Commodity information display method based on user behaviors and related equipment

Abstract

The invention provides a commodity information display method based on user behaviors, and the method comprises the steps: obtaining the historical shopping behavior data of a user in a preset time period and the commodity data of a target commodity when the user clicks to enter a commodity page of the target commodity; if the historical shopping behavior data comprises first historical shopping behavior data corresponding to the target commodity, generating a first commodity display interface of the target commodity based on the commodity data and the first historical shopping behavior data; if the historical shopping behavior data does not include the first historical shopping behavior data corresponding to the target commodity, generating a second commodity display interface of the target commodity based on the commodity data and the historical shopping behavior data; and displaying the first commodity display interface or the second commodity display interface to a user. The personalized commodity display meets the instant demand of the user, the re-purchase guide strategy of the first interface can significantly improve the user experience, and the trust and dependence of the user on the platform are enhanced.

Description

Technical Field

[0001] The present invention relates to the field of video processing technology, and in particular to a commodity information display method based on user behavior and related equipment. Background Art

[0002] With the rapid development of Internet technology, e-commerce has become an indispensable part of people's daily life. With the rapid development of e-commerce platforms and the continuous expansion of user scale, personalized recommendation technology has become a core means to enhance user shopping experience and promote consumption conversion. Traditional e-commerce platforms generally adopt recommendation algorithms based on user behavior analysis to achieve product recommendations through historical browsing, collection, and add-to-cart data.

[0003] However, in terms of the display dimension of product details pages, existing technologies mostly use static display templates, which fail to fully consider the deep impact of individual user behavior differences on the way information is presented. Especially in the scenario where users enter a specific product page, existing systems usually use a unified product description framework and lack a dynamic adaptation mechanism for users' existing cognition (such as historical purchase records), resulting in redundant information received when making repeated purchases, and first-time purchases face information cognition faults and are unable to quickly locate content of interest. In addition, as the proportion of mobile shopping increases, user attention resources are becoming increasingly scarce. How to accurately reach personalized information within a limited screen effect has become an urgent problem that needs to be solved. Summary of the invention

[0004] The embodiment of the present invention provides a method for displaying commodity information based on user behavior, which aims to provide users with personalized commodity information display based on user behavior. When a user has historical shopping behavior data for a target commodity, a personalized display interface can highlight details or preferential information that the user may be concerned about, and enhance the user's willingness to buy. The personalized commodity display not only meets the user's immediate needs and improves the user experience, but also enhances the user's trust and reliance on the platform.

[0005] In a first aspect, an embodiment of the present invention provides a method for displaying product information based on user behavior, the method comprising: When a user clicks to enter the product page of a target product, the user's historical shopping behavior data within a preset time period and the product data of the target product are obtained; If the historical shopping behavior data includes first historical shopping behavior data corresponding to the target product, generating a first product display interface of the target product based on the product data and the first historical shopping behavior data; If the historical shopping behavior data does not include the first historical shopping behavior data corresponding to the target product, generating a second product display interface of the target product based on the product data and the historical shopping behavior data; The first product display interface or the second product display interface is displayed to the user.

[0006] Optionally, the step of generating a first product display interface of the target product based on the product data and the first historical shopping behavior data includes: Extracting the first browsing data and the first purchasing data of the user for the target product from the first historical shopping behavior data, wherein the first browsing data includes a plurality of first interface images corresponding to a display window in which the user does not operate for more than a first preset time period when browsing the target product, and the first purchasing data is the first selection data of the user when purchasing the target product; Generate a plurality of first pages based on the commodity data, the first browsing data, and the first purchase data; Based on the plurality of the first pages, a first commodity display interface of the target commodity is generated.

[0007] Optionally, the step of generating a plurality of first pages from the commodity data, the first browsing data, and the first purchase data includes: Determining at least one first representative image from among the plurality of first interface images according to the content data corresponding to the first interface image; For each of the first representative graphs, determining a weight value of the first representative graph based on a residence time and a data volume of content data corresponding to the first representative graph; Determining, from the commodity data, target commodity content data whose similarity to the content data corresponding to the first representative graph is greater than a first preset similarity threshold; Based on the target product content data, the first purchase data and the weight value, a first long page corresponding to the first representative image is generated, and based on the first remaining product content data that is not matched in the product data, a corresponding first short page is generated, and the page length of the first long page is greater than the page length of the first short page.

[0008] Optionally, the step of determining at least one first representative image from a plurality of first interface images according to the content data corresponding to the first interface image includes: Calculating the image similarity between the first interface images according to the content data corresponding to the first interface images; Based on the image similarity between the first interface images, a plurality of the first interface images are divided into a first-category interface image set and / or a second-category interface image set, wherein the first-category interface image set includes a plurality of the first interface images, and the image similarity between any two of the first interface images in the first-category interface image set is greater than or equal to an image similarity threshold, and the second-category interface image set includes only one of the first interface images, and the image similarity between the first interface images in the second-category interface image set and any one of the first interface images in other interface image sets is less than the image similarity threshold; For each first-category interface image set, multiple first-category interface images in the first-category interface image set are spliced ​​and merged in the order of content data to obtain a first representative image of the first-category interface image set, and each first-category interface image set corresponds to one first representative image; For each set of the second-type interface images, the first interface image in the second-type interface image set is determined as the first representative image of the second-type interface image set, and each set of the second-type interface images corresponds to one first representative image.

[0009] Optionally, the step of generating a first product display interface of the target product based on the plurality of first pages includes: Performing focus prediction on the first page to predict the user's focus on the first page; Based on the focus of the first page, generating a focus sequence in page order, each first page corresponds to a focus of the first page; The focus distance between the focuses of two adjacent first pages in the focus sequence is used as a reference distance, and the reference distance is dynamically adjusted through a dynamic focus coefficient and a dynamic scrolling speed to obtain a dynamic splicing interval between two adjacent first pages, and the two adjacent first pages are spliced ​​based on the dynamic splicing interval.

[0010] Optionally, the step of generating a second product display interface of the target product based on the product data and the historical shopping behavior data includes: Filtering out second historical shopping behavior data corresponding to a reference product from the historical shopping behavior data, wherein the reference product has cross-level similarity with the target product; Extracting the second browsing data and second purchasing data of the user for non-target products from the second historical shopping behavior data, wherein the second browsing data includes a plurality of second interface images corresponding to a display window in which the user does not operate for more than a second preset time period when browsing the reference product, and the second purchasing data is the second selection data of the user for purchasing the reference product; Generate a plurality of second pages based on the commodity data, the second browsing data, and the second purchase data; Based on the plurality of second pages, a second product display interface of the target product is generated.

[0011] Optionally, the step of generating a plurality of second pages based on the commodity data, the second browsing data and the second purchase data includes: Determine at least one second representative image corresponding to each category of parameter products according to the content data corresponding to the second interface image; For at least one second representative graph corresponding to each category of parameter goods, determining reference goods content data in the goods data whose similarity to the content data corresponding to the second representative graph is greater than a second preset similarity; Based on the reference product content data and the second purchase data, a second long page corresponding to the second representative image is generated; based on the second remaining product content data that is not matched in the product data, a corresponding second short page is generated, and the page length of the second long page is greater than the page length of the second short page.

[0012] In a second aspect, an embodiment of the present invention further provides a commodity information display device based on user behavior, the commodity information display device based on user behavior comprising: An acquisition module, used to acquire the historical shopping behavior data of the user within a preset time period and the product data of the target product when the user clicks to enter the product page of the target product; A first generating module, configured to generate a first commodity display interface of the target commodity based on the commodity data and the first historical shopping behavior data if the historical shopping behavior data includes first historical shopping behavior data corresponding to the target commodity; a second generating module, configured to generate a second commodity display interface of the target commodity based on the commodity data and the historical shopping behavior data if the historical shopping behavior data does not include the first historical shopping behavior data corresponding to the target commodity; A display module is used to display the first product display interface or the second product display interface to the user.

[0013] In a third aspect, an embodiment of the present invention provides an electronic device, comprising: a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein when the processor executes the computer program, the steps of the method for displaying product information based on user behavior provided in an embodiment of the present invention are implemented.

[0014] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method for displaying product information based on user behavior provided in an embodiment of the invention are implemented.

[0015] In an embodiment of the present invention, when a user clicks to enter the product page of a target product, the user's historical shopping behavior data within a preset time period and the product data of the target product are obtained; if the historical shopping behavior data includes the first historical shopping behavior data corresponding to the target product, a first product display interface of the target product is generated based on the product data and the first historical shopping behavior data; if the historical shopping behavior data does not include the first historical shopping behavior data corresponding to the target product, a second product display interface of the target product is generated based on the product data and the historical shopping behavior data; the first product display interface or the second product display interface is displayed to the user. When the user has historical shopping behavior data for the target product, the present invention can highlight the details or preferential information that the user may be concerned about in terms of stock user operations, thereby enhancing the user's willingness to buy. The personalized product display meets the user's immediate needs, and the repurchase guidance strategy of the first interface can significantly improve the customer life cycle value, improve the user experience, and enhance the user's trust and dependence on the platform. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 is a flow chart of a method for displaying commodity information based on user behavior provided by an embodiment of the present invention; Figure 2 It is a structural schematic diagram of a commodity information display device based on user behavior provided by an embodiment of the present invention; Figure 3 It is a structural schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0019] like Figure 1 As shown, Figure 1 : is a method flow chart of a method for displaying product information based on user behavior provided by an embodiment of the present invention. The method for displaying product information based on user behavior comprises the steps of: 101. When a user clicks to enter a product page of a target product, historical shopping behavior data of the user within a preset time period and product data of the target product are obtained.

[0020] In an embodiment of the present invention, when a user opens a shopping software, the shopping software may list product covers, which may include product images and product names. The product images and product names may serve as links to product details. The user may click on the product link in the product cover on the terminal interface to enter the product page, which may include product prices, product descriptions, and product details pages. Different products correspond to different product images and product names, as well as different product prices, product descriptions, and product details pages.

[0021] The above-mentioned target product is the product selected or clicked by the user on the product cover.

[0022] The preset time period may be within one month or one year. The preset time period may be determined according to the type of the target product. Different types of products correspond to different preset time periods. For example, if the target product is a fast-moving consumer product, the preset time period may be set shorter. If the target product is a home appliance, the preset time period may be set longer.

[0023] The above-mentioned historical shopping behavior data includes the user's browsing data and purchase data for different commodities. The browsing data includes the user's stay interface, and the purchase data includes the user's purchase style, size, quantity, payment method, discount selection, etc.

[0024] Among them, when users use shopping software, they can obtain the user's browsing data and purchase data by calling the screenshot or screen recording function of the terminal with the user's authorization and consent, or they can obtain the user's browsing data and purchase data from the background (server) of the shopping software.

[0025] The product data of the target product may be content data in the product details page and comment data for the target product, etc. The product data may be obtained from the backend (server) of the shopping software.

[0026] 102. If the historical shopping behavior data includes first historical shopping behavior data corresponding to the target product, a first product display interface of the target product is generated based on the product data and the first historical shopping behavior data. In an embodiment of the present invention, after obtaining the user's historical shopping behavior data within a preset time period and the product data of the target product, the products browsed in the historical shopping behavior data can be compared with the target product to determine whether the product in the historical shopping behavior data is the same as the target product, that is, whether the target product has been purchased by the user within the preset time period, and it can be further determined whether the user's browsing behavior this time has an intention to repurchase.

[0027] If the historical shopping behavior data includes the first historical shopping behavior data corresponding to the target product, that is, the target product has been purchased by the user within a preset time period, it can be further determined that the user's browsing behavior this time has the intention to repurchase, and then based on the product data and the first historical shopping behavior data, a first product display interface for the target product is generated.

[0028] The first product display interface is used to personalize the display of content that the user is interested in based on the user's shopping behavior data for the target product within a preset time period, so that the user does not need to view other redundant information. Other redundant information corresponding to different users may be company introductions, endorsement pictures, etc.

[0029] 103. If the historical shopping behavior data does not include the first historical shopping behavior data corresponding to the target product, a second product display interface of the target product is generated based on the product data and the historical shopping behavior data.

[0030] In an embodiment of the present invention, if the historical shopping behavior data does not include the first historical shopping behavior data corresponding to the target product, that is, the target product has not been purchased by the user within a preset time period, it can be further determined that the user's browsing behavior this time does not have an intention to repurchase, but is a browsing of new products, and then based on the product data and the historical shopping behavior data, a second product display interface for the target product is generated.

[0031] The second product display interface is used to display the content that the user may be interested in the target product according to the shopping behavior data of the user for the non-target product in the preset time period, and to infer the user's interest in the target product through the user's interest in different products, and then generate a second product display interface for the user's interest in the target product. This allows the user to view the content that he or she is more interested in, such as the structural principle of the target product and the comments of the target product, and also reduces the user's browsing of other redundant information. The other redundant information corresponding to different users may be company introductions, endorsement pictures, etc.

[0032] 104. Display the first product display interface or the second product display interface to the user.

[0033] In the embodiment of the present invention, after obtaining the first commodity display interface or the second commodity display interface, the first commodity display interface or the second commodity display interface may be displayed on the terminal.

[0034] When the historical shopping behavior data includes the first historical shopping behavior data corresponding to the target product, only the first product display interface is displayed; when the historical shopping behavior data does not include the first historical shopping behavior data corresponding to the target product, only the second product display interface is displayed.

[0035] In an embodiment of the present invention, when a user clicks to enter the product page of a target product, the user's historical shopping behavior data within a preset time period and the product data of the target product are obtained; if the historical shopping behavior data includes the first historical shopping behavior data corresponding to the target product, a first product display interface of the target product is generated based on the product data and the first historical shopping behavior data; if the historical shopping behavior data does not include the first historical shopping behavior data corresponding to the target product, a second product display interface of the target product is generated based on the product data and the historical shopping behavior data; the first product display interface or the second product display interface is displayed to the user. When the user has historical shopping behavior data for the target product, the present invention can highlight the details or preferential information that the user may be concerned about in terms of stock user operations, thereby enhancing the user's willingness to buy. The personalized product display meets the user's immediate needs, and the repurchase guidance strategy of the first interface can significantly improve the customer life cycle value, improve the user experience, and enhance the user's trust and dependence on the platform.

[0036] It is understandable that in the specific implementation of this application, related data such as user data and historical shopping behavior data are involved. When the embodiments in this application are applied to specific products or technologies, user permission or consent is required, and the collection, use and processing of relevant data, as well as the training, deployment and calling of data models, must comply with relevant laws, regulations and standards of relevant countries and regions.

[0037] Optionally, the step of generating a first product display interface of the target product based on the product data and the first historical shopping behavior data includes: extracting the user's first browsing data and first purchase data for the target product from the first historical shopping behavior data, the first browsing data including several first interface images corresponding to a display window that the user did not operate for more than a first preset time when browsing the target product, and the first purchase data being the first selection data when the user purchased the target product; generating multiple first pages based on the product data, the first browsing data and the first purchase data; and generating the first product display interface of the target product based on the multiple first pages.

[0038] In an embodiment of the present invention, the above-mentioned historical shopping behavior data includes the user's browsing data and purchase data for different commodities, the browsing data includes the user's stay interface, and the purchase data includes the user's purchase style, size, quantity, payment method, discount selection, etc.

[0039] When it is determined that the historical shopping behavior data includes first historical shopping behavior data corresponding to the target product, browsing data corresponding to the target product can be extracted from the historical shopping behavior data as first browsing data, and purchase data corresponding to the target product can be extracted as first shopping data.

[0040] The first browsing data includes a number of first interface images corresponding to the user not operating the display window for more than a first preset time when browsing the target product, which can indicate that the user is interested in the content in the display window. With the user's knowledge and consent, the first interface image can be obtained by taking a screenshot or recording the display window when the user does not operate the display window for more than a first preset time when browsing the target product.

[0041] The first purchase data is the first selection data of the user when purchasing the target product, such as style, size, quantity, payment method, discount and other selection data, which can explain the user's purchase choice of the target product, and thus reduce the user's selection operation when the user repurchases.

[0042] The above-mentioned first page can display the product data and the first purchase data related to the first browsing data for the target product, that is, each first page will correspond to a product data related to the first browsing data and a first purchase data. In this way, when browsing the first page, the user can quickly understand the content of interest through the product data related to the first browsing data, and quickly select the style, size, quantity, payment method, and discount through the first purchase data to achieve fast repurchase, which satisfies the user's browsing of product information and the efficiency of repurchase.

[0043] The first product display interface can display the first page by sliding (such as sliding up and down, sliding left and right), and each sliding switches a first page for display.

[0044] It should be noted that the existing product data is generally displayed in the form of a detail page, and the detail page is in the form of a long picture. After browsing the detail page, you need to return to the purchase link to add purchases, select styles, quantities, payment methods, discounts and other selection operations. In the existing repurchase method, the entrance is in the completed order, and the repurchase is achieved by copying the data of the completed order. The user cannot browse the specific product data. When the product data needs to be re-determined, it is necessary to reopen the product details page for browsing. In this regard, the present invention uses product data, first browsing data and first purchase data to generate multiple first pages; based on multiple first pages, a first product display interface for the target product is generated. In the first product display interface, when the user browses each first page, the purchase data generated by the first purchase data in the first page can be used to quickly place an order, thereby forming a quick repurchase. That is, the user can quickly place an order on each first page, thereby improving the user's repurchase efficiency.

[0045] Optionally, the step of generating multiple first pages from product data, first browsing data and first purchase data includes: determining at least one first representative image from several first interface images based on the content data corresponding to the first interface image; determining a weight value of the first representative image for each first representative image based on the dwell time and the data volume of the content data corresponding to the first representative image; determining target product content data in the product data whose similarity with the content data corresponding to the first representative image is greater than a first preset similarity threshold; generating a first long page corresponding to the first representative image based on the target product content data, the first purchase data and the weight value, and generating a corresponding first short page based on the first remaining product content data that is not matched in the product data, wherein the page length of the first long page is greater than the page length of the first short page.

[0046] In an embodiment of the present invention, the first page may include a first long page and a first short page, wherein the first long page includes a horizontal width and a vertical height, wherein the width of the first long page is the same as or slightly larger than the width of the terminal interface (when it is slightly larger, the first long page can be slid left and right for browsing), and the height of the first long page is the same as or slightly larger than the height of the terminal interface (when it is slightly larger, the first long page can be slid up and down for browsing). The first short page includes a horizontal width and a vertical height, wherein the width of the first short page is smaller than the width of the terminal interface, and the height of the first long page is smaller than the height of the terminal interface.

[0047] Specifically, the first long page is used to display the product data and the first purchase data related to the first browsing data for the target product, that is, each first long page will correspond to a product data related to the first browsing data and a first purchase data. In this way, when browsing the first long page, the user can quickly understand the content of interest through the product data related to the first browsing data, and quickly select the style, size, quantity, payment method, and discount through the first purchase data to achieve fast repeat purchase, which satisfies the user's browsing of product information and the efficiency of repeat purchase.

[0048] The first short page is used to display other redundant information, that is, product data that users are not interested in. By dividing the long and short pages, users can reduce the amount and time of browsing other redundant information, and improve the browsing efficiency of users for target products.

[0049] Specifically, within a preset period of time, the user may purchase the target product multiple times, and each time the user purchases the target product, the user may focus on browsing multiple parts of the content, so there will be multiple first interface images.

[0050] The first interface image can be clustered to obtain multiple clusters, each of which includes at least one first interface image. The first interface image closest to the cluster center can be used as the first representative image of the cluster, that is, each cluster corresponds to a first representative image.

[0051] After the first representative graph is determined, for each first representative graph, the weight value of the first representative graph is determined based on the dwell time and the amount of content data corresponding to the first representative graph. The longer the dwell time and the larger the amount of data, the larger the weight value of the first representative graph. The weight value of the first representative graph is used to determine the ranking and page scrolling speed of the first long page corresponding to the first representative graph. The larger the weight value, the higher the ranking of the first long page and the slower the page scrolling speed.

[0052] The first representative image may be subjected to content recognition through image recognition technology (OCR recognition) to obtain content data of the first representative image, and target product content data whose similarity with the content data corresponding to the first representative image is greater than a first preset similarity threshold is determined in the product data based on the content data of the first representative image.

[0053] The target product content data, the first purchase data, and the weight value may be generated into a first long page corresponding to the scrolling speed through a text graph model.

[0054] For the first remaining product content data that is not matched in the product data, it means that it is not the content that the user is interested in. A brief summary data can be extracted from the first remaining product content data by means of summary extraction to form brief product content data, and the brief product content data is generated into a corresponding first short page by means of the text graph model. It should be noted that a faster scrolling speed can be set for the first short page, and at the same time, no purchase link is set for the first short page.

[0055] In a possible embodiment, the first short page can be spliced ​​between two first long pages, or folded under a related first long page, and can be viewed by clicking on the first long page.

[0056] In a possible embodiment, the first short page may also be linked to the corresponding first remaining product content data, so that the detailed product content data can be viewed.

[0057] Optionally, the step of determining at least one first representative image from a plurality of first interface images according to the content data corresponding to the first interface image includes: calculating the image similarity between the first interface images according to the content data corresponding to the first interface images; dividing the plurality of first interface images into a first-category interface image set and / or a second-category interface image set based on the image similarity between the first interface images, wherein the first-category interface image set includes a plurality of first interface images, and the image similarity between any two first interface images in the first-category interface image set is greater than or equal to an image similarity threshold; the second-category interface image set includes only one first interface image, and the image similarity between the first interface image in the second-category interface image set and any first interface image in other interface image sets is less than an image similarity threshold; for each first-category interface image set, splicing and merging the plurality of first interface images in the first-category interface image set in the order of the content data to obtain a first representative image of the first-category interface image set, and each first-category interface image set corresponds to a first representative image; for each second-category interface image set, determining the first interface image in the second-category interface image set as the first representative image of the second-category interface image set, and each second-category interface image set corresponds to a first representative image.

[0058] In an embodiment of the present invention, content extraction can be performed on the first interface image to obtain content data corresponding to the first interface image. Based on the content data corresponding to the first interface image, the image similarity between the first interface images is calculated. The more similar the content data is, the higher the image similarity between the first interface images is.

[0059] Put multiple first interface images whose similarity is greater than or equal to the image similarity threshold into the same interface image set to obtain a first-category interface image set. In the first-category interface image set, there are multiple first interface images. In the same first-category interface image set, the image similarity between any two first interface images is greater than or equal to the image similarity threshold.

[0060] In the same first-category interface image set, there will be identical content among multiple first interface images, and the identical content is the core content. There will also be some different content. For example, the identical content among the first interface images A, B, and C is 2, 3, and 4, and the different content is: the first interface image A has content 1, the first interface image B has content 5, and the first interface image C has content 6. At this time, the first interface images A, B, and C can be spliced ​​and merged in the order of content data (1, 2, 3, 4, 5) to obtain the first representative image of the first-category interface image set. At this time, the content data of the first representative image is 1, 2, 3, 4, 5.

[0061] The second type of interface diagram set contains a single first representative diagram, and therefore, the first representative diagram can be directly used as the first representative diagram of the second type of interface diagram set.

[0062] Optionally, based on multiple first pages, the step of generating a first product display interface for the target product includes: predicting the focus of the first page to obtain the user's focus on the first page; generating a focus sequence in page order based on the focus of the first page, with each first page corresponding to a focus of the first page; taking the focus distance between the focuses of two adjacent first pages in the focus sequence as a reference distance, dynamically adjusting the reference distance through a dynamic focus coefficient and a dynamic scrolling speed to obtain a dynamic splicing interval between two adjacent first pages, and splicing the two adjacent first pages based on the dynamic splicing interval.

[0063] In an embodiment of the present invention, for the first long page, the focus prediction can be realized by using the user's facial data captured by the terminal camera when the user browses the first interface image, and the user's eye focus direction is extracted through the user's facial data, so as to predict the user's focus on the first interface image according to the user's eye focus direction, and the user's focus on the first interface image is mapped to the first page to obtain the user's focus on the first page. For the first short page, the focus can be determined by determining the center of the area with the most concentrated content.

[0064] In the above first page, the order of the first long page is determined according to the weight value. The larger the weight value, the higher the ranking. The order of the first short page can be determined according to the content relevance of the first long page. The higher the relevance, the closer it is to the corresponding first long page. The above content relevance can be determined by the content similarity between the first long page and the first short page. The higher the content similarity, the greater the content relevance.

[0065] Specifically, the first short page whose content relevance is greater than the relevance threshold can be placed after the corresponding first long page or folded under the corresponding first long page. For the first short page whose content relevance to any first long page is less than the relevance threshold, the first short page can be placed after the last first long page or folded under the last first long page and randomly sorted.

[0066] The focus distance between the focuses of two adjacent first pages in the focus sequence is used as the reference distance. The two adjacent first pages may be a first long page and a first long page.

[0067] The reference distance is dynamically adjusted through a dynamic focus coefficient and a dynamic scrolling speed to obtain a dynamic splicing interval between two adjacent first pages, and the two adjacent first pages are spliced ​​based on the dynamic splicing interval.

[0068] The above dynamic focus coefficient can be expressed by the following formula:

[0069]

[0070]

[0071] Among them, r is the dynamic focus coefficient of the first two pages, is the height of the first page in front, is the width of the first previous page, is the height of the first page after, is the width of the first page after, is the distance from the focus to the upper edge of the first page in the previous first page, is the distance from the focus to the bottom edge of the first page in the previous page, is the distance from the focus to the left edge of the first page in the previous page, The distance from the focus point to the right edge of the first page in the previous page. is the distance from the focus to the upper edge of the first page in the back first page, is the distance from the focus to the bottom edge of the first page in the next page, is the distance from the focus to the left edge of the first page in the next page, The distance from the focus to the right edge of the first page in the next page. Indicates selection and The smallest one, Indicates selection and The smallest one, Indicates selection and The smallest one, Indicates selection and The smallest one.

[0072] The dynamic scrolling speed is determined according to the weight value of the first long page. The larger the weight value of the first long page is, the smaller the dynamic scrolling speed is; the smaller the weight value of the first long page is, the larger the dynamic scrolling speed is.

[0073] The reference distance is dynamically adjusted through a dynamic focus coefficient and a dynamic scrolling speed. The dynamic focus coefficient, the dynamic scrolling speed and the reference distance can be directly multiplied to obtain a dynamic splicing interval between two adjacent first pages.

[0074] After obtaining the dynamic splicing interval between the two first pages, the two adjacent first pages can be spliced ​​at the dynamic splicing interval, so that the first product display interface can display different product content data at adaptive intervals when automatically scrolling.

[0075] Optionally, the step of generating a second product display interface for the target product based on the product data and the historical shopping behavior data includes: screening out second historical shopping behavior data corresponding to the reference product from the historical shopping behavior data, where the reference product and the target product have cross-level similarity; extracting the user's second browsing data and second purchase data for non-target products from the second historical shopping behavior data, the second browsing data including several second interface images corresponding to a display window that the user did not operate for more than a second preset time when browsing the reference product, and the second purchase data being the user's second selection data for purchasing the reference product; generating multiple second pages based on the product data, the second browsing data and the second purchase data; and generating a second product display interface for the target product based on the multiple second pages.

[0076] In an embodiment of the present invention, if the historical shopping behavior data does not include the first historical shopping behavior data corresponding to the target product, that is, the target product has not been purchased by the user within a preset time period, it can be further determined that the user's browsing behavior this time does not have an intention to repurchase, but is a browsing of new products, and then based on the product data and the historical shopping behavior data, a second product display interface for the target product is generated.

[0077] The above-mentioned historical shopping behavior data includes the user's browsing data and purchase data for different commodities. The browsing data includes the user's stay interface, and the purchase data includes the user's purchase style, size, quantity, payment method, discount selection, etc.

[0078] When it is determined that the historical shopping behavior data includes the second historical shopping behavior data corresponding to the non-target product, the browsing data corresponding to the reference product can be extracted from the historical shopping behavior data as the second browsing data, and the purchase data corresponding to the target product can be extracted as the second shopping data. The above-mentioned reference product is an item with cross-level similarity to the target product. The cross-level similarity can include hierarchical similarities such as category association level and functional substitution level, among which, category association level: category association filtering (such as associating "waterproof mobile phone case" when searching for "sports camera"); functional substitution level: functional substitution matching (such as the similarity of "Bluetooth headset" and "sports bracelet" in wireless connection characteristics), etc. In the cross-level similarity, only when the similarity of each level is greater than the preset similarity, it will be identified as a reference product of the target product.

[0079] The second browsing data includes a number of second interface images corresponding to the second preset time period when the user browses the target product without operating the display window, which can indicate that the user is interested in the content in the display window. With the user's knowledge and consent, the second interface image can be obtained by taking a screenshot or recording the display window when the user browses the reference product without operating the display window for more than the second preset time period.

[0080] The second purchase data is the second selection data of the user when purchasing the target product, such as style, size, quantity, payment method, discount and other selection data, which can illustrate the user's purchase choice of the target product, thereby reducing the user's selection operation when the user repurchases.

[0081] The above-mentioned second page can display the product data and second purchase data related to the second browsing data for the reference product, that is, each second page will correspond to a product data related to the second browsing data and a second purchase data. The second purchase data can be predicted by a large model. For example, an input prompt word is constructed through a prompt word project: "The user has purchased the following products, and the corresponding purchase data is as follows: XXX, please output the user's purchase data for the target product", and the input is input into the large language model, and the large language model outputs the corresponding second purchase data. In this way, when browsing the second page, the user can quickly understand the content of interest through the product data related to the second browsing data, and quickly select the style, size, quantity, payment method, and discount through the second purchase data to achieve fast new purchases, which not only satisfies the user's browsing of product information, but also satisfies the efficiency of new purchases.

[0082] The second product display interface can display the second page by sliding (such as sliding up and down, sliding left and right), and each sliding switches a second page for display.

[0083] Optionally, the step of generating multiple second pages based on the product data, the second browsing data and the second purchase data includes: determining at least one second representative image corresponding to each category of reference products according to the content data corresponding to the second interface image; for the at least one second representative image corresponding to each category of reference products, determining in the product data reference product content data having a similarity with the content data corresponding to the second representative image that is greater than a second preset similarity; generating a second long page corresponding to the second representative image based on the reference product content data and the second purchase data, and generating a corresponding second short page based on the second remaining product content data that is not matched in the product data, the page length of the second long page being greater than the page length of the second short page.

[0084] In an embodiment of the present invention, the second page may also be a second long page and a second short page. The generation method of the second long page and the second short page is similar to the generation method of the first long page and the first short page. The difference is that there is at least one second representative image corresponding to multiple reference products in the second long page. Therefore, the second preset similarity needs to be lowered, that is, the second preset similarity is less than the first preset similarity.

[0085] In a possible embodiment, the second product display interface is obtained by splicing or folding the second page. The splicing method or folding method is the same as the splicing method or folding method of the first page in the first product display interface, and the effect is also the same, which is not repeated in the present invention.

[0086] like Figure 2As shown, an embodiment of the present invention provides a commodity information display device based on user behavior, and the commodity information display device based on user behavior includes: The acquisition module 201 is used to acquire the historical shopping behavior data of the user within a preset time period and the product data of the target product when the user clicks to enter the product page of the target product; A first generating module 202, configured to generate a first commodity display interface of the target commodity based on the commodity data and the first historical shopping behavior data if the historical shopping behavior data includes first historical shopping behavior data corresponding to the target commodity; A second generating module 203, configured to generate a second commodity display interface of the target commodity based on the commodity data and the historical shopping behavior data if the historical shopping behavior data does not include the first historical shopping behavior data corresponding to the target commodity; The display module 204 is used to display the first product display interface or the second product display interface to the user.

[0087] Optionally, the first generation module 202 is also used to extract the user's first browsing data and first purchase data for the target product from the first historical shopping behavior data, the first browsing data including several first interface images corresponding to a display window in which the user has not operated the display window for more than a first preset time when browsing the target product, and the first purchase data is the first selection data when the user purchases the target product; based on the product data, the first browsing data and the first purchase data, multiple first pages are generated; based on the multiple first pages, a first product display interface of the target product is generated.

[0088] Optionally, the first generation module 202 is also used to determine at least one first representative image from several first interface images based on the content data corresponding to the first interface image; determine, for each first representative image, a weight value of the first representative image based on the dwell time and the data volume of the content data corresponding to the first representative image; determine in the product data target product content data whose similarity with the content data corresponding to the first representative image is greater than a first preset similarity threshold; generate a first long page corresponding to the first representative image based on the target product content data, the first purchase data and the weight value, and generate a corresponding first short page based on the first remaining product content data that is not matched in the product data, the page length of the first long page being greater than the page length of the first short page.

[0089] Optionally, the first generation module 202 is further used to calculate the image similarity between the first interface images according to the content data corresponding to the first interface images; based on the image similarity between the first interface images, divide a number of the first interface images into a first-category interface image set and / or a second-category interface image set, the first-category interface image set includes a plurality of the first interface images, the image similarity between any two of the first interface images in the first-category interface image set is greater than or equal to an image similarity threshold, the second-category interface image set includes only one first interface image, and the image similarity between the first interface image in the second-category interface image set and any one of the first interface images in other interface image sets is less than the image similarity threshold; for each of the first-category interface image sets, splice and merge the plurality of the first interface images in the first-category interface image set in the order of the content data to obtain a first representative image of the first-category interface image set, and each of the first-category interface image sets corresponds to one first representative image; for each of the second-category interface image sets, determine the first interface image in the second-category interface image set as the first representative image of the second-category interface image set, and each of the second-category interface image sets corresponds to one first representative image.

[0090] Optionally, the first generation module 202 is also used to predict the focus of the first page, predict the user's focus on the first page; based on the focus of the first page, generate a focus sequence in page order, and each first page corresponds to a focus of the first page; use the focus distance between the focuses of two adjacent first pages in the focus sequence as a reference distance, dynamically adjust the reference distance through a dynamic focus coefficient and a dynamic scrolling speed to obtain a dynamic splicing interval between two adjacent first pages, and splice two adjacent first pages based on the dynamic splicing interval.

[0091] Optionally, the second generation module 203 filters out second historical shopping behavior data corresponding to a reference product from the historical shopping behavior data, and the reference product has cross-level similarity with the target product; extracts the user's second browsing data and second purchase data for non-target products from the second historical shopping behavior data, the second browsing data including several second interface images corresponding to a display window in which the user browses the reference product for more than a second preset time without operating the display window, and the second purchase data is the user's second selection data for purchasing the reference product; generates multiple second pages based on the product data, the second browsing data and the second purchase data; and generates a second product display interface for the target product based on the multiple second pages.

[0092] Optionally, the second generation module 203 determines at least one second representative image corresponding to each category of parameter products based on the content data corresponding to the second interface image; for the at least one second representative image corresponding to each category of parameter products, determines in the product data reference product content data whose similarity with the content data corresponding to the second representative image is greater than a second preset similarity; based on the reference product content data and the second purchase data, generates a second long page corresponding to the second representative image, and based on the second remaining product content data that is not matched in the product data, generates a corresponding second short page, the page length of the second long page being greater than the page length of the second short page.

[0093] The device for displaying product information based on user behavior provided in the embodiment of the present invention can realize each process of the method for displaying product information based on user behavior in the above method embodiment, and can achieve the same beneficial effect. To avoid repetition, it will not be described here.

[0094] See also Figure 3 , Figure 3 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention, such as Figure 3 As shown, it includes: a memory 302, a processor 301, and a computer program of a commodity information display method based on user behavior stored in the memory 302 and executable on the processor 301, wherein: The processor 301 is used to call the computer program stored in the memory 302 and execute the following steps: When a user clicks to enter the product page of a target product, the user's historical shopping behavior data within a preset time period and the product data of the target product are obtained; If the historical shopping behavior data includes first historical shopping behavior data corresponding to the target product, generating a first product display interface of the target product based on the product data and the first historical shopping behavior data; If the historical shopping behavior data does not include the first historical shopping behavior data corresponding to the target product, generating a second product display interface of the target product based on the product data and the historical shopping behavior data; The first product display interface or the second product display interface is displayed to the user.

[0095] Optionally, the step of generating a first product display interface of the target product based on the product data and the first historical shopping behavior data, performed by the processor 301, includes: Extracting the first browsing data and the first purchasing data of the user for the target product from the first historical shopping behavior data, wherein the first browsing data includes a plurality of first interface images corresponding to a display window in which the user does not operate for more than a first preset time period when browsing the target product, and the first purchasing data is the first selection data of the user when purchasing the target product; Generate a plurality of first pages based on the commodity data, the first browsing data, and the first purchase data; Based on the plurality of the first pages, a first commodity display interface of the target commodity is generated.

[0096] Optionally, the step of generating a plurality of first pages from the product data, the first browsing data, and the first purchase data, performed by the processor 301, includes: Determining at least one first representative image from among the plurality of first interface images according to the content data corresponding to the first interface image; For each of the first representative graphs, determining a weight value of the first representative graph based on a residence time and a data volume of content data corresponding to the first representative graph; Determining, from the commodity data, target commodity content data whose similarity to the content data corresponding to the first representative graph is greater than a first preset similarity threshold; Based on the target product content data, the first purchase data and the weight value, a first long page corresponding to the first representative image is generated, and based on the first remaining product content data that is not matched in the product data, a corresponding first short page is generated, and the page length of the first long page is greater than the page length of the first short page.

[0097] Optionally, the step of determining at least one first representative image from a plurality of first interface images according to the content data corresponding to the first interface image, performed by the processor 301, includes: Calculating the image similarity between the first interface images according to the content data corresponding to the first interface images; Based on the image similarity between the first interface images, a plurality of the first interface images are divided into a first-category interface image set and / or a second-category interface image set, wherein the first-category interface image set includes a plurality of the first interface images, and the image similarity between any two of the first interface images in the first-category interface image set is greater than or equal to an image similarity threshold, and the second-category interface image set includes only one of the first interface images, and the image similarity between the first interface images in the second-category interface image set and any one of the first interface images in other interface image sets is less than the image similarity threshold; For each first-category interface image set, multiple first-category interface images in the first-category interface image set are spliced ​​and merged in the order of content data to obtain a first representative image of the first-category interface image set, and each first-category interface image set corresponds to one first representative image; For each set of the second-type interface images, the first interface image in the second-type interface image set is determined as the first representative image of the second-type interface image set, and each set of the second-type interface images corresponds to one first representative image.

[0098] Optionally, the step of generating a first product display interface of the target product based on the plurality of first pages, performed by the processor 301, includes: Performing focus prediction on the first page to predict the user's focus on the first page; Based on the focus of the first page, generating a focus sequence in page order, each first page corresponds to a focus of the first page; The focus distance between the focuses of two adjacent first pages in the focus sequence is used as a reference distance, and the reference distance is dynamically adjusted through a dynamic focus coefficient and a dynamic scrolling speed to obtain a dynamic splicing interval between two adjacent first pages, and the two adjacent first pages are spliced ​​based on the dynamic splicing interval.

[0099] Optionally, the step of generating a second product display interface of the target product based on the product data and the historical shopping behavior data, performed by the processor 301, includes: Filtering out second historical shopping behavior data corresponding to a reference product from the historical shopping behavior data, wherein the reference product has cross-level similarity with the target product; Extracting the second browsing data and second purchasing data of the user for non-target products from the second historical shopping behavior data, wherein the second browsing data includes a plurality of second interface images corresponding to a display window in which the user does not operate for more than a second preset time period when browsing the reference product, and the second purchasing data is the second selection data of the user for purchasing the reference product; Generate a plurality of second pages based on the commodity data, the second browsing data, and the second purchase data; Based on the plurality of second pages, a second product display interface of the target product is generated.

[0100] Optionally, the step of generating a plurality of second pages based on the product data, the second browsing data, and the second purchase data, performed by the processor 301, includes: Determine at least one second representative image corresponding to each category of parameter products according to the content data corresponding to the second interface image; For at least one second representative graph corresponding to each category of parameter goods, determining reference goods content data in the goods data whose similarity to the content data corresponding to the second representative graph is greater than a second preset similarity; Based on the reference product content data and the second purchase data, a second long page corresponding to the second representative image is generated; based on the second remaining product content data that is not matched in the product data, a corresponding second short page is generated, and the page length of the second long page is greater than the page length of the second short page.

[0101] It should be noted that the electronic device provided in the embodiment of the present invention can be applied to computers, servers and other devices that can perform a product information display method based on user behavior.

[0102] The electronic device provided in the embodiment of the present invention can implement each process of the method for displaying commodity information based on user behavior in the above method embodiment, and can achieve the same beneficial effect. To avoid repetition, it will not be described here.

[0103] An embodiment of the present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the various processes of the product information display method based on user behavior provided by the embodiment of the present invention are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0104] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the computer-readable storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM).

[0105] The above disclosure is only the preferred embodiment of the present invention, which certainly cannot be used to limit the scope of the present invention. Therefore, equivalent changes made according to the claims of the present invention are still within the scope of the present invention.

Claims

1. A method for displaying product information based on user behavior, characterized in that: The method comprises the following steps: When a user clicks to enter the product page of a target product, the user's historical shopping behavior data within a preset time period and the product data of the target product are obtained; If the historical shopping behavior data includes first historical shopping behavior data corresponding to the target product, generating a first product display interface of the target product based on the product data and the first historical shopping behavior data; If the historical shopping behavior data does not include the first historical shopping behavior data corresponding to the target product, generating a second product display interface of the target product based on the product data and the historical shopping behavior data; The first product display interface or the second product display interface is displayed to the user.

2. The method for displaying product information based on user behavior according to claim 1, characterized in that: The step of generating a first product display interface of the target product based on the product data and the first historical shopping behavior data includes: Extracting the first browsing data and the first purchasing data of the user for the target product from the first historical shopping behavior data, wherein the first browsing data includes a plurality of first interface images corresponding to a display window in which the user does not operate for more than a first preset time period when browsing the target product, and the first purchasing data is the first selection data of the user when purchasing the target product; Generate a plurality of first pages based on the commodity data, the first browsing data, and the first purchase data; Based on the plurality of the first pages, a first commodity display interface of the target commodity is generated.

3. The method for displaying commodity information based on user behavior according to claim 2, characterized in that: The step of generating a plurality of first pages from the commodity data, the first browsing data and the first purchase data comprises: Determining at least one first representative image from among the plurality of first interface images according to the content data corresponding to the first interface image; For each of the first representative graphs, determining a weight value of the representative graph based on the dwell time and the amount of content data corresponding to the first representative graph; Determining, from the commodity data, target commodity content data that matches the content data corresponding to the first representative graph; Based on the target product content data and the weight value, a first long page corresponding to the first representative image is generated, and based on the remaining product content data that is not matched in the product data, a corresponding first short page is generated, and the page length of the first long page is greater than the page length of the first short page.

4. The method for displaying commodity information based on user behavior according to claim 3, characterized in that: The step of determining at least one first representative image from among the plurality of first interface images according to the content data corresponding to the first interface image comprises: Calculating the similarity between the first interface images according to the content data corresponding to the first interface images; Based on the similarity between the first interface images, a plurality of the first interface images are divided into a first-category interface image set and / or a second-category interface image set, wherein the first-category interface image set includes a plurality of the interface images, and the similarity between any two of the first interface images in the first-category interface image set is greater than or equal to a preset similarity, and the second-category interface image set includes only one of the first interface images, and the similarity between the first interface images in the second-category interface image set and any one of the first interface images in other interface image sets is less than the preset similarity; For each first-category interface image set, multiple first-category interface images in the first-category interface image set are spliced ​​and merged in the order of content data to obtain a first representative image of the first-category interface image set, and each first-category interface image set corresponds to one first representative image; For each set of the second-type interface images, the first interface image in the second-type interface image set is determined as the first representative image of the second-type interface image set, and each set of the second-type interface images corresponds to one first representative image.

5. The method for displaying commodity information based on user behavior according to claim 4, characterized in that: The step of generating a first commodity display interface of the target commodity based on the plurality of first pages includes: Performing focus prediction on the first page to predict the user's focus on the first page; Based on the focus of the first page, generating a focus sequence in page order, each first page corresponds to a focus of the first page; The focus distance between the focuses of two adjacent first pages in the focus sequence is used as a reference distance, and the reference distance is dynamically adjusted through a dynamic focus coefficient and a dynamic scrolling speed to obtain a dynamic splicing interval between two adjacent first pages, and the two adjacent first pages are spliced ​​based on the dynamic splicing interval.

6. The method for displaying commodity information based on user behavior according to any one of claims 1 to 5, characterized in that: The step of generating a second product display interface of the target product based on the product data and the historical shopping behavior data includes: Filtering out second historical shopping behavior data corresponding to a reference product from the historical shopping behavior data, wherein the reference product has cross-level similarity with the target product; Extracting the second browsing data and second purchasing data of the user for non-target products from the second historical shopping behavior data, wherein the second browsing data includes a plurality of second interface images corresponding to a display window in which the user does not operate for more than a second preset time period when browsing the reference product, and the second purchasing data is the second selection data of the user for purchasing the reference product; Generate a plurality of second pages based on the commodity data, the second browsing data, and the second purchase data; Based on the plurality of second pages, a second product display interface of the target product is generated.

7. The method for displaying commodity information based on user behavior according to claim 6, characterized in that: The step of generating a plurality of second pages based on the commodity data, the second browsing data and the second purchase data comprises: Determine at least one second representative image corresponding to each category of parameter products according to the content data corresponding to the second interface image; For at least one second representative graph corresponding to each category of parameter goods, determining reference goods content data in the goods data whose similarity to the content data corresponding to the second representative graph is greater than a second preset similarity; Based on the reference product content data and the second purchase data, a second long page corresponding to the second representative image is generated; based on the second remaining product content data that is not matched in the product data, a corresponding second short page is generated, and the page length of the second long page is greater than the page length of the second short page.

8. A commodity information display device based on user behavior, characterized in that: The commodity information display device based on user behavior includes: An acquisition module, used to acquire the historical shopping behavior data of the user within a preset time period and the product data of the target product when the user clicks to enter the product page of the target product; A first generating module, configured to generate a first commodity display interface of the target commodity based on the commodity data and the first historical shopping behavior data if the historical shopping behavior data includes first historical shopping behavior data corresponding to the target commodity; a second generating module, configured to generate a second commodity display interface of the target commodity based on the commodity data and the historical shopping behavior data if the historical shopping behavior data does not include the first historical shopping behavior data corresponding to the target commodity; A display module is used to display the first product display interface or the second product display interface to the user.

9. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of the method for displaying commodity information based on user behavior as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the method for displaying commodity information based on user behavior as described in any one of claims 1 to 7 are implemented.

Images