WO2020200146A1

WO2020200146A1 - Page information processing method, device, and electronic apparatus

Info

Publication number: WO2020200146A1
Application number: PCT/CN2020/081985
Authority: WO
Inventors: 杨鑫; 郑瑶琳; 王威
Original assignee: 阿里巴巴集团控股有限公司
Priority date: 2019-04-04
Filing date: 2020-03-30
Publication date: 2020-10-08
Also published as: CN111782918A

Abstract

A page information processing method, a device, and an electronic apparatus. The method comprises: acquiring data related to a user during a process of displaying a target page (S201); providing information of the target page and the acquired data to a prediction algorithm model configured at a terminal apparatus at which a client is located, so as to predict user points-of-interest information of the target page (S202); obtaining a prediction result returned by the prediction algorithm model (S203); and when a target event is triggered, determining, according to the prediction result, an adjustment scheme for display contents of the target page, and re-rendering and refreshing display of the target page according to the adjustment scheme (S204). The method facilitates exposure of content in which a user finds more interesting, thereby improving the efficiency of a display page, and enhancing user experience.

Description

Page information processing method, device and electronic equipment

This application claims the priority of the Chinese patent application with the application number 201910273123.5 and the invention title of "page information processing method, device and electronic equipment" filed on April 4, 2019, the entire content of which is incorporated into this application by reference.

Technical field

This application relates to the technical field of page information processing, in particular to page information processing methods, devices and electronic equipment.

Background technique

In the network service system, the page is an important tool for conveying various information to the user. For example, in the product object information service system, the recommended information such as "guess you like" on the homepage of the client, the product object information on the homepage of the store, There will be content displayed in the form of a list on the event homepage, search result page, etc. A list page often includes many list items. For example, in a search result page, a search returns 20 results. Through this kind of aggregated display of multiple list items on the same page, users can obtain multiple contents through one page, and users can select the list items of interest from them, and view their detailed pages by clicking, etc.

On the other hand, with the popularity of mobile terminals, most of the traffic is transferred to mobile terminal devices. However, due to the limited screen size of the mobile terminal, the list items that can be displayed at one time are usually very limited, otherwise the recognition of the content displayed in the list items may be affected. For example, for a search result page, only 4 of the list items may be displayed on each screen, and other list items need to be viewed by sliding the screen. However, most of the user's browsing behavior is concentrated on the first few pages. Therefore, for the list items that are ranked relatively low, the entire page is usually closed or exited before the exposure opportunity has been obtained, so that the user may be Lost the opportunity to obtain more interesting information.

Therefore, how to provide users with content that is more in line with user needs or points of interest becomes a technical problem that needs to be solved by those skilled in the art.

Summary of the invention

This application provides page information processing methods, devices, and electronic equipment, which are beneficial to exposing more interesting content to users, improving page display efficiency, and enhancing user experience.

This application provides the following solutions:

A method for processing page information, including:

In the process of displaying the target page, collect user-related data;

Providing the information of the target page and the collected data to a prediction algorithm model set on the terminal device where the client is located, so as to predict the user's point of interest information on the target page;

Obtaining the prediction result returned by the prediction algorithm model;

Under the trigger of the target event, an adjustment scheme for the display content of the target page is determined according to the prediction result, and the target page is re-rendered and refreshed according to the adjustment scheme.

A method for processing page information, including:

The client collects user-related data in the process of displaying the target page;

According to the collected data, predict the user's point of interest information on the target page;

A method for processing product object search result information, including:

The client submits search keyword information to the server;

Receiving page data of a search result page returned by the server, where the search result page includes multiple product object information;

Displaying the search result page according to the page data, and collecting user behavior data generated by the user for the search result page;

Predict the point of interest information of the user according to the collected user behavior data;

Under the trigger of the target event, it is determined according to the prediction result to adjust the page content display scheme of the search result page, and the search result page is re-rendered and refreshed according to the adjusted scheme.

A page information processing device, including:

The data collection unit is used to collect user-related data in the process of displaying the target page;

The data providing unit is used to provide the information of the target page and the collected data to the prediction algorithm model of the terminal device where the client is located, so as to predict the user's interest point information on the target page ；

A prediction result obtaining unit, configured to obtain the prediction result returned by the prediction algorithm model;

The display scheme adjustment unit is configured to determine an adjustment scheme for the display content of the target page according to the prediction result when triggered by a target event, and re-render and refresh the display of the target page according to the adjustment scheme.

A page information processing device, including:

A prediction unit, configured to predict the user’s point of interest information on the target page according to the collected data;

The scheme adjustment unit is configured to determine an adjustment scheme for the display content of the target page according to the prediction result when triggered by a target event, and re-render and refresh the display of the target page according to the adjustment scheme.

A product object search result information processing device, including:

The keyword submission unit is used to submit search keyword information to the server;

The page data receiving unit is configured to receive page data of the search result page returned by the server, where the search result page includes multiple product object information;

A data collection unit, configured to display the search result page according to the page data, and collect user behavior data generated by the user for the search result page;

A prediction unit, configured to predict the point of interest information of the user according to the collected user behavior data;

The scheme adjustment unit is configured to determine, according to the prediction result, to adjust the page content display scheme of the search result page under the trigger of the target event, and re-render and refresh the display of the search result page according to the adjusted scheme.

An electronic device including:

One or more processors; and

A memory associated with the one or more processors, where the memory is used to store program instructions, and when the program instructions are read and executed by the one or more processors, perform the following operations:

In the process of displaying the target page, collect user-related data;

Obtaining the prediction result returned by the prediction algorithm model;

An electronic device including:

One or more processors; and

In the process of displaying the target page, collect user-related data;

An electronic device including:

One or more processors; and

Submit search keyword information to the server;

According to the specific embodiments provided in this application, this application discloses the following technical effects:

Through the embodiments of this application, user-related information can be collected during the process of displaying the target page, which can mainly include some real-time behavior data or surrounding environment information, etc., and can be directly on the client side. Analyze and calculate the collected data to predict the user's possible points of interest at the moment. Further, the display scheme of the page content in the page can be adjusted under the trigger of a specific event, and the page content can be re-rendered and refreshed. In this way, the display scheme of the page content can be adjusted with the collected user-related data, instead of displaying according to the fixed scheme provided by the server. Therefore, it is conducive to exposing more interesting content to users and improving The page display efficiency also improves user experience.

Of course, implementing any product of this application does not necessarily need to achieve all the advantages described above at the same time.

Description of the drawings

In order to explain the embodiments of the present application or the technical solutions in the prior art more clearly, the following will briefly introduce the drawings needed in the embodiments. Obviously, the drawings in the following description are only some of the present application. Embodiments, for those of ordinary skill in the art, without creative work, other drawings can be obtained from these drawings.

Figure 1 is a schematic diagram of a system architecture provided by an embodiment of the present application;

Figure 2 is a flowchart of the first method provided by an embodiment of the present application;

Figures 3-1 to 3-4 are schematic diagrams of interfaces provided by embodiments of the present application;

Figure 4 is a flowchart of a second method provided by an embodiment of the present application;

FIG. 5 is a flowchart of a third method provided by an embodiment of the present application;

FIG. 6 is a schematic diagram of a first device provided by an embodiment of the present application;

Figure 7 is a schematic diagram of a second device provided by an embodiment of the present application;

FIG. 8 is a schematic diagram of a third device provided by an embodiment of the present application;

Fig. 9 is a schematic diagram of an electronic device provided by an embodiment of the present application.

detailed description

The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art fall within the protection scope of this application.

The first thing to note is that in the traditional page display process, the user initiates a request to access a certain page by clicking on a related link in the client, and the client needs to submit the request to the server, and the server returns the specific The page data is then rendered and displayed on the client side. Among them, more and more pages can provide users with a "thousand-thousand-thousand-face" display method. For example, for the homepage of a certain client, different users may display different content when viewing the page. Or, for the same search for a certain keyword, the content displayed on the search result page obtained by different users may be different, and so on. This is because the server usually saves the user’s gender, age, historical access records, behavioral preferences and other information. When a specific page is displayed to a user, the page content can be analyzed based on the personalized information of these users. Personalized adjustments in order to make the displayed content more in line with the needs of users.

This prior art method can indeed help users to obtain content that meets their needs to a certain extent, but the information recorded by the server is usually only the user's personal data, historical records, or user preferences based on historical records. ; And, what content is displayed on the page, and how the content is arranged and laid out are all determined by the server. After the server returns the specific page data to the client, what the client can do The only thing is to render and display according to specific page data.

In practical applications, some users’ points of interest and other information may be generated temporarily, that is to say, historical behavior data may only be used to determine a part of the user’s interest, while another important factor is the real-time behavior of the user. Data, or real-time changes in the user’s surrounding environment, etc. For example, after using a certain search keyword to search and obtain the search results, the content that they are really interested in may be more reflected in the list items that are clicked to view details in this search result. Specifically, for example, a user searches for "windbreaker" in the client of the commodity object information service system, and clicks on a list item from the search results. The color and style of the "windbreaker" in the list item are all possible More in line with the user’s needs for this search. Therefore, if the user’s real-time behavior can be considered in the process of page display, it will be beneficial to provide users with display content more in line with their preferences and improve page display efficiency.

In order to achieve the above objectives, a solution that can be considered is that the client collects user behavior data, and then submits it to the server, and the server adjusts the content on the page. However, the inventor of the present application discovered during the process of implementing the present application that this solution has at least the following shortcomings:

1. The client collects user-related data in real time, submits it to the server, and the server performs calculations, and then returns the adjustment results to the client. This process will experience a certain time delay, for example, a one-minute delay, which makes timeliness Will be greatly reduced. During this period of time, the user is still continuing to browse the page, and the user may have swiped the page to other places for display. At this time, the display is based on the adjustment result calculated one minute ago, which may have lost its meaning. In addition, it may make the adjustment of the page content confusing, which will affect the user's browsing experience;

2. Users are paying more and more attention to their own private information, and some governments have also issued related bills (General Data Protection Regulations, etc.) to protect users' privacy. As a result, when constructing related algorithm schemes and strategies on the server side, it is impossible to get closer to users, and it is also difficult to collect and calculate more sensitive information. It is precisely these sensitive information that may better reflect the user's real-time or temporary point of interest information.

Based on the foregoing considerations, the embodiments of the present application provide another implementation manner. In this implementation manner, user-related data (including real-time behavior data, surrounding environment data, etc.) can be collected "on the end", and directly "On the end" realizes the consumption of data, that is, predicts the user's interest points by performing model calculations, and then adjusts the display plan of the page content according to the prediction results to make it more in line with the needs of users and improve the page display effectiveness.

The feasibility of this scheme has the following points:

First of all, the work of collecting real-time user information can be completed by the client, and when performing specific operations such as prediction, it can be implemented through a pre-created prediction algorithm model. Therefore, in this embodiment of the application, the prediction algorithm can be The model is implemented in the client. That is to say, in the specific implementation, when the user installs the related client program, the related file about the prediction algorithm model will be added to the directory where the client related file is located. The file can also be an executable file. After the relevant components hand over the collected data to the prediction algorithm model, they can start the model to perform corresponding calculation processing and obtain the corresponding prediction results.

On the other hand, the function of collecting specific user-related data and adjusting the content of the page can be implemented in the page code. For example, the relevant undertaking component can be provided in advance, and the function of the component can include: The relevant data is submitted to the algorithm model, and the subsequent algorithm model can also return the prediction result to the undertaking component. Then, the receiving component can adjust the display mode of the specific page content according to the prediction result.

Furthermore, the adjustments made on the "end" in the embodiments of this application are only adjustments to the way the content of the page is displayed. For example, it may specifically include the order of the list items on the list page, or some specific visual components on the page. Appearance attributes, or whether some recommended content/guide content that needs to be selectively displayed is displayed, etc. The above adjusted specific objects are all obtained from the page data returned by the server, and there is no need to re-initiate access or search requests to the server, nor does it involve the adjustment of the specific URL of the page. Therefore, As long as the specific "methods" are implemented in the page, even the purpose of adjusting the display mode of the page content "on the end" is achieved.

In addition, because specific calculations and adjustments are performed "on the end", multiple steps of network transmission and other links are omitted, and real-time performance can be ensured.

Specifically, from the perspective of the implementation architecture, as shown in Figure 1, the embodiments of the present application mainly relate to the prediction algorithm model provided at the client frame layer, and the implementation in the page that specifically needs to provide a display mode to adjust related functions in real time. Related undertaking components. Among them, the server only provides specific page data when the user receives the client request. In the subsequent process of adjusting the display scheme of the page content based on the information collected in real time, the server no longer participates, all on the client side To be done. It should be noted that there can usually be multiple pages in the same client, and there may also be multiple pages that need to implement the above functions at the same time. Therefore, the specific prediction algorithm model can be shared by multiple pages in the same client. In other words, after collecting user-related data on each page, the same prediction algorithm model can perform the prediction of the user's interest points and return the prediction result. Or, in another way, if some pages have some special requirements, a separate prediction algorithm model can also be provided for such pages. In other words, the same client can also include multiple prediction algorithm models (not shown in FIG. 1), which can respectively correspond to different prediction requirements in different pages, and so on.

Among them, there can also be multiple specific application scenarios. For example, the above functions can be implemented in the client provided by the commodity object information service system, or the above functions can also be implemented in the clients of other systems or applications. Here Not limited.

The specific implementation manners provided in the embodiments of the present application are described in detail below.

Example one

First of all, the first embodiment provides a method for processing page information, which is introduced from the perspective of the receiving component in the aforementioned page. For details, refer to Figure 2. The method may specifically include:

S201: In the process of displaying the target page, collect user-related data;

Among them, there may be multiple specific target pages. For example, for a commodity object information service system, it may specifically include the client homepage, the commodity object information in the store homepage, the activity homepage, the search result page, and so on. As long as you want to implement the display content adjustment function locally on the client during the specific display process, you can introduce the undertaking component provided in the embodiment of this application into the page to realize the collection of related data and subsequent page content display methods The adjustment function.

Specifically, when data related to the user is collected, the data related to the user may specifically be data that can reflect the current point of interest/status of the user. For example, in one of the ways, since the user's current real-time behavior may reflect the user's current points of interest, the user's behavior data on the target page can be collected. In the search page scenario of the product object information service client, the specific behavior data can include product object/shop object click, browse, purchase, add to the "shopping cart" and wait for the purchase of the product object information collection, collection, attention, etc., and the benefits push results Clicks, page stay time and other real-time behaviors. These behavioral data can be used to predict specific user points of interest. For example, if you click to view the details of a product object, you can move the page related to or similar to the product object to the front, and so on.

In addition, in addition to specific user behavior data, information data of the surrounding environment where the user is located can also be collected. Specifically, it can include secret scene information such as the user's scene, location, and environment. For example, it may include whether the user is on a vehicle in a driving state, or whether he has entered a physical store, and the weather changes in the geographic location of the user, and so on. Because the changes in the surrounding environment may also reflect the user's points of interest, the way the page content is displayed can also be adjusted according to the surrounding environment information. For example, if you find that a user has entered a physical store during the current display of a search result page, you can move the list items related to the physical store on the search results page to the front; or, if the weather is suddenly found at a certain moment When it turns sunny, you can adjust the appearance attributes of specific visual components on the page, for example, adjust it to a brighter color to match the specific weather changes, and so on.

S202: Provide the information of the target page and the collected data to a prediction algorithm model set on the terminal device where the client is located, so as to predict the user's point of interest information on the target page;

When specific user-related data is collected, it can be provided to a specific prediction algorithm model for calculation. Among them, the information about the target page, including the content data of the page, can be provided to the prediction algorithm model only once when the user-related data is collected for the first time, and then only the specific collected data needs to be provided. The page content data in the page is recorded. In specific implementation, the receiving component in the page can send to the prediction algorithm model every time user-related data is collected, and the prediction algorithm model can also perform a prediction every time new user-related data is received. , And return the forecast result. Or, in specific implementation, the prediction algorithm model can also be configured in advance. For example, the calculation can be triggered only when user-related data of a certain type or meeting other conditions is received. For example, the calculation can be performed only when data related to the "click" behavior is received, other types of data can be ignored, and so on.

Among them, the specific prediction algorithm model may be pre-trained, which can take collected user-related data as input and output specific prediction results. Among them, the prediction result can exist in many forms. For example, if the input collected data is that the user clicks on a related list item, the predicted prediction result can include: the user's response to the remaining undisplayed items on the page The possible level of interest for the list item. Or, if the input collected data is that the user has added a "shopping cart" to a certain list item, the prediction result may include: the user may be about to perform an operation of placing an order for purchase. If the input collected data includes some information related to the surrounding environment, the prediction result may include colors or shapes that the user may like.

S203: Obtain the prediction result returned by the prediction algorithm model;

After the prediction algorithm model obtains the specific prediction result, it can be returned to the receiving component on the page.

S204: Under the trigger of the target event, determine an adjustment scheme for the display content of the target page according to the prediction result, and re-render and refresh the display of the target page according to the adjustment scheme.

Among them, there can be multiple ways to specifically adjust the display content of the page. For example, in one manner, if the target page includes a target list page, for example, a search result page, or a list page of recommended product objects such as "Guess you like", etc., the prediction result includes: The user’s interest level information for the list items on the target list page that have not yet entered the visible range of the display window; at this time, when making specific adjustments, the user can compare the information on the target list page according to the interest level information. The list items are reordered. Specifically, among the list items that have not yet been displayed, the list items that meet the conditions of the user's interest level may be preferentially displayed within the visible range of the display window.

In other words, for list pages such as search results, although the server may have personalized sorting based on the user's history when providing page data, it does not consider the user's real-time behavior data and other factors, so , For some content that users may be really interested in during this search, they are ranked relatively low. However, due to the limited list items that can be displayed on each screen of mobile terminal devices such as mobile phones, the user’s browsing habit is often that after sliding down a few screens, they will not continue to slide down, but choose to close or exit the list page. Get to re-change the search term and re-initiate the search, etc. This makes the list items that are sorted relatively late but actually more in line with the user's current real needs cannot be exposed, and it also affects the user's impression of the accuracy of the search results. In the embodiment of this application, after obtaining a batch of list items from the server, the display scheme of the content in the list items can be adjusted according to the real-time behavior data generated by the user or the data of the surrounding environment information, etc., so that The list that has not been displayed before is placed at a higher position for display first, and may even appear directly in the visible range of the window to achieve information exposure. When the prediction result is relatively accurate, this kind of content adjustment will enable users to obtain the content they want more efficiently and improve search efficiency.

Alternatively, the prediction result may also include: the appearance attribute information of the page that the user is interested in; for example, it can be predicted based on the main color of the specific content in the list item currently clicked or recently clicked by the user, or the current weather change, etc. The appearance attributes of the page that users may be interested in. At this time, the appearance attributes of the target visualization component in the target page can be adjusted according to the appearance attributes of the page that the user is interested in. For example, it may specifically include adjusting the shape and/or color attributes of the outer frame of the target visualization component. Among them, the visualization component may specifically include the background of the page, resource location (commonly known as "pit location"), page header, and so on. In other words, the appearance attributes of these visual components can also be adjusted based on user-related data collected in real time.

In addition, the prediction result includes: probability information that the user will perform the target behavior in the next step; in this case, when the adjustment plan for the display content of the target page is determined according to the prediction result, it may be in the target page Add guidance information for guiding the target behavior. In other words, for some pages, some guiding information may be displayed. For example, for pages related to product object information, the guiding information may include user rights information (coupons, red envelopes, Full discounts, etc.) information. The total amount of specific user rights may be limited, and it is generally hoped to distribute to users who are more likely to use the user rights to avoid expiration and invalidation of the user rights, thereby failing to play its due role. For users who are specifically selected to be able to issue user rights, when the user rights are specifically issued to them, the specific user rights information may be provided to the user in the form of pop-up windows or floating layers when the user visits a specific page. However, in the implementation of the prior art, the server usually decides which users to distribute to. For example, a user submits a search request for a certain search term. At this time, there happens to be a "universal" discount. Coupons can be issued, and the server judges that the user has a higher probability of using the coupon based on the user's past historical data, etc., so the coupon information can be carried in the page data of the specific search result page , So that users can obtain specific coupon information while obtaining search result information, and can perform operations such as receiving. However, because the user’s historical behavior records may not be able to accurately predict whether the user will currently perform a certain behavior, the accuracy of this method of circle selection of users through the server may be relatively low, and it will still be There is a relatively high probability of wasting user rights. And if in the process of browsing a certain page, it can be predicted that the probability of a certain user performing a purchase operation on a certain product object is relatively high, and then the user rights information is issued to it, which may further promote The completion of the transaction also enables the effective use of user rights. However, in the embodiments of the present application, since the real-time behavior data of the user can be collected on the terminal, and the real-time behavior data collected can also be used to predict the next possible behavior of the user, so the above can be achieved. purpose. For example, if it is found that a user has only browsed the search results page, has not clicked on a list item to view details, and has not performed operations such as adding to shopping cart or favorites, it proves the probability that the user may perform purchase behavior at least currently It will be lower. However, if it is found that at a certain moment, the user performs the operation of adding a shopping cart to a certain commodity object or multiple commodity objects, then the user has a high probability of performing the purchase behavior, and at this time, the user can issue the user rights to the user. therefore,

Among them, after it is determined that a certain user is about to perform a purchase behavior, there may be multiple ways to issue user rights and interests to the user. For example, in one way, tag information about user rights can be added to the resource slot where the product object is located, so as to guide the user to click on the product object link to enter its detail page, and then collect related user rights in the detail page . Or, in another way, you can also provide user rights information and operation options for receiving user rights directly through a pop-up window or creating a floating layer, so that the user can directly receive specific user rights on the current page ,and many more.

It should be noted that the specific user rights and other guidance information in the target page can also be provided by the server, but in this embodiment of the application, in the initial state of displaying the target page, such guidance information can be temporarily ignored. Display to avoid waste of user rights and interference to the user’s normal browsing; and only when the user’s real-time behavior and other data determine that the user’s purchase probability is relatively high, then provide relevant information to him , In order to improve the effective utilization of user rights information.

In addition, in specific implementation, after receiving the specific prediction result, the receiving component in the page may not directly adjust the display scheme, but need to wait for the trigger of a specific target event. In other words, since the actions of collecting related data may occur relatively frequently, correspondingly, the accepting page may also receive new prediction results relatively frequently. However, if the specific target page is in the display state when the prediction result is received, the page is directly re-rendered and refreshed, which may affect the user's browsing experience. For this reason, in the embodiment of the present application, although the receiving component may receive multiple prediction results, it may be triggered by a certain target event, and then adjust the display scheme of the page, and refresh the display after re-rendering.

Among them, there may be multiple specific target events. For example, one of them may include: jumping from the target page to another page, and then returning from the other page to the target page. For example, when a user is browsing a product object search result page, he slides the page to the state shown in Figure 3-1, that is, the product objects 1, 2, 3, and 4 are displayed on the list page. Click on one of the product objects 1 and jump to its detail page to view, then close the detail page and return to the search result list page. At this time, the list page is not swiped on the basis of the jump action. However, the content displayed in the visible range of the page window has changed from before the jump. Similar information was displayed. For example, as shown in Figure 3-2, after returning to the list page, the product object 18 appears in the visible range of the window. This is because the algorithm model on the terminal calculates the product object 18 and the currently viewed product object 1 There is a high similarity between them. Therefore, its display position on the page has been adjusted so that the user can be exposed to the user as long as the user returns to the list page. If the solution provided by the embodiment of this application is not adopted, according to the original position of the commodity object 18 on the page, the user may need to continue to slide down many screens to view it, and before that, the user may have logged out or closed the The list page is now, so that the product object information that is likely to be of interest has no chance to be exposed to the user.

Or, for another example, when a user browses the homepage of a certain client, as shown in Figure 3-3, the homepage displays a "guess you like" list, which includes recommendations for the user based on the user's historical behavior records, etc. Information about multiple commodity objects that it may be interested in. Among them, due to the limited screen of the terminal device, the information of only four commodity objects is usually displayed on one screen, and the user can browse more information of recommended commodity objects by sliding the screen up and down. For example, slide the page to the state shown in Figure 3-3, that is, the product objects 1, 2, 3, and 4 are displayed on the list page. At this point, the user clicks on one of the product objects 1 and jumps to its details page to view, then performs the "add to shopping cart" operation on the product object, and then returns to the "Guess you like" list on the homepage. Browse. But at this time, because the user performs the "add to shopping cart" operation, the relevant algorithm can predict that the user will be more likely to perform the next purchase behavior. In order to further increase the purchase conversion rate, as shown in Figure 3-4 After returning to the list page, you can display specific user rights information in the resource slot where the commodity object specifically associated with user rights information is located. For example, as shown at 31 in Figure 3-4, "5 yuan coupon", "30 yuan coupon", "60 yuan coupon" and so on. That is to say, for the client homepage, the adjustment of the page content display scheme can also be implemented locally on the client, so that it can better meet the needs of users generated in real time during the browsing process and improve the efficiency of page display. In addition, in addition to the above search result page and the client home page, this function can also be implemented in other pages, which will not be listed here.

In another case, the target event may specifically include: when the target page is displayed, the client is switched to running in the background, and then switched back to running in the foreground from the background. For example, suppose a user searches for a certain keyword in the client and displays the search result page. In this state, if you need to check a newly received message in another application, you need to exit the current client After running in the background, after the message viewing is completed, return to the current client to continue browsing the previous search result page. In this case, the embodiment of this application can be used as a trigger event to adjust the display scheme in the search result page, that is, before the user returns the client to the background, and after switching to the foreground, although When no operations such as sliding on the search results page are performed, and the page itself does not return to the top of the page by default, the content displayed on the page has changed, and the list items that were originally sorted very low are displayed in the view of the window. Range, etc.

In addition, the target event may also include: an event in which the terminal device where the client is located is unlocked after performing a screen lock action while the target page is displayed. This situation is similar to the situation of front-end and back-end switching mentioned above, that is, the status of the target page is being displayed in the client. If an event occurs that is unlocked after the screen is locked, you can find that the page displayed after unlocking The content has changed from before, etc.

Of course, what needs to be explained here is that the changes in page content described in the embodiments of this application are mainly adjustments to the display scheme. For example, it may include adjusting the display order of page list items, and some of the original displayed Hide the content, or display the content that was not originally displayed, or adjust the appearance properties of some visual components on the page, and so on. The specific content can be obtained from the page data returned by the server, and there is no need to interact with the server during the specific adjustment process.

In short, through the embodiments of this application, user-related information can be collected in the process of displaying the target page, which can mainly include some real-time behavior data or surrounding environment information, etc., and can be directly in the customer The end-side analyzes and calculates the collected data, thereby predicting the possible points of interest of the user at the moment. Further, the display scheme of the page content in the page can be adjusted under the trigger of a specific event, and the page content can be re-rendered and refreshed. In this way, the display scheme of the page content can be adjusted with the collected user-related data, instead of displaying according to the fixed scheme provided by the server. Therefore, it is conducive to exposing more interesting content to users and improving The page display efficiency also improves user experience.

Example two

The second embodiment provides a page information processing method from another angle. In this method, the specific prediction algorithm can also be directly written in the page code, so that the user’s interest points can be completely completed within the page. Forecasts and adjustments to the display plan. Specifically, referring to FIG. 4, the method may specifically include:

S401: In the process of displaying the target page, collect user-related data;

S402: Predict the point of interest information of the user for the target page according to the collected data;

S403: Under the triggering of a target event, determine an adjustment plan for the display content of the target page according to the prediction result, and re-render and refresh the display of the target page according to the adjustment plan.

Example three

The third embodiment mainly introduces specific applications in the search scenario in the commodity object information service system. Specifically, the third embodiment provides a method for processing product object search result information. Referring to FIG. 5, the method may specifically include:

S501: The client submits search keyword information to the server;

S502: Receive page data of a search result page returned by the server, where the search result page includes multiple product object information;

S503: Display the search result page according to the page data, and collect user behavior data generated by the user for the search result page;

S504: Predict the point of interest information of the user according to the collected user behavior data;

S505: Under the trigger of the target event, it is determined according to the prediction result to adjust the page content display scheme of the search result page, and the search result page is re-rendered and refreshed according to the adjusted scheme.

Specifically, the user’s interest level information for the list items on the target list page that have not yet entered the visible range of the display window can be predicted; then, the user experience of the list items that have not yet been displayed can be predicted List items whose interest level meets the conditions are first displayed in the visible range of the display window.

Alternatively, the appearance attribute information of the page that the user is interested in can also be predicted; then, according to the appearance attribute of the page that the user is interested in, the appearance attribute of the target visualization component in the search result page is adjusted.

Alternatively, it is also possible to predict the probability information that the user will perform the purchase behavior in the next step; in this case, the user rights information can be added to the search result page, and the content of the user rights information is carried in the service In the page data returned by the end.

For the unspecified parts in the second embodiment and the third embodiment, please refer to the record in the first embodiment, which will not be repeated here.

Corresponding to Embodiment 1, this embodiment of the present application also provides a page information processing device. Referring to FIG. 6, the device may specifically include:

The data collection unit 601 is used to collect user-related data in the process of displaying the target page;

The data providing unit 602 is configured to provide the information of the target page and the collected data to a prediction algorithm model set on the terminal device where the client is located, so as to predict the user's interest in the target page information;

The prediction result obtaining unit 603 is configured to obtain the prediction result returned by the prediction algorithm model;

The display scheme adjustment unit 604 is configured to determine an adjustment scheme for the display content of the target page according to the prediction result when triggered by a target event, and re-render and refresh the display of the target page according to the adjustment scheme.

Among them, the data collection unit can be specifically used for:

Collect user behavior data performed on the target page.

Wherein, the target page includes a page related to product object information;

The behavior data includes: viewing detailed information, purchasing, adding to a collection of product object information to be purchased, collecting, or following behaviors performed on the product objects displayed on the target page.

Alternatively, the data collection unit may also be specifically used for:

Collect the surrounding environment information data where the user is located.

Wherein, the surrounding environment information data includes: whether the user is on a vehicle in a driving state, or whether he enters a physical store.

Alternatively, the surrounding environment information data includes: weather changes at the geographic location of the user.

Wherein, the target page includes a target list page;

The prediction result includes: information about the user's interest in the list items on the target list page that have not yet entered the visible range of the display window;

The display scheme adjustment unit may be specifically used for:

According to the interest level information, the list items in the target list page are reordered.

Specifically, the display scheme adjustment unit may be specifically used for:

Among the list items that have not yet been displayed, the list items that meet the conditions of the user's interest level are preferentially displayed within the visible range of the display window.

In addition, the prediction result includes: appearance attribute information of the page that the user is interested in;

The display scheme adjustment unit may be specifically used for:

Adjust the appearance attributes of the target visualization component in the target page according to the appearance attributes of the page that the user is interested in.

Specifically, the shape and/or color attributes of the outer frame of the target visualization component can be adjusted.

In addition, the prediction result includes: probability information that the user will perform the target behavior in the next step;

The display scheme adjustment unit may be specifically used for:

Adding guide information for guiding the target behavior to the target page.

Wherein, the target page includes a page related to commodity object information, and the target behavior includes a purchase behavior; in this case, the guide information may include user rights information provided for the user.

Specifically, the display scheme adjustment unit may be used to add label information about user rights and interests in the resource slot where the commodity object is located.

Alternatively, the display scheme adjustment unit may also be used to provide user rights information and operation options for receiving user rights through a pop-up window or creating a floating layer.

Specifically, the target event includes: an event of jumping from the target page to another page, and then returning from the other page to the target page.

Alternatively, the target event includes: in a state where the target page is displayed, the client is switched to run in the background and then back to the foreground from the background.

Alternatively, the target event includes: an event in which the terminal device where the client is located performs a screen lock action and is unlocked when the target page is displayed.

Corresponding to the second embodiment, the embodiment of the present application also provides a page information processing device. Referring to FIG. 7, the device may specifically include:

The data collection unit 701 is used to collect data related to the user in the process of displaying the target page;

The prediction unit 702 is configured to predict the point of interest information of the user for the target page according to the collected data;

The scheme adjustment unit 703 is configured to determine an adjustment scheme for the display content of the target page according to the prediction result when triggered by a target event, and re-render and refresh the display of the target page according to the adjustment scheme.

Corresponding to the third embodiment, the embodiment of the present application also provides a product object search result information processing device. Referring to FIG. 8, the device may specifically include:

The keyword submission unit 801 is used to submit search keyword information to the server;

The page data receiving unit 802 is configured to receive page data of a search result page returned by the server, where the search result page includes multiple product object information;

The data collection unit 803 is configured to display the search result page according to the page data, and collect user behavior data generated by the user for the search result page;

The prediction unit 804 is configured to predict the point of interest information of the user according to the collected user behavior data;

The scheme adjustment unit 805 is configured to determine, according to the prediction result, to adjust the page content display scheme of the search result page when triggered by a target event, and re-render and refresh the display of the search result page according to the adjusted scheme .

Wherein, the prediction unit may be specifically used for:

Predict the user's interest level information for the list items on the target list page that have not yet entered the visible range of the display window;

At this time, the adjusted plan includes:

Among the list items that have not yet been displayed, the list items whose degree of user interest meets the conditions are preferentially displayed within the visible range of the display window.

Or, the prediction unit may be specifically used for:

Predicting the appearance attribute information of the page that the user is interested in;

At this time, the adjusted plan includes:

Adjust the appearance attributes of the target visualization component in the search result page according to the appearance attributes of the page that the user is interested in.

Or, the prediction unit can also be specifically used for:

Predict the probability information that the user will perform the purchase behavior in the next step;

At this time, the adjusted plan includes:

The user rights information is added to the search result page, and the content of the user rights information is carried in the page data returned by the server.

In addition, an embodiment of the present application also provides an electronic device, including:

One or more processors; and

In the process of displaying the target page, collect user-related data;

Obtaining the prediction result returned by the prediction algorithm model;

or,

In the process of displaying the target page, collect user-related data;

or,

Submit search keyword information to the server;

Among them, FIG. 9 exemplarily shows the architecture of an electronic device. For example, the device 900 can be a mobile phone, a computer, a digital broadcasting terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, or a personal digital assistant. , Aircraft, etc.

9, the device 900 may include one or more of the following components: a processing component 902, a memory 904, a power supply component 906, a multimedia component 908, an audio component 910, an input/output (I/O) interface 912, a sensor component 914, and Communication component 916.

The processing component 902 generally controls the overall operations of the device 900, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations. The processing element 902 may include one or more processors 920 to execute instructions to complete all or part of the steps of the method provided by the technical solution of the present disclosure. In addition, the processing component 902 may include one or more modules to facilitate the interaction between the processing component 902 and other components. For example, the processing component 902 may include a multimedia module to facilitate the interaction between the multimedia component 908 and the processing component 902.

The memory 904 is configured to store various types of data to support the operation of the device 900. Examples of such data include instructions for any application or method operating on the device 900, contact data, phone book data, messages, pictures, videos, etc. The memory 904 can be implemented by any type of volatile or nonvolatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable and Programmable Read Only Memory (EPROM), Programmable Read Only Memory (PROM), Read Only Memory (ROM), Magnetic Memory, Flash Memory, Magnetic Disk or Optical Disk.

The power supply component 906 provides power to various components of the device 900. The power supply component 906 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the device 900.

The multimedia component 908 includes a screen that provides an output interface between the device 900 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touch, sliding, and gestures on the touch panel. The touch sensor can not only sense the boundary of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 908 includes a front camera and/or a rear camera. When the device 900 is in an operation mode, such as a shooting mode or a video mode, the front camera and/or the rear camera can receive external multimedia data. Each front camera and rear camera can be a fixed optical lens system or have focal length and optical zoom capabilities.

The audio component 910 is configured to output and/or input audio signals. For example, the audio component 910 includes a microphone (MIC). When the device 900 is in an operating mode, such as a call mode, a recording mode, and a voice recognition mode, the microphone is configured to receive external audio signals. The received audio signal may be further stored in the memory 904 or transmitted via the communication component 916. In some embodiments, the audio component 910 further includes a speaker for outputting audio signals.

The I/O interface 912 provides an interface between the processing component 902 and a peripheral interface module. The above-mentioned peripheral interface module may be a keyboard, a click wheel, a button, and the like. These buttons may include but are not limited to: home button, volume button, start button, and lock button.

The sensor component 914 includes one or more sensors for providing the device 900 with various aspects of state evaluation. For example, the sensor component 914 can detect the on/off status of the device 900 and the relative positioning of components. For example, the component is the display and the keypad of the device 900. The sensor component 914 can also detect the position change of the device 900 or a component of the device 900. , The presence or absence of contact between the user and the device 900, the orientation or acceleration/deceleration of the device 900, and the temperature change of the device 900. The sensor component 914 may include a proximity sensor configured to detect the presence of nearby objects when there is no physical contact. The sensor component 914 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor component 914 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor or a temperature sensor.

The communication component 916 is configured to facilitate wired or wireless communication between the device 900 and other devices. The device 900 can access a wireless network based on a communication standard, such as WiFi, 2G, or 3G, or a combination thereof. In an exemplary embodiment, the communication component 916 receives a broadcast signal or broadcast related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 916 further includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

In an exemplary embodiment, the device 900 can be implemented by one or more application specific integrated circuits (ASIC), digital signal processors (DSP), digital signal processing devices (DSPD), programmable logic devices (PLD), field programmable A gate array (FPGA), controller, microcontroller, microprocessor, or other electronic components are implemented to implement the above methods.

In an exemplary embodiment, there is also provided a non-transitory computer-readable storage medium including instructions, such as a memory 904 including instructions, which can be executed by the processor 920 of the device 900 to complete the method provided by the technical solutions of the present disclosure . For example, the non-transitory computer-readable storage medium may be ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, optical data storage device, etc.

From the description of the foregoing implementation manners, it can be understood that those skilled in the art can clearly understand that this application can be implemented by means of software plus a necessary general hardware platform. Based on this understanding, the technical solution of this application essentially or the part that contributes to the existing technology can be embodied in the form of a software product, and the computer software product can be stored in a storage medium, such as ROM/RAM, magnetic disk , CD-ROM, etc., including several instructions to enable a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method described in each embodiment or some parts of the embodiment of this application.

The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system or the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and for related parts, please refer to the part of the description of the method embodiment. The system and system embodiments described above are merely illustrative, where the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, namely It can be located in one place, or it can be distributed to multiple network units. Some or all of the modules may be selected according to actual needs to achieve the objectives of the solutions of the embodiments. Those of ordinary skill in the art can understand and implement it without creative work.

The page information processing method, device, and electronic equipment provided in this application are described in detail above. Specific examples are used in this article to explain the principles and implementation of this application. The description of the above embodiments is only used to help understand this The application method and its core idea; meanwhile, for the ordinary skilled in the art, according to the idea of this application, there will be changes in the specific implementation and the scope of application. In summary, the content of this specification should not be construed as a limitation on this application.

Claims

A method for processing page information, characterized in that it comprises:

In the process of displaying the target page, collect user-related data;

Providing the information of the target page and the collected data to a prediction algorithm model set on the terminal device where the client is located, so as to predict the user's point of interest information on the target page;

Obtaining the prediction result returned by the prediction algorithm model;

Under the trigger of the target event, an adjustment scheme for the display content of the target page is determined according to the prediction result, and the target page is re-rendered and refreshed according to the adjustment scheme.
The method according to claim 1, wherein:

The collection of user-related data includes:

Collect user behavior data performed on the target page.
The method according to claim 2, wherein:

The target page includes a page related to product object information;

The behavior data includes: viewing detailed information, purchasing, adding to a collection of product object information to be purchased, collecting, or following behaviors performed on the product objects displayed on the target page.
The method according to claim 1, wherein:

The collection of user-related data includes:

Collect the surrounding environment information data where the user is located.
The method according to claim 4, wherein:

The surrounding environment information data includes: whether the user is on a vehicle in a driving state, or whether he enters a physical store.
The method according to claim 4, wherein:

The surrounding environment information data includes: weather changes at the geographic location of the user.
The method according to claim 1, wherein:

The target page includes a target list page;

The prediction result includes: information about the user's interest in the list items on the target list page that have not yet entered the visible range of the display window;

The determining the adjustment scheme for the display content of the target page according to the prediction result includes:

According to the interest level information, the list items in the target list page are reordered.
The method according to claim 7, characterized by comprising:

The reordering the list items in the target list page includes:

Among the list items that have not yet been displayed, the list items whose degree of user interest meets the conditions are preferentially displayed within the visible range of the display window.
The method according to claim 1, wherein:

The prediction result includes: appearance attribute information of the page that the user is interested in;

The determining the adjustment scheme for the display content of the target page according to the prediction result includes:

Adjust the appearance attributes of the target visualization component in the target page according to the appearance attributes of the page that the user is interested in.
The method according to claim 9, wherein:

The adjusting the appearance attributes of the target visualization component in the target page includes:

Adjust the shape and/or color attributes of the outer frame of the target visualization component.
The method according to claim 1, wherein:

The prediction result includes: probability information that the user will perform the target behavior in the next step;

The determining the adjustment scheme for the display content of the target page according to the prediction result includes:

Adding guide information for guiding the target behavior to the target page.
The method according to claim 11, wherein:

The target page includes a page related to commodity object information, and the target behavior includes a purchase behavior;

The guide information includes user rights information provided for the user.
The method according to claim 12, wherein:

The adding guide information for guiding the target behavior to the target page includes:

Add label information about user rights in the resource slot where the product object is located.
The method according to claim 12, wherein:

The adding guide information for guiding the target behavior to the target page includes:

Provide user rights information and operation options for receiving user rights through pop-up windows or creating floating layers.
The method according to claim 1, wherein:

The target event includes: jumping from the target page to another page, and then returning from the other page to the target page.
The method according to claim 1, wherein:

The target event includes: when the target page is displayed, the client is switched to running in the background, and then switched back to running in the foreground from the background.
The method according to claim 1, wherein:

The target event includes: when the target page is displayed, the terminal device where the client is located is executed and then unlocked.
A method for processing page information, characterized in that it comprises:

The client collects user-related data in the process of displaying the target page;

According to the collected data, predict the user's point of interest information on the target page;

Under the trigger of the target event, an adjustment scheme for the display content of the target page is determined according to the prediction result, and the target page is re-rendered and refreshed according to the adjustment scheme.
A method for processing product object search result information, which is characterized in that it comprises:

The client submits search keyword information to the server;

Receiving page data of a search result page returned by the server, where the search result page includes multiple product object information;

Displaying the search result page according to the page data, and collecting user behavior data generated by the user for the search result page;

Predict the point of interest information of the user according to the collected user behavior data;

Under the trigger of the target event, it is determined according to the prediction result to adjust the page content display scheme of the search result page, and the search result page is re-rendered and refreshed according to the adjusted scheme.
The method of claim 19, wherein:

The predicting the user's point of interest information according to the collected user behavior data includes:

Predict the user's interest level information for the list items on the target list page that have not yet entered the visible range of the display window;

The adjusted plan includes:

Among the list items that have not yet been displayed, the list items whose degree of user interest meets the conditions are preferentially displayed within the visible range of the display window.
The method of claim 19, wherein:

The predicting the user's point of interest information according to the collected user behavior data includes:

Predicting the appearance attribute information of the page that the user is interested in;

The adjusted plan includes:

Adjust the appearance attributes of the target visualization component in the search result page according to the appearance attributes of the page that the user is interested in.
The method of claim 19, wherein:

The predicting the user's point of interest information according to the collected user behavior data includes:

Predict the probability information that the user will perform the purchase behavior in the next step;

The adjusted plan includes:

The user rights information is added to the search result page, and the content of the user rights information is carried in the page data returned by the server.
A page information processing device, characterized by comprising:

The data collection unit is used to collect user-related data in the process of displaying the target page;

The data providing unit is used to provide the information of the target page and the collected data to the prediction algorithm model of the terminal device where the client is located, so as to predict the user's interest point information on the target page ；

A prediction result obtaining unit, configured to obtain the prediction result returned by the prediction algorithm model;

The display scheme adjustment unit is configured to determine an adjustment scheme for the display content of the target page according to the prediction result when triggered by a target event, and re-render and refresh the display of the target page according to the adjustment scheme.
A page information processing device, characterized by comprising:

The data collection unit is used to collect user-related data in the process of displaying the target page;

A prediction unit, configured to predict the user’s point of interest information on the target page according to the collected data;

The scheme adjustment unit is configured to determine an adjustment scheme for the display content of the target page according to the prediction result when triggered by a target event, and re-render and refresh the display of the target page according to the adjustment scheme.
A product object search result information processing device, characterized in that it comprises:

The keyword submission unit is used to submit search keyword information to the server;

The page data receiving unit is configured to receive page data of the search result page returned by the server, where the search result page includes multiple product object information;

A data collection unit, configured to display the search result page according to the page data, and collect user behavior data generated by the user for the search result page;

A prediction unit, configured to predict the point of interest information of the user according to the collected user behavior data;

The scheme adjustment unit is configured to determine, according to the prediction result, to adjust the page content display scheme of the search result page under the trigger of the target event, and re-render and refresh the display of the search result page according to the adjusted scheme.
An electronic device, characterized in that it comprises:

One or more processors; and

A memory associated with the one or more processors, where the memory is used to store program instructions, and when the program instructions are read and executed by the one or more processors, perform the following operations:

In the process of displaying the target page, collect user-related data;

Providing the information of the target page and the collected data to a prediction algorithm model set on the terminal device where the client is located, so as to predict the user's point of interest information on the target page;

Obtaining the prediction result returned by the prediction algorithm model;

Under the trigger of the target event, an adjustment scheme for the display content of the target page is determined according to the prediction result, and the target page is re-rendered and refreshed according to the adjustment scheme.
The electronic device according to claim 26, wherein the program instructions are further used to execute the method according to any one of claims 2-17.
An electronic device, characterized in that it comprises:

One or more processors; and

A memory associated with the one or more processors, where the memory is used to store program instructions, and when the program instructions are read and executed by the one or more processors, perform the following operations:

In the process of displaying the target page, collect user-related data;

According to the collected data, predict the user's point of interest information on the target page;

Under the trigger of the target event, an adjustment scheme for the display content of the target page is determined according to the prediction result, and the target page is re-rendered and refreshed according to the adjustment scheme.
An electronic device, characterized in that it comprises:

One or more processors; and

A memory associated with the one or more processors, where the memory is used to store program instructions, and when the program instructions are read and executed by the one or more processors, perform the following operations:

Submit search keyword information to the server;

Receiving page data of a search result page returned by the server, where the search result page includes multiple product object information;

Displaying the search result page according to the page data, and collecting user behavior data generated by the user for the search result page;

Predict the point of interest information of the user according to the collected user behavior data;

Under the trigger of the target event, it is determined according to the prediction result to adjust the page content display scheme of the search result page, and the search result page is re-rendered and refreshed according to the adjusted scheme.
The electronic device according to claim 29, wherein the program instructions are further used to execute the method according to any one of claims 20-22.