Methods, apparatus, devices and storage media for constructing intelligent dynamic pages

Abstract

The present invention relates to the field of research and development management, and discloses a method, device, equipment and storage medium for constructing an intelligent dynamic page, which is used to dynamically display the page according to the interests of different users. The method includes: obtaining an initial page; dividing the initial page into regions based on preset information tags to obtain multiple intermediate regions; receiving an access request sent by a terminal, transmitting the initial page to the terminal for display according to the access request, and acquiring the eye image of the target user through the front camera of the terminal to obtain multiple eye images of the target user; calculating the dwell time of the target user's sight in multiple target areas in turn to obtain multiple gaze time values; classifying multiple target areas according to the multiple gaze time values ​​to obtain key areas and non-key areas; displaying the key areas and non-key areas to obtain a target dynamic display page. The present invention also relates to blockchain technology, and the eye image can be stored in the blockchain.

Description

Technical Field

[0001] The present invention relates to the field of research and development management, and in particular to a method, device, equipment and storage medium for constructing an intelligent dynamic page. Background Art

[0002] With the development of various online media platforms, customers spend their daily time on these content platforms. Therefore, content has become a necessary "hook product" for insurance companies and platforms. Agents or platforms need to publish insurance vertical content every day to stimulate customer demand and achieve potential customer mining and conversion of prospective customers. As we all know, insurance products are complex, and the requirements of the CIRC on major insurance companies are strict. Therefore, the introduction of graphic information of insurance products must be complete, resulting in a longer length of graphic and text.

[0003] However, different customers may have different levels of knowledge and interests in insurance products: for the same product, some customers may be concerned about the coverage of the insurance product, while others may be concerned about the compensation method and amount of the insurance product. Therefore, the current page content cannot meet the needs of different customers on the same page. Summary of the invention

[0004] The main purpose of the present invention is to solve the problem that pages cannot be dynamically displayed according to the interests of different users.

[0005] The first aspect of the present invention provides a method for constructing an intelligent dynamic page, comprising: obtaining an initial page, the initial page being used to introduce insurance products; dividing the initial page into regions based on preset information tags to obtain multiple intermediate regions; receiving an access request sent by a terminal, transmitting the initial page to the terminal for display according to the access request, and collecting an eye image of a target user through a front camera of the terminal to obtain multiple eye images of the target user; based on the multiple eye images and the multiple intermediate regions, calculating the time that the target user's line of sight stays in multiple target regions in turn to obtain multiple gaze time values; classifying the multiple target regions according to the multiple gaze time values ​​to obtain key regions and non-key regions; displaying the key regions and the non-key regions to obtain a target dynamic display page.

[0006] Optionally, in a first implementation method of the first aspect of the present invention, before obtaining the initial page, it also includes: receiving a page creation request sent by a page creation terminal; analyzing the page creation request to determine the corresponding multiple insurance business themes; determining the corresponding content information through the multiple insurance business themes; filling the content information into a preset candidate page to obtain the initial page.

[0007] Optionally, in a second implementation method of the first aspect of the present invention, dividing the initial page into regions based on preset information tags to obtain multiple intermediate regions includes: reading the preset information tags to determine the candidate information type corresponding to the preset tag information; understanding the content of the initial page through the candidate information type to determine the target information type corresponding to the content information in the initial page; and dividing the initial page into regions using the target information type to obtain multiple intermediate regions.

[0008] Optionally, in a third implementation method of the first aspect of the present invention, the access request sent by the receiving terminal, transmitting the initial page to the terminal for display according to the access request, and capturing the eye image of the target user through the front camera of the terminal to obtain multiple eye images of the target user includes: responding to the access request of the terminal, loading the content information of the initial page in the terminal; calling the front camera of the terminal to capture the facial image of the target user to obtain multiple facial images; and capturing the eye image of the target user through the multiple facial images to obtain multiple eye images of the target user.

[0009] Optionally, in a fourth implementation method of the first aspect of the present invention, based on the multiple eye images and the multiple intermediate areas, the dwell time of the target user's sight in the multiple target areas is calculated in sequence to obtain multiple gaze time values, including: identifying multiple eyeball images of the target user from the multiple eye images, and locating multiple pupil coordinates; calculating multiple gaze point position coordinates of the target user's sight on the touch screen of the terminal through the multiple pupil coordinates; determining multiple gaze positions where the target user is currently gazing at the touch screen based on the multiple gaze point position coordinates and the position of the front camera on the terminal; determining multiple corresponding target areas through the multiple gaze positions and the multiple intermediate areas, and calculating the dwell time of the target user's sight in the multiple target areas in sequence to obtain multiple gaze time values.

[0010] Optionally, in a fifth implementation method of the first aspect of the present invention, the classification of the multiple target areas according to the multiple gaze time values ​​to obtain key areas and non-key areas includes: performing numerical analysis on the multiple gaze time values ​​to determine a gaze time threshold; performing numerical judgment on the multiple gaze time values, if there is at least one first gaze time value greater than or equal to the gaze time threshold, then treating the first target area corresponding to the at least one first gaze time value as a key area; if there is at least one second gaze time value less than the gaze time threshold, then treating the second target area corresponding to the at least one second gaze time value as a non-key area.

[0011] Optionally, in a sixth implementation method of the first aspect of the present invention, the display processing of the key area and the non-key area to obtain a target dynamic display page includes: highlighting the information content corresponding to the key area; and folding the information content corresponding to the non-key area to obtain a target dynamic display page.

[0012] The second aspect of the present invention provides a device for constructing an intelligent dynamic page, comprising: an acquisition module, used to acquire an initial page, wherein the initial page is used to introduce insurance products; a division module, used to divide the initial page into regions based on preset information tags to obtain multiple intermediate regions; an acquisition module, used to receive an access request sent by a terminal, transmit the initial page to the terminal for display according to the access request, and acquire the eye image of the target user through the front camera of the terminal to obtain multiple eye images of the target user; a calculation module, used to calculate the stay time of the target user's line of sight in multiple target regions in turn based on the multiple eye images and the multiple intermediate regions to obtain multiple gaze time values; a classification module, used to classify the multiple target regions according to the multiple gaze time values ​​to obtain key regions and non-key regions; a processing module, used to display the key regions and the non-key regions to obtain a target dynamic display page.

[0013] Optionally, in a first implementation method of the second aspect of the present invention, the device for constructing the intelligent dynamic page also includes: a receiving module for receiving a page creation request sent by a page creation terminal; an analysis module for analyzing the page creation request to determine the corresponding multiple insurance business themes; a determination module for determining the corresponding content information through the multiple insurance business themes; and a transmission module for filling the content information into a preset candidate page to obtain an initial page.

[0014] Optionally, in a second implementation method of the second aspect of the present invention, the division module is specifically used to: read the preset information tag to determine the candidate information type corresponding to the preset tag information; understand the content of the initial page through the candidate information type to determine the target information type corresponding to the content information in the initial page; and divide the initial page into regions using the target information type to obtain multiple intermediate regions.

[0015] Optionally, in a third implementation method of the second aspect of the present invention, the acquisition module is specifically used to: respond to an access request from the terminal, and load the content information of the initial page in the terminal; call the front camera of the terminal to capture the facial image of the target user to obtain multiple facial images; and acquire the eye image of the target user through the multiple facial images to obtain multiple eye images of the target user.

[0016] Optionally, in a fourth implementation manner of the second aspect of the present invention, the calculation module is specifically used to: identify multiple eye images of the target user from the multiple eye images, and locate multiple pupil coordinates; calculate multiple gaze point position coordinates of the target user's line of sight on the touch screen of the terminal through the multiple pupil coordinates; determine multiple gaze positions of the target user currently staring at the touch screen based on the multiple gaze point position coordinates and the position of the front camera on the terminal; determine the corresponding multiple target areas through the multiple gaze positions and the multiple intermediate areas, and calculate the residence time of the target user's line of sight in the multiple target areas in turn to obtain multiple gaze time values.

[0017] Optionally, in a fifth implementation method of the second aspect of the present invention, the classification module is specifically used to: perform numerical analysis on the multiple gaze time values ​​to determine a gaze time threshold; perform numerical judgment on the multiple gaze time values, and if there is at least one first gaze time value greater than or equal to the gaze time threshold, then use the first target area corresponding to the at least one first gaze time value as a key area; if there is at least one second gaze time value less than the gaze time threshold, then use the second target area corresponding to the at least one second gaze time value as a non-key area.

[0018] Optionally, in a sixth implementation of the second aspect of the present invention, the processing module is specifically used to: highlight the information content corresponding to the key area; and fold the information content corresponding to the non-key area to obtain a target dynamic display page.

[0019] The third aspect of the present invention provides a device for constructing an intelligent dynamic page, comprising: a memory and at least one processor, wherein the memory stores instructions; the at least one processor calls the instructions in the memory so that the device for constructing an intelligent dynamic page executes the above-mentioned method for constructing an intelligent dynamic page.

[0020] A fourth aspect of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores instructions, which, when executed on a computer, enable the computer to execute the above-mentioned method for constructing an intelligent dynamic page.

[0021] In the technical solution provided by the present invention, an initial page is obtained, and the initial page is used to introduce insurance products; the initial page is divided into regions based on preset information tags to obtain multiple intermediate regions; an access request sent by a terminal is received, and the initial page is transmitted to the terminal for display according to the access request, and the eye image of the target user is collected through the front camera of the terminal to obtain multiple eye images of the target user; based on the multiple eye images and the multiple intermediate regions, the target user's sight stay time in multiple target regions is calculated in turn to obtain multiple gaze time values; the multiple target regions are classified according to the multiple gaze time values ​​to obtain key regions and non-key regions; the key regions and the non-key regions are displayed and processed to obtain a target dynamic display page. In an embodiment of the present invention, an intelligent dynamic page based on user visual dynamic lines dynamically highlights or folds the page by monitoring the user's real-time behavior, so that the same article can better meet the demands of different customers for the same subject content, greatly reducing the threshold for operators to produce content, and also reducing the waste of repeated production of similar content, thereby improving operational efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 A schematic diagram of an embodiment of a method for constructing an intelligent dynamic page in an embodiment of the present invention;

[0023] Figure 2 Schematic diagram of another embodiment of the method for constructing an intelligent dynamic page in an embodiment of the present invention;

[0024] Figure 3 A schematic diagram of an embodiment of a device for constructing an intelligent dynamic page in an embodiment of the present invention;

[0025] Figure 4 A schematic diagram of an embodiment of a device for constructing an intelligent dynamic page in an embodiment of the present invention. DETAILED DESCRIPTION

[0026] Embodiments of the present invention provide a method, device, equipment and storage medium for constructing an intelligent dynamic page. The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including" or "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0027] For ease of understanding, the specific process of the embodiment of the present invention is described below. Figure 1 , an embodiment of the method in the embodiment of the present invention includes:

[0028] 101. Get the initial page, which is used to introduce insurance products;

[0029] It is understandable that the execution subject of the present invention may be a device for constructing an intelligent dynamic page, or a server, which is not specifically limited here. The embodiment of the present invention is described by taking the server as the execution subject as an example.

[0030] Specifically, the server obtains the initial page, which is a business information display page pre-created according to the business theme. After obtaining the initial page, the server can perform further processing on the initial page according to the preset information tag.

[0031] Optionally, before step 101, it also includes: the server receives a page creation request sent by the page creation terminal; the server analyzes the page creation request to determine the corresponding multiple insurance business themes; the server determines the corresponding content information through the multiple insurance business themes; the server fills the content information into a preset candidate page to obtain an initial page.

[0032] Specifically, the server reads the page creation request of the page creation terminal, parses the page creation request, determines the corresponding insurance business theme, which may be customer interaction, demand stimulation and other related topics for insurance business, and determines the corresponding information content based on the related topics. The server plans the graphic content according to the established theme, and layouts the graphic content according to the preset page layout, fills the graphic content into the preset candidate page, and obtains the corresponding initial page.

[0033] 102. Divide the initial page into regions based on the preset information tags to obtain a plurality of intermediate regions;

[0034] Specifically, the preset tag information includes content tags and crowd tags. Content tags refer to content information tags such as character creation, customer interaction, demand stimulation, objection handling and recruitment. Crowd tags refer to crowd information tags such as basic roles, family, marital status, age groups and family roles. The server divides the initial page into regions through the content information tags and the crowd information tags, and obtains multiple corresponding intermediate regions.

[0035] Optionally, step 102 includes: the server reads a preset information tag to determine a candidate information type corresponding to the preset tag information; the server understands the content of the initial page through the candidate information type to determine a target information type corresponding to the content information in the initial page; the server divides the initial page into regions using the target information type to obtain multiple intermediate regions.

[0036] Specifically, the server reads the content information tag and the crowd information tag included in the preset information tag, classifies the content information tag and the crowd information tag, and determines the corresponding candidate information type, which refers to information types such as viewpoints, compensation, and titles. According to the candidate information type, the server understands the content of the initial page, segments the information content of the article, extracts words from the article for frequency weight scoring, and determines the corresponding target information type according to the frequency weight scoring, segments the page according to the target information type, and determines multiple intermediate areas.

[0037] 103. Receive an access request sent by the terminal, transmit the initial page to the terminal for display according to the access request, and collect an eye image of the target user through a front camera of the terminal to obtain multiple eye images of the target user;

[0038] Specifically, the server parses the access request of the terminal and determines the page identifier corresponding to the access request. The server downloads the corresponding initial page according to the page identifier and transmits the initial page to the terminal for display. At the same time, the server calls the front camera of the terminal. When the user browses the initial page on the terminal, the eye image of the target user is collected through the front camera of the terminal.

[0039] Optionally, step 103 includes: the server responds to the access request of the terminal and loads the content information of the initial page in the terminal; the server calls the front camera of the terminal to capture the facial image of the target user and obtains multiple facial images; the server collects the eye image of the target user through the multiple facial images and obtains multiple eye images of the target user.

[0040] Specifically, after parsing the access request of the terminal, the server determines the page identifier corresponding to the access request, and then downloads the corresponding initial page through the page identifier, and loads the information content of the initial page in the terminal, so that the initial page can be displayed to the user in the terminal. The server calls the front camera of the terminal to capture the facial image of the target user who is browsing the page. The facial image can specifically be a facial image including the eye image of the target user. After capturing the facial image, the server scans the facial image, determines the area of ​​the eye image of the target user, and cuts the image of the eye image area of ​​the target user, thereby collecting the eye image of the target user. It should be emphasized that in order to further ensure the privacy and security of the above-mentioned eye image, the above-mentioned eye image can also be stored in a node of a blockchain.

[0041] 104. Based on the multiple eye images and the multiple middle areas, the dwell time of the target user's gaze in the multiple target areas is calculated in sequence to obtain multiple gaze time values;

[0042] Specifically, after collecting the eye image of the target user, the server scans the eye image, which includes the positions of the user's eyes, eyeballs, pupils and other parts, so that the user's eye line of sight can be determined according to the positions of various parts of the eye, and then the position information of the initial page displayed on the terminal at the focus of the user's eye line is determined according to the user's eye line of sight. At the same time, the server tracks the user's line of sight in real time, and calculates the length of time the target user's line of sight stays in different intermediate areas, and obtains multiple gaze time values.

[0043] 105. Classify multiple target areas according to multiple fixation time values ​​to obtain key areas and non-key areas;

[0044] Specifically, the server determines a corresponding gaze time threshold based on the multiple gaze time values. The gaze time threshold is determined by calculating the average value of the multiple gaze time values, and performing mean regression processing on historical user gaze time data pre-stored in a preset database to determine the gaze time threshold. According to the gaze time threshold, the server classifies the multiple target areas gazed by the user to determine the corresponding key areas and non-key areas.

[0045] 106. Display processing is performed on the key area and the non-key area to obtain a target dynamic display page.

[0046] Specifically, after obtaining the corresponding ordinary areas, key areas and non-key areas according to the area classification results, the server performs a first preprocessing based on the determined key area information content to obtain the processed key area content, and performs a second preprocessing on the determined non-key area information content to obtain the processed non-key area content, and after merging the processed key area content and the processed non-key area content, obtains the target dynamic display page.

[0047] In an embodiment of the present invention, the server obtains an initial page and divides the initial page into regions through the content information tag and the crowd information tag, thereby obtaining a plurality of corresponding intermediate regions. The server receives an access request sent by a terminal and parses the access request of the terminal to determine a page identifier corresponding to the access request. The server downloads the corresponding initial page according to the page identifier and displays the initial page on the terminal. At the same time, the server calls the front camera of the terminal. When the target user browses the initial page on the terminal, the eye image of the target user is collected through the front camera of the terminal. After collecting the eye image of the target user, the server scans the eye image and then determines the target user according to the line of sight of the eye of the target user. The position information of the initial page displayed on the terminal at the sight focus, and the server tracks the sight of the target user in real time, and calculates the length of time the sight of the target user stays in different intermediate areas, and obtains multiple gaze time values. The server determines the corresponding gaze time threshold based on the multiple gaze time values. The server performs a first preprocessing on the determined key area information content according to the area classification result, and obtains the processed key area content, and performs a second preprocessing on the determined non-key area information content to obtain the processed non-key area content, and merges the processed key area content and the processed non-key area content to obtain the target dynamic display page. In an embodiment of the present invention, the intelligent dynamic page based on the user's visual line dynamically highlights or folds the page by monitoring the user's real-time behavior, so that the same article can better meet the demands of different customers for the same subject content, greatly reducing the threshold for operators to produce content, and also reducing the waste of repeated production of similar content, thereby improving operational efficiency.

[0048] See also Figure 2 Another embodiment of the method for constructing an intelligent dynamic page in the embodiment of the present invention includes:

[0049] 201. Get the initial page, which is used to introduce insurance products;

[0050] 202. Divide the initial page into regions based on the preset information tags to obtain a plurality of intermediate regions;

[0051] 203. Receive an access request sent by the terminal, transmit the initial page to the terminal for display according to the access request, and collect an eye image of the target user through a front camera of the terminal to obtain multiple eye images of the target user;

[0052] Specifically, in this embodiment, the specific implementation of steps 201-203 is similar to the above steps 101-103, and will not be repeated here.

[0053] 204. Based on the multiple eye images and the multiple middle areas, sequentially calculate the time that the target user's gaze stays in the multiple target areas to obtain multiple gaze time values;

[0054] Specifically, in this embodiment, the specific implementation of step 204 is similar to the above step 104, and will not be repeated here.

[0055] Optionally, step 204 includes: the server identifies multiple eye images of the target user from multiple eye images, and locates multiple pupil coordinates; the server calculates multiple gaze point position coordinates of the target user's line of sight on the touch screen of the terminal through the multiple pupil coordinates; the server determines multiple gaze positions of the target user's current gaze on the touch screen based on the multiple gaze point position coordinates and the position of the front camera on the terminal; the server determines the corresponding multiple target areas through the multiple gaze positions and the multiple intermediate areas, and calculates the stay time of the target user's line of sight in the multiple target areas in turn to obtain multiple gaze time values.

[0056] Specifically, the server scans the eye image, determines the calibration point of the pupil coordinates in the user's eyeball from the eye image, collects the pupil coordinates corresponding to the calibration point through the calibration point, and determines the center coordinates of the spherical surface of the movement trajectory of the pupil based on the characteristics of the pupil movement on the eyeball surface through multiple pupil coordinates, and then determines the gaze point position coordinates of the user's line of sight on the touch screen of the terminal based on the pupil coordinates and the center coordinates. The position coordinates are marked based on a preset coordinate system of the touch screen of the terminal. The preset coordinate system is in the plane where the touch screen is located, with the lower left corner endpoint of the touch screen as the origin, an X-axis is established to the right, and a Y-axis is established upward, and the angle between the X-axis and the Y-axis is 90 degrees. According to the gaze point position coordinates, first determine the user's stay position in the initial page, and then determine multiple target areas where the target user's line of sight is located based on the stay position, and calculate the stay time of the target user's line of sight in the multiple target areas to obtain multiple gaze time values.

[0057] 205. Perform numerical analysis on multiple fixation time values ​​to determine a fixation time threshold;

[0058] Specifically, the server performs numerical analysis on the multiple gaze time values, calculates an average value of the multiple gaze time values, and combines the historical user gaze time values ​​pre-stored in the preset database, performs mean regression processing on the pre-stored historical user gaze time values ​​and the multiple gaze time values, and determines the corresponding gaze time threshold. The gaze time threshold is a gaze time threshold determined after comprehensively considering the multiple gaze times detected in real time and the multiple user gaze time values ​​pre-stored in the database, and is more representative.

[0059] 206. Performing numerical judgment on the multiple gaze time values, if there is at least one first gaze time value greater than or equal to the gaze time threshold, taking a first target area corresponding to the at least one first gaze time value as a key area;

[0060] Specifically, the server performs a numerical judgment on the multiple gaze time values ​​to determine whether there is at least one gaze time value greater than or equal to the gaze time threshold among the multiple gaze time values. If so, the first target area corresponding to the gaze time value greater than or equal to the gaze time threshold is taken as the key area.

[0061] 207. If there is at least one second gaze time value that is less than the gaze time threshold, a second target area corresponding to the at least one second gaze time value is used as a non-key area;

[0062] Specifically, the server performs a numerical judgment on the multiple gaze time values ​​to determine whether there is at least one gaze time value less than the gaze time threshold among the multiple gaze time values, and if so, the second target area corresponding to the gaze time value less than the gaze time threshold is regarded as a non-key area.

[0063] 208. Display processing is performed on the key area and the non-key area to obtain a target dynamic display page.

[0064] Specifically, in this embodiment, the specific implementation of step 208 is similar to the above step 106 and will not be repeated here.

[0065] Optionally, step 208 includes: the server performs highlighting processing on the information content corresponding to the key area; the server performs content folding processing on the information content corresponding to the non-key area to obtain a target dynamic display page.

[0066] Specifically, the server scans the information content of the key areas and the content of the non-key areas, determines the corresponding information content to be processed, and highlights the information content corresponding to the key areas, such as pictures, texts, etc. corresponding to the key areas, folds the content corresponding to the non-key areas, and generates a drop-down selection box. When the user is viewing the page, the user can choose whether to expand the folded content according to the user's wishes.

[0067] In an embodiment of the present invention, after the server collects the eye image of the target user, the server scans the eye image, determines the calibration point of the pupil coordinates in the eyeball of the target user from the eye image, collects the pupil coordinates corresponding to the calibration point through the calibration point, and determines the center coordinates of the spherical surface of the movement trajectory of the pupil according to the characteristics of the pupil movement on the eyeball surface through multiple pupil coordinates, and then determines the gaze point position coordinates of the target user's line of sight on the touch screen of the terminal according to the pupil coordinates and the center coordinates. The position coordinates are marked based on a preset coordinate system of the touch screen of the terminal. The preset coordinate system is in the plane where the touch screen is located, with the lower left corner endpoint of the touch screen as the origin, an X axis is established to the right, and a Y axis is established upward, and the angle between the X axis and the Y axis is 90 degrees. According to the gaze point position coordinates, the user's stay position in the initial page is first determined, and multiple target areas where the user's line of sight is located are determined according to the stay position, and the stay time of the user's line of sight in the multiple target areas is calculated to obtain multiple gaze time values. The server performs numerical analysis on the multiple gaze time values, calculates the average value of the multiple gaze time values, and combines the historical user gaze time values ​​pre-stored in the preset database, performs mean regression processing on the pre-stored historical user gaze time values ​​and the multiple gaze time values, and determines the corresponding gaze time threshold. The gaze time threshold is a gaze time threshold determined after comprehensively considering the multiple gaze times detected in real time and the multiple user gaze time values ​​pre-stored in the database, which is more representative. The server makes a numerical judgment on the multiple gaze time values. It is judged whether there is at least one gaze time value greater than or equal to the gaze time threshold among the multiple gaze time values. If so, the first target area corresponding to the gaze time value greater than or equal to the gaze time threshold is used as the key area. Specifically, the server makes a numerical judgment on the multiple gaze time values.

[0068] It is determined whether there is at least one gaze time value less than the gaze time threshold value among the multiple gaze time values. If so, the second target area corresponding to the gaze time value less than the gaze time threshold value is used as a non-key area. The information content of the key area and the content of the non-key area are scanned to determine the corresponding information content to be processed, and the information content corresponding to the key area, such as pictures, texts and other contents corresponding to the key area, is highlighted, and the content corresponding to the non-key area is folded, and a drop-down selection box is generated. When the user is viewing the page, the user can choose whether to expand the folded content according to the user's wishes. In the embodiment of the present invention, the server collects the user's eye image and calculates the length of time the user's sight stays in the target area, so that the interest range of different users can be more targeted, and the representative gaze time threshold is determined by numerical judgment and analysis of the gaze time value, so that the content of interest to the user can be more effectively confirmed, and the matching accuracy of the content of interest to different users is improved.

[0069] The above describes the method for constructing an intelligent dynamic page in an embodiment of the present invention. The following describes the device for constructing an intelligent dynamic page in an embodiment of the present invention. Figure 3 In one embodiment of the present invention, a device for constructing an intelligent dynamic page includes:

[0070] An acquisition module 3001 is used to acquire an initial page, where the initial page is used to introduce insurance products;

[0071] A division module 3002 is used to divide the initial page into regions based on preset information tags to obtain multiple middle regions;

[0072] The acquisition module 3003 is used to receive an access request sent by a terminal, transmit the initial page to the terminal for display according to the access request, and acquire an eye image of a target user through a front camera of the terminal to obtain multiple eye images of the target user;

[0073] A calculation module 3004 is used to calculate the dwell time of the sight line of the target user in the multiple target areas in sequence based on the multiple eye images and the multiple middle areas to obtain multiple gaze time values;

[0074] A classification module 3005 is used to classify the multiple target areas according to the multiple fixation time values ​​to obtain key areas and non-key areas;

[0075] The processing module 3006 is used to perform display processing on the key area and the non-key area to obtain a target dynamic display page.

[0076] Optionally, the intelligent dynamic page construction device further includes:

[0077] The receiving module 3007 is used to receive a page creation request sent by the page creation terminal;

[0078] An analysis module 3008, configured to analyze the page creation request and determine a plurality of corresponding insurance business topics;

[0079] A determination module 3009, configured to determine corresponding content information through the multiple insurance business topics;

[0080] The transmission module 3010 is used to fill the content information into the preset candidate page to obtain the initial page.

[0081] Optionally, the division module 3002 can also be specifically used to: read the preset information tag to determine the candidate information type corresponding to the preset tag information; understand the content of the initial page through the candidate information type to determine the target information type corresponding to the content information in the initial page; divide the initial page into regions using the target information type to obtain multiple intermediate regions. Optionally, the acquisition module 3003 can also be specifically used to: respond to the access request of the terminal and load the content information of the initial page in the terminal; call the front camera of the terminal to capture the facial image of the target user to obtain multiple facial images; and acquire the eye image of the target user through the multiple facial images to obtain multiple eye images of the target user.

[0082] Optionally, the calculation module 3004 can also be specifically used to: identify multiple eye images of the target user from the multiple eye images, and locate multiple pupil coordinates; calculate multiple gaze point position coordinates of the target user's line of sight on the touch screen of the terminal through the multiple pupil coordinates; determine multiple gaze positions of the target user currently gazing at the touch screen based on the multiple gaze point position coordinates and the position of the front camera on the terminal; determine the corresponding multiple target areas through the multiple gaze positions and the multiple intermediate areas, and calculate the residence time of the target user's line of sight in the multiple target areas in turn to obtain multiple gaze time values.

[0083] Optionally, the classification module 3005 can also be specifically used to: perform numerical analysis on the multiple gaze time values ​​to determine a gaze time threshold; perform numerical judgment on the multiple gaze time values, and if there is at least one first gaze time value greater than or equal to the gaze time threshold, then use the first target area corresponding to the at least one first gaze time value as a key area; if there is at least one second gaze time value less than the gaze time threshold, then use the second target area corresponding to the at least one second gaze time value as a non-key area.

[0084] Optionally, the processing module 3006 may also be specifically used to: highlight the information content corresponding to the key area; and fold the information content corresponding to the non-key area to obtain a target dynamic display page.

[0085] above Figure 3 The apparatus in the embodiment of the present invention is described in detail from the perspective of modular functional entities. The device for constructing an intelligent dynamic page in the embodiment of the present invention is described in detail from the perspective of hardware processing.

[0086] Figure 4 It is a structural schematic diagram of a device for constructing an intelligent dynamic page provided by an embodiment of the present invention. The device 400 for constructing an intelligent dynamic page may have relatively large differences due to different configurations or performances, and may include one or more processors (central processing units, CPU) 410 (for example, one or more processors) and a memory 420, and one or more storage media 430 (for example, one or more massive storage devices) storing application programs 433 or data 432. Among them, the memory 420 and the storage medium 430 can be short-term storage or permanent storage. The program stored in the storage medium 430 may include one or more modules (not shown in the figure), and each module may include a series of instruction operations in the device 400 for constructing an intelligent dynamic page. Furthermore, the processor 410 may be configured to communicate with the storage medium 430 to execute a series of instruction operations in the storage medium 430 on the device 400 for constructing an intelligent dynamic page.

[0087] The intelligent dynamic page construction device 400 may also include one or more power supplies 440, one or more wired or wireless network interfaces 450, one or more input and output interfaces 460, and / or one or more operating systems 431, such as Windows Serve, Mac OS, Uni, Linu, FreeBSD, etc. It will be understood by those skilled in the art that Figure 4The structure of the smart dynamic page construction device shown does not constitute a limitation on the smart dynamic page construction device, and may include more or fewer components than shown in the figure, or a combination of certain components, or a different arrangement of components.

[0088] The present invention also provides a device for constructing an intelligent dynamic page, which includes a memory and a processor. The memory stores computer-readable instructions. When the computer-readable instructions are executed by the processor, the processor executes the steps of the method for constructing the intelligent dynamic page in the above-mentioned embodiments.

[0089] The present invention also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium. Instructions are stored in the computer-readable storage medium. When the instructions are executed on a computer, the computer executes the steps of the method for constructing the intelligent dynamic page.

[0090] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0091] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk and other media that can store program codes.

[0092] The blockchain referred to in this invention is a new application mode of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanism, encryption algorithm, etc. Blockchain is essentially a decentralized database, a string of data blocks generated by cryptographic methods. Each data block contains a batch of network transaction information, which is used to verify the validity of its information (anti-counterfeiting) and generate the next block. Blockchain can include the underlying blockchain platform, platform product service layer, and application service layer.

[0093] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features thereof may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for constructing an intelligent dynamic page, characterized in that: The method for constructing the intelligent dynamic page includes: Obtaining an initial page, where the initial page is used to introduce insurance products; Dividing the initial page into regions based on preset information tags to obtain a plurality of intermediate regions; receiving an access request sent by a terminal, transmitting the initial page to the terminal for display according to the access request, and collecting an eye image of a target user through a front camera of the terminal to obtain multiple eye images of the target user; Based on the multiple eye images and the multiple middle areas, sequentially calculating the time the target user's gaze stays in the multiple target areas to obtain multiple gaze time values; Classifying the multiple target areas according to the multiple fixation time values ​​to obtain key areas and non-key areas; The key area and the non-key area are displayed to highlight the information content corresponding to the key area and to fold the information content corresponding to the non-key area, so as to obtain a target dynamic display page, which also includes a drop-down selection box, and the drop-down selection box is used to expand the folded content.

2. The method for constructing an intelligent dynamic page according to claim 1, characterized in that: Before obtaining the initial page, the method further includes: Receiving a page creation request sent by a page creation terminal; Analyze the page creation request to determine a plurality of corresponding insurance business topics; Determining corresponding content information through the multiple insurance business topics; The content information is filled into the preset candidate page to obtain the initial page.

3. The method for constructing an intelligent dynamic page according to claim 1, characterized in that: The initial page is divided into regions based on the preset information tags to obtain a plurality of intermediate regions including: Reading the preset information tag, and determining the candidate information type corresponding to the preset tag information; Understanding the content of the initial page through the candidate information type, and determining the target information type corresponding to the content information in the initial page; The initial page is divided into regions using the target information type to obtain a plurality of intermediate regions.

4. The method for constructing an intelligent dynamic page according to claim 1, characterized in that: The receiving terminal sends an access request, transmits the initial page to the terminal for display according to the access request, and collects an eye image of the target user through the front camera of the terminal, and obtains multiple eye images of the target user, including: In response to the access request of the terminal, loading the content information of the initial page in the terminal; Invoking the front camera of the terminal to capture the facial image of the target user to obtain multiple facial images; The eye images of the target user are collected through the multiple facial images to obtain multiple eye images of the target user.

5. The method for constructing an intelligent dynamic page according to claim 1, characterized in that: The step of sequentially calculating the dwell time of the target user's sight line in the multiple target areas based on the multiple eye images and the multiple middle areas to obtain multiple gaze time values ​​includes: Identify multiple eyeball images of the target user from the multiple eye images, and locate multiple pupil coordinates; Calculating multiple gaze point position coordinates of the target user's sight on the touch screen of the terminal through the multiple pupil coordinates; Determine, based on the multiple gaze point position coordinates and the position of the front camera on the terminal, multiple gaze positions where the target user is currently gazing at the touch screen; A plurality of corresponding target areas are determined through the plurality of gaze positions and the plurality of intermediate areas, and the dwelling time of the sight lines of the target user in the plurality of target areas is calculated in turn to obtain a plurality of gaze time values.

6. The method for constructing an intelligent dynamic page according to claim 1, characterized in that: The classification of the plurality of target areas according to the plurality of fixation time values ​​to obtain key areas and non-key areas includes: Performing numerical analysis on the multiple fixation time values ​​to determine a fixation time threshold; Performing numerical judgment on the multiple gaze time values, if there is at least one first gaze time value greater than or equal to the gaze time threshold, taking a first target area corresponding to the at least one first gaze time value as a key area; If there is at least one second gaze time value that is smaller than the gaze time threshold, the second target area corresponding to the at least one second gaze time value is taken as a non-key area.

7. The method for constructing an intelligent dynamic page according to any one of claims 1 to 6, characterized in that: The display processing of the key area and the non-key area to obtain a target dynamic display page includes: Highlighting the information content corresponding to the key area; Content folding processing is performed on the information content corresponding to the non-key area to obtain a target dynamic display page.

8. A device for constructing an intelligent dynamic page, characterized in that: The construction device of the intelligent dynamic page includes: An acquisition module, used to acquire an initial page, wherein the initial page is used to introduce insurance products; A division module, used for dividing the initial page into regions based on preset information tags to obtain a plurality of intermediate regions; A collection module, configured to receive an access request sent by a terminal, transmit the initial page to the terminal for display according to the access request, and collect an eye image of a target user through a front camera of the terminal to obtain multiple eye images of the target user; A calculation module, configured to calculate, based on the multiple eye images and the multiple middle areas, the dwell time of the sight line of the target user in the multiple target areas in sequence, to obtain multiple gaze time values; A classification module, used for classifying the multiple target areas according to the multiple fixation time values ​​to obtain key areas and non-key areas; A processing module is used to display the key area and the non-key area, so as to highlight the information content corresponding to the key area and fold the information content corresponding to the non-key area, so as to obtain a target dynamic display page, wherein the target dynamic display page also includes a drop-down selection box, and the drop-down selection box is used to expand the folded content.

9. A device for constructing an intelligent dynamic page, characterized in that: The intelligent dynamic page construction device includes: a memory and at least one processor, wherein the memory stores instructions; The at least one processor calls the instructions in the memory so that the intelligent dynamic page construction device executes the intelligent dynamic page construction method as described in any one of claims 1-7.

10. A computer-readable storage medium having instructions stored thereon, characterized in that: When the instructions are executed by the processor, the method for constructing an intelligent dynamic page as described in any one of claims 1 to 7 is implemented.

Images