Image-text content generation method and device

Abstract

The embodiment of the invention provides an image-text content generation method and device.The image-text content generation method comprises the steps that when image-text content is generated based on an original text, the original text is segmented, and at least two text segments are obtained; and generating a text outline corresponding to the at least two text segments according to the text type of the original text to realize outline generation of the original text. An initial text is generated based on the text schema and the at least two text segments, and a text image is generated for the text schema and the initial text. And integrating the text outline, the initial text and the text image to obtain the target image-text content. And the generation efficiency and quality of the target image-text content are improved.

Description

Technical Field

[0001] The embodiments of this specification relate to the field of computer technology, and particularly to a method and device for generating graphic and text content. Background Art

[0002] With the rapid development of the Internet and new media, graphic and text content has become an important carrier for information dissemination and brand building. However, the traditional way of producing graphic and text content relies on manual writing, review, and typesetting, which is inefficient and costly. In recent years, the rapid development of artificial intelligence technology has brought new possibilities to the production of graphic and text content. In particular, generative AI technologies, such as natural language processing (NLP), computer vision (CV), and deep learning, enable machines to simulate the human creative process and generate high-quality text and image content.

[0003] In the prior art, there are already some AI-based graphic and text content generation tools, such as automatic abstract systems, text generation models (such as GPT series), and image generation models (such as DALL-E, Stable Diffusion). However, these tools often only focus on a single link (such as only generating text or images), and the generation efficiency is low, and it is impossible to guarantee the quality of the generated graphic and text content. Therefore, there is an urgent need for a more effective method for generating graphic and text content to solve the above problems. Summary of the Invention

[0004] In view of this, the embodiments of this specification provide a method for generating graphic and text content. One or more embodiments of this specification also relate to a device for generating graphic and text content, a computing device, a computer-readable storage medium, and a computer program product to solve the technical defects existing in the prior art.

[0005] According to the first aspect of the embodiments of this specification, a method for generating graphic and text content is provided, including: Segment the original text to obtain at least two text segments; Generate a text outline corresponding to the at least two text segments according to the text type of the original text, and generate an initial text based on the text outline and the at least two text segments; Generate a text image for the text outline and the initial text, and integrate the text outline, the initial text, and the text image to obtain the target graphic and text content.

[0006] Optionally, before segmenting the original text to obtain at least two text segments, it further includes: Determine the text to be processed, and detect redundant information in the text to be processed; Remove the redundant information in the text to be processed according to the detection result to obtain the original text.

[0007] Optionally, after segmenting the original text to obtain at least two text segments, the method further includes: Performing content detection on the original text, and if the original text passes the content detection, generating a text outline corresponding to the at least two text segments according to the text type of the original text.

[0008] Optionally, generating a text outline corresponding to the at least two text segments according to the text type of the original text includes: Determining the content theme and text style of the original text, and using the content theme and the text style as the text type; Selecting a graphic and text generation module based on the text type, and using the graphic and text generation module to generate the text outline based on the original text and the at least two text segments.

[0009] Optionally, after generating an initial text based on the text outline and the at least two text segments, the method further includes: Determining expandable text in the initial text; Performing a network search based on the expandable text to obtain extended text corresponding to the initial text; Integrating the text outline, the initial text, and the text image to obtain target graphic and text content includes: Integrating the extended text, the text outline, the initial text, and the text image to obtain the target graphic and text content.

[0010] Optionally, generating a text image for the text outline and the initial text includes: Generating a cover image based on the text outline, and determining at least one chapter information included in the initial text; Extracting chapter text corresponding to each chapter information from the initial text; Generating a chapter image for each chapter text, and using the cover image and each chapter image as the text image.

[0011] Optionally, after generating a text image for the text outline and the initial text, the method further includes: Extracting annotatable content from the initial text and the text image; Generating annotation text for the annotatable content; Integrating the text outline, the initial text, and the text image to obtain target graphic and text content includes: Integrating the annotation text, the text outline, the initial text, and the text image to obtain the target graphic and text content.

[0012] Optionally, after integrating the text outline, the original text, and the text image to obtain the target graphic content, the method further includes: Performing content review and format review on the target graphic content; When the content review and the format review are passed, storing the target graphic content in a database.

[0013] According to a second aspect of the embodiments of the present specification, there is provided a graphic content generation device, including: A segmentation module configured to segment the original text to obtain at least two text segments; A generation module configured to generate a text outline corresponding to the at least two text segments according to the text type of the original text, and generate an original text based on the text outline and the at least two text segments; An integration module configured to generate a text image for the text outline and the original text, and integrate the text outline, the original text, and the text image to obtain the target graphic content.

[0014] According to a third aspect of the embodiments of the present specification, there is provided a computing device, including: A memory and a processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of the above-mentioned graphic content generation method are implemented.

[0015] According to a fourth aspect of the embodiments of the present specification, there is provided a computer-readable storage medium storing computer-executable instructions, and when the instructions are executed by a processor, the steps of the above-mentioned graphic content generation method are implemented.

[0016] According to a fifth aspect of the embodiments of the present specification, there is provided a computer program product including a computer program or instructions, and when the computer program or instructions are executed by a processor, the steps of the above-mentioned graphic content generation method are implemented.

[0017] In the graphic content generation method provided by an embodiment of the present specification, when generating graphic content based on the original text, the original text is segmented to obtain at least two text segments. A text outline corresponding to the at least two text segments is generated according to the text type of the original text, so as to generate an outline for the original text. An original text is generated based on the text outline and the at least two text segments, and a text image is generated for the text outline and the original text. The text outline, the original text, and the text image are integrated to obtain the target graphic content. The generation efficiency and quality of the target graphic content are improved. Description of the Drawings

[0018] Figure 1 It is a schematic diagram of a method for generating graphic content provided by an embodiment of this specification; Figure 2 It is a flowchart of a method for generating graphic content provided by an embodiment of this specification; Figure 3 It is a flowchart of a processing procedure of a method for generating graphic content provided by an embodiment of this specification; Figure 4 It is a schematic structural diagram of a device for generating graphic content provided by an embodiment of this specification; Figure 5 It is a structural block diagram of a computing device provided by an embodiment of this specification. Detailed implementation manners

[0019] In the following description, numerous specific details are set forth in order to provide a thorough understanding of this specification. However, this specification can be implemented in many other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the connotation of this specification. Therefore, this specification is not limited by the specific implementations disclosed below.

[0020] The terms used in one or more embodiments of this specification are for the purpose of describing specific embodiments only and are not intended to limit one or more embodiments of this specification. The singular forms "a", "the", and "said" used in one or more embodiments of this specification and the appended claims are also intended to include the plural forms unless the context clearly dictates otherwise. It should also be understood that the term "and / or" used in one or more embodiments of this specification refers to and includes any or all possible combinations of one or more of the associated listed items.

[0021] It should be understood that although the terms first, second, etc. may be used in one or more embodiments of this specification to describe various information, such information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of one or more embodiments of this specification, the first can also be referred to as the second, and similarly, the second can also be referred to as the first. Depending on the context, the word "if" as used herein can be interpreted as "when" or "while" or "in response to determining".

[0022] In addition, it should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in one or more embodiments of this specification are all information and data authorized by the user or fully authorized by all parties. Moreover, the collection, use, and processing of relevant data need to comply with the relevant laws, regulations, and standards of the relevant countries and regions, and corresponding operation entrances are provided for users to choose to authorize or reject.

[0023] First, the noun terms involved in one or more embodiments of this specification are explained.

[0024] Generative AI: An artificial intelligence technology that can simulate the creative process of humans to generate brand-new and creative content such as text and images, rather than simply analyzing or identifying existing data.

[0025] Natural Language Processing (NLP): A branch of artificial intelligence that focuses on the interaction between computers and human languages, including tasks such as text analysis, text generation, language understanding, and language translation.

[0026] Computer Vision (CV): A branch of artificial intelligence that focuses on enabling computers to understand and interpret digital images and videos and extract useful information from them.

[0027] Text generation models (such as GPT series): Natural language processing models based on deep learning technology that can receive text inputs and generate coherent and natural text outputs, such as GPT, GPT-3, etc.

[0028] Image generation models (such as DALL-E, Stable Diffusion): Computer vision models based on deep learning technology that can generate corresponding image content according to text descriptions or other inputs, such as DALL-E, Stable Diffusion, etc.

[0029] Currently, the production of graphic and text content faces problems such as low efficiency, high cost, and limited creativity. Traditional content production methods rely on a large number of manual edits, which are not only time-consuming and laborious but also difficult to quickly adapt to changes in market demands. Especially when dealing with a large amount of original content, how to efficiently and accurately screen, classify, and generate high-quality graphic and text content has become a major challenge. A graphic and text content generation method provided in one embodiment of this specification aims to introduce Generative AI technology to build an automated and intelligent graphic and text content production link to solve the above problems and improve the efficiency and quality of content production.

[0030] Figure 1The figure shows a schematic diagram of a graphic and text content generation method provided according to an embodiment of this specification. As Figure 1 shown, when generating graphic and text content based on the original text, the original text is segmented to obtain at least two text segments. At least two text outlines corresponding to the text segments are generated according to the text type of the original text, so as to realize the generation of an outline for the original text. An initial text is generated based on the text outline and at least two text segments, and a text image is generated for the text outline and the initial text. Integrating the text outline, the initial text, and the text image can obtain the target graphic and text content. Generating the target graphic and text content with higher readability and equipped with text images based on the original text can improve the generation efficiency and quality of the target graphic and text content and improve the readability of the original text.

[0031] In this specification, a graphic and text content generation method is provided. This specification also relates to a graphic and text content generation device, a computing device, a computer-readable storage medium, and a computer program product, which will be described in detail one by one in the following embodiments.

[0032] See Figure 2 , Figure 2 The figure shows a flowchart of a graphic and text content generation method provided according to an embodiment of this specification, which specifically includes the following steps.

[0033] Step 202: Segment the original text to obtain at least two text segments.

[0034] Specifically, the original text can be network text content obtained through network retrieval, such as news, books, newspapers, papers, articles, or text content obtained by extracting text from video and audio content. When segmenting the original text, it can be segmented according to a preset number of characters. In practical applications, segmenting the original text according to the paragraph character count can obtain at least two text segments.

[0035] Furthermore, before segmenting the original text, since there may be redundant information in the text to be processed corresponding to the original text, redundant information detection can be performed on the text to be processed to remove the redundant information in the text to be processed to obtain the original text. The specific implementation is as follows: Determine the text to be processed, and perform redundant information detection on the text to be processed; remove the redundant information in the text to be processed according to the detection result to obtain the original text.

[0036] Specifically, the text to be processed can be text content containing redundant information. The redundant information can be repeated content contained in the text to be processed. The detection result can be a marking result obtained by marking the redundant information contained in the text to be processed.

[0037] Based on this, obtain text content such as books, newspapers, articles, etc. as the text to be processed. Perform redundant information detection on the text to be processed to detect whether the text to be processed contains redundant information. In the case where redundant information is detected in the text to be processed, remove the redundant information from the text to be processed to obtain the original text.

[0038] For example, in the scenario of generating graphic and text content, text content such as books, newspapers, articles, news, etc. can be obtained as the text to be processed. In the case where the text to be processed is a thesis, use NLP technology to perform redundant information detection on the thesis. In the case where redundant information is detected in the thesis, remove the redundant information to obtain the original text.

[0039] In summary, by removing redundant information from the text to be processed, the readability of the text is improved.

[0040] Step 204: Generate a text outline corresponding to the at least two text segments according to the text type of the original text, and generate an initial text based on the text outline and the at least two text segments.

[0041] Specifically, after segmenting the original text as described above to obtain at least two text segments, a text outline corresponding to the at least two text segments can be generated according to the text type of the original text, and an initial text can be generated based on the text outline and the at least two text segments. Here, the text type refers to the article type of the original text, and the literary style types include but are not limited to news, books, newspapers. The text type can also be the literary style type of the original text, and the literary style types include but are not limited to prose, narrative, argumentative essays, etc. The text outline can be the article outline of the original text or the text abstract of the original text. The initial text refers to the main text content obtained by performing text extraction on the original text, and the text content corresponding to the initial text can be calculated based on a preset ratio. The preset ratio can be the text content ratio set for the original text.

[0042] Based on this, after segmenting the original text as described above to obtain at least two text segments, determine the text type of the original text. Generate a text outline corresponding to the at least two text segments according to the text type of the original text. Generate an initial text corresponding to the original text based on the text outline, the preset ratio, and the at least two text segments.

[0043] Furthermore, considering that not all text content contained in any original text can be directly used for subsequent graphic and text content generation, before performing subsequent processing based on the original text, content detection of the original text is also required. The specific implementation is as follows: Perform content detection on the original text. In the case where the original text passes the content detection, execute generating a text outline corresponding to the at least two text segments according to the text type of the original text.

[0044] Specifically, content detection is used for pre-auditing and quality control of the original text, and can detect the copyright compliance, text content compliance, and logical coherence of the original text.

[0045] Based on this, content detection is performed on the original text, including detecting the copyright compliance and content compliance of the original text, as well as the logical coherence of the content. When the original text passes the content detection, at least two text outlines corresponding to the text segments can be generated according to the text type of the original text.

[0046] In summary, by performing content detection on the original text, the copyright compliance and text content compliance of the original text for subsequent graphic and text content generation can be ensured.

[0047] Furthermore, considering the original texts with different content themes and text styles, the subsequent processing methods are also different. Therefore, before continuing to process at least two text segments, it is necessary to determine the content theme and text style of the original text. The specific implementation is as follows: Determine the content theme and text style of the original text, and use the content theme and the text style as the text type; select a graphic and text generation module based on the text type, and use the graphic and text generation module to generate the text outline based on the original text and the at least two text segments.

[0048] Specifically, the content theme refers to the text theme corresponding to the original text, which can be the described object; the text style refers to the writing style of the original text, or can also refer to the writing style of the original text, that is, the writing style, including the characteristics in terms of word usage, sentence patterns, rhetorical devices, etc. The graphic and text generation module corresponds to the graphic and text production link and has the function of generating graphic and text content based on the original text and at least two text segments. The graphic and text generation module includes an outline extraction model, a text generation model, and an image generation model. The outline extraction model is used to generate the text outline, and the text generation model is used to generate the initial text.

[0049] Based on this, the content theme and text style of the original text are determined through semantic understanding and semantic analysis of the original text. The content theme and text style are used as the text type. A graphic and text generation module that matches the content theme and text style of the original text is selected based on the text type, and the graphic and text generation module is used to generate the text outline based on the original text and at least two text segments.

[0050] Continuing with the above example, in the case where the original text is a weather news item, the content theme of the weather news is determined to be "weather forecast", and the text style is "humorous". Based on the content theme and text style of the original text, a graphic and text generation module is selected. Using the graphic and text generation module, an outline is generated for the weather news, and the following can be obtained: "On November 12th, the weather is sunny, with an east wind of level 3, gusts of 17 km / h, sunrise at 7:30, sunset at 16:56, a guide to preventing static electricity in autumn and winter, an inventory of autumn meteorological data, and a self-help guide for autumn and winter."

[0051] In summary, based on the content theme and text style of the original text, a graphic and text generation module is selected. Using the graphic and text generation module, a text outline is generated based on the original text and at least two text segments, improving the accuracy of text outline generation.

[0052] Step 206: Generate a text image for the text outline and the initial text, and integrate the text outline, the initial text, and the text image to obtain the target graphic and text content.

[0053] Specifically, after generating the text outlines corresponding to at least two text segments according to the text type of the original text and generating the initial text based on the text outlines and at least two text segments as described above, a text image can be generated for the text outline and the initial text, and the text outline, the initial text, and the text image can be integrated to obtain the target graphic and text content. Among them, the text image can include the content illustrations corresponding to the initial text and the cover image of the original text. The target graphic and text content is the graphic and text content corresponding to the original text. The positions of the text image and the initial text in the target graphic and text content are determined after typesetting.

[0054] Based on this, after generating the text outlines corresponding to at least two text segments according to the text type of the original text and generating the initial text based on the text outlines and at least two text segments, a text image is generated for the text outline and the initial text. After typesetting and integrating the text outline, the initial text, and the text image, the target graphic and text content is obtained.

[0055] In practical applications, the text image includes a cover image and chapter images. The cover image corresponds to the text outline, and the chapter images correspond to the text chapters included in the initial text. Each text chapter can correspond to at least one chapter image. The text image can also include a cover image and key point images. The cover image corresponds to the text outline, and the key point images correspond to the key points in the initial text. Each key point corresponds to a key point image.

[0056] Furthermore, considering that the generated target graphic and text content is a complete and readable graphic and text content, when generating the text image, in addition to generating the illustrations corresponding to the text, a cover image corresponding to the text outline can also be generated. The specific implementation is as follows: Generate a cover image based on the text outline, and determine at least one chapter information included in the initial text; extract the chapter text corresponding to each chapter information from the initial text; generate a chapter image for each chapter text, and use the cover image and each chapter image as the text images.

[0057] Specifically, the cover image can represent the main idea of the target graphic content, and the chapter image is used to represent the main idea of a chapter in the initial text.

[0058] Based on this, generate a cover image based on the main idea corresponding to the text outline. Determine at least one chapter information included in the initial text, and extract the chapter text corresponding to each chapter information from the initial text. Generate a chapter image for the main idea corresponding to each chapter text, and use the cover image and each chapter image as the text images.

[0059] In summary, use the cover image corresponding to the text outline and the chapter images corresponding to each chapter text as the text images, which improves the content richness of the subsequent generated target graphic content.

[0060] Furthermore, considering that the generated target graphic content needs to include the content of the original text and also needs to have rich knowledge, therefore, after generating the initial text, the initial text can be expanded with knowledge, and the specific implementation is as follows: Determine the expandable text in the initial text; perform a network search based on the expandable text to obtain the extended text corresponding to the initial text; integrate the text outline, the initial text, and the text images to obtain the target graphic content, including: integrating the extended text, the text outline, the initial text, and the text images to obtain the target graphic content.

[0061] Specifically, the expandable text refers to the text content in the initial text that can be expanded with knowledge, and the extended text is the extended knowledge obtained by performing a network search for the expandable text.

[0062] Based on this, determine the expandable text in the initial text. The expandable text can be professional content such as proper nouns or scientific phenomena in the initial text. Perform a network search based on the expandable text to obtain the extended text corresponding to the initial text. Integrate the extended text, the text outline, the initial text, and the text images to obtain the target graphic content. When typesetting the target graphic content, the extended text can be arranged on the side position of the page where the expandable text is located in the initial text.

[0063] Continuing with the above example, select the scientific phenomenon of "static electricity" in the initial text, obtain relevant content on the scientific phenomenon of "static electricity" through an online search, and use it as the extended text. When generating the target graphic content, add the extended text to the side position of the page where the word "static electricity" is located in the initial text.

[0064] In summary, perform an online search based on the extensible text in the initial text to obtain the extended text, thereby improving the knowledge richness of the target graphic content.

[0065] Furthermore, considering that the initial text is generated based on the original text, the original text may contain key information that is difficult to understand. Annotation content can be added to the key information to facilitate user reading and understanding. The specific implementation is as follows: Extract the annotatable content from the initial text and the text image; generate annotation text for the annotatable content; integrate the text outline, the initial text, and the text image to obtain the target graphic content, including: integrating the annotation text, the text outline, the initial text, and the text image to obtain the target graphic content.

[0066] Specifically, the annotatable content can be the key information in the initial text, and it is necessary to improve the readability of the key information by adding annotations. The annotation text is the annotation content corresponding to the annotatable content determined through search.

[0067] Based on this, select key information in the initial text and the text image, and use the key information as the annotatable content. Determine the annotation text through an online search for the annotatable content. Perform typesetting and integration on the annotation text, the text outline, the initial text, and the text image to obtain the target graphic content with a format convenient for reading.

[0068] Continuing with the above example, in the case where the word "gust of wind" in the initial text is detected as a keyword, a search can be performed for the word "gust of wind" to obtain annotation content about "gust of wind". After typesetting the annotation text, the text outline, the initial text, and the text image, they are integrated into the target graphic content.

[0069] In summary, generate annotation text for the initial text to improve the readability and content richness of the initial text.

[0070] Furthermore, before storing the target graphic content, content review and format review are also required to ensure that the content of the target graphic content is compliant and the format is beautiful. The specific implementation is as follows: Perform content review and format review on the target graphic content; in the case where the content review and the format review are passed, store the target graphic content in the database.

[0071] Based on this, content review and format review are performed on the target graphic and text content. Content review requires ensuring that the target graphic and text content does not contain sensitive words, and the images in the target graphic and text content do not contain illegal image content. When the content review and format review are passed, the target graphic and text content is stored in the database for publication or further use. When the content review and / or format review fails, the generation of the text outline, the initial text, and the text image is restarted until the generated target graphic and text content passes the content review and format review. When the number of times the target graphic and text content fails the content review and format review reaches the threshold, manual intervention can be carried out to detect the reasons for the repeated failure of the review.

[0072] Continuing with the above example, after generating the target graphic and text content, post-review and format verification are performed on the target graphic and text content. Manual or automatic review is performed on the generated target graphic and text content to ensure the content quality, and format verification is performed to ensure beautiful typesetting.

[0073] In summary, content review and format review are performed on the target graphic and text content to ensure the compliance of the content of the target graphic and text content, the beauty of the format, and improve the reading experience of users.

[0074] The graphic and text content generation method provided by an embodiment of this specification, when generating graphic and text content based on the original text, segments the original text to obtain at least two text segments. At least two text outlines corresponding to the text segments are generated according to the text type of the original text, realizing the generation of the outline of the original text. The initial text is generated based on the text outline and at least two text segments, and a text image is generated for the text outline and the initial text. Integrating the text outline, the initial text, and the text image can obtain the target graphic and text content. Improve the generation efficiency and quality of the target graphic and text content.

[0075] The following combines the attached Figure 3 , taking the application of the graphic and text content generation method provided by this specification in the generation of the graphic and text content corresponding to a book or periodical as an example, to further illustrate the graphic and text content generation method. Among them, Figure 3 FIG. shows a flowchart of the processing process of a graphic and text content generation method provided by an embodiment of this specification, specifically including the following steps.

[0076] Step 302: Detect redundant information in the text to be processed, and remove the redundant information in the text to be processed according to the detection result to obtain the original text.

[0077] In practical applications, the text to be processed can be public domain books, newspapers, foreign language content, and text content obtained by performing text recognition on videos and audios. The NLP technology is used to detect redundant information in the text to be processed, and the redundant information contained in the text to be processed is removed to obtain the original text.

[0078] Step 304: Segment the original text to obtain at least two text segments, and perform content detection on the at least two text segments. When the at least two text segments pass the content detection, determine the content theme and text style of the original text.

[0079] After obtaining the original text, segment the original text according to the number of words, and divide the original text into at least two text segments. Conduct a preliminary review on the at least two text segments respectively to determine whether the at least two text segments can be used in the subsequent production process. When the at least two text segments pass the detection, determine the content theme and style characteristics of the original text according to the content of the at least two text segments.

[0080] Step 306: Select a graphic and text generation module based on the content theme and text style, and use the graphic and text generation module to generate a text outline based on the original text and the at least two text segments.

[0081] According to the content theme and style characteristics of the original text, determine the subsequent processing module for the original text. In practical applications, a graphic and text generation module can be selected according to the content theme and style characteristics of the original text, and the graphic and text generation module can be used to generate subsequent graphic and text content. Based on the NLP technology provided by the graphic and text generation module, understand the main idea of the original text and generate an article outline for the original text, that is, a text outline.

[0082] Step 308: Generate an initial text based on the text outline and the at least two text segments, determine the expandable text in the initial text, and conduct a network search based on the expandable text to obtain the extended text corresponding to the initial text.

[0083] Use the text generation model provided by the graphic and text generation module to combine the text outline and the at least two text segments corresponding to the original text to generate the complete body text, that is, the initial text. Integrate a search engine to automatically conduct a network knowledge search based on the expandable text in the initial text, and write extended reading content, and use the extended reading content as the extended text of the initial text.

[0084] Step 310: Generate a text image for the text outline and the initial text.

[0085] Use the image generation model provided by the graphic and text generation module to generate a cover image and illustrations based on the text outline and the initial text, and use the cover image and illustrations as the text image.

[0086] In practical applications, when the original text contains multiple chapters, a cover image can be generated based on the text outline, and at least one chapter information included in the initial text can be determined. Extract the chapter text corresponding to each chapter information from the initial text, and generate a chapter image for each chapter text, and use the cover image and each chapter image as the text image.

[0087] Step 312: Extract annotatable content from the initial text and the text image, and generate annotation text for the annotatable content.

[0088] Automatically identify the key information contained in the initial text and the text image, generate annotation content, and enhance the readability of the text content.

[0089] Step 314: Integrate the extended text, the annotation text, the text outline, the initial text, and the text image to obtain the target graphic and text content.

[0090] Step 316: Conduct content review and format review on the target graphic and text content. When the content review and format review are passed, store the target graphic and text content in the database.

[0091] Ensure the content quality of the generated target graphic and text content through content review, and ensure the beautiful typesetting of the generated target graphic and text content through format review.

[0092] In summary, use generative AI technology to achieve automatic classification and generation of content, improve production efficiency and content quality. Through the graphic and text collaborative generation mechanism, ensure the matching degree and overall coordination of text and images. Through functions such as intelligent classification, collaborative generation, and copyright detection, ensure the personalization and creativity of the content. Integrate the copyright detection function to ensure that the generated content meets copyright requirements and reduce compliance risks.

[0093] Corresponding to the above method embodiment, this specification also provides an embodiment of a graphic and text content generation device. Figure 4 It shows a schematic structural diagram of a graphic and text content generation device provided by an embodiment of this specification. As Figure 4 shown, the device includes: The segmentation module 402 is configured to segment the original text to obtain at least two text segments; The generation module 404 is configured to generate a text outline corresponding to the at least two text segments according to the text type of the original text, and generate an initial text based on the text outline and the at least two text segments; The integration module 406 is configured to generate a text image for the text outline and the initial text, and integrate the text outline, the initial text, and the text image to obtain the target graphic and text content.

[0094] An optional embodiment, the segmentation module 402 is further configured to: Determine the text to be processed, and detect redundant information in the text to be processed; Remove the redundant information in the text to be processed according to the detection result to obtain the original text.

[0095] An optional embodiment, the generation module 404 is further configured to: Perform content detection on the original text, and in the case where the original text passes the content detection, execute generating a text outline corresponding to the at least two text segments according to the text type of the original text.

[0096] An optional embodiment, the generation module 404 is further configured to: Determine the content theme and text style of the original text, and use the content theme and the text style as the text type; Select an image - text generation module based on the text type, and use the image - text generation module to generate the text outline based on the original text and the at least two text segments.

[0097] An optional embodiment, the integration module 406 is further configured to: Determine extensible text in the initial text; Perform a network search based on the extensible text to obtain extended text corresponding to the initial text; Integrating the text outline, the initial text, and the text image to obtain target graphic - text content includes: Integrate the extended text, the text outline, the initial text, and the text image to obtain the target graphic - text content.

[0098] An optional embodiment, the integration module 406 is further configured to: Generate a cover image based on the text outline, and determine at least one chapter information included in the initial text; Extract chapter text corresponding to each chapter information in the initial text; Generate a chapter image for each chapter text, and use the cover image and each chapter image as the text image.

[0099] An optional embodiment, the integration module 406 is further configured to: Extract annotatable content from the initial text and the text image; Generate annotation text for the annotatable content; Integrating the text outline, the initial text, and the text image to obtain target graphic - text content includes: Integrate the annotation text, the text outline, the initial text, and the text image to obtain the target graphic - text content.

[0100] An optional embodiment, the integration module 406 is further configured to: Perform content review and format review on the target graphic and text content; When the content review and the format review are passed, store the target graphic and text content in a database.

[0101] When generating graphic and text content based on the original text, the graphic and text content generation device provided by an embodiment of this specification segments the original text to obtain at least two text segments. Generate at least two text outlines corresponding to the text segments according to the text type of the original text, so as to generate an outline for the original text. Generate an initial text based on the text outline and at least two text segments, and generate a text image for the text outline and the initial text. Integrate the text outline, the initial text and the text image to obtain the target graphic and text content. Improve the generation efficiency and quality of the target graphic and text content.

[0102] The above is a schematic solution of a graphic and text content generation device according to this embodiment. It should be noted that the technical solution of the graphic and text content generation device belongs to the same concept as the technical solution of the above graphic and text content generation method. For the details not described in the technical solution of the graphic and text content generation device, reference can be made to the description of the technical solution of the above graphic and text content generation method.

[0103] Figure 5 The structural block diagram of a computing device 500 provided by an embodiment of this specification is shown. The components of the computing device 500 include but are not limited to a memory 510 and a processor 520. The processor 520 is connected to the memory 510 through a bus 530, and a database 550 is used to store data.

[0104] The computing device 500 also includes an access device 540, which enables the computing device 500 to communicate via one or more networks 560. Examples of such networks include the Public Switched Telephone Network (PSTN), Local Area Network (LAN), Wide Area Network (WAN), Personal Area Network (PAN), or a combination of communication networks such as the Internet. The access device 540 may include one or more of any type of wired or wireless network interface (e.g., a network interface card (NIC)), such as an IEEE 802.11 Wireless Local Area Network (WLAN) wireless interface, a Worldwide Interoperability for Microwave Access (Wi-MAX) interface, an Ethernet interface, a Universal Serial Bus (USB) interface, a cellular network interface, a Bluetooth interface, a Near Field Communication (NFC) interface.

[0105] In one embodiment of the present specification, the above components of the computing device 500, as well as Figure 5 other components not shown, may also be connected to each other, for example, via a bus. It should be understood that Figure 5 the block diagram of the computing device shown is for illustrative purposes only and is not a limitation on the scope of the present specification. Those skilled in the art may add or replace other components as needed.

[0106] The computing device 500 can be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (e.g., a tablet computer, a personal digital assistant, a laptop computer, a notebook computer, a netbook, etc.), a mobile phone (e.g., a smartphone), a wearable computing device (e.g., a smartwatch, smart glasses, etc.), or other types of mobile devices, or a stationary computing device such as a desktop computer or a Personal Computer (PC). The computing device 500 can also be a mobile or stationary server.

[0107] Among them, the processor 520 is used to execute the following computer-executable instructions, which, when executed by the processor, implement the steps of the above-described graphic and text content generation method.

[0108] The above is a schematic solution of a computing device according to this embodiment. It should be noted that the technical solution of this computing device and the technical solution of the above-mentioned graphic and text content generation method belong to the same concept. For the details not described in detail in the technical solution of the computing device, reference can be made to the description of the technical solution of the above-mentioned graphic and text content generation method.

[0109] An embodiment of this specification also provides a computer-readable storage medium, which stores computer-executable instructions. When the computer-executable instructions are executed by a processor, the steps of the above-mentioned graphic and text content generation method are implemented.

[0110] The above is a schematic solution of a computer-readable storage medium according to this embodiment. It should be noted that the technical solution of this storage medium and the technical solution of the above-mentioned graphic and text content generation method belong to the same concept. For the details not described in detail in the technical solution of the storage medium, reference can be made to the description of the technical solution of the above-mentioned graphic and text content generation method.

[0111] An embodiment of this specification also provides a computer program product, including a computer program or instructions. When the computer program or instructions are executed by a processor, the steps of the above-mentioned graphic and text content generation method are implemented.

[0112] The above is a schematic solution of a computer program product according to this embodiment. It should be noted that the technical solution of this computer program product and the technical solution of the above-mentioned graphic and text content generation method belong to the same concept. For the details not described in detail in the technical solution of the computer program product, reference can be made to the description of the technical solution of the above-mentioned graphic and text content generation method.

[0113] The above describes specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve the desired result. Additionally, the processes depicted in the figures do not necessarily require the particular order or sequential order shown to achieve the desired result. In certain implementations, multitasking and parallel processing are also possible or may be advantageous.

[0114] The computer instructions include computer program code, which may be in the form of source code, object code, executable files, or some intermediate forms, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in the computer-readable medium may be appropriately increased or decreased according to the requirements of patent practice. For example, in some regions, according to patent practice, the computer-readable medium does not include electrical carrier signals and telecommunication signals.

[0115] It should be noted that for the foregoing method embodiments, for the sake of simplicity of description, they are all expressed as a series of action combinations. However, those skilled in the art should know that the embodiments of this specification are not limited by the described action sequence, because according to the embodiments of this specification, some steps may be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to the embodiments of this specification.

[0116] In the above embodiments, the descriptions of each embodiment have their own emphases. For the parts not detailed in a certain embodiment, reference may be made to the relevant descriptions of other embodiments.

[0117] The preferred embodiments of this specification disclosed above are only used to help explain this specification. The alternative embodiments do not elaborate on all details and do not limit the invention to the specific embodiments described. Obviously, many modifications and changes can be made according to the content of the embodiments of this specification. This specification selects and specifically describes these embodiments to better explain the principles and practical applications of the embodiments of this specification, so that those skilled in the art can well understand and utilize this specification.

Claims

1. A method for generating graphic content, characterized in that: include: Segment the original text to obtain at least two text segments; Generating a text outline corresponding to the at least two text segments according to the text type of the original text, and generating an initial text based on the text outline and the at least two text segments; A text image is generated for the text outline and the initial text, and the text outline, the initial text and the text image are integrated to obtain target graphic content.

2. The method for generating graphic content according to claim 1, characterized in that: Before segmenting the original text to obtain at least two text segments, the method further includes: Determining a text to be processed, and performing redundant information detection on the text to be processed; Redundant information in the text to be processed is removed according to the detection result to obtain the original text.

3. The method for generating graphic content according to claim 1, characterized in that: After the original text is segmented to obtain at least two text segments, the method further includes: Performing content detection on the original text, and when the original text passes the content detection, generating text outlines corresponding to the at least two text segments according to the text type of the original text.

4. The method for generating graphic content according to claim 1, characterized in that: Generating text outlines corresponding to the at least two text segments according to the text type of the original text includes: Determine the content theme and text style of the original text, and use the content theme and text style as the text type; A graphic-text generation module is selected based on the text type, and the graphic-text generation module is used to generate the text outline based on the original text and the at least two text segments.

5. The method for generating graphic content according to claim 1, characterized in that: After generating the initial text based on the text outline and the at least two text segments, the method further includes: determining expandable text in the initial text; Performing a network search based on the expandable text to obtain an expanded text corresponding to the initial text; The step of integrating the text outline, the initial text and the text image to obtain target graphic content includes: The extended text, the text outline, the initial text and the text image are integrated to obtain the target graphic content.

6. The method for generating graphic content according to claim 1, characterized in that: The step of generating a text image for the text outline and the initial text comprises: generating a cover image based on the text outline, and determining at least one chapter information included in the initial text; Extracting the chapter text corresponding to each chapter information from the initial text; A chapter image is generated for each chapter text, and the cover image and each chapter image are used as the text image.

7. The method for generating graphic content according to claim 1, characterized in that: After generating the text image for the text outline and the initial text, the method further includes: extracting annotatable content from the initial text and the text image; Generate annotation text for the annotatable content; The step of integrating the text outline, the initial text and the text image to obtain target graphic content includes: The annotation text, the text outline, the initial text and the text image are integrated to obtain the target graphic content.

8. The method for generating graphic content according to claim 1, characterized in that: After integrating the text outline, the initial text and the text image to obtain the target graphic content, the method further includes: Conduct content review and format review on the target graphic and text content; When the content review and the format review are passed, the target graphic content is stored in a database.

9. A device for generating graphic content, characterized in that: include: A segmentation module is configured to segment the original text to obtain at least two text segments; A generating module configured to generate a text outline corresponding to the at least two text segments according to the text type of the original text, and generate an initial text based on the text outline and the at least two text segments; The integration module is configured to generate a text image for the text outline and the initial text, and integrate the text outline, the initial text and the text image to obtain target graphic content.

10. A computing device, characterized in that include: Memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of the method for generating graphic content according to any one of claims 1 to 8 are implemented.

11. A computer-readable storage medium, characterized in that: It stores computer executable instructions, which, when executed by a processor, can implement the steps of the method for generating graphic content as described in any one of claims 1 to 8.

12. A computer program product, characterized in that The method comprises a computer program or an instruction, which, when executed by a processor, implements the steps of the method for generating graphic content as described in any one of claims 1 to 8.

Images