User portrait generation method and device, equipment, storage medium and program product

Abstract

The embodiment of the invention provides a user portrait generation method, device and equipment, a computer readable storage medium and a computer program product, and the method relates to the technical field of big data analysis and can be applied to the field of financial science and technology. The method comprises the following steps: acquiring burying point data when a user accesses a system function interface; the burying point data comprises interface information of the system function interface and operation data of a user in the system function interface; obtaining eyeball movement data in a period when the user accesses the system function interface, and determining each function module focused by the user in the period when the user accesses the system function interface and stay duration on each function module based on the eyeball movement data and the interface information; obtaining a face feature state when a user focuses on each function module; and generating a user portrait of the user based on the face feature state, the operation data and the stay duration. According to the method, the accuracy of generating the user portrait is improved.

Description

Technical Field

[0001] The present application relates to the field of big data technology, and in particular to a method, apparatus, device, computer-readable storage medium, and computer program product for generating a user portrait. Background Art

[0002] At present, the way to generate user portraits is usually to extract data mined from user behavior data logs. For example, user feature data is mined from log data such as browsing history, purchase records, and shopping cart records, and user portraits are generated based on the user feature data. In the specific implementation process, it is found that the accuracy of user portraits based on data mined from various types of user behavior data logs is not high. Summary of the invention

[0003] Embodiments of the present application provide a user portrait generation method, apparatus, device, computer-readable storage medium, and computer program product for improving the problem of low accuracy of user portraits.

[0004] In a first aspect, an embodiment of the present application provides a method for generating a user portrait, comprising:

[0005] Acquire the tracking data when the user accesses the system function interface; the tracking data includes the interface information of the system function interface and the operation data of the user in the system function interface;

[0006] Acquire eye movement data of the user during the period of accessing the system function interface, and determine, based on the eye movement data and the interface information, each functional module focused on by the user during the period of accessing the system function interface and the length of time the user stays on each functional module;

[0007] Acquiring the facial feature status of the user when focusing on each functional module;

[0008] A user portrait of the user is generated based on the facial feature status, the operation data and the stay duration.

[0009] In a second aspect, an embodiment of the present application provides a user portrait generation device, including:

[0010] An acquisition module is used to acquire the buried point data when the user accesses the system function interface; the buried point data includes the interface information of the system function interface and the operation data of the user in the system function interface; and acquire the eye movement data of the user during the period of accessing the system function interface;

[0011] A processing module, used for determining each functional module focused on by the user during access to the system functional interface and the length of time the user stays on each functional module based on the eye movement data and the interface information;

[0012] The acquisition module is further used to acquire the facial feature state of the user when focusing on each functional module;

[0013] The processing module is also used to generate a user portrait of the user based on the facial feature state, the operation data and the stay duration.

[0014] In a third aspect, an embodiment of the present application provides an electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the user portrait generation method provided in the first aspect of the embodiment of the present application are implemented.

[0015] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the user portrait generation method provided in the first aspect of the embodiment of the present application are implemented.

[0016] In a fifth aspect, an embodiment of the present application provides a computer program product on which a computer program is stored. When the computer program is executed by a processor, the steps of the user portrait generation method provided in the first aspect of the embodiment of the present application are implemented.

[0017] The technical solution provided in the embodiment of the present application obtains the tracking data when the user accesses the system function interface, and the tracking data includes the interface information of the system function interface and the operation data of the user in the system function interface, and obtains the eye movement data during the period when the user accesses the system function interface, determines the functional modules focused on by the user during the period when the user accesses the system function interface and the length of time the user stays on each functional module based on the eye movement data and the interface information, and obtains the facial feature status of the user when focusing on each functional module, and generates a user portrait of the user based on the facial feature status, operation data and length of time the user stays on each functional module, that is, in the process of generating the user portrait, the multi-dimensional feature information of the user is fully considered, including the functional modules focused on by the user on the system function interface, and the facial feature status, operation data and length of time the user stays on each functional module of the user, so that the obtained user feature information is more accurate, thereby improving the accuracy of generating the user portrait. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 A schematic diagram of an application environment of the user portrait generation method provided in an embodiment of the present application;

[0019] Figure 2A schematic diagram of a process for generating a user portrait provided in an embodiment of the present application;

[0020] Figure 3 Another schematic diagram of a flow chart of a method for generating a user portrait provided in an embodiment of the present application;

[0021] Figure 4 A schematic diagram of another process of the method for generating a user portrait provided in an embodiment of the present application;

[0022] Figure 5 A schematic diagram of the structure of a user portrait generation device provided in an embodiment of the present application;

[0023] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0024] In order to make the purpose, technical solutions and advantages of the present application clearer, the technical solutions in the embodiments of the present application are further described in detail through the following embodiments and in combination with the accompanying drawings. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application. Those skilled in the art can make adjustments to them as needed to suit specific application scenarios. It should also be noted that, for ease of description, only the parts related to the present application are shown in the accompanying drawings, rather than all structures.

[0025] In order to facilitate the understanding of those skilled in the art, some concepts involved in the embodiments of the present application are first introduced:

[0026] User portraits are user images constructed through data labels. For example, each specific information in the historical data generated by the user (such as browsing history or shopping order records) is abstracted into a label, and these labels are used to outline the user's real personal characteristics in many aspects. It has been widely used in various fields, especially in the field of financial technology.

[0027] System function interface refers to the graphical interface for users to interact with computer systems or software. Its main design goal is to allow users to use the various functions of the system or software intuitively and conveniently. For example, the web page interface on a web program and / or the menu interface on an application program.

[0028] SDK (Software Development Kit) is generally a collection of development tools used by software engineers to build application software for specific software packages, software frameworks, hardware platforms, operating systems, etc.

[0029] It should be noted that the information collected in the embodiments of the present application are all information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of the relevant data comply with the relevant laws, regulations and standards of the relevant countries and regions, take necessary confidentiality measures, do not violate public order and good customs, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0030] Figure 1 A schematic diagram of the application environment of the user portrait generation method provided in the embodiment of the present application. Figure 1 , the user portrait generation method is applied to a user portrait generation system. The user portrait generation system may include a terminal 101 and a server 102. The terminal 101 and the server 102 are connected via a wireless network or a wired network. The terminal 101 may be a desktop terminal or a mobile terminal. Optionally, the mobile terminal may be at least one of a PDA (personal digital assistant), a PAD (tablet computer), a PMP (portable multimedia player), a vehicle terminal (such as a vehicle navigation terminal), and a mobile phone. The server 102 may be an independent server or a server cluster consisting of multiple servers.

[0031] It should be noted that the user portrait generation method in the embodiment of the present application can be executed separately by the terminal 101 or the server 102, or can be jointly executed by the terminal 101 and the server 102. The following method embodiment is described by taking the execution subject as an electronic device (the electronic device is the terminal 101 and / or the server 102) as an example.

[0032] Figure 2 A flow chart of a method for generating a user portrait provided in an embodiment of the present application. Figure 2 As shown, the method may include:

[0033] S201. Obtain the tracking data when the user accesses the system function interface.

[0034] The tracking data includes the interface information of the system function interface and the user's operation data in the system function interface. The system function interface here can be the function interface of any business system, for example, the function interface of various banking systems. In some examples, the SDK can be used to obtain the tracking data when the user accesses the system function interface.

[0035] First, use SDK to perform tracking in the system function interface. In an optional implementation, tracking in the system function interface may include: using code tracking technology and / or visual tracking technology to track in the system function interface. Introduction to tracking in the system function interface using code tracking technology:

[0036] Step 1: Select a computer language to complete the tracking code; the computer language includes but is not limited to any one of the following: HyperText Markup Language (HTML), Cascading Style Sheets (CSS), JavaScript.

[0037] Step 2: embed the completed embedding code file into the system function interface through the interface of the system function interface; wherein the embedding code file and the file in the system function interface remain independent.

[0038] The embedding code file and the system function interface file in the embodiment of the present application are independent of each other and do not affect or interfere with each other, thus solving the problem of various embedding codes invading the original pages and business codes.

[0039] After using SDK to embed points in the system function interface, the SDK monitors the behavior events in the system function interface to obtain the interface information of the system function interface and the user's operation data in the system function interface; the operation data includes but is not limited to: the function module operated by the user, the specific operation content of the function module (such as browsing the function module, generating transaction behavior in the function module, etc.), the input information elements and the operation duration, etc. In addition, the SDK can also be used to obtain the interface information in the system function interface; the interface information includes interface elements (that is, which function modules are included in the interface) and the location information of each interface element.

[0040] S202, obtaining eye movement data of a user during access to a system function interface, and determining, based on the eye movement data and interface information, each functional module that the user focuses on during access to the system function interface and the length of time the user stays on each functional module.

[0041] Specifically, when a user accesses a system function interface, the electronic device may collect the user's eye image data through an image sensor, and obtain the eye movement data of the user when accessing the system function interface by analyzing the eye image data. Of course, the electronic device may also capture the user's eye movement data through an infrared-based eye tracker, and this embodiment does not limit the method for obtaining the eye movement data. Furthermore, by analyzing the eye movement data, the location of the eye focus on the system function interface may be obtained, and based on the location of the eye focus and the position information of each interface element in the system function interface, the functional module corresponding to the eye focus location on the system function interface may be determined, thereby obtaining the functional modules focused on by the user during access to the system function interface and the duration of stay on each functional module.

[0042] As an optional implementation, the above S202 may include: determining the user's visual focus based on eye movement data; based on interface information, mapping the visual focus to the system function interface to obtain the functional modules focused on by the user during the period of access to the system function interface; for each functional module, determining the length of time the user stays on the functional module based on the timestamps of the user's eyes entering and leaving the functional module.

[0043] Specifically, after obtaining the eye movement data, the eye movement data is processed by a model-based line of sight estimation method or a corneal reflection-based method to obtain the user's visual focus; further, the position information of the user's visual focus is compared with the position information of each functional module included in the system function interface. If the position information of the visual focus falls within a predefined area of ​​a functional module, then it can be determined that the user is focused on the functional module. Furthermore, for each functional module focused by the user, the time difference between the two timestamps can be calculated based on the timestamp of the user's eye entering the functional module and the timestamp of leaving the functional module, and the time difference can be determined as the length of time the user stays on the functional module.

[0044] S203: Obtain the facial feature status of the user when focusing on each functional module.

[0045] After determining the functional modules focused by the user during the period of accessing the system functional interface, the facial feature state of the user when focusing on each functional module can also be obtained. By analyzing the facial feature state, the user's interest in each functional module can also be obtained to a certain extent.

[0046] As an optional implementation, the above S203 may include: acquiring image data in response to an input operation of the image sensor; and recognizing the image data to obtain a facial feature state of the user when focusing on each functional module.

[0047] Specifically, an image sensor, also known as an image acquisition device, refers to a device that acquires images of a user's face. The image sensor here specifically includes: a SLR color camera, a black and white camera, a surveillance camera, a camera or a terminal with a camera, etc. The terminal with a camera here includes: a mobile phone, a smart bracelet, a tablet computer or a notebook, etc.

[0048] Optionally, the electronic device can access its own front camera and / or microphone, collect the user's facial image through the front camera and / or collect the user's voice data through the microphone, recognize the facial image, and obtain the initial facial feature state. In some examples, voice features such as pitch, speed, and rhythm in the voice data can also be extracted, and the voice features are matched using preset rules to obtain the user's voice state. Finally, the user's final facial feature state is determined based on the user's initial facial feature state obtained from the facial image and the voice state obtained from the voice data.

[0049] S204: Generate a user portrait of the user based on the facial feature status, operation data and stay time.

[0050] Specifically, the user's facial feature state when focusing on each functional module, the operation data for each functional module, and the length of time spent on each functional module are comprehensively considered to determine the user's interest in each functional module, and based on the user's interest in each functional module, a user profile of the user is generated. The user profile may include content data such as name, age, gender, occupation, and functional modules of interest. These user profiles may also be visualized to facilitate data analysts or product analysts to better analyze the user profiles.

[0051] In some examples, the number of times the user focuses on each functional module can also be determined in combination with the user's eye movement data, and a user portrait of the user can be generated by combining the user's facial feature status when focusing on each functional module, the operation data for each functional module, the length of time spent on each functional module, and the number of times the user focuses.

[0052] The user portrait generation method provided in the embodiment of the present application obtains the tracking data when the user accesses the system function interface, and the tracking data includes the interface information of the system function interface and the operation data of the user in the system function interface, and obtains the eye movement data during the period when the user accesses the system function interface, determines the functional modules focused on by the user during the period when the user accesses the system function interface and the length of time the user stays on each functional module based on the eye movement data and the interface information, and obtains the facial feature status of the user when focusing on each functional module, and generates a user portrait of the user based on the facial feature status, operation data and length of time the user stays on each functional module, that is, in the process of generating the user portrait, the multi-dimensional feature information of the user is fully considered, including the functional modules focused on by the user on the system function interface, and the facial feature status, operation data and length of time the user stays on each functional module of the user for each functional module, so that the obtained user feature information is more accurate, thereby improving the accuracy of generating the user portrait.

[0053] In one embodiment, optionally, Figure 3As shown, the above S204 may include:

[0054] S2041. For each functional module, determine the user's interest score for the functional module based on the facial feature state when the user focuses on the functional module, the operation data for the functional module, and the length of time the user stays on the functional module.

[0055] Among them, the interest score is used to characterize the user's interest in the function module. The higher the score value, the higher the user's interest in the function module, and the lower the score value, the lower the user's interest in the function module. It can be understood that if the user's stay time for a certain function module is longer, the facial feature state when focusing on the function module is closer to the first facial feature state, and more operation data is generated in the function module, then the user's interest score for the function module is higher; conversely, if the user's stay time for a certain function module is shorter, the facial feature state when focusing on the function module is closer to the second facial feature state, and less operation data or even no operation data is generated in the function module, then the user's interest score for the function module is lower. The above-mentioned first facial feature state and the second facial feature state are different, and the first facial feature state represents that the user's interest in the function module is higher than the second facial feature state.

[0056] Optionally, the above S2041 may include: for each function module, based on the facial feature state when the user focuses on the function module, determining the user's first interest score for the function module; based on the user's operation data on the function module, determining the user's second interest score for the function module; based on the user's stay time on the function module, determining the user's third interest score for the function module; based on the first interest score, the second interest score and the third interest score, determining the user's final interest score for the function module.

[0057] Specifically, according to the degree of correlation between the facial feature state of the user when focusing on the functional module and the first facial feature state or the second facial feature state, a corresponding score is assigned to the facial feature state of the user, and the score is used as the first interest score of the user for the functional module. The closer to the first facial feature state, the higher the score can be, and the closer to the second facial feature state, the lower the score can be.

[0058] Analyze the operation data, and determine the user's second interest score for the function module based on the analysis results. For example, frequent interactions may indicate a higher user interest. That is, the more operations are performed on the function module, the higher the score is, and the fewer operations are performed on the function module, the lower the score is.

[0059] The length of stay is another indicator for evaluating the user's interest in a functional module. The longer the stay time, the more interested the user is in the functional module, and the higher the third interest score of the functional module is. The shorter the stay time, the lower the third interest score of the functional module is.

[0060] Based on the first interest score, the second interest score, the third interest score and the weight of each score in the final score, the user's final interest score for the functional module is determined. The weight of each score in the final score can be adjusted based on the specific scenario and business objectives. In this process, the multi-dimensional feature information of the user when focusing on the functional module is fully considered, so that the final user's interest score for the functional module is more accurate.

[0061] S2042: Cluster each functional module according to its module features to obtain a clustering module.

[0062] For each functional module focused by the user, each functional module can be clustered according to its module features, and the functional modules whose feature similarity exceeds a preset threshold can be divided into the same group, and the functional modules whose feature similarity does not exceed the preset threshold can be divided into different groups, and the divided groups are used as clustering modules.

[0063] For example, taking the system function interface of online banking as an example, assuming that the functional modules for user clustering are "water bill", "electricity bill", "gas bill", "provident fund", "enterprise annuity", "social security" and "medical insurance", etc., then according to the module characteristics of each functional module, "water bill", "electricity bill" and "gas bill" can be divided into the same group to obtain the clustering module "recharge and payment", and "provident fund", "enterprise annuity", "social security" and "medical insurance" can be divided into the same group to obtain the clustering module "convenience services".

[0064] S2043: Determine the user's interest score for the clustering module based on the interest scores of the functional modules included in the clustering module.

[0065] After obtaining the clustering module, the user's interest score for the clustering module can be comprehensively determined based on the interest scores of the functional modules included in the clustering module. Continuing with the example in S2042 above, for the clustering module "recharge and payment", the user's interest score for the clustering module "recharge and payment" can be determined based on the user's interest scores for "water charges", "electricity charges" and "gas charges". For another example, for the clustering module "convenience services", the user's interest score for the clustering module "convenience services" can be determined based on the user's interest scores for "provident fund", "enterprise annuity", "social security" and "medical insurance".

[0066] S2044. Generate a user profile of the user based on the user's interest score in the clustering module.

[0067] After obtaining the user's interest score for the clustering module, the user's user profile can be generated by combining the user's interest score for the clustering module and the tag information of the clustering module. For example, if there are multiple clustering modules, the clustering modules can be sorted from high to low according to the interest score of each clustering module, and the user profile of the user can be generated based on the sorting result and the tag information of the clustering module.

[0068] In this embodiment, the functional modules focused by the user are clustered according to the module characteristics, and the user portrait is generated using the user's interest score in the clustered modules. This makes the generated user portrait logically more concise and clear, and reduces the dimension and complexity of subsequent user portrait analysis.

[0069] In one embodiment, optionally, Figure 4 As shown, after generating the user portrait, the method may further include:

[0070] S401: Determine at least one target user for a questionnaire survey based on access data of a system function interface within a preset time period.

[0071] Specifically, the access data of the system function interface within a preset time period is collected, and the survey subjects (i.e., target users) of the questionnaire survey are obtained by analyzing the access data obtained. The above preset time period can be set based on actual business needs. For example, the access data of the system function interface within the past six months can be collected, and users whose access frequency exceeds the preset frequency and / or whose access duration exceeds the preset duration can be screened out from the access data, and these users are determined as the target users of the questionnaire survey.

[0072] S402: Determine a module to be optimized in a system function interface according to a user portrait of at least one target user.

[0073] After determining at least one target user of the questionnaire survey, obtain a user portrait of at least one target user, determine the function module of interest to each target user in the system function interface according to the user portrait of each target user, and determine the module to be optimized in the system function interface based on the function module of interest to each target user. In some examples, obtain the function module of interest to at least one target user, count the number of interested users of at least one function module of interest, and determine the function module of interest with more than a preset number of interested users as the module to be optimized in the system function interface, that is, the module to be optimized is the function module of interest to most users, and further optimize these function modules to improve the user experience and increase user stickiness. In some examples, the function module of interest with the largest number of interested users can be determined as the module to be optimized in the system function interface.

[0074] S403: Send a questionnaire to at least one target user; the questionnaire is used to collect optimization opinions for the module to be optimized.

[0075] Specifically, a questionnaire is sent to at least one target user through a preset sending method to collect optimization opinions of at least one target user on the module to be optimized. The preset sending method may be an email, a text message, a pop-up window or a link to the questionnaire inserted in the system function interface, or a combination of any of the above methods. Sending the questionnaire through multiple sending methods improves the sending effect of the questionnaire.

[0076] S404: Receive a questionnaire survey result of at least one target user, and optimize the module to be optimized based on the questionnaire survey result.

[0077] Specifically, the user can fill out a questionnaire and submit it, and the electronic device receives the questionnaire survey results fed back by at least one target user, and uses the questionnaire survey results fed back by at least one target user to optimize the functions of the module to be optimized, and / or optimize the layout of the module to be optimized in the system function interface, etc., so that the module to be optimized better meets the usage needs of the vast majority of users and improves the user experience.

[0078] In this embodiment, based on the access data of the system function interface within a preset time period, at least one target user for the questionnaire survey is determined, and by analyzing the user portrait of the at least one target user, the module to be optimized in the system function interface is determined, and a questionnaire is sent to the at least one target user to collect optimization opinions for the module to be optimized, and the questionnaire survey results fed back by at least one target user are received. Based on the questionnaire survey results fed back by at least one target user, the module to be optimized is further optimized, so that the module to be optimized can better meet the user's usage needs, improve the user experience, and increase user stickiness.

[0079] Figure 5 A schematic diagram of the structure of a user portrait generation device provided in an embodiment of the present application. Figure 5 As shown, the device may include: an acquisition module 501 and a processing module 502.

[0080] Specifically, the acquisition module 501 is used to acquire the buried point data when the user accesses the system function interface; the buried point data includes the interface information of the system function interface and the operation data of the user in the system function interface; and acquire the eye movement data of the user during the period of accessing the system function interface;

[0081] The processing module 502 is used to determine the functional modules focused on by the user during the period of accessing the system functional interface and the length of time the user stays on each functional module based on the eye movement data and the interface information;

[0082] The acquisition module 501 is also used to acquire the facial feature state of the user when focusing on each functional module;

[0083] The processing module 502 is also used to generate a user portrait of the user based on the facial feature state, the operation data and the stay duration.

[0084] On the basis of the above embodiment, optionally, the processing module 502 is also used to determine, for each functional module, the user's interest score in the functional module based on the facial feature state when the user focuses on the functional module, the operation data on the functional module, and the length of time spent on the functional module; cluster the functional modules according to the module features of the functional modules to obtain a clustering module; determine the user's interest score in the clustering module based on the interest scores of the functional modules contained in the clustering module; and generate a user portrait of the user based on the user's interest score in the clustering module.

[0085] On the basis of the above embodiment, optionally, the processing module 502 is also used to determine, for each functional module, a first interest score of the user in the functional module based on the facial feature state when the user focuses on the functional module; determine a second interest score of the user in the functional module based on the user's operation data on the functional module; determine a third interest score of the user in the functional module based on the length of time the user stays on the functional module; and determine a final interest score of the user in the functional module based on the first interest score, the second interest score and the third interest score.

[0086] Based on the above embodiment, optionally, the processing module 502 is also used to determine the visual focus of the user based on the eye movement data; based on the interface information, map the visual focus to the system function interface to obtain the functional modules focused on by the user during the visit to the system function interface; for each functional module, determine the length of time the user stays on the functional module based on the timestamps of the user's eyes entering and leaving the functional module.

[0087] On the basis of the above embodiment, optionally, the acquisition module 501 is also used to acquire image data in response to an input operation of the image sensor; perform feature recognition on the image data to obtain the facial feature state of the user when focusing on each functional module.

[0088] Based on the above embodiment, optionally, the device further includes: a sending module.

[0089] The processing module 502 is further used to determine at least one target user of the questionnaire survey based on the access data of the system function interface within a preset time period; and determine the module to be optimized in the system function interface according to the user portrait of the at least one target user;

[0090] The sending module is used to send a questionnaire to the at least one target user; the questionnaire is used to collect optimization opinions for the module to be optimized;

[0091] The acquisition module 501 is also used to receive the questionnaire survey result of the at least one target user;

[0092] The processing module 502 is also used to optimize the module to be optimized based on the questionnaire survey result.

[0093] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application, such as Figure 6 As shown, the device includes a processor 60, a memory 61, an input device 62 and an output device 63; the number of the processor 60 in the device can be one or more. Figure 6 A processor 60 is taken as an example; the processor 60, memory 61, input device 62 and output device 63 in the device can be connected by a bus or other means. Figure 6 The example of connecting through bus is taken in the following.

[0094] The memory 61 is a computer-readable storage medium that can be used to store software programs, computer executable programs and modules, such as program instructions / modules corresponding to the user portrait generation method in the embodiments of the present application (for example, the acquisition module 501 and the processing module 502 used in the user portrait generation device). The processor 60 executes various functional applications and data processing of the device by running the software programs, instructions and modules stored in the memory 61, that is, implements the user portrait generation method provided in any of the above embodiments.

[0095] The memory 61 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 during the user portrait generation process, etc. In addition, the memory 61 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 61 may further include a memory remotely arranged relative to the processor 60, and these remote memories may be connected to the device / terminal / server 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.

[0096] The input device 62 may be used to receive input digital or character information and generate key signal input related to user settings and function control of the electronic device. The output device 63 may include a display device such as a display screen.

[0097] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0098] Acquire the tracking data when the user accesses the system function interface; the tracking data includes the interface information of the system function interface and the operation data of the user in the system function interface;

[0099] Acquire eye movement data of the user during the period of accessing the system function interface, and determine, based on the eye movement data and the interface information, each functional module focused on by the user during the period of accessing the system function interface and the length of time the user stays on each functional module;

[0100] Acquiring the facial feature status of the user when focusing on each functional module;

[0101] A user portrait of the user is generated based on the facial feature status, the operation data and the stay duration.

[0102] In one embodiment, a computer program product is further provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0103] Acquire the tracking data when the user accesses the system function interface; the tracking data includes the interface information of the system function interface and the operation data of the user in the system function interface;

[0104] Acquire eye movement data of the user during the period of accessing the system function interface, and determine, based on the eye movement data and the interface information, each functional module focused on by the user during the period of accessing the system function interface and the length of time the user stays on each functional module;

[0105] Acquiring the facial feature status of the user when focusing on each functional module;

[0106] A user portrait of the user is generated based on the facial feature status, the operation data and the stay duration.

[0107] The user portrait generation device, electronic device, computer-readable storage medium, and computer program product provided in the above embodiments can execute the user portrait generation method provided in any embodiment of the present application, and have the corresponding functional modules and beneficial effects of executing the method. For technical details not described in detail in the above embodiments, please refer to the user portrait generation method provided in any embodiment of the present application.

[0108] 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 is 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 of each embodiment of the present application.

[0109] It is worth noting that the various units and modules included in the above embodiments are only divided according to functional logic, but are not limited to the above 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.

[0110] Note that the above are only preferred embodiments of the present application and the technical principles used. Those skilled in the art will understand that the present application is not limited to the specific embodiments herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present application. Therefore, although the present application is described in more detail through the above embodiments, the present application is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present application, and the scope of the present application is determined by the scope of the appended claims.

Claims

1. A method for generating a user portrait, characterized in that: include: Obtain the tracking data when users access the system function interface; The tracking data includes interface information of the system function interface and operation data of the user in the system function interface; Acquire eye movement data of the user during the period of accessing the system function interface, and determine, based on the eye movement data and the interface information, each functional module focused on by the user during the period of accessing the system function interface and the length of time the user stays on each functional module; Acquiring the facial feature status of the user when focusing on each functional module; A user portrait of the user is generated based on the facial feature status, the operation data and the stay duration.

2. The method according to claim 1, characterized in that The generating a user portrait of the user based on the facial feature state, the operation data and the stay time includes: For each functional module, based on the facial feature state of the user when focusing on the functional module, the operation data for the functional module, and the length of time spent on the functional module, determine the user's interest score for the functional module; Clustering the functional modules according to their module features to obtain clustering modules; Determining the user's interest score for the clustering module based on the interest scores of the functional modules included in the clustering module; Based on the user's interest score for the clustering module, a user profile of the user is generated.

3. The method according to claim 2, characterized in that The step of determining, for each functional module, the user's interest score for the functional module based on the facial feature state when the user focuses on the functional module, the operation data for the functional module, and the length of time the user stays on the functional module, includes: For each functional module, determining a first interest score of the user for the functional module based on a facial feature state when the user focuses on the functional module; Determining a second interest score of the user for the functional module based on the user's operation data for the functional module; Determining a third interest score of the user for the functional module based on the length of time the user stays on the functional module; Based on the first interest score, the second interest score, and the third interest score, a final interest score of the user for the function module is determined.

4. The method according to claim 1, characterized in that: The determining, based on the eye movement data and the interface information, the functional modules focused on by the user during access to the system functional interface and the length of time the user stays on each functional module includes: determining a visual focus of the user based on the eye movement data; Based on the interface information, the visual focus is mapped to the system function interface to obtain each functional module focused on by the user during access to the system function interface; For each functional module, the length of time the user stays in the functional module is determined based on the timestamps of when the user's eyes enter and leave the functional module.

5. The method according to claim 1, characterized in that The acquiring of the facial feature state of the user when focusing on each functional module includes: Responding to an input operation of the image sensor, acquiring image data; The image data is identified to obtain the facial feature state of the user when focusing on each functional module.

6. The method according to any one of claims 1 to 5, characterized in that Also includes: Determining at least one target user for the questionnaire survey based on access data of the system function interface within a preset time period; Determining a module to be optimized in the system function interface according to the user portrait of the at least one target user; Sending a questionnaire to the at least one target user; The questionnaire is used to collect optimization opinions for the module to be optimized; A questionnaire survey result of the at least one target user is received, and the module to be optimized is optimized based on the questionnaire survey result.

7. A user portrait generation device, characterized in that: include: The acquisition module is used to obtain the tracking data when the user accesses the system function interface; The buried data includes the interface information of the system function interface and the operation data of the user in the system function interface; and the eye movement data of the user during the period of accessing the system function interface; A processing module, used for determining each functional module focused on by the user during access to the system functional interface and the length of time the user stays on each functional module based on the eye movement data and the interface information; The acquisition module is further used to acquire the facial feature state of the user when focusing on each functional module; The processing module is further used to generate a user portrait of the user based on the facial feature state, the operation data and the stay duration.

8. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

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

10. A computer program product having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images