User profiling method, device, equipment and storage medium

Abstract

The present application proposes a user profiling method, apparatus, device and storage medium, wherein the method comprises: merging the network access feature data of the same user according to the correlation between the device feature data and the network access feature data in the user behavior data set to obtain the user network access feature data; and performing user profiling according to the user network access feature data. The technical solution of the embodiment of the present application realizes the merging of the network access feature data of the same user through the correlation between the device feature data and the network access feature data in the user behavior data set, broadens the dimension and quantity of the user network behavior data, and enhances the accuracy of the user behavior profiling.

Description

Technical Field

[0001] The present application relates to the field of computer application technology, and in particular to a user profiling method, apparatus, device and storage medium. Background Art

[0002] User portrait, in simple terms, is to abstract a labeled user model based on information such as user social attributes, living habits and consumption behavior, and to label user information.

[0003] The existing user network access behavior includes user game preferences, sports preferences, reading preferences, video viewing preferences, consumption preferences and other behavioral information as well as some website account information. Figure 1 In the traditional user portrait method, telecom operators build corresponding user portraits by analyzing user network access behavior, broadband accounts and mobile phone numbers. However, the traditional user portrait model construction method can only portray users who use a single network access device. When users use multiple network devices to access the network, traditional technologies often cannot portray real and effective user portraits. Summary of the invention

[0004] The present application provides a user profiling method, apparatus, device and storage medium.

[0005] The present invention provides a user profiling method, which includes:

[0006] According to the correlation between the device feature data and the network access feature data of the user behavior data set, the network access feature data of the same user is merged to obtain the user network access feature data; and the user profile is performed based on the user network access feature data.

[0007] The present application provides a user portrait device, which includes:

[0008] The data processing module is used to merge the network access feature data of the same user according to the correlation between the device feature data and the network access feature data of the user behavior data set to obtain the user network access feature data; the user portrait module is used to create a user portrait based on the user network access feature data.

[0009] The present application provides a device, which includes:

[0010] One or more processors; a memory for storing one or more programs, when the one or more programs are executed by the one or more processors, the one or more processors implement the user profiling method as described in any of the embodiments of the present application.

[0011] An embodiment of the present application provides a storage medium, wherein the storage medium stores a computer program, and when the computer program is executed by a processor, any one of the methods in the embodiments of the present application is implemented.

[0012] The technical solution of the embodiment of the present application determines the correlation between the device feature data and the network access feature data in the user behavior data set, merges the network access feature data of the same user according to the correlation, obtains the user's network access feature data, and profiles the user based on the user's network access feature data, thereby realizing the merging of the network access feature data of multiple network devices of the user, broadening the dimension of the network access feature, and enhancing the accuracy of the user portrait.

[0013] With regard to the above embodiments and other aspects of the present application and their implementation, further description is provided in the accompanying drawings, detailed description and claims. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 An example diagram of a user portrait method in the prior art;

[0015] Figure 2 This is an example diagram of the user portrait method of an embodiment of the present application;

[0016] Figure 3 A flowchart of the steps of the user profiling method according to an embodiment of the present application;

[0017] Figure 4 A flowchart of the steps of the user profiling method according to an embodiment of the present application;

[0018] Figure 5 A schematic diagram of the structure of an association relationship analysis diagram of an embodiment of the present application;

[0019] Figure 6 A schematic diagram of the structure of a user portrait device according to an embodiment of the present application;

[0020] Figure 7 A schematic diagram of a device structure of an embodiment of the present application. DETAILED DESCRIPTION

[0021] In order to make the purpose, technical solution and advantages of the present application more clear, the embodiments of the present application will be described in detail below with reference to the accompanying drawings. It should be noted that the embodiments and features in the embodiments of the present application can be combined with each other arbitrarily without conflict.

[0022] Figure 2 This is an example diagram of the user portrait method of the embodiment of the present application, see Figure 2Currently, most users use multiple network terminals to access the network. Due to the inconsistent identification numbers of various network devices, when generating user behavior data sets, the network access feature data of different network devices are used as network access feature data sets of different users. However, for different network devices of the same user, there is a certain connection between the feature data of the network device and the network access feature data. The device feature data of different network devices corresponding to the same network access feature can be considered to belong to the same user. The network access feature data belonging to the same user can be merged according to the association between the device feature data and the network access feature data. The user portrait can be portrayed through the merged network access feature data to improve the accuracy of the portrait.

[0023] Figure 3 Flow chart of the steps of the user profiling method of the embodiment of the present application; the embodiment of the present application can be applied to the case of user network access behavior profiling using multiple network devices. The method can be executed by a user profiling device, which can be implemented in hardware and / or software. Figure 3 , the method of the embodiment of the present application includes:

[0024] Step 101: Based on the association between device feature data and network access feature data in a user behavior data set, the network access feature data of the same user is merged to obtain user network access feature data.

[0025] Among them, the user behavior data set can be a collection of behavior data generated when a user uses a network device to access the network. The user behavior data set may include user device feature data and network access feature data. The user behavior data set may be collected and organized by a network operator. The device feature data and network access feature data in the user behavior data set may be stored one-to-one. The device feature data may be identification data of a network device that identifies a user to access the network. The network access feature data may be data used by a user to access the network. It can be understood that the network access feature data may include multiple feature data, including user mobile phone numbers, software accounts, mobile phone numbers, and authentication information, etc. The network access feature data may correspond to the behavior data of the device feature data, that is, the behavior data generated by a network device accessing the network is used as the network access feature data of the network device. The user network access feature data may be the data obtained by merging the network access feature data belonging to the same user, and different user network access feature data may correspond to different users.

[0026] Specifically, the association relationship may be a correspondence between device characteristic data and network access characteristic data, and may be jointly identified by the identification number of the device characteristic data and the identification number of the network access characteristic data. For example, the identification number of the device characteristic data may be represented as a, and the network access characteristic data may be represented as b. If there is an association relationship between a and b, the association relationship may be represented as a-b. The existence of an association relationship between the device characteristic data and the network access characteristic data may be that the network access characteristic data is generated in a network device corresponding to the device characteristic data. If the network access characteristic data corresponding to two device characteristic data have the same characteristic data, the network access characteristic data corresponding to the two device characteristic data may be merged as user network access characteristic data of the same user. For example, device characteristic data A has associated network access characteristic data a1, a2 and a3, device characteristic data B has associated network access characteristic data b1, a2, a3, and device characteristic data C has associated network access characteristic data c1, c2 and b1. Since A and B have the same network characteristic data a2 and a3, and B and C have the same network characteristic data b1, it can be determined that A, B and C are device characteristic data of different network devices of the same user, and a1, a2, a3, b1, c1 and c2 can be regarded as user network access characteristic data of the same user.

[0027] Step 102: Create a user profile based on the user network access feature data.

[0028] Specifically, a user profile can be created based on the user's network access feature data, feature extraction can be performed on the user's network access feature data to obtain behavioral feature data, the user can be tagged based on the behavioral feature data, and a tag set formed by various tags can be used as a user profile.

[0029] Exemplarily, the user network access feature data can be expressed in the form of a matrix as follows:

[0030]

[0031] Among them, the user network of each row in the matrix represents the user network access feature data of the same user. The matrix can include different user network access feature data of multiple users. The matrix can be used to simultaneously perform user portraits on multiple users. Different data labels can be corresponding to different user network access feature data. URL_1 can correspond to label a, and url_2 can correspond to label b. The feature label set of each user can be obtained as the corresponding user portrait.

[0032] The technical solution of the embodiment of the present application combines the network access feature data belonging to the same user into user network access feature data through the association relationship between the device feature data of the user behavior data set and the network access feature data, and creates a user profile based on the user network access feature data, thereby realizing the merging of access feature data in the case of multiple network devices of the user, expanding the user's data types, and improving the accuracy of the user's network access profile.

[0033] Figure 4 This is a flowchart of the steps of the user profiling method of the embodiment of the present application. The user profiling method provided by the embodiment of the present application represents the association between device feature data and network access feature data through an analysis diagram, which is convenient for merging the network access feature data of the same user. Figure 4 , the method of the embodiment of the present application specifically includes:

[0034] Step 201: extract the network device identification in the user behavior data set as the device feature data, and at least one of the mobile phone serial number, software account, mobile phone number and network access address as the network access feature data through the portrait data matrix.

[0035] In an embodiment of the present application, a portrait data matrix can be used to extract a matrix of data from a user behavior data set, and the acquired data can be temporarily stored. Each row element in the portrait data matrix can be the behavior data of a user in the user behavior data set, and can include a network device identifier, a mobile phone serial number, a software account, a mobile phone number, and a network access address, etc. The user behavior data set can be stored in the form of fields as elements of the portrait data matrix, wherein the network device identifier used to distinguish the network device can be used as device feature data, and data such as a mobile phone serial number, a software account, a mobile phone number, and a network access address can be used as network access feature data. It can be understood that the types of network access feature data corresponding to different network devices may be different. The network access feature data corresponding to one network device may include data of types such as a mobile phone serial number, a software account, and a network access address, and the network access feature data corresponding to another network device may include data of types such as a mobile phone serial number, a software account, a mobile phone number, and a network access address. Exemplarily, the portrait data matrix can be expressed in the form of the following formula:

[0036]

[0037] Among them, AP_MAC1 can represent the network device identification, IMEI_1 can represent the mobile phone serial number, email_1 can represent the software account, mobile_num1 can represent the mobile phone number, and url_1 can represent the network access address. In order to reduce the amount of data processing, the device feature data and network access feature data in the portrait data matrix can be represented in the form of a unique identification number. AP_MAC1 and url_1 can be specific unique identification numbers instead of specific data content.

[0038] Step 202: Remove the repeated device characteristic data and the network access characteristic data in the behavior characteristic data set.

[0039] In an embodiment of the present application, the user behavior data set may come from multiple operators, and there may be duplicate data in the user behavior data set. The device feature data and network access feature data may be deduplicated in the portrait data matrix.

[0040] Step 203: Use each device feature data and each network access feature data in the user behavior data set as a vertex of the association relationship analysis diagram, and draw a connection line between the device feature data and the network access feature data belonging to a single user behavior data to identify the association relationship between the device feature data and the network access feature data.

[0041] Specifically, the correlation analysis diagram may be an analysis diagram for analyzing the correlation between each device feature data and the network access feature data. Figure 5 This is a schematic diagram of the structure of the correlation analysis diagram of the embodiment of the present application, see Figure 5 In the association relationship analysis diagram, the device feature data 21 and the network access feature data 22 can be represented as vertices. When the device feature data 21 and the network access feature data 22 belong to a single user behavior data, for example, the device feature data 21 and the network access feature data 22 have the same primary key or identification number in the user behavior data set, the device feature data 21 and the network access feature data 22 can be connected using a line 23, and the line 23 can be used as the association relationship between the device feature data and the network access feature data.

[0042] Step 204: determine a maximal connected subgraph according to each association relationship, and determine each association relationship belonging to the same maximal connected subgraph as a relationship to be connected.

[0043] The maximal connected subgraph may be a maximal connected subgraph composed of device feature data and network access feature data. Any device feature data and network access feature data may be associated with each other through a line that identifies the association relationship. Figure 5, AP_MAC1 and AP_MAC2 can be associated through a line, which can indicate that AP_MAC1 and AP_MAC2 belong to the same maximal connected subgraph; the relationship to be connected can be a relationship belonging to the same maximal connected subgraph.

[0044] Specifically, a maximal connected subgraph connected based on each association relationship can be obtained based on the association relationship analysis graph. It can be understood that the association relationship analysis graph may include one or more maximal connected subgraphs, and there may be no connecting lines identifying the association relationships between the maximal connected subgraphs. After obtaining the maximal connected subgraphs, for each maximal connected subgraph, the association relationships belonging to the same maximal connected subgraph can be determined as relationships to be connected. The relationships to be connected may include one or more association relationships. It can be understood that the association relationships belonging to the same relationship to be connected can correspond to the same user.

[0045] In one implementation, determining a maximal connected subgraph according to each association relationship includes:

[0046] The lines in the association relationship analysis graph that are in a connected state are obtained; and a connected subgraph composed of the connected lines is used as a maximal connected subgraph of the association relationship corresponding to the lines.

[0047] In an embodiment of the present application, the association relationship analysis graph can be analyzed, and an image composed of all connected lines can be used as a connected subgraph. In the association relationship analysis graph, there can be multiple connected subgraphs, and there may be no lines between the connected subgraphs. The obtained connected subgraphs can be used as the maximal connected subgraphs of the association relationship corresponding to the lines.

[0048] Step 205: merge the network characteristic access data corresponding to each of the to-be-connected relationships as network access characteristic data of the same user to obtain user network access characteristic data.

[0049] The relationship to be connected may be an association relationship belonging to the same user, and each network access feature data corresponding to the association relationship in the relationship to be connected may belong to the same user.

[0050] Specifically, according to each association relationship in the to-be-connected relationship, the network access feature data corresponding to each association relationship can be obtained, the network access feature data can be merged, and the merged network access feature data can be used as the user network access feature data. Exemplarily, the user network access feature data and device feature data belonging to the same user in the portrait data matrix can be stored in the same row of the portrait data matrix. For example, the portrait data matrix storing the user network access feature data can be expressed as the following formula:

[0051]

[0052] Step 206: extracting the behavior characteristics of the network access characteristic data.

[0053] Specifically, the behavioral characteristics may be characteristics of a user's access to the network, which may include frequently browsed network addresses, frequently used accounts, and login times, etc. The behavioral characteristic data may be obtained by sorting and extracting network access characteristic data. For example, the network address with the most visits in the network access characteristic data may be extracted as the behavioral characteristic data.

[0054] Step 207: searching for a behavior tag in a preset behavior tag set according to the behavior feature.

[0055] The preset behavior tag set may be a tag set that stores preset settings for user portraits, and the behavior tags in the preset behavior tag set may be stored in association with corresponding behavior features.

[0056] Specifically, the corresponding behavior tags can be searched in a pre-stored preset behavior tag set based on the extracted behavior features, the found behavior tags can be used to create user profiles for users, the behavior features can correspond to each user, and the behavior tags found based on the behavior features can correspond to the behavior tags of each user.

[0057] Step 208: Use the tag set consisting of the behavior tags as the user profile of the corresponding user.

[0058] In an embodiment of the present application, the behavior tags corresponding to each user may be sorted, and the behavior tags may form a behavior tag set, and the obtained behavior tag set may be used as a user profile of the corresponding user.

[0059] The technical solution of the embodiment of the present application obtains the network device identification as the device feature data through the portrait data matrix, takes the mobile phone serial number, software account, mobile phone number and network address as the network access feature data, deduplicates the obtained device feature data and network access feature data, builds an association relationship analysis graph according to the device feature data, network access feature data and the association relationship between the device feature data and the network access feature data, determines a maximal connected subgraph based on each association relationship, takes the association relationship belonging to the same maximal connected subgraph as the relationship to be connected, merges the corresponding network feature access data as the network access feature data of the same user according to the relationship to be connected, obtains the user's network access feature data, extracts the behavior feature data of each user's network access feature data, determines the behavior tag set as the user portrait according to each behavior feature data, realizes the access feature data merging in the case of multiple network devices of the user, expands the user's data types, and improves the accuracy of the user's network access portrait.

[0060] Figure 6 This is a schematic diagram of the structure of the user portrait device in the embodiment of the present application, see Figure 6 The device shown in the figure can execute the user portrait method provided by any embodiment of the present application, and has the corresponding functional modules and beneficial effects of the execution method. The device can be implemented by software and / or hardware, specifically including: a data processing module 301 and a user portrait module 302.

[0061] The data processing module 301 is used to merge the network access characteristic data of the same user according to the association relationship between the device characteristic data and the network access characteristic data of the user behavior data set to obtain the user network access characteristic data.

[0062] The user portrait module 302 is used to create a user portrait based on the user network access feature data.

[0063] The technical solution of the embodiment of the present application obtains the correlation between the device feature data and the network access feature data of the user behavior data set through the data processing module, merges the network access feature data belonging to the same user into the user network access feature data, and the user portrait module performs user portrait based on the user network access feature data, thereby realizing the merging of access feature data in the case of multiple network devices of the user, expanding the user's data types, and improving the accuracy of the user's network access portrait.

[0064] In one embodiment, the user profiling device of the embodiment of the present application also includes: a data extraction module, which is used to extract the network device identification in the user behavior data set as the device feature data through the portrait data matrix, and at least one of the mobile phone serial number, software account, mobile phone number and network access address as the network access feature data.

[0065] In one embodiment, the user portrait device of the embodiment of the present application also includes: an image identification module, which is used to use each device feature data and each network access feature data in the user behavior data set as the vertex of the association relationship analysis diagram, and draw a connection line between the device feature data and the network access feature data belonging to a single user behavior data to identify the association relationship between the device feature data and the network access feature data.

[0066] In one implementation, the data processing module 301 includes:

[0067] The unit to be connected is used to determine a maximal connected subgraph according to each association relationship, and determine each association relationship belonging to the same maximal connected subgraph as a relationship to be connected.

[0068] The data merging unit is used to merge the network characteristic access data corresponding to each of the to-be-connected relationships as the network access characteristic data of the same user to obtain the user network access characteristic data.

[0069] In one implementation, the unit to be connected is specifically used to: obtain the lines in the association relationship analysis graph that are in a connected state; and use the connected subgraph composed of each of the connected lines as the maximal connected subgraph of the association relationship corresponding to the line.

[0070] In one implementation, the user portrait module 302 includes:

[0071] The behavior feature unit is used to extract the behavior features of the network access feature data.

[0072] The tag search unit is used to search for a behavior tag in a preset behavior tag set according to the behavior feature.

[0073] A portrait unit is used to use the tag set composed of the behavior tags as a user portrait of the corresponding user.

[0074] In one embodiment, it further includes: a deduplication module for removing duplicated device feature data and network access feature data in the behavior feature data set.

[0075] Figure 7 A schematic diagram of a device structure of an embodiment of the present application is shown in FIG. Figure 7 As shown, the device includes a processor 40, a memory 41, an input device 42 and an output device 43; the number of processors 40 in the device can be one or more. Figure 7 A processor 40 is taken as an example; the device processor 40, the memory 41, the input device 42 and the output device 43 can be connected by a bus or other means. Figure 7 The example of connecting through bus is taken in the following.

[0076] The memory 41 is a computer-readable storage medium that can be used to store software programs, computer executable programs and modules, such as the modules corresponding to the user portrait device in the embodiment of the present application (data processing module 301 and user portrait module 302). The processor 40 executes various functional applications and data processing of the device by running the software programs, instructions and modules stored in the memory 41, that is, realizing the above-mentioned user portrait method.

[0077] The memory 41 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system and at least one application required for a function; the data storage area may store data created according to the use of the terminal, etc. In addition, the memory 41 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some instances, the memory 41 may further include a memory remotely arranged relative to the processor 40, and these remote memories may be connected to the device 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.

[0078] The input device 42 may be used to receive input digital or character information and generate key signal input related to user settings and function control of the device. The output device 43 may include a display device such as a display screen.

[0079] The embodiment of the present application further provides a storage medium containing computer executable instructions, wherein the computer executable instructions are used to execute a user profiling method when executed by a computer processor, the method comprising:

[0080] According to the correlation between the device feature data and the network access feature data of the user behavior data set, the network access feature data of the same user is merged to obtain the user network access feature data; and the user profile is performed based on the user network access feature data.

[0081] Of course, the storage medium containing computer executable instructions provided in an embodiment of the present application, whose computer executable instructions are not limited to the method operations described above, can also execute related operations in the user method provided in any embodiment of the present application.

[0082] Through the above description of the implementation method, the technicians in the relevant field can clearly understand that the present application can be implemented with the help of software and necessary general hardware, and of course it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application can be essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory (FLASH), hard disk or optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0083] It is worth noting that in the embodiment of the above-mentioned user portrait device, the various units and modules included are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application.

[0084] The above description is merely an exemplary embodiment of the present application and is not intended to limit the protection scope of the present application.

[0085] It will be appreciated by those skilled in the art that the term user terminal covers any suitable type of wireless user equipment, such as a mobile phone, a portable data processing device, a portable web browser or a vehicle-mounted mobile station.

[0086] In general, various embodiments of the present application can be implemented in hardware or dedicated circuits, software, logic or any combination thereof. For example, some aspects can be implemented in hardware, while other aspects can be implemented in firmware or software that can be executed by a controller, microprocessor or other computing device, although the present application is not limited thereto.

[0087] Embodiments of the present application may be implemented by executing computer program instructions by a data processor of a mobile device, for example in a processor entity, or by hardware, or by a combination of software and hardware. The computer program instructions may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages.

[0088] The block diagram of any logic flow in the accompanying drawings of the present application can represent program steps, or can represent interconnected logic circuits, modules and functions, or can represent a combination of program steps and logic circuits, modules and functions. The computer program can be stored on a memory. The memory can have any type suitable for the local technical environment and can be implemented using any suitable data storage technology, such as but not limited to read-only memory (ROM), random access memory (RAM), optical memory device and system (digital versatile disc DVD or CD disc), etc. Computer-readable media may include non-transient storage media. The data processor can be any type suitable for the local technical environment, such as but not limited to a general-purpose computer, a special-purpose computer, a microprocessor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a programmable logic device (FGPA) and a processor based on a multi-core processor architecture.

[0089] By way of exemplary and non-limiting examples, a detailed description of exemplary embodiments of the present application has been provided above. However, various modifications and adjustments to the above embodiments will be apparent to those skilled in the art when considered in conjunction with the accompanying drawings and claims, but will not depart from the scope of the present application. Therefore, the proper scope of the present application will be determined according to the claims.

Claims

1. A user profiling method, characterized in that: include: Extracting the network device identifier in the user behavior data set as the device feature data, and at least one of the mobile phone serial number, software account, mobile phone number and network access address as the network access feature data through the portrait data matrix; According to the correlation between the device feature data and the network access feature data of the user behavior data set, the network access feature data of the same user is merged to obtain the user network access feature data; Create a user profile based on the user's network access feature data.

2. The method according to claim 1, characterized in that Before merging the network access feature data of the same user according to the association between the device feature data and the network access feature data of the user behavior data set to obtain the user network access feature data, the method further includes: Each device feature data and each network access feature data in the user behavior data set is used as a vertex of the association relationship analysis diagram, and a connection line is drawn between the device feature data and the network access feature data belonging to a single user behavior data to identify the association relationship between the device feature data and the network access feature data.

3. The method according to claim 1, characterized in that The method of combining the network access feature data of the same user according to the association relationship between the device feature data and the network access feature data of the user behavior data set to obtain the user network access feature data includes: Determine a maximal connected subgraph according to each association relationship, and determine each association relationship belonging to the same maximal connected subgraph as a relationship to be connected; The network characteristic access data corresponding to each of the to-be-connected relationships are merged as network access characteristic data of the same user to obtain user network access characteristic data.

4. The method according to claim 2 or 3, characterized in that: Determining a maximal connected subgraph according to each association relationship includes: Obtaining the connection lines in the association relationship analysis diagram; The connected subgraph formed by the connecting lines is used as the maximal connected subgraph of the corresponding association relationship of the connecting lines.

5. The method according to claim 1, characterized in that The user profiling according to the user network access feature data includes: Extracting behavioral features of the network access feature data; Searching for a behavior tag in a preset behavior tag set according to the behavior feature; The tag set consisting of the behavior tags is used as the user profile of the corresponding user.

6. The method according to any one of claims 1 to 3, characterized in that: Before the association between the device feature data and the network access feature data according to the user behavior data set, it also includes: The repeated device characteristic data and the network access characteristic data in the behavior characteristic data set are removed.

7. A user profiling device, characterized in that: include: A data extraction module, used to extract the network device identification in the user behavior data set as the device feature data, and at least one of the mobile phone serial number, software account, mobile phone number and network access address as the network access feature data through the portrait data matrix; A data processing module, used to merge the network access characteristic data of the same user according to the association relationship between the device characteristic data and the network access characteristic data of the user behavior data set to obtain the user network access characteristic data; The user portrait module is used to create a user portrait based on the user's network access feature data.

8. A user portrait device, characterized in that: The device comprises: one or more processors; a memory for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the user profiling method as described in any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the user profiling method as described in any one of claims 1 to 6 is implemented.

Images