longitudes within the second neighborhood of the second core latitude and longitude q, a second target latitude and longitude is determined, wherein the number of complaint location latitudes and longitudes within the second neighborhood of the second target latitude and longitude is greater than a preset threshold, and the second target latitude and longitude does not correspond to a second cluster C. i Add the latitude and longitude of all complaint locations in the second neighborhood of the second target's latitude and longitude to the second cluster C. i If, within the second neighborhood of the second core latitude and longitude coordinate q, the number of latitude and longitude coordinates of a complaint location is less than or equal to a preset threshold, then the latitude and longitude coordinate of the complaint location is considered noise latitude and longitude and is deleted. Deleting noise latitude and longitude coordinates can eliminate malicious complaints from individual users, making it easier to centrally locate and discover common problems.

[0119] After identifying the second cluster, determining the poor-quality areas where communication services are malfunctioning based on these clusters helps improve the response speed of complaint handling. Compared to spherical clustering algorithms, the poor-quality areas determined by the second cluster are closer to actual geographical conditions and can better identify special shapes such as roads, railway lines, parks, and buildings.

[0120] In this embodiment, a complaint location latitude and longitude is selected from the first cluster as the second core latitude and longitude. All complaint location latitude and longitudes within the second neighborhood of the second core latitude and longitude are determined and added to the second cluster. Among the complaint location latitude and longitudes within the second neighborhood of the second core latitude and longitude, a second target latitude and longitude is determined. The second target latitude and longitude is further defined if the number of complaint location latitudes and longitudes within the second neighborhood exceeds a preset threshold and if the second target latitude and longitude does not correspond to a second cluster. All complaint location latitudes and longitudes within the second neighborhood of the second target latitude and longitude are added to the second cluster. By determining the second cluster using the complaint location latitude and longitudes in the first cluster, and by determining the poor-quality area based on the second cluster, the accuracy of the poor-quality area is improved, thus improving the accuracy of identifying the poor-quality area where communication services have failed.

[0121] Reference Figure 5 The present invention provides a device for determining a region of poor quality, the device comprising:

[0122] The acquisition module 100 is used to determine the latitude and longitude of the complaint location based on the complaint work order data of the communication service;

[0123] The first calculation module 200 is used to determine a first neighborhood radius, determine a first neighborhood of the latitude and longitude of the complaint location based on the first neighborhood radius, and determine a first cluster based on the latitude and longitude of each complaint location and the latitude and longitude of the complaint locations in the corresponding first neighborhood.

[0124] The second calculation module 300 is used to determine the second neighborhood radius based on the first neighborhood radius, determine the second neighborhood of the complaint location latitude and longitude in the first cluster based on the second neighborhood radius, and determine the second cluster based on the complaint location latitude and longitude in each of the first clusters and the complaint location latitude and longitude in the corresponding second neighborhood;

[0125] The determination module 400 is used to determine the poor quality area where the communication service has failed based on the second type of cluster.

[0126] In one embodiment, in determining a first cluster based on the latitude and longitude of each of the complaint locations and the latitude and longitude of the corresponding complaint locations within the first neighborhood, the first calculation module 200 is specifically used for:

[0127] Select one of the latitude and longitude coordinates of the location of the complaint as the first core latitude and longitude coordinate;

[0128] Determine the latitude and longitude of all complaint locations within the first neighborhood of the first core latitude and longitude, and add all the latitude and longitude of the complaint locations to the first cluster;

[0129] Among the latitude and longitude of the complaint locations within the first neighborhood of the first core latitude and longitude, a first target latitude and longitude is determined, wherein the first number of the latitude and longitude of the complaint locations within the first neighborhood of the first target latitude and longitude is greater than a preset threshold, and the first target latitude and longitude does not correspond to the first cluster.

[0130] Add all the latitude and longitude of the complaint locations in the first neighborhood of the first target latitude and longitude to the first cluster.

[0131] In one embodiment, regarding the selection of a latitude and longitude of the complaint location as the first core latitude and longitude, the first calculation module 200 is specifically used for:

[0132] Choose any one of the latitude and longitude coordinates of the complaint location as the first latitude and longitude coordinate to be determined;

[0133] Determine a first number of complaint locations within the first neighborhood of the first latitude and longitude to be determined;

[0134] If the first quantity is greater than a preset threshold, and the first latitude and longitude to be determined does not correspond to the first cluster, then the first latitude and longitude to be determined is taken as the first core latitude and longitude.

[0135] In one embodiment, in determining the second cluster based on the latitude and longitude of the complaint location in each of the first clusters and the latitude and longitude of the complaint location in the corresponding second neighborhood, the second calculation module 300 is specifically used for:

[0136] Select one of the latitude and longitude coordinates of the complaint location from the first cluster as the second core latitude and longitude coordinate;

[0137] Determine the latitude and longitude of all complaint locations within the second neighborhood of the second core latitude and longitude, and add all the latitude and longitude of the complaint locations to the second cluster;

[0138] In the latitude and longitude of the complaint location within the second neighborhood of the second core latitude and longitude, a second target latitude and longitude is determined, wherein the second number of the latitude and longitude of the complaint location within the second neighborhood of the second target latitude and longitude is greater than a preset threshold, and the second target latitude and longitude does not correspond to the second cluster;

[0139] Add all the latitude and longitude of the complaint locations in the second neighborhood of the second target latitude and longitude to the second cluster.

[0140] In one embodiment, the second calculation module 300 is specifically used to select a latitude and longitude coordinate of the complaint location in the first cluster as the second core latitude and longitude coordinate aspect, and the latitude and longitude coordinate of the complaint location is selected as the second core latitude and longitude coordinate aspect.

[0141] Choose any one of the latitude and longitude coordinates of the complaint location in the first cluster as the second latitude and longitude coordinate to be determined;

[0142] Determine a second number of complaint locations' latitude and longitude coordinates within the second neighborhood of the second latitude and longitude coordinates to be determined;

[0143] If the second quantity is greater than or equal to a preset threshold, and the second latitude and longitude to be determined does not correspond to the second cluster, then the second latitude and longitude to be determined is determined as the second core latitude and longitude.

[0144] In one embodiment, in determining the first neighborhood radius, the first calculation module 200 is specifically used for:

[0145] Determine the Manhattan distance between the latitude and longitude of each pair of the stated complaint locations;

[0146] The first neighborhood radius is determined based on the average of the various Manhattan distances.

[0147] In one embodiment, in determining the second neighborhood radius based on the first neighborhood radius, the second calculation module 300 is specifically used for:

[0148] Determine a third number of latitude and longitude coordinates of the complaint locations within the first cluster;

[0149] The second neighborhood radius is determined based on a preset threshold, the first neighborhood radius, and the third quantity.

[0150] The present invention also provides a device for determining poor quality regions, the device comprising a memory, a processor, and a program for determining poor quality regions stored in the memory and executable on the processor, wherein when the program for determining poor quality regions is executed by the processor, it implements the various steps of the method for determining poor quality regions as described in the above embodiments.

[0151] The present invention also provides a computer-readable storage medium storing a program for determining poor quality regions, wherein when the program for determining poor quality regions is executed by a processor, it implements the various steps of the method for determining poor quality regions as described in the above embodiments.

[0152] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0153] 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, system, 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, system, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, system, article, or apparatus that includes that element.

[0154] Through the above description of the embodiments, those skilled in the art can clearly understand that the systems described in the 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 the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a computer-readable storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes several instructions to cause a terminal device (which may be a mobile phone, computer, parking management device, air conditioner, or network device, etc.) to execute the systems described in the various embodiments of the present invention.

[0155] The above are merely preferred embodiments of the present invention and do not limit the scope of the patent. Any equivalent structural or procedural transformations made based on the description and drawings of the present invention, or direct or indirect applications in other related technical fields, are similarly included within the scope of patent protection of the present invention.

Claims

1. A method for determining a region of poor quality, characterized in that, The method for determining the poor quality region includes: Based on the complaint ticket data for communication services, determine the latitude and longitude of the complaint location; The Manhattan distance between the latitude and longitude of each pair of complaint locations is determined. A first neighborhood radius is determined based on the average value of the Manhattan distances. A first neighborhood of the latitude and longitude of the complaint locations is determined based on the first neighborhood radius. A first cluster is determined based on the latitude and longitude of each complaint location and the latitude and longitude of the complaint locations within the corresponding first neighborhood. The radius of the second neighborhood is determined by the following formula: ； in, The radius of the second neighborhood; The radius of the first neighborhood; MinPts The preset threshold; This is the third number of latitude and longitude coordinates of the complaint location within the first cluster; The second neighborhood of the complaint location latitude and longitude in the first cluster is determined based on the second neighborhood radius, and the second cluster is determined based on the complaint location latitude and longitude in each of the first clusters and the complaint location latitude and longitude in the corresponding second neighborhood. The poor-quality areas where the communication service malfunctions are determined based on the second type of cluster; The step of determining the second cluster based on the latitude and longitude of the complaint location in each of the first clusters and the latitude and longitude of the complaint location in the corresponding second neighborhood includes: Select one of the latitude and longitude coordinates of the complaint location from the first cluster as the second core latitude and longitude coordinate; Determine the latitude and longitude of all complaint locations within the second neighborhood of the second core latitude and longitude, and add all the latitude and longitude of the complaint locations to the second cluster; In the latitude and longitude of the complaint location within the second neighborhood of the second core latitude and longitude, a second target latitude and longitude is determined, wherein the second number of the latitude and longitude of the complaint location within the second neighborhood of the second target latitude and longitude is greater than a preset threshold, and the second target latitude and longitude does not correspond to the second cluster; Add all the latitude and longitude of the complaint locations in the second neighborhood of the second target latitude and longitude to the second cluster; The step of determining the first cluster based on the latitude and longitude of each complaint location and the latitude and longitude of the corresponding complaint locations within the first neighborhood includes: Select one of the latitude and longitude coordinates of the location of the complaint as the first core latitude and longitude coordinate; Determine the latitude and longitude of all complaint locations within the first neighborhood of the first core latitude and longitude, and add all the latitude and longitude of the complaint locations to the first cluster; Among the latitude and longitude of the complaint locations within the first neighborhood of the first core latitude and longitude, a first target latitude and longitude is determined, wherein the first number of the latitude and longitude of the complaint locations within the first neighborhood of the first target latitude and longitude is greater than a preset threshold, and the first target latitude and longitude does not correspond to the first cluster. Add all the latitude and longitude of the complaint locations in the first neighborhood of the first target latitude and longitude to the first cluster.

2. The method for determining the poor quality region as described in claim 1, characterized in that, The step of selecting a latitude and longitude coordinate of the complaint location as the first core latitude and longitude coordinate includes: Choose any one of the latitude and longitude coordinates of the complaint location as the first latitude and longitude coordinate to be determined; Determine a first number of complaint locations within the first neighborhood of the first latitude and longitude to be determined; If the first quantity is greater than a preset threshold, and the first latitude and longitude to be determined does not correspond to the first cluster, then the first latitude and longitude to be determined is taken as the first core latitude and longitude.

3. The method for determining the poor quality region as described in claim 1, characterized in that, The step of selecting a latitude and longitude coordinate of the complaint location in the first cluster as the second core latitude and longitude coordinate includes: Choose any one of the latitude and longitude coordinates of the complaint location in the first cluster as the second latitude and longitude coordinate to be determined; Determine a second number of complaint locations' latitude and longitude coordinates within the second neighborhood of the second latitude and longitude coordinates to be determined; If the second quantity is greater than or equal to a preset threshold, and the second latitude and longitude to be determined does not correspond to the second cluster, then the second latitude and longitude to be determined is determined as the second core latitude and longitude.

4. A device for determining a region of poor quality, characterized in that, The device for determining the poor quality region includes: The acquisition module is used to determine the latitude and longitude of the complaint location based on the complaint work order data of the communication service; The first calculation module is used to determine the Manhattan distance between the latitude and longitude of each pair of complaint locations, determine the first neighborhood radius based on the average value of each Manhattan distance, determine the first neighborhood of the latitude and longitude of the complaint location based on the first neighborhood radius, and determine the first cluster based on the latitude and longitude of each complaint location and the latitude and longitude of the complaint locations in the corresponding first neighborhood. The second calculation module is used to determine the second neighborhood radius using the following formula: ； in, The radius of the second neighborhood; The radius of the first neighborhood; MinPts The preset threshold; The third number of complaint locations in the first cluster; the second neighborhood of complaint locations in the first cluster is determined according to the second neighborhood radius; the second cluster is determined according to the complaint locations in each of the first clusters and the complaint locations in the corresponding second neighborhood. The determination module is used to determine the poor quality area where the communication service has failed based on the second cluster type; The step of determining the second cluster based on the latitude and longitude of the complaint location in each of the first clusters and the latitude and longitude of the complaint location in the corresponding second neighborhood includes: Select one of the latitude and longitude coordinates of the complaint location from the first cluster as the second core latitude and longitude coordinate; Determine the latitude and longitude of all complaint locations within the second neighborhood of the second core latitude and longitude, and add all the latitude and longitude of the complaint locations to the second cluster; In the latitude and longitude of the complaint location within the second neighborhood of the second core latitude and longitude, a second target latitude and longitude is determined, wherein the second number of the latitude and longitude of the complaint location within the second neighborhood of the second target latitude and longitude is greater than a preset threshold, and the second target latitude and longitude does not correspond to the second cluster; Add all the latitude and longitude of the complaint locations in the second neighborhood of the second target latitude and longitude to the second cluster; The step of determining the first cluster based on the latitude and longitude of each complaint location and the latitude and longitude of the corresponding complaint locations within the first neighborhood includes: Select one of the latitude and longitude coordinates of the location of the complaint as the first core latitude and longitude coordinate; Determine the latitude and longitude of all complaint locations within the first neighborhood of the first core latitude and longitude, and add all the latitude and longitude of the complaint locations to the first cluster; Among the latitude and longitude of the complaint locations within the first neighborhood of the first core latitude and longitude, a first target latitude and longitude is determined, wherein the first number of the latitude and longitude of the complaint locations within the first neighborhood of the first target latitude and longitude is greater than a preset threshold, and the first target latitude and longitude does not correspond to the first cluster. Add all the latitude and longitude of the complaint locations in the first neighborhood of the first target latitude and longitude to the first cluster.

5. A device for determining poor quality areas, characterized in that, The device for determining the poor quality region includes a memory, a processor, and a program for determining the poor quality region stored in the memory and executable on the processor. When the program for determining the poor quality region is executed by the processor, it implements the steps of the method for determining the poor quality region as described in any one of claims 1-3.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a program for determining poor-quality regions, which, when executed by a processor, implements the steps of the method for determining poor-quality regions as described in any one of claims 1-3.

Images