CN114491213A - Commodity searching method and device based on image, electronic equipment and computer readable storage medium - Google Patents

Abstract

The application discloses a commodity searching method and device based on images, electronic equipment and a computer readable storage medium. The method comprises the following steps: receiving a request of a user for browsing an image, wherein the request comprises a user identifier of the user; according to the user identification, at least one candidate image related to the user identification is obtained from a candidate image library; presenting the candidate image to a user; performing a commodity search according to a reference image selected by a user from the displayed candidate images to obtain at least one candidate commodity; and outputting the candidate commodity to the user. According to the embodiment of the application, the plurality of images related to the user identification are displayed to the user based on the user identification, and the plurality of related commodities are presented to the user based on the reference image selected by the user, so that the user can select a favorite image to search commodities in the process of browsing beauty pictures, and a brand-new image-based shopping guide scheme is provided for the user.

Description

Image-based commodity search method and apparatus, electronic device, and computer-readable storage medium

technical field

The present application relates to the technical field of data processing, and in particular, to an image-based commodity search method and apparatus, an electronic device, and a computer-readable storage medium.

Background technique

With the improvement of people's living standards, online shopping has become the main means of consumption in people's daily life. When consuming on the online platform, users can not only find the product they want by searching the product name or store name, but also find the corresponding product of the same or similar style by uploading their own photos or pictures from other sources. . This kind of image search method is also called "image search", which has become a new type of search solution that crosses the language barrier because it does not require users to enter text to describe the product they want to perform the search. Especially in the context of today's trade globalization, when users in different countries and languages use text to search for goods on a globalized e-commerce platform, the non-English text they input actually needs to be uniformly translated into English before performing the search. As a result, in many cases, the final search result cannot correspond to the actual search demand of the user. In other words, the user's original retrieval request may have a certain possibility of distortion. In this context, the map search solution enables users to "buy when they see it", and can better adapt to the shopping needs of users in different regions, cultures and languages on the same trading platform.

The image search solution in the prior art is only used as a supplementary means for users to search for commodities by text, or is only used to provide users with a tool-based means for searching commodities by means of images. For example, in the prior art, a user usually directly performs a search on an e-commerce platform by taking a photo when he sees a favorite product on the road. Therefore, the image search solution in the prior art is only used as a tool for users to perform commodity search, and cannot cultivate users to form a new mind about the image search method, and e-commerce platforms cannot use image search, an image-based search method, to form a new mind. New shopping guide mode. Therefore, there is a need for a new image search solution that can upgrade the value of image search to users from a pure tool attribute to a shopping guide method that simultaneously satisfies deterministic needs and discovery of new needs.

SUMMARY OF THE INVENTION

Embodiments of the present application provide an image-based commodity search method and device, an electronic device, and a computer-readable storage medium, so as to solve the defect in the prior art that the tool solution in which the user only has a purpose to search for a specific image cannot cultivate user stickiness .

In order to achieve the above purpose, an embodiment of the present application provides an image-based commodity search method, including:

receiving a request from a user to browse images, wherein the request includes a user identification of the user;

According to the user identification, obtain at least one candidate image related to the user identification in the candidate image library;

presenting the candidate image to the user;

perform a commodity search according to the reference image selected by the user from the displayed candidate images to obtain at least one candidate commodity;

The candidate items are output to the user.

The embodiment of the present application also provides an image-based commodity search device, including:

a receiving module, configured to receive a request from a user to browse images, wherein the request includes a user ID of the user;

an acquisition module, configured to acquire at least one candidate image related to the user identification in the candidate image library according to the user identification;

a presentation module, configured to present the candidate image to the user;

a search module for performing a commodity search according to a reference image selected by the user from the displayed candidate images to obtain at least one candidate commodity, and

The display module is further configured to output the candidate commodity to the user.

The embodiment of the present application also provides an electronic device, including:

memory for storing programs;

The processor is configured to run the program stored in the memory, and when the program runs, the image-based commodity search method provided by the embodiment of the present application is executed.

Embodiments of the present application further provide a computer-readable storage medium on which a computer program executable by a processor is stored, wherein, when the program is executed by the processor, the image-based commodity search provided by the embodiments of the present application is implemented method.

The image-based commodity search method and apparatus, electronic device, and computer-readable storage medium provided by the embodiments of the present application display a plurality of images related to the user's identification to the user based on the user's identification and search for a reference image based on the user's selected reference image. Multiple related products are presented to users, so that users can select favorite images to search for products while browsing Meitu, and provide users with a brand-new image-based shopping guide solution.

The above description is only an overview of the technical solution of the present application. In order to be able to understand the technical means of the present application more clearly, it can be implemented according to the content of the description, and in order to make the above-mentioned and other purposes, features and advantages of the present application more obvious and easy to understand , and the specific embodiments of the present application are listed below.

Description of drawings

Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are for purposes of illustrating preferred embodiments only and are not to be considered limiting of the application. Also, the same components are denoted by the same reference numerals throughout the drawings. In the attached image:

1a-1d are schematic diagrams of application scenarios of the image-based commodity search solution provided by the embodiments of the present application;

2 is a flowchart of an embodiment of an image-based commodity search method provided by the present application;

3 is a flowchart of another embodiment of the image-based commodity search method provided by the present application;

FIG. 4 is a flowchart of an embodiment of an image-based commodity search device provided by the present application;

FIG. 5 is a schematic structural diagram of an embodiment of an electronic device provided by the present application.

Detailed ways

Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided so that the present disclosure will be more thoroughly understood, and will fully convey the scope of the present disclosure to those skilled in the art.

Example 1

The solutions provided by the embodiments of the present application can be applied to any system with an online shopping function, such as a server including a chip with image processing and network communication functions and related components, and so on. FIG. 1 is a schematic diagram of an application scenario of an image-based commodity search solution provided by an embodiment of the present application. The scenarios shown in FIGS. 1 a to 1 d are only one example of applicable technical solutions of the present application.

Online shopping has become the main means of consumption in people's daily life. When the user clearly knows the name or keyword of the product they want, they can search by entering text to find the product they want. However, users may see their favorite products on the road or on the Internet without knowing the name of the product, or not sure what keywords should be used to search for the product, so the e-commerce platform also allows users to upload photos or other sources by uploading their own photos. to find the corresponding product of the same or similar style. Such an image search method is also called "image search", which has become a new type of search solution that crosses the language barrier because it does not require users to enter text to describe the product they want to perform the search.

Especially in the context of today's trade globalization, when users in different countries and languages use text to search for goods on a globalized e-commerce platform, the non-English text they input actually needs to be uniformly translated into English before performing the search. In this way, the final search result cannot correspond to the actual search demand of the user in many cases, in other words, the original search demand of the user may be distorted to a certain extent. In the context of such globalized trade, the above-mentioned map search solution can better adapt to the shopping needs of users in different regions, cultures and languages on the same trading platform because users can "see it and buy it".

In the prior art, the image search solution on the e-commerce platform is usually only used as a supplementary means for users to search for products by text, or is only used to provide users with a tool-based means to search for products by image. For example, in the prior art, users are usually unable to determine how to describe the desired product with keywords, for example, when they just see someone wearing their favorite clothes on the road, or when they see someone using their favorite product on a TV program , in these cases, users often don't have a clear idea of the make or model of the item they want. For example, the user sees a person passing by on the road wearing a jacket that looks good, but if a text description is entered, the user can only get a very broad description such as a red jacket, when in fact the user sees the pattern of the clothes and Style cannot be described in words. Therefore, in this case, the e-commerce platform can allow users to directly take pictures of the clothes they see or the passers-by or models wearing the clothes and upload the photographed pictures to the e-commerce platform, and the e-commerce platform can use the image search solution to target The image searches for the corresponding product. However, when the user does not have the desire to buy the product, or does not see the favorite product on the road or in the media, he will not want to perform the search.

Therefore, the image search solution in the prior art is only used as an auxiliary tool for the user to perform a commodity search. In fact, it is a tool only used when the user already roughly knows the commodity he wants, but cannot determine a suitable commodity description keyword. . Therefore, such image search technology cannot be used to cultivate users' new minds about image search methods. For example, it is impossible for users to use the image search tool to search for products to cultivate the habit of users to frequently use the tool to search for products. E-commerce platforms are also unable to form a new shopping guide model through image search, an image-based search method. For example, users don't think of using image search tools when they don't have a clear idea of what products they want, but browsing Meitu is an important means of entertainment in current users' lives. Therefore, there is a need for a new image search solution that can upgrade the value of image search to users from a pure tool attribute to a shopping guide method that simultaneously satisfies deterministic needs and new demand discovery.

1a to 1d are schematic diagrams of application scenarios of the image-based commodity search solution provided by the embodiments of the present application. As shown in FIG. 1a, a user can browse the homepage of a shopping website using a mobile terminal. The home page may be provided with a search bar at the top of the page, and the user may enter the name of the product to be searched for or a keyword describing the product in the search bar. As an auxiliary tool for the text search bar, in the prior art, an image search button, such as a camera icon, can be set on one side of the search bar, so that the user can use the image by clicking the button when the search text cannot be determined. search function. After the user clicks the image search button, the user can enter the image search interface shown in Fig. 1b, which is usually displayed as a photo-taking interface. Take photos of the desired products and upload the photos to the server to perform the image search function. Alternatively, the user can also click an additional button in the interface shown in Figure 1b to select an existing picture or a picture that has been taken before. For example, the user can include pictures of the products he is interested in when browsing other websites Save it to upload to the server of the e-commerce platform by clicking the extra button in the interface shown in Figure 1b. After receiving the picture uploaded by the user, the server can search the commodity database according to the picture, and can send the search result, that is, the searched picture, to the user's terminal, so that it can be displayed on the user's terminal as shown in Figure 1d The search results interface shown. In the interface shown in FIG. 1d , the search result of the commodity corresponding to the image uploaded by the user can be displayed. Therefore, users can make purchases by browsing the search results of these products. Therefore, in the prior art, through the above image search solution, it is possible to provide a user with a search service for a desired product without inputting text.

However, as mentioned above, in the above scheme, the user will click the image search button next to the search bar to perform the function of searching for products by image only when the search text, such as a keyword, cannot be determined, and in other cases , for example, when the product keyword is known, the search text will be directly entered in the search bar to obtain the product search result. Or when you just want to browse products casually, you can view the various products recommended by the e-commerce platform through other columns on the homepage. Therefore, such an image search solution in the prior art is only used as a tool for users to perform commodity search, and cannot cultivate users to form new shopping browsing habits for image search methods, and e-commerce platforms cannot use image search, an image-based search, way to form a new shopping guide model.

Therefore, the embodiments of the present application provide a new image search solution, which can upgrade the value of image search to users from a pure tool attribute to a shopping method that simultaneously satisfies deterministic needs and discovery of new needs. For example, as shown in FIG. 1a, compared with the prior art, the image search solution provided by the embodiment of the present application can still use the existing image search entry, that is, the image search button next to the search bar to enter the image search solution of the embodiment of the present application. Image search function. After the user clicks or presses the image search button shown in FIG. 1a, the main interface of the image search function shown in FIG. 1b, for example, can be displayed to the user, which is different from that in the prior art, where the user is only prompted to generate images by taking pictures. The difference between uploading a photo containing the desired product or uploading an existing image containing the product desired by the user is that the image search solution provided by this embodiment of the present application can further prompt the user to enter the meitu browsing interface on the interface. For example, as shown in FIG. 1b on the interface, a prompt message that the swipe-up operation can enter the Meitu browsing interface can be additionally displayed on the interface. Of course, in the embodiment of the present application, the manner of prompting the user to enter the Meitu browsing interface is not limited to this. For example, a Meitu browse button may be displayed in the photo-taking interface as shown in FIG. 1b to prompt the user to press or click the button to enter Meitu browsing, or it may be displayed in the shopping homepage as shown in FIG. 1a A separate Meitu browsing button, or displaying Meitu in a dynamic manner on the homepage, so that users can click Meitu to browse Meitu. In addition, in the embodiment of the present application, the network address of the Meitu browsing interface can also be shared, so that the user can click on the link of the network address on other websites, emails or social networking tools to enter Meitu browsing.

In this embodiment of the present application, for example, a request for browsing an image sent by a user through a swipe-up operation on an image search interface such as shown in FIG. 1b may be received first. In particular, in this embodiment of the present application, the user ID of the user may be included in the request, so that after the user swipes up, the user may be provided with an image associated with the user ID of the user as the user browses according to the user ID included in the request. candidate image. Therefore, images that may be of interest to the user can be provided to the user by including the user identification of the user in a request sent by the user to browse images. For example, the user can be identified as a young woman through the user identification, and images related to fashion apparel can be obtained from the candidate image database to be provided to the user for browsing as candidate images. After that, the user can view the candidate images on the image browsing interface shown in Fig. 1c, and when he sees the product that he is interested in, for example, the image that contains the fashionable skirt is selected as shown in the dotted box in Fig. 1c, The image of the fashionable dress can be used as a reference image to perform a product search, so that a product search result such as shown in Figure 1d can be obtained, that is, the user is shown a plurality of images of candidate products related to the products contained in the reference image. . Therefore, when a user uses the product search method provided by the embodiment of the present application, he actually searches for a product only when he finds an image containing the product he likes in the process of browsing various pictures. In the prior art, the user only performs a picture search process when he wants to find a product. On the contrary, the user is based on the original intention of browsing images, and when entering the picture search interface of the embodiment of the present application, the user is not sure what to search for. What product, or even the need to search for the product, just to browse the various images recommended for it, and can find the product you like in the process of browsing the various images similar to the treasure hunt process, that is, contains your own An image of the desired item. For example, as shown in FIG. 1c, when the user is a young woman, after the user sends a request to browse images through a swipe-up operation in the image search interface of FIG. 1b, the user can be provided with fashionable clothes suitable for young women. various images. Therefore, when the user finds an image of a model wearing a pink dress in the process of browsing these images and likes the wearing effect of the dress, he can directly use the liked image as a reference image to perform a product search. In this way, the user will gradually become accustomed to or like to browse various images through the image search solution of the embodiment of the present application, find images containing the products they like, and use the images to search and purchase products.

Therefore, the image-based product search solution provided by the embodiment of the present application displays a plurality of images related to the user's ID to the user based on the user's ID and presents a plurality of related products to the user based on the reference image selected by the user, In this way, users can select their favorite images to search for products in the process of browsing Meitu, and provide users with a brand-new image-based shopping guide solution.

The foregoing embodiments are descriptions of the technical principles and exemplary application frameworks of the embodiments of the present application, and the specific technical solutions of the embodiments of the present application will be further described in detail below through multiple embodiments.

Embodiment 2

FIG. 2 is a flowchart of an embodiment of an image-based commodity search method provided by this application. The execution body of the method can be various terminal or server devices with display and input capabilities, or can be integrated on these devices. device or chip. As shown in Figure 2, the image-based product search method may include the following steps:

S201, a request for browsing images from a user is received.

In step S201, a user's request to browse images may be received in the existing image search interface shown in FIG. 1b, for example, in the image search interface shown in FIG. 1b, a prompt is displayed to prompt the user to swipe up to display more images information, so that the user can, based on the prompt information, perform a swipe-up operation to submit a request for browsing images to the server when he wants to browse more images. In addition, a separate image browsing icon may also be displayed on the homepage of an existing shopping website or application, so that the user can input a request for browsing images in step S201 by clicking on the icon. In particular, in this embodiment of the present application, when a user inputs a request to browse images through operations such as swiping up or clicking, the user ID of the user may be included in the request, so that the system can know the user who initiated the image browsing request.

S202, according to the user identification, obtain at least one candidate image related to the user identification in the candidate image library.

After receiving the user's request for browsing images in step S201, at least one candidate image related to the user identifier may be acquired from the preset candidate image library in step S202 according to the user identifier included in the request. In the embodiment of the present application, the candidate image library may be model images and/or product images prepared by various merchants on the e-commerce platform in advance for various commodities provided by themselves, or may also be provided by a cooperative third party Various images related to the item. The user ID can be the login account used by the user to shop on the e-commerce platform or the user ID allocated by the system to the user, or it can be any other ID that can identify the user, so that the system can in step S202 according to the user submitted The user request contained in the request is used to provide the user with images relevant to the user, which can avoid providing the user with images that the user is not interested in at all, and can be further used to provide the user with images that are of interest to the user as much as possible, thereby enhancing the The stickiness of users using the image search solution of this application.

S203, showing the candidate image to the user.

S204: Execute a commodity search according to the reference image selected by the user from the displayed candidate images to obtain at least one candidate commodity.

In step S203, the images associated with the user obtained in step S202, such as images that the user may be interested in, may be sent to the user, so as to be displayed on the user's terminal in step S203, and the user may display in the browsing step S203 In the process of selecting these images, for example, by clicking on the image containing the product you like, and in step S204, you can perform a product search according to the product selected by the user, so as to obtain at least one candidate product, which may be the user Candidates for the desired item.

S205, output candidate product images to the user.

Therefore, in step S205, at least one candidate commodity obtained by the search in step S204 may be displayed on the user's terminal. In the embodiment of the present application, the correlation between the searched commodity candidates and the reference image selected by the user may be further obtained when the commodity search is performed in step S204, and the obtained candidate commodities are sorted according to the correlation in step S205, to display to the user. Thus, the user can purchase the product based on the displayed product.

Therefore, the image-based commodity search method provided by the embodiment of the present application displays a plurality of images related to the user's identification to the user based on the user's identification and presents a plurality of related commodities to the user based on the reference image selected by the user, In this way, users can select their favorite images to search for products in the process of browsing Meitu, and provide users with a brand-new image-based shopping guide solution.

Embodiment 3

FIG. 3 is a flowchart of another embodiment of an image-based commodity search method provided by the present application. As shown in FIG. 3 , the image-based commodity search method may include the following steps:

S301, acquiring the marketing image uploaded by the store to construct a candidate image library.

In this embodiment of the present application, the marketing map uploaded by the store that provides the shopping service may be acquired in step S301 in advance, and the marketing map may include the target commodities provided by the merchant, so that candidates may be constructed by using the acquired marketing maps. Image library, in order to provide users with various images from the candidate image library for users to browse according to different users

S302, obtain a commodity image from a third party to construct a candidate image library.

In addition to constructing a candidate image library according to commodity images provided by existing merchants on the e-commerce platform in step S301, the method provided by this embodiment of the present application can also acquire commodity images from a third party in step S302. It can be, for example, an image platform or a commodity evaluation or display platform, etc., so that it can have various images containing commodities. Therefore, in this embodiment of the present application, in step S302, images containing commodities can be obtained from these third parties. Commodity images to build a candidate image library, so as to provide users with various images according to the user's request.

In addition, since the third-party product image obtained in step S302 is not an image for shopping, a grouping label with a matching relationship with the product can be further set for the third-party product image, so as to provide users with candidates When using an image, the corresponding image can be selected according to the grouping label.

S303, a link is set on the page of the third-party application, which is used by the user to click to input a request for browsing images.

In step S303, the user may click a specially set link on the page of the third-party application other than the e-commerce platform that provides the image search solution of the embodiment of the present application, and the link may be provided by the e-commerce platform to the third party The developer of the application may also actively set a link to the website that provides the image search solution of the embodiment of the present application in its page, so that the user can click the link to input a request for browsing images when using the application. . And when the user inputs a request for browsing images by clicking on the link, the user ID of the user can be included in the request, so that the system can know the user who initiated the image browsing request.

S304 , setting an input control on the lens page used for image search, for the user to swipe up the page to input a request for browsing images.

In addition to the link set by the user in step S303 by clicking on the page of the third-party application, an input control can also be set in the lens interface shown in FIG. 1b in step S304 to prompt the user to slide up to display more images, Therefore, based on the prompt information, the user can submit a request for browsing images to the server by performing a swipe-up operation through the input control when he wants to browse more images. In this embodiment of the present application, when a user inputs a request for browsing images through a swipe-up operation, the user ID of the user may be included in the request, so that the system can know the user who initiated the image browsing request.

S305, according to the user identification, obtain at least one candidate image related to the user identification in the candidate image library.

After receiving the user's request for browsing images in step S303 or S304, in step S305, at least one user identifier related to the user identifier may be obtained from, for example, the candidate image library constructed in steps S301 and/or S302 according to the user identifier included in the request. candidate image.

The user ID can be the login account used by the user to shop on the e-commerce platform or the user ID assigned by the system to the user, or it can be any other ID that can identify the user, so that the system can in step S305 according to the user submitted The user request contained in the request is used to provide the user with images relevant to the user, which can avoid providing the user with images that the user is not interested in at all, and can be further used to provide the user with images that are of interest to the user as much as possible, thereby enhancing the The stickiness of users using the image search solution of this application.

S306, showing the candidate image to the user.

S307: Execute a commodity search according to the reference image selected by the user from the displayed candidate images to obtain at least one candidate commodity.

In step S306, the images associated with the user obtained in step S305, such as images that the user may be interested in, may be sent to the user, so as to be displayed on the user's terminal in step S307, and the user may display in the browsing step S306 In the process of selecting these images, for example, by clicking on the image containing the product you like, and in step S307, you can perform a product search according to the product selected by the user, so as to obtain at least one candidate product, which may be the user Candidates for the desired item.

S308, output the candidate product image to the user.

Therefore, in step S308, at least one candidate commodity obtained by the search in step S307 may be displayed on the user's terminal. In the embodiment of the present application, the correlation between the searched commodity candidates and the reference image selected by the user may be further obtained when the commodity search is performed in step S307, and the obtained candidate commodities are sorted according to the correlation in step S308, to display to the user. Thus, the user can purchase the product based on the displayed product.

Therefore, the image-based commodity search method provided by the embodiment of the present application displays a plurality of images related to the user's identification to the user based on the user's identification and presents a plurality of related commodities to the user based on the reference image selected by the user, In this way, users can select their favorite images to search for products in the process of browsing Meitu, and provide users with a brand-new image-based shopping guide solution.

Embodiment 4

FIG. 4 is a schematic structural diagram of an embodiment of an image-based product search apparatus provided by the present application, which can be used to execute the image-based product search method shown in FIG. 2 and FIG. 3 . As shown in FIG. 4 , the apparatus may include: a receiving module 41 , an acquiring module 42 , a displaying module 43 and a searching module 44 .

The receiving module 41 may be configured to receive a user's request for browsing images.

For example, in the existing image search interface shown in FIG. 1b, the receiving module 41 can receive the user's request for browsing images. For example, in the image search interface shown in FIG. 1b, the user can be prompted to swipe up to display more images. information, so that the user can, based on the prompt information, perform a swipe-up operation to submit a request for browsing images to the server when he wants to browse more images. In addition, it is also possible to display a separate image browsing icon on the homepage of an existing shopping website or application so that the user can input a request for browsing images by clicking on the icon. In particular, in this embodiment of the present application, when a user inputs a request to browse images through operations such as swiping up or clicking, the user ID of the user may be included in the request, so that the system can know the user who initiated the image browsing request.

In addition, in the embodiment of the present application, the product search apparatus may further include a building module 45, and the building module 45 may be used to obtain the marketing map uploaded by the store and the product map from a third party, so as to construct a candidate image library.

In this embodiment of the present application, a marketing map uploaded by a store providing shopping services may be acquired in advance through the building module 45, and the marketing map may include target commodities provided by the merchant, so that candidates may be constructed by using the acquired marketing maps An image library, so as to provide users with various images from the candidate image library for users to browse according to different users. In addition to constructing a candidate image library based on commodity images provided by existing merchants on the e-commerce platform, the building module 45 can also acquire commodity images from a third party, which may be, for example, an image platform or a commodity evaluation or display platform and so on, so that it can have various images containing commodities. Therefore, in this embodiment of the present application, the building module 45 can obtain commodity images containing commodities from these third parties to construct a candidate image library, so as to facilitate the user The request provides the user with various images.

In addition, since the third-party product image obtained by the building module 45 is not an image for shopping, the building module 45 can further set a grouping label with a matching relationship with the product for the product image from the third party, so as to facilitate the user When a candidate image is provided, the corresponding image can be selected according to the grouping label.

In addition, the commodity search apparatus according to the present application may further include a processing module 46, which may be used to set a link on a page of a third-party application for clicking by a user to input a request to browse images.

The user can click a specially set link on the page of the third-party application except the e-commerce platform that provides the image search solution of the embodiment of the present application, and the link can be provided by the e-commerce platform to the developer of the third-party application, The developer may also actively set a link to the website providing the image search solution of the embodiment of the present application in its page, so that the user can click the link to input a request for browsing images when using the application. And when the user inputs a request for browsing images by clicking on the link, the user ID of the user can be included in the request, so that the system can know the user who initiated the image browsing request.

In addition, the processing module 46 may also be configured to set an input control on the lens page for image search, for the user to slide up the page to input a request to browse images.

In addition to setting links in the pages of the third-party applications, the processing module 46 can also set input controls in the lens interface shown in FIG. 1b to prompt the user to slide up to display more images, so that the user can make decisions based on the prompt information. Through the input control, when you want to browse more images, you can perform a sliding operation to submit a request for browsing images to the server. In this embodiment of the present application, when a user inputs a request for browsing images through a swipe-up operation, the user ID of the user may be included in the request, so that the system can know the user who initiated the image browsing request.

The obtaining module 42 may be configured to obtain at least one candidate image related to the user identification from the candidate image library according to the user identification.

After receiving the user's request for browsing images, the obtaining module 42 may obtain at least one candidate image related to the user identification from the candidate image library constructed by the building module 45 according to the user identification included in the request.

The user ID can be the login account used by the user for shopping on the e-commerce platform or the user ID assigned by the system to the user, or it can be any other ID that can identify the user, so that the system can identify the user according to the information contained in the request submitted by the user. User requests to provide users with images related to users, which can avoid providing users with images that users are not interested in at all, and can be further used to provide users with images that are of interest to users as much as possible, thereby enhancing the use of this application by users The stickiness of the graph search scheme.

The presentation module 43 may be used to present candidate images to the user.

The search module 44 may be configured to perform a commodity search according to the reference image selected by the user from the displayed candidate images to obtain at least one candidate commodity.

The display module 43 can display the images associated with the user obtained by the acquisition module 42, such as images that the user may be interested in, to the user, so as to be displayed on the user's terminal, for example, and the user can browse these images displayed by the display module 43. In the process, the image containing the product you like is selected by, for example, clicking, and the search module 44 can perform a product search according to the product selected by the user, so as to obtain at least one candidate product, which may be the one the user wants. The candidate item for the item.

In addition, the presentation module 43 can also be used to output candidate commodity images to the user.

Therefore, the display module 43 can display on the user's terminal at least one candidate commodity obtained by the search module 44 . In the embodiment of the present application, when the search module 44 performs a commodity search, the correlation between the searched commodity candidates and the reference image selected by the user may be further obtained, and the display module 43 sorts the candidate commodities obtained by the search according to the correlation, to display to the user. Thus, the user can purchase the product based on the displayed product.

Therefore, the image-based commodity search device provided by the embodiment of the present application displays a plurality of images related to the user's identification to the user based on the user's identification and presents a plurality of related commodities to the user based on the reference image selected by the user, In this way, users can select their favorite images to search for products in the process of browsing Meitu, and provide users with a brand-new image-based shopping guide solution.

Embodiment 5

The above describes the internal function and structure of the commodity search device, which can be implemented as an electronic device. FIG. 5 is a schematic structural diagram of an embodiment of an electronic device provided by the present application. As shown in FIG. 5 , the electronic device includes a memory 51 and a processor 52 .

The memory 51 is used to store programs. In addition to the above-described programs, the memory 51 may also be configured to store various other data to support operations on the electronic device. Examples of such data include instructions for any application or method operating on the electronic device, contact data, phonebook data, messages, pictures, videos, etc.

Memory 51 may be implemented by any type of volatile or non-volatile storage device or 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 or Optical Disk.

The processor 52 is not limited to a processor (CPU), but may also be a graphics processing unit (GPU), a field programmable gate array (FPGA), an embedded neural network processor (NPU), or an artificial intelligence (AI) chip, etc. processing chip. The processor 52, coupled with the memory 51, executes the program stored in the memory 51, so as to execute the image-based commodity search method in any one of the second to fourth embodiments above.

Further, as shown in FIG. 5 , the electronic device may further include: a communication component 53 , a power supply component 54 , an audio component 55 , a display 56 and other components. Only some components are schematically shown in FIG. 5 , which does not mean that the electronic device only includes the components shown in FIG. 5 .

The communication component 53 is configured to facilitate wired or wireless communication between the electronic device and other devices. Electronic devices can access wireless networks based on communication standards, such as WiFi, 3G, 4G or 5G, or a combination thereof. In one exemplary embodiment, the communication component 53 receives broadcast signals or broadcast related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 53 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module may be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

The power supply assembly 54 provides power to various components of the electronic device. Power supply components 54 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to electronic devices.

Audio component 55 is configured to output and/or input audio signals. For example, audio component 55 includes a microphone (MIC) that is configured to receive external audio signals when the electronic device is in operating modes, such as calling mode, recording mode, and voice recognition mode. The received audio signal may be further stored in the memory 51 or transmitted via the communication component 53 . In some embodiments, audio assembly 55 also includes a speaker for outputting audio signals.

Display 56 includes a screen, which 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 a user. The touch panel includes one or more touch sensors to sense touch, swipe, and gestures on the touch panel. The touch sensor may not only sense the boundaries of a touch or swipe action, but also detect the duration and pressure associated with the touch or swipe action.

Those of ordinary skill in the art can understand that all or part of the steps of implementing the above method embodiments may be completed by program instructions related to hardware. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the steps including the above method embodiments are executed; and the foregoing storage medium includes: ROM, RAM, magnetic disk or optical disk and other media that can store program codes.

Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, but not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: The technical solutions described in the foregoing embodiments can still be modified, or some or all of the technical features thereof can be equivalently replaced; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the technical solutions of the embodiments of the present invention. scope.

Claims (10)

1. An image-based commodity search method, comprising: receiving a request from a user to browse images, wherein the request includes a user identification of the user; According to the user identification, obtain at least one candidate image related to the user identification in the candidate image library; presenting the candidate image to the user; perform a commodity search according to the reference image selected by the user from the displayed candidate images to obtain at least one candidate commodity; The candidate items are output to the user. 2. The image-based commodity search method according to claim 1, wherein the method further comprises: An input control is provided on the lens page for image search for the user to swipe up the page to input the request to browse images. 3. The image-based commodity search method according to claim 1, wherein the method further comprises: A link is set on the page of the third-party application for clicking by the user to enter a request to browse the image. 4. The image-based commodity search method according to claim 1, wherein the method further comprises: The marketing image uploaded by the store is obtained to construct the candidate image library. 5. The image-based commodity search method according to claim 1, wherein the method further comprises: Obtain product images from third parties to build the candidate image library. 6. The image-based commodity search method according to claim 5, wherein the commodity map from a third party is provided with a grouping label having a matching relationship with the commodity. 7. An image-based commodity search device, comprising: a receiving module, configured to receive a request from a user to browse images, wherein the request includes a user ID of the user; an acquisition module, configured to acquire at least one candidate image related to the user identification in the candidate image library according to the user identification; a presentation module, configured to present the candidate image to the user; a search module for performing a commodity search according to a reference image selected by the user from the displayed candidate images to obtain at least one candidate commodity, and The display module is further configured to output the candidate commodity to the user. 8. The image-based commodity search device of claim 7, wherein the device further comprises: The processing module is configured to set an input control on the lens page of the image search, for the user to swipe up the page to input the request for browsing the image. 9. An electronic device comprising: memory for storing programs; The processor is configured to run the program stored in the memory, and when the program runs, the image-based commodity search method according to any one of claims 1-6 is executed. 10. A computer-readable storage medium having stored thereon a computer program executable by a processor, wherein the program, when executed by the processor, implements an image-based commodity according to any one of claims 1-6 search method.

Images