A book IP design method and system based on AIGC technology
By analyzing the book content, determining the audience and style, establishing a material library and optimizing the design, and using AIGC technology to generate book IP, the problem of insufficient application of AIGC in the field of icon and image design is solved, and effective design and optimization of book IP is achieved.
Patent Information
- Application Number
- CN202410747765.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-06-11
- Publication Date
- 2024-11-26
- Estimated Expiration
- 2044-06-11
AI Technical Summary
In the prior art, AIGC technology has fewer applications in the fields of icon and image design, especially in the design of book IP.
By analyzing the book content, determining the audience and style, establishing a material library, designing the initial book IP using the material library, and obtaining the finished book IP through evaluation optimization, and generating the book IP with generative artificial intelligence technology.
It uses AIGC technology to interpret book content, design a book IP that meets the book theme and audience needs, and improves the intuitiveness and efficiency of the design.
Smart Images

Figure CN118570339B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of image design, and in particular to a book IP design method and system based on AIGC technology. Background Art
[0002] With the development of artificial intelligence, the cumulative integration of technologies such as GAN, CLIP, Transformer, Diffusion, pre-trained models, multimodal technology, and generation algorithms has led to the outbreak of AIGC. AIGC is generative artificial intelligence, which refers to the technology based on artificial intelligence technical methods such as generative adversarial networks and large pre-trained models, which generates relevant content with appropriate generalization capabilities through learning and recognition of existing data. AIGC technology can use artificial intelligence algorithms to generate content with certain creativity and quality. Through training models and learning from a large amount of data, AIGC can generate relevant content based on the input conditions or guidance. For example, by entering keywords, descriptions or samples, AIGC can generate articles, images, audio, etc. that match them. Nowadays, artificial intelligence generation technology has been widely used in scenarios where images or text are generated.
[0003] Although AIGC is frequently used in the fields of text and images, it is less used in design fields such as icons or images. Especially for the design of book IP, there is currently no technology that can use AIGC to interpret the content of the book and independently design the book image based on the content. Summary of the invention
[0004] The present application provides a book IP design method and system based on AIGC technology, so as to achieve the technical effect of using AIGC technology to interpret book content and design book IP, and solve the problem of blank application of AIGC in the field of icon and image design in the prior art.
[0005] In the first aspect, the present application provides a book IP design method based on AIGC technology, which is used to design a book IP according to the content of the book, and the method includes: analyzing the content of the book, and determining the audience and style of the book according to the content of the book; establishing a material library according to the audience and style, and using the materials in the material library to design the book IP to obtain an initial book IP; evaluating the initial book IP, and optimizing the initial book IP according to the evaluation results to obtain a finished book IP.
[0006] In a possible implementation, the content of a book includes text, and the content of the book is analyzed, and the audience and style of the book are determined based on the content of the book, including: extracting nouns and adjectives from the text, and classifying the nouns and adjectives, classifying the nouns according to audience group categories, and classifying the adjectives according to style categories; calculating the frequency of occurrence of each noun, sorting the frequency of occurrence of each noun from large to small, counting the audience group categories corresponding to the top 30% of the nouns in the sorting results, and using the audience group category with the largest count as the audience of the book; calculating the number of adjectives corresponding to each style category, determining the style category containing the largest number of adjectives, and using the style category as the first style of the book.
[0007] In a possible implementation, the content of the book also includes pictures. The content of the book is analyzed, and the audience and style of the book are determined based on the content of the book, including: color recognition, element recognition, and artistic style recognition of the pictures to obtain the color, element, and artistic style of each picture; extracting the text paragraphs corresponding to each picture, and extracting adjectives in the text based on the corresponding color, element, and artistic style of the picture; classifying the adjectives, calculating the number of adjectives corresponding to each style category, determining the style category containing the largest number of adjectives, and using the style category as the second style of the book.
[0008] In one possible implementation, a material library is established based on the audience and style, including: determining whether a first style and a second style are the same style; if the first style and the second style are the same style, determining the first style or the second style as the style of the book, and using elements in the picture as materials to generate a material library; if the first style and the second style are different styles, using the first style as the style of the book, and obtaining materials from the Internet based on the first style, nouns and adjectives obtained from the text to generate a material library.
[0009] In one possible implementation, the book IP is designed using materials in the material library to obtain an initial book IP, including: classifying the materials in the material library according to roles, scenes, and props; calculating the relevant parameters between the materials and the audience and style in the material library; comparing the relevant parameters between each material and the audience and style, and determining the material with the highest calculated relevant parameters as the final material; and combining the final materials to obtain the initial book IP.
[0010] In one possible implementation, an initial book IP is evaluated, and the initial book IP is optimized based on the evaluation results to obtain a finished book IP, including: establishing a book question-and-answer platform, setting up questionnaires on the book question-and-answer platform, scoring the answers to the questionnaires, and selecting evaluators based on the scores of the questionnaires; establishing an online interactive platform, setting up scoring nodes on the online interactive platform, and evaluators scoring the initial book IP based on the scoring nodes; wherein the scoring nodes include: artistic scoring nodes, subject relevance scoring nodes, and subjective evaluation nodes.
[0011] In one possible implementation, an initial book IP is evaluated, and the initial book IP is optimized based on the evaluation results to obtain a finished book IP, including: setting weight values for the scores of scoring nodes, and performing weighted integrated calculations on the artistic evaluation scores, thematic relevance evaluation scores, and subjective evaluation scores based on the weight values to obtain a comprehensive evaluation score; comparing the comprehensive evaluation score and the evaluation threshold, and optimizing or redesigning the initial book IP based on the comparison results; the comprehensive evaluation score is M, the first evaluation threshold is P, and the second evaluation threshold is Q; when M<P, the initial book IP needs to be redesigned; when P<M<Q, the initial book IP needs to be optimized; when M>Q, the initial book IP is set as the finished book IP.
[0012] In a possible implementation, the method also includes: setting parameters of the finished book IP, the parameters including: the size of the finished book IP, the pixels of the finished book IP; setting reviewers to review the finished book IP, and promoting the finished book IP after passing the review of the reviewers.
[0013] On the second aspect, the present application provides a book IP design system based on AIGC technology, the system is used to implement a book IP design method based on AIGC technology, and the book IP design system based on AIGC technology includes: a content analysis module, the content analysis module is used to analyze the content of the book, and determine the audience and style of the book according to the content of the book; a book IP design module, the book IP design module is used to establish a material library according to the audience and style, and use the materials in the material library to design the book IP to obtain an initial book IP; an evaluation optimization module, the evaluation optimization module is used to evaluate the initial book IP, optimize the initial book IP according to the evaluation results, and obtain a finished book IP.
[0014] The above technical solution provided by the embodiment of the present application has the following advantages over the prior art: by analyzing the content of the book, the most intuitive and clear audience and style of the book are determined, which is more intuitive and convenient for the subsequent design of the book IP than determining the content outline or content connection through the book content. The audience and style of the book are the main factors affecting the design of the book IP. Subsequently, the initial book IP can be designed through the established material library, and the final finished book IP can be optimized according to the evaluation, realizing the design of the book IP using generative artificial intelligence AIGC. BRIEF DESCRIPTION OF THE DRAWINGS
[0015] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.
[0016] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.
[0017] One or more embodiments are exemplarily described by pictures in the corresponding drawings, and these exemplified descriptions do not constitute limitations on the embodiments. Elements with the same reference numerals in the drawings represent similar elements, and unless otherwise stated, the figures in the drawings do not constitute proportional limitations.
[0018] Figure 1 A flowchart of a book IP design method based on AIGC technology provided in an embodiment of the present application. DETAILED DESCRIPTION
[0019] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.
[0020] In order to solve the problem of the application gap of AIGC in the field of icon and image design in the prior art, the present application provides a book IP design method and system based on AIGC technology to achieve the technical effect of using AIGC technology to interpret book content and design book IP.
[0021] In some embodiments, see Figure 1, provides a book IP design method based on AIGC technology, the method is used to design a book IP according to the content of the book, the method includes:
[0022] Step S100: Analyze the content of the book and determine the audience and style of the book according to the content of the book;
[0023] Step S200: Establish a material library according to the audience and style, and use the materials in the material library to design the book IP to obtain an initial book IP;
[0024] Step S300: Evaluate the initial book IP, optimize the initial book IP according to the evaluation result, and obtain the finished book IP.
[0025] Specifically, AIGC technology is a generative artificial intelligence that can generate text or images, while book IP design is an image design or icon design, which is mainly composed of image elements. Therefore, generative artificial intelligence technology, that is, AIGC technology, can also be used to generate book IP.
[0026] Furthermore, the book IP of a book needs to fit the content of the book, that is, the theme, overall style and audience of the book. Therefore, in this design plan, the first step is to analyze the content of the book, determine the overall style and audience of the book based on the content of the book, and further determine the theme of the book.
[0027] The audience and style of a book are the two main factors that affect the design of a book IP. Therefore, a material library is established based on the audience and style of the book, and the materials in the material library are used to design the book IP. This ensures that the designed IP is in line with the overall style of the book, and can also be more inclined towards the audience, establishing a connection between the audience and the book. After the material library is established, the materials in the material library are used to design the book IP, and the initial book IP is formed through the combination of multiple materials.
[0028] Furthermore, the initial book IP is evaluated, rated by readers, and optimized or redesigned accordingly, and finally the finished book IP is output.
[0029] In this embodiment, by analyzing the content of the book, the most intuitive and clear audience and style of the book are determined. Compared with determining the content outline or content connection through the book content, the subsequent design of the book IP is more intuitive and convenient. The audience and style of the book are the main factors affecting the design of the book IP. Subsequently, the initial book IP can be designed through the established material library, and the final finished book IP can be optimized according to the evaluation, realizing the design of the book IP using generative artificial intelligence AIGC.
[0030] In some embodiments, the content of the book includes text, and analyzing the content of the book to determine the audience and style of the book based on the content of the book includes:
[0031] Extract nouns and adjectives from the text and classify them. Nouns are classified according to audience categories, and adjectives are classified according to style categories.
[0032] Calculate the frequency of each noun, sort the frequency of each noun from largest to smallest, count the audience group categories corresponding to the top 30% of the nouns in the sorting results, and use the audience group category with the largest count as the audience of the book;
[0033] Count the number of adjectives corresponding to each style category, determine the style category containing the largest number of adjectives, and use the style category as the first style of the book.
[0034] Specifically, the content of the book includes two content forms: text and pictures. This embodiment mainly analyzes the text and determines the audience and style of the book based on the text. The words in the text content of the book that have a strong correlation with the audience and style are nouns and adjectives. Therefore, nouns are used to confirm the audience of the book, and adjectives are used to confirm the style of the book. Using nouns to determine the audience of the book is achieved by judging in which age group or a certain group the extracted nouns are frequently used. For example, when the noun is a blood glucose meter, it can be directly associated with the diabetic group, confirming that the audience is diabetic patients. The style of the book is mainly rendered by adjectives, so adjectives are used as the basis for confirming the style of the book.
[0035] Furthermore, nouns and adjectives are classified, nouns are classified according to the type of audience, different nouns are bundled with different audience groups, and different adjectives are bundled with different style categories.
[0036] The frequency of occurrence of each noun in the text of the entire book is calculated. The higher the frequency of occurrence, the more relevant it is to the content of the book. The noun processing is optimized, and the last 70% of the nouns with the lowest frequency of occurrence are discarded. These nouns do not appear frequently, have little impact on the content of the book, and are not core-related to the content of the book. Therefore, the first 30% of the nouns in the frequency of occurrence ranking results are the main nouns that affect the audience. The audience categories involved in these nouns are counted, and the audience category with the most counts confirms the audience of the book. This setting can avoid too many nouns interfering with the analysis and judgment of the audience.
[0037] After classification, the adjectives in each style category are counted to obtain the style category corresponding to the adjective with the largest count, and this style category is set as the first style of the book. The first style is a style determined according to the text content of the book.
[0038] In this embodiment, by extracting and processing nouns and adjectives in text, the audience and style of the book can be determined, making it easier to use the audience and style to design the book IP.
[0039] In some embodiments, the content of the book also includes pictures, and analyzing the content of the book to determine the audience and style of the book based on the content of the book includes:
[0040] Perform color recognition, element recognition and artistic style recognition on the pictures to obtain the color, element and artistic style of each picture;
[0041] Extract the text paragraphs corresponding to each picture, and extract the adjectives in the text according to the corresponding colors, elements and artistic styles of the pictures;
[0042] The adjectives are classified, the number of corresponding adjectives in each style category is calculated, the style category containing the largest number of adjectives is determined, and the style category is used as the second style of the book.
[0043] Specifically, the content of a book also includes picture content, and the pictures are illustrations in the book and cover illustrations. The illustrations of a book can also represent the style of the book, so the pictures are processed and the style of the book is obtained again using the pictures as the second style, so as to more comprehensively understand and confirm the style of the book.
[0044] Among the illustrations in a book, factors that influence the style of the book include: the elements involved in the picture, such as the objects drawn in the picture; the colors in the picture, such as whether the colors of the picture are mainly cool or warm; the artistic style of the picture, such as comic style or realistic style, etc.
[0045] Identify the colors, elements and artistic styles in the picture, extract the text paragraphs related to the picture in the book, and further extract adjectives from the text paragraphs. The principle of extracting adjectives is to confirm the adjectives associated with the text paragraphs based on the colors, elements and artistic styles identified in the picture. The database stores adjectives associated with colors, elements and artistic styles. By comparing the adjectives in the database with the adjectives in the text paragraphs, the corresponding adjectives are finally extracted.
[0046] After classification, the adjectives in each style category are counted to obtain the style category corresponding to the adjective with the largest count, and this style category is set as the second style of the book. The second style is a style determined according to the picture content of the book.
[0047] In this embodiment, the second style is obtained through the picture. The second style is obtained in order to more accurately obtain the style of the book, thereby further determining the design of the book IP.
[0048] In some embodiments, a material library is created based on audience and style, including:
[0049] Determine whether the first style and the second style are the same style;
[0050] If the first style and the second style are the same style, the first style or the second style is determined as the style of the book, and the elements in the picture are used as materials to generate a material library;
[0051] If the first style and the second style are different styles, the first style is used as the style of the book, and materials are obtained from the Internet based on the first style and nouns and adjectives obtained from the text to generate a material library.
[0052] Specifically, determine whether the first style obtained from the text content and the second style obtained from the picture content are consistent. If they are consistent, it means that the style of the text and the picture of the book are consistent, set the style of the book IP to the same style, and directly use the elements in the picture as materials to form a material library. When the first style and the second style are inconsistent, it means that the style difference between the text content and the picture content is large. The style of the book IP is determined by the first style determined by the text content, and the first style is set as the book style. Furthermore, after determining the style of the book, obtain materials based on the nouns and adjectives obtained from the text to generate a material library.
[0053] In this embodiment, when the first style and the second style are the same, the elements in the picture can be directly used as materials to form a material library, so that the text, pictures and book IP of the book can be kept in the same style. When the first style and the second style are inconsistent, the first style is used as the book style, which is determined based on the most important text content in the book, and can ensure that the book IP does not deviate from the theme or content of the book.
[0054] In some embodiments, the book IP is designed using materials in the material library to obtain an initial book IP, including: classifying the materials in the material library according to roles, scenes, and props; calculating the relevant parameters between the materials and the audience and style in the material library; comparing the relevant parameters between each material and the audience and style, and determining the material with the highest calculated relevant parameters as the final material; and combining the final materials to obtain the initial book IP.
[0055] Specifically, for the various materials in the material library, they are classified according to roles, scenes and props, and there are multiple materials under each category. Calculate the relevant parameters between each material in the material library and the audience and style. Each material is labeled with a corresponding keyword. The audience category and style category are bound to a corresponding entry library. Calculate the correlation between each material keyword and the entry in the entry library to obtain the relevant parameters between the material and the audience and style. When there are multiple entries in the entry library that have a high degree of similarity with the material's keyword, the more entries that appear, the greater the relevant parameters. The material with the highest relevant parameters in each category is used as the final material, and finally the initial book IP is obtained through the designer's combined design.
[0056] In this embodiment, by calculating relevant parameters, materials with a strong correlation with the style and audience are obtained for design, and the obtained initial book IP is more consistent with the content of the book.
[0057] In some embodiments, the initial book IP is evaluated, and the initial book IP is optimized according to the evaluation result to obtain the finished book IP, including:
[0058] Establish a reading question-and-answer platform, set up questionnaires on the reading question-and-answer platform, score the answers to the questionnaires, and select evaluators based on the scores of the questionnaires;
[0059] Establish an online interactive platform, set scoring nodes on the online interactive platform, and evaluators score the initial book IPs according to the scoring nodes;
[0060] Among them, the scoring nodes include: artistic scoring nodes, topic relevance scoring nodes, and subjective evaluation nodes.
[0061] Specifically, the evaluation of the initial book IP needs to be achieved through the book question-and-answer platform and the online interactive platform. The book question-and-answer platform is used to screen out reviewers from readers, and the online interactive platform is used for the screened reviewers to score the initial book IP.
[0062] Furthermore, in order to facilitate evaluators to conduct comprehensive scoring of the initial book IP, multiple scoring nodes are set up on the online interactive platform. Each scoring node corresponds to a scoring item from a different angle. The scoring nodes include: artistic scoring node, theme relevance scoring node, and subjective evaluation node. The scores corresponding to the corresponding scoring nodes are: artistic evaluation score, theme relevance evaluation score, and subjective evaluation score.
[0063] In this embodiment, by setting a questionnaire for readers, readers who have a deep understanding of the book content can be selected as evaluators, so that the evaluators can have a better scoring effect. By setting different scoring nodes, it is possible to help evaluate the initial book IP from multiple angles, which is convenient for subsequent optimization of the initial book IP from multiple aspects.
[0064] In some embodiments, the initial book IP is evaluated, and the initial book IP is optimized according to the evaluation result to obtain the finished book IP, including:
[0065] Set weight values for the scores of the scoring nodes, and perform weighted integrated calculations on the artistic evaluation score, the theme relevance evaluation score, and the subjective evaluation score according to the weight values to obtain a comprehensive evaluation score;
[0066] Compare the comprehensive evaluation score and the evaluation threshold, and optimize or redesign the initial book IP according to the comparison results;
[0067] The comprehensive evaluation score is M, the first evaluation threshold is P, and the second evaluation threshold is Q; when M<P, the initial book IP needs to be redesigned; when P<M<Q, the initial book IP needs to be optimized; when M>Q, the initial book IP is set as the finished book IP.
[0068] Specifically, corresponding weight values are set for the art evaluation score, the theme relevance evaluation score, and the subjective evaluation score, and weight calculation is performed to obtain a comprehensive evaluation score. When comparing the comprehensive evaluation scores, two thresholds are set. The first evaluation threshold is the minimum score standard. When the score is less than the first evaluation threshold, it means that the comprehensive evaluation score is too low and the initial book IP needs to be redesigned; the second evaluation threshold is the highest score standard. When the score is greater than the second evaluation threshold, it means that the comprehensive evaluation score is high and the initial book IP is well designed and does not need to be changed; and when the comprehensive evaluation score is between the first evaluation threshold and the second evaluation threshold, it means that the initial book IP needs to be optimized and improved.
[0069] In this embodiment, the initial book IP is further operated by calculating the comprehensive evaluation score and comparing the threshold value, and the initial book IP is redesigned or optimized according to the score, so that the final finished book IP can better meet the requirements of readers.
[0070] In some embodiments, the comprehensive evaluation score calculation formula is:
[0071] ;
[0072] Among them, M is the comprehensive evaluation score, A is the theme relevance evaluation score, B is the artistry evaluation score, C is the subjective evaluation score, α is the weight value of the theme relevance evaluation score, β is the weight value of the artistry evaluation score, is the weight value of the subjective evaluation score; α>β> , and α+β+ =1.
[0073] Specifically, the weight value of the theme relevance evaluation score is greater than the weight value of the artistry evaluation score, which is greater than the weight value of the subjective evaluation score. This reduces the proportion of readers' subjective evaluation scores and increases the proportion of theme relevance evaluation scores. This allows the final comprehensive evaluation score to more accurately reflect the degree of relevance between the initial book IP and the theme, and the scoring is more scientific.
[0074] In some embodiments, the method also includes: setting parameters of the finished book IP, the parameters including: the size of the finished book IP, the pixels of the finished book IP; setting reviewers to review the finished book IP, and promoting the finished book IP after passing the review of the reviewers.
[0075] Specifically, after obtaining the finished book IP, the parameters of the finished book IP need to be set so that it can be applied to a variety of scenarios. The set parameters are mainly size and pixels, ensuring that the finished book IP can appear completely and clearly in multiple application scenarios. The auditor conducts the final review of the finished book IP. After confirming the relevance between the finished book IP and the book, the finished book IP is promoted using the online interactive platform and the book question-and-answer platform.
[0076] In some embodiments, a book IP design system based on AIGC technology is also provided. The system is used to implement a book IP design method based on AIGC technology. The book IP design system based on AIGC technology includes: a content analysis module, which is used to analyze the content of the book and determine the audience and style of the book based on the content of the book; a book IP design module, which is used to establish a material library based on the audience and style, and use the materials in the material library to design the book IP to obtain an initial book IP; an evaluation optimization module, which is used to evaluate the initial book IP, optimize the initial book IP based on the evaluation results, and obtain a finished book IP.
[0077] In this embodiment, through the module setting of the system, the above-mentioned book IP design method can be implemented using the system modules.
[0078] The foregoing is merely a specific embodiment of the present invention, which enables those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features claimed herein.
Claims
1. A book IP design method based on AIGC technology, characterized in that: The method is used to design a book IP according to the content of the book, and the method comprises: Analyze the content of the book and determine the audience and style of the book based on the content of the book; Establish a material library according to the audience and the style, and use the materials in the material library to design the book IP to obtain an initial book IP; Evaluate the initial book IP, and optimize the initial book IP according to the evaluation result to obtain a finished book IP; The content of the book includes text, and the analyzing the content of the book and determining the audience and style of the book according to the content of the book include: Extracting nouns and adjectives from the text, and classifying the nouns and adjectives, wherein the nouns are classified according to audience categories, and the adjectives are classified according to style categories; Calculate the frequency of occurrence of each noun, sort the frequency of occurrence of each noun from large to small, count the audience group categories corresponding to the top 30% of the nouns in the sorting results, and use the audience group category with the largest number of counts as the audience of the book; Calculating the number of the adjectives corresponding to each of the style categories, determining the style category containing the largest number of adjectives, and using the style category as the first style of the book; The content of the book also includes pictures. Analyzing the content of the book and determining the audience and style of the book according to the content of the book include: Performing color recognition, element recognition and artistic style recognition on the pictures to obtain the color, element and artistic style of each picture; Extracting the text paragraph corresponding to each of the pictures, and extracting adjectives in the text according to the color, the element and the artistic style corresponding to the picture; Classifying the adjectives, calculating the number of the adjectives corresponding to each style category, determining the style category containing the largest number of adjectives, and using the style category as the second style of the book; The step of establishing a material library according to the audience and the style includes: Determining whether the first style and the second style are the same style; If the first style and the second style are the same style, determining the first style or the second style as the style of the book, and using the elements in the picture as materials to generate a material library; If the first style and the second style are different styles, the first style is used as the style of the book, and materials are obtained from the Internet to generate a material library according to the first style and the nouns and adjectives obtained from the text; The step of designing the book IP using the materials in the material library to obtain the initial book IP includes: Classifying the materials in the material library according to roles, scenes and props; Calculating correlation parameters between the material, the audience and the style in the material library; Comparing the relevant parameters between each of the materials and the audience and the style, and determining the material with the highest calculated relevant parameter as the final material; Combining the final materials to obtain the initial book IP; The step of evaluating the initial book IP and optimizing the initial book IP according to the evaluation result to obtain a finished book IP includes: Establishing a reading question-and-answer platform, wherein the reading question-and-answer platform sets a questionnaire, scores the answers to the questionnaire, and selects evaluators based on the scores of the questionnaire; Establishing a network interactive platform, wherein the network interactive platform is provided with scoring nodes, and the evaluator scores the initial book IP according to the scoring nodes; The scoring nodes include: an artistry scoring node, a topic relevance scoring node, and a subjective evaluation node.
2. The book IP design method based on AIGC technology according to claim 1 is characterized in that: The step of evaluating the initial book IP and optimizing the initial book IP according to the evaluation result to obtain a finished book IP includes: Setting weight values for the scores of the scoring nodes, and performing weighted integrated calculation on the artistic evaluation score, the theme relevance evaluation score, and the subjective evaluation score according to the weight values to obtain a comprehensive evaluation score; Comparing the comprehensive evaluation score with the evaluation threshold, and optimizing or redesigning the initial book IP according to the comparison result; The comprehensive evaluation score is M, and the evaluation threshold includes a first evaluation threshold and a second evaluation threshold, the first evaluation threshold is P, and the second evaluation threshold is Q; when M<P, the initial book IP needs to be redesigned; when P<M<Q, the initial book IP needs to be optimized; when M>Q, the initial book IP is set as the finished book IP.
3. The book IP design method based on AIGC technology according to claim 1 is characterized in that: The method further comprises: Setting parameters of the finished book IP, the parameters including: the size of the finished book IP and the pixels of the finished book IP; A reviewer is assigned to review the finished book IP. After passing the review by the reviewer, the finished book IP is promoted.
4. A book IP design system based on AIGC technology, characterized in that: The system is used to implement the book IP design method based on AIGC technology as described in any one of claims 1 to 3, and the book IP design system based on AIGC technology includes: A content analysis module, the content analysis module is used to analyze the content of the book and determine the audience and style of the book according to the content of the book; A book IP design module, wherein the book IP design module is used to establish a material library according to the audience and the style, and to design the book IP using the materials in the material library to obtain an initial book IP; An evaluation and optimization module is used to evaluate the initial book IP, optimize the initial book IP according to the evaluation result, and obtain a finished book IP.
