User behavior data acquisition and business processing method and device

Abstract

The embodiment of the invention provides a user behavior data acquisition and business processing method and device. The method can comprise the steps that sight line focus coordinates, corresponding to a sight line focus of a user, on a screen are obtained through a sight line tracking technology, a collection area on the screen is determined according to the sight line focus coordinates, the collection area is an area concerned by the sight line of the user, and an image corresponding to the collection area is recognized and processed. Image content included in the image is obtained, collected user behavior data is generated, and the user behavior data at least comprises a user identifier of the user and the image content.

Description

Technical Field

[0001] The present invention relates to the field of data collection technology, and in particular to a method and device for collecting user behavior data and processing business data. Background Art

[0002] Currently, traditional user behavior data is collected by passing the attribute data generated by the user's interaction with the product UI to the background for interaction, such as opening a page, clicking on page elements, etc., and then the user-related behavior data can be obtained from the back-end service log and business database.

[0003] This solution collects data generated by the backend, and cannot collect behaviors that occur in large quantities on the frontend and do not interact with the backend, such as the user's subconscious gaze behavior. In addition, traditional collection methods, excluding factors such as misoperation, mostly collect behavioral data with strong user subjective intentions, and cannot collect user subconscious behavior data. Summary of the invention

[0004] In order to overcome the problems existing in the related art, this specification provides a user behavior data collection, business processing method and device.

[0005] In a first aspect of any embodiment of this specification, a user behavior data collection method is provided, which is applied to a collection plug-in, and the method includes:

[0006] Through the eye tracking technology, the coordinates of the user's eye focus on the screen are obtained;

[0007] Determine a collection area on the screen according to the sight focus coordinates, where the collection area is the area where the user's sight focuses;

[0008] Performing recognition processing on the image corresponding to the acquisition area to obtain image content included in the image;

[0009] Generate collected user behavior data, the user behavior data at least including: a user identification of the user and the image content.

[0010] In a second aspect of any embodiment of this specification, a service processing method is provided, the method comprising:

[0011] Acquire collected user behavior data, wherein the user behavior data is collected by the user behavior data collection method described in any embodiment of this specification;

[0012] Describing user portraits based on the user behavior data;

[0013] Based on the user portrait, corresponding business processing is performed.

[0014] In a third aspect of any embodiment of this specification, a user behavior data collection device is provided, which is applied to a collection plug-in, and the device includes:

[0015] A coordinate acquisition module is used to obtain the coordinates of the user's gaze focus corresponding to the gaze focus on the screen through gaze tracking technology;

[0016] An area determination module, used to determine a collection area on the screen according to the sight focus coordinates, wherein the collection area is an area where the user's sight focuses;

[0017] An image recognition module, used to perform recognition processing on the image corresponding to the acquisition area to obtain the image content included in the image;

[0018] The data generation module is used to generate collected user behavior data, wherein the user behavior data at least includes: a user identification of the user and the image content.

[0019] In a fourth aspect of any one of the embodiments of this specification, a service processing device is provided, the device comprising:

[0020] A data acquisition module, used to acquire collected user behavior data, wherein the user behavior data is collected by the user behavior data collection method described in any embodiment of this specification;

[0021] A portrait description module, used to describe a user portrait based on the user behavior data;

[0022] The business processing module is used to perform corresponding business processing based on the user portrait.

[0023] According to a fifth aspect of any embodiment of this specification, there is provided an electronic device, including:

[0024] processor;

[0025] a memory for storing processor-executable instructions;

[0026] The processor implements the method described in any embodiment of this specification by running the executable instructions.

[0027] According to a sixth aspect of any embodiment of the present specification, there is provided a computer-readable storage medium on which computer instructions are stored, and when the instructions are executed by a processor, the steps of the method described in any embodiment of the present specification are implemented.

[0028] The technical solutions provided by the embodiments of this specification may have the following beneficial effects:

[0029] According to the above embodiments, the eye tracking technology is used to obtain the eye focus coordinates on the screen corresponding to the user's eye focus, and the collection area on the screen is determined based on the eye focus coordinates. The image corresponding to the collection area is recognized and processed to obtain the image content included in the image, and the collected user behavior data is generated. Since the area of ​​the user's eye focus is determined based on the acquired eye focus coordinates, the image corresponding to the collection area is recognized and processed to generate the collected user behavior data, there is no need for the user to interact with the back end, and the subconscious behavior of the user occurring at the front end can be collected. At the same time, by including the user identifier and the image content in the image corresponding to the collection area in the generated collected user behavior data, the collected user behavior data is made richer and more accurate.

[0030] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present specification. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0032] Figure 1 is a flow chart of a method for collecting user behavior data according to an exemplary embodiment of this specification;

[0033] Figure 2 is a schematic diagram of a PCCR gaze tracking technology according to an exemplary embodiment of the present specification;

[0034] Figure 3 is a schematic diagram of an initial position of a first anchor point according to an exemplary embodiment of the present specification;

[0035] Figure 4 is a schematic diagram of dividing a moving range according to an exemplary embodiment of the present specification;

[0036] Figure 5 is a schematic diagram of a first anchor point exceeding a moving range according to an exemplary embodiment of the present specification;

[0037] Figure 6 is a flow chart of a method for determining a collection area according to an exemplary embodiment of the present specification;

[0038] Figure 7 is a schematic diagram of constructing a region to be evaluated according to an exemplary embodiment of this specification;

[0039] Figure 8 is a schematic diagram of screening an area to be evaluated according to an exemplary embodiment of this specification;

[0040] Fig. 9 is a schematic diagram of a virtual grid and adjacent grids according to an exemplary embodiment of the present specification;

[0041] Fig.10 is a schematic diagram of selecting a region to be circled according to an exemplary embodiment of this specification;

[0042] Fig.11 is a schematic diagram of determining a collection area according to an exemplary embodiment of this specification;

[0043] Fig.12 is a flow chart of a business processing method according to an exemplary embodiment of this specification;

[0044] Fig.13 is a schematic structural diagram of an electronic device according to an exemplary embodiment of the present specification;

[0045] Fig.14 is a block diagram of a user behavior data collection device according to an exemplary embodiment of the present specification;

[0046] Fig.15 It is a block diagram of a service processing device according to an exemplary embodiment of this specification. DETAILED DESCRIPTION

[0047] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementations described in the following exemplary embodiments do not represent all implementations consistent with this specification. Instead, they are merely examples of devices and methods consistent with some aspects of this specification as detailed in the appended claims.

[0048] The terms used in this specification are for the purpose of describing specific embodiments only and are not intended to limit this specification. The singular forms "a", "the" and "the" used in this specification and the appended claims are also intended to include plural forms unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.

[0049] It should be understood that although the terms first, second, third, etc. may be used in this specification to describe various information, this information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of this specification, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0050] Currently, when collecting user behavior data, it is usually based on the interaction between the user and the product, and the behavior data actively generated by the user is collected. However, it is impossible to collect the subconscious behavior of the user when using the product without interacting with the system, such as the user's subconscious gaze behavior.

[0051] In order to solve the above problems, the embodiments of this specification propose a method for collecting user behavior data. To further illustrate this specification, the following embodiments are provided:

[0052] like Figure 1 As shown, Figure 1 This is a flowchart of a user behavior data collection method according to an exemplary embodiment of this specification, which is applied to a collection plug-in, which can be installed on mobile phones, tablets, computers and other devices, and these devices can pre-install eye tracking hardware and enable the system permissions of the device. Among them, the eye tracking hardware includes but is not limited to: light-emitting diode arrays, cameras, etc., and the system permissions include but are not limited to: light-emitting diode array permissions, camera permissions, and network permissions.

[0053] The user behavior data collection method may include the following steps:

[0054] Step 102: Obtain the coordinates of the user's gaze focus on the screen by using gaze tracking technology.

[0055] In this step, the acquisition plug-in can be introduced into the client of the device. During the operation of the acquisition plug-in, it can be initialized to establish a coordinate system for the entire screen with the lower left corner of the device screen as the origin of the coordinate system. The acquisition plug-in can obtain the user's line of sight focus coordinates on the screen corresponding to the line of sight focus through line of sight tracking technology. The line of sight focus is the focus point where the user's line of sight intersects, and the line of sight focus coordinates are the coordinate point of the user's line of sight focus in the coordinate system of the screen.

[0056] Gaze tracking technology records eye movement trajectories and extracts data such as gaze point, gaze time and number, eye saccade distance, pupil size, etc., and calculates each person's gaze point when looking at the screen in real time. It includes: corneal reflection method, sclera-iris edge method, pupil-corneal reflection technology, etc.

[0057] Taking PCCR (Pupil Center Corneal Reflection) technology as an example, Figure 2 A schematic diagram of a PCCR gaze tracking technology is shown. Light emitted by a light emitting diode array 202 illuminates an eye 204 to produce obvious reflections, and a camera 206 is used to collect images of the eye 204 with these reflections, and the images collected by the camera are used to identify the reflections of the light source on the cornea 208 and the pupil 210.

[0058] The eye movement vector PG is calculated by the angle between the cornea 208 and the pupil 210 reflection, and then the direction of this vector is combined with the geometric features of other reflections to calculate the direction of the sight focus X. According to the direction of the sight focus X, the position of the sight focus X on the screen is determined, and the sight focus coordinates corresponding to the position of the sight focus X are obtained based on the coordinate system of the screen.

[0059] Furthermore, the acquisition plug-in can set a time window, which is a time period used to determine the area of ​​the user's gaze focus. In each time window, the gaze focus coordinates can be recorded once at a fixed interval. For example, the time window can be 5 seconds, and the fixed time interval can be 50 milliseconds, then 100 gaze focus coordinates will be obtained in each time window.

[0060] When each time window is opened, the origin of the coordinate system established on the screen is used as the initial position of the first anchor point. Figure 3 A schematic diagram showing the initial position of the first anchor point is shown in Figure 3 , the origin O of the coordinate system established according to the screen is used as the initial position of the first anchor point Q.

[0061] When the user drags the page on the screen, the first anchor point will move with the page on the screen. The origin O of the coordinate system can be used as the second anchor point, and a certain area containing the second anchor point can be selected as the moving range. The movement range of the page on the screen can be determined based on whether the anchor point position of the first anchor point exceeds the moving range, thereby judging the validity of the acquired sight focus coordinates.

[0062] Figure 4 A schematic diagram showing a division of the moving range is shown in Figure 4, the second anchor point is the coordinate system origin O. For example, the moving range 42 can be divided into a circular area including the coordinate system origin O with the coordinate system origin O as the center and 15% of the screen width as the radius. Before the end of the current five-second time window, the collection plug-in can collect a sight focus coordinate based on the user's sight focus every 50 milliseconds. If the anchor point position of the first anchor point Q never exceeds the moving range, the 100 sight focus coordinates recorded in this time window are valid.

[0063] If the anchor point position of the first anchor point exceeds the moving range within the five-second time window, the collected sight focus coordinates of the current time window are discarded. The next time window is reopened and the anchor point position of the first anchor point is reset. Figure 5 A schematic diagram showing a first anchor point exceeding the moving range is shown, Figure 5 As shown, the anchor point position of the first anchor point Q exceeds the moving range 42 as the page moves. The acquisition plug-in discards the sight focus coordinates acquired in the current time window, opens the next time window, and reacquires the sight focus coordinates.

[0064] As described above, by determining whether the anchor point position of the first anchor point exceeds the moving range in each time window, invalid sight focus coordinates can be discarded to ensure the validity of the collected sight focus coordinates, thereby ensuring the accuracy of the subsequently collected user behavior data.

[0065] Step 104: Determine a collection area on the screen according to the sight focus coordinates, where the collection area is the area that the user's sight focuses on.

[0066] In this step, the acquisition plug-in can determine the area on the screen where the user's sight is focused, as the acquisition area, according to the sight focus coordinates obtained in step 102. The acquisition area can be used to analyze and obtain the area where the user's sight is focused.

[0067] For example, the collection area can be determined by circling the collection area according to the density of the sight focus coordinates; or, for another example, the collection area can be determined by circling the collection area according to the gaze time of the sight focus coordinates. How to determine the collection area on the screen according to the sight focus coordinates will be further described in subsequent embodiments.

[0068] Step 106: performing recognition processing on the image corresponding to the acquisition area to obtain image content included in the image.

[0069] In this step, the acquisition plug-in can take a screenshot of the acquisition area determined in step 104 through the screenshot function in the system of the device, obtain an image corresponding to the acquisition area, and use image recognition technology to identify and process the image to obtain the image content included in the image. The image content is the information that the user focuses on based on the image recognition corresponding to the acquisition area, which is used to generate user behavior data. The image content can be object information, text information, object type and other information.

[0070] It can be understood that image recognition technology uses deep learning and neural networks to process digital images and identify patterns and features in images, using trained models to accurately classify new images into different categories, including: CNN (Convolutional Neural Networks), residual neural networks and other technologies.

[0071] Taking CNN technology as an example, the acquisition plug-in can use CNN technology to identify the image corresponding to the acquisition area and obtain the image content in the image. The image content is the image information obtained by image recognition processing, which may include: objects included in the image, and object categories corresponding to the objects. The objects included in the image are objects, text information and other information recognized based on the image, such as televisions, computers, books, journals, etc. The object category corresponding to the object is the type of object included in the image, such as electronic equipment corresponding to televisions and computers, and literary works corresponding to books and journals.

[0072] CNN technology can be pre-trained for targeted object classification. After training, CNN technology can be used to identify objects included in an image and the object categories corresponding to the objects. If the identified object category does not belong to the predefined type, the image is judged to be meaningless and the image content corresponding to the image is discarded. The predefined types can be one or more.

[0073] Exemplarily, the predefined type may be furniture. If the image content in the image identified using CNN technology is a television and an electronic device type corresponding to the television, since the electronic device type does not conform to the predefined furniture type, the image is judged to be meaningless and the identified television and electronic device types are discarded.

[0074] As described above, by performing recognition processing on the image corresponding to the collection area, the objects included in the image and the object categories corresponding to the objects are obtained, so that image content that conforms to the predefined type can be collected, avoiding the use of meaningless image content to generate user behavior data, making the user behavior data more accurate, and allowing for a more precise description of subsequent user portraits.

[0075] Step 108: Generate collected user behavior data, the user behavior data at least including: the user identification of the user and the image content.

[0076] In this step, the collection plug-in can generate collected user behavior data based on the image content obtained in step 106. The user behavior data is data that can reflect the user's preferences and intentions, and at least includes: the user identification of the user and the image content. Among them, the user identification of the user can be a user ID, a user name, or other user information, which can be used to associate the behavior of the same user on a certain device, so as to facilitate the subsequent creation of a user portrait for the user.

[0077] In one example, the user behavior data may also include a collection time. The collection time may be used to identify the time corresponding to the collection of the sight focus coordinates. For example, it may be the time when the sight focus coordinates are collected, or it may be the time period of the time window corresponding to the sight focus coordinates, recording the time when the user behavior occurs.

[0078] As described above, by including the time of collecting the sight focus coordinates in the generated collected user behavior data, it is possible to avoid the impact of data reporting delays on the timeliness of the data, ensure the accuracy of the user behavior data, and facilitate the analysis of user behavior in different time periods.

[0079] The collection plug-in can use a preset data structure to store user behavior data. The storage method can be stored in the form of a local file on the device's client, or it can be stored in the device's server in a custom interface reporting method.

[0080] Exemplarily, the preset data structure may be a dictionary, which stores user behavior data in the form of key-value pairs. An example of the preset data structure is as follows:

[0081] {

[0082] "uuid": "value1",

[0083] "user": "value2",

[0084] "collect_time": "value3",

[0085] "contents": [

[0086] "value4" ]

[0088] "attrs":{"key1":"value5"}

[0089] }

[0090] Among them, uuid and the corresponding value1 are used to store the unique identifier of the reported user behavior data, user and the corresponding value2 are used to store the user ID of the user, collect_time and the corresponding value3 are used to store the collection time, contents and the corresponding value4 are used to store the image content, and key1 and the corresponding value5 in attrs can store extended attributes such as the duration of the focus of vision and the number of times the image content is paid attention to.

[0091] The user behavior data collection method of the present embodiment determines the area of ​​user's line of sight as the collection area based on the acquired line of sight focus coordinates, identifies and processes the image corresponding to the collection area, and generates collected user behavior data without the need for the user to interact with the back end, and can collect the user's subconscious behavior occurring at the front end; at the same time, by including the user identifier and the image content in the image corresponding to the collection area in the generated collected user behavior data, the collected user behavior data can be made richer and more accurate.

[0092] In the above embodiment, the method for determining the acquisition area is described, that is, the acquisition plug-in can determine the acquisition area according to the sight focus coordinates. In the following embodiment, how to determine the acquisition area according to the sight focus coordinates will be described in more detail, and can be applied to any of the above embodiments.

[0093] The acquisition plug-in can divide the screen into multiple virtual grids before determining the acquisition area on the screen according to the sight focus coordinates. For example, the width of the screen can be divided into 25 rows and the length of the screen can be divided into 40 columns, and the entire screen will be divided into 25*40=1000 virtual grids.

[0094] See also Figure 6 , Figure 6 This is a flowchart of a method for determining a collection area according to an exemplary embodiment of the present specification. The method for determining a collection area may include the following steps:

[0095] Step 602: Obtain the sight focus coordinates in each time window and an area to be evaluated corresponding to each sight focus coordinate, wherein the area to be evaluated includes the corresponding sight focus coordinates.

[0096] In this step, the acquisition plug-in can obtain the sight focus coordinates in each time window, and construct a corresponding area to be evaluated according to each sight focus coordinate, and the area to be evaluated contains the corresponding sight focus coordinates. The area to be evaluated is an area containing one or more sight focus coordinates, which is used to preliminarily screen the area of ​​user concern and can be constructed into shapes such as circles and rectangles.

[0097] Figure 7A schematic diagram of constructing an area to be evaluated is shown in FIG. Figure 7 As shown, for example, the acquisition plug-in can construct a circular area with each sight focus coordinate as the center and 10% of the screen width as the radius. Each circular area containing the sight focus coordinate is used as the area to be evaluated. For example, Figure 7 One of the sight focus coordinates 71 can be used as the center of the circle to construct a corresponding area to be evaluated 72.

[0098] Step 604: For any of the to-be-evaluated areas, if the number of coordinates of the sight focus coordinates in the to-be-evaluated area meets a preset number condition, the to-be-evaluated area is regarded as a dense area.

[0099] In this step, the acquisition plug-in can determine whether the number of coordinates of the sight focus coordinates in any area to be evaluated meets the preset number condition. If the preset number condition is met, the area to be evaluated is regarded as a dense area. A dense area is an area that meets the preset number condition among multiple areas to be evaluated, and is used to identify the area of ​​user concern that is initially screened out.

[0100] The preset quantity condition may be, for example, a preset quantity threshold. If the total number of sight focus coordinates collected in each time window is 100, the quantity threshold may be preset to 15. If the number of sight focus coordinates in the area to be evaluated is greater than or equal to 15, the area to be evaluated is regarded as a dense area.

[0101] The preset quantity condition may also be to sort the areas to be evaluated according to the number of coordinates of the sight focus coordinates in the area to be evaluated, and select the N areas to be evaluated with the largest number of coordinates as the dense area, where N is a natural number greater than or equal to 1 and less than the number of areas to be evaluated.

[0102] Figure 8 A schematic diagram of screening the area to be evaluated is shown. Figure 8 The coordinates of some sight focus points in a time window and the corresponding area to be evaluated are displayed. The acquisition plug-in can calculate the distance between the center of the area to be evaluated and other sight focus coordinates, and count the number of focal points that are less than or equal to the radius of the area to be evaluated. The number of focal points plus the sight focus coordinates corresponding to the center of the circle is the number of sight focus coordinates in the area to be evaluated.

[0103] Based on the number of coordinates of the sight focus coordinates in the area to be evaluated, all the areas to be evaluated within the time window are sorted. Figure 8As shown, illustratively, the time window contains 20 areas to be evaluated, and 14 areas to be evaluated with the largest number of coordinates can be screened out. The acquisition plug-in can treat these 14 areas to be evaluated as dense areas, retain the sight focus coordinates in the dense areas, and discard other sight focus coordinates collected in the time window.

[0104] Step 606: Determine the acquisition area on the screen based on the virtual grid where the sight focus coordinates in the dense area are located.

[0105] The acquisition plug-in may determine the acquisition area on the screen based on the virtual grid where the sight focus coordinates acquired in step 604 are located.

[0106] The acquisition plug-in can obtain the virtual grids where the coordinates of each sight focus included in the dense area are located, merge the connected virtual grids in the obtained virtual grids, and construct the area to be selected. Among them, if the virtual grid contains part or all of the sight focus coordinates, the virtual grid is the virtual grid where the sight focus coordinates are located, and the area to be selected is the area constructed based on the virtual grid where the sight focus coordinates are located, which can be used to determine the acquisition area and further filter the area of ​​user concern.

[0107] When merging virtual grids, if multiple virtual grids where the sight focus coordinates are located are adjacent to each other at edges or corners, the multiple virtual grids are merged. The adjacent grids of the merged virtual grids are further merged, and the adjacent grids are virtual grids that intersect with the virtual grid at edges or corners. Fig. 9 A schematic diagram of a virtual grid and adjacent grids is shown, wherein the adjacent grids are 8 virtual grids intersecting with the edges or corners of the virtual grid a as shown in the figure.

[0108] The acquisition plug-in can construct the area containing the sight focus coordinates in the outermost virtual grid according to the limit coordinates of multiple adjacent grids of the merged virtual grid as the area to be selected. The limit coordinates are the coordinates of the lower left corner and the upper right corner, or the coordinates of the lower right corner and the upper left corner. The shape of the area to be selected can be rectangular, circular, etc.

[0109] Fig.10 A schematic diagram of selecting a region to be circled is shown. Fig.10 As shown, the shape of the area to be selected is a rectangle as an example. First, the virtual grids where the sight focus coordinates are adjacent to the edges or corners of the virtual grids are merged. According to the adjacent grids of the merged virtual grids, the coordinates of the lower left corner and the upper right corner, or the coordinates of the lower right corner and the upper left corner are found, and a rectangular area containing the sight focus coordinates in the outermost virtual grid is constructed, and the rectangular area is used as the area to be selected.

[0110] As described above, by selecting the area to be evaluated whose number of sight focus coordinates meets the preset quantity conditions as the dense area, the area where the user's sight is focused is further screened out, which can filter out some inaccurate sight focus coordinates, avoid calculating the virtual grids corresponding to all sight focus coordinates, and reduce the calculation workload of the acquisition plug-in.

[0111] Furthermore, the collection plug-in can determine, for any area to be selected among the multiple areas to be selected screened out in the above embodiment, whether the number of coordinates of the sight focus coordinates in the area to be selected meets the preset collection conditions; if the preset collection conditions are met, the area to be selected is selected as the collection area.

[0112] Among them, the preset collection condition, for example, can be a preset collection threshold, and whether to use the area to be selected as the collection area is determined according to the collection threshold. The collection threshold can be set according to the total number of sight focus coordinates collected in each time window. If the total number is 100, the collection threshold can be preset as the total number of coordinates * 20%, that is, 200. If the number of coordinates of the sight focus coordinates in the area to be selected is greater than or equal to 200, the area to be selected is selected as the collection area.

[0113] The collection threshold can also be set according to the total number of coordinates on the screen. If the total number of coordinates on the screen is 1000, the collection threshold can be preset as the total number of coordinates * preset percentage. For example, the preset percentage can be 20%, and the collection threshold is 1000 * 20% = 200. If the number of coordinates of the sight focus coordinates in the area to be selected is greater than or equal to 200, the area to be selected is selected as the collection area.

[0114] See also Fig.11 , Fig.11 A schematic diagram of determining a collection area is shown. For example, the total number of coordinates on the screen is 70, the preset percentage is 10%, and the collection threshold is 70*10%=7. The number of coordinates of the sight focus coordinates in the first area to be selected 1101 is 8, the number of coordinates of the sight focus coordinates in the second area to be selected 1102 is 3, and the number of coordinates of the sight focus coordinates in the third area to be selected 1103 is 2. Only if the number of coordinates of the sight focus coordinates in the first area to be selected 1101 is greater than or equal to the collection threshold, the first area to be selected 1101 is determined as the collection area.

[0115] The preset collection condition may also be to sort the areas to be selected according to the number of coordinates of the sight focus coordinates in the area to be selected, and select M areas to be selected with the largest number of coordinates as the collection areas, where M is a natural number greater than or equal to 1 and less than the number of the areas to be selected that are selected.

[0116] As described above, by judging whether an area to be selected is a collection area according to the number of coordinates of the sight focus coordinates among the multiple areas to be selected, the areas that the user focuses on can be screened out, and the areas to be selected that do not meet the coordinate quantity conditions can be filtered out, thereby further ensuring the accuracy of the collected user behavior data.

[0117] In the above embodiment, a method for collecting user behavior data is described. In the following embodiment, how to apply user behavior data will be described in more detail, and can be applied to any of the above embodiments.

[0118] See also Fig.12 , Fig.12 This is a flowchart of a business processing method according to an exemplary embodiment of the present specification, and the method may include the following steps:

[0119] Step 1202: Acquire collected user behavior data, where the user behavior data is collected by the user behavior data collection method in any of the above embodiments.

[0120] In this step, the collection plug-in can obtain the user behavior data collected according to the user behavior data collection method in any of the above embodiments.

[0121] Step 1204: Describe the user portrait based on the user behavior data.

[0122] In this step, the collection plug-in can describe the user portrait based on the user behavior data obtained in step 1202. The user portrait refers to a labeled user model abstracted from user attributes, user preferences, living habits, user behavior and other information, which is used to improve marketing accuracy and recommendation matching.

[0123] Step 1206: Execute corresponding business processing based on the user portrait.

[0124] In this step, the collection plug-in can perform corresponding business processing based on the user portrait. Business processing is the personalized processing of the business provided to the user, which may include: personalized recommendation, targeted marketing, etc.

[0125] The business processing method of this embodiment can make the user portrait more accurate and comprehensive by describing the user portrait based on the collected subconscious user behavior data, and perform corresponding business processing based on the user portrait, so as to provide users with more accurate personalized services.

[0126] In another embodiment, the user profile may include: the user's purchase intention. The collection plug-in may mark different priorities for multiple recommended information according to the user's purchase intention in the user profile. The higher the priority, the more the recommended information matches the user's purchase intention. The purchase intention is obtained based on the analysis of user behavior data and is used to mark the product information that the user focuses on. The recommended information is business data provided to the user by the business support, which may be information such as products and advertisements.

[0127] The collection plug-in can recommend target information to be recommended to the user from multiple information to be recommended based on priority. The target information to be recommended is the business data that the business ultimately recommends to the user, and can be information such as goods and advertisements. The selection method of the target information to be recommended can be, for example, selecting the information to be recommended that ranks in the top three in priority, or selecting the information to be recommended that ranks in the top 50% in priority.

[0128] For example, the collected user behavior data includes: 6 times for furniture products, 4 times for clothing products, 3 times for electronic products and 2 times for food products. The purchase intention in the user portrait is from high to low: furniture products, clothing products, electronic products and food products.

[0129] In the e-commerce scenario, the e-commerce platform supports providing users with a variety of recommended information such as furniture products, clothing products, electronic products, and food products. The priority of the recommended information is marked according to the purchase intention in the user portrait. The priority is from high to low: furniture products, clothing products, electronic products, food products, and other products. Among the multiple recommended information, furniture products are the most compatible with the user's purchase intention.

[0130] Based on the priorities of the four pieces of information to be recommended, the top three pieces of information to be recommended are selected, that is, the target information to be recommended is furniture products, clothing products and electronic products, and furniture products, clothing products and electronic products are preferentially recommended to users.

[0131] As described above, by marking the priority of the recommended information according to the purchase intention in the user portrait, and recommending the target recommended information to the user based on the priority, the information that best matches the user's purchase intention can be recommended to the user first, thereby facilitating targeted marketing for different users.

[0132] Fig.13 is a schematic diagram of the structure of an electronic device according to an exemplary embodiment of this specification. Fig.13At the hardware level, the electronic device includes a processor 1302, an internal bus 1304, a network interface 1306, a memory 1308, and a non-volatile memory 1310, and may also include hardware required for other services. The processor 1302 reads the corresponding computer program from the non-volatile memory 1310 into the memory 1308 and then runs it, forming a user behavior data collection device at the logical level. Of course, in addition to the software implementation, this application does not exclude other implementation methods, such as logic devices or a combination of software and hardware, etc., that is to say, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.

[0133] Fig.14 is a block diagram of a user behavior data collection device according to an exemplary embodiment of this specification. Fig.14 The device includes: a coordinate acquisition module 1402, a region determination module 1404, an image recognition module 1406 and a data generation module 1408, wherein:

[0134] The coordinate acquisition module 1402 is used to acquire the coordinates of the user's gaze focus corresponding to the screen through gaze tracking technology.

[0135] The area determination module 1404 is used to determine the collection area on the screen according to the sight focus coordinates, and the collection area is the area where the user's sight focuses.

[0136] The image recognition module 1406 is used to perform recognition processing on the image corresponding to the acquisition area to obtain the image content included in the image.

[0137] The data generation module 1408 is used to generate collected user behavior data, and the user behavior data at least includes: the user identification of the user and the image content.

[0138] In one example, the coordinate acquisition module 1402, when used to obtain the line of sight coordinates corresponding to the user's line of sight on the screen, includes: when the time window is opened, the origin of the coordinate system established according to the screen is used as the initial position of the first anchor point, and the first anchor point moves with the page movement of the screen, and the time window is a time period for determining the collection area; if before the end of the time window, if the anchor point position of the first anchor point does not exceed the moving range, based on the user's line of sight, multiple line of sight coordinates collected in the time window are obtained, and the moving range is the area including the second anchor point, and the second anchor point is the origin of the coordinate system.

[0139] In one example, the area determination module 1404, before being used to determine the collection area on the screen according to the line of sight focus coordinates, further includes: dividing the screen into multiple virtual grids; the area determination module 1404, when used to determine the collection area on the screen according to the line of sight focus coordinates, includes: obtaining the line of sight focus coordinates in each time window, and an area to be evaluated corresponding to each line of sight focus coordinate, the area to be evaluated containing the corresponding line of sight focus coordinates; for any of the areas to be evaluated, if the number of coordinates of the line of sight focus coordinates in the area to be evaluated meets a preset number condition, then the area to be evaluated is regarded as a dense area; based on the virtual grid where the line of sight focus coordinates in the dense area are located, the collection area on the screen is determined.

[0140] In one example, the area determination module 1404, when used for a virtual grid corresponding to the line of sight focus coordinates of the dense area, includes: obtaining the virtual grids where the line of sight focus coordinates included in the dense area are respectively located; merging the connected virtual grids in the obtained virtual grids to construct an area to be selected, and the area to be selected is used to determine the collection area on the screen.

[0141] In one example, the user behavior data further includes: a collection time, and the collection time is used to identify the time corresponding to the collection of the sight focus coordinates.

[0142] In one example, the image content includes: objects included in the image, and object categories corresponding to the objects.

[0143] Fig.15 is a block diagram of a service processing device according to an exemplary embodiment of this specification. Fig.15 The device includes: a data acquisition module 1502, a portrait description module 1504 and a business processing module 1506, wherein:

[0144] The data acquisition module 1502 is used to acquire collected user behavior data, and the user behavior data is collected by the user behavior data collection method described in any embodiment of this specification.

[0145] The portrait description module 1504 is used to describe the user portrait based on the user behavior data.

[0146] The business processing module 1506 is used to perform corresponding business processing based on the user portrait.

[0147] In one example, the user portrait includes: the user's purchasing intention; the business processing module 1506, when used to perform corresponding business processing based on the user portrait, includes: marking different priorities of multiple information to be recommended according to the purchasing intention, the higher the priority, the more the information to be recommended matches the user's purchasing intention; based on the priority, recommending to the user the target information to be recommended selected from the multiple information to be recommended.

[0148] The implementation process of the functions and effects of each unit in the above-mentioned device is specifically described in the implementation process of the corresponding steps in the above-mentioned method, and will not be repeated here.

[0149] For the device embodiment, since it basically corresponds to the method embodiment, the relevant parts can refer to the partial description of the method embodiment. The device embodiment described above is only schematic, wherein the modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules, that is, they may be located in one place, or they may be distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this specification. A person of ordinary skill in the art can understand and implement it without paying creative labor.

[0150] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory including instructions, and the above instructions can be executed by a processor of a resource access device to implement any of the methods described in the above embodiments.

[0151] The non-temporary computer-readable storage medium may be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc., and the present application does not limit this.

[0152] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0153] Those skilled in the art will readily appreciate other embodiments of the specification after considering the specification and practicing the invention claimed herein. The specification is intended to cover any variations, uses or adaptations of the specification that follow the general principles of the specification and include common knowledge or customary techniques in the art that are not claimed in the specification. The specification and examples are to be considered exemplary only, and the true scope and spirit of the specification are indicated by the following claims.

[0154] It should be understood that the present description is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present description is limited only by the appended claims.

[0155] The above description is only a preferred embodiment of this specification and is not intended to limit this specification. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of this specification should be included in the scope of protection of this specification.

Claims

1. A user behavior data collection method, characterized in that: Applied to a collection plug-in, the method includes: Through the eye tracking technology, the coordinates of the user's eye focus on the screen are obtained; Determine a collection area on the screen according to the sight focus coordinates, where the collection area is the area where the user's sight focuses; Performing recognition processing on the image corresponding to the acquisition area to obtain image content included in the image; Generate collected user behavior data, the user behavior data at least including: a user identification of the user and the image content.

2. The method according to claim 1, characterized in that The obtaining of the coordinates of the user's sight focus corresponding to the sight focus on the screen includes: When the time window is opened, the origin of the coordinate system established according to the screen is used as the initial position of the first anchor point, and the first anchor point moves along with the page movement of the screen, and the time window is a time period for determining the acquisition area; If before the end of the time window, if the anchor point position of the first anchor point does not exceed the moving range, based on the user's line of sight focus, obtain multiple line of sight focus coordinates collected within the time window, and the moving range is the area including the second anchor point, and the second anchor point is the origin of the coordinate system.

3. The method according to claim 1, characterized in that Before determining the acquisition area on the screen according to the sight focus coordinates, the method further includes: dividing the screen into a plurality of virtual grids; The step of determining the acquisition area on the screen according to the sight focus coordinates includes: Acquire the sight focus coordinates in each time window and an area to be evaluated corresponding to each sight focus coordinate, wherein the area to be evaluated includes the corresponding sight focus coordinates; For any of the areas to be evaluated, if the number of coordinates of the sight focus coordinates in the area to be evaluated meets a preset number condition, the area to be evaluated is regarded as a dense area; The acquisition area on the screen is determined based on the virtual grid where the sight focus coordinates in the dense area are located.

4. The method according to claim 3, characterized in that: The virtual grid corresponding to the sight focus coordinates of the dense area includes: Obtain virtual grids where the coordinates of each sight focus in the dense area are located; The connected virtual grids in the acquired virtual grids are merged to construct a region to be selected, and the region to be selected is used to determine the acquisition region on the screen.

5. The method according to claim 1, characterized in that: The user behavior data also includes: The acquisition time is used to identify the time corresponding to the acquisition of the sight focus coordinates.

6. The method according to claim 1, characterized in that The image content includes: objects included in the image, and object categories corresponding to the objects.

7. A business processing method, characterized in that: The method comprises: Acquire collected user behavior data, wherein the user behavior data is collected by the user behavior data collection method according to any one of claims 1 to 6; Describing user portraits based on the user behavior data; Based on the user portrait, corresponding business processing is performed.

8. The method according to claim 7, characterized in that The user portrait includes: the user's purchasing intention; The performing corresponding business processing based on the user portrait includes: According to the purchase intention, the plurality of recommended information are marked with different priorities, wherein the higher the priority, the more the recommended information matches the purchase intention of the user; Based on the priority, target information to be recommended selected from the plurality of information to be recommended is recommended to the user.

9. A user behavior data collection device, characterized in that: Applied to a collection plug-in, the device comprises: A coordinate acquisition module is used to obtain the coordinates of the user's gaze focus corresponding to the gaze focus on the screen through gaze tracking technology; An area determination module, used to determine a collection area on the screen according to the sight focus coordinates, wherein the collection area is an area where the user's sight focuses; An image recognition module, used to perform recognition processing on the image corresponding to the acquisition area to obtain the image content included in the image; The data generation module is used to generate collected user behavior data, wherein the user behavior data at least includes: a user identification of the user and the image content.

10. A service processing device, characterized in that: The device comprises: A data acquisition module, used to acquire collected user behavior data, wherein the user behavior data is collected by the user behavior data collection method according to any one of claims 1 to 6; A portrait description module, used to describe a user portrait based on the user behavior data; The business processing module is used to perform corresponding business processing based on the user portrait.

11. An electronic device, characterized in that: include: processor; a memory for storing processor-executable instructions; The processor implements the method according to any one of claims 1 to 8 by running the executable instructions.

12. A computer-readable storage medium having computer instructions stored thereon, characterized in that: When the instruction is executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

Images