Method for providing commodity search result information and electronic equipment

By identifying and predicting products that meet the target quality standards and giving priority to displaying their information content, it solves the problem that users find it difficult to find authentic products in "Search products with pictures", improves search efficiency and purchase conversion rate, and especially improves niche brands and the exposure and efficiency of "Overseas Direct Purchase" services.

CN118939874APending Publication Date: 2024-11-12TAOBAO CHINA HLDG LTD
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202410950465.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-15
Publication Date
2024-11-12

AI Technical Summary

Technical Problem

During the process of "searching products with pictures", it is difficult for users to quickly find genuine products that meet the target quality standards from the same products, resulting in low search efficiency and low purchase conversion rate.

Method used

By analyzing the images submitted by users, identifying products and predicting products that meet the target quality standards, the information content of these products is preferred on the search results page, including brand introductions and value points, and using AI to generate content and enrich display.

Benefits of technology

It improves the efficiency of users in finding products that meet the target quality standards, improves the click-through rate and purchase conversion rate of search results, especially for niche brands and "overseas direct purchase" services.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118939874A_ABST
    Figure CN118939874A_ABST
Patent Text Reader

Abstract

The embodiment of the invention discloses a method for providing commodity search result information and electronic equipment, and the method comprises the steps: responding to a commodity search request submitted by a user, and determining an input image associated with the request; determining at least one hit commodity from a commodity set provided by a commodity information service system according to the input image, and predicting a target commodity meeting a target quality standard from the at least one commodity according to shop information corresponding to the commodity; in the process that a client displays a search result page, a first display area and a second display area are provided in the search result page, and the first display area is located above the second display area and used for preferentially displaying the information content of the target commodity. The second display area is used for displaying the commodity search result information flow. Through the embodiment of the invention, the user can be helped to more quickly find the commodity which possibly belongs to the original certified product, the search efficiency is improved, and the user can be helped to make a decision.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of commodity information processing, and in particular to a method, a device and an electronic device for providing commodity search result information. Background Art

[0002] Image-based product search is generally defined as "search for products by image". Different from the general search method which mainly relies on keywords, the emergence of the "search for products by image" function allows users to initiate product searches by uploading pictures or taking photos of physical objects, thus eliminating the need for users to convert the desired products into keyword descriptions, making it easier for users to search for the desired products more accurately.

[0003] However, in actual applications, in the process of "searching for products by image", the search results may include multiple identical products, and the prices and other aspects of these identical products may be different, so users often have difficulty in making a choice among them. Summary of the invention

[0004] The present application provides a method and an electronic device for providing product search result information, which can help users find products that may be original and authentic more quickly, improve their search efficiency, and also help users make decisions.

[0005] This application provides the following solutions:

[0006] A method for providing product search result information, comprising:

[0007] In response to a product search request submitted by a user, determining an input image associated with the request;

[0008] According to the input image, at least one hit commodity is determined from a commodity set provided by a commodity information service system, and according to store information corresponding to the commodity, a target commodity that meets a target quality standard is predicted from the at least one commodity;

[0009] In the process of displaying the search result page on the client, a first display area and a second display area are provided in the search result page. The first display area is located above the second display area and is used to preferentially display the information content of the target product. The second display area is used to display the product search result information flow.

[0010] The step of predicting a target commodity that meets a target quality standard from the at least one commodity according to the store information corresponding to the commodity includes:

[0011] Determine whether, among the stores corresponding to the at least one product, there is a store opened by the product information service system and / or mainly selling products with brand trust endorsement purchased through standard channels. If so, predict the product corresponding to the store as a target product that meets the target quality standards.

[0012] The step of predicting a target commodity that meets a target quality standard from the at least one commodity according to the store information corresponding to the commodity includes:

[0013] It is determined whether there is a store opened or authorized to be opened by the brand in the product information service system among the stores corresponding to the at least one product. If so, the product corresponding to the store is predicted to be a target product that meets the target quality standard.

[0014] The first display area includes a first resource position that fills the entire screen horizontally, so as to display the information content of the target product through the first resource position;

[0015] The second display area includes a plurality of second resource locations, and the plurality of second resource locations include at least two columns in a vertical direction, so as to display the commodity search result information flow through the plurality of second resource locations.

[0016] According to different commodity categories to which the target commodity belongs, the first resource position of the first display area content corresponds to different display heights.

[0017] The target product information includes:

[0018] The target product's detail page link information, brand introduction information, and / or product value point information.

[0019] If the target product involves foreign language packaging, the information content of the target product further includes: information on the translation result of the packaging copy of the target product.

[0020] Among them, it also includes:

[0021] Through an artificial intelligence (AI) large-scale parameter model, content generation is performed based on the product details information and / or related public network information of the target product to obtain AI-generated content for display in the first display area as the information content of the target product.

[0022] Different product categories have different graphic container templates.

[0023] The method further comprises:

[0024] According to the category to which the target product belongs, the corresponding graphic container template information is provided to the AI ​​large-scale parameter model, wherein the graphic container template information is used to define the type, size and / or layout information of the content to be generated, so that the AI ​​large-scale parameter model generates content according to the graphic container template;

[0025] Fill the AI-generated graphic content into the corresponding graphic container template to generate the information content of the target product;

[0026] When the information content of the target product is displayed in the first display area, a corresponding graphic container is loaded according to the product category to which the target product belongs, so as to display the information content of the target product based on the graphic container.

[0027] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of any of the methods described above.

[0028] An electronic device, comprising:

[0029] one or more processors; and

[0030] A memory associated with the one or more processors, the memory being used to store program instructions, wherein the program instructions, when read and executed by the one or more processors, execute the steps of any of the aforementioned methods.

[0031] A computer program product comprises a computer program / computer executable instructions, wherein the computer program / computer executable instructions implement the steps of any of the aforementioned methods when executed by a processor in an electronic device.

[0032] According to the specific embodiments provided in this application, this application discloses the following technical effects:

[0033] Through the embodiment of the present application, after the user inputs an image and initiates a product search request, at least one hit product can be determined from the product set provided by the product information service system based on the input image, and the store information corresponding to the product can be determined. After that, the target product that meets the target quality standard can be predicted from the at least one product based on the store information. Then, in the process of displaying the search result page on the client, a first display area and a second display area can be provided in the search result page. The first display area is located above the second display area and is used to give priority to displaying the information content of the target product. The second display area is used to display the product search result information flow. In this way, users can find products that may meet the target quality standards more quickly, improve their search efficiency, and help users make decisions.

[0034] In addition, in the preferred manner, when displaying such products that may meet the target quality standards, relevant information such as brand introduction and product main value point introduction can be provided so that users can obtain this information through the search results page without entering the specific product details page, and then can use this information to determine whether to click to view the detailed information of the product, etc., to avoid or reduce the situation of "dissuading" users from buying products directly after seeing the price on the search results page. Therefore, it is also helpful to improve the click-through rate, browse-to-purchase conversion rate and other indicators of such products. For some niche brands, it is helpful to improve the product exposure rate of these brands. For services such as "overseas direct purchase" provided by the product information service system, it also gives more users the opportunity to perceive the existence of the service, thereby improving the service efficiency of the entire "overseas direct purchase" service sector.

[0035] Furthermore, the content generation capabilities of the AI ​​big model can be combined to generate graphic and text content, so that when displaying products that may meet the target quality standards, users can be provided with richer content through AI generation. These contents are not limited to the content extracted or summarized from the product details page, but can also include brand-related content searched from public network systems, such as brand introduction, positioning, and even the latest brand developments, etc.

[0036] Of course, any product implementing the present application does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0038] Figure 1 It is a schematic diagram of the system architecture provided by the embodiment of the present application;

[0039] Figure 2 is a flow chart of the method provided in the embodiment of the present application;

[0040] Figure 3 is a schematic diagram of a related interface provided in an embodiment of the present application;

[0041] Figure 4 It is a schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0042] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments in the present application belong to the scope of protection of this application.

[0043] First of all, it should be noted that in some commodity information service systems, "overseas direct purchase" services can be provided. The platform party can open a self-operated store that mainly sells cross-border brand products, and prepare specific goods to the platform party's domestic local warehouse by purchasing from the relevant formal channels of the cross-border brand party, so that domestic consumers can purchase cross-border brand products without going abroad. Or, in another way, the cross-border brand party can also directly open a brand-owned store through the platform, or authorize a third party to open a brand store on the platform, etc. Whether it is a cross-border brand product store operated by the platform itself, or a store operated or authorized by the cross-border brand party, the goods sold therein usually meet certain quality standards, for example, they are usually "authentic" products with official endorsement of the corresponding brand, etc. Providing such "authentic" cross-border brands to consumers through a specific commodity information service system can enable the commodity information service system to achieve differentiated supply of scarce goods.

[0044] However, in actual applications, the above-mentioned cross-border brands may involve a large number of niche brands. Since domestic consumers have limited knowledge of such brands and rarely initiate searches by searching for brand names, this also leads to relatively small product exposures. This further leads to the problem of weak user perception of the entire "cross-border direct purchase" related functions. Correspondingly, the click-through rate, browse-purchase conversion rate, etc. of the products are often at a relatively low level.

[0045] On the other hand, in addition to initiating searches through keywords, the product information service system usually provides consumers with the function of "searching products by pictures". When consumers do not know the brand and other information of the products, they can initiate product searches by uploading pictures. In addition, consumers have the opportunity to come into contact with some overseas brand products in real life, and may even have the intention to buy them. However, since they do not know the specific brand names, they may usually use the "search products by pictures" function of the product information service system to initiate searches. For example, on some short video platforms, there will be a large number of fashion bloggers, celebrities, etc. sharing cross-border niche brand outfits. Consumers will "plant grass" for a certain niche clothing through such short video platforms, and then search for the corresponding products in the product information service system through screenshots and other methods.

[0046] However, the commodity information service system is usually a comprehensive information service system. In addition to the above-mentioned "cross-border direct purchase" service, it also includes other types of stores, some of which may provide "cross-border purchasing agent" services, and some stores may sell "imitations" of some brands, including some imitations of cross-border brands. Even multiple different stores may sell "imitations" of the same product, and their respective sales prices are not exactly the same, etc. In this context, when consumers "search for products by image", although the product itself may indeed be an original product of a cross-border brand, the search results given by the system may contain a large number of the same products, which may include products from the above-mentioned "purchasing agent" channels, or "imitations" produced by multiple domestic manufacturers, etc. This results in very complicated search results. Although there are products with better quality assurance provided by the aforementioned "cross-border direct purchase" service, they are mixed with a large number of imitations or purchasing agents. Therefore, it is difficult for users to quickly find the purchase channel of "authentic products". Even if they can find the real "authentic products", they may not understand the brand positioning, characteristics, price and other information of the "authentic products", so it is difficult to generate real clicks and purchase conversions.

[0047] It can be seen that whether through traditional keyword-based product searches or "image search for products", it is difficult to bring effective clicks or conversions to genuine products provided by channels such as "cross-border direct purchases", so that these high-quality product information is difficult to reach consumer users, and consumers also find it difficult to purchase such products that meet certain quality standards.

[0048] In view of the above situation, in the embodiment of the present application, the existing "search for goods by image" service is improved. Specifically, after the consumer user initiates the request of "search for goods by image", the subject identification related to the goods can be performed first according to the input image, and then the hit goods can be determined in the goods collection such as the goods pool of the goods information service system, and these goods are usually multiple. After that, instead of directly screening and sorting these goods according to a certain strategy and returning them to the user, the target goods (for example, genuine goods) that may meet the target quality standards can be predicted from the hit goods according to the store information associated with these goods, and the information content of the target goods that may meet the target quality standards can be displayed preferentially in the search results page. For example, a special display area can be provided in the search results page, which can be called the first display area, and the predicted product information that may meet the target quality standards is displayed in the first display area. Specifically, when displaying, relevant brand introduction, brand positioning and other information can also be provided to help users decide whether to click to view details or purchase after having some understanding of the specific brand. In the second display area below the above-mentioned first display area, a specific product search result information flow is displayed.

[0049] Among them, when judging whether there are goods that may meet the target quality standards among the hit goods, the judgment can be mainly made based on the stores associated with the goods. Specifically, if it is a store opened by the product information service system and / or mainly sells goods with brand trust endorsement purchased through standard channels, or a store opened or authorized by the brand in the product information service system (including the "cross-border direct purchase" store operated by the product information service system in the aforementioned "cross-border direct purchase" scenario, or the store operated or authorized by the cross-border brand, etc.), since the goods in these stores are usually brand-endorsed, for example, they are goods purchased through formal channels, or the brand may provide relevant certification materials when opening a store or releasing goods, etc., therefore, the goods released in these stores can usually be judged as target goods that meet the target quality standards. Therefore, if there are goods released by such stores among the goods hit by the search request initiated by the goods, they can be considered as goods that meet the target quality standards, and can be displayed to users first.

[0050] In this way, since the stores opened by the above-mentioned product information service system and / or mainly sell brand products with brand trust endorsement purchased through standard channels, or the stores opened or authorized by the brand in the product information service system, may include stores related to the "cross-border direct purchase" service section, giving priority to displaying the products in such stores is also conducive to achieving traffic to the "cross-border direct purchase" service section, increasing the exposure of "cross-border direct purchase" related products, and then helping to improve click-through rate, browse-purchase conversion rate, and so on.

[0051] Of course, in actual applications, when "cross-border direct purchase" is not involved, the solution provided by the embodiment of the present application can also be used to predict the target products that meet the target quality standards in the "search for products by image" scenario, and give priority to displaying them to users. For example, suppose that after a user enters an image to initiate a product search, it is found that the above-mentioned products involving "cross-border direct purchase" do not exist among the products hit by the search. Then, the probability that the specific product meets the target quality standard can also be judged based on the situation of the store associated with the specific product. For example, a store is opened by a well-known brand, or the store name may contain the word "original", or the store has a relatively high rating and a high historical praise rate, etc. The specific products may meet the target quality standards and can therefore be displayed preferentially.

[0052] From the perspective of system architecture, see Figure 1 The embodiment of the present application mainly involves the server and client in the commodity information service system, wherein the client is mainly used to interact with the user and display the corresponding page, so that the user can input images and initiate specific commodity search requests, and the server is mainly used to execute the background search logic. In the embodiment of the present application, the judgment of whether the commodity meets the target quality standard and the provision of information content of the target commodity that meets the target quality standard can all be executed by the server, and the specific processing results are returned to the client for display.

[0053] The specific implementation scheme provided in the embodiments of the present application is described in detail below.

[0054] First, the present application embodiment provides a method for providing product search result information, see Figure 2 , the method may include:

[0055] S201: In response to a product search request submitted by a user, determining an input image associated with the request.

[0056] Among them, the user can initiate a specific search request through the search entry provided by the client. For example, a search entry can be provided on the client homepage and other pages. The search entry can be used to initiate an image-based product search. After that, the user can choose to upload a certain image saved locally, or can also start the camera device to shoot, and upload the captured photo as an input image, etc. In a typical application scenario, the specific input image can also be a related picture of a product that the user has been "planted" with in a social network or short video platform system. The user can first save such a picture to a local album, etc., and then initiate a product search based on such a picture in the product information service system, etc. After the client receives the user's search request, it can forward it to the server and upload the specific input image to the server.

[0057] S202: According to the input image, determine at least one hit commodity from a commodity set provided by a commodity information service system, and determine store information corresponding to the commodity.

[0058] After receiving a specific search request, the server can first determine at least one hit product from the product set provided by the product information service system according to the input image, and determine the store information corresponding to the product. The above product set can specifically be a "product pool" in the product information service system, which can include all products published in the system, and of course, it can also be a product set composed of some products in the full amount of products, etc.

[0059] Specifically, when matching the input image with the products in the product set, the subject related to the product can be identified from the input image. For example, assuming that the foreground image in the input image mainly has a person wearing a certain piece of clothing, then in the scene of searching for products, this piece of clothing may be the object that the user needs to search for, so it can be identified as a subject related to the product, etc. In specific implementation, this process of identifying the subject image from the input image can also be performed on the client, and the client can upload the identified subject image to the server, or the client can directly upload the input image to the server, and the server recognizes the subject image, etc.

[0060] After identifying the subject image related to the product from the input image, the server can retrieve the product matching the subject image from the product collection. During the matching process, comparison based on image visual features can be performed, which will not be described in detail here.

[0061] After determining at least one of the hit products, in the embodiment of the present application, the store information corresponding to these products can also be determined. This store information is the store opened by the corresponding merchant in the product information service system, and the products released by the merchant will be associated with the store. Therefore, after determining a certain product, the corresponding store information can be determined based on this association.

[0062] S203: According to the input image, at least one hit commodity is determined from a commodity set provided by a commodity information service system, and according to store information corresponding to the commodity, a target commodity that meets a target quality standard is predicted from the at least one commodity.

[0063] After determining the store associated with the hit product, the target product that meets the target quality standard can be predicted from the at least one product based on the store information. In the embodiment of the present application, in addition to determining which products in the system match the subject image in the user input image, it is also possible to determine which of these products may meet the target quality standard, so as to help the user find the product that meets the target quality standard more quickly.

[0064] Specifically, when judging whether a certain product meets the target quality standard, it can be judged mainly based on the associated store information. For example, in one way, it can be judged whether there is a store opened by the product information service system and / or mainly sells products with brand trust endorsement purchased through standard channels among the stores corresponding to the at least one product. If so, the product corresponding to the store can be predicted as a target product that meets the target quality standard. Alternatively, it can be judged whether there is a store opened or authorized by the brand in the product information service system among the stores corresponding to at least one product. If so, the product corresponding to the store is predicted as a target product that meets the target quality standard. For example, if among the multiple products hit, the store corresponding to a certain product is a product released by a store officially endorsed by the brand in the above-mentioned "cross-border direct purchase" scenario, then the product usually meets the target quality standard. Therefore, the service end can predict such a product as a target product that meets the target quality standard.

[0065] Of course, if at least one of the hit products corresponds to a store that does not have an official endorsement from the brand in the above-mentioned "cross-border direct purchase" scenario, the probability that a specific product meets the target quality standard can also be predicted based on the store's rating, historical evaluation, etc. At this point, multiple products that may meet the target quality standard can be predicted for the user to choose from, etc.

[0066] After predicting the target products that may meet the target quality standard, the server may provide the client with information about the target products, so that the client may give priority to displaying the information about the target products when displaying the search result page.

[0067] The target product information content may include not only the link information of the target product's details page, but also the corresponding brand introduction information and / or product value point information, etc. In this way, users do not need to enter the product details page, but can directly understand the specific brand, product value point and other information on the product search result page, which helps users to make a more rational decision whether to click to view product details or whether to buy, rather than being "dissuaded" by the price after seeing that the price is relatively high.

[0068] In addition, if the specific target product involves foreign language packaging, for example, some overseas brands of health products, cosmetics, etc., the outer packaging may introduce the relevant ingredients, specifications, effects, usage methods, etc. of the product in foreign languages, then the information content of the target product may also include: the translation result information of the packaging copy of the target product. In this way, users can directly obtain this information from the product search result page, which is also helpful for users to make decisions.

[0069] Among them, in the specific implementation, the information content of the target product can also be generated by an AI (artificial intelligence) large-scale parameter model (hereinafter referred to as the AI ​​big model), that is, the information content specifically displayed to the user can be AI-generated content. Specifically, the AI ​​big model can generate content based on the product details information and / or related public network information of the target product to generate AI-generated content, and the specific AI-generated content may include graphic content. Among them, the image content can be directly selected from the product details page. The main picture of the product can also be generated by the AI ​​big model based on the main picture of the product, and then the main picture of the product is synthesized with the AI-generated background elements to generate an image, etc. In addition, the AI ​​big model can also summarize the text content in the product details page and / or the text content related to the brand introduction searched from the public network to generate text content related to brand introduction, introduction of the main value points of the product, etc.

[0070] In specific implementation, different graphic container templates can also be provided for different commodity categories. Such graphic container template information can be used to define the type, size and / or layout information of the content to be generated. In this way, when the content is generated by the AI ​​big model, the corresponding graphic container template information can also be provided to the AI ​​big model according to the category to which the target commodity belongs, so that the AI ​​big model can generate content according to the graphic container template. Afterwards, the graphic content generated by AI can be filled into the corresponding graphic container template and provided to the client for display. Among them, the graphic container templates corresponding to different commodity categories can have different sizes. For example, for clothing products, it is usually necessary to display the commodity information through relatively large-sized pictures. Therefore, the height of the graphic container template can be relatively high; while for categories such as health products, the commodity information may be described more in text, and there is no need to display large-sized commodity pictures. Therefore, the height of the graphic container can also be relatively low to avoid unnecessary occupation of page resources of the search results page.

[0071] S203: In the process of displaying the search result page on the client, a first display area and a second display area are provided in the search result page, wherein the first display area is located above the second display area and is used to preferentially display the information content of the target product, and the second display area is used to display the product search result information flow.

[0072] After receiving the information content of the target product predicted to meet the target quality standard, the client can display it preferentially on the search results page. Specifically, when displaying the information content of the target product on the search results page, since the search results page usually displays the product search results in the form of a "double-column flow", that is, the page includes multiple resource locations, which are arranged in two columns, with two resource locations in each row, and more search results can be viewed by sliding the page up and down, etc. In this case, the information content of the target product predicted to meet the target quality standard can be displayed in a resource location in the "double-column flow", for example, the first resource location, etc.

[0073] However, in the embodiment of the present application, there may be a lot of information that needs to be revealed through the search results page, including brand introduction, introduction to the main value points of the product, etc., and the resource position size in the "double-column flow" is usually limited, and it is difficult to carry too much information content. In addition, the first resource position is usually also called the "first pit", which usually also needs to undertake tasks such as "promotion" of the product, which may conflict with the need to display original authentic products in the embodiment of the present application.

[0074] Therefore, in the embodiment of the present application, other methods can be used to implement it. Specifically, a special display area can be set at the top of the search result page, etc., to display the information content of the target product predicted to be an original authentic product. Specifically, a first display area and a second display area can be provided in the search result page, the first display area is located above the second display area, and is used to display the information content of the target product first, and the second display area is used to display the product search result information flow. Among them, in a preferred implementation, the first display area can fill the full screen in the horizontal direction, and the height in the vertical direction can depend on the display requirements of the specific product category, that is, the first resource position of the first display area content corresponds to different display heights according to the different product categories to which the target product belongs. In addition, the second display area may include multiple second resource positions, and the multiple second resource positions may include at least two columns in the vertical direction, so as to display the product search result information flow through the multiple second resource positions. In this way, since the first display area can fill the full screen in the horizontal direction, compared with the resource positions in the "double-column flow" or "multi-column flow", it has more display space at least in the horizontal direction and can carry more information content.

[0075] For example, Figure 3 As shown in a practical application example, suppose the input image uploaded by the user is as follows Figure 3 As shown in (A), it is a screenshot of the relevant interface on a short video platform. The "bloggers" on the short video platform may be introducing makeup techniques, etc. However, the user is more interested in the clothes worn by the blogger and wants to buy them. Therefore, after taking a screenshot, the user uploads it to the product information service system to initiate a product search. In the traditional way, the product search results will be directly returned, and multiple matching product information will be displayed in the form of a "double column stream". In the embodiment of the present application, it will be determined based on the store information corresponding to the hit product whether there is a target product that may meet the target quality standard. If so, Figure 3 As shown at 31 in (B), the relevant information of the target product can be displayed in the dedicated resource position at the top of the page (the ordinary "double-column flow" is displayed below the dedicated resource position, which may also include the target product). It can include specific brand combinations, introductions to the main value points of the product, etc., so that users can make the next decision after having a preliminary understanding of this information.

[0076] In summary, through the embodiments of the present application, after the user inputs an image and initiates a product search request, at least one hit product can be determined from the product set provided by the product information service system based on the input image, and the store information corresponding to the product can be determined. After that, the target product that meets the target quality standard can be predicted from the at least one product based on the store information. Then, in the process of displaying the search result page on the client, a first display area and a second display area can be provided in the search result page. The first display area is located above the second display area and is used to give priority to displaying the information content of the target product. The second display area is used to display the product search result information flow. In this way, users can find products that may meet the target quality standards more quickly, improve their search efficiency, and help users make decisions.

[0077] In addition, in the preferred manner, when displaying such products that may meet the target quality standards, relevant information such as brand introduction and product main value point introduction can be provided so that users can obtain this information through the search results page without entering the specific product details page, and then can use this information to determine whether to click to view the detailed information of the product, etc., to avoid or reduce the situation of "dissuading" users from buying products directly after seeing the price on the search results page. Therefore, it is also helpful to improve the click-through rate, browse-to-purchase conversion rate and other indicators of such products. For some niche brands, it is helpful to improve the product exposure rate of these brands. For services such as "overseas direct purchase" provided by the product information service system, it also gives more users the opportunity to perceive the existence of the service, thereby improving the service efficiency of the entire "overseas direct purchase" service sector.

[0078] Furthermore, the content generation capabilities of the AI ​​big model can be combined to generate graphic and text content, so that when displaying products that may meet the target quality standards, users can be provided with richer content through AI generation. These contents are not limited to the content extracted or summarized from the product details page, but can also include brand-related content searched from public network systems, such as brand introduction, positioning, and even the latest brand developments, etc.

[0079] It should be noted that the embodiments of the present application may involve the use of user data. In actual applications, user-specific personal data can be used in the scheme described herein within the scope permitted by applicable laws and regulations, subject to the requirements of applicable laws and regulations of the country where the user is located (for example, with the user's explicit consent, effective notification to the user, etc.).

[0080] Corresponding to the aforementioned method embodiment, the embodiment of the present application further provides a device for providing product search result information, which may include:

[0081] An input image determining unit, configured to determine an input image associated with a commodity search request submitted by a user;

[0082] A prediction unit, configured to determine at least one hit commodity from a commodity set provided by a commodity information service system according to the input image, and predict a target commodity that meets a target quality standard from the at least one commodity according to store information corresponding to the commodity;

[0083] A display unit is used to provide a first display area and a second display area in the search result page during the process of displaying the search result page on the client, wherein the first display area is located above the second display area and is used to give priority to displaying the information content of the target product, and the second display area is used to display the product search result information flow.

[0084] The prediction unit may be specifically used for:

[0085] Determine whether, among the stores corresponding to the at least one product, there is a store opened by the product information service system and / or mainly selling products with brand trust endorsement purchased through standard channels. If so, predict the product corresponding to the store as a target product that meets the target quality standards.

[0086] Alternatively, the prediction unit may be specifically used for:

[0087] It is determined whether there is a store opened or authorized to be opened by the brand in the product information service system among the stores corresponding to the at least one product. If so, the product corresponding to the store is predicted to be a target product that meets the target quality standard.

[0088] The first display area includes a first resource position that fills the entire screen horizontally, so as to display the information content of the target product through the first resource position;

[0089] The second display area includes a plurality of second resource locations, and the plurality of second resource locations include at least two columns in a vertical direction, so as to display the commodity search result information flow through the plurality of second resource locations.

[0090] Specifically, according to different commodity categories to which the target commodity belongs, the first resource position of the first display area content corresponds to different display heights.

[0091] The target product information includes:

[0092] The target product's detail page link information, brand introduction information, and / or product value point information.

[0093] If the target product involves foreign language packaging, the information content of the target product further includes: information on the translation result of the packaging copy of the target product.

[0094] The device may further include:

[0095] The AI ​​generation unit is used to generate content based on the product details information and / or related public network information of the target product through an artificial intelligence AI large-scale parameter model, and obtain AI-generated content for display in the first display area as the information content of the target product.

[0096] Different product categories have different graphic container templates.

[0097] The device may also include:

[0098] A template providing unit, used to provide the corresponding image-text container template information to the AI ​​large-scale parameter model according to the category to which the target product belongs, wherein the image-text container template information is used to define the type, size and / or layout information of the content to be generated, so that the AI ​​large-scale parameter model generates content according to the image-text container template;

[0099] A filling unit, used to fill the AI-generated graphic content into the corresponding graphic container template to generate the information content of the target product;

[0100] The container loading unit is used to load a corresponding graphic container according to the product category to which the target product belongs when displaying the information content of the target product in the first display area, so as to display the information content of the target product based on the graphic container.

[0101] In addition, an embodiment of the present application further provides a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, the steps of any one of the methods in the aforementioned method embodiments are implemented.

[0102] And an electronic device, comprising:

[0103] one or more processors; and

[0104] A memory associated with the one or more processors, the memory being used to store program instructions, wherein the program instructions, when read and executed by the one or more processors, execute the steps of the method described in any one of the aforementioned method embodiments.

[0105] A computer program product includes a computer program / computer executable instructions, which, when executed by a processor in an electronic device, implement the steps of the method described in the aforementioned method embodiment.

[0106] in, Figure 4 The architecture of an electronic device is exemplarily shown. For example, device 400 can be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, an aircraft, etc.

[0107] Reference Figure 4 , device 400 may include one or more of the following components: a processing component 402 , a memory 404 , a power component 406 , a multimedia component 408 , an audio component 410 , an input / output (I / O) interface 412 , a sensor component 414 , and a communication component 416 .

[0108] The processing component 402 generally controls the overall operation of the device 400, such as operations associated with display, phone calls, data communications, camera operations, and recording operations. The processing component 402 may include one or more processors 420 to execute instructions to complete all or part of the steps of the method provided by the technical solution of the present disclosure. In addition, the processing component 402 may include one or more modules to facilitate the interaction between the processing component 402 and other components. For example, the processing component 402 may include a multimedia module to facilitate the interaction between the multimedia component 408 and the processing component 402.

[0109] The memory 404 is configured to store various types of data to support operations on the device 400. Examples of such data include instructions for any application or method operating on the device 400, contact data, phone book data, messages, pictures, videos, etc. The memory 404 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0110] The power supply component 406 provides power to the various components of the device 400. The power supply component 406 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the device 400.

[0111] The multimedia component 408 includes a screen that provides an output interface between the device 400 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundaries of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 408 includes a front camera and / or a rear camera. When the device 400 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera may receive external multimedia data. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

[0112] The audio component 410 is configured to output and / or input audio signals. For example, the audio component 410 includes a microphone (MIC), and when the device 400 is in an operating mode, such as a call mode, a recording mode, and a speech recognition mode, the microphone is configured to receive an external audio signal. The received audio signal can be further stored in the memory 404 or sent via the communication component 416. In some embodiments, the audio component 410 also includes a speaker for outputting audio signals.

[0113] I / O interface 412 provides an interface between processing component 402 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include but are not limited to: a home button, a volume button, a start button, and a lock button.

[0114] The sensor assembly 414 includes one or more sensors for providing various aspects of status assessment for the device 400. For example, the sensor assembly 414 can detect the open / closed state of the device 400, the relative positioning of components, such as the display and keypad of the device 400, and the sensor assembly 414 can also detect the position change of the device 400 or a component of the device 400, the presence or absence of user contact with the device 400, the orientation or acceleration / deceleration of the device 400, and the temperature change of the device 400. The sensor assembly 414 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 414 may also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 414 may also include an accelerometer, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0115] The communication component 416 is configured to facilitate wired or wireless communication between the device 400 and other devices. The device 400 can access a wireless network based on a communication standard, such as WiFi, or a mobile communication network such as 2G, 3G, 4G / LTE, 5G, etc. In an exemplary embodiment, the communication component 416 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 416 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0116] In an exemplary embodiment, the device 400 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above methods.

[0117] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 404 including instructions, and the above instructions can be executed by a processor 420 of a device 400 to complete the method provided by the technical solution of the present disclosure. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0118] It can be known from the description of the above implementation methods that those skilled in the art can clearly understand that the present application can be implemented by means of software plus a necessary general hardware platform. Based on such an understanding, the technical solution of the present application can be essentially or partly contributed to the prior art in the form of a software product, which can be stored in a storage medium such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in the various embodiments of the present application or certain parts of the embodiments.

[0119] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can refer to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system or system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can refer to the partial description of the method embodiment. The system and system embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0120] The above is a detailed introduction to the method and electronic device for providing product search result information provided by the present application. This article uses specific examples to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and core ideas of the present application. At the same time, for those skilled in the art, according to the ideas of the present application, there will be changes in the specific implementation methods and application scopes. In summary, the content of this specification should not be understood as limiting the present application.

Claims

1. A method for providing product search result information, characterized in that: include: In response to a product search request submitted by a user, determining an input image associated with the request; According to the input image, at least one hit commodity is determined from a commodity set provided by a commodity information service system, and according to store information corresponding to the commodity, a target commodity that meets a target quality standard is predicted from the at least one commodity; In the process of displaying the search result page on the client, a first display area and a second display area are provided in the search result page. The first display area is located above the second display area and is used to preferentially display the information content of the target product. The second display area is used to display the product search result information flow.

2. The method according to claim 1, characterized in that The step of predicting a target commodity that meets a target quality standard from the at least one commodity according to the store information corresponding to the commodity includes: Determine whether, among the stores corresponding to the at least one product, there is a store opened by the product information service system and / or mainly selling products with brand trust endorsement purchased through standard channels. If so, predict the product corresponding to the store as a target product that meets the target quality standards.

3. The method according to claim 1, characterized in that The step of predicting a target commodity that meets a target quality standard from the at least one commodity according to the store information corresponding to the commodity includes: It is determined whether there is a store opened or authorized to be opened by the brand in the product information service system among the stores corresponding to the at least one product. If so, the product corresponding to the store is predicted to be a target product that meets the target quality standard.

4. The method according to claim 1, characterized in that: The first display area includes a first resource position that fills the entire screen horizontally, so that the information content of the target product is displayed through the first resource position; The second display area includes a plurality of second resource locations, and the plurality of second resource locations include at least two columns in a vertical direction, so as to display the commodity search result information flow through the plurality of second resource locations.

5. The method according to claim 4, characterized in that According to different commodity categories to which the target commodity belongs, the first resource position of the first display area content corresponds to different display heights.

6. The method according to claim 1, characterized in that The information content of the target product includes: The target product's detail page link information, brand introduction information, and / or product value point information.

7. The method according to claim 6, characterized in that If the target product involves foreign language packaging, the information content of the target product further includes: information on the translation result of the packaging copy of the target product.

8. The method according to claim 1, 6 or 7, characterized in that: Also includes: Through an artificial intelligence (AI) large-scale parameter model, content generation is performed based on the product details information and / or related public network information of the target product to obtain AI-generated content for display in the first display area as the information content of the target product.

9. The method according to claim 8, characterized in that Different product categories have different graphic container templates. The method further comprises: According to the category to which the target product belongs, the corresponding graphic container template information is provided to the AI ​​large-scale parameter model, wherein the graphic container template information is used to define the type, size and / or layout information of the content to be generated, so that the AI ​​large-scale parameter model generates content according to the graphic container template; Fill the AI-generated graphic content into the corresponding graphic container template to generate the information content of the target product; When the information content of the target product is displayed in the first display area, a corresponding graphic container is loaded according to the product category to which the target product belongs, so as to display the information content of the target product based on the graphic container.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method described in any one of claims 1 to 9 are implemented.

11. An electronic device, characterized in that: include: one or more processors; as well as A memory associated with the one or more processors, the memory being used to store program instructions, wherein when the program instructions are read and executed by the one or more processors, the steps of the method according to any one of claims 1 to 9 are executed.

12. A computer program product comprising a computer program / computer executable instructions, characterized in that: When the computer program / computer executable instructions are executed by a processor in an electronic device, the steps of the method according to any one of claims 1 to 9 are implemented.

Citation Information

Cited By

  • Automatic matching method for picture template and material

    CN122153108A