Reading material typesetting construction method and system based on excellent child reading material analysis

Abstract

The invention discloses a reading material typesetting construction method and system based on excellent child reading material analysis, and relates to the technical field of reading material typesetting strategy generation, first, excellent child reading material data is collected and split into independent content units, then text content is recognized, semantic keywords are extracted, and a relation tree is constructed; identifying the image content, extracting an image description keyword, and establishing a mapping relation with the semantic keyword group relation tree; according to the scheme, the decoration components are divided and positioned, decoration component probe points are set, and a probe point array template is formed and associated with the semantic keyword group relation tree; combining the elements into an excellent typesetting data reference group, configuring reading material types, and constructing an excellent typesetting data reference library; and performing value evaluation on the current reading material typesetting strategy to determine an optimal strategy. By systematically analyzing excellent reading material typesetting, a scientific basis and effective guidance are provided for children's reading material typesetting design, and the reading experience and attraction of children's reading materials can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of book typesetting strategy generation, and in particular to a book typesetting construction method and system based on analysis of excellent children's books. Background Art

[0002] In the field of children's reading promotion and publishing, the layout design of children's books needs to closely follow the laws of children's cognitive development. Children of different ages have significant differences in text recognition, image comprehension, color perception, etc., which requires that the layout strategy must be carefully designed according to the cognitive characteristics of the target age group. As a key factor in improving the reading experience and stimulating children's interest in reading, the importance of the layout strategy of reading materials is becoming increasingly prominent. However, in the face of the vast amount of children's book resources, how to effectively use past excellent reading cases and select layout strategies that are both in line with children's cognitive characteristics and can stimulate reading interest has become a technical problem that needs to be solved urgently. Summary of the invention

[0003] The purpose of the present invention is to provide a method and system for constructing a reading material typesetting that can perform optimal evaluation on the reading material typesetting.

[0004] The present invention discloses a method for constructing a typesetting of reading materials based on analysis of excellent children's reading materials, comprising: Acquire a number of excellent children's book materials, and separate the excellent children's book materials into independent content to obtain a number of independent content units; Identify the text content of each independent content unit to obtain the paragraph content, perform semantic recognition on the paragraph content, determine a number of semantic keywords, and combine the semantic keywords in the original order to obtain semantic keyword groups, and group and mark the semantic keyword groups based on the sentences to which different semantic keywords belong to obtain a number of semantic sub-keyword groups, and construct a semantic keyword group relationship tree for situations where the paragraph content can be combined; Recognize the image content of each independent content unit, output the recognition result in the form of image text description to obtain image description information, combine the image description keywords in the image description information to obtain image description keyword groups, and establish a mapping relationship between the image description keyword groups and the semantic keyword group relationship tree based on the correspondence between the image content and the text content; The decoration components in the independent content unit are divided and positioned, and a number of decoration component detection points are evenly set for each decoration component, each decoration component detection point is set with a position coordinate and a color parameter, and all the decoration component detection points are combined according to the original positions to form a decoration component detection point array template, and an association relationship is established between the decoration component detection point array template and the semantic keyword group relationship tree; The combination of the semantic keyword group relationship tree, the image description keyword and the decoration component exploration point array template is recorded as an excellent typesetting data reference group, and the reading material type is configured for the excellent typesetting data reference group to obtain an excellent typesetting data reference library; Use the excellent typesetting data reference library to conduct a value assessment on several reading material typesetting strategies currently being constructed, and determine the optimal reading material typesetting strategy based on the value assessment.

[0005] In some embodiments disclosed in the present invention, the method for constructing a semantic keyword phrase relationship tree includes: According to the original order of the paragraph content, a paragraph content sequence is constructed, and based on the paragraph content sequence, a trunk of a semantic keyword group key tree is constructed, wherein each semantic keyword group corresponds to a tree node; Analyze the contents of each paragraph and other paragraphs that can be paralleled, and extend a tree branch at the corresponding tree node to form a semantic keyword relationship tree.

[0006] In some embodiments disclosed in the present invention, a method for performing semantic recognition on a text content and determining a number of semantic keywords includes: A focus keyword library is set for excellent children's books. The focus keyword library includes several types of focus keyword sets, and each type of focus keyword set includes several focus keywords; Preprocess the text content, including word segmentation, stop word removal and part-of-speech tagging, to obtain several candidate keywords, and analyze the attention level of the candidate keywords, including determining the occurrence frequency and relative relationship characteristics of the candidate keywords, and determining the attention level of the candidate keywords based on the occurrence frequency and relative relationship characteristics, and screening out several candidate keywords based on the attention level of the candidate keywords; Based on the pre-marked type of the text content, the focus keyword set called in the focus keyword library is determined, and several candidate keywords are brought into the focus keyword set for comparison. If there is a mapped focus keyword in the focus keyword set, the corresponding candidate keyword is identified as a semantic keyword.

[0007] In some embodiments disclosed in the present invention, the method for determining the attention level of candidate keywords includes: Determine the relative position of the candidate keyword in the sentence, and based on the determined relative position, configure an initial attention parameter for the candidate keyword, and based on the occurrence frequency of the candidate keyword, modify the initial attention parameter to obtain the attention degree; The expression for calculating the degree of attention is: ; in, For the level of attention, is the attention conversion coefficient, is the initial focus parameter, is the frequency of occurrence of the candidate keywords, is the frequency impact adjustment coefficient, Adjust constants for frequency effects; The method for determining the relative position of the candidate keywords in the sentence includes performing syntactic structure analysis on the sentence, identifying the subject, predicate and object components, and determining the position of the candidate keywords in the syntactic structure.

[0008] In some embodiments disclosed in the present invention, the method for identifying the image content of each independent content unit includes: Divide the content units in the image content, including objects, people, animals and scenes in the image content, and determine the directional relationship between the objects, people and animals; Constructing an image description information group according to the image content, the image description information group includes a plurality of object description units, a plurality of person description units, a plurality of animal description units and a scene description unit, wherein the object description unit includes a plurality of object description keywords, the person description unit includes a plurality of person description keywords, the animal description unit includes a plurality of animal description keywords, and the scene description unit includes a plurality of scene description keywords; Based on the pointing relationship between objects, people and animals, a unit relationship sequence is constructed for the corresponding object description units, person description units and animal description units, and the unit relationship sequence includes other object description units, person description units or animal description units with pointing relationship.

[0009] In some embodiments disclosed in the present invention, the method for evaluating the value of the currently constructed reading material typesetting strategy by using an excellent typesetting data reference library includes: Analyze the layout strategy of the reading material, determine the semantic keywords in the strategy, and construct the semantic sub-keyword groups in the strategy based on the semantic keywords in the strategy; Analyze the typesetting strategy of the reading material, determine the image description information of the image content in the strategy, determine the detection point array template of the decorative component in the strategy, and construct the image description information group in the strategy based on the image description information; The semantic sub-keyword group in the strategy, the image description information group in the strategy and the decorative component probe point array template in the strategy corresponding to the reading material typesetting strategy form a typesetting data reference group in the strategy; Several retrieval factors are determined for the typesetting data reference group in the strategy, and based on the retrieval factors, several excellent typesetting data reference groups are retrieved from the excellent typesetting data reference library, and the retrieved excellent typesetting data reference groups are compared with the typesetting data reference groups in the strategy. Based on the comparison results, the value assessment value of the reading material typesetting strategy currently being constructed is determined.

[0010] In some embodiments disclosed in the present invention, a method for determining a number of search factors in a layout data reference group in a strategy includes: Randomly select a number of first initial retrieval factors from the semantic sub-keyword group in the strategy, randomly select a number of second initial retrieval factors from the image description information group in the strategy, and randomly select a number of third initial retrieval factors from the decoration component probe point array template in the strategy; The first initial retrieval factor, the second initial retrieval factor and the third initial retrieval factor are respectively substituted into the excellent typesetting data reference library, and the reference group mapping number of the excellent typesetting data reference group mapped by each initial retrieval factor is calculated respectively. If the reference group mapping number is greater than or equal to the preset value, the corresponding initial retrieval factor is retained, and the retained initial retrieval factor is identified as the retrieval factor for the final search in the excellent data reference library.

[0011] In some embodiments disclosed in the present invention, the method of comparing the retrieved excellent typesetting data reference group with the typesetting data reference group in the strategy includes: The first mapping parameter mapped in the semantic sub-keyword group relationship tree relative to the excellent typesetting data reference group in the analysis strategy, the second mapping parameter of the image description keyword group relative to the image description keyword group of the excellent typesetting data reference group in the analysis strategy, and the third mapping parameter of the decoration component probe point array template relative to the decoration component probe point array template of the excellent typesetting data reference group in the analysis strategy; Based on the first mapping parameter, the second mapping parameter and the third mapping parameter, determine the degree of equivalence between each retrieved excellent typesetting data reference group and the typesetting data reference group in the strategy, and determine the value evaluation value of the reading material typesetting strategy based on the corresponding equivalence degrees of all retrieved excellent typesetting data reference groups; Among them, the expression for calculating the degree of equality between the excellent typesetting data reference group and the typesetting data reference group in the strategy is: ; in, To the same extent, is the first mapping parameter weight adjustment coefficient, is the second mapping parameter weight adjustment coefficient, is the third mapping parameter weight adjustment coefficient, is the mapping calculation function of the semantic sub-keyword group in the strategy, which is used to determine whether the semantic sub-keyword group in the i1th strategy is mapped to the semantic keyword group relationship tree. If the mapping is determined, then Output 1, otherwise output 0, wherein the method of determining whether the semantic sub-keyword group in the policy is mapped to the semantic keyword group relationship tree includes judging whether the proportion of the semantic sub-keywords in the policy that are mapped in the semantic sub-keyword group in the policy is greater than or equal to a preset value, and if it is greater than or equal to the preset value, then it is determined that the semantic sub-keyword group in the policy is mapped to the semantic keyword group relationship tree, is the semantic sub-keyword group mapping impact adjustment coefficient in the strategy, is the semantic sub-keyword group mapping impact adjustment constant in the strategy, n1 is the number of semantic sub-keyword groups in the strategy, is the mapping calculation function of the image description keywords in the strategy, which is used to determine whether the image description keywords in the i2th strategy are mapped to the image description keyword group of the excellent typesetting data reference group. If the mapping is determined, then Output 1, otherwise output 0. is the impact adjustment coefficient of the image description keyword mapping in the strategy, is the mapping adjustment constant of the image description keyword group in the strategy, n2 is the number of image description keywords in the strategy in the image description keyword group, The mapping calculation function for the decoration component probe point array template in the strategy is used to determine whether the decoration component probe point in the i3th strategy is mapped to the decoration component probe point array template of the excellent typesetting data reference group. If the mapping is determined, then Output 1, otherwise output 0. It is the adjustment coefficient of the detection point mapping impact of the decoration component in the strategy. Adjust constants for the detection point mapping effect of the decoration component in the strategy, The number of probe points in the probe point array template of the decoration component in the strategy.

[0012] In some embodiments disclosed in the present invention, a method for determining the value evaluation value of a reading material typesetting strategy based on the equivalent degree corresponding to all retrieved excellent typesetting data reference groups is also disclosed, including: Determine the number of the first reference groups of the retrieved excellent typesetting data reference groups, and judge whether the degree of equality corresponding to each excellent typesetting data reference group is greater than or equal to a preset value, and if it is greater than or equal to the preset value, mark the reading typesetting strategy once; Calculate the reference group quantity ratio of the second reference group quantity to the first reference group quantity of the marked reading material typesetting strategy, analyze the preset reference group quantity ratio interval to which the reference group quantity ratio belongs, and identify the value assessment value corresponding to the preset reference group quantity ratio interval as the value assessment value corresponding to the reading material typesetting strategy.

[0013] In some embodiments disclosed in the present invention, a reading material typesetting construction system based on analysis of excellent children's books is also disclosed, including: The first module is used to obtain a number of excellent children's book materials and split the excellent children's book materials into independent content to obtain a number of independent content units; The second module is used to identify the text content of each independent content unit to obtain the text content, and to perform semantic recognition on the text content to determine a number of semantic keywords, and to combine the semantic keywords in the original order to obtain semantic keyword groups, and to group and mark the semantic keyword groups based on the sentences to which different semantic keywords belong to obtain a number of semantic sub-keyword groups, and to construct a semantic keyword group relationship tree for situations where the text content can be combined; The third module is used to identify the image content of each independent content unit, output the identification result in the form of image text description to obtain image description information, combine the image description keywords in the image description information to obtain image description keyword groups, and establish a mapping relationship between the image description keyword groups and the semantic keyword group relationship tree based on the correspondence between the image content and the text content; The fourth module is used to divide and locate the decoration components in the independent content unit, and evenly set a number of decoration component detection points for each decoration component, each decoration component detection point is set with a position coordinate and a color parameter, and all the decoration component detection points are combined according to the original position to form a decoration component detection point array template, and the decoration component detection point array template is associated with the semantic keyword group relationship tree; The fifth module is used to record the combination of the semantic keyword group relationship tree, the image description keyword and the decoration component exploration point array template as an excellent typesetting data reference group, and configure the reading type for the excellent typesetting data reference group to obtain an excellent typesetting data reference library; The sixth module is used to use the excellent typesetting data reference library to conduct value assessment on several reading material typesetting strategies currently being constructed, and determine the optimal reading material typesetting strategy based on the value assessment value.

[0014] The present invention discloses a method and system for constructing a typesetting of reading materials based on the analysis of excellent children's books, and relates to the technical field of typesetting strategy generation of reading materials. First, excellent children's book materials are collected and split into independent content units, and then the text content is identified, semantic keywords are extracted, and a relationship tree is constructed; the image content is identified, image description keywords are extracted, and a mapping relationship is established with the semantic keyword group relationship tree; the scheme also divides and locates the decorative components, and sets the decorative component exploration points to form an exploration point array template, which is associated with the semantic keyword group relationship tree; these elements are combined into an excellent typesetting data reference group, and the reading type is configured to construct an excellent typesetting data reference library; the current reading typesetting strategy is evaluated for value, and the optimal strategy is determined. The present invention provides a scientific basis and effective guidance for the typesetting design of children's books by systematically analyzing the typesetting of excellent reading materials, which helps to improve the reading experience and attractiveness of children's books.

[0015] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 This is a method step diagram of a method for constructing a book typesetting based on analysis of excellent children's books disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0017] The technical solution of the present invention is further described below through the accompanying drawings and embodiments.

[0018] The following will be combined with the accompanying drawings and specific embodiments to clearly and completely describe the technical solution of the present invention. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention and cannot be understood as limiting the scope of protection of the present invention. Those skilled in the art in this field can make some non-essential improvements and adjustments based on the content of the present invention described below. In the present invention, unless otherwise clearly specified and limited, the technical terms used in the present invention should be the common meanings understood by the technical personnel described in the present invention.

[0019] Example:

[0020] The present invention discloses a method for constructing a typesetting of reading materials based on the analysis of excellent children's books, see Figure 1 ,include: Step S100, obtaining a number of excellent children's book materials, and performing independent content splitting on the excellent children's book materials to obtain a number of independent content units.

[0021] The core of this step is to collect and organize excellent children's books as the basis for subsequent analysis. In order to deeply understand the typesetting strategies in these books, each book is first divided into several independent content units. These content units can be story chapters, knowledge point introductions, illustrations, etc., which are the basic elements that constitute the books. By splitting, the typesetting elements in each unit, such as text, images, decorative components, etc., can be analyzed more carefully, providing clear analysis objects for subsequent steps.

[0022] Step S200, recognize the text content of each independent content unit to obtain the paragraph content, and perform semantic recognition on the paragraph content to determine a number of semantic keywords, and combine the semantic keywords in the original order to obtain semantic keyword groups, and group and mark the semantic keyword groups based on the sentences to which different semantic keywords belong to obtain a number of semantic sub-keyword groups, and construct a semantic keyword group relationship tree for the situation where the paragraph content can be combined.

[0023] In this step, the text of each independent content unit after the split is first recognized to extract the content of the paragraph. Subsequently, these paragraphs are deeply analyzed using semantic recognition technology to determine several semantic keywords. These keywords are the core and essence of the paragraph content. Next, these keywords are combined in the original order to form semantic keyword groups, and based on the sentences to which different keywords belong, the keyword groups are further grouped and marked to obtain several semantic sub-keyword groups. Finally, based on the logical relationship between the paragraph contents, a semantic keyword group relationship tree is constructed to intuitively display the hierarchical structure and association relationship of the paragraph content.

[0024] In some embodiments disclosed in the present invention, the method for constructing a semantic keyword phrase relationship tree includes: Step S201 : construct a text content sequence according to the original order of the text content, and construct a trunk of a semantic keyword group key tree based on the text content sequence, wherein each semantic keyword group corresponds to a tree node.

[0025] In some embodiments disclosed in the present invention, the first step of constructing a semantic keyword relationship tree is to process the order of the text content. According to the original order of the text content, that is, the order in which they appear in the reading material, a text content sequence is constructed. This sequence provides a clear timeline or logic line to help understand the association and hierarchy between the texts.

[0026] Next, the trunk of the semantic keyword group key tree is constructed based on this text content sequence. In this process, each semantic keyword group is regarded as an independent tree node, and these nodes are arranged on the trunk in the order of the text content. In this way, the trunk reflects the basic flow and main information points of the text content, providing a solid foundation for subsequent analysis and presentation.

[0027] Step S202 , analyzing each paragraph content for other paragraph contents that can be paralleled, and extending a tree branch at the corresponding tree node to form a semantic keyword group relationship tree.

[0028] After constructing the trunk of the semantic keyword group key tree, it is necessary to further analyze the parallel relationship between the content of the paragraphs. Parallel relationships refer to the relationship between paragraphs that are independent of each other in content, theme or logic, but together constitute a complete story or knowledge point. By identifying these parallel relationships, we can have a deeper understanding of the internal connection and hierarchical structure between paragraphs.

[0029] After identifying the parallel relationship, one or more tree branches are extended from the corresponding tree nodes to represent these parallel relationships. Each tree branch represents a parallel text content or semantic keyword group, which are connected to the nodes on the trunk and together form a semantic keyword group relationship tree. This relationship tree not only reflects the order of the text content, but also reveals the parallel and hierarchical relationship between them, providing strong support for the subsequent analysis and optimization of the reading material typesetting strategy.

[0030] In some embodiments disclosed in the present invention, a method for performing semantic recognition on a text content and determining a number of semantic keywords includes: Step S203, a focus keyword library is set for excellent children's books, the focus keyword library includes several types of focus keyword sets, and each type of focus keyword set includes several focus keywords.

[0031] In some embodiments disclosed in the present invention, in order to more accurately identify semantic keywords in the content of a passage, a focus keyword library is first set for excellent children's books. This keyword library is pre-constructed and contains multiple types of focus keyword sets, and each type of keyword set is carefully selected and organized for a specific theme, field or content type. For example, for story-telling books, the focus keyword set may include character names, place names, event keywords, etc.; for popular science books, it may include keywords such as scientific terms and concept explanations. Such a setting can ensure that in the subsequent analysis, the core and key information in the passage content can be captured in a targeted manner.

[0032] Step S204, preprocessing the text content, including word segmentation, removal of stop words and part-of-speech tagging, to obtain a number of candidate keywords, and performing attention degree analysis on the candidate keywords, including determining the occurrence frequency and relative relationship characteristics of the candidate keywords, and based on the occurrence frequency and relative relationship characteristics, determining the attention degree of the candidate keywords, and based on the attention degree of the candidate keywords, screening out a number of candidate keywords.

[0033] Next, the text content is preprocessed to convert the original text into a form more suitable for analysis. The preprocessing steps include word segmentation, stop word removal, and part-of-speech tagging. Through these operations, a series of candidate keywords can be obtained. Then, the attention level of these candidate keywords is analyzed, mainly examining their frequency of occurrence and relative relationship characteristics. The frequency of occurrence reflects the importance and significance of the keywords in the text, while the relative relationship characteristics help understand the association and hierarchy between keywords. Based on these analysis results, the attention level of each candidate keyword can be determined, and a number of candidate keywords with high attention levels can be screened out as candidates for subsequent analysis.

[0034] Step S205, based on the pre-marked type of the text content, determine the focus keyword set called in the focus keyword library, and bring several candidate keywords into the focus keyword set for comparison. If there is a mapped focus keyword in the focus keyword set, the corresponding candidate keyword is identified as a semantic keyword.

[0035] After completing the screening of candidate keywords, call the corresponding focus keyword set from the focus keyword library according to the pre-marked type of the text content. This step is to ensure that the analysis can closely fit the actual characteristics and needs of the text content. Then, bring the screened candidate keywords into the focus keyword set for comparison. If a focus keyword matching the candidate keyword is found in the focus keyword set, then this candidate keyword is identified as a semantic keyword. This identification process not only takes into account the characteristics and importance of the keywords themselves, but also fully considers their relevance and representativeness under specific types and topics, thereby ensuring the accuracy and effectiveness of semantic keyword recognition.

[0036] In some embodiments disclosed in the present invention, the method for determining the attention level of candidate keywords includes: Step S2041, determine the relative position of the candidate keyword in the sentence, and configure an initial attention parameter for the candidate keyword based on the determined relative position, and modify the initial attention parameter based on the occurrence frequency of the candidate keyword to obtain the attention degree.

[0037] The expression for calculating the degree of attention is: .

[0038] in, For the level of attention, is the attention conversion coefficient, is the initial focus parameter, is the frequency of occurrence of the candidate keywords, is the frequency impact adjustment coefficient, Adjust constants for frequency effects; The method for determining the relative position of the candidate keywords in the sentence includes performing syntactic structure analysis on the sentence, identifying the subject, predicate and object components, and determining the position of the candidate keywords in the syntactic structure.

[0039] Step S300, recognize the image content of each independent content unit, output the recognition result in the form of image text description to obtain image description information, combine the image description keywords in the image description information to obtain image description keyword groups, and establish a mapping relationship between the image description keyword groups and the semantic keyword group relationship tree based on the correspondence between the image content and the text content.

[0040] This step focuses on the recognition and analysis of image content. For each image in an independent content unit, image recognition technology is used to convert it into an image text description, thereby extracting the key information in the image. Next, the keywords in these image descriptions are combined to form image description keyword groups. In order to deeply understand the connection between image and text content, a mapping relationship between image description keyword groups and semantic keyword group relationship trees is established based on the correspondence between image content and text content. This step helps to grasp the layout and presentation of images in typesetting, and how they echo the text content.

[0041] In some embodiments disclosed in the present invention, the method for identifying the image content of each independent content unit includes: Step S301 : dividing the content units in the image content, including objects, people, animals and scenes in the image content, and determining the directional relationship between the objects, people and animals.

[0042] When identifying the image content of each independent content unit, the image is first divided carefully to identify and distinguish the various content units in the image, which may include objects, people, animals, and scenes. The purpose of this step is to decompose the complex image content into basic elements that are easier to understand and analyze. Then, the relationship between these content units is deeply analyzed, especially the directional relationship between objects, people, and animals, such as who is using what object, the interaction between people and animals, etc. These directional relationships are crucial to understanding the story clues, emotional expression, and visual focus in the image content.

[0043] Step S302, constructing an image description information group according to the image content, the image description information group includes a plurality of object description units, a plurality of character description units, a plurality of animal description units and a scene description unit, wherein the object description unit includes a plurality of object description keywords, the character description unit includes a plurality of character description keywords, the animal description unit includes a plurality of animal description keywords, and the scene description unit includes a plurality of scene description keywords.

[0044] After completing the division of image content units, we start to build an image description information group. This information group is a comprehensive and detailed description of the image content, which includes several object description units, character description units, animal description units, and scene description units. Each description unit contains a series of description keywords, which are accurate distillations of the characteristics, attributes, or states of the corresponding content units. By building such a description information group, we can understand and express the image content more systematically, providing a rich information basis for subsequent analysis and presentation.

[0045] Step S303, based on the pointing relationship between objects, people and animals, construct a unit relationship sequence for the corresponding object description units, person description units and animal description units, the unit relationship sequence includes other object description units, person description units or animal description units with pointing relationship.

[0046] Finally, based on the pointing relationship between the objects, characters, and animals determined in step S301, the corresponding description units are arranged in order to construct a unit relationship sequence. This sequence not only reflects the association and interaction between the various elements in the image content, but also reveals the hierarchy and order between them. For example, a character description unit may point to an object description unit, indicating that the character is using the object; and an animal description unit may follow a character description unit, indicating that the animal is part of or the result of the character's action. By constructing such a unit relationship sequence, the story clues and emotional expressions in the image content can be presented more clearly, providing strong support for the typesetting and presentation of reading materials.

[0047] Step S400, divide and locate the decoration components in the independent content unit, and evenly set a number of decoration component probe points for each decoration component, each decoration component probe point is set with a position coordinate and a color parameter, and all the decoration component probe points are combined according to the original position to form a decoration component probe point array template, and an association relationship is established between the decoration component probe point array template and the semantic keyword group relationship tree.

[0048] In this step, we focus on the decorative components in the reading material, such as borders, backgrounds, icons, etc. First, these decorative components are divided and located to clarify their positions and functions in the typesetting. Then, a number of decorative component probe points are evenly set for each decorative component, and the position coordinates and color parameters are set for each probe point. These probe points constitute the probe point array template of the decorative component, which can fully reflect the morphological and color characteristics of the decorative component. Finally, the decorative component probe point array template is associated with the semantic keyword group relationship tree, so that the coordination and integrity of the decorative component with the text and image content can be comprehensively considered in the subsequent analysis.

[0049] Step S500, record the combination of the semantic keyword group relationship tree, the image description keyword and the decoration component probe point array template as an excellent typesetting data reference group, and configure the reading material type for the excellent typesetting data reference group to obtain an excellent typesetting data reference library.

[0050] After the previous steps, the typesetting elements in excellent children's books have been comprehensively analyzed and extracted. In this step, the semantic keyword group relationship tree, image description keywords, and decorative component exploration point array templates are combined to form an excellent typesetting data reference group. These data reference groups are a concentrated embodiment of the typesetting strategy of excellent reading materials. Next, each data reference group is configured with a corresponding reading material type, such as story, popular science, picture book, etc., so that it can be matched and referenced more accurately in subsequent applications. Finally, all excellent typesetting data reference groups are combined to construct an excellent typesetting data reference library, which provides rich data support for the subsequent evaluation and optimization of reading material typesetting strategies.

[0051] Step S600, using an excellent typesetting data reference library to conduct a value assessment on several currently constructed reading material typesetting strategies, and based on the value assessment value, determine the optimal reading material typesetting strategy.

[0052] In this step, we use the built excellent typesetting data reference library to evaluate the value of several currently constructed typesetting strategies for reading materials. Through comparison and analysis, we can evaluate the pros and cons of each typesetting strategy in terms of content presentation, visual effects, reading experience, etc., and give corresponding value evaluation values. Finally, based on these evaluation values, we can determine the optimal typesetting strategy for reading materials, providing scientific and effective guidance for the publication and promotion of children's books.

[0053] In some embodiments disclosed in the present invention, the method for evaluating the value of the currently constructed reading material typesetting strategy by using an excellent typesetting data reference library includes: Step S601 , analyzing the typesetting strategy of the reading material, determining the semantic keywords in the strategy, and constructing the semantic sub-keyword groups in the strategy based on the semantic keywords in the strategy.

[0054] In the initial stage of value assessment of the currently constructed reading material layout strategy, the layout strategy must first be analyzed in depth. The core of this step is to identify and extract the semantic keywords in the strategy. These keywords are the core elements of the reading material content and are crucial for understanding the theme, plot and knowledge points of the reading material. After extracting the semantic keywords, these keywords are further combined according to their inherent logical relationships and hierarchical structures to form semantic sub-keyword groups in the strategy. The purpose of this step is to simplify the complex reading material content into a form that is easier to analyze and compare, providing a clear basis for subsequent value assessment.

[0055] Step S602: Analyze the typesetting strategy of the reading material, determine the image description information of the image content in the strategy, determine the detection point array template of the decoration component in the strategy, and construct the image description information group in the strategy based on the image description information.

[0056] Next, we continue to analyze the layout strategy of reading materials, focusing on the image content and decorative components in the strategy. For the image content, we extract and organize the image description information, including key elements such as objects, people, animals, and scenes in the image, and form the image description information group in the strategy. These information groups can intuitively reflect the role and effect of images in the layout of reading materials, which is of great significance for evaluating the visual appeal and information transmission ability of reading materials. At the same time, we also determine the decorative component exploration point array templates in the strategy. These templates describe the characteristics of the position, shape, and color of the decorative components in the layout, which are important bases for evaluating the aesthetics and integrity of the layout of reading materials.

[0057] Step S603 , forming a strategy layout data reference group by combining the strategy semantic sub-keyword group, the strategy image description information group and the strategy decoration component detection point array template corresponding to the reading material layout strategy.

[0058] After completing the analysis of semantic keywords, image description information, and decorative components, these elements are integrated to form a reference group of typographic data in the strategy. This reference group is a comprehensive and specific description of the reading material typographic strategy, which includes the core elements of the reading material content, the key features of the visual presentation, and the detailed information of the typographic design. By constructing such a reference group, the overall effect and value of the reading material typographic strategy can be understood and evaluated more systematically.

[0059] Step S604, determine a number of retrieval factors for the typesetting data reference group in the strategy, and based on the retrieval factors, retrieve a number of excellent typesetting data reference groups in the excellent typesetting data reference library, compare the retrieved excellent typesetting data reference groups with the typesetting data reference group in the strategy, and determine the value assessment value of the reading material typesetting strategy currently being constructed based on the comparison results.

[0060] Finally, according to the characteristics and requirements of the typesetting data reference group in the strategy, several retrieval factors are determined. These retrieval factors are the basis for searching similar or related typesetting data in the excellent typesetting data reference library. Through the search, one or more groups of excellent typesetting data reference groups similar to the currently constructed reading material typesetting strategy can be found. Next, these retrieved excellent typesetting data reference groups are compared and analyzed in detail with the typesetting data reference groups in the strategy to evaluate their pros and cons in terms of content presentation, visual effects, reading experience, etc. Finally, based on these comparison results, the value assessment value of the currently constructed reading material typesetting strategy can be determined. This value reflects the relative position and level of the strategy in excellent typesetting practice, and provides clear guidance and basis for subsequent optimization and improvement.

[0061] In some embodiments disclosed in the present invention, a method for determining a number of search factors in a layout data reference group in a strategy includes: Step S6041, randomly select a number of first initial retrieval factors from the semantic sub-keyword group in the strategy, randomly select a number of second initial retrieval factors from the image description information group in the strategy, and randomly select a number of third initial retrieval factors from the decoration component probe point array template in the strategy.

[0062] The process of determining a number of retrieval factors in the typesetting data reference group in the strategy first involves randomly screening the initial retrieval factors. The purpose of this step is to randomly select a certain number of keywords, description information or probe point features from the semantic sub-keyword group, image description information group and decorative component probe point array template in the strategy as initial retrieval factors. These initial retrieval factors will serve as the starting point for subsequent searches for similar or related typesetting data in the excellent typesetting data reference library.

[0063] Specifically, several first initial retrieval factors are randomly selected from the semantic sub-keyword groups in the strategy. These factors may be the core words or phrases in the content of the reading material, which are crucial for understanding the theme and plot of the reading material. At the same time, several second initial retrieval factors are randomly selected from the image description information group in the strategy. These factors describe the key elements or features in the image, such as objects, people, animals or scenes. In addition, several third initial retrieval factors are randomly selected from the decorative component exploration point array template in the strategy. These factors represent the specific position, shape or color characteristics of the decorative component in the layout.

[0064] Step S6042, substitute the first initial retrieval factor, the second initial retrieval factor and the third initial retrieval factor into the excellent typesetting data reference library respectively, calculate the reference group mapping number of the excellent typesetting data reference group mapped by each initial retrieval factor respectively, if the reference group mapping number is greater than or equal to the preset value, retain the corresponding initial retrieval factor, and identify the retained initial retrieval factor as the retrieval factor for the final search in the excellent data reference library.

[0065] Next, the selected initial search factors need to be verified to determine whether they are suitable as the basis for searching in the excellent typesetting data reference library. The core of this step is to calculate the number of reference group mappings of excellent typesetting data reference groups mapped by each initial search factor in the excellent typesetting data reference library. If the number of reference group mappings of an initial search factor is greater than or equal to the preset value (this preset value can be set according to actual conditions, such as the scale, diversity or search needs of the typesetting data), it means that this search factor has a certain degree of representativeness and universality in the excellent typesetting data, and can help find similar or related typesetting data. Therefore, this initial search factor is retained as a valid search factor.

[0066] Through the screening and verification of this step, a group of representative and effective retrieval factors can be determined, which will serve as the basis for subsequent searches for similar or related typographical data in the excellent typographical data reference library. This method can ensure that the search process is more accurate and efficient, thereby finding more excellent typographical data reference groups that are similar or related to the currently constructed reading material typesetting strategy, providing strong support for the value evaluation and optimization of the strategy.

[0067] In some embodiments disclosed in the present invention, the method of comparing the retrieved excellent typesetting data reference group with the typesetting data reference group in the strategy includes: Step S6043, the first mapping parameter mapped in the semantic sub-keyword group relationship tree relative to the excellent typesetting data reference group in the analysis strategy, the second mapping parameter mapped in the image description keyword group relative to the image description keyword group of the excellent typesetting data reference group in the analysis strategy, and the third mapping parameter mapped in the decoration component probe point array template relative to the decoration component probe point array template of the excellent typesetting data reference group in the analysis strategy.

[0068] Step S6044, based on the first mapping parameter, the second mapping parameter and the third mapping parameter, determine the degree of equivalence between each retrieved excellent typesetting data reference group and the typesetting data reference group in the strategy, and based on the corresponding degrees of equivalence of all retrieved excellent typesetting data reference groups, determine the value assessment value of the reading material typesetting strategy.

[0069] Among them, the expression for calculating the degree of equality between the excellent typesetting data reference group and the typesetting data reference group in the strategy is: .

[0070] in, To the same extent, is the first mapping parameter weight adjustment coefficient, is the second mapping parameter weight adjustment coefficient, is the third mapping parameter weight adjustment coefficient, is the mapping calculation function of the semantic sub-keyword group in the strategy, which is used to determine whether the semantic sub-keyword group in the i1th strategy is mapped to the semantic keyword group relationship tree. If the mapping is determined, then Output 1, otherwise output 0, wherein the method of determining whether the semantic sub-keyword group in the policy is mapped to the semantic keyword group relationship tree includes judging whether the proportion of the semantic sub-keywords in the policy that are mapped in the semantic sub-keyword group in the policy is greater than or equal to a preset value, and if it is greater than or equal to the preset value, then it is determined that the semantic sub-keyword group in the policy is mapped to the semantic keyword group relationship tree, is the semantic sub-keyword group mapping impact adjustment coefficient in the strategy, is the semantic sub-keyword group mapping impact adjustment constant in the strategy, n1 is the number of semantic sub-keyword groups in the strategy, is the mapping calculation function of the image description keywords in the strategy, which is used to determine whether the image description keywords in the i2th strategy are mapped to the image description keyword group of the excellent typesetting data reference group. If the mapping is determined, then Output 1, otherwise output 0. is the impact adjustment coefficient of the image description keyword mapping in the strategy, is the mapping adjustment constant of the image description keyword group in the strategy, n2 is the number of image description keywords in the strategy in the image description keyword group, The mapping calculation function for the decoration component probe point array template in the strategy is used to determine whether the decoration component probe point in the i3th strategy is mapped to the decoration component probe point array template of the excellent typesetting data reference group. If the mapping is determined, then Output 1, otherwise output 0. It is the adjustment coefficient of the decorative component exploration point mapping in the strategy. Adjust constants for the detection point mapping effect of the decoration component in the strategy, The number of probe points in the probe point array template of the decoration component in the strategy.

[0071] In some embodiments disclosed in the present invention, a method for determining the value evaluation value of a reading material typesetting strategy based on the equivalent degree corresponding to all retrieved excellent typesetting data reference groups is also disclosed, including: Step S60441, determine the first reference group number of the retrieved excellent typesetting data reference group, and judge whether the degree of equivalence corresponding to each excellent typesetting data reference group is greater than or equal to a preset value. If it is greater than or equal to the preset value, mark the reading material typesetting strategy once.

[0072] Step S60442, calculate the reference group quantity ratio of the second reference group quantity to the first reference group quantity of the marked reading material typesetting strategy, analyze the preset reference group quantity ratio interval to which the reference group quantity ratio belongs, and identify the value assessment value corresponding to the preset reference group quantity ratio interval as the value assessment value corresponding to the reading material typesetting strategy.

[0073] In some embodiments disclosed in the present invention, a reading material typesetting construction system based on analysis of excellent children's books is also disclosed, including: The first module is used to obtain a number of excellent children's book materials, and to separate the excellent children's book materials into independent content to obtain a number of independent content units.

[0074] The second module is used to identify the text content of each independent content unit to obtain the text content, and perform semantic recognition on the text content to determine a number of semantic keywords, and combine the semantic keywords in the original order to obtain semantic keyword groups, and group and mark the semantic keyword groups based on the sentences to which different semantic keywords belong to obtain a number of semantic sub-keyword groups. In view of the fact that the text content can be combined, a semantic keyword group relationship tree is constructed.

[0075] The third module is used to identify the image content of each independent content unit, output the identification result in the form of image text description to obtain image description information, combine the image description keywords in the image description information to obtain image description keyword groups, and establish a mapping relationship between the image description keyword groups and the semantic keyword group relationship tree based on the correspondence between the image content and the text content.

[0076] The fourth module is used to divide and locate the decoration components in the independent content unit, and evenly set a number of decoration component detection points for each decoration component, each decoration component detection point is set with a position coordinate and a color parameter, and all the decoration component detection points are combined according to the original position to form a decoration component detection point array template, and the decoration component detection point array template is associated with the semantic keyword group relationship tree; The fifth module is used to record the combination of semantic keyword group relationship tree, image description keyword and decoration component probe point array template as an excellent typesetting data reference group, and configure the reading type for the excellent typesetting data reference group to obtain an excellent typesetting data reference library.

[0077] The sixth module is used to use the excellent typesetting data reference library to conduct value assessment on several reading material typesetting strategies currently being constructed, and determine the optimal reading material typesetting strategy based on the value assessment value.

[0078] The present invention discloses a method and system for constructing a typesetting of reading materials based on the analysis of excellent children's books, and relates to the technical field of typesetting strategy generation of reading materials. First, excellent children's book materials are collected and split into independent content units, and then the text content is identified, semantic keywords are extracted, and a relationship tree is constructed; the image content is identified, image description keywords are extracted, and a mapping relationship is established with the semantic keyword group relationship tree; the scheme also divides and locates the decorative components, and sets the decorative component exploration points to form an exploration point array template, which is associated with the semantic keyword group relationship tree; these elements are combined into an excellent typesetting data reference group, and the reading type is configured to construct an excellent typesetting data reference library; the current reading typesetting strategy is evaluated for value, and the optimal strategy is determined. The present invention provides a scientific basis and effective guidance for the typesetting design of children's books by systematically analyzing the typesetting of excellent reading materials, which helps to improve the reading experience and attractiveness of children's books.

[0079] Through the description of the above implementation methods, those skilled in the art can clearly understand that the present invention can be implemented by hardware, or by software plus a necessary general hardware platform. Based on such an understanding, the technical solution of the present invention can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.), including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each implementation scenario of the present invention.

[0080] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that they can still modify or replace the technical solution of the present invention with equivalents, and these modifications or equivalent replacements cannot cause the modified technical solution to deviate from the spirit and scope of the technical solution of the present invention.

Claims

1. A method for constructing a typesetting of reading materials based on the analysis of excellent children's books, characterized in that: include: Acquire a number of excellent children's book materials, and separate the excellent children's book materials into independent content to obtain a number of independent content units; Identify the text content of each independent content unit to obtain the paragraph content, perform semantic recognition on the paragraph content, determine a number of semantic keywords, and combine the semantic keywords in the original order to obtain semantic keyword groups, and group and mark the semantic keyword groups based on the sentences to which different semantic keywords belong to obtain a number of semantic sub-keyword groups, and construct a semantic keyword group relationship tree for situations where the paragraph content can be combined; Recognize the image content of each independent content unit, output the recognition result in the form of image text description to obtain image description information, combine the image description keywords in the image description information to obtain image description keyword groups, and establish a mapping relationship between the image description keyword groups and the semantic keyword group relationship tree based on the correspondence between the image content and the text content; The decoration components in the independent content unit are divided and positioned, and a number of decoration component detection points are evenly set for each decoration component, each decoration component detection point is set with a position coordinate and a color parameter, and all the decoration component detection points are combined according to the original positions to form a decoration component detection point array template, and an association relationship is established between the decoration component detection point array template and the semantic keyword group relationship tree; The combination of the semantic keyword group relationship tree, the image description keyword and the decoration component exploration point array template is recorded as an excellent typesetting data reference group, and the reading material type is configured for the excellent typesetting data reference group to obtain an excellent typesetting data reference library; Use the excellent typesetting data reference library to conduct a value assessment on several reading material typesetting strategies currently being constructed, and determine the optimal reading material typesetting strategy based on the value assessment.

2. The method for constructing a typesetting of reading materials based on the analysis of excellent children's books according to claim 1, characterized in that: The method of constructing a semantic keyword phrase relationship tree includes: According to the original order of the paragraph content, a paragraph content sequence is constructed, and based on the paragraph content sequence, a trunk of a semantic keyword group key tree is constructed, wherein each semantic keyword group corresponds to a tree node; Analyze the contents of each paragraph and other paragraphs that can be paralleled, and extend a tree branch at the corresponding tree node to form a semantic keyword relationship tree.

3. The method for constructing a typesetting of reading materials based on the analysis of excellent children's books according to claim 1, characterized in that: Methods for performing semantic recognition on the content of a text segment and determining a number of semantic keywords include: A focus keyword library is set for excellent children's books. The focus keyword library includes several types of focus keyword sets, and each type of focus keyword set includes several focus keywords; Preprocess the text content, including word segmentation, stop word removal and part-of-speech tagging, to obtain several candidate keywords, and analyze the attention level of the candidate keywords, including determining the occurrence frequency and relative relationship characteristics of the candidate keywords, and determining the attention level of the candidate keywords based on the occurrence frequency and relative relationship characteristics, and screening out several candidate keywords based on the attention level of the candidate keywords; Based on the pre-marked type of the text content, the focus keyword set called in the focus keyword library is determined, and several candidate keywords are brought into the focus keyword set for comparison. If there is a mapped focus keyword in the focus keyword set, the corresponding candidate keyword is identified as a semantic keyword.

4. The method for constructing a typesetting of reading materials based on analysis of excellent children's books according to claim 3, characterized in that: Methods for determining the popularity of candidate keywords include: Determine the relative position of the candidate keyword in the sentence, and based on the determined relative position, configure an initial attention parameter for the candidate keyword, and based on the occurrence frequency of the candidate keyword, modify the initial attention parameter to obtain the attention degree; The expression for calculating the degree of attention is: ； in, For the level of attention, is the attention conversion coefficient, is the initial focus parameter, is the frequency of occurrence of the alternative keywords, is the frequency impact adjustment coefficient, Adjust constants for frequency effects; The method for determining the relative position of the candidate keywords in the sentence includes performing syntactic structure analysis on the sentence, identifying the subject, predicate and object components, and determining the position of the candidate keywords in the syntactic structure.

5. The method for constructing a typesetting of reading materials based on the analysis of excellent children's books according to claim 1, characterized in that: The method for identifying the image content of each independent content unit includes: Divide the content units in the image content, including objects, people, animals and scenes in the image content, and determine the directional relationship between the objects, people and animals; Constructing an image description information group according to the image content, the image description information group including a plurality of object description units, a plurality of person description units, a plurality of animal description units and a scene description unit, wherein the object description unit includes a plurality of object description keywords, the person description unit includes a plurality of person description keywords, the animal description unit includes a plurality of animal description keywords, and the scene description unit includes a plurality of scene description keywords; Based on the pointing relationship between objects, people and animals, a unit relationship sequence is constructed for the corresponding object description units, person description units and animal description units, and the unit relationship sequence includes other object description units, person description units or animal description units with pointing relationship.

6. The method for constructing a typesetting of reading materials based on the analysis of excellent children's books according to claim 5, characterized in that: Methods for using excellent typesetting data reference libraries to evaluate the value of currently constructed reading material typesetting strategies include: Analyze the layout strategy of the reading material, determine the semantic keywords in the strategy, and construct the semantic sub-keyword groups in the strategy based on the semantic keywords in the strategy; Analyze the typesetting strategy of the reading material, determine the image description information of the image content in the strategy, determine the detection point array template of the decorative component in the strategy, and construct the image description information group in the strategy based on the image description information; The semantic sub-keyword group in the strategy, the image description information group in the strategy and the decorative component probe point array template in the strategy corresponding to the reading material typesetting strategy form a typesetting data reference group in the strategy; Several retrieval factors are determined for the typesetting data reference group in the strategy, and based on the retrieval factors, several excellent typesetting data reference groups are retrieved from the excellent typesetting data reference library, and the retrieved excellent typesetting data reference groups are compared with the typesetting data reference groups in the strategy. Based on the comparison results, the value assessment value of the reading material typesetting strategy currently being constructed is determined.

7. The method for constructing a typesetting of reading materials based on the analysis of excellent children's books according to claim 6, characterized in that: Methods for determining a number of search factors in the layout of the data reference group in the strategy include: Randomly select a number of first initial retrieval factors from the semantic sub-keyword group in the strategy, randomly select a number of second initial retrieval factors from the image description information group in the strategy, and randomly select a number of third initial retrieval factors from the decoration component probe point array template in the strategy; The first initial retrieval factor, the second initial retrieval factor and the third initial retrieval factor are respectively substituted into the excellent typesetting data reference library, and the reference group mapping number of the excellent typesetting data reference group mapped by each initial retrieval factor is calculated respectively. If the reference group mapping number is greater than or equal to the preset value, the corresponding initial retrieval factor is retained, and the retained initial retrieval factor is identified as the retrieval factor for the final search in the excellent data reference library.

8. The method for constructing a typesetting of reading materials based on analysis of excellent children's books according to claim 6, characterized in that: The method for comparing the retrieved excellent typesetting data reference group with the typesetting data reference group in the strategy includes: The first mapping parameter mapped in the semantic sub-keyword group relationship tree relative to the excellent typesetting data reference group in the analysis strategy, the second mapping parameter of the image description keyword group relative to the image description keyword group of the excellent typesetting data reference group in the analysis strategy, and the third mapping parameter of the decoration component probe point array template relative to the decoration component probe point array template of the excellent typesetting data reference group in the analysis strategy; Based on the first mapping parameter, the second mapping parameter and the third mapping parameter, determine the degree of equivalence between each retrieved excellent typesetting data reference group and the typesetting data reference group in the strategy, and determine the value evaluation value of the reading material typesetting strategy based on the corresponding equivalence degrees of all retrieved excellent typesetting data reference groups; Among them, the expression for calculating the degree of equality between the excellent typesetting data reference group and the typesetting data reference group in the strategy is: ； in, To the same extent, is the first mapping parameter weight adjustment coefficient, is the second mapping parameter weight adjustment coefficient, is the third mapping parameter weight adjustment coefficient, is the mapping calculation function of the semantic sub-keyword group in the strategy, which is used to determine whether the semantic sub-keyword group in the i1th strategy is mapped to the semantic keyword group relationship tree. If the mapping is determined, then Output 1, otherwise output 0, wherein the method of determining whether the semantic sub-keyword group in the policy is mapped to the semantic keyword group relationship tree includes judging whether the proportion of the semantic sub-keywords in the policy that are mapped in the semantic sub-keyword group in the policy is greater than or equal to a preset value, and if it is greater than or equal to the preset value, then it is determined that the semantic sub-keyword group in the policy is mapped to the semantic keyword group relationship tree, is the semantic sub-keyword group mapping impact adjustment coefficient in the strategy, is the semantic sub-keyword group mapping impact adjustment constant in the strategy, n1 is the number of semantic sub-keyword groups in the strategy, is the mapping calculation function of the image description keywords in the strategy, which is used to determine whether the image description keywords in the i2th strategy are mapped to the image description keyword group of the excellent typesetting data reference group. If the mapping is determined, then Output 1, otherwise output 0. is the impact adjustment coefficient of the image description keyword mapping in the strategy, is the mapping adjustment constant of the image description keyword group in the strategy, n2 is the number of image description keywords in the strategy in the image description keyword group, The mapping calculation function for the decoration component probe point array template in the strategy is used to determine whether the decoration component probe point in the i3th strategy is mapped to the decoration component probe point array template of the excellent typesetting data reference group. If the mapping is determined, then Output 1, otherwise output 0. It is the adjustment coefficient of the detection point mapping impact of the decoration component in the strategy. Adjust constants for the detection point mapping effect of the decoration component in the strategy, The number of probe points in the probe point array template of the decoration component in the strategy.

9. The method for constructing a typesetting of reading materials based on analysis of excellent children's books according to claim 8, characterized in that: Based on the equivalent degree of all retrieved excellent typesetting data reference groups, the method for determining the value assessment value of the reading material typesetting strategy includes: Determine the number of the first reference groups of the retrieved excellent typesetting data reference groups, and judge whether the degree of equality corresponding to each excellent typesetting data reference group is greater than or equal to a preset value, and if it is greater than or equal to the preset value, mark the reading typesetting strategy once; Calculate the reference group quantity ratio of the second reference group quantity to the first reference group quantity of the marked reading material typesetting strategy, analyze the preset reference group quantity ratio interval to which the reference group quantity ratio belongs, and identify the value assessment value corresponding to the preset reference group quantity ratio interval as the value assessment value corresponding to the reading material typesetting strategy.

10. A reading material typesetting construction system based on the analysis of excellent children's books, characterized by: include: The first module is used to obtain a number of excellent children's books and split the excellent children's books into independent content units; The second module is used to identify the text content of each independent content unit to obtain the text content, and to perform semantic recognition on the text content to determine a number of semantic keywords, and to combine the semantic keywords in the original order to obtain semantic keyword groups, and to group and mark the semantic keyword groups based on the sentences to which different semantic keywords belong to obtain a number of semantic sub-keyword groups, and to construct a semantic keyword group relationship tree for situations where the text content can be combined; The third module is used to identify the image content of each independent content unit, output the identification result in the form of image text description to obtain image description information, combine the image description keywords in the image description information to obtain image description keyword groups, and establish a mapping relationship between the image description keyword groups and the semantic keyword group relationship tree based on the correspondence between the image content and the text content; The fourth module is used to divide and locate the decoration components in the independent content unit, and evenly set a number of decoration component detection points for each decoration component, each decoration component detection point is set with a position coordinate and a color parameter, and all the decoration component detection points are combined according to the original position to form a decoration component detection point array template, and the decoration component detection point array template is associated with the semantic keyword group relationship tree; The fifth module is used to record the combination of the semantic keyword group relationship tree, the image description keyword and the decoration component exploration point array template as an excellent typesetting data reference group, and configure the reading type for the excellent typesetting data reference group to obtain an excellent typesetting data reference library; The sixth module is used to use the excellent typesetting data reference library to conduct value assessment on several reading material typesetting strategies currently being constructed, and determine the optimal reading material typesetting strategy based on the value assessment value.

Images