Picture display method, device, medium and program product

The language model generates text and pictures related to the input text, and uses parallax sliding album display to solve the problem of insufficient display of multiple pictures in smart graphic and text answers, and improves the depth and user experience of information display.

CN119046438APending Publication Date: 2024-11-29BEIJING ZITIAO NETWORK TECH CO LTD
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
CN202411274948.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-11
Publication Date
2024-11-29

AI Technical Summary

Technical Problem

The existing intelligent graphic and text answers have shortcomings in the aggregation and display of multiple pictures, which limits the depth and breadth of information expression, and the user's interaction with the picture is insufficient, affecting the user experience.

Method used

Generate generated text related to the input text through the language model, and determine multiple pictures based on the generated text, and display them using the parallax sliding album, allowing users to independently control the sliding to view multiple pictures.

Benefits of technology

It has improved the breadth and depth of Q&A information display, increased users' interest in multi-level aggregation display, and enhanced users' sense of participation and experience.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119046438A_ABST
    Figure CN119046438A_ABST
Patent Text Reader

Abstract

The embodiment of the invention provides a picture display method and device, a storage medium and a computer program product. The method comprises the following steps: in response to an obtained input text of a user, determining a generated text for the input text through a language model; determining a plurality of pictures corresponding to the generated text based on the generated text; and displaying the plurality of determined pictures in a parallax sliding photo album mode. According to the method disclosed by the embodiment of the invention, firstly, the generated text related to the text input by the user is generated through the language model, and then the plurality of pictures corresponding to the generated text are determined according to the generated text, so that the user can be allowed to autonomously control and slide the plurality of pictures related to the input text; the interest of the user in the pictures displayed in a multi-level mode is attracted and stimulated, and the participation sense and the experience sense of the user are improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure generally relates to the field of computers, and more particularly to a method for displaying pictures, an electronic device, a computer-readable storage medium, and a computer program product. Background Art

[0002] With the rapid development of artificial intelligence (AI) technology, intelligent picture and text answers, as a cutting-edge information presentation method, are slowly being integrated into all aspects of people's daily lives. Intelligent picture and text answers refer to the use of artificial intelligence technology, combined with natural language processing (NLP) and computer vision (CV) technologies, to generate answers that contain both text and images. This answer method aims to provide users with a more intuitive, vivid and comprehensive information display through the organic combination of images and text. Summary of the invention

[0003] According to an exemplary embodiment of the present disclosure, a method for displaying a picture, an electronic device, a computer storage medium, and a computer program product are provided.

[0004] In a first aspect of the present disclosure, a method for displaying pictures is provided, comprising: in response to obtaining input text from a user, determining generated text for the input text through a language model; based on the generated text, determining a plurality of pictures corresponding to the generated text; and displaying the determined plurality of pictures in a parallax sliding album manner.

[0005] In a second aspect of the present disclosure, an electronic device is provided, comprising: at least one processing unit; and at least one memory, wherein the at least one memory is coupled to the at least one processing unit and stores instructions for execution by the at least one processing unit, and when the instructions are executed by the at least one processing unit, the electronic device executes the method described in the first aspect of the present disclosure.

[0006] In a third aspect of the present disclosure, a computer-readable storage medium is provided. The computer-readable storage medium has machine-executable instructions stored thereon. When the machine-executable instructions are executed by a device, the device performs the method described in the first aspect of the present disclosure.

[0007] According to a fourth aspect of the present disclosure, a computer program product is provided, comprising computer executable instructions, wherein the computer executable instructions implement the method described in the first aspect of the present disclosure when executed by a processor.

[0008] The invention summary is provided to introduce a series of concepts in a simplified form, which will be further described in the specific embodiments below. The invention summary is not intended to identify the key features or essential features of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, wherein:

[0010] Figure 1 A schematic diagram showing an example system in which embodiments of the present disclosure can be implemented;

[0011] Figure 2 A flowchart of a method for displaying a picture according to an embodiment of the present disclosure is shown;

[0012] Figure 3A-3B FIG. 4 is a schematic diagram showing an exemplary process of a user viewing multiple pictures about a certain point by sliding according to an embodiment of the present disclosure;

[0013] Figure 4A-4D A schematic diagram showing an exemplary process in which a user views multiple pictures about answers with steps by sliding according to an embodiment of the present disclosure;

[0014] Figure 5 A schematic diagram showing an exemplary process of displaying multiple pictures through a puzzle container according to an embodiment of the present disclosure;

[0015] Figure 6 A schematic diagram showing an exemplary process of determining a picture container size according to an embodiment of the present disclosure;

[0016] Figure 7 A schematic diagram showing an exemplary process of displaying pictures of different sizes in the same answer according to an embodiment of the present disclosure;

[0017] Figure 8 A schematic block diagram showing an example apparatus according to some embodiments of the present disclosure; and

[0018] Fig. 9 A block diagram of an example device that may be used to implement embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0019] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments set forth herein, which are instead provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for illustrative purposes and are not intended to limit the scope of protection of the present disclosure.

[0020] As mentioned above, intelligent picture and text answers are a new type of information presentation method with powerful information expression capabilities. However, in the current practice of presenting information by mixing pictures and text, most intelligent picture and text answers only stay at the simple mixing of a single picture, lacking the ability to aggregate and display multiple pictures to illustrate a certain point. This single picture and text mixed display method not only limits the depth and breadth of the expression of picture and text information, but also weakens the interactivity between users and pictures, affecting the user experience.

[0021] In view of this, an embodiment of the present disclosure provides a method for displaying pictures. The method may include: in response to obtaining a user's input text, determining a generated text for the input text through a language model; based on the generated text, determining a plurality of pictures corresponding to the generated text; and displaying the determined plurality of pictures in the form of a parallax sliding album. By adopting the method according to an embodiment of the present disclosure, it is possible to generate text related to the input text through a language model, and determine a plurality of pictures corresponding to the generated text, thereby realizing the function of aggregated display of the plurality of pictures, and improving the breadth and depth of the question and answer information display. At the same time, the method can also allow the user to independently control the sliding of multiple pictures related to the input text, which not only attracts and stimulates the user's interest in the multi-level aggregated display of pictures, but also improves the user's sense of participation and experience.

[0022] The embodiments of the present disclosure will be described in detail below in conjunction with the accompanying drawings. Figure 1 A schematic diagram of an example environment 100 is shown in which embodiments of the present disclosure can be implemented. Figure 1 Interface 110 shows a display interface of intelligent graphic answering, on which the user can be provided with pictures and text information related to the text input by the user.

[0023] like Figure 1As shown, in the interface 110, the bubble box (dialog box) on the right side, such as area 120, is the text content input by the user. These text contents can be questions that the user needs to seek answers to or requests made by the user. It can be understood that the text here can be the text after the user's voice is converted into text, because the user can submit questions or requests through the voice button in area 170, which can improve the convenience of user operation. The bubble box (dialog class) on the left side of the interface 110, such as area 130, displays a mixed text and picture reply that matches the text content input by the user. In some embodiments, when the content of the bubble box is too much and exceeds the length of the interface 110, the user can view the content beyond the interface 110 by scrolling up and down.

[0024] In some embodiments, when the user types text and clicks a send button (not shown), the text typed by the user can be displayed in real time in the right area of ​​the question-and-answer page, and at the same time, a mixed text-and-picture answer consisting of generated text and multiple determined pictures can be displayed in real time in the left area of ​​the question-and-answer page. This question-and-answer method that simulates face-to-face communication can enhance the interactivity and realism of the conversation and improve the user experience.

[0025] refer to Figure 1 , when the user inputs "A city travel recommendation", an instant reply related to "A city travel recommendation" can be obtained. The text in area 130 can be obtained with the help of a language model (or an intelligent agent such as artificial intelligence technology). In some embodiments, the text in area 142 and area 152 can be used to obtain the respective related pictures. For example, for the text "Building: The Soul of City A" in area 142, multiple pictures related to it can be obtained, and these pictures can be pictures of "Building" from different angles. It can be seen in the picture container 144 that these aggregated multiple pictures related to "Building" can be displayed in the form of a parallax sliding album, which can facilitate users to view different pictures by sliding left and right, thereby improving the interactivity between users and pictures.

[0026] It is understandable that this kind of graph aggregates multiple pictures of a certain key point, and there is no structural order relationship between them. Therefore, when the user slides these pictures, the texts of the pictures corresponding to them will not change with the sliding of the pictures. For example, when the user slides from the first picture of a building to the second picture of a building, the text "Building: The Soul of City A" corresponding to it is static and unchanged, and will not slide with the sliding of the pictures.

[0027] In some embodiments, if multiple pictures of "building" in the picture container 144 have their own corresponding generated text descriptions (for example, the description of the first picture is "top floor", and the description of the second picture is "side of the building"), which can be displayed below the picture container 144, when the user slides each picture related to the "building", the corresponding text will also slide synchronously, thereby maintaining the consistency of the picture and text descriptions.

[0028] Continue to refer Figure 1 In some embodiments, for the text "lake: beautiful" in area 152, a single picture related to it can also be obtained, so that it can be displayed to the user in the form of a single picture and text mixed in the picture container 154. Through this diversified picture and text layout method of mixing multiple pictures and a single picture, it can provide users with a more clear and direct diversified reading experience.

[0029] In some embodiments, a single mixed text and image container 154 and a mixed multiple text and image container 144 can be displayed simultaneously in area 130. It can be seen that the generated text, image container and determined image are all displayed in the left dialog box of the question and answer page.

[0030] Continue to refer Figure 1 In some embodiments, the user can also switch to different question-and-answer modes through the buttons in area 160, such as switching to an image generation mode, where the user can input their requirements for generated images to instantly obtain relevant images, or switching to a music generation mode, where a user-defined music clip can be generated. For example, the user can also switch to a help me write mode, where a text generated according to the user's needs can be quickly obtained.

[0031] By adopting the method according to the embodiment of the present disclosure, the generated text related to the user input text is first generated by the language model, and then multiple pictures corresponding to the generated text are determined according to the generated text, thereby realizing the function of aggregate display of the multiple pictures in the intelligent picture-text question and answer, and improving the breadth and depth of the question and answer information display. At the same time, the method can also allow the user to independently control the sliding of multiple pictures related to the input text, which not only attracts and stimulates the user's interest in the multi-level aggregated display of pictures, but also improves the user's sense of participation and experience.

[0032] Combined with the above Figure 1 A block diagram of an example environment 100 is depicted in which embodiments of the present disclosure can be implemented. Figure 2 A method for displaying a picture according to an embodiment of the present disclosure is described. Figure 22 shows a flowchart of a method 200 for displaying a picture according to an embodiment of the present disclosure. The method 200 can be executed at any suitable computing device. It should be understood that the numbers in the flowchart of the method 200 do not represent the order in which these steps are executed. Some or all of these steps can be executed in parallel, or the order of execution can be interchanged, and the present disclosure does not limit this. In addition, Figure 2 The method 200 in the embodiment may also include additional steps not shown and / or may omit the steps shown, and the scope of the present disclosure is not limited in this respect.

[0033] In block 202, in response to obtaining a user input text, a generated text for the input text is determined by a language model. Figure 1 , when receiving the text “A city tourism recommendation” in area 120 input by the user, the generated text related to the text “A city tourism recommendation” can be obtained through the language model, such as Figure 1 The text shown in area 130 may be generated by a language model. In some embodiments, the text may also be generated by an agent having language model capabilities.

[0034] In block 204, based on the generated text, a plurality of pictures corresponding to the generated text are determined. Figure 1 , when the text in area 130 corresponding to the text "A City Tourism Recommendation" input by the user is obtained, in order to vividly display the generated answer to the user, multiple pictures with high relevance can be interspersed in the text answer, so as to help the user understand the content of the generated text more intuitively. It is understandable that these multiple pictures are closely related to the user's input text and the generated text. In some embodiments, these pictures can be pictures captured on the web page while generating the text in area 130, and these pictures can also be pictures searched in the gallery. It is understandable that the determination and acquisition methods of pictures are diverse, and the present disclosure does not limit this.

[0035] In block 206, the determined multiple pictures are displayed in a parallax sliding album manner. Figure 1 In order to make the display method of the above-mentioned multiple pictures fit the user's operating habits and improve the user's operating experience, the above-mentioned multiple pictures can be displayed in the area 130 in the form of a parallax sliding album, so that the user can browse the aggregated multiple pictures in a limited screen space by sliding left and right, thereby improving the convenience of browsing.

[0036] Therefore, according to the method for displaying pictures in the embodiment of the present disclosure, it is possible to generate text related to the input text through the language model, and determine multiple pictures corresponding to the generated text, thereby realizing the function of displaying the multiple pictures in an aggregated manner in the intelligent question and answer with the help of the language model, and improving the breadth and depth of the display of graphic and text information. At the same time, the method can also allow users to independently control the sliding of multiple pictures related to the input text, which not only attracts and stimulates the user's interest in the multi-level aggregated display of pictures, but also improves the user's sense of participation and experience.

[0037] The following will be combined with the attached Figure 3A-3B Describes the process used to display an image. Figure 3A-3B FIG. 4 is a schematic diagram showing an exemplary process of a user viewing multiple pictures about a certain point by sliding according to an embodiment of the present disclosure. It can be understood that Figure 3A-3B The interactive interface is only illustrative and can be adapted to multiple terminals and displayed accordingly.

[0038] Figure 3A A schematic diagram of an exemplary process 300A in which a user slides to view multiple pictures about a certain point according to an embodiment of the present disclosure is shown. It can be understood that the process of intelligent question and answer is instant messaging. In the display interface 310A, when the user enters "A city food recommendation" and sends it, the text entered by the user can be displayed in the right area 312A of the display interface 310A, which can facilitate the user to view and determine that the text has been sent successfully. When the sending is successful, the left area 320A of the display interface 310A can display a mixed graphic and text reply related to "A city food recommendation" in real time. It can be seen that the text shown in the left area 320A is related to "A city food recommendation", and these texts can be generated by a language model, or can also be generated by an intelligent agent with language model capabilities.

[0039] In some embodiments, the language model may be a language model with multimodal capabilities. In some embodiments, the language model may be trained by training texts, training images related to the training texts, and some training generation prompts. In some embodiments, candidate texts corresponding to the input texts may be obtained first, and then the generated texts may be summarized from the candidate texts with the help of the language model.

[0040] Continue to refer Figure 3A In order to improve the readability of the reply to "A city food recommendation", the text content in the mixed text and picture in the left area 320A is presented in a point-by-point form, such as the food in A city can be noodles, fish, etc. This point-by-point presentation of text is more in line with the reading habits of human users. In some embodiments, for each key point, multiple pictures corresponding to the key point can be presented.

[0041] In some embodiments, before these pictures are determined, natural language processing (NLP) technology can be used to pre-process the generated text to extract corresponding keywords, and then use these keywords to determine the corresponding multiple pictures. For example, for the text "Surface: The Soul of City A" in area 322A, the keywords obtained by natural language processing technology can be "Surface" and "City A", so that multiple pictures related to the "Surface" of "City A" can be determined based on these keywords.

[0042] In some embodiments, the webpage can also be searched for pictures related to the input text according to the generated text corresponding to the input text. In some embodiments, the gallery can also be searched for related pictures directly, for example, the gallery can be searched for related pictures with the help of the keywords "noodles" and "city A".

[0043] Continue to refer Figure 3A In some embodiments, after multiple pictures are determined, these multiple pictures related to the "face" can be aggregated and displayed in the picture container 326A in the form of a parallax sliding album. As shown in the picture container 326A, the picture 324A is presented at the top.

[0044] In some embodiments, if multiple pictures are multiple pictures of a certain key point in the generated text, then these multiple pictures can be arranged randomly in the picture container without any order requirement. For example, these multiple pictures are all related to "face", that is, multiple pictures of the key point of "face", then the arrangement order of these "face" pictures in the picture container 326A has no strict order, and can be arranged according to the determined order, or can also be arranged according to the size of the picture, or can also be randomly shuffled for layout. In some embodiments, the user can view these multiple pictures by sliding left and right.

[0045] Figure 3B FIG. 3 is a schematic diagram showing an exemplary process 300B in which a user slides to the left to view multiple pictures of key points about a “face” according to an embodiment of the present disclosure. Figure 3B As shown, when the user slides left once in the area of ​​the picture container 326A, the following Figure 3B The second picture 324B shown. Similarly, the user can also slide right on the page of picture 324B to view picture 324A. In some embodiments, these pictures are all related to the key point of "face", so when the user slides left and right, the generated text describing the "face" in area 322A remains unchanged.

[0046] In some embodiments, the user can slide multiple pictures in the picture container 326A in a loop, for example, slide all the way to the right, and when sliding to the last picture, slide again to return to the first picture. It is understandable that the user does not need to enter the secondary page to slide the pictures in the picture container 326A, but only needs to operate on the current page. This method of reducing the number of page jumps makes the picture display smoother, thereby improving the user's browsing efficiency of the pictures and texts generated by the intelligent question and answer.

[0047] The following will be combined Figure 4A-4D to describe. Figures 4A-4D Schematic diagrams showing exemplary processes 400A, 400B, 400C, and 400D of a user viewing multiple pictures about a step-by-step answer by sliding according to an embodiment of the present disclosure. Figure 4A In the display interface 410A, when the user inputs "How to make Kung Pao Chicken" and sends it, the text input by the user can be displayed in the right area 412A of the display interface 410A, i.e., the dialog box. The left area 420A of the display interface 410A, i.e., the reply dialog box, can display the mixed text and picture reply related to "How to make Kung Pao Chicken" in real time. It can be seen that the text shown in the left area 420A, i.e., the dialog box, is related to "How to make Kung Pao Chicken". Similarly, these texts can be generated by a language model, or can also be generated by an intelligent agent with language model capabilities.

[0048] like Figure 4A As shown, in order to help users better understand the specific steps of each step, the text content in the mixed text and graphics in the left area 420A, i.e., the dialog box, can be presented in steps. Figure 4A As shown, area 420A, i.e., the dialog box, shows "Step 1" of "How to make Kung Pao Chicken". Figures 4B-4D , area 420A, i.e., the dialog box, also displays "Step 2" 422B, "Step 3" 422C, and "Step 7" 422D of "How to make Kung Pao Chicken".

[0049] refer to Figure 4A In order to reduce the ambiguity of the text description, each step can be associated with a picture. For example, for the corresponding text description "Step 1" 422A, "Step 1: Remove the fascia from the chicken breast and cut it into small pieces", the corresponding picture can be determined to be a picture 424A of "chicken breast cut into small pieces". Figures 4B-4D, for the descriptions of "step 2" 422B, "step 3" 422C, and "step 7" 422D, the pictures determined are picture 424B of "marinated muscle material", picture 424C of "diced material", and picture 424D of "frying in a pan". It can be understood that the multiple pictures here are related. In some embodiments, these pictures are arranged in the order of text descriptions, with a strict order, which is proportional to the relevance of the text descriptions, so when the user slides the picture, the corresponding generated text description corresponding to the picture will also slide accordingly. In some embodiments, the pictures corresponding to the steps can also be dynamic, or can also be in the form of short videos.

[0050] refer to Figure 4A and 4B In order to enhance the coherence between the step answers, the pictures associated with each step can also be aggregated into a picture container 426A, so that the user can view the text description and pictures of each step in detail by simply sliding left and right without occupying too much space in the answer. For example, after viewing "Step 1" 422A, the user can switch to "Step 2" by sliding left on the picture container 426A. Figure 4B The related picture 424B of "Step 2" shown, and the text description "Step 2" 422B for the picture 424B will also be displayed along with the sliding display of the picture 424B.

[0051] For example, refer to Figure 4B and 4C After viewing "Step 2" 422B, the user can switch to the next step by sliding left on the image container 426B. Figure 4C The picture 424C is shown, and the text description "Step 3" 422C for the picture 424C will also be displayed along with the sliding display of the picture 424C.

[0052] refer to Figure 4A and Figure 4D In some embodiments, the user can view the step description and picture he wants to view by swiping left and right on the picture container 426A. For example, after switching to "step 7" 422D shown in FIG. 4 to view picture 424D, the user can swipe right on the picture container 426A to switch to "step 6", and then swipe right to switch to "step 1" 422A, or swipe left directly to switch to "step 1" 422A. This diverse roller skating method provides users with a rich operating experience.

[0053] In intelligent question and answering with the help of language models, through such graphic layout and presentation method, users can not only quickly obtain responses to their requests and questions, but also understand the specific operations of each step more intuitively with the help of multiple pictures, thereby improving the efficiency of obtaining question and answer information and user experience.

[0054] The following will be combined Figure 5 to describe. Figure 5 FIG. 5 is a schematic diagram showing an exemplary process 500 of displaying multiple pictures through a puzzle container according to an embodiment of the present disclosure. Figure 5 As shown, in the display interface 510, when the user types and sends the question or request of "How to make Kung Pao Chicken", the description of the question or request can be immediately displayed in the right area of ​​the display interface 510. The left area 520 of the display interface 510, i.e., the dialog box, can display the graphic content related to "How to make Kung Pao Chicken" in real time. It can be seen that what is displayed in the left area 520, i.e., the dialog box, is not just a text description, but a mixed format that combines pictures and text, which can provide users with a richer and more intuitive way of displaying information. At the same time, these graphic and textual contents can be generated by a language model, or can also be generated by an intelligent agent with language model capabilities.

[0055] like Figure 5 As shown, in order to help users better understand the specific steps of each step, the mixed text and images in the left area 520, i.e., the dialog box, can be presented in steps. And in order to reduce the ambiguity of the text description, the pictures associated with each step can be determined. Further, in order to allow users to see all relevant information at a glance, multiple pictures can be spliced ​​into a large picture in the picture container for display. For example, for the key point of cooking materials, the pictures of all the materials can be spliced ​​and displayed in the same picture container, because the pictures of these materials are parallel and parallel key points. It can be seen that pictures 522, 524, and 526 are spliced ​​into a large puzzle, so that they can be displayed in picture container 528.

[0056] Continue to refer Figure 5 When the user clicks on the picture 522, the full view of the picture 522 can be displayed, and the text description of the picture 522 can be displayed at the same time. In some embodiments, the number of the aggregated multiple pictures is displayed by the number of the superscript 530. In some embodiments, when the user clicks on the superscript 530, other pictures can also be displayed in the same way as the picture 522.

[0057] In intelligent question and answer with the help of language model, the method of displaying multiple pictures in a mixed layout of pictures and texts can improve the breadth and depth of intelligent question and answer information. At the same time, this method can also allow users to independently control the sliding of multiple pictures related to the input text, which not only attracts and stimulates users' interest in multi-level aggregated pictures, but also improves users' sense of participation and experience.

[0058] Figure 6 FIG. 6 is a schematic diagram showing an exemplary process 600 of determining the image container size according to an embodiment of the present disclosure. Figure 6 In order to make the mixed text and image layout presented to the user more beautiful and in line with the user's operating habits, the size of the image container used to display the image can be determined first. At 610, the width of the image container is determined. In some embodiments, the width of the image container can be determined according to the width of the bubble box.

[0059] To explain what a bubble frame is, the following will combine Figure 7 to describe. Figure 7 A schematic diagram showing an exemplary process 700 of displaying pictures of different sizes in the same answer according to an embodiment of the present disclosure. Figure 7 The area 720 displayed in the display interface 710 is a bubble box, which can also be called a dialog box. The following description will be taken as an example of the picture container 724. In some embodiments, the width of the picture container can be the width of the bubble minus a predetermined width (usually 32 units), and the width of the picture container 724 is the width of the bubble box 720 minus 32 units.

[0060] return Figure 6 At 620, the height of the image container is determined. In some embodiments, the height of the image container is the width of the image container multiplied by the ratio value of the image container. The ratio value of the image container is determined by comparing it with a preset ratio condition. At 621, the ratio of the first image can be obtained, and then the ratio value of the image container 724 can be determined by comparing the ratio of the first image with the preset ratio condition. Figure 7 Assuming that multiple pictures will be displayed in the picture container 724, the height of the picture container 724 can be determined according to the ratio of the first picture (ie, the picture that the user sees first by default).

[0061] Continue to refer Figure 6At 622, if the ratio of the first picture is greater than 16:9, then 16:9 may be determined as the ratio value of the picture container 724 at 623. At 624, if the ratio of the first picture is greater than 1:1 but less than 16:9, then the ratio of the first picture may be used as the ratio value of the picture container 724 at 625. At 626, if the ratio of the first picture is less than 1:1, then the ratio of the first picture may be used as the ratio value of the picture container 724 at 627.

[0062] Continue to refer Figure 6 When the height and width of the picture container are determined, the size of the picture to be displayed in the picture container can be determined at 630. In some embodiments, if the size of the picture to be displayed is too long or too wide, the picture to be displayed can be adaptively adjusted according to the determined size of the picture container, thereby improving the user's browsing experience.

[0063] It is understandable that in the same graphic answer, the size of the image container for each answer to each point may be different. Figure 7 , Figure 7 The picture container 724 shown is for the generated text description 722, and its size is inconsistent with the size of the picture container 734 for the generated text description 732, but can be displayed in the same graphic answer at the same time, which depends on the size of the first picture in the picture determined by the text generated according to the text input by the user. In this way, the visual effect of the presentation can be optimized, thereby improving the user experience.

[0064] Figure 8 800 is a schematic block diagram of an example device 800 according to some embodiments of the present disclosure. The device 800 may be implemented in software, hardware, or a combination of both. Figure 8 As shown, the device 800 includes a text generation determination module 810 , a picture determination module 820 and a picture display module 830 .

[0065] In some embodiments, the generated text determination module 810 may determine the generated text for the input text through a language model in response to obtaining the user's input text. The picture determination module 820 may determine multiple pictures corresponding to the generated text based on the generated text. The picture display module 830 may display the determined multiple pictures in the form of a parallax sliding album. Figure 8 The device 800 can be used to achieve the above combination Figures 1 to 7 For the sake of brevity, the process will not be described in detail here.

[0066] The division of modules or units in the embodiments of the present disclosure is schematic and is only a logical function division. There may be other division methods in actual implementation. In addition, each functional unit in the disclosed embodiments may be integrated into one unit, or may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0067] Fig. 9 900 is a block diagram of an example device that can be used to implement an embodiment of the present disclosure. It should be understood that Fig. 9 The device 900 shown is merely an example and should not constitute any limitation on the functionality and scope of the implementations described herein.

[0068] like Fig. 9 As shown, the device 900 is in the form of a general-purpose computing device. The components of the computing device 900 may include, but are not limited to, one or more processors or processing units 910, a memory 920, a storage device 930, one or more communication units 940, one or more input devices 950, and one or more output devices 960. The processing unit 910 may be an actual or virtual processor and is capable of performing various processes according to a program stored in the memory 920. In a multi-processor system, multiple processing units execute computer executable instructions in parallel to increase the parallel processing capabilities of the computing device 900.

[0069] The computing device 900 typically includes a plurality of computer storage media. Such media may be any available media accessible to the computing device 900, including but not limited to volatile and non-volatile media, removable and non-removable media. The memory 920 may be a volatile memory (e.g., register, cache, random access memory (Random Access Memory, RAM)), a non-volatile memory (e.g., read-only memory (Read Only Memory, ROM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read Only Memory, EEPROM), flash memory) or some combination thereof. The storage device 930 may be a removable or non-removable medium, and may include a machine-readable medium, such as a flash drive, a disk, or any other medium, which may be capable of being used to store information and / or data (e.g., training data for training) and may be accessed within the computing device 900.

[0070] The computing device 900 may further include additional removable / non-removable, volatile / non-volatile storage media. Fig. 9As shown in , a disk drive for reading or writing from a removable, non-volatile disk (e.g., a "floppy disk") and an optical drive for reading or writing from a removable, non-volatile optical disk may be provided. In these cases, each drive may be connected to the bus (not shown) by one or more data media interfaces. Memory 920 may include a computer program product 925 having one or more program modules that are configured to perform various methods or actions of various implementations of the present disclosure.

[0071] The communication unit 940 implements communication with other computing devices through a communication medium. Additionally, the functions of the components of the computing device 900 can be implemented in a single computing cluster or multiple computing machines that can communicate through a communication connection. Therefore, the computing device 900 can operate in a networked environment using a logical connection with one or more other servers, a network personal computer (PC), or another network node.

[0072] Input device 950 may be one or more input devices, such as a mouse, keyboard, tracking ball, etc. Output device 960 may be one or more output devices, such as a display, a speaker, a printer, etc. Computing device 900 may also communicate with one or more external devices (not shown) through communication unit 940 as needed, such as storage devices, display devices, etc., communicate with one or more devices that allow users to interact with computing device 900, or communicate with any device that allows computing device 900 to communicate with one or more other computing devices (e.g., a network card, a modem, etc.). Such communication may be performed via an input / output (I / O) interface (not shown).

[0073] According to an example implementation of the present disclosure, a computer-readable storage medium is provided, on which computer-executable instructions are stored, wherein the computer-executable instructions are executed by a processor to implement the method described above. According to an example implementation of the present disclosure, a computer program product is also provided, the computer program product is tangibly stored on a non-transitory computer-readable medium and includes computer-executable instructions, and the computer-executable instructions are executed by a processor to implement the method described above. According to an example implementation of the present disclosure, a computer program product is provided, on which a computer program is stored, and when the program is executed by a processor, the method described above is implemented.

[0074] Various aspects of the present disclosure are described herein with reference to the flowcharts and / or block diagrams of the methods, devices, equipment, and computer program products implemented according to the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer-readable program instructions.

[0075] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processing unit of the computer or other programmable data processing device, a device that implements the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0076] Computer-readable program instructions can be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, so that the instructions executed on the computer, other programmable data processing apparatus, or other device implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0077] The flow chart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to multiple implementations of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a part of a module, program segment or instruction, and a part of a module, program segment or instruction includes one or more executable instructions for realizing the logical function of the specification. In some implementations as replacements, the function marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous square boxes can actually be executed substantially in parallel, and they can sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be realized by a special hardware-based system that performs the function or action of the specification, or can be realized by a combination of special hardware and computer instructions.

[0078] The above descriptions of various implementations of the present disclosure are illustrative, non-exhaustive, and not limited to the disclosed implementations. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described implementations. The selection of terms used herein is intended to best explain the principles of the implementations, practical applications, or improvements to the technology in the marketplace, or to enable other persons of ordinary skill in the art to understand the various implementations disclosed herein.

Claims

1. A method for displaying a picture, the method comprising: In response to obtaining a user input text, determining a generated text for the input text by using a language model; Based on the generated text, determining a plurality of pictures corresponding to the generated text; as well as The determined multiple pictures are displayed in a parallax sliding album manner.

2. The method according to claim 1, wherein displaying the determined plurality of pictures in a parallax sliding album manner comprises: In response to the multiple pictures being determined to satisfy the first condition, the multiple pictures are arranged in sequence in the picture container by sliding the parallax album.

3. The method according to claim 2, further comprising: In response to detecting a user sliding on the picture container area, sliding the plurality of pictures determined to be arranged in sequence; and Synchronously slide the generated texts corresponding to the determined multiple pictures.

4. The method according to claim 1, wherein displaying the determined plurality of pictures in a parallax sliding album manner comprises: In response to the determined plurality of pictures satisfying a second condition, displaying the determined plurality of pictures in a picture container by means of the parallax sliding album; as well as In response to detecting a user sliding on the picture container area, the displayed multiple pictures are slid, wherein texts corresponding to the multiple pictures remain unchanged.

5. The method according to claim 1, wherein displaying the determined plurality of pictures in a parallax sliding album manner comprises: In response to the multiple pictures being determined to satisfy the third condition, the multiple pictures are displayed in the picture container in a puzzle manner.

6. The method according to claim 1, wherein the plurality of pictures are displayed in a picture container, and the picture container is displayed in a dialog box, further comprising: Determine the width of the image container based on the width of the dialog box and a preset width; Determine the height of the picture container based on the width and the proportion of the top picture in the picture container; as well as Based on the height and the width, a display size of the determined plurality of pictures displayed in the picture container is determined.

7. The method according to claim 6, further comprising: In response to the ratio value of the top-ranked picture satisfying a first ratio condition, determining the ratio value to be a ratio of the picture container; In response to the ratio value of the top-ranked picture satisfying a second ratio condition, determining that the ratio of the picture container is a second ratio; as well as In response to the ratio value of the top-ranked picture satisfying a third ratio condition, the ratio of the picture container is determined to be a third ratio.

8. The method according to claim 1, wherein in response to obtaining a user input text, determining a generated text for the input text by using a language model comprises: In response to detecting the user's input voice, the input voice is converted into the input text.

9. The method according to claim 8, further comprising: Acquire multiple candidate texts corresponding to the input text; as well as The language model determines the generated text based on the multiple candidate texts.

10. The method according to claim 9, further comprising: The language model is trained by means of training prompts, training pictures and training texts corresponding to the training pictures, wherein the training prompts instruct the language model to determine the pictures corresponding to the training texts.

11. The method according to claim 1, wherein based on the generated text, determining a plurality of pictures corresponding to the generated text comprises: Acquire a web page corresponding to the generated text and the input text, and determine the plurality of pictures from the web page; or Based on the image search, the plurality of images are determined.

12. The method according to claim 1, further comprising: In response to detecting that the user clicks on the send button, displaying the input text in a dialog box in the right area of ​​the question-and-answer page; as well as The generated text and the multiple pictures are displayed in a dialog box in the left area of ​​the question and answer page.

13. An electronic device comprising: at least one processing unit; At least one memory, the at least one memory being coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, the instructions, when executed by the at least one processing unit, causing the electronic device to perform the method according to any one of claims 1 to 12.

14. A computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the method according to any one of claims 1 to 12 when executed by a processor.

15. A computer program product having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the method according to any one of claims 1 to 12.

Citation Information

Patent Citations

  • Information display method and device, equipment and storage medium

    CN115811638A

  • Large model image-text dialogue method and device, equipment and storage medium

    CN117633173A

  • Picture preview method and device and storage medium

    CN118093080A

  • Multi-modal interaction method and device

    CN118585637A

  • Systems and methods for question-answering using a multi-modal end to end learning system

    US20240095455A1