Full-automatic poster making device and method, electronic equipment and medium thereof

Through the fully automatic poster production device, using large language model and image generation technology, combined with spatial analysis, the problem of time-consuming and lack of intelligence in text generation and layout in the existing technology is solved, and fast, automatic and efficient poster generation is achieved. Improves creativity quality and efficiency.

CN119006656APending Publication Date: 2024-11-22SHANGHAI SHUHENG INFORMATION TECH CO LTD
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202410394075.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-04-02
Publication Date
2024-11-22

AI Technical Summary

Technical Problem

In the prior art, the model of generating images fails to effectively deal with problems related to generating text content, resulting in the text generation and layout process being time-consuming and lacking intelligence and automation, making it difficult to meet the needs of fast and personalized content.

Method used

Using fully automatic poster production devices and methods, combining large language models, generative adversarial networks (GANs) and spatial analysis technology, the user interface module collects requirements, and the text generation module generates context-compatible copy, and the prompt word generation module extracts keywords. The image generation module generates image content, the spatial analysis module recognizes the best text position, the text adaptation and layout module adjusts the font and layout, and the output module integrates the output module to generate posters.

Benefits of technology

Fast, automatic and precise text generation and typography are achieved, improving efficiency and creative quality, reducing design difficulty and cost, and ensuring personalization and brand consistency of content.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119006656A_ABST
    Figure CN119006656A_ABST
Patent Text Reader

Abstract

The invention relates to a full-automatic poster making device and method, electronic equipment and a medium thereof, and the device comprises a user interface module which provides an interactive interface for a user; the text generation module is used for understanding the requirements of the user by using a large language model technology and generating copywriting conforming to the context according to the requirements; the cue word generation module is used for further processing the copywriting provided by the text generation module and extracting core keywords capable of guiding image creation; the image generation module is used for generating image content conforming to the copywriting theme according to the cue word; the spatial analysis module is used for identifying the optimal spatial position for placing the text on the image through an image processing and analysis technology; the text adapting and typesetting module is used for further adapting and designing the text according to a spatial analysis result; the output module is used for finally generating a designed and edited poster; according to the method, the text can be quickly, automatically and accurately generated and typeset, and the problems of low time efficiency and creativity limitation in manual poster making are solved.
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a fully automatic poster making device, method, electronic equipment and medium thereof. [Background Technology]

[0002] With the development of artificial intelligence and natural language processing technology, image generation can be automated through models such as generative adversarial networks (GANs). However, the generative models in the existing technology mainly focus on the automatic generation of graphics, images or video content, and fail to effectively deal with the problems related to generating text content. Traditional text generation, such as articles, reports or any scenario that requires structured text, still requires a lot of manual participation, including text creation, editing and typesetting.

[0003] These traditional methods are not only time-consuming, but may not meet the rapidly evolving content needs, especially in real-time and large-scale personalized content generation application scenarios. In addition, the existing text editing and typesetting software also mainly relies on user input and lacks intelligence and automation, which limits the efficiency and creative ability of users.

[0004] Therefore, there is currently a need to be able to quickly, automatically and accurately generate and typeset text. [Summary of the invention]

[0005] The purpose of the present invention is to provide a fully automatic poster making device, method, electronic device and medium thereof, which can quickly, automatically and accurately generate and typeset text, and solve the problems of low time efficiency and creativity limitation in manual poster making.

[0006] In one aspect, the present invention provides a fully automatic poster making device, comprising:

[0007] A user interface module is used to provide an interactive interface for users;

[0008] The text generation module uses large language model technology to understand user needs and generate contextual copy based on the needs;

[0009] The prompt word generation module is used to further process the copy provided by the text generation module and extract the core keywords that can guide image creation;

[0010] An image generation module, which uses computer vision technology, including but not limited to generative adversarial networks (GANs), to generate image content that matches the theme of the copy based on the prompt words;

[0011] A spatial analysis module for identifying the best spatial location for placing text on an image through image processing and analysis techniques;

[0012] The text adaptation and typesetting module is used to further adapt and design the text according to the results of spatial analysis;

[0013] Output module for rendering posters incorporating text and images into electronic formats or print-ready files.

[0014] In a possible implementation, the user interface module allows the user to specify parameters including but not limited to the theme, style, text requirements and size of the poster, and the interface of the user interface module adopts a graphical or text input form.

[0015] In another possible implementation, the text adaptation and typesetting module determines the font size, style and final typesetting layout of the text according to the dimensions of the blank area, so that the text content is naturally integrated into the image and the effect of information dissemination is enhanced.

[0016] In another aspect, the present invention provides a fully automatic poster making method, comprising the following steps:

[0017] 1) Requirements collection: Users input specific requirements for posters through the user interface module;

[0018] 2) Text creation: The text generation module receives user requirements as input and generates contextually appropriate copy based on the requirements by running a large language model;

[0019] 3) Prompt word generation: Based on the generated text content, the large language model continues to generate prompt words for image creation to guide the image generation module to generate visual elements that fit the content;

[0020] 4) Image creation: The image generation module uses the generative adversarial network (GANs) technology to generate image content that matches the text based on the prompt words;

[0021] 5) Analyze image space: Use image processing techniques to find blank areas in the generated image that are suitable for placing text;

[0022] 6) Text adaptation and layout: Determine the font size, style and final layout of the text based on the dimensions of the blank area, so that the text content is naturally integrated into the image;

[0023] 7) Final output: The designed and edited poster is finally generated by the output module.

[0024] In a possible implementation, in step 1), the specific requirements of the poster include but are not limited to the theme, style guide, text content and size of the poster. The user interface module is responsible for collecting all user inputs and converting these information formats into input data for subsequent processing steps.

[0025] In another possible implementation, in step 5), areas suitable for text layout are identified, and size characteristics of these areas are calculated to provide necessary information for text adaptation so that the text can be integrated into the image without interfering with visual elements of the image.

[0026] In another possible implementation, in step 6), the text adaptation step is to adjust the font, size and content length of the text according to the blank area information provided by the spatial analysis module to ensure that it fits the blank area in the image while maintaining visual harmony with the overall image.

[0027] In other possible embodiments, in step 6), the text layout step is that the processed text will be rendered and placed in the designated blank area of ​​the image. This step takes into account the alignment, spacing and layout balance of the text to ensure that the visual effect of the text elements in the poster is consistent with the overall design.

[0028] In a third aspect of the present invention, an electronic device is proposed, comprising a memory and a processor, wherein the memory stores a program executable on the processor, and when the program is executed by the processor, the electronic device implements the above method.

[0029] According to a fourth aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a program, and when the program is executed by a processor, the above method is implemented.

[0030] Compared with the prior art, the present invention has the following advantages:

[0031] (1) Improved efficiency: The present invention reduces the time required for manual participation in text creation, image design, and typesetting through an automated process, which means that posters can be produced more quickly and has a significant efficiency advantage in generating large amounts of personalized content;

[0032] (2) Improving creative quality: The large language model and image generation model of the present invention can generate a variety of creative text and image options based on a given input, from which users can choose or further customize, thereby improving the innovation and attractiveness of the final work;

[0033] (3) Reduce design difficulty: The present invention reduces the technical threshold for designing posters. Even non-professionals can use the system to create high-quality visual works, thus broadening the audience range of creation.

[0034] (4) Consistency and coordination: The present invention ensures that the text content is visually coordinated with the image elements through automatic analysis and adjustment, which helps maintain brand consistency and enhances the visual sense of integrity;

[0035] (5) Flexibility and customizability: The present invention allows users to customize input parameters, including text style, image theme, etc., thereby providing a high degree of customizability to meet different design requirements;

[0036] (6) Adaptive design: The text length and font size of the present invention can automatically adapt to the blank area of ​​the image, thereby optimizing space utilization and visual comfort, eliminating the need for complex manual adjustment processes;

[0037] (7) Cost savings: The automated poster generation of the present invention replaces professional design human resources and reduces design costs, which is an important cost benefit, especially for companies that require a large amount of content;

[0038] In summary, the invention can integrate the latest AI technology to automate the creative content production process, generate high-quality, attractive and brand and purpose-consistent design works, while reducing the user's workload, reducing costs, and providing personalized and efficient design solutions; through advanced technologies such as large language models, image generation models and spatial analysis models, it can quickly, automatically and accurately generate and typeset text, solving the problems of time inefficiency and creative limitations in hand-made posters. [Drawings]

[0039] Figure 1 It is a schematic flow diagram of the method of the present invention;

[0040] Figure 2 It is a structural schematic diagram of the device of the present invention;

[0041] Figure 3 It is a schematic diagram of the principle of the present invention;

[0042] Figure 4 It is a structural schematic diagram of the electronic device of the present invention. [Specific implementation method]

[0043] References to "one embodiment" or "some embodiments" etc. described in this specification mean that a particular feature, structure or characteristic described in conjunction with the embodiment is included in one or more embodiments of the present invention. Thus, the phrases "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. appearing in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0044] In order to make the purpose, technical solutions and advantages of the present invention more clear, the present invention will be further described below in conjunction with the accompanying drawings and specific embodiments:

[0045] By integrating advanced technologies such as large language models, image generation models and spatial analysis models, the present invention can quickly, automatically and accurately generate and typeset text, solving the problems of low time efficiency and creative limitations in handmade posters.

[0046] As attached Figure 2 As shown, in some embodiments, the present invention provides a fully automatic poster production device, including: a user interface module, used to provide an interactive interface for users; a text generation module, used to use large language model technology to understand user needs and generate contextual copy according to the needs; a prompt word generation module, used to further process the copy provided by the text generation module, and extract core keywords that can guide image creation; an image generation module, used to use computer vision technology, including but not limited to generative adversarial networks GANs, to generate image content that conforms to the theme of the copy according to the prompt words; a spatial analysis module, used to identify the best spatial position for placing text on the image through image processing and analysis technology; a text adaptation and typesetting module, used to further adapt and design the text according to the results of spatial analysis; an output module, used to render the poster integrating text and image into an electronic format or a file ready for printing.

[0047] In some other embodiments, the main components of the fully automatic poster making device of the present invention are as follows:

[0048] 1. User interface module: Provides a user-friendly interactive interface that allows users to specify the poster's theme, style, text requirements, size and other parameters in detail. The interface can be graphical or in text input form, ensuring that users can easily convey their design intent.

[0049] 2. Text generation module: Using advanced large language model technology, it intelligently generates attractive titles, rich and accurate content and other necessary text descriptions based on user input. This module is specially designed to understand user needs and creatively generate contextual copy based on needs.

[0050] 3. Prompt word generation module: further processes the text provided by the text generation module to extract core keywords that can guide image creation.

[0051] 4. These cues are the input to the image generation module, which uses the latest image generation techniques, such as Generative Adversarial Networks (GANs), to generate high-quality, visually appealing images that match the text content.

[0052] 5. Spatial Analysis Module: Uses sophisticated image processing and analysis techniques to identify the best spatial location for text placement on the image. This module ensures that the text fits into the image without interfering with the main visual elements of the image. This step is critical to maintaining the overall aesthetic of the poster.

[0053] 6. Text adaptation and layout module: further adapt and design the text according to the results of spatial analysis. This involves determining the font size, style and final layout of the text according to the dimensions of the blank area, so that the text content can be naturally integrated into the image and enhance the effect of information dissemination.

[0054] 7. Output module: responsible for rendering the poster with integrated text and images into electronic format or ready-to-print files. This module ensures that the output poster maintains high resolution and printing quality, meeting users' expectations for professional quality.

[0055] As attached Figure 1 As shown, in some other embodiments, the present invention provides a fully automatic poster making method, comprising the following steps:

[0056] 1) Requirements collection: Users input specific requirements for posters through the user interface module;

[0057] 2) Text creation: The text generation module receives user requirements as input and generates contextually appropriate copy based on the requirements by running a large language model;

[0058] 3) Prompt word generation: Based on the generated text content, the large language model continues to generate prompt words for image creation to guide the image generation module to generate visual elements that fit the content;

[0059] 4) Image creation: The image generation module uses the generative adversarial network (GANs) technology to generate image content that matches the text based on the prompt words;

[0060] 5) Analyze image space: Use image processing techniques to find blank areas in the generated image that are suitable for placing text;

[0061] 6) Text adaptation and layout: Determine the font size, style and final layout of the text based on the dimensions of the blank area, so that the text content is naturally integrated into the image;

[0062] 7) Final output: The designed and edited poster is finally generated by the output module.

[0063] In other embodiments, the fully automatic poster making method of the present invention has the following detailed steps:

[0064] (1) Requirements collection: Users input the specific requirements of their posters, such as theme, style guide, text content, and poster size, through a customized user interface; this module is responsible for collecting all user inputs and formatting this information into input data for subsequent processing steps.

[0065] (2) Text creation: The text generation module receives user requirements as input and runs a large language model to automatically generate creative and topic-related titles, main text, and other necessary explanatory text; the generated text will be initially reviewed to ensure that it meets the content and quality standards.

[0066] (3) Prompt word generation: Based on the generated text content, the large language model will continue to generate prompt words for image creation. These prompt words closely reflect the theme of the text content to guide the image generation module to generate visual elements that fit the content.

[0067] (4) Image creation: The image generation module uses technologies such as generative adversarial networks (GANs) to synthesize images based on prompt words; this module adjusts multiple visual elements such as color, style, texture, etc. to generate image content that is closely related to the text topic.

[0068] (5) Analyze image space: This module uses image processing technology to find blank areas in the generated image that are suitable for placing text; it identifies areas suitable for text layout and calculates the size characteristics of these areas to provide necessary information for text adaptation.

[0069] (6) Text and space adaptation: The text adaptation and typesetting module adjusts the font, size, and content length of the text based on the blank area information provided by the spatial analysis module to ensure that they can properly fit into the blank area of ​​the image while maintaining visual harmony with the overall image.

[0070] (7) Text layout: The processed text will be rendered and carefully placed in the designated blank area of ​​the image. This step takes into account the alignment, spacing and layout balance of the text to ensure that the visual effect of the text elements in the poster is consistent with the overall design.

[0071] (8) Final output: The designed and edited poster will be finally generated by the output module. Users can choose to save it in digital format or print it out for further use; this module supports various output formats to meet different purposes and quality requirements.

[0072] The working principle of the present invention is: based on advanced artificial intelligence technology, including natural language processing (NLP) and computer vision; through the information collected by the user interface module, the text generation module and the prompt word generation module use a large language model to intelligently create copy and keywords to guide image generation; the image generation module uses computer vision technology, especially models such as Conditional GANs, and uses the generated prompt words to create image content that matches the copy theme.

[0073] The present invention is further described below with reference to specific cases:

[0074] Embodiment: Xiao Zhang is a music teacher at a community middle school. She wants to make a poster to promote an upcoming school concert. Although music is Xiao Zhang's strong point, with the help of the automatic poster creation device of the present invention, she can also easily become a poster design expert.

[0075] 1. Input promotional information: Xiao Zhang enters relevant information about the concert in the user interface, including the event name "Community Middle School Annual Concert", time, location, performers and other basic information.

[0076] 2. Automatic copywriting: After Xiao Zhang clicks the "Generate Copywriting" button, the text generation module uses the large language model (AI) to automatically conceive a series of creative titles and content based on the input information; for example: "A feast of harmony and melody, if you miss it, you will have to wait another year."

[0077] 3. Generate image prompt words: After the text is determined, the system will automatically extract keywords and generate image prompt words, such as "children playing musical instruments", "joyful audience", "grand concert stage".

[0078] 4. Image production: Next comes the time for the image generation module to work. It creates patterns and backgrounds that match the theme of the concert based on the prompts, such as a stage on a quiet night or a picture of a group of children playing enthusiastically.

[0079] 5. Matching text and images: At this point, the spatial analysis module will analyze these images and find the most suitable location for inserting text; the system will prompt that there is a sky background area that is very suitable for placing title text.

[0080] 6. Text layout and design: The text adaptation and layout module automatically selected a font that is suitable for the night stage theme and easy to read for Xiao Zhang, and made precise adjustments to the copy to ensure that the text neither blocks the main elements of the picture nor clearly displays all necessary information.

[0081] 7. Output and sharing: Xiao Zhang, who is satisfied, clicks the "Generate Poster" button, and the system generates a professional promotional poster. Xiao Zhang can choose to save it as an electronic poster or print it directly, and easily promote it in the community and school.

[0082] Through the above specific embodiments, it can be seen that the automatic poster creation device of the present invention provides a convenient and efficient solution for non-design professionals such as Xiao Zhang to produce professional-level posters.

[0083] In some other embodiments of the present invention, an electronic device is disclosed, as shown in the attached Figure 4 As shown, the electronic device includes a processor and a memory, the processor and the memory are connected via a bus, and the memory stores a program that can be run on the processor. When the program is executed by the processor, the electronic device implements the above method. Specifically, the hardware composition of the electronic device includes: one or more processors 401; memory 402; display 403; one or more application programs (not shown); and one or more computer programs 404, and the above devices can be connected via one or more communication buses 405. The one or more computer programs 404 are stored in the above memory 402 and are configured to be executed by the one or more processors 401, and the one or more computer programs 404 include instructions.

[0084] The present invention also provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a computer, the method described in the above method embodiment is implemented. Specific beneficial effects can be found in the above method embodiment.

[0085] The present invention also provides a computer program product, which implements the method described in the above method embodiment when executed by a computer. Specific beneficial effects can be found in the above method embodiment.

[0086] Through the description of the above implementation methods, technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. The specific working process of the system, device and unit described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0087] Each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0088] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: flash memory, mobile hard disk, read-only memory, random access memory, disk or optical disk and other media that can store program codes.

[0089] The above embodiments are only used to illustrate the technical solutions of the present invention, but not to limit it. Under the idea of ​​the present invention, the technical features in the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other changes in different aspects of the present invention as described above. Although the present invention is described in detail with reference to the above embodiments, it should be understood by those skilled in the art that the technical solutions described in the above embodiments can still be modified, or some of the technical features can be replaced by equivalents. However, these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application.

[0090] The present invention is not limited to the above-mentioned implementation modes, and any other changes, modifications, substitutions, combinations, and simplifications made without departing from the spirit and principle of the present invention shall be equivalent replacement modes and shall be included in the protection scope of the present invention.

Claims

1. A fully automatic poster making device, characterized in that: include: A user interface module is used to provide an interactive interface for users; The text generation module uses large language model technology to understand user needs and generate contextual copy based on the needs; The prompt word generation module is used to further process the copy provided by the text generation module and extract the core keywords that can guide image creation; An image generation module, which uses computer vision technology, including but not limited to generative adversarial networks (GANs), to generate image content that matches the theme of the copy based on the prompt words; A spatial analysis module for identifying the best spatial location for placing text on an image through image processing and analysis techniques; The text adaptation and typesetting module is used to further adapt and design the text according to the results of spatial analysis; Output module for rendering posters incorporating text and images into electronic formats or print-ready files.

2. The device according to claim 1, characterized in that: The user interface module allows the user to specify parameters including but not limited to the theme, style, text requirements and size of the poster. The interface of the user interface module adopts a graphical or text input form.

3. The device according to claim 1, characterized in that: The text adaptation and typesetting module determines the font size, style and final typesetting layout of the text according to the dimensions of the blank area, so that the text content is naturally integrated into the image and the effect of information dissemination is enhanced.

4. A fully automatic poster making method, characterized in that: The following steps are involved: 1) Requirements collection: Users input specific requirements for posters through the user interface module; 2) Text creation: The text generation module receives user requirements as input and generates contextually appropriate copy based on the requirements by running a large language model; 3) Prompt word generation: Based on the generated text content, the large language model continues to generate prompt words for image creation to guide the image generation module to generate visual elements that fit the content; 4) Image creation: The image generation module uses the generative adversarial network (GANs) technology to generate image content that matches the text based on the prompt words; 5) Analyze image space: Use image processing techniques to find blank areas in the generated image that are suitable for placing text; 6) Text adaptation and layout: Determine the font size, style and final layout of the text based on the dimensions of the blank area, so that the text content is naturally integrated into the image; 7) Final output: The designed and edited poster is finally generated by the output module.

5. The method according to claim 4, characterized in that: In step 1), the specific requirements of the poster include but are not limited to the theme, style guide, text content and size of the poster. The user interface module is responsible for collecting all user inputs and converting these information formats into input data for subsequent processing steps.

6. The method according to claim 4, characterized in that: In step 5), areas suitable for text layout are identified, and the size characteristics of these areas are calculated to provide necessary information for text adaptation so that the text can be integrated into the image without interfering with the visual elements of the image.

7. The method according to claim 4, characterized in that: In step 6), the text adaptation step is to adjust the font, size and content length of the text according to the blank area information provided by the spatial analysis module to ensure that it fits the blank area in the image while maintaining visual harmony with the overall image.

8. The method according to claim 4, characterized in that: In step 6), the text layout step is that the processed text will be rendered and placed in the designated blank area of ​​the image. This step takes into account the alignment, spacing and layout balance of the text to ensure that the visual effect of the text elements in the poster is consistent with the overall design.

9. An electronic device, characterized in that: The electronic device comprises a memory and a processor, wherein the memory stores a program executable on the processor, and when the program is executed by the processor, the electronic device implements the method as claimed in any one of claims 4 to 8.

10. A computer-readable storage medium, wherein a program is stored in the computer-readable storage medium, characterized in that: When the program is executed by a processor, the method according to any one of claims 4 to 8 is implemented.

Citation Information

Cited By

  • Poster generation method and device, computer equipment and storage medium

    CN120278767A