Content display method, apparatus, device, storage medium, program product

Abstract

The present application provides a content display method, device, equipment, storage medium and program product, which can better meet the needs of users by using an intelligent system. The method comprises the following steps: displaying first information on a first page; a user and an intelligent system have a conversation through the first page; the first information is used to indicate an inquiry about a first product; displaying first multimedia content on the first page; the first multimedia content is output by the intelligent system; the first multimedia content is used to indicate a combination effect of a first image and the first product; the first image is used to present a first visual feature matched with the first product by the user; and the first visual feature is matched with the first information.

Description

Technical Field

[0001] This article relates to the field of computer technology, and in particular to a content display method, apparatus, device, storage medium, and program product. Background Technology

[0002] In related technologies, users can converse with intelligent systems such as AI (Artificial Intelligence) systems to meet their needs through dialogue. With the diversification of user needs, how to better utilize intelligent systems to satisfy those needs is one of the issues that needs to be considered. Summary of the Invention

[0003] In one scenario, a content display method, apparatus, device, storage medium, or program product is provided that can better meet user needs using an intelligent system.

[0004] In a first aspect, a content display method is provided, comprising: displaying first information on a first page; a user and an intelligent system engaging in dialogue through the first page; the first information being used to indicate an inquiry about a first product; displaying first multimedia content on the first page; the first multimedia content being output by the intelligent system; the first multimedia content being used to indicate the combined effect of a first image and the first product; the first image being used to present a first visual feature matching the user and the first product; and the first visual feature matching the first information.

[0005] In a second aspect, a content display device is provided, comprising: a first display unit for displaying first information on a first page; a user and an intelligent system engaging in dialogue through the first page; the first information indicating an inquiry about a first product; a second display unit for displaying first multimedia content on the first page; the first multimedia content being output by the intelligent system; the first multimedia content indicating a combination effect of a first image and the first product; the first image presenting a first visual feature matching the user and the first product; and the first visual feature matching the first information.

[0006] Thirdly, an electronic device is provided, comprising: a processor; and a memory for storing computer-executable instructions for causing the processor to perform the method described in the first aspect.

[0007] Fourthly, a computer-readable storage medium is provided for storing computer-executable instructions, wherein a processor executes the computer-executable instructions to implement the method described in the first aspect.

[0008] Fifthly, a computer program product is provided, the computer program product comprising a computer program, wherein a processor executes the computer program to implement the method described in the first aspect above.

[0009] In one scenario, a user interacts with an intelligent system through a first page. The first page displays initial information, indicating an inquiry about a first product. It also displays multimedia content, output by the intelligent system. This multimedia content represents the combined effect of a first image and the first product. The first image presents a first visual characteristic matching the user and the first product, and this first visual characteristic matches the initial information. Therefore, when a user inquires about the first product, the intelligent system can output the multimedia content. This multimedia content demonstrates the combined effect of the first image and the first product, and the first image presents the user's first visual characteristic matching the first product and the initial information. Through this multimedia content, the user can quickly understand the application effect of the first product and determine whether it meets their needs, thus achieving the goal of better fulfilling user needs using the intelligent system. Attached Figure Description

[0010] To more clearly illustrate the technical solution, the accompanying drawings used in the description will be briefly introduced below. Obviously, the accompanying drawings in the following description only record some implementation situations. For those skilled in the art, other drawings can be obtained from these drawings without creative effort. Figure 1 This is a schematic diagram illustrating an application scenario for a content display method provided under certain conditions. Figure 2 This is a flowchart illustrating a content display method provided in one scenario. Figure 3a A schematic diagram illustrating the first information and first multimedia content provided in a given scenario; Figure 3b A schematic diagram of the first information and first multimedia content provided in another scenario; Figure 4a This is a schematic diagram illustrating the display of first multimedia content in one scenario. Figure 4b This is a schematic diagram illustrating the display of the first multimedia content in another scenario; Figure 4c This is a schematic diagram illustrating the display of the first multimedia content in yet another scenario; Figure 5 This is a diagram illustrating the purchase information of the first product provided in one scenario. Figure 6A schematic diagram of the structure of a content display device provided in one scenario; Figure 7 This is a schematic diagram of the structure of an electronic device provided in one scenario. Detailed Implementation

[0011] To enable those skilled in the art to better understand the technical solutions in one or more of the scenarios described below, the technical solutions in one or more of the scenarios described below will be clearly and completely described below in conjunction with one or more accompanying drawings. Obviously, the scenarios described are only some of the scenarios, not all of them. Based on one or more of the scenarios described below, all other implementations obtained by those skilled in the art without inventive effort should fall within the protection scope of this document.

[0012] It is understood that before using any of the technical solutions described below, relevant parties should be informed of the type, scope of use, and usage scenarios of the information involved and their authorization obtained in an appropriate manner in accordance with relevant laws and regulations.

[0013] For example, upon receiving a user's proactive request, a prompt message can be sent to the user to explicitly inform them that the requested operation will require the acquisition and use of the user's personal information. This allows the user to independently choose whether to provide personal information to the software or hardware such as electronic devices, applications, servers, or storage media that perform the technical operation, based on the prompt message.

[0014] As an optional but non-limiting implementation, in response to a user's active request, sending a prompt message to the user can be done via a pop-up window, where the prompt message can be presented in text format. Furthermore, the pop-up window can also include a selection control allowing the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0015] It is understood that the above notification and user authorization process is merely illustrative and does not limit the implementation of the various scenarios described below. Other methods that comply with relevant laws and regulations may also be applied to the implementation of the various scenarios described below.

[0016] In one scenario, a content display method, apparatus, device, storage medium, or program product is provided, capable of better meeting user needs using an intelligent system. This method can be implemented on and executed by a terminal device, which includes, but is not limited to, laptops, tablets, desktop computers, set-top boxes, mobile devices (e.g., mobile phones, portable music players, personal digital assistants, dedicated messaging devices, portable gaming devices), smartphones, smart speakers, smartwatches, smart TVs, in-vehicle terminals, and various other types of terminal devices.

[0017] In this paper, an intelligent system refers to a system capable of autonomous control based on machine learning models. An intelligent system is, for example, a virtual object or physical entity that can make decisions and autonomously execute actions based on machine learning models to achieve preset goals or complete preset tasks. An intelligent system can be an automated program that understands user intent and can utilize models or invoke tools to complete various types of tasks. In some cases, examples of intelligent systems may include, but are not limited to: agents, bots, chatbots, digital avatars, intelligent customer service, digital assistants, etc. Alternatively, an intelligent system can also be an intelligent role implemented based on machine learning models. Intelligent systems can process user requests based on generative models (e.g., language models, multimodal models) to perform specified types of tasks. In some cases, intelligent systems may also be associated with virtual accounts, which may have corresponding avatars or nicknames. In some cases, intelligent systems can be deployed on the terminal side or on the backend server side.

[0018] Figure 1 This is a schematic diagram illustrating an application scenario of a content display method provided in one particular situation, such as... Figure 1 As shown, the scenario includes terminal device 101. Figure 1 In this system, terminal device 101 can be any user's terminal device. Terminal device 101 displays an interactive page 1001. Users can interact with the intelligent system through the interactive page, sending various forms of dialogue messages such as text, voice, images, and video. The intelligent system processes the dialogue messages sent by the user and displays the results on the interactive page 1001. The processed results can be various forms of dialogue messages such as text, voice, images, and video. The intelligent system fulfills user needs through dialogue, for example, fulfilling various needs such as image generation, image editing, and video generation. Figure 1 The following example illustrates how a user requests a book recommendation from an intelligent system.

[0019] Figure 2 This is a flowchart illustrating a content display method provided in one scenario, which can be executed by a terminal device, such as... Figure 2 As shown, the method includes: Step S202: First information is displayed on the first page; the user and the intelligent system engage in dialogue through the first page; the first information is used to indicate an inquiry about the first product; Step S204: Display first multimedia content on the first page; the first multimedia content is output by the intelligent system; the first multimedia content is used to represent the combined effect of the first image and the first product; the first image is used to present the first visual feature that matches the user and the first product; the first visual feature is matched with the first information.

[0020] In one scenario, a user interacts with an intelligent system through a first page. The first page displays initial information, indicating an inquiry about a first product. It also displays multimedia content, output by the intelligent system. This multimedia content represents the combined effect of a first image and the first product. The first image presents a first visual characteristic matching the user and the first product, and this first visual characteristic matches the initial information. Therefore, when a user inquires about the first product, the intelligent system can output the multimedia content. This multimedia content demonstrates the combined effect of the first image and the first product, and the first image presents the user's first visual characteristic matching the first product and the initial information. Through this multimedia content, the user can quickly understand the application effect of the first product and determine whether it meets their needs, thus achieving the goal of better meeting user needs using the intelligent system.

[0021] In step S202 above, the terminal device displays a first page, which includes the interactive page of the intelligent system, for example... Figure 1 The interactive page within the system. Users interact with the intelligent system through this first page. The first page displays initial information, which can be sent by the user to the intelligent system. This initial information can be a conversational message in various forms, such as text, voice, image, or video.

[0022] The first information is used to indicate a query for a first product. Specifically, the first information can represent a user querying the intelligent system for a first product. In some cases, the first product can be a product the user already owns, or a product recommended to the user by the intelligent system. In one example, the first information could be "Please recommend a hat; I usually wear a medium-sized hat." In this first information, the first product includes a hat, and it is a product recommended to the user by the intelligent system; the first information is used to request the intelligent system to recommend a hat to the user. In another example, the first information could be "Help me see if this dress suits me." This first information also includes an image or video of the dress; in this first information, the first product includes the dress, and it is a product the user already owns; the first information is used to query the intelligent system whether the dress matches the user's preferences.

[0023] In some cases, product information, including details about the primary product, can also be displayed on the first page. This product information may include, but is not limited to, one or more of the following: product name, product link, product image, and product video. By displaying this information on the first page, users can gain a more detailed understanding of the product. Furthermore, by combining this product information with multimedia content, users can more accurately determine whether the product meets their needs.

[0024] In one scenario, the product information for the first product is input by the user. For example, the user's first message might include, "Help me see if this dress suits me," and this message might also include an image or video of the dress. In this case, the user's need for an existing intelligent system that queries the first product can be met. The intelligent system provides a combination of the first product and its image, allowing the user to intuitively understand whether the first product suits them.

[0025] In another scenario, the product information for the first product is output by the intelligent system. For example, if a user sends a message such as, "Please recommend a hat; I usually wear a medium-sized hat," the intelligent system, in addition to outputting the first multimedia content, can also recommend the first product and output its product information, such as, "I recommend the XX brand XX hat, which would be perfect for you." The product information includes the product name, which is "XX brand XX hat" in this example. In this case, the first multimedia content represents the combined effect of the first image and the first product, "XX brand XX hat." This allows the intelligent system to recommend the first product and output its product information, helping the user understand the product in more detail and fulfilling their need to obtain the desired product through the intelligent system.

[0026] In step S204 above, the terminal device displays first multimedia content on the first page. The first multimedia content is output by the intelligent system. Specifically, the first multimedia content can be generated by the intelligent system. The first multimedia content includes at least one of images and videos. The first multimedia content is used to represent the combined effect of a first image and a first product; the first image is used to present a first visual feature matching the user and the first product; and the first visual feature matches first information.

[0027] The user possesses a first visual characteristic, which is presented through a first image. The user can pre-authorize the intelligent system to access this first visual characteristic. Based on the first image and the first product, the intelligent system generates first multimedia content, enabling the user to quickly understand the application effects of the first product and determine whether the first product meets their needs.

[0028] The first visual feature is matched with the first product, and the first visual feature is matched with the first piece of information. For example, if the first information includes: "Please recommend a hat for me; I usually wear a medium-sized hat," then the first information is used to inquire about a medium-sized hat. Since a hat is worn on the head, the first visual feature must at least include the user's head size (medium size). As another example, if the first information includes: "Can you help me see if this dress suits me?" then the first information is used to inquire about the degree of match between the dress and the user. Since a dress is a type of clothing, and whether clothing matches the user is related to the user's body shape and silhouette, the first visual feature must at least include the user's body shape and silhouette.

[0029] The user's primary visual characteristics are presented through a first image. In some cases, the aforementioned first image is obtained through an intelligent system, and the first image includes an image of a virtual object, which is obtained through the intelligent system.

[0030] Specifically, the user can pre-authorize the intelligent system to obtain the first visual feature. For example, the intelligent system displays a pop-up window to the user asking: "Do you allow me to authorize the acquisition of your visual features?" After the user confirms (by triggering a confirmation component), the intelligent system obtains the user's first visual feature and creates a virtual object based on it. The first image is then derived from the virtual object, and this first image includes the image of the virtual object. In a concrete example, the intelligent system can create the virtual object based on the user's first visual feature using a large model or intelligent agent.

[0031] In this scenario, the intelligent system can create virtual objects with the user's authorization and use the image of the virtual object as the first image to represent the user's first visual characteristics, thus preparing for the generation of the first multimedia content.

[0032] In one scenario, the virtual object includes a virtual representation corresponding to the user. This virtual representation can reflect the user's secondary visual characteristics; for example, it could include a full-body virtual avatar of the user. In this case, the user also needs to authorize the intelligent system with their secondary visual characteristics, which include the primary visual characteristics. After receiving the authorized secondary visual characteristics, the intelligent system can create a virtual object based on the user's secondary visual characteristics using a large model or intelligent agent. This virtual object includes the user's corresponding virtual representation. In this scenario, the virtual object includes the user's corresponding virtual representation, achieving the effect of reflecting more visual characteristics of the user beyond their primary visual characteristics.

[0033] In another scenario, the virtual object includes a virtual representation of a first visual feature. The intelligent system can create a virtual object based on the user's first visual feature using a large model or agent. This virtual object includes a virtual representation of the first visual feature. The virtual representation corresponds to the first visual feature. The user can pre-authorize the intelligent system to access this first visual feature; for example, the intelligent system displays a pop-up window asking the user if they wish to authorize access to their visual feature. After the user confirms (e.g., triggering a confirmation component), the intelligent system acquires the user's first visual feature and creates a virtual object based on it, including the virtual representation of the first visual feature.

[0034] In one example, if the first visual feature includes the user's head size, then the virtual representation includes a virtual head whose size matches the user's head size. This virtual representation may not reflect other features.

[0035] In this case, the virtual object generated by the intelligent system is used to represent a virtual representation of the first visual feature, without needing to represent information unrelated to the first visual feature, thereby improving the efficiency of creating virtual objects and ensuring that the first multimedia image can be accurately generated.

[0036] In the above process, users can describe the first and second visual features to the intelligent system through text, voice, or other means to achieve the effect of authorization.

[0037] The user's primary visual characteristics are presented through a first image. In some cases, the first image may also be displayed, and this first image may be input by the user. In this case, the user can input the first image into the intelligent system; the first image may be a real or virtual image of the user, and it may represent the user's primary visual characteristics, such as head size. Alternatively, the user may manually input the first image into the intelligent system to represent their primary visual characteristics. The first image may be displayed on the first page.

[0038] Figure 3a This is a schematic diagram of the first information and the first multimedia content provided in a certain situation, such as... Figure 3a As shown, in this scenario, a user can send a first message to the intelligent system, such as "Does this outfit suit me?". Before or after the user sends this first message, the intelligent system creates a virtual representation to indicate the first visual feature, such as... Figure 3a The cartoon upper-body image in the system uses the user's upper body outline as its primary visual feature. Before or after sending the initial information, the user also sends an image of their clothing to the intelligent system (the diagram illustrates sending the clothing image before sending the initial information as an example). This initial information is used to request a determination of the match between the user and the clothing. In this scenario, the intelligent system can use this initial information to determine, for example... Figure 3a The system combines cartoon characters with images of clothing to generate a "fitting" image. This image is then output to the user as the primary multimedia content, allowing them to quickly determine if the clothing suits them.

[0039] Figure 3b A schematic diagram of the first information and first multimedia content provided in another scenario, such as Figure 3b As shown, in this scenario, the user can send a first message to the intelligent system, such as "recommend a hat for me." Before the user sends the first message, the intelligent system creates a virtual representation to represent the first visual feature authorized by the user, such as "medium-sized head." Figure 3b The cartoon avatar in the image has primary visual features including the user's head size. This primary information is used to request suitable hat recommendations for the user. In this scenario, the intelligent system can use this primary information to recommend hats such as… Figure 3bThe system combines a cartoon avatar with an image of the recommended hat to generate a "hat try-on" image. This image is then output to the user as the primary multimedia content, recommending hats and allowing the user to quickly determine the hat's appearance using the image.

[0040] In some cases, there are multiple first multimedia content items and multiple first products, and the first multimedia content items respectively present a combined effect of the first products; displaying the first multimedia content items on the first page includes: The first multimedia content is displayed on the first page in the first layout; the first layout is used to show the differences in the effects of various combinations on the first page.

[0041] In this scenario, the user can specify multiple first products, or the intelligent system can recommend multiple first products to the user. To display each first product separately, the intelligent system also generates a first multimedia content (such as an image) for each product. Each first multimedia content showcases the combined effect of a first product and a first image, and the first image in each multimedia content is identical. Then, the various multimedia contents are displayed on the first page according to a first layout, which can include various methods such as a four-grid, nine-grid, horizontal, and vertical layout. The first layout is used to display the differences in the effects of different combinations on the first page, allowing users to quickly browse the differences in the effects of different first products based on the same first image, thus helping users compare the effects of different first products. Of course, the first images in each multimedia content can also be completely different or partially the same and partially different.

[0042] In one scenario, the first product in each piece of multimedia content corresponds to different attributes of the same item. For example, based on the user's first visual characteristic, "shape and silhouette," three dresses are recommended, each corresponding to a different color of the same dress.

[0043] In another scenario, the first product in each piece of multimedia content is a different item. For example, based on the user's primary visual characteristic, "head size," four hats are recommended, each a different item. This allows for comparison of multiple products.

[0044] Figure 4a This is a schematic diagram illustrating the display of first multimedia content in one scenario, such as... Figure 4a As shown, in this scenario, the continuation Figure 3bFor example, the intelligent system recommends four different hats to the user. These four hats correspond to four products, and four images are displayed for each product. Each image is a piece of multimedia content. The four pieces of multimedia content are displayed in a four-square grid, which makes it easy for the user to understand the effects of different products and to compare the effects.

[0045] Based on the above, all multimedia content can be displayed on the first page in the first layout, making it easy for users to quickly understand the differences in the effects of each product through the first layout.

[0046] In some cases, there are multiple first multimedia content items, and each first multimedia content item is displayed and combined from different perspectives; the first multimedia content is displayed on the first page, including: The first multimedia content is displayed on the first page according to the second layout; the second layout is related to the perspective of each piece of first multimedia content.

[0047] In this scenario, the user can specify a first product, or the intelligent system can recommend a first product to the user. To fully showcase the first product, the intelligent system also generates multiple first multimedia content pieces, such as images, for the first product. Each first multimedia content piece displays the combined effect of the first product and the first image from different perspectives. Then, the first multimedia content pieces are displayed on the first page according to a second layout, which includes the display order of each first multimedia content piece. The display order of each first multimedia content piece in the second layout is related to the perspective corresponding to each first multimedia content piece. In one example, the preset perspective display order is: front, back, left, right. Based on the perspective corresponding to each first multimedia content piece and this preset perspective display order, the display order of each first multimedia content piece in the second layout is determined. For example, if the perspective corresponding to the first multimedia content piece includes front, back, and right, then the display order of each first multimedia content piece in the second layout is: first multimedia content from the front perspective, first multimedia content from the back perspective, and first multimedia content from the right perspective.

[0048] Figure 4b This is an illustration of displaying the first multimedia content in another scenario, such as... Figure 4b As shown, in this scenario, the continuation Figure 3b For example, the intelligent system recommends a hat to the user and displays three images in the order of perspective: front, back, and right, so that the user can understand the wearing effect of the hat from different perspectives.

[0049] In this way, the first multimedia content is displayed on the first page in a second layout. The second layout is related to the perspective of each piece of first multimedia content, which also makes it easier for users to understand the combined effect of the first product from different perspectives, thus improving the user's product acquisition experience.

[0050] In some cases, there are multiple first products, each corresponding to multiple product categories, and the first multimedia content displays one first product corresponding to each product category; the above method also includes: In response to a trigger on the first multimedia content, different first products are switched to be displayed for at least one type of product within the first multimedia content.

[0051] For example, the first message might include: "Recommend my spring outing outfits." The intelligent system recommends two outfits, thus the first products include two tops and two pairs of pants, and the product categories include tops and bottoms. When displaying the first multimedia content, it shows one first product corresponding to each product category, such as displaying one top and one pair of pants. In this example, the first image includes an image of the user's virtual representation (the user's full-body virtual image). If the user triggers the first multimedia content, in response to the trigger, different first products can be displayed for at least one product category within the first multimedia content. For example, different tops can be displayed, or different pairs of pants can be displayed, or both tops and pants can be displayed simultaneously.

[0052] Figure 4c This is an illustration of displaying the first multimedia content in yet another scenario, such as... Figure 4c As shown, continuing from the previous example, if the user triggers... Figure 4c The left and right arrows corresponding to the tops in the image allow users to switch between trying on different tops. If the user triggers... Figure 4c The left and right arrows corresponding to the top in the image allow users to switch between trying on different bottoms. If the user triggers... Figure 4c The left and right arrows corresponding to the outfits in the game allow you to switch between different tops and bottoms simultaneously.

[0053] As can be seen from the above scenarios, when the first product is divided into multiple categories, the first multimedia content can also display one first product corresponding to each category, and users can switch between displaying different first products for at least one category of products in the first multimedia content, enriching the ways users can browse the combination effect of the first product and the first image.

[0054] In some cases, the first information includes scene information, and the first multimedia content includes the scene corresponding to the scene information. The first multimedia content may include a foreground portion and a background portion. The foreground portion is used to represent the combined effect of the first product and the first image, and the background portion is used to represent the scene corresponding to the scene information. For example, if the first information includes "Recommend suitable outfits for a spring outing in the park," then the foreground portion of the first multimedia content displays the combined effect of different outfits with the first image, the first image includes an image of the user's corresponding virtual representation (the user's full-body virtual avatar), and the background portion of the first multimedia content displays the park scene. In this scenario, the first multimedia content can also be generated based on the scene provided by the user, allowing the user to browse the combined effect of the first product and the first image within the provided scene.

[0055] In some cases, the first multimedia content is generated in the following manner: Input the product information, first image, and first information of the first product into the intelligent system; The intelligent system generates first multimedia content based on the product information, first image, and first information of the first product.

[0056] Specifically, the product information, first image, and first information of a first product are input into the intelligent system. The product information of the first product includes one or more of the following: product name, product link, product image, and product video. The intelligent system can generate first multimedia content based on the product information, first image, and first information of the first product, using a large model or intelligent agent. For example, when the first information includes scene information, the intelligent system generates an image of the first product using a raw image model, combines the image of the first product with the first image to obtain an initial image or video, and modifies the background content of the initial image or video according to the scene required in the first information to obtain the first multimedia content. Alternatively, when the first information does not include scene information, the intelligent system generates an image of the first product using a raw image model, combines the image of the first product with the first image to obtain an initial image or video, and modifies the content of the initial image or video according to the query about the first product in the first information to obtain the first multimedia content, ensuring that the first multimedia content matches the first information. For example, if the user's first information concerns whether the size of the dress fits them, the first multimedia content can emphasize the degree of matching between the dress size and the user.

[0057] This method eliminates the need for data preprocessing. The intelligent system can directly generate multimedia content based on the product information, image, and other information of the first product, achieving efficient generation of multimedia content.

[0058] In some cases, the first multimedia content is generated in the following manner: Obtain the second image; the second image corresponds to the first product; The second image, the first image, and the first information are input into the intelligent system; The intelligent system generates first multimedia content based on the second image, the first image, and the first information.

[0059] Specifically, a second image representing the first product is first acquired. Then, the second image, the first image, and the first information are input into the intelligent system. The intelligent system then generates first multimedia content based on the second image, the first image, and the first information. For example, if the first information includes scene information, the intelligent system uses a raw image model to combine the second image with the first image to obtain an initial image or video. Based on the scene required in the first information, the background content of the initial image or video is modified to obtain the first multimedia content. Alternatively, if the first information does not include scene information, the intelligent system uses a raw image model to combine the second image with the first image to obtain an initial image or video. Based on inquiries about the first product in the first information, the content of the initial image or video is modified to obtain the first multimedia content, ensuring that the first multimedia content matches the first information. For instance, if the user's first information concerns whether the hat color suits them, the first multimedia content can emphasize the degree of match between the hat color and the user.

[0060] In this way, the second image corresponding to the first product can be obtained in advance, and the intelligent system does not need to generate an image for the first product, thus ensuring the accuracy of the first multimedia content.

[0061] In one scenario, acquiring the second image includes: Based on the product attributes of the first product, a second image is obtained; the second image is used to present the product attributes of the first product, and the product attributes match the first information.

[0062] First, the product attributes of the first product are determined based on the first information, and these product attributes match the first information. For example, if the first information is used to request a lipstick recommendation, then the first product includes lipstick, and the product attribute matching the first information includes lipstick color. Similarly, if the first information is used to request a dress recommendation, then the first product includes dress, and the product attribute matching the first information includes dress style. Then, an image that can represent the determined product attributes of the first product is obtained as a second image. For example, images of different lipstick shades are obtained as the second image, and images of dress styles are obtained as the second image.

[0063] In this scenario, the situation is taken into account that when the product attributes of the first product include multiple attributes, some product attributes match the first information while others do not. For example, the lipstick color matches the first information but the lipstick shape does not. Therefore, the attributes of the first product that match the first information are determined, and then the image representing that attribute is obtained as the second image. This improves the accuracy of obtaining the second image and thus improves the accuracy of the generated first multimedia content.

[0064] In some cases, the first image includes the second product, or the first information includes product information of the second product; displaying first multimedia content on the first page includes: The first page displays the first multimedia content, which is used to represent the combined effect of the first image, the first product, and the second product.

[0065] The second product is a product the user already owns. It can be displayed in the first image, presented along with the first visual feature. The product information of the second product can also be included in the first information. For example, if the first image shows a full-body virtual avatar of the user holding a water cup, that water cup is the second product. Or, if the first information includes "Recommend a pair of headphones to use with my existing phone," then the "phone" is the second product. The product information of the second product includes at least one of the following: product name, link, logo, image, and video. The second product is used or displayed in conjunction with the first product.

[0066] In this case, the first multimedia content is displayed on the first page. The first multimedia content is used to represent the combined effect of the first image, the first product, and the second product, thereby representing the combined effect of the first product with the user's first visual characteristics and with the user's existing products.

[0067] Therefore, based on the above scenarios, the combination of the first product, the existing product, and the first image can be displayed in conjunction with the user's existing products, thus satisfying the user's need to query the first product based on their existing products.

[0068] When the first multimedia content is used to represent the combined effect of the first image, the first product, and the second product, in some cases, the first multimedia content is generated in the following manner: Input the product information of the first product, the product information of the second product, the first image, and the first information into the intelligent system; The intelligent system generates first multimedia content based on the product information of the first product, the product information of the second product, the first image, and the first information.

[0069] Specifically, product information of a first product, product information of a second product, a first image, and first information are input into the intelligent system. The product information of the first product includes one or more of the following: product name, product link, product image, and product video. The product information of the second product includes one or more of the following: product name, product link, product image, and product video. The intelligent system can generate first multimedia content based on the product information of the first product, the product information of the second product, the first image, and the first information, using a large model or intelligent agent. For example, when the first information includes scene information, the intelligent system generates images of the first product and the second product using a raw image model. It then combines the images of the first product and the second product with the first image to obtain an initial image or video. Based on the scene required in the first information, the background content of the initial image or video is modified to obtain the first multimedia content. For example, when the first information does not include scene information, the intelligent system generates images of the first product and the second product through a raw image model. It combines the images of the first product and the second product with the first image to obtain an initial image or video. Based on the queries about the first product in the first information, it modifies the content of the initial image or video to obtain the first multimedia content, so that the first multimedia content matches the first information. For example, if the user's first information focuses on whether the size of the dress is suitable for them and whether the dress matches the second product (an existing backpack), then the first multimedia content can emphasize the degree of matching between the dress size and the user, and highlight the degree of matching between the dress and the backpack.

[0070] This method eliminates the need for data preprocessing. The intelligent system can directly generate the first multimedia content based on the product information of the first product, the product information of the second product, the first image, and the first information, thus achieving efficient generation of the first multimedia content.

[0071] When the first multimedia content is used to represent the combined effect of the first image, the first product, and the second product, in some cases, the first multimedia content is generated in the following manner: Obtain the second image; the second image corresponds to the first product; obtain the third image; the third image corresponds to the second product; The second image, the third image, the first image, and the first information are input into the intelligent system; The intelligent system generates first multimedia content based on the second image, the third image, the first image, and the first information.

[0072] Specifically, a second image representing a first product and a third image representing a second product are first acquired. Then, the second image, third image, first image, and first information are input into an intelligent system. The intelligent system generates first multimedia content based on these elements. For example, if the first information includes scene information, the intelligent system uses a raw image model to combine the second image with the third and first images to obtain an initial image or video. Based on the scene requested in the first information, the background content of the initial image or video is modified to obtain the first multimedia content. Similarly, if the first information does not include scene information, the intelligent system uses a raw image model to combine the second image with the third and first images to obtain an initial image or video. Based on inquiries about the first product in the first information, the content of the initial image or video is modified to obtain the first multimedia content, ensuring that the first multimedia content matches the first information. For instance, if the user's first information focuses on whether the hat color suits them and whether the hat matches the second product (an existing backpack), the first multimedia content can emphasize the degree of matching between the hat color and the user, as well as the degree of matching between the hat and the backpack.

[0073] In this way, the second image corresponding to the first product and the third image corresponding to the second product can be obtained in advance. The intelligent system does not need to generate images for the first and second products, thus ensuring the accuracy of the first multimedia content.

[0074] In one scenario, acquiring the third image includes: Based on the product attributes of the second product, a third image is obtained; the third image is used to present the product attributes of the second product, and the product attributes match the first information.

[0075] First, the product attributes of the second product are determined based on the first information, and these attributes match the first information. For example, if the first information requests a lipstick recommendation, and the lipstick needs to be paired with an existing foundation, then the second product includes the foundation, and the product attribute matching the first information includes the foundation color. Similarly, if the first information requests a dress recommendation, and the dress needs to be paired with an existing backpack, then the second product includes the backpack, and the product attribute matching the first information includes the backpack style. Then, an image that represents the determined product attributes of the second product is obtained as the third image. For example, an image of the foundation color is obtained as the third image, or an image of the backpack style is obtained as the third image.

[0076] In this scenario, the situation is taken into account that when the product attributes of the second product include multiple attributes, some product attributes match the first information while others do not. For example, the color of the foundation matches the first information, but the shape of the foundation bottle does not match the first information. Therefore, the attributes of the second product that match the first information are determined, and then the image representing that attribute is obtained as the third image. This improves the accuracy of obtaining the third image and thus improves the accuracy of the generated first multimedia content.

[0077] In some cases, when the first product is recommended by the intelligent system, the purchase information for that first product can also be displayed on the first page. Figure 5 This is an illustration of purchasing information for the first product provided in a given scenario, such as... Figure 5 As shown, continuing Figure 3b For example, the intelligent system can also input purchase information for recommended hats into the user's input.

[0078] In summary, the user and the intelligent system interact through a first page, which displays initial information indicating an inquiry about a first product. The first page also displays multimedia content, output by the intelligent system. This multimedia content represents the combined effect of a first image and the first product. The first image presents the user's visual characteristics that match the first product, and these visual characteristics are matched with the initial information. Therefore, when a user inquires about the first product, the intelligent system can output the multimedia content. This multimedia content represents the combined effect of the first image and the first product. The first image presents the user's visual characteristics that match the first product and the initial information. Thus, through this multimedia content, the user can quickly understand the application effect of the first product and determine whether it meets their needs, achieving the goal of using the intelligent system to better meet the user's requirements.

[0079] Figure 6 This is a schematic diagram of the structure of a content display device provided in one scenario, such as... Figure 6 As shown, the device includes: The first display unit 62 is used to display first information on a first page; the user and the intelligent system have a dialogue through the first page; the first information is used to indicate an inquiry about a first product; The second display unit 64 is used to display first multimedia content on the first page; the first multimedia content is output by the intelligent system; the first multimedia content is used to represent the combined effect of the first image and the first product; the first image is used to present the first visual feature that matches the user and the first product; the first visual feature matches the first information.

[0080] Optionally, a third display unit is further included for displaying product information on the first page; the product information includes product information of the first product.

[0081] Optionally, the product information is input by the user.

[0082] Optionally, the product information is output by the intelligent system.

[0083] Optionally, the first image is obtained through the intelligent system; the first image includes an image of a virtual object; the virtual object is obtained through the intelligent system.

[0084] Optionally, the virtual object includes a virtual representation corresponding to the user.

[0085] Optionally, the virtual object includes a virtual representation for representing the first visual feature.

[0086] Optionally, a fourth display unit is further included, for: displaying the first image; the first image being input by the user.

[0087] Optionally, the number of the first multimedia content is multiple, the number of the first products is multiple, and the first multimedia content respectively presents the combined effect of the first products; the second display unit is specifically used to: display the first multimedia content on the first page according to a first layout; the first layout is used to display the effect differences of each combined effect on the first page.

[0088] Optionally, the first image includes the second product, or the first information includes product information of the second product; the second display unit is specifically used to: display the first multimedia content on the first page, wherein the first multimedia content is used to represent the combined effect of the first image, the first product, and the second product.

[0089] Optionally, there may be multiple first multimedia contents, and each first multimedia content displays the combined effect from a different perspective; the second display unit is specifically used to: display the first multimedia content on the first page according to a second layout; the second layout is related to the perspective corresponding to each first multimedia content.

[0090] Optionally, the number of the first products is multiple, each first product corresponds to multiple product categories, and the first multimedia content displays one first product corresponding to each product category; it also includes a switching unit, used to: in response to a trigger on the first multimedia content, switch the display of different first products in the first multimedia content for at least one product category.

[0091] Optionally, it further includes a first generation unit, configured to: input product information, the first image, and the first information into the intelligent system; the product information includes product information of the first product; and generate the first multimedia content through the intelligent system based on the product information, the first image, and the first information.

[0092] Optionally, it further includes a second generation unit, configured to: acquire a second image; the second image corresponds to the first product; input the second image, the first image, and the first information into the intelligent system; and generate the first multimedia content through the intelligent system based on the second image, the first image, and the first information.

[0093] Optionally, the second generation unit is specifically used to: obtain the second image based on the product attributes of the first product; the second image is used to present the product attributes of the first product, and the product attributes match the first information.

[0094] Optionally, the first information includes scene information, and the first multimedia content includes the scene corresponding to the scene information.

[0095] The content display devices described above can implement each process of the content display method described above and achieve the same effect and function, which will not be repeated here.

[0096] In one instance, an electronic device was also provided. Figure 7 This is a schematic diagram of the structure of an electronic device provided in one scenario, such as... Figure 7 As shown, electronic devices can vary considerably due to differences in configuration or performance. They may include one or more processors 701 and memories 702, with the memory 702 storing one or more application programs or data. The memory 702 can be temporary or persistent storage. The application programs stored in the memory 702 may include one or more modules (not shown), each module including a series of computer-executable instructions from the electronic device. Furthermore, the processor 701 may be configured to communicate with the memory 702, executing the series of computer-executable instructions stored in the memory 702 on the electronic device. The electronic device may also include one or more power supplies 703, one or more wired or wireless network interfaces 704, one or more input or output interfaces 705, one or more keyboards 706, etc.

[0097] In one specific scenario, the electronic device includes a processor; and a memory for storing computer-executable instructions for causing the processor to perform: The first page displays the first piece of information; the user interacts with the intelligent system through the first page; the first piece of information is used to indicate an inquiry about the first product; The first multimedia content is displayed on the first page; the first multimedia content is output by the intelligent system; the first multimedia content is used to represent the combined effect of the first image and the first product; the first image is used to present the first visual feature that matches the user and the first product; the first visual feature matches the first information.

[0098] The electronic devices described above can implement each process of the content display method described above and achieve the same effect and function, so they will not be repeated here.

[0099] In one embodiment, a computer-readable storage medium is also provided for storing computer-executable instructions, which, when executed by a processor, implement: The first page displays the first piece of information; the user interacts with the intelligent system through the first page; the first piece of information is used to indicate an inquiry about the first product; The first multimedia content is displayed on the first page; the first multimedia content is output by the intelligent system; the first multimedia content is used to represent the combined effect of the first image and the first product; the first image is used to present the first visual feature that matches the user and the first product; the first visual feature matches the first information.

[0100] The computer-readable storage media described above can implement each process of the content display method described above and achieve the same effect and function, so they will not be repeated here.

[0101] In one embodiment, a computer program product is also provided, the computer program product comprising a computer program, which, when executed by a processor, implements: The first page displays the first piece of information; the user interacts with the intelligent system through the first page; the first piece of information is used to indicate an inquiry about the first product; The first multimedia content is displayed on the first page; the first multimedia content is output by the intelligent system; the first multimedia content is used to represent the combined effect of the first image and the first product; the first image is used to present the first visual feature that matches the user and the first product; the first visual feature matches the first information.

[0102] The computer program products described above can implement each process of the content display method and achieve the same effect and function, so they will not be repeated here.

[0103] In all the above scenarios, the computer-readable storage medium includes read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk, etc.

[0104] In the 1990s, improvements to a technology could be clearly distinguished as either hardware improvements (e.g., improvements to the circuit structure of diodes, transistors, switches, etc.) or software improvements (improvements to the methodology). However, with technological advancements, many methodological improvements today can be considered direct improvements to the hardware circuit structure. Designers almost always obtain the corresponding hardware circuit structure by programming the improved methodology into the hardware circuit. Therefore, it cannot be said that a methodological improvement cannot be implemented using hardware physical modules. For example, a Programmable Logic Device (PLD) (such as a Field Programmable Gate Array (FPGA)) is such an integrated circuit whose logic function is determined by the user programming the device. Designers can program and "integrate" a digital system onto a PLD themselves, without needing chip manufacturers to design and manufacture dedicated integrated circuit chips. Furthermore, nowadays, instead of manually manufacturing integrated circuit chips, this programming is mostly implemented using "logic compiler" software. Similar to the software compiler used in program development, the original code before compilation must also be written in a specific programming language, called a Hardware Description Language (HDL). There are many HDLs, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, and RHDL (Ruby Hardware Description Language). Currently, the most commonly used are VHDL (Very-High-Speed ​​Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also understand that by simply performing some logic programming on the method flow using one of these hardware description languages ​​and programming it into an integrated circuit, the hardware circuit implementing the logical method flow can be easily obtained.

[0105] The controller can be implemented in any suitable manner. For example, it can take the form of a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro)processor, logic gates, switches, application-specific integrated circuits (ASICs), programmable logic controllers, and embedded microcontrollers. Examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicon Labs C8051F320. A memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art will also recognize that, in addition to implementing the controller in purely computer-readable program code form, the same functionality can be achieved by logically programming the method steps to make the controller take the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers. Therefore, such a controller can be considered a hardware component, and the means included therein for implementing various functions can also be considered as structures within the hardware component. Alternatively, the means for implementing various functions can be considered as both software modules implementing the method and structures within the hardware component.

[0106] The systems, devices, modules, or units described above can be implemented by computer chips or physical entities, or by products with certain functions. A typical implementation device is a computer. Specifically, a computer can be, for example, a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or any combination of these devices.

[0107] For ease of description, the above devices are described in terms of function, divided into various units. Of course, in implementing the above scenarios, the functions of each unit can be implemented in one or more software and / or hardware components.

[0108] Those skilled in the art will understand that one or more of the above-described embodiments can be provided as methods, systems, or computer program products. Therefore, one or more of the above-described embodiments can take the form of entirely hardware, entirely software, or a combination of software and hardware aspects. Furthermore, one or more of the above-described embodiments can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0109] The above description refers to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to the above descriptions. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0110] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0111] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0112] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0113] One or more of the above scenarios can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform a specific task or implement a specific abstract data type. One or more of the above scenarios can also be practiced in distributed computing environments, where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0114] The above scenarios are described in a progressive manner. Similar or identical parts between scenarios can be referred to interchangeably. Each scenario focuses on its differences from the others. In particular, the system description is relatively simple because it is fundamentally similar to the method description; relevant parts can be found in the method description.

[0115] The above description is only a partial description and is not intended to limit the scope of this document. Various modifications and variations can be made to this document by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this document should be included within the scope of the claims herein.

Claims

1. A content display method, comprising: The first information is displayed on the first page; Users interact with the intelligent system through the first page; The first information is used to indicate an inquiry about the first product; The first multimedia content is displayed on the first page; the first multimedia content is output by the intelligent system; the first multimedia content is used to represent the combined effect of the first image and the first product; the first image is used to present the first visual feature that matches the user and the first product; the first visual feature matches the first information.

2. The method according to claim 1, further comprising: Product information is displayed on the first page; The product information includes the product information of the first product.

3. The method according to claim 2, wherein the product information is input by the user.

4. The method according to claim 2, wherein the product information is output by the intelligent system.

5. The method according to claim 1, wherein the first image is obtained through the intelligent system; the first image includes an image of a virtual object; and the virtual object is obtained through the intelligent system.

6. The method according to claim 5, wherein the virtual object includes the virtual representation corresponding to the user.

7. The method of claim 5, wherein the virtual object includes a virtual representation for representing the first visual feature.

8. The method according to claim 1, further comprising: Display the first image; The first image was input by the user.

9. The method according to claim 1, wherein the number of the first multimedia content is multiple, the number of the first products is multiple, and the first multimedia content respectively presents the combined effect of the first products; The step of displaying the first multimedia content on the first page includes: The first multimedia content is displayed on the first page according to the first layout; The first layout is used to display the differences in the effects of each combination on the first page.

10. The method according to claim 1, wherein the first image includes a second product, or the first information includes product information of the second product; the step of displaying the first multimedia content on the first page includes: The first multimedia content is displayed on the first page, and the first multimedia content is used to represent the combined effect of the first image, the first product, and the second product.

11. The method according to claim 1, wherein the number of the first multimedia content is multiple, and each of the first multimedia content displays the combined effect from a different perspective; the step of displaying the first multimedia content on the first page includes: The first multimedia content is displayed on the first page according to the second layout; The second layout is related to the perspective corresponding to each of the first multimedia contents.

12. The method according to claim 1, wherein the quantity of the first product is multiple, each first product corresponds to multiple product categories, and the first multimedia content displays one first product corresponding to each product category; the method further includes: In response to a trigger on the first multimedia content, for at least one type of product in the first multimedia content, different first products are switched to be displayed.

13. The method according to claim 1, wherein the first multimedia content is generated in the following manner: The product information, the first image, and the first information are input into the intelligent system; the product information includes the product information of the first product. The intelligent system generates the first multimedia content based on the product information, the first image, and the first information.

14. The method according to claim 1, wherein the first multimedia content is generated in the following manner: Obtain a second image; the second image corresponds to the first product; The second image, the first image, and the first information are input into the intelligent system; The intelligent system generates the first multimedia content based on the second image, the first image, and the first information.

15. The method according to claim 14, wherein acquiring the second image comprises: The second image is obtained based on the product attributes of the first product; the second image is used to present the product attributes of the first product, and the product attributes match the first information.

16. The method according to claim 1, wherein the first information includes scene information, and the first multimedia content includes the scene corresponding to the scene information.

17. A content display device, comprising: The first display unit is used to display first information on the first page; Users interact with the intelligent system through the first page; The first information is used to indicate an inquiry about the first product; The second display unit is used to display the first multimedia content on the first page; The first multimedia content is output by the intelligent system; the first multimedia content is used to represent the combined effect of the first image and the first product; the first image is used to present the first visual feature that matches the user and the first product; the first visual feature matches the first information.

18. An electronic device comprising: processor; as well as, A memory for storing computer-executable instructions for causing the processor to implement the method described in any one of claims 1-16.

19. A computer-readable storage medium for storing computer-executable instructions, wherein a processor, when executing the computer-executable instructions, implements the method according to any one of claims 1-16.

20. A computer program product comprising a computer program, wherein a processor executes the computer program to implement the method described in any one of claims 1-16.

Images