Page processing method, device and readable medium

Abstract

Embodiments of the present application provide a page processing method and device and readable medium. The method comprises: obtaining browsing behavior data of a user in a page browsing process; analyzing the browsing behavior data to determine intention information of the user, the intention information comprising an intention stage and an intention type; determining preference information of the user, determining a mapping relationship between the intention information and the preference information; determining page layout information corresponding to the intention stage according to the mapping relationship, the page layout information comprising external layout information and internal layout information; upon receiving a page request, determining page layout information corresponding to the intention stage of the request and generating a corresponding page. The intention of the user can be determined based on the behavior of the user, and a page meeting the intention of the user is generated, so that the user can quickly obtain the required content, and the processing efficiency is improved.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a page processing method, a terminal device, and a machine-readable medium. Background Technology

[0002] With the development of technology, more and more e-commerce websites are providing services to users, who can shop on these websites and select the goods they need.

[0003] Users on e-commerce websites often have diverse and personalized shopping needs, and they frequently have different focuses when browsing product pages. However, current e-commerce website pages often have fixed layouts, forcing users to manually search for the content they need, which is inefficient. Summary of the Invention

[0004] This application provides a page processing method to improve processing efficiency.

[0005] Accordingly, embodiments of this application also provide an electronic device and a machine-readable medium to ensure the implementation and application of the above methods.

[0006] To address the aforementioned problems, this application discloses a page processing method, the method comprising:

[0007] Obtain user browsing behavior data during the page browsing process;

[0008] The browsing behavior data is analyzed to determine the user's intent information, which includes intent stage and intent type;

[0009] Determine the user's preference information, and determine the mapping relationship between the intent information and the preference information;

[0010] Based on the mapping relationship, the page layout information corresponding to the intent stage is determined, and the page layout information includes: external layout information and internal layout information;

[0011] Upon receiving a page request, the page layout information corresponding to the intent stage of the request is determined and the corresponding page is generated.

[0012] Optionally, the step of obtaining at least one of the following browsing behavior data during the user's page browsing process:

[0013] User dwell information during page browsing, including dwell time;

[0014] Click information of a user's click behavior during page browsing, the click information including: the type of object clicked and the number of clicks;

[0015] The operation information includes the user's actions during page browsing, including the operation type and operation content.

[0016] Optionally, analyzing the browsing behavior data to determine the user's intent information includes:

[0017] The browsing behavior data is analyzed to determine the corresponding intent stage;

[0018] Determine the browsing type corresponding to the intent stage, and select the type that meets the intent conditions as the intent type.

[0019] Optionally, the step of analyzing the browsing behavior data to determine the corresponding intent stage includes:

[0020] Based on the behavior of the launch page, the intent phase is determined to be the first intent phase;

[0021] When the first dwell time on the page exceeds the first time threshold, the intent stage is determined to be the second intent stage;

[0022] When the number of clicks on the object display container on the page exceeds the number of clicks threshold, the intent stage is determined to be the third intent stage;

[0023] When the second dwell time on the object page exceeds the second time threshold, the intent stage is determined to be the fourth intent stage, and the object page is launched based on the click on the object display container;

[0024] When the operation behavior on the object page is the target operation behavior, the intent stage is determined to be the fifth intent stage.

[0025] Optionally, determining the browsing type corresponding to the intent stage and selecting a type that meets the intent conditions as the intent type includes:

[0026] Determine the type of the object being browsed, and determine the intent stage corresponding to that type;

[0027] Select the type that meets the intent conditions in the intent phase as the intent type.

[0028] Optionally, determining the mapping relationship between the intent information and the preference information includes:

[0029] Determine the external layout mapping relationship based on intent stage, intent type, aesthetic preference, and layout method information;

[0030] Determine the internal layout mapping relationship between the intent stage, intent information, and information preferences.

[0031] Optionally, determining the page layout information corresponding to the intent stage based on the mapping relationship includes:

[0032] The external layout information corresponding to the intent stage is determined based on the external mapping relationship and visual style information;

[0033] The internal layout information corresponding to the intent stage is determined based on the internal mapping relationship and visual style information.

[0034] Optionally, determining the page layout information for the intent stage corresponding to the request and generating the corresponding page includes:

[0035] Determine the user's intent stage based on the page request, and obtain the page layout information corresponding to the intent stage;

[0036] Based on the page layout information, determine the page elements, arrange the page elements according to the page layout information, and generate the corresponding page.

[0037] This application also discloses a page processing method, the method comprising:

[0038] The system detects user browsing behavior and records corresponding browsing behavior data, which is used to determine user intent information.

[0039] Upload the aforementioned browsing behavior data;

[0040] Send a page request;

[0041] Receive page data, the page data being determined based on the page layout information of the intent stage corresponding to the request, the page layout information of the intent stage being based on a mapping relationship, and the mapping relationship being determined based on intent information and preference information;

[0042] The page data is parsed and the corresponding page is displayed.

[0043] Optionally, issuing a page request includes at least one of the following steps:

[0044] When the browsing conditions on the page are met, a page request is generated and sent so that the page can continue to be displayed;

[0045] When returning to the page from another page, a page request is generated and sent.

[0046] This application also discloses an electronic device, including: a processor; and a memory storing executable code thereon, which, when executed, causes the processor to perform the method described in this application.

[0047] This application also discloses one or more machine-readable media storing executable code thereon, which, when executed, causes a processor to perform the method described in this application.

[0048] Compared with the prior art, the embodiments of this application have the following advantages:

[0049] In this embodiment, browsing behavior data of a user during page browsing can be acquired, analyzed, and the user's intent information can be determined. The intent information includes intent stage and intent type. Then, the mapping relationship between the intent information and preference information is determined, thereby obtaining the user's intent type and preferences at different intent stages. Then, the page layout information corresponding to the intent stage is determined based on the mapping relationship. The page layout information includes external layout information and internal layout information. When a page request is received, the page layout information corresponding to the intent stage of the request is determined and the corresponding page is generated. This enables the determination of the user's intent based on the user's behavior and the generation of a page that matches the user's intent, facilitating the user to quickly obtain the required content and improving processing efficiency. Attached Figure Description

[0050] Figure 1 This is a schematic diagram illustrating a page processing example according to an embodiment of this application;

[0051] Figure 2 This is a flowchart illustrating the steps of an embodiment of a page processing method according to this application;

[0052] Figure 3 This is a schematic diagram illustrating an example of intent-stage judgment according to an embodiment of this application;

[0053] Figure 4 This is a schematic diagram illustrating an example of intent type determination according to an embodiment of this application;

[0054] Figure 5 This is a schematic diagram illustrating an example of page adjustment according to an embodiment of this application;

[0055] Figure 6 This is a flowchart illustrating the steps of another embodiment of the page processing method in this application;

[0056] Figure 7 This is a flowchart of the steps of an optional embodiment of a page processing method according to this application;

[0057] Figure 8 This is a schematic diagram of the structure of a device provided in an embodiment of this application. Detailed Implementation

[0058] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0059] The embodiments of this application can be applied to page layout scenarios to generate pages that meet user needs. For example, Figure 1 As shown, user intent can be analyzed based on user browsing behavior on the page, and the page layout can be determined based on user intent information, so that the page display style is more in line with user needs, and users can more easily obtain the information they need, thus improving browsing efficiency.

[0060] Reference Figure 2 The diagram illustrates a flowchart of an embodiment of a page processing method according to this application.

[0061] Step 202: Obtain user browsing behavior data during the page browsing process.

[0062] When browsing e-commerce websites, users sometimes first browse navigation pages such as the homepage, search page, product type-specific pages, and activity pages. These navigation pages guide users to browse product items. Users can view product cards for multiple product items on the navigation page, thus identifying the product based on the product cards. For products of interest, users can click on the product card to enter the product details page and view detailed information about that product. The product cards are arranged in a card-style layout, displaying product information on the cards. Alternatively, the navigation page can also arrange product information by area, other elements, etc., and this embodiment does not impose any limitations on this approach.

[0063] Users can view multiple product items and their information on the navigation page, thus browsing behavior data can be obtained based on the user's browsing behavior on this page. In this embodiment of the application, the acquisition of user behavior, preferences, and other information is performed only after obtaining the user's authorization.

[0064] During a user's browsing process, various browsing behaviors may occur, such as scrolling up and down (or moving) on ​​the page, hovering, and clicking. Clicking may also correspond to page redirects, and the user's browsing behavior on the redirected pages can also yield corresponding browsing behavior data. For example, clicking on a product card may redirect to the product details page, where the user can also scroll (or move), hover, and click. Based on the click behavior, corresponding actions can be performed, such as adding to favorites, adding to cart, or purchasing, and the corresponding browsing behavior data can be obtained.

[0065] In one optional embodiment, acquiring user browsing behavior data during page browsing includes at least one of the following steps: determining user dwell information during page browsing, the dwell information including: dwell time; determining click information of user click behavior during page browsing, the click information including: click object type and click count; determining operation information of user operation behavior during page browsing, the operation information including: operation type and operation content. When a user browses a page, they are staying on that page, and the corresponding dwell time can be recorded as dwell information. In other examples, users may also stay at places of interest during page browsing, thus detecting user dwell behavior. Dwell information can be detected based on dwell behavior, including recording the user's location on the page and the time spent at that location, generating dwell information based on the location and dwell time. Users may also click on content of interest during page browsing, recording user click behavior and corresponding click information, such as recording the clicked product object, determining the type of the product object, and determining the number of clicks on the page, determining click information based on the click object type and click count. Users may perform various actions while browsing a page, and these actions can be identified and recorded. For example, when browsing a product details page, users may add products they are interested in to their favorites or shopping carts. These actions can be recorded, including the action type and content. For instance, if a user clicks "favorite," the action type can be identified as "favorite," and the action content is "favorite a specific product," thus providing the corresponding action information.

[0066] In this embodiment, a user's browsing behavior on a page can be limited to a single page or multiple related pages. For example, while browsing a navigation page, a user can click on a product that interests them to navigate to the product details page, where they can browse and interact. They can also return to the navigation page to continue browsing information on other products and click on details of interest. Browsing behavior data is continuously recorded throughout this process.

[0067] Step 204: Analyze the browsing behavior data to determine the user's intent information, which includes intent stage and intent type.

[0068] Recorded browsing behavior data can be analyzed to determine user intent and obtain intent information. User intent refers to the user's operational intention during page browsing, such as the real-time intent of a user browsing pages on an e-commerce website, including whether they are interested in a product or the object of their interest. In other examples, user preference information can also be analyzed based on historical behavior data; this application does not limit this approach. Intent information characterizes user intent and includes intent stage and intent type. Intent stage refers to the current stage of the user's browsing intent; different intent stages can be identified on different pages and with different browsing behavior data. Intent type refers to the type of product or object the user is interested in; the type of product or object the user is interested in can be determined based on the user's browsing behavior.

[0069] In one optional embodiment, analyzing the browsing behavior data to determine the user's intent information includes: analyzing the browsing behavior data to determine the corresponding intent stage; determining the browsing type corresponding to the intent stage; and selecting the type that meets the intent conditions as the intent type. The browsing behavior data can be analyzed to determine the conditions satisfied by the browsing behavior, thereby determining the current intent stage. Different stage conditions can be set for different intent stages, and the current intent stage can be determined based on the satisfied stage conditions. In some examples, the intent stages can also have a hierarchical relationship, so that the user enters the corresponding intent stage as the browsing behavior progresses. After determining the intent stage, the intent type can also be determined based on the intent stage. This can be done by filtering product objects based on the current intent stage and then using the type of the corresponding product object as the intent type, or by selecting product objects corresponding to the intent stages that meet the conditions based on the product objects and then using the type of the corresponding product object as the intent type.

[0070] Optionally, the analysis of the browsing behavior data to determine the corresponding intent stage includes: determining the intent stage as a first intent stage based on the behavior of the launch page; determining the intent stage as a second intent stage when the first dwell time on the page exceeds a first time threshold; determining the intent stage as a third intent stage when the number of clicks on the object display container on the page exceeds a number threshold; determining the intent stage as a fourth intent stage when the second dwell time on the object page exceeds a second time threshold, wherein the object page is launched based on the click on the object display container; and determining the intent stage as a fifth intent stage when the operation behavior on the object page is the target operation behavior. When a user enters the navigation page from the launch page, the behavior of the launch page can be collected, including browsing behavior information after the page launch is completed. The behavior of the launch page can be used to determine the corresponding intent stage, which is taken as the first intent stage. When a user browses on the page, it can be considered as staying on the page, thereby detecting the first dwell time. When the first dwell time on the page exceeds the first time threshold, the intent stage is determined as the second intent stage. Users can also click on display containers such as product cards, areas containing product objects, and containers for product images on the page. Clicking on these display containers may trigger page redirects or display of detailed product information. The number of times a user clicks on these display containers can be recorded. When the number of clicks exceeds a threshold, the intent stage is determined to be the third intent stage. After a user's click redirects to a new page, the corresponding second dwell time on that page can be recorded. When the second dwell time on the product page exceeds a second time threshold, the intent stage is determined to be the fourth intent stage. While browsing on a new page, such as a product details page, users may perform actions such as adding to favorites, adding to cart, or purchasing. Actions that meet certain conditions can be considered target actions, indicating that the user is interested in the product. Actions such as adding to favorites, adding to cart, and purchasing are considered target actions. When such actions on the product page are target actions, the intent stage is determined to be the fifth intent stage.

[0071] The user intent stages can be hierarchical, following the user psychological process outlined in the ISMAS model. ISMAS divides user behavior into five stages: I (Interest), where differentiated product information sparks consumer interest; S (Search), prompting users to actively gather information; M (Mouth), focusing on other users' unique evaluations of the product; A (Action), which can be understood as making a purchase decision based on product reviews and descriptions; and S (Share), sharing shopping experiences through social networks. This model can be combined with user browsing behavior on a webpage to determine the hierarchical intent stages and set corresponding conditions for each stage. In one optional embodiment, the user intent stages are divided into "Enter" - "Browse" - "Explore" - "Learn More" - "Interest," where "Enter" refers to the stage of entering the page. E-commerce websites often have high browsing and bounce rates, thus requiring rapid attraction and retention of users who enter. The "Browsing" stage corresponds to the "Interest" stage. At this stage, users haven't yet developed an interest in a particular product type and are therefore in a passive exploration state. The "Exploration" stage corresponds to the "Search" stage. Compared to the browsing stage, users develop an interest in products, such as items they might want to learn about or purchase. In this stage, users' acquisition of product information changes from passive to active. The "Detailed Understanding" stage corresponds to the "Mouth" stage. At this stage, user behavior upgrades from general browsing and exploration to examining and evaluating products of interest. The "Interested" stage corresponds to the "Action" stage. At this stage, users have a basic grasp of product information and may make an interesting decision to purchase or add the product to their favorites.

[0072] In this embodiment of the application, for the conditions corresponding to each intent stage, browsing behavior data can be analyzed based on big data to determine inflection points, peak values, medians, modes, and other values. The specific judgment thresholds of the user intent migration process can be obtained through analysis, thereby setting the corresponding conditions.

[0073] like Figure 3In the example shown, after entering the navigation page, the user is identified as being in the entry stage. If the time spent browsing the navigation page exceeds a first time threshold (e.g., 8, 9, or 10 seconds), the user is identified as being in the browsing stage. During the browsing stage, if the number of clicks on object display containers such as product cards exceeds a certain threshold (e.g., 2, 3, or 4), the user is identified as being in the exploration stage. Based on the user's clicks, the user proceeds to the product details page. If the time spent browsing the product details page exceeds a second time threshold (e.g., 11, 12, or 13 seconds), and multiple clicks lead to the exploration stage, multiple product details pages are viewed. The user is identified as being in the detailed understanding stage if the time spent on each page meets the second time threshold, or if the number of times the time spent meets the second time threshold exceeds the corresponding threshold. After the user performs actions such as adding to favorites, adding to cart, or purchasing on the product details page, the user is identified as being in the interest stage.

[0074] In practical processing, real-time intent stages can be calculated separately for each type of product, and the product type with the highest intent stage can be selected as the intent product type. In one optional embodiment, determining the browsing type corresponding to the intent stage and selecting a type that meets the intent conditions as the intent type includes: determining the type corresponding to the browsed object and determining the intent stage corresponding to that type; selecting a type whose intent stage meets the intent conditions as the intent type. The browsed product object and its type can be determined based on the page, and then the intent stage corresponding to that type can be determined; selecting a type whose intent stage meets the intent conditions as the intent type, such as selecting the N types with the highest hierarchy or priority of the intent stage as the intent type, where N is a positive integer not less than 1. Figure 4 In one example shown, product type 3 occupies the highest intent stage among all product types. Therefore, it can be assumed that the product type that the user is currently interested in is product type 3, and the overall intent stage reached is intent stage 4, where the intended product type is located.

[0075] This enables the analysis of user intent based on user browsing behavior data. This analysis can be based on real-time browsing behavior data or on browsing behavior data over a certain period of time.

[0076] Step 206: Determine the user's preference information and determine the mapping relationship between the intent information and the preference information.

[0077] User preference information can be obtained, which can be determined based on the user's historical behavior information. This preference information can include aesthetic preferences and information preferences. Aesthetic preferences characterize the numbering used for page layout, influencing the proportion of images and text in page elements and the quantity and density of design elements. For example, the proportion and number of object display containers for product objects in the layout; a larger object display container allows for a larger proportion of the product image and more white space. Information preferences characterize the user's preference for information associated with product objects, such as the type of information preferred. For example, if a user has a preference for product reviews or discounts, information with higher preference can be highlighted. User item number information can also be abstracted, such as aesthetic preferences: 0 = preference for sparseness, 1 = preference for density; information preferences: 0 = preference for discounts, 1 = preference for quality, etc. Different preferences correspond to different layout methods, thus establishing a mapping relationship between preference information, intent information, and layout method information. Layout method information includes information on various layout methods, such as the size proportion of object display containers on the page, row and column relationships, and information types. Different types of preferences can reflect users' preferences for different types of information. Combining the intent stage and intent type can determine the layout preference for the target intent type at the corresponding intent stage.

[0078] In one optional embodiment, determining the mapping relationship between the intent information and the preference information includes: determining the external layout mapping relationship of intent stage, intent type, aesthetic preference, and layout method information; and determining the internal layout mapping relationship of the intent stage, intent information, and information preference. The external layout mapping relationship is a layout mapping for the object display container on the page, and the internal layout mapping relationship is a mapping of the layout within the object display container.

[0079] Regarding the external layout mapping relationship, since aesthetic preferences can reflect preferences such as the proportion of the product object's image to the size of the object display container, and the density of its arrangement, a width-to-height ratio biased towards a certain target can be selected within the aspect ratio range, thereby determining the size ratio of the display container. Furthermore, the content the user focuses on may differ at different intent stages; therefore, the size ratio can be adjusted based on the user's intent, resulting in the corresponding external layout mapping relationship. A mapping relationship can be established between intent stage, intent type, aesthetic preference, and layout method information. Aesthetic preference corresponds to the layout and proportion information of the object display container on the page, thus obtaining the external layout mapping relationship corresponding to the intent stage, intent type, aesthetic preference, and layout method information. An example of an external layout mapping relationship is shown in Table 1:

[0080]

[0081]

[0082] Regarding the internal layout mapping relationship, since descriptive information can serve as a basis for users' evaluation and decision-making regarding products, selecting the appropriate type of descriptive information can improve users' evaluation of the product. Therefore, different descriptive information does not have an equal status in the display container. Based on the intent stage, it can be determined that the core task of the displayed content within the object display container for this product object is to attract, introduce, or persuade; based on the intent type, it can be determined that the displayed content for this product object should emphasize the information type required for attracting, introducing, or persuading. This results in a mapping relationship containing two input quantities: user intent stage and intent product type, and one output quantity: the type of descriptive information to be highlighted based on information preferences. Table 2 below shows an example of such a mapping relationship:

[0083]

[0084]

[0085] The aforementioned information preferences can determine the descriptive information highlighted in the object display container. When there are multiple descriptive information options, one or more options can be randomly selected, depending on the settings of the descriptive information in the object display container.

[0086] Step 208: Determine the page layout information corresponding to the intent stage based on the mapping relationship. The page layout information includes: external layout information and internal layout information.

[0087] Once the mapping relationship is established, the page layout information for the user at different intent stages can be determined. This page layout information includes both external and internal layout information. The external layout information is the overall layout of the page, including the layout of the title, object display containers, etc., while the internal layout information is the layout information within the object display containers.

[0088] In this embodiment of the application, the visual style information of the description information can be classified according to the description information type (hereinafter referred to as type), color information, and visual level (hereinafter referred to as level):

[0089] 1) Type: Used to distinguish the content of the descriptive information.

[0090] 2) Color: Used to ensure visual harmony. For example, classifying colors according to the warmth or coolness of the main color tone can be extended to other more detailed color classification methods.

[0091] 3) Rating: This rating is used to evaluate the visual style's ability to influence users; a strong influence indicates a prominent presentation. It is evaluated based on the size, color, and other visual elements of a design. For example, it can be graded from low to high visual intensity as 1, 2, and 3.

[0092] In one optional embodiment, determining the page layout information corresponding to the intent stage based on the mapping relationship includes: determining the external layout information corresponding to the intent stage based on the external mapping relationship and visual style information; and determining the internal layout information corresponding to the intent stage based on the internal mapping relationship and visual style information. Specifically, determining the external layout information corresponding to the intent stage based on the external mapping relationship and visual style information includes: determining the intent type, aesthetic preference, and layout method information corresponding to the intent stage based on the external mapping relationship; and determining the page's color scheme based on the color information in the visual style information. Determining the internal layout information corresponding to the intent stage based on the internal mapping relationship and visual style information includes: determining the intent type and information preference corresponding to the intent stage based on the internal mapping relationship; and determining the information quantity, information level, and information color based on the visual style information.

[0093] By statistically analyzing various pages and their display effects, the range of descriptive information corresponding to containers of different sizes was determined. An example is shown in Table 3 below:

[0094] Size ratio (Description information) Quantity Level and 3:4 1，2，3 2，3，4，5 3:5 2，3，4 5，6，7 3:6 2，3，4 6，7，8 3:7 3，4，5 6，7，8，9 2:1 4，5 9，10，11，12 5:2 1，2，3 3，4，5，6 5:4 1，2，3，4 3，4，5，6

[0095] The above is an example. In actual processing, the size ratio is not one of 3:4, 3:5, 3:6, 3:7, 5:4, 5:2, or 2:1, but is still within the above-mentioned ratio fluctuation range; or the removal, replacement, or addition of individual size ratios are all within the scope of the embodiments of this application.

[0096] After determining the descriptive information type corresponding to each intent stage, the inner and outer layouts can be determined based on visual style information. The layout information within an object display container is shown below:

[0097] 1) The quantity of descriptive information should be within the range of information quantity, such as the range in the "Quantity" column of Table 3;

[0098] 2) The highlighted descriptive information has the highest visual style among all descriptive information;

[0099] 3) The sum of the "levels" of each descriptive information is within the specified range, such as the range in the "Sum of Levels" column of Table 3;

[0100] 4) The colors of each descriptive piece of information match;

[0101] Based on the above method, several design elements (UI materials) with different visual styles, levels, and consistent colors can be obtained and applied to the page layout process. This reveals the constraints of the container's external layout on the number of elements within the container, and the constraints of the selection preferences for descriptive information on the visual style of the information, thereby simplifying the selection process of design elements.

[0102] This allows for the determination of intent types and preferences at different intent stages based on the correspondence, and then, combined with visual style information, the determination of page layout information, including page colors, external layout information such as the number of rows and columns and size ratios of object display containers on the page, and internal layout information such as the size of images, the amount and level of descriptive information within object display containers. The corresponding page elements can also be selected based on this layout information.

[0103] Step 210: Upon receiving a page request, determine the page layout information for the intent stage corresponding to the request and generate the corresponding page.

[0104] When a user visits a page, they can issue a page request. The user's current intent stage can be determined based on their previous behavior. This allows for the acquisition of page layout information corresponding to that intent stage, along with the relevant page elements. These elements are then arranged according to the page layout information to generate the corresponding page. Specifically, determining the page layout information corresponding to the intent stage of the request and generating the corresponding page includes: determining the user's current intent stage based on the page request; acquiring the page layout information corresponding to that intent stage; determining the page elements based on the page layout information; and arranging the page elements according to the page layout information to generate the corresponding page. The page request may carry the intent stage, or the user's intent stage may be determined after receiving the page request. For example, if the user has previously browsed the page and transmitted relevant browsing behavior data, the current intent stage can be determined based on this browsing behavior data. Upon receiving the request, this intent stage is identified as the user's current intent stage. Then, the page layout information corresponding to this intent stage is determined. Based on this page layout information, the required page elements, including images, text, links, and other elements, can be selected and arranged according to the page layout information to generate the corresponding page. Specifically, page elements are laid out based on internal layout information to obtain the display content of each object's display container; the display content of each object's display container is then laid out according to the external layout information to determine the page data and generate the corresponding page.

[0105] In this embodiment, network model algorithms can also be used to automatically generate pages. For example, a Generative Adversarial Network (GAN) algorithm can be used to generate the layout within a container given page layout information, such as the size ratio of the object display container and the design elements within the container. This includes determining the required page elements, such as cropped images of product objects and text information, generating the display content within the object display container and the page based on the page layout information, and obtaining the corresponding page data.

[0106] In summary, user browsing behavior data during page browsing can be acquired, analyzed, and used to determine user intent information, including intent stage and intent type. Then, a mapping relationship between the intent information and preference information is established to obtain the user's intent type and preferences at different intent stages. Based on this mapping relationship, the page layout information corresponding to the intent stage is determined, including external and internal layout information. Upon receiving a page request, the page layout information corresponding to the intent stage of the request is determined, and the corresponding page is generated. This allows for the determination of user intent based on user behavior and the generation of pages that match the user's intent, facilitating quick access to the required content and improving processing efficiency.

[0107] Based on the above embodiments, this application also provides a page processing method that can acquire browsing behavior data during a user's page access process, so as to provide the required page feedback in subsequent accesses.

[0108] Reference Figure 5 The diagram illustrates an example of page adjustment according to an embodiment of this application, which can adjust the page layout according to the user's browsing behavior, thereby providing the information needed by the user.

[0109] Reference Figure 6 The diagram illustrates a flowchart of another embodiment of the page processing method of this application.

[0110] Step 602: Detect the user's browsing behavior and record the corresponding browsing behavior data, which is used to determine the user's intent information.

[0111] The process of detecting user browsing behavior and recording corresponding browsing behavior data includes at least one of the following steps: detecting user browsing behavior on the page and recording the corresponding dwell time, using the dwell time as dwell information; detecting user click behavior during page browsing and recording the click object type and number of clicks as click information; and detecting user operation behavior during page browsing and recording the operation type and operation content as operation information.

[0112] Step 604: Upload the browsing behavior data.

[0113] Browsing behavior data can be uploaded in real time or periodically during the user's browsing process, such as once every 5 seconds.

[0114] Step 606: Send a page request.

[0115] As a user continues browsing a webpage, when the page meets certain conditions, a page request is generated and sent to continue displaying the page. For example, actions such as turning a page or scrolling down may trigger a page request to retrieve the corresponding page data for display. Furthermore, when returning to the page from other pages, such as returning from a product details page, a page request can also be generated and sent, thus enabling the issuance of a page request. Figure 5 You can send page requests to the server.

[0116] Step 608: Receive page data. The page data is determined based on the page layout information of the intent stage corresponding to the request. The page layout information of the intent stage is based on a mapping relationship, which is determined based on intent information and preference information.

[0117] Based on the above process, the server can analyze the user's browsing behavior data and determine intent information, thereby identifying the user's current intent stage and subsequently determining the corresponding page data for that intent stage, which is then returned to the client. For example... Figure 5 The server sends the page data to the client.

[0118] Step 610: Parse the page data and display the corresponding page.

[0119] The client-side can parse the page data and then display the corresponding page. For example... Figure 5 Subsequent user requests can change the page layout, making it easier for users to obtain the information they need.

[0120] Based on the above embodiments, this application also provides a page processing method that can analyze user intent and generate pages that meet user needs based on browsing behavior data during the user's page access process.

[0121] Reference Figure 7 The diagram illustrates a flowchart of an optional embodiment of a page processing method according to this application.

[0122] Step 702: Obtain user browsing behavior data during the page browsing process.

[0123] Step 704: Analyze the browsing behavior data to determine the corresponding intent stage.

[0124] The analysis of the browsing behavior data to determine the corresponding intent stage includes: determining the intent stage as a first intent stage based on the behavior of launching the page; determining the intent stage as a second intent stage when the first dwell time on the page exceeds a first time threshold; determining the intent stage as a third intent stage when the number of clicks on the object display container on the page exceeds a number threshold; determining the intent stage as a fourth intent stage when the second dwell time on the object page exceeds a second time threshold, wherein the object page is launched based on the click on the object display container; and determining the intent stage as a fifth intent stage when the operation behavior on the object page is the target operation behavior.

[0125] Step 706: Determine the browsing type corresponding to the intent stage, and select the type that meets the intent conditions as the intent type.

[0126] The step of determining the browsing type corresponding to the intent stage and selecting a type that meets the intent conditions as the intent type includes: determining the type corresponding to the browsing object and determining the intent stage corresponding to the type; and selecting a type that meets the intent conditions in the intent stage as the intent type.

[0127] Step 708: Determine the external layout mapping relationship of intent stage, intent type, aesthetic preference and layout method information.

[0128] Step 710: Determine the internal layout mapping relationship of the intent stage, intent information, and information preference.

[0129] Step 712: Determine the external layout information corresponding to the intent stage based on the external mapping relationship and visual style information.

[0130] Step 714: Determine the internal layout information corresponding to the intent stage based on the internal mapping relationship and visual style information.

[0131] Step 716: Determine the user's intent stage based on the page request, and obtain the page layout information corresponding to the intent stage.

[0132] Step 718: Determine page elements based on the page layout information, arrange the page elements according to the page layout information, and generate the corresponding page.

[0133] This application's embodiments incorporate diverse online behavioral data for processing user intent. By using browsing behavior data to determine real-time intent, the ability to interpret and guide user behavior in real time is significantly improved compared to traditional user profiling methods. Furthermore, this application's embodiments can automatically generate pages using algorithms, reducing or replacing some of the interface design work for designers. It can quickly generate a large amount of display content for product objects that meets requirements for container layout, prominent information presentation, visual style differences, and uniformity, thereby improving design and development efficiency.

[0134] Furthermore, in the UI layout generation process, the embodiments of this application include the outer layout of the container, the description information inside the container, and their visual styles into the scope of personalized generation, which improves the diversity of the layout and strengthens the ability to guide users in both visual and informational aspects.

[0135] This application's embodiments study and analyze the design space in the navigation page (or shopping guide page) of an e-commerce app, proposing design elements with significant influence and empirical constraints between some design elements, such as the constraint relationship between the layout outside the container and the constraint relationship between the selection preference of descriptive information and the visual style of the information, thereby simplifying the selection process of design elements.

[0136] This application extends the application of real-time user behavior data and user profiles, predicts behavior based on user online behavior sequences, and innovatively links the user's real-time intent with the selection and arrangement of UI design elements, enabling the shopping guide UI to change with the user's intent, further meeting the user's current needs and enhancing the user's exploration and interest.

[0137] Using adversarial neural networks to generate content displayed within containers enables the large-scale generation of product object content that conforms to design principles, thus achieving intelligent UI design. This intelligent generation technology, combined with user intent and long-term user preferences for selecting design elements (container layout, information content, and information style), achieves personalized UI design.

[0138] It should be noted that, for the sake of simplicity, the method embodiments are all described as a series of actions. However, those skilled in the art should understand that the embodiments of this application are not limited to the described order of actions, because according to the embodiments of this application, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also understand that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of this application.

[0139] Based on the above embodiments, this embodiment also provides a page processing device, which is applied to an electronic device used in a server-side device (cluster) of an e-commerce website.

[0140] The module acquires user browsing behavior data during the page browsing process.

[0141] The intent analysis module is used to analyze the browsing behavior data to determine the user's intent information, which includes intent stage and intent type.

[0142] The mapping module is used to determine the user's preference information and the mapping relationship between the intent information and the preference information.

[0143] The layout determination module is used to determine the page layout information corresponding to the intent stage based on the mapping relationship. The page layout information includes: external layout information and internal layout information.

[0144] The page generation module is used to determine the page layout information of the intent stage corresponding to the request and generate the corresponding page when a page request is received.

[0145] In summary, user browsing behavior data during page browsing can be acquired, analyzed, and used to determine user intent information, including intent stage and intent type. Then, a mapping relationship between the intent information and preference information is established to obtain the user's intent type and preferences at different intent stages. Based on this mapping relationship, the page layout information corresponding to the intent stage is determined, including external and internal layout information. Upon receiving a page request, the page layout information corresponding to the intent stage of the request is determined, and the corresponding page is generated. This allows for the determination of user intent based on user behavior and the generation of pages that match the user's intent, facilitating quick access to the required content and improving processing efficiency.

[0146] Optionally, obtaining at least one of the following browsing behavior data of the user during page browsing includes at least one of the following steps: user dwell information during page browsing, the dwell information including: dwell time; click information of user click behavior during page browsing, the click information including: click object type and click count; operation information of user operation behavior during page browsing, the operation information including: operation type and operation content.

[0147] Optionally, the intent analysis module includes a stage analysis submodule and a type analysis submodule, wherein:

[0148] The stage analysis submodule is used to analyze the browsing behavior data and determine the corresponding intent stage;

[0149] The type analysis submodule is used to determine the browsing type corresponding to the intent stage and select the type that meets the intent conditions as the intent type.

[0150] Optionally, the stage analysis submodule is used to determine the intent stage as a first intent stage based on the behavior of the launch page; when the first dwell time on the page exceeds a first time threshold, the intent stage is determined as a second intent stage; when the number of clicks on the object display container on the page exceeds a number threshold, the intent stage is determined as a third intent stage; when the second dwell time on the object page exceeds a second time threshold, the intent stage is determined as a fourth intent stage, and the object page is launched based on the click on the object display container; when the operation behavior on the object page is the target operation behavior, the intent stage is determined as a fifth intent stage.

[0151] Optionally, the type analysis submodule is used to determine the type corresponding to the browsed object and determine the intent stage corresponding to the type; and select the type that meets the intent conditions in the intent stage as the intent type.

[0152] Optionally, the mapping module is used to determine the external layout mapping relationship of intent stage, intent type, aesthetic preference and layout method information; and to determine the internal layout mapping relationship of intent stage, intent information and information preference.

[0153] Optionally, the layout determination module is used to determine the external layout information corresponding to the intent stage based on the external mapping relationship and visual style information; and to determine the internal layout information corresponding to the intent stage based on the internal mapping relationship and visual style information.

[0154] Optionally, the page generation module is used to determine the user's intent stage based on the page request, obtain page layout information corresponding to the intent stage, determine page elements based on the page layout information, and arrange the page elements according to the page layout information to generate the corresponding page.

[0155] This application's embodiments incorporate diverse online behavioral data for processing user intent. By using browsing behavior data to determine real-time intent, the ability to interpret and guide user behavior in real time is significantly improved compared to traditional user profiling methods. Furthermore, this application's embodiments can automatically generate pages using algorithms, reducing or replacing some of the interface design work for designers. It can quickly generate a large amount of display content for product objects that meets requirements for container layout, prominent information presentation, visual style differences, and uniformity, thereby improving design and development efficiency.

[0156] Furthermore, in the UI layout generation process, the embodiments of this application include the outer layout of the container, the description information inside the container, and their visual styles into the scope of personalized generation, which improves the diversity of the layout and strengthens the ability to guide users in both visual and informational aspects.

[0157] This application's embodiments study and analyze the design space in the navigation page (or shopping guide page) of an e-commerce app, proposing design elements with significant influence and empirical constraints between some design elements, such as the constraint relationship between the layout outside the container and the constraint relationship between the selection preference of descriptive information and the visual style of the information, thereby simplifying the selection process of design elements.

[0158] This application extends the application of real-time user behavior data and user profiles, predicts behavior based on user online behavior sequences, and innovatively links the user's real-time intent with the selection and arrangement of UI design elements, enabling the shopping guide UI to change with the user's intent, further meeting the user's current needs and enhancing the user's exploration and interest.

[0159] Using adversarial neural networks to generate content displayed within containers enables the large-scale generation of product object content that conforms to design principles, thus achieving intelligent UI design. This intelligent generation technology, combined with user intent and long-term user preferences for selecting design elements (container layout, information content, and information style), achieves personalized UI design.

[0160] This application also provides a non-volatile readable storage medium storing one or more modules (programs). When these modules are applied to a device, they enable the device to execute the instructions for the method steps in this application.

[0161] This application provides one or more machine-readable media storing instructions that, when executed by one or more processors, cause an electronic device to perform one or more of the methods described in the above embodiments. In this application, the electronic device includes various types of devices such as terminal devices and servers (clusters).

[0162] The embodiments of this disclosure can be implemented as an apparatus configured to use any suitable hardware, firmware, software, or any combination thereof, including electronic devices such as terminal devices, servers (clusters), etc., within a data center. Figure 8 An exemplary apparatus 800 is schematically shown that can be used to implement the various embodiments described in this application.

[0163] In one embodiment, Figure 8An exemplary device 800 is shown, which includes one or more processors 802, a control module (chipset) 804 coupled to at least one of the processors 802, a memory 806 coupled to the control module 804, a non-volatile memory (NVM) / storage device 808 coupled to the control module 804, one or more input / output devices 810 coupled to the control module 804, and a network interface 812 coupled to the control module 804.

[0164] Processor 802 may include one or more single-core or multi-core processors, and processor 802 may include any combination of general-purpose processors or special-purpose processors (e.g., graphics processors, application processors, baseband processors, etc.). In some embodiments, device 800 can serve as a terminal device, server (cluster), or other device as described in the embodiments of this application.

[0165] In some embodiments, apparatus 800 may include one or more computer-readable media (e.g., memory 806 or NVM / storage device 808) having instructions 814 and one or more processors 802 that are combined with the one or more computer-readable media and configured to execute the instructions 814 to implement the module and thus perform the actions described in this disclosure.

[0166] In one embodiment, the control module 804 may include any suitable interface controller to provide any suitable interface to at least one of the processors 802 and / or any suitable device or component communicating with the control module 804.

[0167] The control module 804 may include a memory controller module to provide an interface to the memory 806. The memory controller module may be a hardware module, a software module, and / or a firmware module.

[0168] Memory 806 may be used, for example, to load and store data and / or instructions 814 for device 800. In one embodiment, memory 806 may include any suitable volatile memory, such as suitable DRAM. In some embodiments, memory 806 may include double data rate type quad synchronous dynamic random access memory (DDR4 SDRAM).

[0169] In one embodiment, the control module 804 may include one or more input / output controllers to provide an interface to the NVM / storage device 808 and (one or more) input / output devices 810.

[0170] For example, NVM / storage device 808 may be used to store data and / or instructions 814. NVM / storage device 808 may include any suitable non-volatile memory (e.g., flash memory) and / or may include any suitable (one or more) non-volatile storage devices (e.g., one or more hard disk drives (HDDs), one or more optical disc drives (CDs), and / or one or more digital universal optical disc (DVD) drives).

[0171] NVM / storage device 808 may include storage resources that are physically part of a device on which device 800 is mounted, or that are accessible to the device but do not necessarily have to be part of the device. For example, NVM / storage device 808 may be accessed via a network via one or more input / output devices 810.

[0172] One or more input / output devices 810 may provide an interface for device 800 to communicate with any other suitable device. Input / output devices 810 may include communication components, audio components, sensor components, etc. A network interface 812 may provide an interface for device 800 to communicate via one or more networks. Device 800 may wirelessly communicate with one or more components of a wireless network according to any of one or more wireless network standards and / or protocols, such as accessing a wireless network based on a communication standard, such as WiFi, 2G, 3G, 4G, 5G, etc., or a combination thereof.

[0173] In one embodiment, at least one of the processors 802 may be logically packaged with one or more controllers (e.g., memory controller modules) of the control module 804. In one embodiment, at least one of the processors 802 may be logically packaged with one or more controllers of the control module 804 to form a system-in-package (SiP). In one embodiment, at least one of the processors 802 may be integrated with the logic of one or more controllers of the control module 804 on the same die. In one embodiment, at least one of the processors 802 may be integrated with the logic of one or more controllers of the control module 804 on the same die to form a system-on-a-chip (SoC).

[0174] In various embodiments, device 800 may be, but is not limited to, a server, desktop computing device, or mobile computing device (e.g., laptop, handheld computing device, tablet, netbook, etc.). In various embodiments, device 800 may have more or fewer components and / or different architectures. For example, in some embodiments, device 800 includes one or more cameras, a keyboard, a liquid crystal display (LCD) screen (including a touchscreen display), a non-volatile memory port, multiple antennas, a graphics chip, an application-specific integrated circuit (ASIC), and a speaker.

[0175] The detection device can use a main control chip as a processor or control module, and sensor data, position information, etc. can be stored in a memory or NVM / storage device. The sensor group can be used as an input / output device, and the communication interface can include a network interface.

[0176] As the device embodiment is basically similar to the method embodiment, the description is relatively simple, and relevant parts can be found in the description of the method embodiment.

[0177] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0178] This application describes embodiments with reference to flowchart illustrations and / or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of this application. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, generate instructions for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0179] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing terminal device to operate in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0180] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal equipment, causing a series of operational steps to be performed on the computer or other programmable terminal equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable terminal equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0181] Although preferred embodiments of the present application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of the embodiments of the present application.

[0182] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or terminal device. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or terminal device that includes said element.

[0183] The foregoing has provided a detailed description of a page processing method, a terminal device, and a machine-readable medium provided in this application. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for processing a webpage, characterized in that, The method includes: Obtain user browsing behavior data during the page browsing process; The browsing behavior data is analyzed to determine the corresponding intent stage; The type of browsing corresponding to the intent stage is determined, and the type that meets the intent conditions is selected as the intent type. The intent information includes the intent stage and the intent type. The intent stages have a progressive hierarchical relationship. As the user's browsing behavior progresses, the user enters the corresponding intent stage. The intent type is the type of the product object. Determine the user's preference information, and determine the mapping relationship between the intent information and the preference information, wherein the preference information includes: aesthetic preferences; Based on the mapping relationship, the page layout information corresponding to the intent stage is determined, and the page layout information includes: external layout information and internal layout information; Upon receiving a page request, determine the page layout information for the intent stage corresponding to the request and generate the corresponding page; The step of analyzing the browsing behavior data to determine the corresponding intent stage includes: Based on the behavior of the launch page, the intent phase is determined to be the first intent phase; When the first dwell time on the page exceeds the first time threshold, the intent stage is determined to be the second intent stage; When the number of clicks on the object display container on the page exceeds the number of clicks threshold, the intent stage is determined to be the third intent stage; When the second dwell time on the object page exceeds the second time threshold, the intent stage is determined to be the fourth intent stage, and the object page is launched based on the click on the object display container; When the operation behavior on the object page is the target operation behavior, the intent stage is determined to be the fifth intent stage.

2. The method according to claim 1, characterized in that, The method involves obtaining at least one of the following browsing behavior data from the user during the page browsing process: User dwell information during page browsing, including dwell time; Click information of a user's click behavior during page browsing, the click information including: the type of object clicked and the number of clicks; The operation information includes the user's actions during page browsing, including the operation type and operation content.

3. The method according to claim 1, characterized in that, The step of determining the browsing type corresponding to the intent stage and selecting a type that meets the intent conditions as the intent type includes: Determine the type of the object being browsed, and determine the intent stage corresponding to that type; Select the type that meets the intent conditions in the intent phase as the intent type.

4. The method according to claim 1, characterized in that, Determining the mapping relationship between the intent information and the preference information includes: Determine the external layout mapping relationship based on intent stage, intent type, aesthetic preference, and layout method information; Determine the internal layout mapping relationship between the intent stage, intent information, and information preferences.

5. The method according to claim 4, characterized in that, Determining the page layout information corresponding to the intent stage based on the mapping relationship includes: The external layout information corresponding to the intent stage is determined based on the external mapping relationship and visual style information; The internal layout information corresponding to the intent stage is determined based on the internal mapping relationship and visual style information.

6. The method according to claim 1, characterized in that, Determining the page layout information for the intent stage corresponding to the request and generating the corresponding page includes: Determine the user's intent stage based on the page request, and obtain the page layout information corresponding to the intent stage; Based on the page layout information, determine the page elements, arrange the page elements according to the page layout information, and generate the corresponding page.

7. An electronic device, characterized in that, include: processor; and A memory having executable code stored thereon, which, when executed, causes the processor to perform the method as described in any one of claims 1-6.

8. One or more machine-readable media having executable code stored thereon, which, when executed, causes a processor to perform the method as described in any one of claims 1-6.

Images