Page information recommendation method and device, computer equipment and readable storage medium

Abstract

The invention relates to a page information recommendation method and device, computer equipment, a computer readable storage medium and a computer program product, and can be applied to the field of financial science and technology, the field of Internet of Things or other related fields. The method comprises the following steps: establishing a jump relationship among a plurality of pages by acquiring browsing data of a user, determining a tendency page of the user according to the browsing data under the condition that the user does not meet a misoperation condition according to a prediction model, determining a target page according to the browsing data and the tendency page, and displaying the target page on the user. The page information of the target page is recommended to the user through the jump relation, page information recommendation deviation caused by misoperation of the user can be avoided, the tendency page of the user is determined through the browsing data, then the target page is determined, the prediction accuracy of the target page can be improved, and therefore the response rate is increased.

Description

Technical Field

[0001] This application relates to the field of artificial technology and can be used in the fields of financial technology, Internet of Things, or other related fields. In particular, it relates to a method, device, computer device, and readable storage medium for page information recommendation. Background Art

[0002] With the rapid development of Internet technology, in order to practice the concept of customer-centricity, more and more Internet institutions, financial institutions such as banks, have begun to explore technical methods for displaying mobile banking pages with personalized content for each user. When users enter deep function pages through multiple clicks, the requirements for the "back" button are diverse. Sometimes users hope to return to the home page with one click, and sometimes they hope to return to the previous page. However, currently, most of the back buttons on mobile or web pages are uniformly set to return one by one or return to the home page with one click, unable to meet the personalized needs of customers. Summary of the Invention

[0003] Based on this, in view of the above technical problems, it is necessary to provide a method, device, computer device, and readable storage medium for page information recommendation that can improve the response rate.

[0004] In a first aspect, this application provides a method for page information recommendation, including:

[0005] Obtain the browsing data of the user;

[0006] Establish jump relationships between multiple pages; the multiple pages include all the pages accessed by the user during the process of browsing page information;

[0007] When it is determined according to the prediction model that the user does not meet the misoperation condition, determine the user's preferred page according to the browsing data;

[0008] Determine the target page according to the browsing data and the preferred page, and recommend the page information of the target page to the user through the jump relationship.

[0009] In one of the embodiments, the browsing data includes user portrait data, historical transaction data, eye movement data, and page data; the step of obtaining the browsing data of the user includes:

[0010] Obtain the user portrait data and historical transaction data of the user from the server;

[0011] Collect the eye movement data of the user during the process of browsing page information through a mobile device; the eye movement data includes the browsing area and browsing duration;

[0012] Obtain page data according to the number of clicks and the stay duration of the user during the process of browsing page information.

[0013] In one embodiment, the steps of establishing the jump relationships between multiple pages include:

[0014] Obtain the front-end web page codes of multiple pages;

[0015] Extract the page association information from the front-end web page codes; the page association information includes link address information, button function information, jump logic information, and text content information;

[0016] Match multiple pages according to the page association information to obtain the jump relationships between multiple pages.

[0017] In one embodiment, the steps of determining that the user does not meet the misoperation condition according to the prediction model include:

[0018] Obtain the target vector according to the eye movement data and page data;

[0019] Obtain the operation data of the user during the process of browsing page information; the operation data includes the click area and jump result of the user;

[0020] When it is determined according to the operation data that the current page browsed by the user has changed, set the misoperation label to 1;

[0021] Use the target vector as the independent variable and the misoperation label as the dependent variable to solve the prediction model to obtain the misoperation probability;

[0022] When the misoperation probability is less than the preset probability, determine that the user does not meet the misoperation condition.

[0023] In one embodiment, the steps of determining the user's preferred page according to the browsing data include:

[0024] Divide multiple pages according to the browsing area, and classify all areas according to the area information corresponding to each area to obtain multiple types of areas;

[0025] Obtain the target browsing area corresponding to the longest browsing duration when the current page changes, and determine the target area information corresponding to the target browsing area;

[0026] According to the target area information, respectively obtain the overlap degrees between each previous page accessed by the user during the process of browsing page information and the current page before the current page;

[0027] Take the page corresponding to the highest overlap degree as the user's preferred page.

[0028] In one embodiment, the steps of determining the target page according to the browsing data and the preferred page include:

[0029] Generate an input vector according to the browsing data and the preferred page;

[0030] Use the input vector as the input data of the decision tree model, and output the candidate pages;

[0031] When the candidate pages include at least two pages, determine the user type of the user according to the user profile data;

[0032] Determine the target page according to all the candidate pages corresponding to the users of the user type.

[0033] In one embodiment, recommending the page information of the target page to the user through the jump relationship includes:

[0034] When the user triggers a page jump, jump to the target page through the jump relationship;

[0035] When the target page is a comprehensive page, recommend the preview information in the target page to the user;

[0036] When the target page is a transaction page, recommend the transaction services in the target page to the user.

[0037] In a second aspect, the present application also provides a page information recommendation device, including:

[0038] An acquisition module, configured to acquire the browsing data of the user;

[0039] A building module, configured to build the jump relationship between multiple pages; the multiple pages include all the pages accessed by the user during the process of browsing page information;

[0040] A determination module, configured to determine the tendency page of the user according to the browsing data when it is determined according to the prediction model that the user does not meet the misoperation condition;

[0041] A recommendation module, configured to determine the target page according to the browsing data and the tendency page, and recommend the page information of the target page to the user through the jump relationship.

[0042] In a third aspect, the present application also provides a computer device, including a memory and a processor, where the memory stores a computer program, and when the processor executes the computer program, the method steps of any item in the first aspect are implemented.

[0043] In a fourth aspect, the present application also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the method steps of any item in the first aspect are implemented.

[0044] In a fifth aspect, the present application also provides a computer program product, including a computer program, and when the computer program is executed by a processor, the method steps of any item in the first aspect are implemented.

[0045] The above-mentioned page information recommendation method, device, computer equipment, computer-readable storage medium and computer program product obtain the browsing data of the user, establish the jump relationship between multiple pages, and when it is determined according to the prediction model that the user does not meet the misoperation condition, determine the user's preferred page according to the browsing data, and determine the target page according to the browsing data and the preferred page, and recommend the page information of the target page to the user through the jump relationship, which can avoid the deviation of page information recommendation caused by the user's misoperation. Since the user's preferred page is determined according to the browsing data and then the target page is determined, the prediction accuracy of the target page can be improved, thereby improving the response rate. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following will briefly introduce the drawings required for use in the description of the embodiments of the present application or related technologies. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other related drawings can also be obtained based on these drawings.

[0047] Figure 1 It is an application environment diagram of the page information recommendation method in an embodiment;

[0048] Figure 2 It is a flowchart of the page information recommendation method in an embodiment;

[0049] Figure 3 It is a flowchart of the page information recommendation method in an embodiment;

[0050] Figure 4 It is a structural block diagram of the page information recommendation device in an embodiment;

[0051] Figure 5 It is an internal structure diagram of the computer equipment in an embodiment. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0052] In order to make the purpose, technical solutions and advantages of the present application clearer, the following will further describe the present application in detail with reference to the drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present application and are not used to limit the present application.

[0053] The page information recommendation method provided by the embodiments of the present application can be applied to, for example Figure 1In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or can be placed on the cloud or other network servers. Among them, the terminal 102 is used to obtain the user's browsing data from the server 104, establish the jump relationship between multiple pages, and when it is determined according to the prediction model that the user does not meet the misoperation condition, determine the user's tendency page according to the browsing data, determine the target page according to the browsing data and the tendency page, and recommend the page information of the target page to the user through the jump relationship. Among them, the terminal 102 can be but is not limited to various personal computers, laptop computers, smart phones, tablet computers, Internet of Things devices and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart in-vehicle devices, projection devices, etc. The portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The head-mounted device can be a virtual reality (VR) device, an augmented reality (AR) device, smart glasses, etc. The server 104 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services.

[0054] In an exemplary embodiment, as Figure 2 shown, a method for recommending page information is provided. Taking the method applied to Figure 1 the terminal 102 in it as an example, it includes the following steps 202 to step 208. Among them:

[0055] S202: Obtain the user's browsing data.

[0056] Optionally, the browsing data includes user portrait data, historical transaction data, eye movement data and page data. Among them, the user portrait data and historical transaction data can be obtained from the server, the eye movement data can be collected by the terminal or mobile device. When the user browses the page information, the gazing actions of the user's eyes during the browsing process are collected through the camera of the terminal or mobile device, including but not limited to the browsing area and browsing duration of each page that the user browses, etc. The page data can include the number of clicks and the stay duration of the user during the browsing process.

[0057] S204: Establish the jump relationship between multiple pages; the multiple pages include all the pages accessed by the user during the browsing of the page information.

[0058] Optionally, the jump relationship can be expressed as: Page 1 - Jump - Page 2. By establishing the jump relationship between pages based on all the pages accessed by the user during the process of browsing page information, it is possible to quickly jump to the page that has an associated relationship with the current page. For example, setting Page 1 as the return page of Page 2, when the user triggers the return button, it jumps from Page 2 to Page 1.

[0059] S206: When it is determined according to the prediction model that the user does not meet the misoperation condition, determine the user's preferred page based on the browsing data.

[0060] Optionally, the prediction model is used to detect whether the user's operation is a misoperation, that is, the page triggered by the user for jumping is not the page the user needs. Among them, the prediction model takes eye movement data and operation data as inputs, and outputs the probability of being a misoperation. The operation data refers to the click area and jump result when the user triggers a jump on the current page. For example, the user clicks on a picture on the current page and mistakenly jumps to another page (such as the previous page of the current page). Optionally, the preferred page is the page the user needs. Determine the user's intention at this time based on the browsing data, and then determine the page that the user is more inclined to browse according to the user's intention.

[0061] S208: Determine the target page based on the browsing data and the preferred page, and recommend the page information of the target page to the user through the jump relationship.

[0062] Optionally, the target page is the final page determined based on the preferred page and the browsing data. Among them, the target page is predicted by a decision tree model. The input of the decision tree model is the vector data generated from the browsing data and the preferred page, and the output is the page probability of each predicted page being the target page. The page with the highest page probability is used as the target page. When the user triggers a jump, quickly jump to the target page through the jump relationship between the current page and the target page to recommend the page information of the target page to the user.

[0063] In the above page information recommendation method, by obtaining the user's browsing data, establishing the jump relationship between multiple pages, when it is determined according to the prediction model that the user does not meet the misoperation condition, determining the user's preferred page based on the browsing data, determining the target page based on the browsing data and the preferred page, and recommending the page information of the target page to the user through the jump relationship, it can avoid deviations in page information recommendation caused by user misoperations. Since the user's preferred page is determined based on the browsing data and then the target page is determined, it can improve the prediction accuracy of the target page, thereby improving the response rate.

[0064] In an exemplary embodiment, the browsing data includes user profile data, historical transaction data, eye movement data, and page data; the steps of obtaining the user's browsing data include: obtaining the user's user profile data and historical transaction data from a server; collecting the user's eye movement data during the process of browsing page information through a mobile device; the eye movement data includes the browsing area and the browsing duration; obtaining the page data according to the number of clicks and the staying duration of the user during the process of browsing page information.

[0065] Optionally, taking the financial scenario as an example, the user profile data and historical transactions can be obtained from the information retained by the user in the financial institution. Among them, the user profile data includes the user type of the user, such as whether the user prefers a certain type of information, etc. The eye movement data is collected through the camera of the mobile device or terminal. Taking the user browsing the mobile banking software as an example, when the user triggers the startup of the mobile banking, the terminal calls the front camera to obtain the browsing area of the end user and the browsing duration of this area. It should be noted that the eye movement data is collected after the user's authorization. The page data includes the number of clicks and the staying duration of the user during the process of browsing page information. Among them, the number of clicks can be the number of clicks of various controls (such as buttons, links, etc.) on the page by the user, and the staying duration is the staying duration of the user after clicking the control.

[0066] In this embodiment, by obtaining the user's user profile data, historical transaction data, eye movement data, and page data, the triggering behavior of the user can be accurately identified, providing accurate data support for determining the target page, thereby improving the prediction accuracy of the target page.

[0067] In an exemplary embodiment, the steps of establishing the jump relationship between multiple pages include: obtaining the front-end web page code of multiple pages; extracting the page association information in the front-end web page code; the page association information includes link address information, button function information, jump logic information, and text content information; matching multiple pages according to the page association information to obtain the jump relationship between multiple pages.

[0068] Optionally, the front-end web page code includes but is not limited to the hypertext markup language (HTML), cascading style sheets (CSS), and scripting language (PHP) codes of the page. By extracting information from the front-end web page code, the page association information in the front-end web page code is obtained. Among them, the page association information includes but is not limited to link address information, button function information, jump logic information, and text content information, etc.

[0069] Further, regarding the page as an entity, entity extraction, relationship extraction, and attribute extraction are performed on the page association information to identify the words or phrases representing entities in the text, as well as the attribute information of the entities, so as to extract the association relationships between entities, associate the pages with each other, and obtain the jump relationships between pages. Among them, the jump relationship can be understood as the hyperlink relationship between pages. When page 1 contains a hyperlink pointing to page 2, a connection relationship can be established between page 1 and page 2. This connection relationship can be one-way, that is, page 1 points to page 2, or it can be two-way, that is, page 1 and page 2 point to each other.

[0070] In this embodiment, by extracting the page association information of the page and matching multiple pages according to the page association information, the jump relationships between multiple pages are obtained, and the jump operation triggered by the user can be quickly responded to, and the page required by the user can be jumped to.

[0071] In an exemplary embodiment, the steps of determining that the user does not meet the misoperation condition according to the prediction model include: obtaining a target vector according to the eye movement data and page data; obtaining the operation data of the user during the process of browsing the page information; the operation data includes the click area and jump result of the user; in the case of determining that the current page browsed by the user changes according to the operation data, setting the misoperation label to 1; using the target vector as the independent variable and the misoperation label as the dependent variable, solving the prediction model to obtain the misoperation probability; in the case where the misoperation probability is less than the preset probability, determining that the user does not meet the misoperation condition.

[0072] Optionally, the eye movement data and page data of the user are used as inputs, expressed in the form of an n-dimensional vector, as the independent variable of the prediction model. The jump result is the jump page triggered by the click area of the user on the current page. For example, if the user returns to the previous page within a preset time after clicking on a certain picture on the current page, it is considered that a misoperation has occurred at this time, and the misoperation label is set to 1, otherwise it is set to 0. Further, the misoperation label is used as the dependent variable of the prediction model. The input target vector is mapped into a data between 0 and 1 through the prediction model, and the parameters are solved by the maximum likelihood estimation method or the cross-entropy loss function to obtain the probability that the user's current operation is a misoperation. When the misoperation probability is small, it is determined that the user is not operating by mistake.

[0073] In this embodiment, by using the eye movement data and page data to determine whether the user's current operation is a misoperation, it is possible to avoid deviations in page information recommendation caused by the user's misoperation, thereby improving the prediction accuracy of the target page.

[0074] In an exemplary embodiment, the step of determining a user's propensity page according to browsing data includes: dividing multiple pages into regions according to the browsing area, classifying all regions according to the region information corresponding to each region to obtain multiple types of regions; obtaining a target browsing region corresponding to the longest browsing duration when the current page changes, and determining target region information corresponding to the target browsing region; according to the target region information, respectively obtaining the overlap degree between each pre-page accessed by the user during the process of browsing page information and the current page before the current page; and taking the page with the highest overlap degree as the user's propensity page.

[0075] Optionally, the pages are divided into regions according to the user's eye movement data on the same page, and the regions are classified according to the information type and text information of each region. Each type of region can be considered to correspond to a type of region information. Taking the financial field as an example, the region information may include income information, risk information, term information, price information, etc. When the user triggers a jump and the current page changes, obtain the target browsing region with the longest browsing duration before the trigger.

[0076] Further, according to the target region information of the target browsing region, match the overlap degree between each page before the current page and the current page, where the overlap degree includes the information overlap degree and the advantage degree. The information overlap degree refers to the number of region information of each region in the pre-page that matches the target region information of the current page. If there is a region in the pre-page whose region information matches the target region information of the current page, the information overlap degree is set to 1, and so on. The advantage degree refers to the priority degree of different types of region information. Compare the refined information of the target region information of the current page with the region information in the pre-page. If the refined information of the pre-page has a higher priority degree, the advantage degree is set to 1. By normalizing the information overlap degree and the advantage degree, obtain the final overlap degree, and take the page with the highest overlap degree as the user's propensity page.

[0077] Specifically, taking the financial field as an example, assume that the user's browsing path is home page - investment - wealth management - wealth management list page - product 1 details page. At this time, the user clicks back. First, determine the target region information that the user browsed before clicking the back button on the page. For example, the yield rate of the product 1 details page that the user is concerned about, obtain the specific value of this indicator, and analyze whether there are the same regions in all the pre-pages of this page. Among them, the investment page, the wealth management page, and the wealth management list page all have product income information and display the yield rate value. Among them, the yield rates of the 2 fund products displayed on the investment page are higher. Then the possible pages to return to are the home page, investment, wealth management, and wealth management list page, and the scores are (0, 2, 1, 1). After normalization, the scores are (0, 1, 0.5, 0.5).

[0078] In this embodiment, by dividing multiple pages according to the browsing area, and determining the overlapping degree between each pre-page and the current page according to the area information corresponding to each area, and taking the page corresponding to the highest overlapping degree as the user's preferred page, the accuracy of the preferred page can be improved, thereby improving the prediction accuracy of the target page.

[0079] In an exemplary embodiment, the steps of determining the target page according to the browsing data and the preferred page include: generating an input vector according to the browsing data and the preferred page; using the input vector as the input data of the decision tree model to output candidate pages; in the case where the candidate pages include at least two pages, determining the user type of the user according to the user portrait data; and determining the target page according to the candidate pages corresponding to all users of the user type.

[0080] Optionally, represent the browsing data and the preferred page as an m-dimensional vector and use it as the input data of the prediction tree model. The output of the decision tree model is the candidate page. If there is only one page, use this page as the target page. If there are at least two pages, determine the user type of the user according to the user portrait data, and use the candidate page corresponding to the user with the largest number under the current user type as the target page.

[0081] In this embodiment, by generating an input vector according to the browsing data and the preferred page, and outputting the predicted candidate pages through the decision tree model, and then determining the target page, the prediction accuracy of the target page can be improved, thereby improving the response rate.

[0082] In one of the embodiments, the page information of the target page recommended to the user through the jump relationship includes: in the case where the user triggers a page jump, jumping to the target page through the jump relationship; in the case where the target page is a comprehensive page, recommending the preview information in the target page to the user; in the case where the target page is a transaction page, recommending the transaction service in the target page to the user.

[0083] Optionally, when the user triggers a page jump through the terminal, the terminal directly jumps to the target page through the jump relationship, and recommends different types of page information to the user according to the page attribute of the target page. For example, when the target page is a comprehensive page (i.e., an overview page or a menu page), the page information recommended to the user is the preview information. When the target page is a transaction page (i.e., a page for handling transaction services), the page information recommended to the user is the transaction service, such as purchasing a deposit, etc. In addition, the page hierarchy of the target page can also be displayed to the user. The page hierarchy refers to how many levels the user drills down from entering the terminal to reach this page.

[0084] In this embodiment, when the user triggers a page jump, the target page is jumped to through the jump relationship. According to the page attributes of the target page, different types of page information can be recommended to the user in a targeted manner, thereby improving the prediction accuracy of the target page.

[0085] In an exemplary embodiment, as Figure 3 shown, a page information recommendation method is provided, and the method includes the following steps:

[0086] Obtain the user portrait data and historical transaction data of the user from the server; collect the eye movement data of the user during the process of browsing page information through a mobile device; the eye movement data includes the browsing area and the browsing duration; obtain the page data according to the number of clicks and the stay duration of the user during the process of browsing page information.

[0087] Obtain the front-end web page codes of multiple pages; extract the page association information in the front-end web page codes; the page association information includes link address information, button function information, jump logic information, and text content information; match the multiple pages according to the page association information to obtain the jump relationships between the multiple pages.

[0088] Among them, the multiple pages include all the pages accessed by the user during the process of browsing page information.

[0089] Obtain the target vector according to the eye movement data and the page data; obtain the operation data of the user during the process of browsing page information; the operation data includes the click area and the jump result of the user; when it is determined according to the operation data that the currently browsed page of the user has changed, set the misoperation label to 1; use the target vector as the independent variable and the misoperation label as the dependent variable to solve the prediction model to obtain the misoperation probability; when the misoperation probability is less than the preset probability, determine that the user does not meet the misoperation condition.

[0090] When it is determined according to the prediction model that the user does not meet the misoperation condition, divide the multiple pages into regions according to the browsing area, classify all regions according to the region information corresponding to each region to obtain multiple types of regions; obtain the target browsing area corresponding to the longest browsing duration when the current page changes, and determine the target region information corresponding to the target browsing area; according to the target region information, respectively obtain the overlapping degrees between each previous page accessed by the user during the process of browsing page information and the current page before the current page; use the page with the highest overlapping degree as the user's preferred page.

[0091] Generate an input vector based on browsing data and a propensity page; use the input vector as input data for a decision tree model to output candidate pages; in the case where the candidate pages include at least two pages, determine the user type of the user according to user portrait data; determine a target page according to the candidate pages corresponding to all users of the user type.

[0092] In the case where the user triggers a page jump, jump to the target page through the jump relationship; in the case where the target page is a comprehensive page, recommend preview information in the target page to the user; in the case where the target page is a transaction page, recommend transaction services in the target page to the user.

[0093] In this embodiment, by obtaining the browsing data of the user, establishing jump relationships between multiple pages, in the case where it is determined according to the prediction model that the user does not meet the misoperation condition, determining the propensity page of the user according to the browsing data, determining the target page according to the browsing data and the propensity page, and recommending the page information of the target page to the user through the jump relationship, it is possible to avoid deviations in page information recommendation caused by user misoperations. Since the propensity page of the user is determined according to the browsing data and then the target page is determined, the prediction accuracy of the target page can be improved, thereby improving the response rate.

[0094] It should be understood that although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be executed alternately or alternately with at least a part of other steps or steps or stages in other steps.

[0095] Based on the same inventive concept, an embodiment of the present application also provides a page information recommendation device for implementing the page information recommendation method involved above. The implementation solutions provided by this device to solve problems are similar to the implementation solutions described in the above method. Therefore, the specific limitations in one or more embodiments of the page information recommendation device provided below can refer to the limitations on the page information recommendation method in the above text, and will not be repeated here.

[0096] In an exemplary embodiment, as Figure 4 shown, a page information recommendation device is provided, including: an acquisition module 10, a establishment module 20, a determination module 30, and a recommendation module 40, where:

[0097] An acquisition module 10 for acquiring the browsing data of a user.

[0098] A building module 20 for building the jump relationships between multiple pages; the multiple pages include all the pages accessed by the user during the process of browsing page information.

[0099] A determination module 30 for determining the tendency page of the user according to the browsing data when it is determined according to a prediction model that the user does not meet the misoperation condition.

[0100] A recommendation module 40 for determining a target page according to the browsing data and the tendency page, and recommending the page information of the target page to the user through the jump relationship.

[0101] In an exemplary embodiment, the browsing data includes user portrait data, historical transaction data, eye movement data, and page data; the acquisition module 10 is further configured to acquire the user portrait data and historical transaction data of the user from a server; collect the eye movement data of the user during the process of browsing page information through a mobile device; the eye movement data includes a browsing area and a browsing duration; and acquire the page data according to the number of clicks and the stay duration of the user during the process of browsing page information.

[0102] In an exemplary embodiment, the building module 20 is further configured to acquire the front-end web page codes of multiple pages; extract the page association information in the front-end web page codes; the page association information includes link address information, button function information, jump logic information, and text content information; and match the multiple pages according to the page association information to obtain the jump relationships between the multiple pages.

[0103] In an exemplary embodiment, the determination module 30 is further configured to obtain a target vector according to the eye movement data and the page data; acquire the operation data of the user during the process of browsing page information; the operation data includes the click area and the jump result of the user; when it is determined according to the operation data that the currently browsed page of the user changes, set the misoperation label to 1; use the target vector as an independent variable and the misoperation label as a dependent variable to solve the prediction model to obtain a misoperation probability; and determine that the user does not meet the misoperation condition when the misoperation probability is less than a preset probability.

[0104] In an exemplary embodiment, the determination module 30 is further configured to divide multiple pages according to the browsing area, classify all areas according to the area information corresponding to each area to obtain multiple types of areas; obtain the target browsing area corresponding to the longest browsing duration when the current page changes, and determine the target area information corresponding to the target browsing area; according to the target area information, respectively obtain the overlap degree between each pre-page accessed by the user during the browsing of page information and the current page before the current page; and use the page with the highest overlap degree as the user's preferred page.

[0105] In an exemplary embodiment, the recommendation module 40 is further configured to generate an input vector according to the browsing data and the preferred page; use the input vector as the input data of the decision tree model, and output to obtain candidate pages; in the case where the candidate pages include at least two pages, determine the user type of the user according to the user portrait data; and determine the target page according to all the candidate pages corresponding to the users of the user type.

[0106] In an exemplary embodiment, the recommendation module 40 is further configured to, when the user triggers a page jump, jump to the target page through the jump relationship; in the case where the target page is a comprehensive page, recommend the preview information in the target page to the user; and in the case where the target page is a transaction page, recommend the transaction service in the target page to the user.

[0107] Each module in the above page information recommendation device can be implemented in whole or in part by software, hardware, and their combination. The above modules can be embedded in the processor of the computer device in hardware form or be independent of it, or be stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to the above respective modules.

[0108] In an exemplary embodiment, a computer device is provided. The computer device can be a terminal, and its internal structure diagram can be as Figure 5As shown in the figure. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit, and an input device. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface, the display unit, and the input device are connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, near field communication (NFC), or other technologies. When the computer program is executed by the processor, it implements a method for recommending page information. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer covered on the display screen, or a button, a trackball, or a touchpad provided on the computer device housing, or an external keyboard, touchpad, or mouse, etc.

[0109] Those skilled in the art can understand that Figure 5 the structure shown in the figure is only a block diagram of some structures related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0110] In an exemplary embodiment, a computer device is provided, including a memory and a processor. A computer program is stored in the memory. When the processor executes the computer program, the following steps are implemented: obtaining the browsing data of the user; establishing the jump relationship between multiple pages; the multiple pages include all the pages accessed by the user during the process of browsing page information; when it is determined according to the prediction model that the user does not meet the misoperation condition, determining the tendency page of the user according to the browsing data; determining the target page according to the browsing data and the tendency page, and recommending the page information of the target page to the user through the jump relationship.

[0111] In one embodiment, the browsing data includes user profile data, historical transaction data, eye movement data, and page data; obtaining the user's browsing data when the processor executes the computer program includes: obtaining the user's user profile data and historical transaction data from the server; collecting the eye movement data of the user during the process of browsing page information through a mobile device; the eye movement data includes the browsing area and the browsing duration; obtaining the page data according to the number of clicks and the stay duration of the user during the process of browsing page information.

[0112] In one embodiment, establishing the jump relationship between multiple pages when the processor executes the computer program includes: obtaining the front-end web page code of multiple pages; extracting the page association information in the front-end web page code; the page association information includes link address information, button function information, jump logic information, and text content information; matching multiple pages according to the page association information to obtain the jump relationship between multiple pages.

[0113] In one embodiment, determining that the user does not meet the misoperation condition when the processor executes the computer program includes: obtaining the target vector according to the eye movement data and the page data; obtaining the operation data of the user during the process of browsing page information; the operation data includes the click area and the jump result of the user; when it is determined according to the operation data that the current page browsed by the user has changed, setting the misoperation label to 1; using the target vector as the independent variable and the misoperation label as the dependent variable to solve the prediction model to obtain the misoperation probability; when the misoperation probability is less than the preset probability, determining that the user does not meet the misoperation condition.

[0114] In one embodiment, determining the user's preferred page according to the browsing data when the processor executes the computer program includes: dividing multiple pages into regions according to the browsing area, classifying all regions according to the region information corresponding to each region to obtain multiple types of regions; obtaining the target browsing region corresponding to the longest browsing duration when the current page changes, and determining the target region information corresponding to the target browsing region; respectively obtaining the overlap degree between each pre-page accessed by the user and the current page before the current page according to the target region information; using the page with the highest overlap degree as the user's preferred page.

[0115] In one embodiment, determining the target page according to the browsing data and the preferred page when the processor executes the computer program includes: generating an input vector according to the browsing data and the preferred page; using the input vector as the input data of the decision tree model and outputting the candidate pages; when there are at least two candidate pages, determining the user type of the user according to the user profile data; determining the target page according to all the candidate pages corresponding to the users of the user type.

[0116] In one embodiment, the page information for recommending a target page to a user through a jump relationship when the processor executes a computer program includes: when the user triggers a page jump, jumping to the target page through the jump relationship; when the target page is a comprehensive page, recommending preview information in the target page to the user; when the target page is a transaction page, recommending transaction services in the target page to the user.

[0117] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented: obtaining browsing data of a user; establishing jump relationships between multiple pages; the multiple pages include all pages accessed by the user during the process of browsing page information; when it is determined according to a prediction model that the user does not meet the misoperation condition, determining the user's inclined page according to the browsing data; determining a target page according to the browsing data and the inclined page, and recommending the page information of the target page to the user through the jump relationship.

[0118] In one embodiment, the browsing data includes user portrait data, historical transaction data, eye movement data, and page data; obtaining the browsing data of the user when the computer program is executed by the processor includes: obtaining the user portrait data and historical transaction data of the user from a server; collecting eye movement data of the user during the process of browsing page information through a mobile device; the eye movement data includes a browsing area and a browsing duration; obtaining page data according to the number of clicks and the stay duration of the user during the process of browsing page information.

[0119] In one embodiment, establishing jump relationships between multiple pages when the computer program is executed by the processor includes: obtaining the front-end web page code of the multiple pages; extracting page association information from the front-end web page code; the page association information includes link address information, button function information, jump logic information, and text content information; matching the multiple pages according to the page association information to obtain jump relationships between the multiple pages.

[0120] In one embodiment, determining that the user does not meet the misoperation condition according to a prediction model when the computer program is executed by the processor includes: obtaining a target vector according to the eye movement data and the page data; obtaining operation data of the user during the process of browsing page information; the operation data includes the click area and the jump result of the user; when it is determined according to the operation data that the current page browsed by the user changes, setting the misoperation label to 1; using the target vector as an independent variable and the misoperation label as a dependent variable to solve the prediction model to obtain a misoperation probability; when the misoperation probability is less than a preset probability, determining that the user does not meet the misoperation condition.

[0121] In one embodiment, when the computer program is executed by a processor, determining a user's preferred page based on browsing data includes: dividing multiple pages into regions according to the browsing area, classifying all regions according to the region information corresponding to each region to obtain multiple types of regions; obtaining a target browsing region corresponding to the longest browsing duration when the current page changes, and determining target region information corresponding to the target browsing region; according to the target region information, respectively obtaining the overlap degree between each previous page accessed by the user during the process of browsing page information and the current page before the current page; and taking the page with the highest overlap degree as the user's preferred page.

[0122] In one embodiment, when the computer program is executed by a processor, determining a target page based on browsing data and a preferred page includes: generating an input vector based on the browsing data and the preferred page; using the input vector as input data of a decision tree model to output candidate pages; in the case where the candidate pages include at least two pages, determining the user type of the user according to the user portrait data; and determining the target page according to the candidate pages corresponding to all users of the user type.

[0123] In one embodiment, when the computer program is executed by a processor, recommending page information of a target page to a user through a jump relationship includes: in the case where the user triggers a page jump, jumping to the target page through the jump relationship; in the case where the target page is a comprehensive page, recommending preview information in the target page to the user; and in the case where the target page is a transaction page, recommending transaction services in the target page to the user.

[0124] In one embodiment, there is provided a computer program product including a computer program, which when executed by a processor implements the following steps: obtaining the browsing data of a user; establishing a jump relationship between multiple pages, where the multiple pages include all pages accessed by the user during the process of browsing page information; in the case where it is determined according to a prediction model that the user does not meet the misoperation condition, determining the user's preferred page according to the browsing data; determining the target page according to the browsing data and the preferred page, and recommending page information of the target page to the user through the jump relationship.

[0125] In one embodiment, the browsing data includes user portrait data, historical transaction data, eye movement data, and page data; when the computer program is executed by a processor, obtaining the browsing data of a user includes: obtaining the user portrait data and historical transaction data of the user from a server; collecting the eye movement data of the user during the process of browsing page information through a mobile device, where the eye movement data includes a browsing area and a browsing duration; and obtaining page data according to the number of clicks and the stay duration of the user during the process of browsing page information.

[0126] In one embodiment, establishing the jump relationships among multiple pages when the computer program is executed by a processor includes: obtaining the front-end web page codes of multiple pages; extracting the page association information from the front-end web page codes; the page association information includes link address information, button function information, jump logic information, and text content information; and matching the multiple pages according to the page association information to obtain the jump relationships among the multiple pages.

[0127] In one embodiment, determining that the user does not meet the misoperation condition according to a prediction model when the computer program is executed by a processor includes: obtaining a target vector according to the eye movement data and page data; obtaining the operation data of the user during the process of browsing the page information; the operation data includes the click area and jump result of the user; when it is determined according to the operation data that the current page browsed by the user has changed, setting the misoperation label to 1; using the target vector as the independent variable and the misoperation label as the dependent variable to solve the prediction model to obtain the misoperation probability; and determining that the user does not meet the misoperation condition when the misoperation probability is less than the preset probability.

[0128] In one embodiment, determining the user's preferred page according to the browsing data when the computer program is executed by a processor includes: dividing multiple pages into regions according to the browsing region, classifying all regions according to the region information corresponding to each region to obtain multiple types of regions; obtaining the target browsing region corresponding to the longest browsing duration when the current page changes, and determining the target region information corresponding to the target browsing region; according to the target region information, respectively obtaining the overlapping degree between each pre-page accessed by the user during the process of browsing the page information and the current page before the current page; and taking the page with the highest overlapping degree as the user's preferred page.

[0129] In one embodiment, determining the target page according to the browsing data and the preferred page when the computer program is executed by a processor includes: generating an input vector according to the browsing data and the preferred page; using the input vector as the input data of the decision tree model and outputting to obtain candidate pages; when the candidate pages include at least two pages, determining the user type of the user according to the user portrait data; and determining the target page according to all the candidate pages corresponding to the users of the user type.

[0130] In one embodiment, recommending the page information of the target page to the user through the jump relationship when the computer program is executed by a processor includes: when the user triggers a page jump, jumping to the target page through the jump relationship; when the target page is a comprehensive page, recommending the preview information in the target page to the user; and when the target page is a transaction page, recommending the transaction service in the target page to the user.

[0131] It should be noted that the user information (including but not limited to user browsing data, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use, and processing of relevant data need to comply with relevant regulations.

[0132] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided in this application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., and are not limited thereto. The processors involved in the embodiments provided in this application can be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, data processing logics based on quantum computing, artificial intelligence (AI) processors, etc., and are not limited thereto.

[0133] The technical features of the above embodiments can be combined arbitrarily. For the sake of concise description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope recorded in this application.

[0134] The above-described embodiments merely represent several implementation manners of this application. The description is relatively specific and detailed, but it should not be construed as a limitation on the patent scope of this application. It should be noted that for those of ordinary skill in the art, without departing from the concept of this application, several modifications and improvements can still be made, and these all belong to the protection scope of this application. Therefore, the protection scope of this application should be subject to the appended claims.

Claims

1. A method for recommending page information, characterized in that, The method includes: Obtaining the browsing data of the user; Establishing the jump relationships between multiple pages; the multiple pages include all the pages accessed by the user during the process of browsing page information; When it is determined according to the prediction model that the user does not meet the misoperation condition, determining the tendency page of the user according to the browsing data; Determining the target page according to the browsing data and the tendency page, and recommending the page information of the target page to the user through the jump relationships.

2. The method according to claim 1, wherein The browsing data includes user portrait data, historical transaction data, eye movement data, and page data; the obtaining of the browsing data of the user includes: Obtaining the user portrait data and historical transaction data of the user from the server; Collecting the eye movement data of the user during the process of browsing page information through a mobile device; the eye movement data includes the browsing area and the browsing duration; Obtaining page data according to the number of clicks and the stay duration of the user during the process of browsing page information.

3. The method according to claim 1, characterized in that, The establishing of the jump relationships between multiple pages includes: Obtaining the front-end web page codes of multiple pages; Extracting the page association information in the front-end web page codes; the page association information includes link address information, button function information, jump logic information, and text content information; Matching the multiple pages according to the page association information to obtain the jump relationships between the multiple pages.

4. The method according to claim 2, characterized in that, The determining that the user does not meet the misoperation condition according to the prediction model includes: Obtaining a target vector according to the eye movement data and the page data; Obtaining the operation data of the user during the process of browsing page information; the operation data includes the click area and the jump result of the user; When it is determined according to the operation data that the currently browsed page of the user has changed, setting the misoperation label to 1; Using the target vector as the independent variable and the misoperation label as the dependent variable to solve the prediction model to obtain the misoperation probability; When the misoperation probability is less than the preset probability, determining that the user does not meet the misoperation condition.

5. The method according to claim 4, wherein The determining of the tendency page of the user according to the browsing data includes: Dividing the multiple pages according to the browsing area, classifying all the areas according to the area information corresponding to each area to obtain multiple types of areas; Obtaining the target browsing area corresponding to the longest browsing duration when the currently browsed page changes, and determining the target area information corresponding to the target browsing area; According to the target area information, respectively obtaining the overlapping degrees between each pre-page accessed by the user before the current page and the current page during the process of browsing page information; Taking the page corresponding to the highest overlapping degree as the tendency page of the user.

6. The method according to claim 1, wherein The determining of the target page according to the browsing data and the tendency page includes: Generating an input vector according to the browsing data and the tendency page; Using the input vector as the input data of the decision tree model and outputting to obtain candidate pages; When the candidate pages include at least two pages, determining the user type of the user according to the user portrait data; Determine a target page based on all candidate pages corresponding to all users of the corresponding user type.

7. The method according to claim 1, wherein The page information for recommending the target page to the user through the jump relationship includes: In the case where the user triggers a page jump, jump to the target page through the jump relationship; In the case where the target page is a comprehensive page, recommend the preview information in the target page to the user; In the case where the target page is a transaction page, recommend the transaction service in the target page to the user.

8. A page information recommendation device, characterized in that, The device includes: An acquisition module for acquiring the browsing data of the user; A building module for building a jump relationship between multiple pages; the multiple pages include all pages accessed by the user during the process of browsing page information; A determination module for determining the tendency page of the user according to the browsing data in the case where it is determined according to the prediction model that the user does not meet the misoperation condition; A recommendation module for determining a target page according to the browsing data and the tendency page, and recommending the page information of the target page to the user through the jump relationship.

9. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images