Method for providing product information, and electronic device

Abstract

Disclosed in the present application are a method for providing product information, and an electronic device. The method comprises: displaying a target image in a product information page, wherein the target image comprises image content of at least one product element; in response to a target operation executed by a user in respect of a target position in the target image, segmenting image content of an associated target product element at the target position by means of an artificial intelligence (AI) large-scale parameter model; and on the basis of the segmented image content of the target product element, performing matching calculation between same and product instances in a product instance set, and providing information of at least one successfully matched product instance. By means of the present application, the traffic steering efficiency of product instances can be improved without relying on manual configuration by merchants, and users are also provided with a new method for quickly acquiring a product search result.

Description

Method and electronic device for providing product information

[0001] This disclosure claims priority to a Chinese patent application filed with the Patent Office of China on March 28, 2024, with application number 202410375000.3 and application name “Method and electronic device for providing product information”, the entire contents of which are incorporated by reference into this disclosure. Technical Field

[0002] The present disclosure relates to the field of information processing technology, and in particular to a method and electronic device for providing commodity information. Background Art

[0003] In the product information service system, in the merchant's store page or product details page, it is often the case that multiple combinations of products are made and displayed on the same picture. For example, for clothing products, many merchants will take pictures of the model after the model has matched a set of clothes to show the effect of the clothes on the body, the effect of matching with other clothes, etc. In this case of displaying multiple products on the same picture, since the multiple products in the same picture may be products sold in the same store, the merchant may also hope to divert multiple products through the picture. For example, the details page of a certain clothing A shows a picture of a model wearing the clothes A, where the model also matches clothes B and C from the same store. At this time, the merchant may hope to divert clothes B and C through the picture of the model wearing the clothes.

[0004] In order to achieve this goal, in the existing technology, merchants are usually required to perform configuration work in advance. Specifically, hot spots can be circled in the above picture, and then links can be configured for the hot spots. In this way, when the user browses the picture, if a hot spot is clicked, the user can jump to the page corresponding to the link configured for the hot spot for display. For example, the area where clothing B is located in the above picture can jump to the details page of clothing B for display, and so on.

[0005] The above method can achieve the diversion of multiple different products based on the same picture. However, the specific implementation requires merchants to have certain production experience and relies on merchants to manually perform configuration operations. If the merchant does not configure hot areas and links, consumers will not be able to know how to purchase the products in the combination from the picture. Summary of the Invention

[0006] The present disclosure provides a method and electronic device for providing product information, which can improve the traffic diversion efficiency of product instances without relying on manual configuration of merchants, and at the same time provide users with a new way to quickly obtain product search results.

[0007] The present disclosure provides the following solutions:

[0008] A method for providing product information, comprising:

[0009] Displaying a target image on a product information page, wherein the target image includes image content of at least one product element;

[0010] In response to a target operation performed by a first user on a target position in the target image, segmenting image content of a target product element associated with the target position using an artificial intelligence (AI) large-scale parameter model;

[0011] Based on the segmented image content of the target product element, a matching calculation is performed with the product instances in the product instance set, and information of at least one product instance that is successfully matched is provided.

[0012] Among them, also include:

[0013] In the process of segmenting the image content of the target product element, the AI ​​large-scale parameter model is used to complete the image of the occluded part of the target product element in the target image, so as to perform matching calculations with the product instances in the product instance set based on the completed image content.

[0014] Among them, also include:

[0015] After segmenting the image content of the target product element, operation options regarding a plurality of optional search ranges are provided so as to perform matching calculations with product instances in a corresponding product instance set within the search range selected by the user.

[0016] The product information page also includes a search condition input control for initiating a product search;

[0017] The matching calculation based on the segmented image content of the target product element and the product instances in the product instance set includes:

[0018] After segmenting the image content of the target product element, in response to the operation of dragging the segmented image content of the target product element to the search condition input control, the step of performing matching calculation based on the segmented image content of the target product element and the product instances in the product instance set is triggered.

[0019] The at least one successfully matched product instance includes a product instance having the same or similar features as the target product element.

[0020] The product information page includes a product details page of a certain product, the target image includes the image content of the product and the image content of other product elements used to match the product, and the segmented target product element is one of the other product elements;

[0021] The matching calculation based on the segmented image content of the target product element and the product instances in the product instance set includes:

[0022] Perform product instance matching calculations within the same store as the product or across the entire platform, and provide information about at least one successfully matched product instance.

[0023] The product information page includes a product information aggregation page associated with a target store, and the target image includes at least one product element in the target store;

[0024] The matching calculation based on the segmented image content of the target product element and the product instances in the product instance set includes:

[0025] A matching calculation of product instances is performed within the same store range of the target store or within the entire platform range, and information of at least one product instance that is successfully matched is provided.

[0026] The product information page includes a cross-store product information aggregation page;

[0027] The matching calculation based on the segmented image content of the target product element and the product instances in the product instance set includes:

[0028] Perform matching calculations for product instances across the entire platform and provide information about at least one successfully matched product instance.

[0029] The step of performing matching calculation based on the segmented image content of the target product element and the product instances in the product instance set includes:

[0030] Perform keyword recognition on the image content of the segmented target product elements;

[0031] The identified keywords are used to construct prompt text expressed in natural language for communicating with the AI ​​large-scale parameter model, so as to determine at least one matching product instance from the product instance set through the AI ​​large-scale parameter model.

[0032] According to the different types of the product information pages, different segmentation granularities are used when performing keyword recognition, and different restrictive conditions are used when constructing the prompt text.

[0033] A product search method, comprising:

[0034] Displaying a target image on a product information page, wherein the target image includes image content of at least one product element;

[0035] In response to a click or long press operation performed by the first user on a target position in the target image, segmenting the image content of the target product element associated with the target position using an AI large-scale parameter model;

[0036] In response to the first user's operation of dragging the segmented image content to the search input control of the product information page, a request for product search based on the segmented image content is initiated, and corresponding product search results are provided.

[0037] A product search method, comprising:

[0038] Displaying a target image on a product information page, wherein the target image includes image content of at least one product element;

[0039] In response to a click or long press operation performed by the first user on a target position in the target image, segmenting the image content of the target product element associated with the target position using an AI large-scale parameter model;

[0040] Provides search operation options for initiating product search requests;

[0041] In response to a product search request initiated by the first user through the search operation option, a search result of a product search based on the segmented image content of the target product element is provided.

[0042] The search operation options include different search operation options corresponding to a plurality of different search ranges, so as to provide product search results within the search range selected by the user.

[0043] A store page design method, comprising:

[0044] receiving a target image uploaded by a second user during a store page design process, wherein the target image is used to demonstrate a matching relationship or matching effect between a plurality of product elements;

[0045] Identify and prompt the image content of multiple target product elements that can be segmented from the target image using an AI large-scale parameter model;

[0046] After receiving the confirmation operation of the second user on the image content segmentation result, the target image is published on the store page, so that when the first user browses the store page, in response to the target operation performed by the first user on the target position in the target image, the AI ​​large-scale parameter model segments the image content of the target product element associated with the target position, and provides product search results based on the segmented image content of the target product element.

[0047] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of any of the aforementioned methods.

[0048] An electronic device, comprising:

[0049] one or more processors; and

[0050] 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.

[0051] A computer program product comprises a computer program / computer executable instructions, wherein the computer program / computer executable instructions, when executed by a processor in an electronic device, implement the steps of any of the aforementioned methods.

[0052] According to the specific embodiments provided by the present disclosure, the present disclosure discloses the following technical effects:

[0053] Through the embodiment of the present disclosure, in the process of displaying the target image in the product information page, if the target image includes the image content of at least one product element, the user can perform a target operation on the target position in the target image. Accordingly, the image content of the target product element associated with the target position can be segmented through an AI (artificial intelligence) large-scale parameter model. After that, the image content of the segmented target product element can be matched with the product instances in the product instance set, and information of at least one product instance that is successfully matched can be provided. In this way, it is possible to divert traffic to a specific product instance through a target image containing the image content of at least one product element, without relying on operations such as hot spot area selection and link configuration by the publisher of the target image. In addition, the successfully matched product instance can be one or more. Therefore, compared with the prior art that can only divert traffic to a single product corresponding to a pre-configured link, the diversion efficiency of the product instance can also be improved, while providing users with a new way to quickly obtain product search results.

[0054] Of course, any product implementing the present disclosure does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0056] FIG1 is a schematic diagram of a system architecture provided by an embodiment of the present disclosure;

[0057] FIG2 is a flow chart of a first method provided by an embodiment of the present disclosure;

[0058] FIG3 is a schematic diagram of an interface provided by an embodiment of the present disclosure;

[0059] FIG4 is a flow chart of a second method provided by an embodiment of the present disclosure;

[0060] FIG5 is a flowchart of a third method provided by an embodiment of the present disclosure;

[0061] FIG6 is a flowchart of a fourth method provided by an embodiment of the present disclosure;

[0062] FIG7 is a schematic diagram of an electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0063] The following will be combined with the accompanying drawings in the embodiments of the present disclosure to clearly and completely describe the technical solutions in the embodiments of the present disclosure. Obviously, the embodiments described are only part of the embodiments of the present disclosure, rather than all the embodiments. Based on the embodiments of the present disclosure, all other embodiments obtained by ordinary technicians in this field are within the scope of protection of the present disclosure.

[0064] In the embodiment of the present disclosure, the image processing capabilities of the AI ​​(Artificial Intelligence) large-scale parameter model (which can be referred to as the "AI large model") in terms of intelligent "cutting out" can be used to segment the image content of the commodity elements contained in the image, and then initiate the matching of commodity instances based on the image content of the segmented commodity elements, and provide the user with information about the successfully matched commodity instances. Specifically, for merchants, for images containing multiple commodity elements, there is no need to circle the hotspot area and configure the link. It is only necessary to directly publish such images on the commodity information page (for example, the store homepage or the commodity details page, etc.). When the user is browsing such an image, if he needs to obtain the corresponding commodity instance information for a certain commodity element, he can click or long press the location of the image content of the commodity element in the image. After that, the AI ​​large model can perform the segmentation of the image content corresponding to the commodity element. Then, based on the image content corresponding to the segmented commodity element, the matching calculation can be performed with the commodity instances in the commodity instance set. The information of the successfully matched commodity instance can be provided to the user for display.

[0065] Among them, the "commodity elements" in the embodiments of the present disclosure refer to elements related to commodities in an image. For example, an image is a photo of a model wearing a set of clothes. The clothes include a skirt, a cardigan, and an inner top. The skirt, cardigan, and inner top are elements related to commodities, that is, elements that may be sold as commodities, but have not yet been specific to one or some specific commodity instances. "Commodity instance" refers to a commodity object that has been published in the current commodity information service system. It is associated with attributes such as commodity ID, price, specification parameters, detailed information, etc., and is an object that can perform purchase operations. For example, a specific commodity published in a store belongs to a "commodity instance". The embodiment of the present disclosure is to segment elements that may belong to commodities from an image, and then match the corresponding commodity instances in the current commodity information service system. Users can perform operations such as purchase and adding to a "shopping cart" based on this commodity instance.

[0066] Through the above method, since the image content of the commodity element can be segmented from the image and matched with the commodity instance, and the commodity instance information of the successful match can be fed back, even if the merchant user does not perform operations such as hotspot circle selection and link configuration in the image during the process of "decorating" the store page, it is still possible to divert multiple commodities through the image. It is even possible to divert more commodities. For example, under the existing implementation method, when the merchant decorates the store page, a link is configured for each element in an image, then only the traffic can be diverted to the commodity associated with the link. However, in the embodiment of the present disclosure, after the image content of a commodity element is segmented, the matched commodity instances can be multiple, for example, not only including a commodity instance with the highest matching degree of the image content, but also more commodity instances with similar features, such as multiple similar commodities in the same store, and even similar commodity instances can be matched across the entire platform, etc. Therefore, more efficient diversion can be achieved.

[0067] From the perspective of system architecture, referring to FIG1 , the embodiment of the present disclosure can provide the above-mentioned commodity element segmentation, commodity instance matching and other related functions in the commodity information service system, and can receive requests initiated by users through long press and other methods on the relevant pages of the client. After that, the server can call a specific AI large model to perform tasks such as commodity element segmentation and commodity instance matching, and return the matching results to the client for display. For example, the client can display the search results page of the commodity instance, and so on. The user can further browse based on the various commodity instances displayed on the matching result page. If there is a commodity instance that meets their needs, they can perform operations such as purchase and adding to the "shopping cart".

[0068] The specific implementation scheme provided by the embodiment of the present disclosure is introduced in detail below.

[0069] Example 1

[0070] First, the first embodiment of the present disclosure provides a method for providing product information from the perspective of a consumer-side client (that is, the perspective of a consumer user. In the present embodiment, the consumer user is referred to as a first user, and correspondingly, a seller user or a merchant user is referred to as a second user). Referring to FIG. 2 , the method may specifically include:

[0071] S201: Displaying a target image on a product information page, wherein the target image includes image content of at least one product element.

[0072] Among them, the product information page can include multiple types. For example, one of them can be the product details page of a specific product. In this product details page, a target image containing the image content of at least one product element can be displayed. For example, a certain product is a skirt. In order to show the upper body effect of the skirt, the product details page includes a model's upper body picture. In the model's upper body picture, the skirt is matched with a sweater cardigan and a top as an inner layer. At this time, the skirt, sweater cardigan and inner layer belong to three different product elements in the image. In the process of browsing such an image, the user may need to view the information of the product corresponding to the sweater cardigan, and may even need to perform a purchase operation on it, etc. Of course, if a target image only includes the image content of one product element, the image content of the product element can also be segmented out, and subsequent matching operations of product instances can be performed.

[0073] Alternatively, the product information page can be an aggregated page for product information associated with a particular store, displaying information for multiple products within the same store. This can include displaying a combination or combination of multiple product elements within the same image. While browsing such an image, users may also want to view information about the product instance corresponding to a particular product element, or even make a purchase.

[0074] Alternatively, the product information page can be a cross-store product information aggregation page, including a product recommendation information flow page, or a marketing event venue page, etc. This type of page can also include the display of multiple different product elements through the same image or combination display effects, etc.

[0075] S202: In response to a target operation performed by the first user on a target position in the target image, segment the image content of the target product element associated with the target position through an artificial intelligence (AI) large-scale parameter model.

[0076] If a user needs to obtain information about a product instance corresponding to a certain product element while browsing the above-mentioned image containing multiple product elements, he or she can directly perform a target operation such as long pressing on a target position in the area where the product element is located in the image. After that, the AI ​​large-scale parameter model can segment the image content of the target product element associated with the target position.

[0077] AI big models refer to machine learning models with large parameters and complex computational structures. These models are typically built using deep neural networks and have billions or even hundreds of billions of parameters. Big models are designed to improve their expressiveness and predictive performance, enabling them to handle more complex tasks and data. Artificial intelligence systems based on big AI models can achieve intelligent behavior by using computational models to simulate human intelligent behavior, thinking, and cognitive processes. In other words, big AI models can provide an explanation and simulation of human intelligence and can also be used to build higher-level AI systems.

[0078] Based on the above characteristics of the AI ​​big model, in the embodiment of the present disclosure, this AI big model can be used to realize the segmentation of the image content of the commodity elements in the image. Of course, in the specific implementation, in order to improve the accuracy of the segmentation, the AI ​​big model can be trained in advance for the scenario required by the embodiment of the present disclosure to improve its ability to identify commodity elements. In addition, in order to enable the segmented commodity elements to match the corresponding commodity instances, the pictures of multiple commodity instances within the entire platform and other ranges can be scanned and modeled in advance, and the keywords and other information can be extracted, and the AI ​​big model can be trained with these pictures, keywords, etc., so that the AI ​​big model has the ability to identify commodity elements of various categories and different characteristics, and can preliminarily determine whether a certain element can be matched to the corresponding commodity instance, and then determine whether the commodity element corresponding to the area currently operated by the user can be segmented out and perform subsequent commodity instance matching and other operations. If so, the specific segmentation processing is performed.

[0079] It should be noted that since the image content of a product element is segmented from a combined image of multiple product elements, the image content of the product element may be obscured by other product elements or other elements in the image. For example, the back of the cardigan shown at 31 in Figure 3(A) is obscured by the model's body or the top she is wearing underneath. In this case, if the image content is segmented directly from the original image, the image content of the product element may be incomplete. Therefore, in a preferred embodiment, the image content of the segmented product element that is obscured in the target image can be supplemented using an AI large model, etc. This can also make the subsequent product instance matching results based on the product element more accurate. For example, for the cardigan shown at 31 in Figure 3(A), after the user performs a long press operation, the segmented and supplemented image content of the product element can be shown at 32 in Figure 3(B), where the missing part of the back of the product element has been supplemented. Among them, the ability to complete this image can also be provided by the AI ​​big model, and the AI ​​big model can also be trained in advance using pictures related to various product elements to improve its ability to complete the image content of various product elements.

[0080] S202: performing a matching calculation with product instances in the product instance set based on the segmented image content of the target product element, and providing information of at least one product instance that is successfully matched.

[0081] After segmenting the image content of the target product element, a matching calculation can be performed based on this image content with product instances in the product instance set to determine the information of at least one successfully matched product instance and return it to the user. A product instance is a product that has been published to the product information service system and is associated with a unique identifier such as a product ID provided by the product information service system. It also has product attributes defined in the product information service system.

[0082] In specific implementations, the aforementioned product instance matching-related processing can be automatically triggered after the image content of the target product element is segmented. Alternatively, it can be manually triggered by the user. There are various ways for the user to manually trigger the process. For example, in one approach, after the image content corresponding to the target product element is segmented, an operation option for initiating a search or other operations can be provided at a location near the image content. The user can trigger the specific matching process by clicking on the operation option. In actual applications, when matching product instances, the specific search scope can also be varied. For example, it can include matching within the store, or matching across the entire platform, etc. When displaying operation options, operation options for different search scopes can also be provided, so that matching calculations can be performed with product instances in the corresponding product instance set within the search scope selected by the user. For example, as shown at 33 in FIG. 3(B), multiple different options such as "Same Style in This Store" and "Same Style Across All Platforms" can be provided, and the user can select one of these options to initiate a search based on their needs.

[0083] Alternatively, in another manner, if the current product information page has a search condition input control for initiating a product search, such as a search input box, then after segmenting the image content of the target product element, the image content of the target product element can be set to a draggable state, and the user can perform an operation of dragging the segmented image content of the target product element to the search condition input control, thereby triggering a specific search process, that is, the step of performing a matching calculation based on the segmented image content of the target product element with the product instances in the product instance set. For example, as shown in Figure 3(C), after the user performs a long press operation on the image shown in Figure 3(A) to segment the image content of the target product element, the user can drag the image content to the search input box shown in 34 in Figure 3(C) to trigger the search process.

[0084] Among them, in the aforementioned automatic triggering search process, the specific search scope can also be dynamically determined based on the type of product information page where the specific request is initiated. That is, different types of product information pages usually correspond to different fields, and accordingly, the user's needs or demands may be different. For example, if the current product information page is the product details page of a certain product instance, at this time, the specific target image includes the image content of the product instance and the image content of other product elements used to match the product instance, and the segmented target product element is one of the other product elements. In this case, the user may need to search for the same / similar products in the same store (that is, product instances with the same or similar features as the target product element), or may need to search for the same / similar products across the entire platform. Therefore, the product instance matching calculation can be performed within the same store of the store to which the product belongs or across the entire platform, and information about at least one successfully matched product instance is provided. Of course, in the case of a full-platform search, if the current product also has a successfully matched same / similar item in the store, the successfully matched same / similar items in that store can be displayed first, and so on.

[0085] If the product information page is a product information aggregation page associated with the target store, then the specific target image includes at least one product element in the target store, and may also include product elements in stores other than the current store. In this case, the matching calculation of product instances can also be performed within the same store as the target store or across the entire platform, and information on at least one successfully matched product instance can be provided. Alternatively, the search for the same / similar product instances can be prioritized within the same store. If there are no matching product instances in the store, or the number of matching product instances is relatively small, the same / similar product instances can be searched across the entire platform, and so on.

[0086] In addition, if the product information page is a cross-store product information aggregation page, for example, a client homepage containing a product recommendation information flow, or an event venue page for some marketing activities, etc., then the matching calculation of product instances can be performed across the entire platform, and information about at least one product instance that has been successfully matched can be provided.

[0087] Specifically, when performing a product instance matching operation based on the image content of the segmented product elements, there are multiple implementation methods. For example, in one method, keyword recognition can be first performed based on the image content of the segmented product elements, and then product instance matching can be performed based on the keywords. The keyword-based product instance matching can be implemented using traditional methods, such as determining the matching degree between the product instance title, text content in the image and text details, and the extracted keywords to determine the matching product instance. Alternatively, in another method, this product matching process can also be performed by the AI ​​large model. In this case, since the AI ​​large model typically requires prompt text input, this prompt text is a text input used to guide the large model to generate specific content. Its function is to tell the large model what to do and can also provide it with some necessary information and constraints, etc. Therefore, after keyword recognition is performed on the image content of the segmented target product element, the recognized keywords can also be used to construct prompt text expressed in natural language for dialogue with the AI ​​large-scale parameter model, so that the AI ​​large-scale parameter model can determine at least one matching product instance from the product instance set.

[0088] Specifically, in various scenarios, keyword recognition can be performed at different granularities. When constructing prompt text, different constraints can also be set within the prompt text. For example, in scenarios like product detail pages and store pages, there may be a greater need to match instances of the same or similar items within the same store. In this case, the keyword granularity can be more refined. For example, the product elements segmented in Figure 3(B) can be refined to include style, color, material, fabric type, collar type, button-up, and so on. When constructing prompt text, more restrictive constraints can also be set, such as "I want to find a short-length cardigan sweater in the same store, red, cashmere, round neck, buttoned." In public scenarios like client homepages, there may be a greater need to match instances of the same or similar items across the entire platform. In this case, the keyword granularity can be coarser, for example, only down to the category granularity. When constructing prompt text, the constraints can also be more relaxed, such as "I want to find a short-length cardigan sweater."

[0089] In summary, through the embodiments of the present disclosure, in the process of displaying the target image in the product information page, if the target image includes the image content of multiple product elements, the user can perform a target operation on the target area in the target image. Accordingly, the image content of the target product element associated with the target area can be segmented through an AI (artificial intelligence) large-scale parameter model. After that, the image content of the segmented target product element can be matched with the product instances in the product instance set, and information about at least one product instance that is successfully matched can be provided. In this way, it is possible to divert traffic to a specific product instance through a target image containing image content of multiple product elements, without relying on operations such as hot spot area selection and link configuration by the publisher of the target image. In addition, the successfully matched product instance can be one or more. Therefore, compared with the prior art that can only divert traffic to a single product corresponding to a pre-configured link, the diversion efficiency of the product instance can also be improved, while providing users with a new way to quickly obtain product search results.

[0090] Example 2

[0091] In the aforementioned embodiment 1, the specific interaction method is mainly introduced from the perspective of the first user. In particular, in the specific implementation, an implementation scheme for product search based on the image content segmented by the AI ​​large model can also be provided. That is to say, in the prior art, the user either enters a keyword to initiate a product search, or takes a photo of a physical product or selects a picture from the local album to initiate a product search. However, in the embodiment 2 of the present disclosure, you can click or long press a certain position in a target image from a specific product information page. Correspondingly, the AI ​​large model can segment the image content of the target product element associated with that position. After that, the user can drag the segmented image content to the search input box in the current product information page to initiate a product search request.

[0092] Specifically, this second embodiment provides a product search method. Referring to FIG4 , the method may include:

[0093] S401: Displaying a target image on a product information page, wherein the target image includes image content of at least one product element;

[0094] S402: In response to a click or long press operation performed by the first user on a target position in the target image, segmenting image content of a target product element associated with the target position using an AI large-scale parameter model;

[0095] S403: In response to the first user's operation of dragging the segmented image content to the search input control of the product information page, a request for product search based on the segmented image content is initiated, and corresponding product search results are provided.

[0096] Example 3

[0097] This third embodiment also provides another product search method from the perspective of the first user performing a product search. Unlike the second embodiment, after the user clicks or long presses a certain position in the image and the AI ​​model segments the image content of the target product element, a search operation option for initiating a product search request can be provided directly near the image content. In this way, the first user can initiate a search request through this operation option without having to drag the segmented image content to the search input box. Specifically, as shown in Figure 5, the method may include:

[0098] S501: Displaying a target image on a product information page, wherein the target image includes image content of at least one product element;

[0099] S502: In response to a click or long press operation performed by the first user on a target position in the target image, segmenting image content of a target product element associated with the target position using an AI large-scale parameter model;

[0100] S503: providing a search operation option for initiating a product search request;

[0101] S504: In response to the product search request initiated by the first user through the search operation option, provide search results for product search based on the segmented image content of the target product element.

[0102] Specifically, the search operation options include different search operation options corresponding to a plurality of different search scopes, for example, "same style in store" or "same style on all platforms", etc. In this way, product search results can be provided within the search scope selected by the user.

[0103] Example 4

[0104] This fourth embodiment mainly provides a store page design method from the perspective of the second user (i.e., a merchant or seller user, etc.). Among them, since it can provide image segmentation and product matching or product search based on the segmented image, when the second user is designing the store page (which can also be called the "decoration" of the store page, including the design of the page layout of the products displayed on the "shelves" in the store, marketing promotion content, etc.), for the target image that needs to display the matching relationship or matching effect between multiple products, it is no longer necessary to configure hot links for each product, but the target image can be directly placed in a resource position in the store page. Of course, in order to enable the second user to more intuitively perceive the function of searching based on the image content segmented by AI provided by the embodiment of the present disclosure, and also to verify the effect or accuracy of AI segmentation, after the second user uploads a target image, the AI ​​large model can identify the image content of multiple target product elements that can be segmented in the target image and prompt it to the second user. In this way, after the user confirms the segmentation result, the target image can be officially published to the store page. Specifically, this fourth embodiment provides a store page design method, see Figure 6, the method may include:

[0105] S601: Receive a target image uploaded by a second user during the store page design process, wherein the target image includes image content of at least one product element;

[0106] S602: Identifying and providing prompts for the image contents of multiple target product elements that can be segmented from the target image using an AI large-scale parameter model;

[0107] S603: After receiving the confirmation operation of the second user on the image content segmentation result, the target image is published on the store page, so that when the first user browses the store page, in response to the target operation performed by the first user on the target position in the target image, the AI ​​large-scale parameter model segments the image content of the target product element associated with the target position, and provides product search results based on the segmented image content of the target product element.

[0108] For the parts not described in detail in the above-mentioned embodiments 2 to 4, please refer to the description of embodiment 1 and other parts of this specification, and will not be repeated here.

[0109] It should be noted that the embodiments of the present disclosure may involve the use of user data. In actual applications, user-specific personal data may be used in the scenarios described herein within the scope permitted by applicable laws and regulations, subject to compliance with 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.).

[0110] Corresponding to the first embodiment, the embodiment of the present disclosure further provides a device for providing product information, which may include:

[0111] An image display unit, configured to display a target image on a product information page, wherein the target image includes image content of at least one product element;

[0112] an image content segmentation unit, configured to segment the image content of the target product element associated with the target position in the target image by using an artificial intelligence (AI) large-scale parameter model in response to a target operation performed by the first user on the target position in the target image;

[0113] The product matching unit is configured to perform matching calculations with product instances in the product instance set based on the segmented image content of the target product element, and provide information about at least one product instance that has been successfully matched.

[0114] The device may further include:

[0115] An image completion unit is used to use the AI ​​large-scale parameter model to complete the image of the target product element that is obscured in the target image during the process of segmenting the image content of the target product element, so as to perform matching calculations with product instances in the product instance set based on the completed image content.

[0116] In addition, the device may further include:

[0117] The search operation option providing unit is used to provide operation options regarding multiple optional search ranges after segmenting the image content of the target product element, so as to perform matching calculations with product instances in the corresponding product instance set within the search range selected by the user.

[0118] Alternatively, if the product information page further includes a search condition input control for initiating a product search, the product matching unit may be specifically configured to:

[0119] After segmenting the image content of the target product element, in response to the operation of dragging the segmented image content of the target product element to the search condition input control, the step of performing matching calculation based on the segmented image content of the target product element and the product instances in the product instance set is triggered.

[0120] The at least one successfully matched product instance includes a product instance having the same or similar features as the target product element.

[0121] Specifically, the product information page includes a product details page of a certain product, the target image includes the image content of the product and the image content of other product elements used to match the product, and the segmented target product element is one of the other product elements;

[0122] At this time, the product matching unit can be specifically used to:

[0123] Perform product instance matching calculations within the same store as the product or across the entire platform, and provide information about at least one successfully matched product instance.

[0124] Alternatively, the product information page includes a product information aggregation page associated with a target store, and the target image includes at least one product element in the target store;

[0125] At this time, the product matching unit can be specifically used to:

[0126] A matching calculation of product instances is performed within the same store range of the target store or within the entire platform range, and information of at least one product instance that is successfully matched is provided.

[0127] Alternatively, the product information page includes a cross-store product information aggregation page;

[0128] At this time, the product matching unit can be specifically used to:

[0129] Perform matching calculations for product instances across the entire platform and provide information about at least one successfully matched product instance.

[0130] Specifically, the product matching unit can be used to

[0131] Perform keyword recognition on the image content of the segmented target product elements;

[0132] The identified keywords are used to construct prompt text expressed in natural language for communicating with the AI ​​large-scale parameter model, so as to determine at least one matching product instance from the product instance set through the AI ​​large-scale parameter model.

[0133] According to the different types of the product information pages, different segmentation granularities are used when performing keyword recognition, and different restrictive conditions are used when constructing the prompt text.

[0134] Corresponding to the second embodiment, the embodiment of the present disclosure further provides a product search device, which may include:

[0135] An image display unit, configured to display a target image on a product information page, wherein the target image includes image content of at least one product element;

[0136] an image content segmentation unit, configured to segment the image content of the target product element associated with the target position in the target image by using an AI large-scale parameter model in response to a click or long press operation performed by the first user on the target position in the target image;

[0137] The first search unit is configured to initiate a request for searching for products based on the segmented image content in response to the first user dragging the segmented image content to the search input control of the product information page, and provide corresponding product search results.

[0138] Corresponding to the third embodiment, the embodiment of the present disclosure further provides a product search device, which may include:

[0139] An image display unit, configured to display a target image on a product information page, wherein the target image includes image content of at least one product element;

[0140] an image content segmentation unit, configured to segment the image content of the target product element associated with the target position in the target image by using an AI large-scale parameter model in response to a click or long press operation performed by the first user on the target position in the target image;

[0141] A search operation option providing unit, configured to provide a search operation option for initiating a product search request;

[0142] The second search unit is configured to provide search results for a product search based on the segmented image content of the target product element in response to a product search request initiated by the first user through the search operation option.

[0143] The search operation options include different search operation options corresponding to a plurality of different search ranges, so as to provide product search results within the search range selected by the user.

[0144] Corresponding to the fourth embodiment, the embodiment of the present disclosure further provides a store page design device, which may include:

[0145] An image receiving unit, configured to receive a target image uploaded by a second user during the store page design process, wherein the target image is used to display a matching relationship or matching effect between multiple product elements;

[0146] a prompting unit, configured to identify and prompt the image contents of a plurality of target product elements that can be segmented from the target image using an AI large-scale parameter model;

[0147] The image publishing unit is used to publish the target image to the store page after receiving the confirmation operation of the second user on the image content segmentation result, so that when the first user browses the store page, in response to the target operation performed by the first user on the target position in the target image, the AI ​​large-scale parameter model segments the image content of the target product element associated with the target position, and provides product search results based on the segmented image content of the target product element.

[0148] In addition, an embodiment of the present disclosure further provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the steps of any one of the methods in the aforementioned method embodiments are implemented.

[0149] And an electronic device comprising:

[0150] one or more processors; and

[0151] 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 one of the method embodiments described above.

[0152] 7 exemplarily shows the architecture of an electronic device. For example, device 700 may 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.

[0153] 7 , device 700 may include one or more of the following components: a processing component 702 , a memory 704 , a power component 706 , a multimedia component 708 , an audio component 710 , an input / output (I / O) interface 712 , a sensor component 714 , and a communication component 716 .

[0154] The processing component 702 generally controls the overall operation of the device 700, such as operations associated with display, phone calls, data communications, camera operation, and recording operations. The processing component 702 may include one or more processors 720 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 702 may include one or more modules to facilitate interaction between the processing component 702 and other components. For example, the processing component 702 may include a multimedia module to facilitate interaction between the multimedia component 708 and the processing component 702.

[0155] The memory 704 is configured to store various types of data to support operations on the device 700. Examples of such data include instructions for any application or method operating on the device 700, contact data, phone book data, messages, pictures, videos, etc. The memory 704 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.

[0156] The power supply component 706 provides power to the various components of the device 700. The power supply component 706 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the device 700.

[0157] The multimedia component 708 includes a screen that provides an output interface between the device 700 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 touches, slides, and gestures on the touch panel. The touch sensor can not only sense the boundaries of a touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 708 includes a front camera and / or a rear camera. When the device 700 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera can receive external multimedia data. Each front camera and rear camera can be a fixed optical lens system or have a focal length and optical zoom capability.

[0158] The audio component 710 is configured to output and / or input audio signals. For example, the audio component 710 includes a microphone (MIC), which is configured to receive external audio signals when the device 700 is in an operating mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signal can be further stored in the memory 704 or transmitted via the communication component 716. In some embodiments, the audio component 710 also includes a speaker for outputting audio signals.

[0159] I / O interface 712 provides an interface between processing component 702 and peripheral interface modules, such as a keyboard, click wheel, buttons, etc. These buttons may include but are not limited to: a home button, volume buttons, a start button, and a lock button.

[0160] Sensor assembly 714 includes one or more sensors for providing various aspects of device 700 status assessment. For example, sensor assembly 714 can detect the open / closed state of device 700, the relative positioning of components, such as the display and keypad of device 700. Sensor assembly 714 can also detect changes in the position of device 700 or a component of device 700, the presence or absence of user contact with device 700, the orientation or acceleration / deceleration of device 700, and changes in the temperature of device 700. Sensor assembly 714 can include a proximity sensor configured to detect the presence of nearby objects without any physical contact. Sensor assembly 714 can also include an optical sensor, such as a CMOS (Complementary Metal-Oxide-Semiconductor) or CCD (Charge-Coupled Device) image sensor, for use in imaging applications. In some embodiments, sensor assembly 714 can also include an accelerometer, a gyroscope, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0161] The communication component 716 is configured to facilitate wired or wireless communication between the device 700 and other devices. The device 700 can access a wireless network based on a communication standard, such as WiFi (Wireless Fidelity), or a mobile communication network such as 2G (Second Generation), 3G (Third Generation), 4G (Fourth Generation) / LTE (Long Term Evolution), or 5G (Fifth Generation). In an exemplary embodiment, the communication component 716 receives broadcast signals or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 716 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.

[0162] In an exemplary embodiment, the device 700 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.

[0163] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 704 including instructions. The instructions can be executed by the processor 720 of the device 700 to perform 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.

[0164] The embodiments of the present disclosure further provide a computer program product, including a computer program / computer executable instructions, which implements the steps of any one of the methods described in the aforementioned method embodiments when the computer program / computer executable instructions are executed by a processor in an electronic device.

[0165] Through the description of the above embodiments, it can be seen that those skilled in the art can clearly understand that the present disclosure can be implemented by means of software plus a necessary general hardware platform. Based on this understanding, the technical solution of the present disclosure, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product can be stored in a storage medium such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of 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 various embodiments or certain parts of the embodiments of the present disclosure.

[0166] Each embodiment in this specification is described in a progressive manner. The same or similar parts between the embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments. In particular, for system or system embodiments, since they are basically similar to method embodiments, the description is relatively simple. For relevant parts, 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 can be selected according to actual needs to achieve the purpose of the solution of this embodiment. A person of ordinary skill in the art can understand and implement it without expending creative work.

[0167] The above is a detailed introduction to the method and electronic device for providing product information provided by the present disclosure. Specific examples are used herein to illustrate the principles and implementation methods of the present disclosure. The description of the above embodiments is intended only to help understand the method and core concept of the present disclosure. At the same time, those skilled in the art will appreciate that variations in the specific implementation methods and scope of application may occur based on the concepts of the present disclosure. In summary, the contents of this specification should not be construed as limiting the present disclosure.

Claims

1. A method for providing product information, wherein: include: Displaying a target image on a product information page, wherein the target image includes image content of at least one product element; In response to a target operation performed by a first user on a target position in the target image, segmenting image content of a target product element associated with the target position using an artificial intelligence (AI) large-scale parameter model; Based on the segmented image content of the target product element, a matching calculation is performed with the product instances in the product instance set, and information of at least one product instance that is successfully matched is provided.

2. The method according to claim 1, wherein Also includes: In the process of segmenting the image content of the target product element, the AI ​​large-scale parameter model is used to complete the image of the occluded part of the target product element in the target image, so as to perform matching calculations with the product instances in the product instance set based on the completed image content.

3. The method according to claim 1 or 2, wherein: Also includes: After segmenting the image content of the target product element, operation options regarding a plurality of optional search ranges are provided so as to perform matching calculations with product instances in a corresponding product instance set within the search range selected by the user.

4. The method according to claim 1, wherein The product information page also includes a search condition input control for initiating a product search; The matching calculation based on the segmented image content of the target product element and the product instances in the product instance set includes: After segmenting the image content of the target product element, in response to the operation of dragging the segmented image content of the target product element to the search condition input control, the step of performing matching calculation based on the segmented image content of the target product element and the product instances in the product instance set is triggered.

5. The method according to any one of claims 1 to 4, wherein: The at least one successfully matched commodity instance includes a commodity instance having the same or similar features as the target commodity element.

6. The method according to any one of claims 1 to 5, wherein: The product information page includes a product details page of a certain product, the target image includes the image content of the product and the image content of other product elements used to match the product, and the segmented target product element is one of the other product elements; The matching calculation based on the segmented image content of the target product element and the product instances in the product instance set includes: Perform product instance matching calculations within the same store as the product or across the entire platform, and provide information about at least one successfully matched product instance.

7. The method according to any one of claims 1 to 5, wherein: The product information page includes a product information aggregation page associated with a target store, and the target image includes at least one product element in the target store; The matching calculation based on the segmented image content of the target product element and the product instances in the product instance set includes: A matching calculation of product instances is performed within the same store range of the target store or within the entire platform range, and information of at least one product instance that is successfully matched is provided.

8. The method according to any one of claims 1 to 5, wherein: The product information page includes a cross-store product information aggregation page; The matching calculation based on the segmented image content of the target product element and the product instances in the product instance set includes: Perform matching calculations for product instances across the entire platform and provide information about at least one successfully matched product instance.

9. The method according to any one of claims 1 to 8, wherein: The matching calculation based on the segmented image content of the target product element and the product instances in the product instance set includes: Perform keyword recognition on the image content of the segmented target product elements; The identified keywords are used to construct prompt text expressed in natural language for communicating with the AI ​​large-scale parameter model, so as to determine at least one matching product instance from the product instance set through the AI ​​large-scale parameter model.

10. The method according to claim 9, wherein: According to the different types of the product information pages, different segmentation granularities are adopted when performing keyword recognition, and different restrictive conditions are adopted when constructing the prompt text.

11. A product search method, wherein: include: Displaying a target image on a product information page, wherein the target image includes image content of at least one product element; In response to a click or long press operation performed by the first user on a target position in the target image, segmenting the image content of the target product element associated with the target position using an AI large-scale parameter model; In response to the first user's operation of dragging the segmented image content to the search input control of the product information page, a request for product search based on the segmented image content is initiated, and corresponding product search results are provided.

12. A product search method, wherein: include: Displaying a target image on a product information page, wherein the target image includes image content of at least one product element; In response to a click or long press operation performed by the first user on a target position in the target image, segmenting the image content of the target product element associated with the target position using an AI large-scale parameter model; Provides search operation options for initiating product search requests; In response to a product search request initiated by the first user through the search operation option, a search result of a product search based on the segmented image content of the target product element is provided.

13. The method according to claim 12, wherein: The search operation options include different search operation options corresponding to a plurality of different search ranges, so as to provide product search results within the search range selected by the user.

14. A store page design method, wherein: include: receiving a target image uploaded by a second user during a store page design process, wherein the target image is used to demonstrate a matching relationship or matching effect between a plurality of product elements; Identify and prompt the image content of multiple target product elements that can be segmented from the target image using an AI large-scale parameter model; After receiving the confirmation operation of the second user on the image content segmentation result, the target image is published on the store page, so that when the first user browses the store page, in response to the target operation performed by the first user on the target position in the target image, the AI ​​large-scale parameter model segments the image content of the target product element associated with the target position, and provides product search results based on the segmented image content of the target product element.

15. A computer-readable storage medium having a computer program stored thereon, wherein: When the program is executed by a processor, the steps of the method according to any one of claims 1 to 14 are implemented.

16. An electronic device, wherein: 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 14 are performed.

17. A computer program product comprising a computer program / computer executable instructions, wherein: 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 14 are implemented.

Images