Method for providing commodity information and electronic equipment

Abstract

The embodiment of the invention discloses a method for providing commodity information and electronic equipment, which are applied to a client of a commodity information service system, and the method comprises the following steps: in a target interface of the client of the commodity information service system, providing an operation option for performing artificial intelligence (AI) design based on a commodity image of a target commodity; after an operation request of a user is received, obtaining design demand information of commodity design based on first main body image content of the commodity image input by the user; obtaining a target image according to the design demand information, the target image being generated by the following steps: generating prompt information for dialogue with an AI large model, and calling the AI large model according to the commodity image and the prompt information, the AI large model processes first main body image content in the commodity image according to the prompt information, and a target image is generated; and returning the target image to the user. According to the embodiment of the invention, a user can conveniently purchase commodities meeting creative requirements of the user.

Description

Technical Field

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

[0002] In the commodity information service system (generally referred to as "e-commerce platform", etc.), there are some special buyers, for example, Class B buyers (merchants who purchase on e-commerce platforms, they usually wholesale goods for resale or production). When purchasing a certain type of commodity, these buyers may have some vague and relatively abstract creative ideas. However, such creativity faces challenges such as unclear implementation path and unpredictable success or failure from concept to implementation, which also makes it difficult for users to purchase goods that meet their creative needs. Summary of the invention

[0003] The present application provides a method and electronic device for providing product information, which can facilitate users to purchase products that meet their creative needs.

[0004] This application provides the following solutions:

[0005] A method for providing commodity information, the method being applied to a client of a commodity information service system, comprising:

[0006] In the target interface of the commodity information service system client, an operation option for performing artificial intelligence AI design based on the commodity image of the target commodity is provided;

[0007] After receiving the user's operation request through the operation option, obtaining the design requirement information input by the user for product design based on the first main image content of the product image;

[0008] A target image is acquired according to the design requirement information, and the target image is generated in the following manner: prompt information for communicating with the AI ​​big model is generated, and the AI ​​big model is called according to the product image and the prompt information, so that the AI ​​big model processes the first main image content in the product image according to the prompt information to generate a target image, wherein the target image includes a second main image content obtained by modifying the first main image content, so as to visually express the user's design requirements through the modified second main image content;

[0009] The target image is returned to the user so that the user can obtain information about the corresponding product based on the second main image content in the target image.

[0010] Among them, the target interface includes a product information display page of the target product, and the users include merchant-type buyer users in the product information service system. The merchant-type buyer users include: buyer users who purchase or customize products in bulk through the product information service system for resale or production purposes.

[0011] The step of obtaining the design requirement information input by the user for product design based on the first main image content of the product image includes:

[0012] Obtain design requirement information expressed by the user through text description content input.

[0013] The step of obtaining the design requirement information input by the user for product design based on the first main image content of the product image includes:

[0014] An editing interface for circling the first main image content of the product image is provided, so that the user can circle a local area from the first main image content of the product image and express the design requirement information for the local area by entering text description content.

[0015] Among them, it also includes:

[0016] After returning the target image to the user, further user input of the requirement information for modifying the second main image content in the target image is received so as to regenerate the prompt information, and the AI ​​big model modifies the second main image content in the target image.

[0017] Among them, it also includes:

[0018] A product search request based on the target image is received from a user, and product search results matching the second main image content in the target image are returned.

[0019] Among them, it also includes:

[0020] If there is no product matching the second main image content in the target image in the product information service system, factory-type merchant information with product customization capability is provided according to the category to which the target product belongs.

[0021] Among them, the AI ​​big model is obtained after fine-tuning and training using data in the commodity information service system in advance, so that the generated second main image content has the attributes that can produce corresponding products.

[0022] A method for providing commodity information, the method being applied to a service end of a commodity information service system, comprising:

[0023] Receiving design requirement information submitted by a client, wherein the design requirement information includes: design requirement information for product design based on a first main image content in a product image of a target product input by a user;

[0024] Generate prompts for conversations with the AI ​​model;

[0025] Calling the AI ​​big model according to the product image and the prompt information, so that the AI ​​big model processes the first main image content in the product image according to the prompt information to generate a target image, wherein the target image includes the second main image content obtained by modifying the first main image content, so as to visually express the user's design requirements through the modified second main image content;

[0026] The target image is returned to the client so that the user can obtain information about the corresponding product based on the second main image content in the target image.

[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 embodiments of the present application, in the process of displaying the information of the target product to the buyer user, an operation option for artificial intelligence AI design based on the product image of the target product can be provided. After receiving the user's operation request through the operation option, the design requirement information for product design based on the first main image content of the product image input by the user can be obtained; then, prompt information for dialogue with the AI ​​big model can be generated according to the design requirement information, and the AI ​​big model can be called according to the product image and the prompt information, so that the AI ​​big model processes the first main image content in the product image according to the prompt information to generate a target image, and the target image includes the second main image content obtained by modifying the first main image content, so as to visually express the design requirement through the modified second main image content. Finally, the generated target image can be returned to the user so that the user can obtain the information of the corresponding product based on the second main image content in the target image. In this way, further design based on the first main image content in the specific product image can be provided within the product information service system to generate a target image, so that the user's abstract creativity and ideas in product design can be converted into intuitive visual images, which is convenient for users to express their needs more accurately; and, since the second main image content of the specific target product is generated based on the first main image content in the product image of a real product, the second main image content in the generated target image can be an image that is more realistic and closer to the product image of the real product, so as to facilitate finding the real existing product supply in the product information service system.

[0034] 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

[0035] 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.

[0036] Figure 1 It is a schematic diagram of the system architecture provided by the embodiment of the present application;

[0037] Figure 2 is a flowchart of a client-side method provided in an embodiment of the present application;

[0038] Figures 3-1 to 3-4 is a schematic diagram of an interface provided by an embodiment of the present application;

[0039] Figure 4 is a flow chart of the server-side method provided in an embodiment of the present application;

[0040] Figure 5 It is a schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0041] 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.

[0042] First of all, it should be noted that the inventor of this application discovered in the process of realizing this application that for Class B buyer users, unlike ordinary individual consumer users, Class B buyer users themselves are usually merchants or operators, and they usually purchase some goods in bulk through the commodity information service system, and then use them for resale or production, etc. Therefore, these Class B users usually also need to continuously innovate the commodities they operate in order to better attract and retain their customers. In addition, these Class B users may also have relatively keen market insights and can discover some new trends, etc. For example, for a certain type of commodity, Class B users may roughly know that some design elements may be more popular with customers, etc. If the user can accurately describe the characteristics and other information of the commodity he needs, the corresponding commodity can be searched in the commodity information service system. However, in some cases, the user may find it difficult to accurately describe his ideas or creativity, etc., so that it is difficult to convert his ideas into actual purchasable commodities.

[0043] In response to the above situation, an embodiment of the present application provides a solution. In this solution, when a buyer user browses specific product information through a product information service system, an operation option for invoking an AI (Artificial Intelligence) design assistant can be provided in the relevant page. The user can superimpose his or her own creative ideas on the relevant images of the product currently being browsed, and use the content understanding and generation capabilities of the AI ​​big model (the so-called AI big model refers to a deep learning model containing massive parameters, which can usually be called an AI large-scale parameter model, or an AI big model, etc. This type of AI big model can store and process a large amount of information due to its large scale, thereby achieving higher performance in various tasks) to understand the user's creative ideas and generate a target image based on the product image of the current product. Through this target image, the user's creative ideas can be visualized. For example, when a user is browsing a product image of a cup, he thinks that if he makes some new designs based on the cup, for example, adding a certain pattern to a certain position on the cup body, it may make the product more attractive, etc. Therefore, he can click on the "AI design" and other operation options on the page and describe his specific creativity, ideas, and concepts. The specific description method can be described in text, or the user can be provided with tools to edit the product image of the current product, so that the user can circle a certain area of ​​the product image, so that the user can enter specific design requirements description information for a specific area. After that, the corresponding target image can be generated by the AI ​​big model, so as to realize the visual presentation of the user's creative ideas. In the specific implementation, if the user is not satisfied with the specific target image after viewing it, he can further communicate with the AI ​​big model, thereby triggering the AI ​​big model to modify the target image until the user is satisfied.

[0044] Afterwards, since the user's design creativity and ideas have been presented through the target image, the user can directly initiate a product search based on the target image, and accordingly, the information of the products matching the target image in the current product information service system can be returned to the user. If there is no spot product matching the target image in the current product information service system, the information of factory-type merchant users with product customization capabilities can also be recommended to the user based on the specific product category and other information, so that the user can contact such merchant users to realize customized production of the products they need, etc.

[0045] It should be noted here that the embodiment of the present application is to conduct an image-based product search after redesigning the main image content in the product image through the AI ​​big model. In another implementation method, the user can generate images in advance through other systems or tools, that is, convert their ideas or creativity into visual images, and then use the image to initiate a product search in the product information service system. However, in the embodiment of the present application, since specific image generation related services are provided within the specific product information service system, users can directly initiate specific AI design requests in the system while browsing product information, and convert their creative ideas into visual images, and can directly search for related products in the system, thereby realizing a "one-stop" service. In addition, in the embodiment of the present application, the user can express relevant creativity or ideas based on browsing the product image of a specific product, and then generate a target image. In addition, in a preferred manner, the specific AI big model can also be pre-trained with data related to the product information service system, rather than using a general AI big model for image generation. Therefore, the generated target image can be an image that is more realistic and closer to the real product image, so as to facilitate finding the real existing product supply in the product information service system. If a general AI big model is used in other systems or applications for image generation in advance, the generated image may be difficult to find the real product supply in the product information service system due to reasons such as being unsuitable for actual production.

[0046] From the perspective of system architecture, see Figure 1, the embodiment of the present application can provide corresponding services or functions in the commodity information service system, and the commodity information service system may include a client and a server, wherein the client may be a client for buyer users, and the buyer user may browse the information of specific commodities through the client, and the relevant operation options for invoking the AI ​​design assistant may be provided in the relevant interface for displaying the commodity information, and if the user needs to superimpose his own design creativity, ideas, etc. on the commodity image of the currently browsed commodity, the AI ​​design assistant may be invoked through the operation option, and then the user may input his own design requirement information, including describing his own creative requirements in text form, or may also circle the commodity image, etc. Afterwards, specific prompt information (Prompt) may be generated based on the user's design requirement information, and the prompt information and the commodity image of the current commodity may be input to the AI ​​big model, and the AI ​​big model may understand the user's creative ideas, etc., and generate the target image based on the commodity image of the current commodity. Among them, the AI ​​big model may usually be called by the server, and then the server returns the target image generated by the AI ​​big model to the client, and the client displays it. After viewing the specific generated target image, the user can further input modification requirements through the relevant interface in the client to modify the target image until the user is satisfied. Then, the user can also initiate a product search based on the final generated target image. If there is a matching product, it can be returned to the user. If there is no matching product, factory-type merchant information with relevant customization service capabilities can also be provided.

[0047] Among them, Prompt in the field of AI usually refers to a piece of text or instruction entered by the user, which is used to guide the artificial intelligence system to generate corresponding content. Specifically in the field of image generation or "image modification" in the embodiment of the present application, a Prompt can be a detailed description of the image content, a text description of the modification requirements, or other prompt information that helps the system understand the user's intention. Through a reasonably designed Prompt, the user can effectively guide AI to generate expected results, so that it can better meet personalized customization needs. As for AI image modification, it refers to the process of modifying or adjusting existing images using AI technology. Through deep learning and computer vision technology, the system can understand and process user-specified modification requirements, such as style upgrades, color changes, style modifications, pattern designs, material improvements, etc. This technology allows users to mark specific areas on the image and describe the modification requirements, thereby automatically generating modified images that meet user needs.

[0048] The specific implementation scheme provided in the embodiments of the present application is described in detail below.

[0049] Embodiment 1

[0050] First, the first embodiment of the present application provides a method for providing product information, which is applied to a client of a product information service system, see Figure 2 , the method may specifically include:

[0051] S201: In the target interface of the commodity information service system client, an operation option for performing artificial intelligence AI design based on the commodity image of the target commodity is provided.

[0052] Users can browse product information in the client of the product information service system, where the target interface can include pages such as the product details page. In this target interface, operation options for invoking the AI ​​design assistant can be provided, that is, the above-mentioned operation options for AI design based on the main image content in the product image of the target product (in order to facilitate the distinction from the modified main image content, the main image content before modification is referred to as the first main image content, and the modified main image content is referred to as the second main image content). Among them, since the same product may usually be associated with multiple product images, in order to facilitate implementation, the above-mentioned operation options can be provided at the specific product image granularity, so that users can initiate requests based on a specific product image, and accordingly, AI design can be performed based on the specific product image later. For example, in a specific implementation method, the product details page usually includes a main image container, in which multiple product main images can be displayed through carousels and the like. Therefore, if Figure 3-1 As shown at 31 in the figure, the above operation options can be provided in the main image container area. If the main image container receives an operation request initiated by the user when it is switched to a certain product image (as shown at 32), it can be considered that the product image is the image required by the user as the design basis. In specific implementation, in order to facilitate the subsequent completion of the design, a white background image containing the front image of the target product can usually be used as the design basis image.

[0053] S202: After receiving an operation request from the user through the operation option, obtaining design requirement information input by the user for product design based on the first main image content of the product image.

[0054] After receiving the user's operation request through the specific operation options, the user can enter specific design requirement information. Specifically, the user can enter his design requirements in a variety of ways, for example, he can express his creative requirements by entering a text description, etc. Or, in another way, in order to make the specific creative requirements more specific and make the main image content in the generated image more in line with the user's needs, multiple specific design requirement category options can also be provided to the user, for example, Figure 3-1As shown at 33 in the figure, it may include "adding a product mark (e.g., a logo, etc.)", "changing local detail attributes", "adding text to describe a new picture", etc.

[0055] If the user chooses "Add product logo", he can upload a pre-designed logo image. If there is no pre-designed logo image, he can also enter his own ideas about the logo. During this process, the AI ​​big model can also guide users to gradually improve their ideas or creativity through dialogue and other methods. For example, the AI ​​big model can ask the user what style he likes, whether to use text or pattern as the logo, etc. After that, the AI ​​big model can help the user complete the logo design. If the user is satisfied, the AI ​​big model can also merge the specific logo image with the product image of the current product to synthesize it into a new target image.

[0056] If the user selects "Change local detail attributes", the user can enter the specific changes that need to be made to the part of the current product image in the form of text description, for example, "Change the lower half to metal material", etc. Alternatively, in order to facilitate the user to specify the specific part to be changed, an image editing tool can also be provided, through which the user can circle the area of ​​the product image of the current product, and then describe the specific changes that need to be made in the form of text.

[0057] If the user selects "Add text to describe a new image", they can enter text to describe specific design ideas or thoughts. For example, if the product currently being browsed is a water cup, the user can enter text such as Figure 3-1 As shown in 34, "Please add a compass to the body of the water cup to create a creative cup for outdoor camping", etc.

[0058] S203: Acquire a target image according to the design requirement information, wherein the target image is generated in the following manner: generate prompt information for communicating with the AI ​​big model, and call the AI ​​big model according to the product image and the prompt information, so that the AI ​​big model processes the first main image content in the product image according to the prompt information to generate a target image, wherein the target image includes a second main image content obtained by modifying the first main image content, so as to visually express the user's design requirements through the modified second main image content.

[0059] After the user inputs the design requirement information, the main program (the main program can run on the server side, the client can submit the design requirement information to the server, and the server executes the specific target image generation logic. Of course, in some cases, the main program can also be executed on the client side to complete the target image generation logic) can generate prompt information for communicating with the AI ​​big model according to the design requirement information, that is, prompt, and then the AI ​​big model can be called according to the product image and the prompt information, so that the AI ​​big model processes the first main image content in the product image according to the prompt information to generate a target image. The target image can include the second main image content obtained by modifying the first main image content, so as to visually express the user's design requirements through the modified second main image content. That is, the user's original abstract creative ideas are more intuitively presented through the modified second main image content in the target image, so that the user's needs can be more accurately known before the user initiates a formal product search. For example, still using Figure 3-1 Take the example shown in the figure. When browsing a water cup, the user initiated an AI design request and entered his own creative requirements: "Please add a compass to the cup to create a creative outdoor camping cup." The target image generated by the AI ​​large model can be as follows: Figure 3-1 As shown in 35.

[0060] Of course, in the specific implementation process, the user can also interact with the AI ​​big model multiple times at any time, including making local modifications to the second subject image content in the target image generated by the AI ​​big model, etc., until the user is satisfied. For example, suppose the AI ​​big model generates two target images, such as Figure 3-2 As shown in , but the user still needs to modify the material of a certain part of the cup body, he can continue to enter "I want to modify the material". At this time, since the user may need to modify the material of a certain area, the user can also be guided to use image editing tools, such as Figure 3-2 As shown at 36 in FIG. 1 , when the user chooses to use the tool, the currently generated target image can be displayed in the editing interface, and the user can perform operations such as circling a part of the area, and then express what kind of modification operation is performed on the area in the form of text. For example, Figure 3-3 As shown in the figure, it shows the interface of the editing tool. The user circles a part of the target image and enters the specific modification operation to be performed on the area in the input box on the right, for example, "change the material of this part to silicone and the color to brown". After clicking the "Regenerate" button, the AI ​​model can modify the target image as follows: Figure 3-4 shown.

[0061] S204: Return the target image to the user, so that the user can obtain information about the corresponding product based on the second main image content in the target image.

[0062] After a specific target image is generated, it can be returned to the user for display, so that the user can obtain relevant product information based on the second main image content in the target image. Specifically, a product search request based on the target image initiated by the user can be received, and product search results matching the target image can be returned. In other words, after the user selects a specific product image and enters his or her own design requirement information, the AI ​​large model can modify the first main image content in the product image and generate a target image containing the second main image content, thereby converting the user's abstract ideas into visual intuitive images, and the user can initiate a product search based on this image. Since the target image is generated based on the product image of a specific product, the probability of searching for actual products based on the target image is guaranteed.

[0063] Of course, in actual applications, there may be situations where no product matching the target image can be found. In this case, since there may be factory-type merchants in the system, which usually provide product customization services, information about factory-type merchants with product customization capabilities can also be provided based on the category to which the target product belongs. In this way, users can inquire with factory-type merchants, and if they are satisfied, they can directly reach a cooperation agreement, etc.

[0064] In summary, through the embodiments of the present application, in the process of displaying the information of the target product to the buyer user, an operation option for artificial intelligence AI design based on the product image of the target product can be provided. After receiving the user's operation request through the operation option, the design requirement information for product design based on the first main image content of the product image input by the user can be obtained; then, prompt information for dialogue with the AI ​​big model can be generated according to the design requirement information, and the AI ​​big model can be called according to the product image and the prompt information, so that the AI ​​big model processes the first main image content in the product image according to the prompt information to generate a target image, and the target image includes the second main image content obtained by modifying the first main image content, so as to visually express the design requirement through the modified second main image content. Finally, the generated target image can be returned to the user so that the user can obtain the information of the corresponding product based on the second main image content in the target image. In this way, further design based on the first main image content in the specific product image can be provided within the product information service system to generate a target image, so that the user's abstract creativity and ideas in product design can be converted into intuitive visual images, which is convenient for users to express their needs more accurately; and, since the second main image content of the specific target product is generated based on the first main image content in the product image of a real product, the second main image content in the generated target image can be an image that is more realistic and closer to the product image of the real product, so as to facilitate finding the real existing product supply in the product information service system.

[0065] Embodiment 2

[0066] The second embodiment corresponds to the first embodiment and provides a method for providing product information. The method is applied to the service end of the product information service system. Figure 4 , the method may include:

[0067] S401: receiving design requirement information submitted by a client, wherein the design requirement information includes: design requirement information for product design based on a first main image content in a product image of a target product input by a user;

[0068] S402: Generate prompt information for communicating with the AI ​​big model;

[0069] S403: calling the AI ​​big model according to the product image and the prompt information, so that the AI ​​big model processes the first main image content in the product image according to the prompt information to generate a target image, wherein the target image includes the second main image content obtained by modifying the first main image content, so as to visually express the user's design requirements through the modified second main image content;

[0070] S404: Return the target image to the client, so that the user can obtain information about the corresponding product based on the second main image content in the target image.

[0071] For the parts not described in detail in the second embodiment, please refer to the description of the first embodiment and other parts of this specification, which will not be repeated here.

[0072] 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.).

[0073] Corresponding to the first embodiment, the embodiment of the present application further provides a device for providing product information, the device being applied to a client of a product information service system, comprising:

[0074] An operation option providing unit, configured to provide, in a target interface of the commodity information service system client, an operation option for performing artificial intelligence AI design based on a commodity image of a target commodity;

[0075] A design requirement information receiving unit, configured to obtain, after receiving an operation request from a user through the operation option, design requirement information for commodity design based on the first main image content of the commodity image input by the user;

[0076] A target image acquisition unit is used to acquire a target image according to design requirement information, wherein the target image is generated in the following manner: prompt information for communicating with the AI ​​big model is generated, and the AI ​​big model is called according to the product image and the prompt information, so that the AI ​​big model processes the first main image content in the product image according to the prompt information to generate a target image, wherein the target image includes a second main image content obtained by modifying the first main image content, so as to visually express the user's design requirements through the modified second main image content;

[0077] The target image providing unit is used to return the target image to the user so that the user can obtain the information of the corresponding commodity based on the second main image content in the target image.

[0078] Among them, the target interface includes a product information display page of the target product, and the users include merchant-type buyer users in the product information service system. The merchant-type buyer users include: buyer users who purchase or customize products in bulk through the product information service system for resale or production purposes.

[0079] Specifically, the design requirement information receiving unit can be used to:

[0080] Obtain design requirement information expressed by the user through text description content input.

[0081] Alternatively, the design requirement information receiving unit may be specifically used for:

[0082] An editing interface for circling the product image is provided, so that the user can circle a local area from the product image and express the design requirement information for the local area by entering text description content.

[0083] In addition, the device may also include:

[0084] A modification requirement receiving unit is used to receive the user's further input requirement information for modifying the second main image content in the target image after returning the target image to the user, so as to regenerate the prompt information and allow the AI ​​large model to modify the second main image content in the target image.

[0085] Furthermore, the device may further include:

[0086] The search request receiving unit is configured to receive a commodity search request based on the target image initiated by a user, and return a commodity search result matching the second main image content in the target image.

[0087] The factory information providing unit is used to provide factory-type merchant information with product customization capability according to the category to which the target product belongs if there is no product matching the second main image content in the target image in the product information service system.

[0088] Among them, the AI ​​big model is obtained after fine-tuning and training using data in the commodity information service system in advance, so that the generated second main image content has the attributes that can produce corresponding products.

[0089] Corresponding to the second embodiment, the embodiment of the present application further provides a device for providing product information, which is applied to the server of the product information service system, including:

[0090] A design requirement information receiving unit, configured to receive design requirement information submitted by a client, wherein the design requirement information includes: design requirement information for product design based on the first main image content in the product image of the target product input by the user;

[0091] A prompt information generating unit, used to generate prompt information for communicating with the AI ​​big model;

[0092] a target image generating unit, configured to call the AI ​​big model according to the product image and the prompt information, so that the AI ​​big model processes the first main image content in the product image according to the prompt information to generate a target image, wherein the target image includes a second main image content obtained by modifying the first main image content, so as to visually express the user's design requirements through the modified second main image content;

[0093] The target image returning unit is used to return the target image to the client so that the user can obtain the information of the corresponding commodity based on the second main image content in the target image.

[0094] 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.

[0095] And an electronic device, comprising:

[0096] one or more processors; and

[0097] 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.

[0098] 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.

[0099] in, Figure 5 The architecture of an electronic device is exemplarily shown. For example, device 500 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.

[0100] Reference Figure 5 , device 500 may include one or more of the following components: a processing component 502 , a memory 504 , a power component 506 , a multimedia component 508 , an audio component 510 , an input / output (I / O) interface 512 , a sensor component 514 , and a communication component 516 .

[0101] The processing component 502 generally controls the overall operation of the device 500, such as operations associated with display, phone calls, data communications, camera operations, and recording operations. The processing component 502 may include one or more processors 520 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 502 may include one or more modules to facilitate the interaction between the processing component 502 and other components. For example, the processing component 502 may include a multimedia module to facilitate the interaction between the multimedia component 508 and the processing component 502.

[0102] The memory 504 is configured to store various types of data to support operations on the device 500. Examples of such data include instructions for any application or method operating on the device 500, contact data, phone book data, messages, pictures, videos, etc. The memory 504 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.

[0103] Power supply component 506 provides power to various components of device 500. Power supply component 506 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to device 500.

[0104] The multimedia component 508 includes a screen that provides an output interface between the device 500 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 508 includes a front camera and / or a rear camera. When the device 500 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.

[0105] The audio component 510 is configured to output and / or input audio signals. For example, the audio component 510 includes a microphone (MIC), and when the device 500 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 504 or sent via the communication component 516. In some embodiments, the audio component 510 also includes a speaker for outputting audio signals.

[0106] I / O interface 512 provides an interface between processing component 502 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.

[0107] The sensor assembly 514 includes one or more sensors for providing various aspects of status assessment for the device 500. For example, the sensor assembly 514 can detect the open / closed state of the device 500, the relative positioning of components, such as the display and keypad of the device 500, and the sensor assembly 514 can also detect the position change of the device 500 or a component of the device 500, the presence or absence of user contact with the device 500, the orientation or acceleration / deceleration of the device 500, and the temperature change of the device 500. The sensor assembly 514 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 514 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 514 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0108] The communication component 516 is configured to facilitate wired or wireless communication between the device 500 and other devices. The device 500 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 516 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 516 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.

[0109] In an exemplary embodiment, the device 500 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.

[0110] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 504 including instructions, and the above instructions can be executed by a processor 520 of the device 500 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.

[0111] 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.

[0112] 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 creative work.

[0113] The above is a detailed introduction to the method and electronic device for providing commodity information provided by the present application. The principles and implementation methods of the present application are described in detail using specific examples. The description of the above embodiments is only used to help understand the method and core idea of ​​the present application. At the same time, for those skilled in the art, according to the idea of ​​the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the present application.

Claims

1. A method for providing product information, characterized in that: The method is applied to a client of a commodity information service system, and includes: In the target interface of the commodity information service system client, an operation option for performing artificial intelligence AI design based on the commodity image of the target commodity is provided; After receiving the user's operation request through the operation option, obtaining the design requirement information input by the user for product design based on the first main image content of the product image; A target image is acquired according to the design requirement information, and the target image is generated in the following manner: prompt information for communicating with the AI ​​big model is generated, and the AI ​​big model is called according to the product image and the prompt information, so that the AI ​​big model processes the first main image content in the product image according to the prompt information to generate a target image, wherein the target image includes a second main image content obtained by modifying the first main image content, so as to visually express the user's design requirements through the modified second main image content; The target image is returned to the user so that the user can obtain information about the corresponding product based on the second main image content in the target image.

2. The method according to claim 1, characterized in that The target interface includes a product information display page of the target product, and the users include merchant-type buyer users in the product information service system. The merchant-type buyer users include: buyer users who purchase or customize products in bulk through the product information service system for resale or production purposes.

3. The method according to claim 1, characterized in that The obtaining of design requirement information input by a user for product design based on the first main image content of the product image includes: Obtain design requirement information expressed by the user through text description content input.

4. The method according to claim 1, characterized in that: The obtaining of design requirement information input by a user for product design based on the first main image content of the product image includes: An editing interface for circling the first main image content of the product image is provided, so that the user can circle a local area from the first main image content of the product image and express the design requirement information for the local area by entering text description content.

5. The method according to claim 1, characterized in that: Also includes: After returning the target image to the user, further user input of the requirement information for modifying the second main image content in the target image is received so as to regenerate the prompt information, and the AI ​​big model modifies the second main image content in the target image.

6. The method according to claim 1, characterized in that Also includes: A product search request based on the target image is received from a user, and product search results matching the second main image content in the target image are returned.

7. The method according to claim 1, characterized in that Also includes: If there is no product matching the second main image content in the target image in the product information service system, factory-type merchant information with product customization capability is provided according to the category to which the target product belongs.

8. The method according to any one of claims 1 to 7, characterized in that: The AI ​​big model is obtained after fine-tuning and training using data in the commodity information service system in advance, so that the generated second main image content has the attributes that can produce the corresponding product.

9. A method for providing product information, characterized in that: The method is applied to the service end of the commodity information service system, and includes: Receiving design requirement information submitted by a client, wherein the design requirement information includes: design requirement information for product design based on a first main image content in a product image of a target product input by a user; Generate prompts for conversations with the AI ​​model; Calling the AI ​​big model according to the product image and the prompt information, so that the AI ​​big model processes the first main image content in the product image according to the prompt information to generate a target image, wherein the target image includes the second main image content obtained by modifying the first main image content, so as to visually express the user's design requirements through the modified second main image content; The target image is returned to the client so that the user can obtain information about the corresponding product based on the second main image content in the target image.

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.

Images