User service feature identification method and device, equipment and storage medium

By dividing the 5G network into three-dimensional grids and using XDR and MR measurement reports combined with the DBSCAN algorithm, high-frequency service areas and stable users are identified, solving the problem of accuracy in identifying user service characteristics in the 5G network and improving the targeting of network optimization and user experience.

CN118945672APending Publication Date: 2024-11-12CHINA UNITED NETWORK COMM GRP CO LTD

Patent Information

Application Number
CN202310521843.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2023-05-10
Publication Date
2024-11-12

AI Technical Summary

Technical Problem

In 5G networks, the inability to accurately identify user service characteristics in different geographical areas leads to a lack of targeted network optimization, which affects user experience.

Method used

By dividing the target area into three-dimensional grids, using XDR data and MR measurement reports as a correlation, and employing density-based clustering algorithms (such as DBSCAN) to cluster the three-dimensional grids, high-frequency service areas and stable users are identified, and their service characteristics are analyzed.

Benefits of technology

It enables accurate identification of user service characteristics in different regions, supports targeted network optimization, and improves user experience.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118945672A_ABST
    Figure CN118945672A_ABST
Patent Text Reader

Abstract

The invention belongs to the technical field of communication, and particularly relates to a user service feature identification method and device, equipment and a storage medium. The method comprises the following steps: acquiring an MR (Measurement Report) of a user in a target area; according to the XDR data and the MR measurement report of the user, determining a corresponding service event in each three-dimensional grid divided in the target area; determining the three-dimensional grids with the same type of business events as candidate three-dimensional grids, clustering the candidate three-dimensional grids according to the position information of the candidate three-dimensional grids, and determining a cluster comprising a plurality of candidate three-dimensional grids; and according to the XDR data of the users, determining user service features of the target users in each cluster. According to the invention, the user service characteristics of different areas can be accurately identified.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of communication technology, and in particular to a method, device, equipment and storage medium for identifying user service characteristics. Background Art

[0002] With the popularization of 5G networks, services such as video and live broadcasting have become the most common application scenarios of 5G. In large cities, there are usually very large numbers of users and business volumes. However, in different geographical areas, different user business characteristics (business types of high-frequency applications, application types, traffic usage, etc.) are often different. For example, users in residential areas may often watch live broadcasts, and users in commercial areas may have more video services. Users in different areas may frequently use different types of applications and traffic usage. For example, in residential areas, traffic usage will be relatively less.

[0003] If network problems occur when users are using 5G networks, the user experience will obviously be reduced. The causes of network problems are generally different in different regions and in different environments (such as different hardware devices) due to different user service characteristics. Therefore, it is necessary to optimize the network in a targeted manner based on the user service characteristics of different regions.

[0004] Therefore, being able to accurately identify the service characteristics of users in different areas is very important for optimizing 5G services, so it is necessary to propose a solution that can more accurately identify the service characteristics of users in different areas. Summary of the invention

[0005] The present application provides a method, apparatus, device, and storage medium for identifying user service characteristics, which are used to more accurately identify user service characteristics in different areas.

[0006] In a first aspect, the present application provides a method for identifying user service features, the method being applied to a server, the method comprising:

[0007] Obtain MR measurement reports of users in the target area;

[0008] Determine the corresponding service event in each three-dimensional grid divided in the target area according to the user's XDR data and MR measurement report;

[0009] Determine stereo grids with the same type of business events as candidate stereo grids, and cluster the candidate stereo grids according to position information of the candidate stereo grids to determine a cluster cluster containing a plurality of the candidate stereo grids;

[0010] The user service characteristics of the target user in each of the clusters are determined according to the XDR data of the user.

[0011] In the above preferred technical solution of the method for identifying user service features, clustering the candidate three-dimensional grids according to the position information of the candidate three-dimensional grids includes:

[0012] In the target area, determining a number of cluster center points;

[0013] The DBSCAN algorithm based on density and noise is adopted to cluster the candidate stereo grids according to the cluster center point according to the preset cluster distance value.

[0014] In the above preferred technical solution of the method for identifying user service characteristics, the cluster center point includes: a base station in the target area.

[0015] In the above-mentioned preferred technical solution of the method for identifying user service features, clustering the candidate three-dimensional grids according to the preset clustering distance value based on the cluster center point includes:

[0016] According to the frequency point and the physical cell identifier PCI of the base station sector, among the candidate three-dimensional grids having the same type of service events, determine a candidate three-dimensional grid of the same sector in the coverage area of ​​each sector of each of the base stations;

[0017] In each sector coverage area of ​​each of the base stations, the candidate three-dimensional grids in the same sector are clustered according to the preset clustering distance value.

[0018] In the above preferred technical solution of the method for identifying user service features, before determining the user service features of the target user in each of the clusters, the method further includes:

[0019] In the target area, determine a first candidate user whose service usage times and service usage duration exceed a threshold value according to the N4 interface data of the 5G network;

[0020] Among the first candidate users, the target user is determined based on the N3 interface data and the N4 interface data of the 5G network.

[0021] In the above-mentioned preferred technical solution of the method for identifying user service characteristics, determining, in the target area, the first candidate user whose service usage times and service usage duration exceed the threshold according to the N4 interface data of the 5G network includes:

[0022] Determine business users of business events of the same type within a first preset time range;

[0023] Determine the number of times the service is used and the duration of service use by the service user within a first preset duration range;

[0024] The service user whose service usage times are greater than or equal to a preset times threshold and whose service usage duration is greater than or equal to a preset time threshold is determined as the first candidate user.

[0025] In the above-mentioned preferred technical solution of the method for identifying user service characteristics, among the first candidate users, determining the target user according to the N3 interface data and the N4 interface data of the 5G network includes:

[0026] Determine a cluster of the same type in the cluster clusters, wherein the service event type corresponding to the cluster of the same type is consistent with the service event type corresponding to the first candidate user;

[0027] Within a second preset time range, determining regional users among the first candidate users that appear in each of the same type of clusters;

[0028] Within the second preset time range, the percentage of days that users appear in the area and the high-frequency appearance period are determined, and the percentage of days that users appear is:

[0029] The ratio of the number of days that the regional users appear in the same type of clusters within the second preset time range to the second preset time range;

[0030] The high-frequency occurrence period is:

[0031] The users in the area frequently appear in the clusters of the same type within the second preset time range;

[0032] The regional users whose occurrence days account for a proportion greater than or equal to a preset day account threshold and whose high-frequency occurrence time period meets a preset time period are determined as the target users.

[0033] In the above preferred technical solution of the method for identifying user service features, after determining the user service features of the target user in each of the clusters according to the user's XDR data, the method further includes:

[0034] Within a third preset time range, if the ratio of the number of target users to the number of all users appearing in the same type of cluster is greater than or equal to a preset proportion threshold, the user service feature is marked to the same type of cluster.

[0035] In the above preferred technical solution of the user service feature identification method, determining the corresponding service event in each of the three-dimensional grids according to the MR measurement report includes:

[0036] Constructing a three-dimensional grid feature fingerprint library of the target area;

[0037] Collecting the MR measurement reports of network users in the target area, and locating the MR measurement reports to the three-dimensional grid according to the three-dimensional grid feature fingerprint library;

[0038] The XDR data is associated with the MR measurement report to determine a corresponding service event in each of the three-dimensional grids.

[0039] In a second aspect, the present application provides a user service feature identification device, the device comprising:

[0040] A grid division module is used to divide the target area into a number of three-dimensional grids according to a preset accuracy;

[0041] A first determination module is used to determine the corresponding service event in each three-dimensional grid divided in the target area according to the XDR data and the MR measurement report, and determine the three-dimensional grids with the same type of service events as candidate three-dimensional grids;

[0042] A clustering module, used for clustering each of the candidate stereo grids according to the position information of each of the candidate stereo grids, and determining a clustering cluster including a plurality of the candidate stereo grids;

[0043] The second determination module is used for:

[0044] The user service characteristics of the target user in each of the clusters are determined according to the XDR data of the user.

[0045] In a third aspect, the present application provides a user service feature identification device, the device comprising: a processor and a memory;

[0046] The memory is used to store computer programs;

[0047] The processor is used to execute the computer program stored in the memory to implement the above-mentioned method for identifying user service characteristics.

[0048] In a fourth aspect, the present application provides a readable storage medium having a computer program stored thereon; the computer program is used to implement the method for identifying user service characteristics as described above.

[0049] The present application provides a method, device, equipment, and storage medium for identifying user service characteristics. First, a three-dimensional grid is divided in the target area. By associating the user's XDR data and the MR measurement report, the user's service is located in a specific three-dimensional grid. On this basis, by clustering the three-dimensional grid based on density, areas with high-density use of a certain type of service can be obtained, and then stable users of the corresponding type of service can be screened out in these areas. The service characteristics of these stable users can be analyzed based on the XDR data, thereby accurately identifying the user service characteristics of different areas. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0051] Figure 1 is a flow chart of a method for identifying user service characteristics provided in an embodiment of the present application;

[0052] Figure 2 is a flow chart of a candidate stereo grid clustering method provided in an embodiment of the present application;

[0053] Figure 3 is a flow chart of a method for clustering candidate stereo grids in the same sector provided in an embodiment of the present application;

[0054] Figure 4 This is a schematic diagram of clustering candidate stereo grids in the same sector provided by an embodiment of the present application;

[0055] Figure 5 This is a flow chart for determining a target user provided by an embodiment of the present application;

[0056] Figure 6 Schematic diagram of a device for identifying user service characteristics provided in an embodiment of the present application;

[0057] Figure 7 It is a schematic diagram of a device for identifying user service characteristics provided in an embodiment of the present application.

[0058] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0059] In order to make the purpose, technical solutions and advantages of this application clearer, the technical solutions in this application will be clearly and completely described below in conjunction with the drawings in this application. Obviously, the described embodiments are part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0060] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in sequences other than those illustrated or described herein, for example.

[0061] In the embodiments of the present application, the words "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0062] As mentioned above, if network problems occur when users are using 5G networks, the service experience will obviously be reduced. Different user service characteristics and different environments (such as different hardware devices) in different regions generally cause different reasons for network problems. Therefore, it is necessary to optimize the network in a targeted manner according to the user service characteristics in different regions. Traditional network analysis methods cannot accomplish this task.

[0063] In the era of big data, XDR data and MR measurement reports are the two main types of data on the network side.

[0064] XDR data is a detailed record of signaling and services used by the application system generated after processing based on the full amount of data. In the 5G network, XDR data can collect 5G network N3 and N4 interface data, which includes user information, service information, call record information, etc.

[0065] MR measurement report refers to the information sent every 480ms on the service channel (470ms on the signaling channel). MR measurement report mainly includes three types of measurement reports: MRO, MRS and MRE. MRO represents the periodic measurement report sample data file, which contains the user positioning parameter information and network evaluation coverage information.

[0066] Therefore, XDR data and MR measurement reports can be actually applied to network problem mining and analysis after being cleaned, associated, and algorithmically mined using big data analysis methods.

[0067] On this basis, the present application proposes a method, device, equipment, and storage medium for identifying user service characteristics. The core concept is to divide the target area into several three-dimensional grids, and through the association of XDR data and MR measurement reports, the user's service can be located in a specific three-dimensional grid. The three-dimensional grids corresponding to the same type of service are clustered using a density-based clustering algorithm to obtain the area where this service is frequently used. Then, the stable users in the area are determined, and the XDR data of the stable users are used for analysis to obtain the user service characteristics of these areas, so that subsequent network optimization analysis can be carried out in a targeted manner.

[0068] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0069] Figure 1 is a flow chart of a method for identifying user service features provided in an embodiment of the present application, such as Figure 1 As shown, in embodiment 1 of the present application, a method for identifying user service features applied to a server is provided, the method comprising:

[0070] S101, obtaining MR measurement reports of users in a target area;

[0071] S102, determining the corresponding service event in each three-dimensional grid divided in the target area according to the user's XDR data and MR measurement report;

[0072] S103, determining stereo grids with the same type of business events as candidate stereo grids, and clustering the candidate stereo grids according to the position information of the candidate stereo grids to determine a clustering cluster including a plurality of candidate stereo grids;

[0073] S104: Determine the user service characteristics of the target user in each cluster according to the user's XDR data.

[0074] In this embodiment, the target area is a geographical area to be analyzed, which may be a city, a residential area, a commercial area, a village, etc. First, an MR measurement report of the target area needs to be obtained to facilitate subsequent use for business event positioning.

[0075] In step S102, in order to accurately locate the user's business events, the target area needs to be divided into different sub-areas of smaller sizes. Specifically, different sub-areas of smaller sizes can be divided into a geographical area by rasterization, and multiple grids can be divided, and each grid can correspond to a sub-area. In practical applications, the area can be rasterized according to different accuracy requirements. For example, for cities with high business volume, the accuracy can be appropriately improved, such as the length and width of the three-dimensional grid is 20 meters, or 50 meters. For villages with low business volume, the accuracy can be appropriately reduced, such as the length and width are 200 meters, etc. Due to different needs, the length and width of the three-dimensional grid can also be different, as the basis for rasterization.

[0076] When it is necessary to divide a three-dimensional grid in an urban area, due to the existence of buildings, dividing the grid only on a two-dimensional plane cannot achieve accurate positioning of business events. According to actual needs, the three-dimensional grid can be set at different heights. For example, in a general floor, the height can be set to 3 meters.

[0077] In step S102, since the user's XDR data carries user information and service information, and the MR measurement report contains the user's positioning information, the XDR data and the MR measurement report are associated. When the target area has been divided into several three-dimensional grids, the user's service events can be located in a specific three-dimensional grid. Specifically, the UE S1AP ID in the XDR data can be associated with the UE S1AP ID in the MR data to associate the XDR data with the MR measurement report. The UE S1AP ID is the content in the UE context and is also the index field in the S1AP message. UE refers to the user terminal. In this way, each three-dimensional grid corresponds to a service event, and the service event includes a video event, a live broadcast event, etc. The type of service event can be determined according to the analysis requirements.

[0078] In step S103, the stereo grids corresponding to the same type of business events are first determined as candidate stereo grids. All candidate stereo grids are marked with the same type of business events, for example, all are video events. On this basis, using a density-based clustering algorithm, these candidate stereo grids corresponding to the same type of business events can be clustered into several clusters according to the density of these grids, that is, the distance between the grids, and each cluster contains multiple candidate stereo grids. The distance variable of the clustering is variable, and finally step S103 obtains several high-density use areas of this type of business events, and each cluster is equivalent to an area composed of multiple stereo grids.

[0079] In step S104, it is necessary to determine the target users in the target area according to certain screening principles. The screening principles may be service usage duration, service usage frequency, application usage type, frequency of occurrence in clusters, number of network problems, etc. Then, the user service characteristics of the target users are analyzed according to the XDR data of the target users. The user service characteristics may include: user service type, service time, service duration, application type, traffic usage, call duration, service-related performance indicators, and service network requirements. These data may be based on hourly granularity.

[0080] Through the technical solution in Example 1, it is possible to accurately identify user service characteristics in different areas, thereby facilitating subsequent analysis of network problems in different areas.

[0081] Step S103 in Example 1 requires the use of a density-based clustering algorithm. Figure 2 is a flow chart of a candidate stereo grid clustering method provided in an embodiment of the present application, such as Figure 2 As shown, in Example 2, a feasible technical solution is proposed for the clustering process, and the clustering method includes:

[0082] S201, determining a number of cluster center points in the target area;

[0083] S202 , using a density-based DBSCAN algorithm with noise, clustering each candidate stereo grid according to a preset cluster distance value based on the cluster center point.

[0084] In this embodiment, DBSCAN (Density-Based Spatial Clustering of Applications with Noise) is a density-based spatial clustering algorithm. The algorithm divides areas with sufficient density into clusters and finds clusters of arbitrary shapes in a spatial database with noise. It defines a cluster as the largest set of density-connected points. The principle is that the algorithm randomly selects one of the many sample points, draws a circle around the selected sample point, specifies the radius of the circle and the minimum number of sample points contained in the circle, and if there are enough sample points within the specified radius (i.e., the clustering distance value), the center of the circle is transferred to the internal sample point, and the internal sample point is used as the cluster center point, and other nearby sample points are circled. The clustering distance value can be adjusted according to the required accuracy, such as 10 meters.

[0085] When the DBSCAN algorithm is applied in the field of communications, in Example 3 of the present application, a base station can be selected as the cluster center point. In actual mobile communication services, by building multiple base stations in different geographical locations, mobile communication signals can cover as many different areas as possible. A base station may refer to a radio transceiver station that transmits information to a mobile terminal through a mobile communication exchange center in a certain radio coverage area.

[0086] In practical applications, a base station can usually be divided into multiple sectors. The sector here refers to the area covered by a base station or a part of the base station (the part pointed by the sector antenna) in the mobile communication system, in which the mobile terminal can communicate with the base station through the wireless channel. It is precisely because the base station communicates with the mobile terminals near it that the base station can be used as the clustering center. In this way, after the clustering is completed, the formed cluster is actually associated with the base station, so that when the network needs to be optimized and analyzed later, a base station can be quickly located.

[0087] Since base stations are divided into sectors, simply locating a base station is not enough. Figure 3 is a flow chart of a method for clustering candidate stereo grids in the same sector provided by an embodiment of the present application, such as Figure 3 As shown, the embodiment of the present application also provides a method for clustering three-dimensional grids of candidates in the same sector when the base station is used as a cluster center point, the method comprising:

[0088] S301, according to the frequency point and physical cell identifier PCI of the base station sector, among the candidate three-dimensional grids having the same type of service events, determine the candidate three-dimensional grid of the same sector in the coverage area of ​​each sector of each base station;

[0089] S302: In each sector coverage area of ​​each base station, cluster candidate three-dimensional grids in the same sector according to a preset clustering distance value.

[0090] The frequency point and the physical cell identifier PCI are used to filter out the service events in the same sector. Because the service events have been located in the candidate three-dimensional grids, the candidate three-dimensional grids in the same sector can be filtered out through the service events in the same sector.

[0091] Figure 4 This is a schematic diagram of clustering candidate stereo grids in the same sector provided in the embodiment of the present application. Figure 4 The clustering of candidate stereo grids in the same sector in Example 3 of the present application is described.

[0092] exist Figure 4 The network includes: a base station 401, a first sector 402, a second sector 403, a third sector 404, a first cluster 405, a second cluster 406, and a third cluster 407.

[0093] exist Figure 4 It can be seen that the base station 401 is divided into three sectors, namely the first sector 402, the second sector 403 and the third sector 404. The first sector 402 is clustered into a first cluster 405, the second sector 403 is clustered into a second cluster 406, and the third sector 404 is clustered into a third cluster 407. In actual applications, each sector may have multiple clusters, and the base station may have more than three sectors. If there are N sectors, the N sectors are clustered separately.

[0094] By clustering each sector of the base station separately, due to the principle of the DBSCAN algorithm, the final clustering cluster is associated with the sector of the base station. In this way, when optimizing the network problem later, it is easy to know in which sector of the base station the problematic service is located.

[0095] Furthermore, it is also necessary to determine the target users in the cluster. Figure 5 This is a flow chart for determining a target user provided by an embodiment of the present application, such as Figure 5 As shown, in Embodiment 4 of the present application, the method for determining the target user includes:

[0096] S501, determining business users of business events of the same type within a first preset time range;

[0097] S502, determining the number of times a service user uses a service and the service usage duration within a first preset duration;

[0098] S503, determining a service user whose service usage times are greater than or equal to a preset times threshold and whose service usage duration is greater than or equal to a preset time threshold as a first candidate user;

[0099] S504, determining clusters of the same type in the clusters;

[0100] S505: determining, within a second preset time period, regional users among the first candidate users that appear in each cluster of the same type;

[0101] S506, determining the percentage of days in which regional users appear and the high-frequency appearance time period within the second preset time range;

[0102] S507: Determine regional users whose occurrence days account for a percentage greater than or equal to a preset day account threshold and whose high-frequency occurrence period meets a preset period as target users.

[0103] In this example:

[0104] The business event type corresponding to the cluster of the same type is consistent with the business event type corresponding to the first candidate user;

[0105] The percentage of days of occurrence is:

[0106] The ratio of the number of days that regional users appear in the same type of clusters within the second preset time range to the second preset time range;

[0107] The high frequency periods are:

[0108] The regional users are in a high-frequency appearance period of the same type of clusters within the second preset time range.

[0109] After completing the clustering for each type of business event, only the high-density usage area of ​​this type of business event (i.e., the same type of clustering clusters) is found. First, it is necessary to find the stable users of this type of business, that is, the first candidate users, and then find the target users who appear frequently in the same type of clustering clusters among the first candidate users. The target users are both users who use the service frequently and those who appear frequently in the high-density usage area of ​​this type of business event. Therefore, the user business characteristics of the target users can reflect the user business characteristics of these same type of clustering clusters.

[0110] When determining the first candidate user, it is necessary to determine the number of times the service user uses the service and the service usage duration within the first preset time range; when determining the target user, it is necessary to determine the percentage of days the regional users appear and the high-frequency appearance time periods within the second preset time range. The first preset time range and the second preset time range can be set as needed, and the number of service uses, service usage duration, percentage of days of appearance, and high-frequency appearance time periods can be obtained by analyzing the N3 interface data and N4 interface data of the user's 5G network. Specifically, the second preset time range can be 7 days. A first candidate user appears in the same type of clustering cluster for 4 days in these 7 days, and the high-frequency appearance time period is from 7 pm to 8 pm, which meets the preset time period, then this first candidate user can be judged as the target user.

[0111] After obtaining the target user, in Embodiment 5 of the present application, regional steady-state user portrait analysis may also be performed, and the analysis method includes:

[0112] Within the third preset time range, if the ratio of the number of target users to the number of all users appearing in the same type of cluster is greater than or equal to the preset proportion threshold, the user service feature is marked to the same type of cluster.

[0113] The third preset time range and preset proportion threshold can also be determined according to demand. For example, the third preset time range can be set to seven days, and the preset proportion threshold can be set to 30%. That is, in seven days, if the target users appearing in the same type of cluster account for more than 30% of all users appearing in the same type of cluster, the user service characteristics of the target users are marked to the same type of cluster. The reason for this setting is that when the ratio of the number of target users to the number of all users appearing in the same type of cluster is greater than or equal to the preset proportion threshold, the association between the user service characteristics of the target users and the same type of cluster is further enhanced.

[0114] In the present application, to associate a business event with a stereo grid, a technique of associating an MR measurement report with a stereo grid feature fingerprint library is also required. In Example 6 of the present application, the method includes:

[0115] Constructing a three-dimensional grid feature fingerprint library of the target area;

[0116] Collecting MR measurement reports of network users in the target area, and locating the MR measurement reports to the three-dimensional grid according to the three-dimensional grid feature fingerprint library;

[0117] The XDR data is associated with the MR measurement report to determine a corresponding service event in each of the three-dimensional grids.

[0118] In Embodiment 7 of the present application, a device for identifying user service characteristics is provided. Figure 6 Schematic diagram of a device for identifying user service characteristics provided in an embodiment of the present application, such as Figure 6 As shown, the device includes: a grid division module 601, a first determination module 602, a clustering module 603, and a second determination module 604;

[0119] A grid division module 601 is used to divide the target area into a number of three-dimensional grids according to a preset accuracy;

[0120] A first determination module 602 is used to determine the corresponding service event in each three-dimensional grid divided in the target area according to the XDR data and the MR measurement report, and determine the three-dimensional grids with the same type of service events as candidate three-dimensional grids;

[0121] The clustering module 603 is used to cluster the candidate stereo grids according to the position information of the candidate stereo grids, and determine a cluster including a plurality of the candidate stereo grids;

[0122] The second determining module 604 is used to:

[0123] The user service characteristics of the target user in each of the clusters are determined according to the XDR data of the user.

[0124] In Embodiment 8 of the present application, a device for identifying user service characteristics is provided. Figure 7 Schematic diagram of a device for identifying user service features provided in an embodiment of the present application, such as Figure 7 As shown, the device 70 includes: a processor 701, a memory 702, and a communication component 703, and the processor 701, the memory 702, and the communication component 703 are connected via a bus 704. ;

[0125] The memory 702 is used to store computer programs;

[0126] The processor 701 is configured to execute the computer program stored in the memory to implement the above-mentioned method for identifying user service characteristics.

[0127] In the above Figure 7 In the illustrated embodiment, it should be understood that the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in the invention may be directly implemented as being executed by a hardware processor, or may be executed by a combination of hardware and software modules in the processor.

[0128] The memory may include a high-speed memory (Random Access Memory, RAM), and may also include a non-volatile memory (Non-volatile Memory, NVM), such as at least one disk memory.

[0129] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the bus in the drawings of this application is not limited to only one bus or type of bus.

[0130] In Embodiment 9 of the present application, a readable storage medium is further provided, on which a computer program is stored; the computer program is used to implement the user feature recognition method as described above.

[0131] The computer-readable storage medium mentioned above can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The readable storage medium can be any available medium that can be accessed by a general or special-purpose computer.

[0132] An exemplary readable storage medium is coupled to a processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (Application Specific Integrated Circuits, referred to as ASIC). Of course, the processor and the readable storage medium can also exist in the device as discrete components.

[0133] The division of the units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interface, device or unit, which may be electrical, mechanical or other forms.

[0134] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0135] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0136] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0137] Those skilled in the art can understand that all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, disk or optical disk and other media that can store program codes.

[0138] So far, the technical solution of the present application has been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present application is obviously not limited to these specific embodiments, and the above embodiments are only used to illustrate the technical solution of the present application rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for identifying user service characteristics, characterized in that: Applied to a server, the method comprises: Obtain MR measurement reports of users in the target area; Determine, according to the user's XDR data and the MR measurement report, a corresponding service event in each three-dimensional grid divided in the target area; Determine stereo grids with the same type of business events as candidate stereo grids, and cluster the candidate stereo grids according to position information of the candidate stereo grids to determine a cluster cluster containing a plurality of the candidate stereo grids; The user service characteristics of the target user in each of the clusters are determined according to the XDR data of the user.

2. The method according to claim 1, characterized in that: The clustering of the candidate stereo grids according to the position information of the candidate stereo grids includes: In the target area, determining a number of cluster center points; The DBSCAN algorithm based on density and noise is adopted to cluster the candidate stereo grids according to the cluster center point according to the preset cluster distance value.

3. The method according to claim 2, characterized in that The cluster center point includes: a base station in the target area.

4. The method according to claim 3, characterized in that The clustering of the candidate stereo grids according to the cluster center points according to a preset cluster distance value includes: According to the frequency point and the physical cell identifier PCI of the base station sector, among the candidate three-dimensional grids having the same type of service events, determine a candidate three-dimensional grid of the same sector in the coverage area of ​​each sector of each of the base stations; In each sector coverage area of ​​each of the base stations, the candidate three-dimensional grids in the same sector are clustered according to the preset clustering distance value.

5. The method according to claim 1, characterized in that Before determining the user service characteristics of the target user in each of the clusters, the method further includes: In the target area, determine a first candidate user whose service usage times and service usage duration exceed a threshold value according to the N4 interface data of the 5G network; Among the first candidate users, the target user is determined based on the N3 interface data and the N4 interface data of the 5G network.

6. The method according to claim 5, characterized in that Determining, in the target area, a first candidate user whose service usage times and service usage duration exceed a threshold according to N4 interface data of the 5G network includes: Determine business users of business events of the same type within a first preset time range; Determine the number of times the service is used and the duration of service use by the service user within a first preset duration range; The service user whose service usage times are greater than or equal to a preset times threshold and whose service usage duration is greater than or equal to a preset time threshold is determined as the first candidate user.

7. The method according to claim 6, characterized in that Among the first candidate users, determining the target user according to N3 interface data and N4 interface data of the 5G network includes: Determine a cluster of the same type in the cluster clusters, wherein the service event type corresponding to the cluster of the same type is consistent with the service event type corresponding to the first candidate user; Determine, within a second preset time range, regional users among the first candidate users that appear in each of the same type of clusters; Within the second preset time range, the percentage of days that users appear in the area and the high-frequency appearance period are determined, and the percentage of days that users appear is: The ratio of the number of days that the regional users appear in the same type of clusters within the second preset time range to the second preset time range; The high-frequency occurrence period is: The users in the area frequently appear in the clusters of the same type within the second preset time range; The regional users whose occurrence days account for a proportion greater than or equal to a preset day account threshold and whose high-frequency occurrence time period meets a preset time period are determined as the target users.

8. The method according to claim 6, characterized in that After determining the user service characteristics of the target user in each of the clusters according to the XDR data of the user, the method further includes: Within a third preset time range, if the ratio of the number of target users to the number of all users appearing in the same type of cluster is greater than or equal to a preset proportion threshold, the user service feature is marked to the same type of cluster.

9. The method according to any one of claims 1 to 8, characterized in that: Determining the corresponding service event in each of the three-dimensional grids according to the MR measurement report includes: Constructing a three-dimensional grid feature fingerprint library of the target area; Collecting the MR measurement reports of network users in the target area, and locating the MR measurement reports to the three-dimensional grid according to the three-dimensional grid feature fingerprint library; The XDR data is associated with the MR measurement report to determine a corresponding service event in each of the three-dimensional grids.

10. A device for identifying user service characteristics, characterized in that: The device comprises: A grid division module is used to divide the target area into a number of three-dimensional grids according to a preset accuracy; A first determination module is used to determine the corresponding service event in each three-dimensional grid divided in the target area according to the XDR data and the MR measurement report, and determine the three-dimensional grids with the same type of service events as candidate three-dimensional grids; A clustering module, used for clustering each of the candidate stereo grids according to the position information of each of the candidate stereo grids, and determining a clustering cluster including a plurality of the candidate stereo grids; The second determination module is used for: The user service characteristics of the target user in each of the clusters are determined according to the XDR data of the user.

11. A device for identifying user service characteristics, characterized in that: The device comprises: a processor and a memory; The memory is used to store computer programs; The processor is used to execute the computer program stored in the memory to implement the method for identifying user service characteristics according to any one of claims 1 to 8.

12. A readable storage medium, characterized in that: The readable storage medium stores a computer program; the computer program is used to implement the method for identifying user service characteristics according to any one of claims 1 to 8.

Citation Information

Patent Citations

  • Radio frequency fingerprint information base generation method and device and grid positioning method and device

    CN111385805A

  • Method and device for evaluating total user quantity

    CN113453253A

  • Network planning method and device, computing equipment and computer readable storage medium

    CN114257957A

  • High-value network area identification method and device, electronic equipment and storage medium

    CN115866627A

  • Antenna parameter adjusting method and device

    CN115866636A

Cited By

  • Communication method and communication apparatus

    WO2026113938A1