Display method and device

Abstract

The invention provides a display method and device. The method comprises the following steps: displaying a target image sequence in response to an interaction operation indicating to input target input data into a target intelligent engine to generate image data; generating target image data in response to the target intelligent engine, and displaying the target image data; wherein the target image sequence at least comprises a first image and a second image; the first image and / or the second image are / is associated with the target input data.

Description

Technical Field

[0001] The present application relates to display technology, and in particular to a display method and device. Background Art

[0002] Currently, images can be generated by inputting data. However, the image generation process typically takes time. During this waiting period, the current display method uses traditional waiting animations, such as progress bars or flashing icons. While traditional waiting animations can indicate that the image is being generated, they have no direct connection to the input data, resulting in a poor user experience. Summary of the Invention

[0003] Embodiments of the present application provide a display method and device.

[0004] According to the first aspect of the present application, a display method is provided, which includes: displaying a target image sequence in response to an interactive operation indicating that target input data is input into a target intelligent engine to generate image data; displaying the target image data in response to the target intelligent engine generating target image data; wherein, the target image sequence includes at least a first image and a second image; the first image and / or the second image is associated with the target input data.

[0005] According to one embodiment of the present application, the method further includes: if the target input data is first input data, the target image sequence is a first image sequence; if the target input data is second input data, the target image sequence is a second image sequence.

[0006] According to one embodiment of the present application, the first image and / or the second image includes first image content and second image content; the first image content has a first correlation with the target input data, and the second image content has a second correlation with the target image data.

[0007] According to one embodiment of the present application, the first image and / or the second image contains target image content representing the target input data; the target image content has first image parameters in the first image, and the target image content has second image parameters in the second image, and the first image parameters are different from the second image parameters.

[0008] According to one embodiment of the present application, the target input data is text data; and the target image content is the text data.

[0009] According to one embodiment of the present application, the text data has a first display disorder in the first image; and the text data has a second display disorder in the second image.

[0010] According to one embodiment of the present application, the first image is the image data output by the target intelligent engine in the first stage; the second image is the image data output by the target intelligent engine in the second stage; and the target image data is the image data finally output by the target intelligent engine.

[0011] According to one embodiment of the present application, the method also includes: performing feature analysis on the target input data to obtain keyword features; determining the association weight between the keyword features and the process of the target intelligent engine generating target image data; and adjusting the target image sequence based on the association weight to obtain an adjusted target image sequence.

[0012] According to one embodiment of the present application, displaying the target image sequence includes: obtaining style information corresponding to the target input data; adjusting display parameters corresponding to the target image sequence according to the style information; and displaying the target image sequence based on the adjusted display parameters.

[0013] According to the second aspect of the present application, a display device is provided, comprising: a first display module for displaying a target image sequence in response to an interactive operation indicating that target input data is input into a target intelligent engine to generate image data; a second display module for displaying the target image data in response to the target intelligent engine generating the target image data; wherein the target image sequence includes at least a first image and a second image; the first image and / or the second image is associated with the target input data. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The above and other objects, features and advantages of the exemplary embodiments of the present application will become readily understood by reading the detailed description below with reference to the accompanying drawings. In the accompanying drawings, several embodiments of the present application are shown in an illustrative and non-limiting manner, in which:

[0015] In the drawings, the same or corresponding reference numerals denote the same or corresponding parts.

[0016] Figure 1 The processing flow diagram of the display method provided in the embodiment of the present application is shown as follows Figure 1 ;

[0017] Figure 2 The processing flow diagram of the display method provided in the embodiment of the present application is shown as follows Figure 2 ;

[0018] Figure 3 The processing flow diagram of the display method provided in the embodiment of the present application is shown as follows Figure 3 ;

[0019] Figure 4 A diagram showing an application scenario of the display method provided in an embodiment of the present application is shown;

[0020] Figure 5 An optional schematic diagram of a display device provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0021] In order to make the purpose, features, and advantages of this application more obvious and easy to understand, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without making creative efforts shall fall within the scope of protection of this application.

[0022] In the following description, reference is made to “some embodiments”, which describes a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0023] In the following description, the terms "first\second" involved are merely used to distinguish similar objects and do not represent a specific ordering of the objects. It is understandable that "first\second" can be interchanged with a specific order or sequence where permitted, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein.

[0024] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application pertains. The terms used herein are for the purpose of describing the embodiments of this application only and are not intended to limit this application.

[0025] The processing flow of the display method provided in the embodiment of the present application is described. Figure 1 , Figure 1 This is a schematic diagram of the processing flow of the display method provided in the embodiment of the present application Figure 1 , will combine Figure 1 Steps S101-S102 are shown for explanation.

[0026] Step S101 , in response to an interactive operation instructing to input target input data into a target intelligent engine to generate image data, display a target image sequence.

[0027] In some embodiments, the target input data may include: data input by the user to prompt the target intelligent engine to generate an image. The target input data may specifically include input data such as text data, image data, and audio data, and may include only one type of data or multiple types of data. The embodiments of the present application do not limit the specific input data. The target intelligent engine may include: a model that processes the target input data and generates image data based on artificial intelligence technology. The embodiments of the present application do not limit the specific model. The interactive operation may include the user interacting with the target intelligent engine through set instructions. Specific interactive operations may include: instructions such as instructions for inputting text data, instructions for inputting image data, and instructions for inputting audio data. The embodiments of the present application do not limit the specific interactive operations. The target image sequence may include: a series of images displayed during the process of the target intelligent engine generating target image data.

[0028] The target intelligent engine can be a target model with more than 100 million weight parameters. The target model learns the characteristics and patterns of input information by training on large amounts of diverse data. It typically has hundreds of millions to hundreds of billions of model parameters (model parameters are variables that control the behavior of the target model), capable of capturing complex relationships and patterns in the input information. The target input data guides the target model's reasoning.

[0029] In one embodiment, the target model can be a generative model. For example, it can include a visual large model, a multimodal large model, etc. The model involved in the embodiments of the present application can be a general large model or an expert large model obtained by fine-tuning based on needs, and the embodiments of the present application do not limit this.

[0030] Step S102 , in response to the target intelligent engine generating target image data, displaying the target image data; wherein the target image sequence includes at least a first image and a second image; the first image and / or the second image are associated with the target input data.

[0031] In some embodiments, the target image data may include: image data ultimately generated by the target intelligent engine. The first image may include: any image in the target image sequence. The first image may be associated with the target input data. The second image may include: a subsequent image of the first image in the target image sequence. The second image may be associated with the target input data. One of the first image and the second image may be associated with the target input data. The target image sequence may be a continuous animation consisting of the first image and the second image, and the continuous animation and the target input data are associated. When the target intelligent engine generates the target image data, the target image sequence is hidden and the target image data is displayed.

[0032] The method of the embodiment of the present application displays a target image sequence that is related to the input data and changes dynamically during the waiting period for image generation, so that the waiting animation is more semantically consistent with the process of generating target image data, thereby enhancing the user's intuitive perception of the process of the device generating image data and improving the user experience.

[0033] In some embodiments, the display method may further include: if the target input data is the first input data, the target image sequence is the first image sequence; if the target input data is the second input data, the target image sequence is the second image sequence.

[0034] As an example, the first input data and the second input data are different input data. Specifically, the first input data and the second input data may differ in data type, format, and semantics. For example, the first input data may be input text data, while the second input data may be input image data. The first input data and the second input data may also be of the same data type but different in content. For example, the first input data may be a piece of text data describing the generation of a building landscape image, while the second input data may be a piece of text data describing the generation of a car image. Both are text data but different in content. Correspondingly, the first image sequence and the second image sequence are different image sequences. The first image sequence may be associated with the first input data, while the second image sequence may be associated with the second input data. The first image sequence may specifically be a continuous animation consisting of a series of images associated with the first input data. The second image sequence may specifically be a continuous animation consisting of a series of images related to the second input data. When the input data are different, the corresponding displayed image sequences are also different.

[0035] The method of the embodiment of the present application makes the waiting animation more semantically consistent with the process of generating target image data by displaying a target image sequence that is related to the input data and changes dynamically during the waiting period for image generation. Different image sequences are displayed according to different input data, thereby enhancing the user's intuitive perception of the process of the device generating image data and improving the user experience.

[0036] In some embodiments, the first image and / or the second image includes first image content and second image content; the first image content has a first correlation with the target input data, and the second image content has a second correlation with the target image data.

[0037] As an example, the first image may include first image content, and the second image may include second image content. Displaying the target image sequence may include sequentially displaying the first image and the second image. For example, at a first moment, first image content having a first correlation with the target input data is displayed, and at a second moment, second image content having a second correlation with the target image data is displayed. The target image sequence may represent the process of the target input data changing into the target image data, specifically, the first image content related to the target input data may decrease, while the second image content related to the generated target image data may increase.

[0038] As an example, the first image may include the first image content and the second image content. The second image may include the first image content and the second image content. The target input data includes the input "generate a brightly lit city, including tall buildings and roads." The target image sequence is displayed. First, the first image is displayed, and the first image contains both the first image content and the second image content. The first image content is a simple text graphic of "tall buildings" and "roads", which has a first correlation with the target input data; the second image content can be the lighting effects of tall buildings and roads, which has a second correlation with the target image data. Then, the second image is displayed, and the second image contains both the first image content and the second image content. The first image content in the second image gradually decreases, for example, the outline of the simple text graphic begins to fade; the second image content gradually increases, for example, the lighting effects of tall buildings and the trajectory images of roads become more obvious.

[0039] The method of the embodiment of the present application displays a dynamically changing target image sequence that is related to the input data and the final generated image during the waiting period for image generation, so that the waiting animation is more semantically consistent with the process of generating target image data, thereby enhancing the user's intuitive perception of the device's image data generation process and improving the user experience.

[0040] In some embodiments, the first image and / or the second image contains target image content representing target input data; the target image content has first image parameters in the first image, and the target image content has second image parameters in the second image, and the first image parameters are different from the second image parameters.

[0041] As an example, the target image content may include: content related to the target input data. The target image content may be information extracted from the input data. The first image parameter may be used to control a gradient display visual effect of displaying the target image content in the first image, and the second image parameter may be used to control a gradient display visual effect of displaying the target image content in the second image. The gradient display visual effect may include: size gradient display, hue gradient display, transparency gradient display, and rotation angle gradient display. The image parameters of the target image content may include at least one of the following: position in the image, size of the area occupied in the image, hue in the image, transparency in the image, and rotation angle in the image.

[0042] The method of the embodiment of the present application makes the waiting animation more semantically consistent with the process of generating target image data by displaying a target image sequence that is related to the input data and changes dynamically during the waiting period for image generation. By adjusting the image parameters of the target image content, the dynamic change of the image sequence is achieved, so that the user can feel the process of image generation during the waiting period, enhance the user's intuitive perception of the process of image data generation by the device, and improve the user experience.

[0043] In some embodiments, the target input data is text data; and the target image content is text data.

[0044] As an example, the target input data includes inputting the text data "generate a tranquil lake surrounded by mountains". The target image sequence is displayed. First, the first image is displayed, and the first image contains the target image content. The target image content is the text data of "lake", "tranquility", "surrounded" and "mountains". The text data of "lake" in the target image content corresponds to the first image parameters of the first image including a light blue hue, 100% transparency, and a rotation angle of 0 degrees. Then, the second image is displayed, and the second image contains the target image content. The target image content is the text data of "lake", "tranquility", "surrounded" and "mountains". The text data of "lake" in the target image content corresponds to the second image parameters of the second image including a dark blue hue, 80% transparency, and a rotation angle of 5 degrees.

[0045] In some embodiments, the text data has a first display clutter in the first image; and the text data has a second display clutter in the second image.

[0046] As an example, display chaos can be expressed as a process in which text data changes from being neatly arranged to being scattered and randomly moved. First, the first image is displayed, and the text data contained in the first image are "lake surface", "tranquility", "surrounded" and "mountains". In the first image, the text data has a low display chaos, the text is neatly arranged, the character spacing is uniform, the color of all text data is uniformly light blue, the transparency is 100%, there is no rotation angle, the overall layout is regular, and the text content is displayed in a centralized manner. Then, the second image is displayed, and the text data contained in the second image are "lake surface", "tranquility", "surrounded" and "mountains". However, at this time, the text data has a high display chaos. The text arrangement of the text data becomes scattered, the character spacing is irregular, the color of some text data changes to dark blue, the transparency is reduced to 80%, and each text has a rotation angle of 5 degrees. The overall layout of the text data is scattered and disordered, and the display position of the text data in the second image changes randomly.

[0047] The method of the embodiment of the present application makes the waiting animation more semantically consistent with the process of generating target image data by displaying a target image sequence related to the input text data and dynamically changing during the waiting period for image generation, converts the text content into visual elements, and intuitively presents the image generation process by changing the display confusion of the text data, so that the user can feel the image generation process during the waiting period, enhances the user's intuitive perception of the process of image data generation by the device, and improves the user experience.

[0048] In some embodiments, the first image is image data output by the target intelligent engine in the first stage; the second image is image data output by the target intelligent engine in the second stage; and the target image data is image data finally output by the target intelligent engine.

[0049] As an example, the target input data includes the input "generate an image of a kitten." A target image sequence is displayed, comprising a first image and a second image. The first image displayed first represents the image data output by the target intelligent engine in the first stage. For example, the first image is a preliminary outline image generated by the target intelligent engine based on the target input data. The first image may include a simple outline of a kitten, including a basic head, ears, eyes, and whiskers, with relatively simple colors and details, such as a single beige kitten with small black dots as eyes. The second image displayed next represents the image data output by the target intelligent engine in the second stage. For example, the second image is generated by the target intelligent engine based on the target input data and the preliminary outline image. Compared to the first image, the second image adds more details, such as the texture of the kitten's fur, highlights on the eyes, specific details in the whiskers, and a simple rendering of the background, such as adding a blurred indoor environment. The target intelligent engine continues processing, ultimately outputting the target image data. In response to the target intelligent engine outputting the target image data, the target image sequence is hidden and the target image data is displayed. The target image data contains richer details, such as the delicate texture of the kitten's fur, the bright expression of its eyes, and the natural curvature of its whiskers. The background is also clearer, such as the addition of furniture and toys, and the overall color is soft with corresponding light and shadow effects.

[0050] The method of the embodiment of the present application displays a target image sequence related to the input data during the waiting period for image generation, so that the waiting animation is more semantically consistent with the process of generating target image data. By outputting image data in stages, the gradual improvement process of image generation is displayed, and dynamic changes of the image sequence are realized, so that the user can feel the process of image generation during the waiting period, enhance the user's intuitive perception of the process of image data generation by the device, and improve the user experience.

[0051] In some embodiments, the processing flow of the display method is shown as follows: Figure 2 ,like Figure 2 As shown, in step S103, adjusting the encoding verification parameters corresponding to the data block based on the data block parameters may specifically include:

[0052] Step S201: Perform feature analysis on target input data to obtain keyword features.

[0053] Step S202: determining the association weight between the keyword feature and the process of the target intelligent engine generating the target image data.

[0054] Step S203 : adjusting the target image sequence based on the association weight to obtain an adjusted target image sequence.

[0055] In some embodiments, feature analysis may include analyzing target input data to extract key features therein. Keyword features may include key information extracted from the target input data. Association weights may include a correlation measure between the keyword features and the process of generating target image data by the target intelligent engine. Specifically, the association weights may represent the importance of the keyword features in the process of generating the target image data. Adjusting the target image sequence may include adjusting the image content in the target image sequence.

[0056] As an example, the target input data includes the text data "Generate a cute kitten image." Feature analysis of the target input data reveals keyword features including "generate," "one," "cute," "kitten," and "image." Determining the association weights between the keyword features and the process of generating target image data by the target intelligent engine includes determining an association weight of 0.3 for "generate," 0.5 for "one," 0.9 for "cute," 0.9 for "kitten," and 0.6 for "image." The target image sequence is adjusted based on the association weights. For example, the keywords "kitten" and "cute" have high association weights. Adjusting the image content associated with "kitten" and "cute" in the target image sequence makes them more prominently displayed. Specifically, making them more prominently displayed may include adjusting image parameters of the image content associated with "kitten" and "cute." For example, adjusting the hue of the image content associated with "kitten" and "cute" to a brighter hue, adjusting the position of the image content associated with "kitten" and "cute" to the center of the image, etc. The embodiment of the present application does not limit the specific method of adjusting the image parameters. Then, the adjusted target image sequence is displayed.

[0057] The method of the embodiment of the present application makes the waiting animation more semantically consistent with the process of generating target image data by displaying the target image sequence related to the input data during the waiting period of image generation, optimizes the image sequence through feature analysis and weight adjustment, enables the user to feel the process of image generation during the waiting period, enhances the user's intuitive perception of the process of image data generation by the device, and improves the user experience.

[0058] In some embodiments, the processing flow of the display method is shown as follows: Figure 3 ,like Figure 3 As shown, the display target image sequence in step S101 may specifically include:

[0059] Step S301: Obtain style information corresponding to target input data.

[0060] Step S302: adjusting display parameters corresponding to the target image sequence according to the style information.

[0061] Step S303: displaying the target image sequence based on the adjusted display parameters.

[0062] In this embodiment, style information may include: a pre-set style type used to assist the target intelligent engine in generating images. Specific style information may include: professional style, relaxed style, and minimalist style. This embodiment of the application does not limit the specific style information. Display parameters may include: parameters that control the image display effect of the target image sequence. Specific display parameters may include parameters such as lighting parameters, color parameters, and detail parameters. This embodiment of the application does not limit the specific display parameters.

[0063] For example, the style information may be a professional style. The corresponding lighting parameters for the professional style may include: the image displays realistic lighting effects. The color parameters may include: the image uses realistic colors. The detail parameters may include: the image contains a variety of realistic details. The style information may be adjusted to a minimalist style. The corresponding lighting parameters for the minimalist style may include: the image displays basic light and dark lighting effects. The color parameters may include: the image uses a single or contrasting color. The detail parameters may include: the image contains fewer details.

[0064] The method of the present application embodiment displays a target image sequence related to the input data during the waiting period for image generation, making the waiting animation more semantically consistent with the process of generating the target image data. The display parameters of the image sequence are adjusted based on the style information. This meets the user's needs for different styles, allows the user to experience the image generation process during the waiting period, enhances the user's intuitive perception of the device's image data generation process, and improves the user experience.

[0065] refer to Figure 4 , the application scenario diagram of the display method provided in the embodiment of the present application is applied to the visual effect of the text-to-picture process.

[0066] Step A1: input text data that instructs the target intelligent engine to generate target image data. The text data is used to describe the target image data to be generated.

[0067] Step A2 displays a continuous animation. The animation may include: each character in the input text data gradually disperses independently, each moving randomly in a different direction. After reaching the edge of the screen, the characters are reflected and continue to move on the screen. At the same time, each character undergoes a random gradient change in attributes such as size, color, blur level, and rotation angle.

[0068] In step A3, if the target intelligent engine has completed the generation of the target image data, the blur level of each character continues to increase and fades out. At the same time, the target image data gradually fades from completely transparent to fully displayed, and the blur level of the target image data also changes from highly blurred to completely clear.

[0069] The following continues to describe an exemplary structure of the display device 90 provided in the embodiment of the present application implemented as a software module. In some embodiments, such as Figure 5 As shown, the display device 90 may include: a first display module 901, for displaying a target image sequence in response to an interactive operation indicating that target input data is input into a target intelligent engine to generate image data; a second display module 902, for displaying the target image data in response to the target intelligent engine generating the target image data; wherein, the target image sequence includes at least a first image and a second image; the first image and / or the second image is associated with the target input data.

[0070] In some embodiments, if the target input data is first input data, the target image sequence is a first image sequence; if the target input data is second input data, the target image sequence is a second image sequence.

[0071] In some embodiments, the first image and / or the second image includes first image content and second image content; the first image content has a first correlation with the target input data, and the second image content has a second correlation with the target image data.

[0072] In some embodiments, the first image and / or the second image contains target image content representing the target input data; the target image content has first image parameters in the first image, and the target image content has second image parameters in the second image, and the first image parameters are different from the second image parameters.

[0073] In some embodiments, the target input data is text data; and the target image content is the text data.

[0074] In some embodiments, the text data has a first display clutter level in the first image; and the text data has a second display clutter level in the second image.

[0075] In some embodiments, the first image is image data output by the target intelligent engine in the first stage; the second image is image data output by the target intelligent engine in the second stage; and the target image data is image data finally output by the target intelligent engine.

[0076] In some embodiments, the display device also includes an adjustment module, which is used to: perform feature analysis on the target input data to obtain keyword features; determine the association weight between the keyword features and the process of the target intelligent engine generating target image data; and adjust the target image sequence based on the association weight to obtain an adjusted target image sequence.

[0077] In some embodiments, the second display module 902 may be configured to: obtain style information corresponding to the target input data; adjust display parameters corresponding to the target image sequence according to the style information; and display the target image sequence based on the adjusted display parameters.

[0078] It should be noted that the description of the device of the embodiment of the present application is similar to the description of the method embodiment above, and has similar beneficial effects as the method embodiment, so it will not be repeated here. Figures 1 to 4 The present invention shall be understood by reference to the description of any of the accompanying drawings.

[0079] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this application can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this application can be achieved. This is not a limitation herein.

[0080] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features being referred to. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. Throughout the description of this application, "plurality" means two or more, unless otherwise specifically defined.

[0081] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A display method, comprising: displaying a target image sequence in response to an interaction instructing input of target input data to a target intelligence engine to generate image data; In response to the target intelligence engine generating target image data, displaying the target image data; The target image sequence includes at least a first image and a second image; the first image and / or the second image are associated with the target input data.

2. The method according to claim 1, further comprising: If the target input data is the first input data, the target image sequence is the first image sequence; If the target input data is the second input data, the target image sequence is the second image sequence.

3. The method according to claim 1, The first image and / or the second image includes first image content and second image content; The first image content has a first correlation with the target input data, and the second image content has a second correlation with the target image data.

4. The method according to claim 1, The first image and / or the second image contains target image content representing the target input data; the target image content has first image parameters in the first image, and the target image content has second image parameters in the second image, and the first image parameters are different from the second image parameters.

5. The method according to claim 4, The target input data is text data; The target image content is the text data.

6. The method according to claim 5, The text data has a first display disorder in the first image; The text data has a second display disorder in the second image.

7. The method according to claim 1, The first image is image data output by the target intelligent engine in the first stage; The second image is image data output by the target intelligent engine in the second stage; The target image data is the image data finally output by the target intelligent engine.

8. The method according to claim 1, further comprising: Performing feature analysis on the target input data to obtain keyword features; determining an association weight between the keyword feature and a process of generating target image data by the target intelligent engine; The target image sequence is adjusted based on the association weight to obtain an adjusted target image sequence.

9. The method according to claim 1, wherein displaying the target image sequence comprises: Obtaining style information corresponding to the target input data; adjusting display parameters corresponding to the target image sequence according to the style information; Based on the adjusted display parameters, the target image sequence is displayed.

10. A display device comprising: a first display module for displaying a target image sequence in response to an interaction operation instructing input of target input data into a target intelligent engine to generate image data; The second display module is used to display the target image data in response to the target intelligent engine generating the target image data; wherein the target image sequence includes at least a first image and a second image; the first image and / or the second image are associated with the target input data.

Images