Method and system for identifying a user's home area

Abstract

The application provides a user's resident area identification method, comprising the following steps: screening the control plane data of the user in 4G / 5G network switching, taking the switching signaling as a boundary, generating first user data, which is user identification, cell unique identification, start time, end time and resident duration, wherein the resident duration is equal to the end time minus the start time; according to the first user data, merging the resident duration of the user in the same cell, generating second user data, which is user identification, cell unique identification and resident duration; after the second user data is associated with the working parameters, generating third user data and sorting according to the resident duration, wherein the third user data is user identification, cell unique identification, resident duration, longitude and latitude; clustering the cells passed by the user according to the resident duration and the longitude and latitude positions and generating clusters; calculating the cluster centers and selecting the cluster center with the longest resident duration as the user's resident area. The application also provides a user's resident area identification system.

Description

TECHNICAL FIELD

[0001] The present application relates to a method, system, device and computer readable storage medium for identifying a user's resident area. BACKGROUND

[0002] In the application environment of a mobile network, identifying the resident information of a mobile user is beneficial to better guarantee the service experience of the user and is beneficial to business promotion. The method and problems existing in the prior art are that: (1) based on the fact that a coordinate point falls into a preset grid, the model accuracy excessively depends on the scientific nature of the grid division. (2) based on a clustering algorithm, the selection of a clustering center needs a large amount of computing resources, and a cluster with an excessively large radius is not avoided in the process, and the cluster with an excessively large radius is low in accuracy of identifying the resident position. SUMMARY

[0003] To solve the above problems, the present application provides a method for identifying a user's resident area.

[0004] The method comprises the following steps: screening the control plane data of the user in 4G / 5G network switching, generating first user data based on the switching signaling, the first user data comprising: user identifier, cell unique identifier, start time, end time, residence duration, wherein the residence duration = end time - start time; merging the residence duration of the user in the same cell according to the first user data, generating second user data, the second user data comprising: user identifier, cell unique identifier, merged residence duration; after associating the second user data with the working parameters, generating third user data and sorting according to the associated residence duration, wherein the third user data comprises: user identifier, cell unique identifier, associated residence duration, longitude, latitude; clustering the cells passed by the user according to the associated residence duration and the longitude and latitude positions and generating a cluster; calculating the cluster center and selecting the cluster center with the longest associated residence duration as the resident area of the user.

[0005] According to the advantageous design scheme of the present application, for the 4G / 5G data in a given time, the switching signaling is used as a boundary, the start time of the switching signaling is used as the end time of the last cell, and the end time of the switching signaling is used as the start time of the next cell.

[0006] According to the advantageous design scheme of the present application, wherein the 4G interface is an S1-MME interface, the 5G interface is an N1 / N2 interface, the start time is a starttime in the S1-MME interface or a procedure_start_time in the N1 / N2 interface, and the end time is an endtime in the S1-MME interface or a procedure_end_time in the N1 / N2 interface.

[0007] According to an advantageous design of the present application, when the user appears in the same cell at different time periods, the residence time of the user in the same cell in the first user data is combined to generate second user data.

[0008] According to an advantageous design of the present application, the sorting is in reverse order.

[0009] According to an advantageous design of the present application, the calculation method of the cluster center is as follows:

[0010] Wherein, eci is the unique identification of the cell, and n is the number of cells in the cluster.

[0011] According to an advantageous design of the present application, the distance between any cell outside the cluster and the cluster center of all existing clusters is calculated, and the distance is taken as the distance between the any cell outside the cluster and the cluster.

[0012] According to an advantageous design of the present application, the first cell passed by the user is taken as the first cluster and the cluster center at initialization.

[0013] According to an advantageous design of the present application, when the distance between any cell outside the cluster and any cluster center is less than the threshold value, the cell is added to the cluster and the cluster center position is updated, when the distance between any cell outside the cluster and multiple cluster centers is less than the threshold value, the cell is added to the cluster with the shortest distance and the cluster center position is updated, otherwise, the cell will be taken as the cluster center of a new cluster, thereby forming the cluster centers of several new clusters.

[0014] According to an advantageous design of the present application, the threshold value is any value in the range of 500 meters to 5000 meters, for example, 2000 meters.

[0015] According to an advantageous design of the present application, the sum of the associated residence time of all cells in each cluster is calculated, and the cluster center with the longest associated residence time is selected as the permanent residence area of the user.

[0016] According to another aspect of the present application, a system for identifying the permanent residence area of a user is provided, the system comprising:

[0017] The first data generation module is configured to filter the control plane data of the user in 4G / 5G network switching, generate first user data based on the switching signaling, and the first user data includes: user identification, unique cell identification, start time, end time, and residence time, wherein the residence time = end time - start time.

[0018] a second data generation module configured to generate second user data by merging the residence time length of the user in the same cell according to the first user data, the second user data comprising: user identification, cell unique identification, and the merged residence time length;

[0019] a third data generation module configured to generate third user data and sort the third user data according to the associated residence time length after the second user data is associated with the operating parameter, the third user data comprising: user identification, cell unique identification, associated residence time length, longitude, and latitude;

[0020] a clustering module configured to cluster the cells passed by the user according to the associated residence time length and position and generate clusters,

[0021] a calculation module configured to calculate the cluster center and select the cluster center with the longest associated residence time length as the permanent residence area of the user.

[0022] According to another aspect of the present application, an electronic device is provided, which comprises:

[0023] at least one processor;

[0024] a memory having at least one program stored thereon, when the at least one program is executed by the at least one processor, the at least one processor implements the above-mentioned method for identifying the permanent residence area of a user.

[0025] According to still another aspect of the present application, a computer readable storage medium is provided, the computer readable storage medium having a computer program stored thereon, when the program is executed by a processor, the method for identifying the permanent residence area of a user is implemented.

[0026] In general, according to the present application, the cells are sorted according to the residence time length before clustering, so that the cells with longer residence time length are either easy to become cluster centers or are added to the already formed clusters with longer residence time length, which is beneficial to form more advantageous clusters. The cluster center is considered according to the position and residence time length of each cell during clustering, so that the cluster center is closer to the cells with longer residence time length in the cluster, thereby making the result closer to the actual permanent residence area of the user. Therefore, the model is established by using the operator data, the permanent residence area information of the user is more accurately identified, and the user experience is better guaranteed and the market front-line work is promoted. BRIEF DESCRIPTION OF DRAWINGS

[0027] Figure 1 is a flowchart of the method for identifying the permanent residence area of a user provided by the present application. DETAILED DESCRIPTION

[0028] In order for those skilled in the art to better understand the technical solutions of the present application, the technical solutions in the present application will be clearly and completely described below in conjunction with the drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of protection of the present application.

[0029] The present application provides a user's resident area identification method.

[0030] The method comprises the following steps: screening the control plane data of the user in the 4G / 5G network switching, generating first user data, the first user data comprising: user identification, cell unique identification, start time, end time, residence duration, wherein the residence duration = end time - start time; according to the first user data, merging the residence duration of the user in the same cell, generating second user data, the second user data comprising: user identification, cell unique identification, merged residence duration; after associating the second user data with the working parameters, generating third user data and sorting according to the associated residence duration, wherein the third user data comprises: user identification, cell unique identification, associated residence duration, longitude, latitude; clustering the cells passed by the user according to the associated residence duration and the longitude and latitude positions and generating clusters; calculating the cluster center and selecting the cluster center with the longest associated residence duration as the user's resident area.

[0031] According to the advantageous design scheme of the present application, for the 4G / 5G data in a given time, the switching signaling is taken as the boundary, the start time of the switching signaling is taken as the end time of the last cell, and the end time of the switching signaling is taken as the start time of the next cell.

[0032] According to the advantageous design scheme of the present application, wherein the 4G interface is S1-MME interface, the 5G interface is N1 / N2 interface, the start time is the starttime in the S1-MME interface or the procedure_start_time in the N1 / N2 interface, and the end time is the endtime in the S1-MME or the procedure_end_time in the N1 / N2.

[0033] According to the advantageous design scheme of the present application, when the user appears in the same cell at different time periods, the residence duration of the user in the same cell in the first user data is merged to generate the second user data.

[0034] According to the advantageous design scheme of the present application, the sorting is in reverse order.

[0035] According to the advantageous design scheme of the present application, wherein the calculation method of the cluster center is:

[0036] wherein eci is a cell unique identity, n is the number of cells in the cluster.

[0037] According to an advantageous design of the present application, the distance between any cell outside the cluster and all cluster centers of the existing cluster is calculated, and the distance is taken as the distance between the any cell outside the cluster and the cluster.

[0038] According to an advantageous design of the present application, the first cell passed by the user is taken as the first cluster and the cluster center in the initialization.

[0039] According to an advantageous design of the present application, when the distance between any cell outside the cluster and any cluster center is less than a threshold value, the cell is added to the cluster and the cluster center position is updated, when the distance between any cell outside the cluster and multiple cluster centers is less than the threshold value, the cell is added to the cluster with the shortest distance and the cluster center position is updated, otherwise, the cell is taken as the cluster center of a new cluster, so that the cluster centers of several new clusters can be formed.

[0040] According to an advantageous design of the present application, the threshold value is any value in the range of 500 meters to 5000 meters, for example, 2000 meters.

[0041] According to an advantageous design of the present application, the sum of the associated residence time of all cells in each cluster is calculated, and the cluster center with the longest associated residence time is selected as the permanent residence area of the user.

[0042] According to another aspect of the present application, a system for identifying the permanent residence area of a user is provided, the system comprising:

[0043] A first data generation module is configured to filter the control plane data of the user in 4G / 5G network switching, generate first user data based on the switching signaling, and the first user data comprises: user identity, cell unique identity, start time, end time, and residence time, wherein the residence time = end time - start time.

[0044] A second data generation module is configured to merge the residence time of the user in the same cell based on the first user data, generate second user data, and the second user data comprises: user identity, cell unique identity, and merged residence time.

[0045] A third data generation module is configured to generate third user data after the second user data is associated with the operating parameters, and sort the associated residence time, wherein the third user data comprises: user identity, cell unique identity, associated residence time, longitude, and latitude.

[0046] a clustering module configured to cluster the cells passed by the user according to the associated residence time and location and generate clusters,

[0047] a calculation module configured to calculate cluster centers and select the cluster center with the longest associated residence time as the permanent residence area of the user.

[0048] According to another aspect of the present application, an electronic device is provided, which comprises:

[0049] at least one processor;

[0050] a memory having at least one program stored thereon, when the at least one program is executed by the at least one processor, the at least one processor implements the above-mentioned user permanent residence area identification method.

[0051] According to still another aspect of the present application, a computer readable storage medium is provided, which has a computer program stored thereon, when the program is executed by a processor, the above-mentioned user permanent residence area identification method is implemented.

[0052] Next, in order to better illustrate the user permanent residence area identification method according to the present application, an example is given.

[0053] According to the present application, a user permanent residence area identification method is provided, which filters the control plane data of the user in 4G or 5G network switching, generates user trajectory by taking switching signaling as the boundary; merges and sorts the residence time of the user in the same cell; after associating with the operating parameter, clusters are sequentially completed according to the associated residence time and location, and the cluster center with the longest associated residence time is selected as the permanent residence area of the user.

[0054] Some field descriptions are as follows.

[0055] S1-MME data switching signaling part field description

[0056]

[0057] N1 / N2 interface switching signaling data part field description

[0058]

[0059]

[0060] Operating parameter data

[0061] Field name Field description eci / nci Cell unique identity longitude Longitude latitude Latitude

[0062] Step S1 processes the original data list to generate user trajectory.

[0063] For 4G or 5G data in a given time (4G interface: S1-MME, 5G interface: N1 / N2), the start time of the handover signaling (starttime in S1-MME or procedure_start_time in N1 / N2) is taken as the end time of the previous cell, and the end time of the handover signaling (endtime in S1-MME or procedure_end_time in N1 / N2) is taken as the start time of the next cell, and data in the following format is generated: user identifier, cell unique identifier, start time, end time, and residence duration, where the residence duration = end time - start time.

[0064] Step S2 merges the duration information of the user in the same cell.

[0065] Since the user can appear in the same cell at different time periods, the data of step S1 is merged with the duration information of the user in the same cell to generate data in the following format: user identifier, cell unique identifier, and residence duration.

[0066] Step S3 associates the data of step S2 with the operating parameters to generate data in the following format: user identifier, cell unique identifier, residence duration, longitude, and latitude.

[0067] Step S4 sorts (in reverse order) the data in step S3 according to the residence duration.

[0068] Step S5 clusters the cells passed through by the user according to certain rules, and the specific steps are as follows:

[0069] First, the 1st cell in step S4 is taken as the cluster center of the 1st cluster. For the remaining cells in step S4, the distance between this cell and all cluster centers is traversed. If the shortest cluster center is less than 2 km, it is considered that this cell should be in this cluster, and the cell is added to the shortest cluster center. Otherwise, it is considered that the cell is located at an isolated position point, and a new cluster is generated with this cell.

[0070] Cluster center calculation method:

[0071]

[0072] Where eci is the cell unique identifier, and n is the number of cells in the cluster.

[0073] Here, it needs to be noted that each cluster center simultaneously considers the location (i.e. longitude and latitude) and the residence time of each cell in the current cluster. According to the formula, the weight of the cell with a long residence time is large, and the cluster center calculated in this way is closer to the cell with a longer residence time in the cluster. In actual situations, assuming that there are 3 cells in this cluster, cell a has been resident for 3 hours, cell b has been resident for 1 hour, and cell c has been resident for 10 minutes, the cluster center should be closer to a, so that the result is closer to the actual situation.

[0074] For example: for user1, the following data is obtained after step S4:

[0075]

[0076] Example Step 1: Set Eci1 as the cluster center of the first cluster, and the first cluster is [Eci1]

[0077] Example Step 2: According to the longitude and latitude, the distance between Eci2 and the cluster center Eci1 of the first cluster is 5km (greater than the threshold of 2km), so Eci2 does not belong to any existing cluster, and a new cluster must be generated, with Eci2 as the cluster center of the second cluster.

[0078] Example Step 3: The distance between Eci3 and the cluster center (i.e. Eci1) of the first cluster is 0.5km, and the distance between Eci3 and the cluster center (i.e. Eci2) of the second cluster is 5.5km, so the cluster with the shortest distance to Eci3 is the first cluster, and the distance is less than 2km, so Eci3 is aggregated into the first cluster. At this time, since the first cluster has changed from [Eci1] to [Eci1, Eci3], the cluster center needs to be updated according to the above formula, and the cluster center of the second cluster [Eci2] remains unchanged.

[0079] Example Step 4: The distance between Eci4 and the cluster center of the first cluster [Eci1, Eci3] is 10km, and the distance between Eci4 and the cluster center of the second cluster [Eci2] is 12km, both of which are >2km, so the third cluster is generated as [Eci4], and the cluster center is Eci4

[0080] Example Step 5: The distance between Eci5 and the cluster center of the first cluster [Eci1, Eci3] is 3km, the distance between Eci5 and the cluster center of the second cluster [Eci2] is 1.5km, and the distance between Eci5 and the cluster center of the third cluster [Eci4] is 11km, so the cluster with the shortest distance to Eci5 is the second cluster, and the distance is less than 2km, so Eci5 is aggregated into the second cluster. Since the second cluster has changed from [Eci2] to [Eci2, Eci5], the cluster center needs to be updated according to the above formula, and the cluster centers of other clusters remain unchanged.

[0081] For example, step 6: calculate the distance between Eci6 and the cluster centers of the first, second and third clusters respectively, the shortest distance is the cluster center of the third cluster, and the distance is 1.8km, Eci6 is clustered into the third cluster. The third cluster becomes [Eci4, Eci6], and the cluster center needs to be updated according to the above formula, and the cluster centers of other clusters remain unchanged.

[0082] Step S6 calculates the residence time of all cells in each cluster, and selects the cluster center with the longest residence time as the permanent residence area of the user. For each cluster, the sum of the residence time of all cells in the cluster is calculated, and the center point of the cluster with the longest residence time is selected as the permanent residence area. Therefore, the cluster center is a latitude and longitude point, which is obtained by weighting the latitude and longitude of all cells in the cluster.

[0083] For example, step 7: the residence time of the first cluster [Eci1, Eci3] is 12h, the residence time of the second cluster [Eci2, Eci5] is 8h, and the residence time of the third cluster [Eci4, Eci6] is 4h, so the permanent residence area of the user is the cluster center of the first cluster.

[0084] According to the present application, the cells are sorted according to the residence time before clustering, so that the cells with longer residence time are either easy to become cluster centers or are added to the clusters with longer residence time, which is beneficial to form more advantageous clusters. The cluster center considers the position and residence time of each cell during clustering, so that the cluster center is closer to the cells with longer residence time in the cluster, so that the result is closer to the actual permanent residence area of the user. Therefore, the model is established by using the operator data, the user's permanent residence information is more accurately identified, and the user experience is better protected and the market front-line work is promoted.

[0085] Those skilled in the art can understand that all or some of the steps in the method disclosed above, the functional modules / units in the system and the device can be implemented as software, firmware, hardware and appropriate combinations thereof. In the hardware implementation, the division between the functional modules / units mentioned in the above description does not necessarily correspond to the division of physical components; for example, one physical component can have multiple functions, or one function or step can be performed by several physical components in cooperation. Some or all of the physical components can be implemented as software executed by a processor, such as a central processing unit, a digital signal processor or a microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit. Such software can be distributed on a computer readable medium, which can include computer storage media (or non-transitory media) and communication media (or transitory media). As known to those skilled in the art, the term computer storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tapes, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store the desired information and can be accessed by a computer. In addition, as known to those skilled in the art, communication media typically includes computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism, and can include any information delivery medium.

[0086] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement to part or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for identifying a user's frequently visited area, characterized in that, The method includes the following steps: The control plane data of users in 4G / 5G mobile networks is filtered, and the first user data is generated with the handover signaling as the boundary. The first user data includes: user identifier, cell unique identifier, start time, end time, and dwell time, where dwell time = end time - start time. For 4G / 5G data within a given time period, the start time of the handover signaling is used as the end time of the previous cell, and the end time of the handover signaling is used as the start time of the next cell. Based on the first user data, the dwell time of users in the same cell is merged to generate second user data. The second user data includes: user identifier, cell unique identifier, and merged dwell time. After the second user data is associated with the engineering parameters, third user data is generated and sorted according to the associated dwell time. The third user data includes: user ID, cell unique ID, associated dwell time, longitude, and latitude. The communities visited by the user are clustered and generated based on the associated dwell time and latitude and longitude location; Calculate the cluster center and select the cluster center with the longest associated residence time as the user's permanent residence area.

2. The method according to claim 1, characterized in that, in, The 4G interface is the S1-MME interface, and the 5G interface is the N1 / N2 interface. The start time is the starttime in the S1-MME interface or the procedure_start_time in the N1 / N2 interface, and the end time is the endtime in the S1-MME interface or the procedure_end_time in the N1 / N2 interface.

3. The method according to claim 1, characterized in that, When a user appears in the same community at different time periods, the duration of the user's stay in the same community in the first user data is merged to generate the second user data.

4. The method according to claim 1, characterized in that, The sorting is in reverse order.

5. The method according to claim 1, characterized in that, in, Methods for calculating cluster centers: Where eci is the unique identifier of the cell, and n is the number of cells in the cluster.

6. The method according to claim 5, characterized in that, The distance between any cell outside the cluster that the user has passed through and the cluster center of all existing clusters is calculated. This distance is used as the distance between the cell outside the cluster and the cluster.

7. The method according to claim 6, characterized in that, During initialization, the first cell that the user passes through is designated as the first cluster and its center.

8. The method according to claim 6, characterized in that, If the distance between any cell outside a cluster and any cluster center is less than a threshold value, the cell is added to that cluster and the cluster center position is updated. If the distance between any cell outside a cluster and multiple cluster centers is less than a threshold value, the cell outside the cluster is added to the cluster with the shortest distance and the cluster center position is updated. Otherwise, this cell will be used as the cluster center of a new cluster, thus forming several new cluster centers.

9. The method according to claim 8, characterized in that, The threshold value is any value between 500 meters and 5000 meters.

10. The method according to claim 9, characterized in that, The threshold value is 2000 meters.

11. The method according to claim 1, characterized in that, Calculate the total associated dwell time of all cells in each cluster, and select the cluster center with the longest associated dwell time as the user's permanent residence area.

12. A user's permanent residence area identification system, characterized in that, include: The first data generation module is configured to filter control plane data of users in 4G / 5G mobile networks and generate first user data with handover signaling as the boundary. The first user data includes: user identifier, cell unique identifier, start time, end time, and dwell time, where dwell time = end time - start time. For 4G / 5G data within a given time period, the start time of the handover signaling is used as the end time of the previous cell, and the end time of the handover signaling is used as the start time of the next cell. The second data generation module is configured to generate second user data by merging the dwell time of users in the same cell based on the first user data. The second user data includes: user identifier, cell unique identifier, and merged dwell time. The third data generation module is set up to generate third user data after the second user data is associated with the engineering parameters, and sort it according to the associated dwell time. The third user data includes: user ID, unique cell ID, associated dwell time, longitude, and latitude. The clustering module is configured to cluster the cells visited by a user based on associated dwell time and location, and generate clusters accordingly. The calculation module is configured to calculate cluster centers and select the cluster center with the longest associated dwell time as the user's permanent residence area.

13. An electronic device, comprising: At least one processor; A memory storing at least one program, which, when executed by the at least one processor, causes the at least one processor to implement the method according to any one of claims 1-11.

14. A computer-readable storage medium having a computer program stored thereon, the program being executed by a processor to implement the method of any one of claims 1-11.

Images