User type identification method and device, nonvolatile storage medium and electronic equipment

Abstract

The invention discloses a user type identification method and device, a nonvolatile storage medium and electronic equipment. The method comprises the following steps: acquiring application program traffic data of terminal equipment of a target object in a first preset time period; determining resident position information and non-resident position information of the target object according to the position information corresponding to the flow data of the application program; determining communication behavior information of the target object according to cell connection data in the application flow data; and determining a user type of the target object according to the resident position information, the non-resident position information and the communication behavior information, the user type being used for indicating an allocation optimization mode of communication resources. The technical problem that the communication service provided by an operator does not conform to the actual demand of the user due to the fact that the user type cannot be determined in the related technology is solved.

Description

Technical Field

[0001] The present application relates to the field of communications, and in particular, to a user type identification method, device, non-volatile storage medium and electronic device. Background Art

[0002] At present, related technologies are unable to identify users' permanent behavior types, resulting in the inability to specifically address complaints and needs of users with different behavioral characteristics, which affects user perception and usage experience.

[0003] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0004] The embodiments of the present application provide a user type identification method, device, non-volatile storage medium and electronic device to at least solve the technical problem that the communication services provided by the operator do not meet the actual needs of the user due to the inability to determine the user type in the related technology.

[0005] According to one aspect of an embodiment of the present application, a user type identification method is provided, including: obtaining application traffic data of a terminal device of a target object in a first preset time period; determining the permanent location information and non-resident location information of the target object based on location information corresponding to the application traffic data; determining the communication behavior information of the target object based on the cell connection data in the application traffic data, wherein the communication behavior information includes the total duration of the target mobile behavior of the target object in the first preset time period, and the proportion of the duration in the first preset time period, and the target mobile behavior includes the behavior of switching cells at a frequency greater than a preset frequency; determining the user type of the target object based on the permanent location information, the non-resident location information and the communication behavior information, wherein the user type is used to indicate the optimization method for allocating communication resources.

[0006] Optionally, the resident location information includes the number of resident areas of the target object, and the non-resident location information includes a first discrete ratio between the number of discrete sampling points obtained after clustering the sampling points of the application traffic data and the number of all sampling points; determining the user type based on the resident location information, the non-resident location information and the communication behavior information includes: determining a preset number set, wherein the preset number set includes a first preset number, a second preset number, a third preset number and a fourth preset number; determining a preset ratio set, wherein the preset ratio set includes a first preset ratio, a second preset ratio, a third preset ratio, a fourth preset ratio and a fifth preset ratio; determining the user type based on the number of resident areas, the first discrete ratio, the preset number set and the preset ratio set, or determining the user type based on the number of resident areas, the first discrete ratio, the duration ratio, the preset number set and the preset ratio set.

[0007] Optionally, determining the user type according to the number of permanent areas, the first discrete ratio, the preset number set and the preset ratio set includes: when the number of permanent areas is the first preset number and the ratio is less than the first preset ratio, determining the user type as a fixed area user.

[0008] Optionally, determining the user type based on the number of permanent areas, the first discrete ratio, the preset number set and the preset ratio set includes: determining the second preset time period and the third preset time period in the first preset time period, and determining the second permanent area information and the second discrete ratio corresponding to the second preset time period, and the third permanent area information and the third discrete ratio corresponding to the third preset time period, wherein the second permanent area information includes the first permanent area position and the first permanent area number corresponding to the second preset time period, and the third permanent area information includes the second permanent area position and the second permanent area number corresponding to the third preset time period; when the number of first permanent areas is the second preset number, the second discrete ratio is less than the second preset ratio, the number of second permanent areas is the third preset number, the third discrete ratio is less than the third preset ratio, and the distance between the first permanent area position and the second permanent area position is greater than the preset distance, the user type is determined to be a regular commuting user, wherein the second preset number and the third preset number are both 1.

[0009] Optionally, determining the user type based on the number of permanent areas, the first discrete ratio, the duration ratio, a preset number set and a preset ratio set includes: when the number of permanent areas is a fourth preset number, the ratio is greater than the fourth preset ratio, and the duration ratio is greater than the fifth preset ratio, determining the user type as a field user.

[0010] Optionally, determining the permanent location information and non-resident location information of the target object based on the location information corresponding to the application traffic data includes: sampling the application traffic data to obtain multiple sampling data points, and determining the location information of the sampling data points based on the location information corresponding to the application traffic data; clustering the multiple sampling data points based on the location information of each sampling data point to obtain multiple cluster centers, and determining the central location information of each cluster center, as well as the number of cluster centers, wherein each cluster center corresponds to a permanent area of ​​the target object, the number of cluster centers is the number of permanent areas, the center location information is the permanent area location information of the permanent areas, and the permanent location information includes the permanent area location information and the number of permanent areas; determining the proportion of discrete points, wherein the proportion of discrete points is the ratio of the number of data points that are not marked with corresponding cluster centers to the number of all data points after clustering, and the non-resident location information includes the proportion of discrete points.

[0011] Optionally, determining the communication behavior information of the target object based on the cell connection data in the application traffic data includes: dividing a first preset time period into multiple sub-time periods, wherein the duration of each sub-time period is equal; determining the number of cell connections in the cell connection data corresponding to each sub-time period, wherein when the number of cell connections is greater than the preset number of cells, determining the communication behavior corresponding to the sub-time period as the target mobile behavior; determining the ratio between the number of sub-time periods corresponding to the target mobile behavior and the total number of all sub-time periods as the duration ratio.

[0012] According to another aspect of an embodiment of the present application, a user type identification device is also provided, including: a first processing module, used to obtain application traffic data of a terminal device of a target object in a first preset time period; a second processing module, used to determine the permanent location information and non-resident location information of the target object based on the location information corresponding to the application traffic data; a third processing module, used to determine the communication behavior information of the target object based on the cell connection data in the application traffic data, wherein the communication behavior information includes the total duration corresponding to the target mobile behavior of the target object in the first preset time period, and the proportion of the duration in the first preset time period, and the target mobile behavior includes the behavior of switching cells at a frequency greater than a preset frequency; a fourth processing module, used to determine the user type of the target object based on the permanent location information, the non-resident location information and the communication behavior information, wherein the user type is used to indicate the optimization method for allocating communication resources.

[0013] According to another aspect of an embodiment of the present application, a non-volatile storage medium is provided, in which a program is stored, wherein when the program is running, a device where the non-volatile storage medium is located is controlled to execute a user type identification method.

[0014] According to another aspect of an embodiment of the present application, there is further provided an electronic device, including: a memory and a processor, the processor being configured to run a program stored in the memory, wherein the user type identification method is executed when the program is run.

[0015] According to another aspect of an embodiment of the present application, a computer program product is also provided, including a computer program, and the computer program implements the user type identification method when executed by a processor.

[0016] In an embodiment of the present application, the application traffic data of the terminal device of the target object in the first preset time period is obtained; the permanent location information and non-resident location information of the target object are determined based on the location information corresponding to the application traffic data; the communication behavior information of the target object is determined based on the cell connection data in the application traffic data, wherein the communication behavior information includes the total duration of the target mobile behavior of the target object in the first preset time period, and the target mobile behavior includes the behavior of switching cells with a frequency greater than a preset frequency; the user type of the target object is determined based on the permanent location information, the non-resident location information and the communication behavior information, wherein the user type is used to indicate the method of optimizing the allocation of communication resources. By determining the permanent location information, the non-resident location information and the communication behavior information of the target object based on the application traffic data, and then determining the user type of the target object, the purpose of accurately determining the user type is achieved, thereby realizing the technical effect of determining the actual demand information of the target object based on the user type, thereby solving the technical problem that the communication service provided by the operator does not meet the actual needs of the user due to the inability to determine the user type in the related technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0018] Figure 1 It is a structural schematic diagram of a computer terminal (mobile terminal) provided according to an embodiment of the present application;

[0019] Figure 2 It is a flowchart of a user type identification method provided according to an embodiment of the present application;

[0020] Figure 3 This is a schematic diagram of clustering results of users in a fixed area provided according to an embodiment of the present application;

[0021] Figure 4 It is a schematic diagram of clustering results of a second preset time period of a regular commuting user provided according to an embodiment of the present application;

[0022] Figure 5 is a schematic diagram of clustering results of a third preset time period of a regular commuting user provided according to an embodiment of the present application;

[0023] Figure 6 It is a combined schematic diagram of clustering results of a second preset time period and a third preset time period of a regular commuting user provided according to an embodiment of the present application;

[0024] Figure 7is a schematic diagram of clustering results of field users provided according to an embodiment of the present application;

[0025] Figure 8 This is a schematic diagram of the time ratio of an off-site user provided according to an embodiment of the present application;

[0026] Fig. 9 It is a structural diagram of a user type identification device provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0027] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0028] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application 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 data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0029] In order to better understand the embodiments of the present application, the technical terms involved in the embodiments of the present application are explained as follows:

[0030] DPI: Deep Packet Inspection, an application layer traffic detection and control technology based on data packets, performs in-depth detection and analysis on different layers of data packets (such as IP address, application layer port, application layer protocol, payload content, etc.), thereby obtaining the application layer information of the entire data flow or data packet, and then performs statistical analysis and control on the traffic according to the system-defined policies.

[0031] At present, the user experience perception evaluation of mobile communication networks is changing from extensive unified evaluation to refined evaluation based on user behavior. Users with different behavioral characteristics have different network experience requirements. In the future, there will be more and more scenarios for targeted network optimization based on different user behavior characteristics.

[0032] The mobile communication network user experience perception evaluation in related technologies is mainly monitored and evaluated through unified network performance perception indicators, using the same set of evaluation criteria for all users, focusing only on the user's network characteristics and paying less attention to the user's resident behavior characteristics. It is difficult to identify the different behavior characteristics of users, making it difficult to solve complaints and demand issues from users with different behavior characteristics in a targeted manner, thus affecting the improvement of user perceived satisfaction.

[0033] In order to solve the above problems, relevant solutions are provided in the embodiments of the present application, which are described in detail below.

[0034] According to an embodiment of the present application, a method embodiment of a user type identification method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0035] The method embodiments provided in the embodiments of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Figure 1 FIG. 1 shows a hardware structure block diagram of a computer terminal (or mobile device) for implementing a user type identification method. Figure 1 As shown, the computer terminal 10 (or mobile device 10) may include one or more (102a, 102b, ..., 102n are used to illustrate) processors 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 104 for storing data, and a transmission device 106 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the BUS bus), a network interface, a power supply and / or a camera. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.

[0036] It should be noted that the one or more processors 102 and / or other data processing circuits described above may generally be referred to herein as "data processing circuits". The data processing circuits may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuit may be a single independent processing module, or may be incorporated in whole or in part into any of the other components in the computer terminal 10 (or mobile device). As described in the embodiments of the present application, the data processing circuit acts as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0037] The memory 104 can be used to store software programs and modules of application software, such as program instructions / data storage devices corresponding to the user type identification method in the embodiment of the present application. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, realizing the above-mentioned user type identification method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the computer terminal 10 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0038] The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the computer terminal 10. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0039] The display may be, for example, a touch screen liquid crystal display (LCD) that enables a user to interact with a user interface of the computer terminal 10 (or mobile device).

[0040] In the above operating environment, the present application embodiment provides a method for identifying user types, such as Figure 2 As shown, the method comprises the following steps:

[0041] Step S202, obtaining application flow data of the terminal device of the target object in a first preset time period;

[0042] In the technical solution provided in step S202, the application traffic data includes 4G_DPI_S1-MME data and 5G_DPI_N1N2 data. After obtaining the application traffic data, for 4G_DPI_S1-MME data, the process type procedure_type is filtered in the data as Attach, Service Request, TAU, Detach, and the corresponding procedure_type values ​​are 1, 2, 5, and 6. For 5G_DPI_N1N2 data, the process type procedure_type is filtered as Registration, De-registration, and Service Request, and the corresponding procedure_type values ​​in the data are 0, 1, and 2.

[0043] After that, the application traffic data needs to be preprocessed, including deleting null values, extracting recording time, connecting cell data, associating cell latitude and longitude coordinate data, etc.

[0044] In some embodiments of the present application, the application traffic data in the above-mentioned first preset time period may be 7 days of 4G_DPI_S1-MME sample data and 5G_DPI_N1N2 sample data, and the sample set data has complete time and geographical distribution.

[0045] Step S204, determining the resident location information and non-resident location information of the target object according to the location information corresponding to the application flow data;

[0046] In the technical solution provided in step S204, the step of determining the permanent location information and non-resident location information of the target object based on the location information corresponding to the application traffic data includes: sampling the application traffic data to obtain multiple sampling data points, and determining the location information of the sampling data points based on the location information corresponding to the application traffic data; clustering the multiple sampling data points based on the location information of each sampling data point to obtain multiple cluster centers, and determining the central location information of each cluster center, as well as the number of cluster centers, wherein each cluster center corresponds to a permanent area of ​​the target object, the number of cluster centers is the number of permanent areas, the central location information is the permanent area location information of the permanent areas, and the permanent location information includes the permanent area location information and the number of permanent areas; determining the proportion of discrete points, wherein the proportion of discrete points is the ratio of the number of data points that are not marked with corresponding cluster centers to the number of all data points after clustering, and the non-resident location information includes the proportion of discrete points.

[0047] Specifically, the Mean-shift clustering algorithm can be used for model training. The specific process includes the following steps:

[0048] The first step is data preprocessing: select the longitude and latitude of the sample data as input parameters and delete the null values ​​in the data set.

[0049] The second step is model initialization: kernel density estimation is used to initialize the seed position, and the initialization parameters are configured as bandwidth = 0.01, cluster_all = False.

[0050] The third step is model training and data fitting: obtain the number of cluster centers obtained by model fitting and the center positioning coordinates of each cluster center.

[0051] Step 4: Data calibration: adjust the categories that meet the following conditions to discrete categories, the conditions are: classification data volume / total data volume*100%<20%.

[0052] The fifth step is to count the sample discrete points: the proportion of sample discrete points discrete_points_per = sampling points of unmarked cluster centers / total sampling points.

[0053] After that, it can be determined that each cluster center is the resident area of ​​the target object, and the number of resident areas resident_area, the location of the cluster center as the resident area location center_coordinates, and the proportion of sample discrete points discrete_points_per are recorded.

[0054] Step S206, determining the communication behavior information of the target object according to the cell connection data in the application traffic data, wherein the communication behavior information includes the ratio of the total duration of the target mobility behavior of the target object in the first preset time period to the duration of the first preset time period, and the target mobility behavior includes the behavior of switching cells at a frequency greater than a preset frequency;

[0055] In the technical solution provided in step S206, the step of determining the communication behavior information of the target object according to the cell connection data in the application traffic data includes: dividing the first preset time period into a plurality of sub-time periods, wherein the duration of each sub-time period is equal; determining the number of cell connections in the cell connection data corresponding to each sub-time period, wherein, when the number of cell connections is greater than the preset number of cells, determining the communication behavior corresponding to the sub-time period as the target mobile behavior; determining the ratio between the number of sub-time periods corresponding to the target mobile behavior and the total number of all sub-time periods as the duration ratio;

[0056] Optionally, the above sub-time period can be set by the user, for example, one hour or half an hour.

[0057] In some embodiments of the present application, taking a sub-time period of one hour as an example, the number of connected cells in each hour, cell_connect_hour_num, can be counted. For each hour, the time period when cell_connect_hour_num>n0 is recorded as frequent mobility hour hour_mobility, otherwise it is recorded as fixed area hour hour_fixed. The frequent mobility hour is the sub-time period in which the corresponding communication behavior is the target mobility behavior.

[0058] Then, the total number of frequent mobility hours in the period, hour_mobility_sum and the total number of hours, hour_all, can be counted, and the proportion of frequent mobility hours, hour_mobility_per = hour_mobility_sum / hour_all, where the proportion of frequent mobility hours is the same as the duration proportion mentioned above.

[0059] Step S208, determining the user type of the target object according to the resident location information, the non-resident location information and the communication behavior information, wherein the user type is used to indicate an optimization method for allocating communication resources.

[0060] In the technical solution provided in step S208, the resident location information includes the number of resident areas of the target object, and the non-resident location information includes a first discrete ratio between the number of discrete sampling points obtained after clustering the sampling points of the application traffic data and the number of all sampling points; determining the user type based on the resident location information, the non-resident location information and the communication behavior information includes: determining a preset number set, wherein the preset number set includes a first preset number, a second preset number, a third preset number and a fourth preset number; determining a preset ratio set, wherein the preset ratio set includes a first preset ratio, a second preset ratio, a third preset ratio, a fourth preset ratio and a fifth preset ratio; determining the user type based on the number of resident areas, the first discrete ratio, the preset number set and the preset ratio set, or determining the user type based on the number of resident areas, the first discrete ratio, the duration ratio, the preset number set and the preset ratio set.

[0061] For ease of description, in the embodiment of the present application, the first preset number, the second preset number, the third preset number and the fourth preset number are set to n1, n2, n3 and n4 respectively, and the first preset ratio, the second preset ratio, the third preset ratio, the fourth preset ratio and the fifth preset ratio are set to p1, p2, p3, p4 and p5 respectively.

[0062] In some embodiments of the present application, n1, n2, n3 and n4 are all positive integers, and the default value is 1. The specific value can also be set by the user. The recommended value range of p1 is (5%, 25%), the recommended value range of p2 is (15%, 40%), the recommended value range of p3 is (5%, 25%), the recommended value range of p4 is (30%, 65%), and the recommended value range of p4 is (20%, 50%).

[0063] As an optional implementation, data of various types of users whose user types are known can be obtained in advance, and information such as the number of permanent areas, the first discrete ratio and the proportion of duration in the statistics can be counted. Then, based on the statistical results, specific values ​​of the preset numbers in the above-mentioned preset number set and the values ​​of the above-mentioned preset ratios can be set.

[0064] In some embodiments of the present application, user types may include fixed-area users, regular commuting users (also referred to as office workers), field users, and other users. The characteristic of fixed-area users is that users are in a fixed area for a long time, and the characteristic of regular commuting users is that users are in different fixed areas during the day and at night, and there is a certain distance between the two areas. The characteristic of field users is that users are in a fixed area and have frequent movement behaviors. Other users are all users who cannot be classified into the above three categories.

[0065] In some embodiments of the present application, the step of determining the user type based on the number of permanent areas, the first discrete ratio, the preset number set and the preset ratio set includes: when the number of permanent areas is the first preset number and the ratio is less than the first preset ratio, determining the user type as a fixed area user.

[0066] Specifically, when determining whether the user type of the target object is a fixed-area user, the number of resident areas resident_area and the proportion of sample discrete points discrete_points_per of the target area may be determined first, and whether the target object is a fixed-area user may be determined based on the following judgment conditions:

[0067] 1) Number of resident areas resident_area = n1.

[0068] 2) Discrete point ratio discrete_points_per <p1。

[0069] As an optional implementation, take the sample data source as an example: the elderly at home, whose activities during the period are mainly at home and a small amount of short-distance outings, are fixed-area user types. Assuming that the sample data volume is 1446, the results obtained after clustering the sample data are as follows: Figure 3As shown, the number of resident areas of sample data resident_area = 1, and the proportion of discrete points discrete_points_per = 2.5%. Figure 3 The yellow labels are clustered points, accounting for 97.5% of the total number, and the purple labels are discrete points, accounting for 2.5% of the total number. The cluster center coordinates are [116.093982, 24.30122442]. The value of n1 in the above judgment criteria can be 1, and the value of p1 can be 10%.

[0070] In some embodiments of the present application, the step of determining the user type based on the number of permanent areas, the first discrete ratio, the preset number set and the preset ratio set includes: determining the second preset time period and the third preset time period in the first preset time period, and determining the second permanent area information and the second discrete ratio corresponding to the second preset time period, and the third permanent area information and the third discrete ratio corresponding to the third preset time period, wherein the second permanent area information includes the first permanent area position and the first permanent area number corresponding to the second preset time period, and the third permanent area information includes the second permanent area position and the second permanent area number corresponding to the third preset time period; when the number of first permanent areas is the second preset number, the second discrete ratio is less than the second preset ratio, the number of second permanent areas is the third preset number, the third discrete ratio is less than the third preset ratio, and the distance between the first permanent area position and the second permanent area position is greater than the preset distance, the user type is determined to be a regular commuting user, wherein the second preset number and the third preset number are both 1.

[0071] Specifically, the second preset time period is a time period corresponding to daytime, which may be 07:00-19:00. The third preset time period is a time period corresponding to nighttime, which may be 00:00-07:00 and 19:00-00:00.

[0072] When determining whether the user type is a regular commuter, you can obtain daytime data and nighttime data separately to obtain the number of permanent areas, permanent area locations, and sample discrete point ratios discrete_points_per for the user during the day and at night. Then make a judgment based on the following criteria:

[0073] 1) Number of resident areas during the day resident_area_daytime = n2, daytime discrete points ratio daytime_discrete_points_per <p2。

[0074] 2) Number of resident areas at night resident_area_night = n3, proportion of discrete points at night night_discrete_points_per <p3。

[0075] 3) The distance between the daytime and nighttime resident areas is resident_areas_distance>d meters.

[0076] In some embodiments of the present application, the sample data source is taken as an example of an operator data analyst, whose activities during the period are mainly going to work in the company during the day, staying at home at night, and commuting between two points. They are office workers (regular commuting users). Assume that the number of samples is 1613, and the sample data is divided into two parts: daytime data and nighttime data according to the following time periods:

[0077] 1) Daytime data: 07:00–19:00.

[0078] 2) Nighttime data: 00:00–07:00 and 19:00–00:00.

[0079] Then, the Mean-shift clustering algorithm was used to train the model for the two parts of data, and the clustering results were as follows: Figure 4 and Figure 5 As shown. Figure 4 is the clustering result of daytime data, Figure 5 This is the clustering result of night data. Figure 4 The yellow labels are clustered points, accounting for 90% of the total number. The purple labels are discrete points, accounting for 10% of the total number. The number of cluster centers is 1, and the cluster center labels are [113.2897845, 23.12700365]. Figure 5 The yellow labels are clustered points, accounting for 99% of the total number. The purple labels are discrete points, accounting for 1% of the total number. The number of cluster centers is 1, and the cluster center labels are [113.33084, 23.16692].

[0080] right Figure 4 and Figure 5 The sample data obtained by analysis is: the number of resident areas during the day is resident_area_daytime = 1, and the proportion of discrete points during the day is daytime_discrete_points_per = 10%. The number of resident areas at night is resident_area_night = 1, and the proportion of discrete points at night is night_discrete_points_per = 1%.

[0081] As an optional implementation, Figure 6 As shown, it can be Figure 4 and Figure 5The clustering result shown is displayed in a coordinate system, so that the distance between the resident areas during the day and night is obtained as resident_areas_distance = 6100 meters. In the above judgment criteria, n2 and n3 can both be equal to 1, p2 can be equal to 30%, p3 can be equal to 10%, and d can be 2000 meters.

[0082] As an optional implementation, the step of determining the user type based on the number of permanent areas, the first discrete ratio, the duration ratio, a preset number set and a preset ratio set includes: when the number of permanent areas is a fourth preset number, the ratio is greater than the fourth preset ratio, and the duration ratio is greater than the fifth preset ratio, determining the user type as a field user.

[0083] When determining whether the user type is an out-of-town user, you can first obtain the number of permanent areas of the target object, the proportion of sample discrete points, and the proportion of frequent mobility hours hour_mobility_per. Then make a judgment based on the following judgment conditions:

[0084] 1) Number of resident areas: resident_area = n4.

[0085] 2) Discrete point proportion discrete_points_per>p4.

[0086] 3) The proportion of frequent mobility hours: hour_mobility_per>p5.

[0087] In some embodiments of the present application, the sample data source is a freight driver. For example, the driver's activities during the period are mainly driving outdoors during the day and resting in a fixed area at night. He is an out-of-town user type. Assuming that the sample data volume is 10434, the clustering results obtained after clustering the sample data are as follows: Figure 7 As shown. Figure 7 As can be seen, the yellow label is the clustering mark point, accounting for 24% of the total number. The purple label is the discrete point, accounting for 76% of the total number. The number of cluster centers is 1, and the cluster center coordinates are [116.09420238, 24.30138705]. In addition, according to the number of cells connected per hour in the sample data, cell_connect_hour_count, for each hour, the time period when cell_connect_hour_count> the preset number of times (for example, 10 times) is recorded as frequent mobility hours hour_mobility, then Figure 8 As shown, the frequent mobility hour ratio of the sample is hour_mobility_per=42%.

[0088] In the above judgment conditions, n4 may be equal to 1, p4 may be equal to 50%, and p5 may be equal to 30%.

[0089] The method adopts the method of obtaining application traffic data of a terminal device of a target object in a first preset time period; determining the resident location information and non-resident location information of the target object based on the location information corresponding to the application traffic data; determining the communication behavior information of the target object based on the cell connection data in the application traffic data, wherein the communication behavior information includes the ratio of the total duration of the target mobile behavior of the target object in the first preset time period to the duration in the first preset time period, and the target mobile behavior includes the behavior of switching cells with a frequency greater than a preset frequency; determining the user type of the target object based on the resident location information, the non-resident location information and the communication behavior information, wherein the user type is used to indicate the method of optimizing the allocation of communication resources. By determining the resident location information, the non-resident location information and the communication behavior information of the target object based on the application traffic data, and then determining the user type of the target object, the purpose of accurately determining the user type is achieved, thereby realizing the technical effect of determining the actual demand information of the target object based on the user type, thereby solving the technical problem that the communication service provided by the operator does not meet the actual needs of the user due to the inability to determine the user type in the related technology.

[0090] Compared with the mobile communication network user experience perception evaluation method in the related art, the user type identification method provided in the embodiment of the present application provides a solution for identifying different behavioral characteristics of users, and improves the ability of refined mobile network user perception evaluation based on user behavior. In addition, combined with the DPI data of the new generation of mobile communications, a method for identifying the resident area of ​​mobile network users and a method for identifying the mobility behavior of mobile network users are proposed for the first time. Based on the multi-dimensional network usage data of users, the correlation conversion between user network data and user behavior characteristics is realized, and a modeling evaluation of user resident behavior characteristics is constructed, which improves the accuracy and reliability of user behavior identification.

[0091] Moreover, compared with the user type identification method provided in the embodiment of the present application and the related technology in which user perception evaluation can only be carried out through extensive unified evaluation, the method increases the analytical means for mobile network optimization staff to carry out user perception repair, thereby improving work efficiency.

[0092] The present application embodiment provides a user type identification device, Fig. 9 is a schematic diagram of the structure of the device. Fig. 9It can be seen that the device includes: a first processing module 90, which is used to obtain the application traffic data of the terminal device of the target object in the first preset time period; a second processing module 92, which is used to determine the permanent location information and non-resident location information of the target object based on the location information corresponding to the application traffic data; a third processing module 94, which is used to determine the communication behavior information of the target object based on the cell connection data in the application traffic data, wherein the communication behavior information includes the total duration corresponding to the target mobile behavior of the target object in the first preset time period, and the proportion of the duration in the first preset time period, and the target mobile behavior includes the behavior of switching cells with a frequency greater than a preset frequency; a fourth processing module 96, which is used to determine the user type of the target object based on the permanent location information, the non-resident location information and the communication behavior information, wherein the user type is used to indicate the optimization method for allocating communication resources.

[0093] In some embodiments of the present application, the second processing module 92 determines the permanent location information and non-resident location information of the target object based on the location information corresponding to the application traffic data, including the following steps: sampling the application traffic data to obtain multiple sampling data points, and determining the location information of the sampling data points based on the location information corresponding to the application traffic data; clustering the multiple sampling data points based on the location information of each sampling data point to obtain multiple cluster centers, and determining the center location information of each cluster center, as well as the number of cluster centers, wherein each cluster center corresponds to a permanent area of ​​the target object, the number of cluster centers is the number of permanent areas, the center location information is the permanent area location information of the permanent areas, and the permanent location information includes the permanent area location information and the number of permanent areas; determining the proportion of discrete points, wherein the proportion of discrete points is the ratio of the number of data points that are not marked with corresponding cluster centers to the number of all data points after clustering, and the non-resident location information includes the proportion of discrete points.

[0094] In some embodiments of the present application, the step in which the third processing module 94 determines the communication behavior information of the target object based on the cell connection data in the application traffic data includes: dividing the first preset time period into multiple sub-time periods, wherein the duration of each sub-time period is equal; determining the number of cell connections in the cell connection data corresponding to each sub-time period, wherein when the number of cell connections is greater than the preset number of cells, determining the communication behavior corresponding to the sub-time period as the target mobile behavior; determining the ratio between the number of sub-time periods in which the corresponding communication behavior is the target mobile behavior and the total number of all sub-time periods is the duration ratio.

[0095] In some embodiments of the present application, the resident location information includes the number of resident areas of the target object, and the non-resident location information includes a first discrete ratio between the number of discrete sampling points obtained after clustering the sampling points of the application traffic data and the number of all sampling points; the step of the fourth processing module 96 determining the user type based on the resident location information, the non-resident location information and the communication behavior information includes: determining a preset number set, wherein the preset number set includes a first preset number, a second preset number, a third preset number and a fourth preset number; determining a preset ratio set, wherein the preset ratio set includes a first preset ratio, a second preset ratio, a third preset ratio, a fourth preset ratio and a fifth preset ratio; determining the user type based on the number of resident areas, the first discrete ratio, the preset number set and the preset ratio set, or determining the user type based on the number of resident areas, the first discrete ratio, the duration ratio, the preset number set and the preset ratio set.

[0096] In some embodiments of the present application, the step in which the fourth processing module 96 determines the user type based on the number of permanent areas, the first discrete ratio, the preset number set and the preset ratio set includes: when the number of permanent areas is the first preset number and the ratio is less than the first preset ratio, determining that the user type is a fixed area user.

[0097] In some embodiments of the present application, the step of the fourth processing module 96 determining the user type based on the number of permanent areas, the first discrete ratio, the preset number set and the preset ratio set includes: determining the second preset time period and the third preset time period in the first preset time period, and determining the second permanent area information and the second discrete ratio corresponding to the second preset time period, and the third permanent area information and the third discrete ratio corresponding to the third preset time period, wherein the second permanent area information includes the first permanent area position and the first permanent area number corresponding to the second preset time period, and the third permanent area information includes the second permanent area position and the second permanent area number corresponding to the third preset time period; when the number of first permanent areas is the second preset number, the second discrete ratio is less than the second preset ratio, the number of second permanent areas is the third preset number, the third discrete ratio is less than the third preset ratio, and the distance between the first permanent area position and the second permanent area position is greater than the preset distance, determining that the user type is a regular commuting user, wherein the second preset number and the third preset number are both 1.

[0098] In some embodiments of the present application, the fourth processing module 96 determines the user type based on the number of permanent areas, the first discrete ratio, the duration ratio, a preset number set and a preset ratio set, including: when the number of permanent areas is a fourth preset number, the ratio is greater than the fourth preset ratio, and the duration ratio is greater than the fifth preset ratio, the user type is determined to be a field user, wherein the fourth preset ratio is greater than the third preset ratio.

[0099] It should be noted that the various modules in the above-mentioned user type identification device can be program modules (for example, a set of program instructions that implement a certain specific function) or hardware modules. For the latter, it can be expressed in the following forms, but is not limited to this: the expression form of each of the above-mentioned modules is a processor, or the functions of each of the above-mentioned modules are implemented by a processor.

[0100] According to an embodiment of the present application, a non-volatile storage medium is also provided, in which a program is stored, wherein when the program is running, the device where the non-volatile storage medium is located is controlled to execute the following user type identification method: obtain application traffic data of the terminal device of the target object in a first preset time period; determine the permanent location information and non-resident location information of the target object based on the location information corresponding to the application traffic data; determine the communication behavior information of the target object based on the cell connection data in the application traffic data, wherein the communication behavior information includes the total duration of the target mobile behavior of the target object in the first preset time period and the proportion of the duration in the first preset time period, and the target mobile behavior includes the behavior of switching cells with a frequency greater than a preset frequency; determine the user type of the target object based on the permanent location information, the non-resident location information and the communication behavior information, wherein the user type is used to indicate the optimization method for allocating communication resources.

[0101] According to an embodiment of the present application, an electronic device is also provided, including a memory and a processor, the processor being used to run a program stored in the memory, wherein the following user type identification method is executed when the program is running: obtaining application traffic data of a terminal device of a target object in a first preset time period; determining the permanent location information and non-resident location information of the target object based on the location information corresponding to the application traffic data; determining the communication behavior information of the target object based on the cell connection data in the application traffic data, wherein the communication behavior information includes the total duration of the target mobile behavior of the target object in the first preset time period and the proportion of the duration in the first preset time period, and the target mobile behavior includes the behavior of switching cells with a frequency greater than a preset frequency; determining the user type of the target object based on the permanent location information, the non-resident location information and the communication behavior information, wherein the user type is used to indicate the optimization method for allocating communication resources.

[0102] According to an embodiment of the present application, a computer program product is also provided, including a computer program, which implements the following user type identification method when executed by a processor: obtaining application traffic data of a terminal device of a target object in a first preset time period; determining the permanent location information and non-resident location information of the target object based on the location information corresponding to the application traffic data; determining the communication behavior information of the target object based on the cell connection data in the application traffic data, wherein the communication behavior information includes the total duration of the target mobile behavior of the target object in the first preset time period, and the proportion of the duration in the first preset time period, and the target mobile behavior includes the behavior of switching cells at a frequency greater than a preset frequency; determining the user type of the target object based on the permanent location information, the non-resident location information and the communication behavior information, wherein the user type is used to indicate the optimization method for allocating communication resources.

[0103] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0104] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0105] 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 units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0106] In addition, each functional unit in each embodiment of the present application 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. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0107] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the relevant technology or all or part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes 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 method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, RandomAccess Memory), mobile hard disk, disk or optical disk, etc. Various media that can store program codes.

[0108] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for identifying user type, characterized in that: include: Acquire application flow data of a terminal device of a target object in a first preset time period; Determine the resident location information and the non-resident location information of the target object according to the location information corresponding to the application flow data; Determine the communication behavior information of the target object according to the cell connection data in the application traffic data, wherein the communication behavior information includes the total duration of the target mobility behavior of the target object in the first preset time period as a percentage of the duration in the first preset time period, and the target mobility behavior includes a behavior of switching cells at a frequency greater than a preset frequency; The user type of the target object is determined according to the permanent location information, the non-resident location information and the communication behavior information, wherein the user type is used to indicate an optimization method for allocating communication resources.

2. The user type identification method according to claim 1, characterized in that: The resident location information includes the number of resident areas of the target object, and the non-resident location information includes a first discrete ratio between the number of discrete sampling points obtained after clustering the sampling points of the application traffic data and the number of all sampling points; Determining the user type according to the resident location information, the non-resident location information, and the communication behavior information includes: Determine a preset quantity set, wherein the preset quantity set includes a first preset quantity, a second preset quantity, a third preset quantity and a fourth preset quantity; Determine a preset ratio set, wherein the preset ratio set includes a first preset ratio, a second preset ratio, a third preset ratio, a fourth preset ratio and a fifth preset ratio; The user type is determined based on the number of permanent areas, the first discrete ratio, the preset number set and the preset ratio set, or the user type is determined based on the number of permanent areas, the first discrete ratio, the duration ratio, the preset number set and the preset ratio set.

3. The user type identification method according to claim 2, characterized in that: Determining the user type according to the number of permanent areas, the first discrete ratio, the preset number set, and the preset ratio set includes: When the number of permanent areas is the first preset number and the first discrete ratio is smaller than the first preset ratio, it is determined that the user type is a fixed-area user.

4. The user type identification method according to claim 2, characterized in that: Determining the user type according to the number of permanent areas, the first discrete ratio, the preset number set, and the preset ratio set includes: Determine a second preset time period and a third preset time period in the first preset time period, and determine second permanent area information and a second discrete ratio corresponding to the second preset time period, and third permanent area information and a third discrete ratio corresponding to the third preset time period, wherein the second permanent area information includes a first permanent area position and a first permanent area quantity corresponding to the second preset time period, and the third permanent area information includes a second permanent area position and a second permanent area quantity corresponding to the third preset time period; When the first permanent area number is the second preset number, the second discrete ratio is less than the second preset ratio, the second permanent area number is the third preset number, the third discrete ratio is less than the third preset ratio, and the distance between the first permanent area location and the second permanent area location is greater than the preset distance, the user type is determined to be a regular commuting user, wherein the second preset number and the third preset number are both 1.

5. The user type identification method according to claim 2, characterized in that: Determining the user type according to the number of resident areas, the first discrete ratio, the duration ratio, the preset number set, and the preset ratio set includes: When the number of resident areas is a fourth preset number, the first discrete ratio is greater than the fourth preset ratio, and the duration ratio is greater than the fifth preset ratio, it is determined that the user type is an off-site user.

6. The user type identification method according to claim 1, characterized in that: Determining the resident location information and the non-resident location information of the target object according to the location information corresponding to the application flow data includes: Sampling the application traffic data to obtain a plurality of sampling data points, and determining location information of the sampling data points according to location information corresponding to the application traffic data; According to the position information of each of the sampling data points, the plurality of sampling data points are clustered to obtain a plurality of cluster centers, and the central position information of each of the cluster centers and the number of the cluster centers are determined, wherein each of the cluster centers corresponds to a permanent area of ​​the target object, the number of the cluster centers is the number of the permanent areas, the central position information is the permanent area position information of the permanent areas, and the permanent position information includes the permanent area position information and the number of the permanent areas; Determine the proportion of discrete points, wherein the proportion of discrete points is the ratio between the number of data points without marking the corresponding cluster center and the number of all data points in the clustered data points, and the non-resident position information includes the proportion of discrete points.

7. The user type identification method according to claim 1, characterized in that: Determining the communication behavior information of the target object according to the cell connection data in the application traffic data includes: Dividing the first preset time period into a plurality of sub-time periods, wherein each of the sub-time periods is of equal length; Determine the number of cell connections in the cell connection data corresponding to each of the sub-time periods, wherein, when the number of cell connections is greater than a preset number of cells, determine that the communication behavior corresponding to the sub-time period is the target mobility behavior; Determine that the ratio between the number of the sub-time periods in which the corresponding communication behavior is the target movement behavior and the total number of all the sub-time periods is the duration ratio.

8. A user type identification device, characterized in that: include: A first processing module, used to obtain application flow data of a terminal device of a target object in a first preset time period; A second processing module, used to determine the resident location information and non-resident location information of the target object according to the location information corresponding to the application flow data; A third processing module is used to determine the communication behavior information of the target object according to the cell connection data in the application traffic data, wherein the communication behavior information includes the ratio of the total duration corresponding to the target mobility behavior of the target object in the first preset time period to the duration in the first preset time period, and the target mobility behavior includes the behavior of switching cells with a frequency greater than a preset frequency; The fourth processing module is used to determine the user type of the target object according to the permanent location information, the non-resident location information and the communication behavior information, wherein the user type is used to indicate an optimization method for allocating communication resources.

9. A non-volatile storage medium, characterized in that: The non-volatile storage medium stores a program, wherein when the program is executed, the device where the non-volatile storage medium is located is controlled to execute the user type identification method according to any one of claims 1 to 7.

10. An electronic device, characterized in that: include: A memory and a processor, wherein the processor is used to run a program stored in the memory, wherein the program executes the user type identification method according to any one of claims 1 to 7 when running.

11. A computer program product, characterized in that The invention comprises a computer program, which implements the user type identification method according to any one of claims 1 to 7 when being executed by a processor.

Images