Intelligent printing and typesetting method and device based on machine learning

Abstract

The invention relates to the technical field of image generation, and discloses an intelligent printing and typesetting method and device based on machine learning, and the method comprises the steps: collecting a demand description set of a user for target printing and typesetting, carrying out the feature extraction and conversion of the demand description set, and generating high-dimensional leading feature distribution to represent typesetting demands; performing data simulation on the high-dimensional feature distribution for multiple times by utilizing a pre-trained intelligent printing typesetting model to generate printing typesetting of multiple original versions, collecting optimization suggestions of users on typesetting of the original versions through a user feedback channel, adjusting the high-dimensional feature distribution according to feedback, and performing simulation again through the intelligent model to obtain typesetting of multiple original versions. Through analyzing the description mode of the demand description set provided by the user, the demand description set is subjected to value-oriented analysis, so that the intelligent printing and typesetting model is driven to work, and the problem that the intelligent typesetting efficiency is relatively low due to the fact that customer expectation cannot be accurately identified in the prior art is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of image generation, and in particular to an intelligent printing typesetting method and device based on machine learning. Background Art

[0002] Traditional printing typesetting design generally relies on manual experience or typesetting templates based on fixed rules. This method has certain limitations and cannot fully adapt to users' changing and personalized typesetting needs. In addition, the manual typesetting process is not only cumbersome and time-consuming, but the quality and effect of the design are also easily limited by the designer's experience, making it difficult to achieve a typesetting effect that fully meets user needs.

[0003] In recent years, with the rapid development of machine learning, deep learning and natural language processing technologies, intelligent typesetting technology has gradually become an effective means to improve typesetting efficiency and accuracy. Intelligent printing typesetting methods based on machine learning can automatically identify user needs and optimize typesetting design by learning from a large number of historical typesetting samples, thereby generating high-quality printed product typesetting plans. However, when using machine learning models for intelligent printing typesetting, it is often impossible to accurately identify the expectations of customers for the finished product in their needs, which leads to errors in the generation direction, leaving room for improvement in the efficiency of intelligent printing typesetting. Summary of the invention

[0004] The purpose of the present invention is to provide a method and device for intelligent printing typesetting based on machine learning, aiming to solve the problem in the prior art that the customer expectations cannot be accurately identified, resulting in low efficiency of intelligent typesetting.

[0005] The present invention is implemented in this way. In a first aspect, the present invention provides an intelligent printing typesetting method based on machine learning, comprising: Obtaining a user's requirement description set for printing and typesetting of a target finished product; wherein the requirement description set includes a plurality of requirement description information, and the requirement description information is used to describe the user's typesetting requirements for printing and typesetting of the target finished product; Extracting the feature of the description mode and converting the feature of the guiding value on the demand description set, so as to obtain the high-dimensional guiding feature distribution of the demand description set corresponding to the target finished product printing typesetting; Performing multiple data simulations on the high-dimensional guiding feature distribution according to a pre-trained intelligent printing typesetting model to obtain a plurality of original version printing typesets corresponding to the high-dimensional guiding feature distribution; Building a user feedback channel based on each of the original version printing layouts, and accepting user optimization suggestions for each of the original version printing layouts through the user feedback channel; The high-dimensional guiding feature distribution is modified according to the optimization suggestion, and data simulation is performed on the modified high-dimensional guiding feature distribution according to the pre-trained intelligent printing typesetting model to obtain the target finished product printing typesetting.

[0006] In a second aspect, the present invention provides an intelligent printing typesetting device based on machine learning, which is used to implement an intelligent printing typesetting method based on machine learning as described in any one of the first aspects, including: A demand acquisition module is used to acquire a user's demand description set for printing and typesetting of a target finished product; wherein the demand description set includes a plurality of demand description information, and the demand description information is used to describe the user's typesetting demand for printing and typesetting of the target finished product; A guidance analysis module, used for extracting the features of the description mode and converting the features of the guidance value of the demand description set to obtain a high-dimensional guidance feature distribution of the demand description set corresponding to the target finished product printing typesetting; A preliminary simulation module, used for performing multiple data simulations on the high-dimensional guiding feature distribution according to a pre-trained intelligent printing typesetting model, so as to obtain a plurality of original versions of printing typesetting corresponding to the high-dimensional guiding feature distribution; An optimization feedback module, used to construct a user feedback channel based on each of the original version printing layouts, and accept optimization suggestions from users on each of the original version printing layouts through the user feedback channel; The typesetting correction module is used to correct the high-dimensional guiding feature distribution according to the optimization suggestion, and perform data simulation on the corrected high-dimensional guiding feature distribution according to the pre-trained intelligent printing typesetting model to obtain the target finished product printing typesetting.

[0007] The present invention provides an intelligent printing typesetting method based on machine learning, which has the following beneficial effects: The present invention collects a set of user demand descriptions for target printing and typesetting, extracts and transforms features of the demand description set, generates a high-dimensional directed feature distribution to characterize the typesetting requirements, uses a pre-trained intelligent printing and typesetting model to perform multiple data simulations on the high-dimensional feature distribution, generates multiple original versions of printing and typesetting, collects user optimization suggestions for the typesetting of each original version through a user feedback channel, adjusts the high-dimensional feature distribution based on the feedback, and re-simulates through the intelligent model to generate the final target finished product printing and typesetting, analyzes the description pattern of the demand description set provided by the user, and guides the value analysis of the demand description set, thereby driving the operation of the intelligent printing and typesetting model, thereby solving the problem of low efficiency of intelligent typesetting caused by the inability to accurately identify customer expectations in the prior art. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] Figure 1It is a schematic diagram of the steps of an intelligent printing typesetting method based on machine learning provided by an embodiment of the present invention; Figure 2 It is a structural schematic diagram of an intelligent printing and typesetting device based on machine learning provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0009] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0010] The implementation of the present invention is described in detail below in conjunction with specific embodiments.

[0011] Reference Figure 1 , Figure 2 As shown, a preferred embodiment of the present invention is provided.

[0012] In a first aspect, the present invention provides an intelligent printing typesetting method based on machine learning, comprising: S1: Obtaining a user's requirement description set for printing and typesetting of a target finished product; wherein the requirement description set includes a number of requirement description information, and the requirement description information is used to describe the user's typesetting requirements for printing and typesetting of the target finished product; S2: extracting the feature of the description mode and converting the feature of the guiding value of the demand description set to obtain a high-dimensional guiding feature distribution of the demand description set corresponding to the target finished product printing typesetting; S3: performing multiple data simulations on the high-dimensional guiding feature distribution according to the pre-trained intelligent printing typesetting model to obtain several original versions of printing typesetting corresponding to the high-dimensional guiding feature distribution; S4: constructing a user feedback channel based on the printing and typesetting of each original version, and accepting optimization suggestions from users on the printing and typesetting of each original version through the user feedback channel; S5: Correcting the high-dimensional guiding feature distribution according to the optimization suggestion, and performing data simulation on the corrected high-dimensional guiding feature distribution according to the pre-trained intelligent printing typesetting model to obtain the target finished product printing typesetting.

[0013] Specifically, in step S1 of the embodiment provided by the present invention, a set of user requirement descriptions for target finished product printing and typesetting is obtained. The target finished product printing and typesetting is the printing and typesetting that the user wants to obtain, that is, the user provides corresponding requirement description information based on his or her expectations for the final product of the printing and typesetting that he or she wants to obtain. These requirement description information describe the user's typesetting requirements for the target finished product printing and typesetting, and multiple requirement description information together constitute a requirement description set.

[0014] More specifically, the requirement description information can be text or an image. Different types of requirement description information convey different user expectations, so different parsing methods are needed to obtain the user's actual expectations for the target finished product printing layout.

[0015] It should be noted that the technical solution of the present invention uses a machine learning algorithm model that has been pre-trained with a large amount of data to generate corresponding printing layouts for the expectations put forward by users. The generation effect of the printing layout depends on two points: one is the training degree of the machine learning algorithm model, and the other is the accuracy of the user expectations input into the model.

[0016] Specifically, in step S2 of the embodiment provided by the present invention, in order to improve the accuracy of user expectations input into the model, feature extraction of description patterns and feature conversion of guiding values ​​are performed on the requirement description set to obtain a high-dimensional guiding feature distribution of the target finished product printing layout corresponding to the requirement description set.

[0017] It can be understood that the purpose of this step is to extract the features of the description pattern of the requirement description set proposed by the user, determine the analysis method for conducting value analysis on the requirement description set itself based on the extracted description pattern, and then use the obtained analysis method to conduct value analysis on the requirement description set, and obtain the user's actual expectations for the target finished product printing and typesetting, which is applied to the model generation direction of the pre-trained intelligent printing and typesetting model, that is, the high-dimensional guided feature distribution.

[0018] More specifically, the description pattern is the existence pattern of each requirement description information in the requirement description set provided by the user, including the proportion of information type of each requirement description information and the emotional color of the wording used in each requirement description information. The guiding value is the model production direction that can be applied to the intelligent printing and typesetting model actually fed back by the requirement description information provided by the user, that is, the guiding feature that guides the intelligent printing and typesetting model to perform intelligent generation work.

[0019] More specifically, based on the proportion of information types of each requirement description information, the conversion method for converting the requirement description information into the model generation direction of the intelligent printing and typesetting model can be derived. When the proportion of text and image in the requirement description set is different, the method of converting the text-type requirement description information and the image-type requirement description information is also different. This is because the final presentation of the target finished product printing and typesetting is in the form of an image. Therefore, there is a difference in the degree of fit between the text-type requirement description information and the image-type requirement description information and the target finished product printing and typesetting. When the proportions of the text-type requirement description information and the image-type requirement description information are different, the specific degree of fit will also be affected. Therefore, it is necessary to adjust the conversion method according to the proportion.

[0020] More specifically, based on the emotional color of the wording used in each requirement description information, the conversion method of converting the requirement description information into the model generation direction of the intelligent printing and typesetting model can be derived. Each requirement description information itself contains emotional color, and its emotional color can guide the user to one aspect of the final presentation state of the target finished product printing and typesetting, and the requirement description information can lead to multiple generation directions of the intelligent printing and typesetting model. Based on the aspect obtained from the emotional color, the multiple generation directions that the requirement description information can lead to are selected and determined, so as to accurately obtain the model generation direction that can feedback the user's actual expectations and can be applied to the intelligent printing and typesetting model, that is, high-dimensional guided feature distribution.

[0021] Specifically, in step S3 of the embodiment provided by the present invention, multiple data simulations are performed on the high-dimensional guiding feature distribution according to the pre-trained intelligent printing and typesetting model to obtain several original versions of printing and typesetting corresponding to the high-dimensional guiding feature distribution. The intelligent printing and typesetting model is a machine learning algorithm model that has been pre-trained with a large amount of training data. Through the generation of the intelligent printing and typesetting model, the original version of printing and typesetting that meets the expected target finished product printing and typesetting can be obtained quickly and efficiently.

[0022] More specifically, the training data of the intelligent printing typesetting model is a large number of typesetting samples and the corresponding high-dimensional guided feature distribution. Therefore, the intelligent printing typesetting model can produce several corresponding original versions of printing typesetting through the high-dimensional guided feature distribution.

[0023] More specifically, the high-dimensional guiding feature distribution is the user's expectation of the target finished product printing and typesetting, which is implemented in the working guidance direction of the intelligent printing and typesetting model, and the original version printing and typesetting is the working feedback of the intelligent printing and typesetting model corresponding to the high-dimensional guiding feature distribution. It should be noted that several original version printing and typesetting can be of two types. The first type is consistent in the general direction but has deviations in details, and the second type has different understandings of the high-dimensional guiding feature distribution in the general direction, that is, it is inconsistent in the general direction.

[0024] Specifically, in step S4 of the embodiment provided by the present invention, a user feedback channel is constructed based on each original version printing layout, and the user's optimization suggestions for each original version printing layout are accepted through the user feedback channel. The optimization suggestions received through the user feedback channel are used to determine which of several original version printing layouts best meets the user's expectations, and subsequent optimization is performed based on the user's feedback to further improve the printing layout, thereby obtaining the target finished printing layout.

[0025] It should be noted that the user feedback channel can have various forms, including a basic selection form, that is, for users to interactively select the original version of the printing layout that best meets their expectations. The user feedback channel can also be a description form consistent with the demand description set, that is, for users to interact to provide optimization suggestions in text and image form, and through the analysis of the optimization suggestions, further obtain the expectations for the target finished product printing layout reflected by the user's identification information.

[0026] Specifically, in step S5 of the embodiment provided by the present invention, the high-dimensional guiding feature distribution is corrected according to the optimization suggestion, and the corrected high-dimensional guiding feature distribution is simulated according to the pre-trained intelligent printing typesetting model to obtain the target finished product printing typesetting.

[0027] It can be understood that after obtaining the optimization suggestions, the high-dimensional guiding feature distribution is corrected to obtain a high-dimensional guiding feature distribution that better meets user expectations, and data simulation is performed on the corrected high-dimensional guiding feature distribution according to the pre-trained intelligent printing and typesetting model. After that, the steps of obtaining the optimization suggestions and correcting the high-dimensional guiding feature distribution according to the optimization suggestions can be repeated, and this process is continuously repeated until the target finished printing and typesetting is obtained.

[0028] The present invention provides an intelligent printing typesetting method based on machine learning, which has the following beneficial effects: The present invention collects a set of user demand descriptions for target printing and typesetting, extracts and transforms features of the demand description set, generates a high-dimensional directed feature distribution to characterize the typesetting requirements, uses a pre-trained intelligent printing and typesetting model to perform multiple data simulations on the high-dimensional feature distribution, generates multiple original versions of printing and typesetting, collects user optimization suggestions for the typesetting of each original version through a user feedback channel, adjusts the high-dimensional feature distribution based on the feedback, and re-simulates through the intelligent model to generate the final target finished product printing and typesetting, analyzes the description pattern of the demand description set provided by the user, and guides the value analysis of the demand description set, thereby driving the operation of the intelligent printing and typesetting model, thereby solving the problem of low efficiency of intelligent typesetting caused by the inability to accurately identify customer expectations in the prior art.

[0029] Preferably, the step of obtaining a user's requirement description set for target finished product printing and typesetting includes: S11: receiving the demand description information of the target finished product printing and typesetting provided by the user through the information interaction port; S12: Evaluate the completeness and rationality of the requirement description information provided by the user, and mark the vulnerabilities of the requirement description information according to the evaluation result to obtain a correction mark based on the requirement description information; S13: receiving information correction processing corresponding to the correction mark from the user through the information interaction port, so as to perform description correction on the vulnerability of the requirement description information and obtain the final version of the requirement description information; S14: combining all final versions of the requirement description information provided by the user through the information interaction port to obtain the requirement description set.

[0030] Specifically, the system provides an information interaction port for users to input typesetting requirement description information. Users input the requirement description through this port. It is understandable that users have overall conceptual expectations for the target finished product printing and typesetting, but are unable to specifically describe the specific layout or construct all the details. Therefore, the requirement description information needs to be parsed and the model generated later.

[0031] More specifically, the completeness and rationality of the requirement description information provided by the user is evaluated, and the vulnerabilities of the requirement description information are marked based on the evaluation results to obtain correction marks based on the requirement description information. The requirement description information input by the user is analyzed using natural language processing (NLP) and rule verification technologies to evaluate the completeness and rationality of the information, mark the deficiencies or contradictions found, and generate correction marks.

[0032] More specifically, the information correction process is performed by receiving the correction mark corresponding to the user through the information interaction port to describe and correct the loopholes in the requirement description information, so as to obtain the final version of the requirement description information, and the evaluation result (correction mark) is fed back to the user to prompt the content that needs to be supplemented or modified. The user submits the corrected requirement description information again through the information interaction port, and the system evaluates the corrected information again to ensure that all loopholes and deficiencies have been corrected.

[0033] More specifically, the final versions of the requirement description information submitted by users multiple times are integrated to generate a complete requirement description set, which includes all the details of user requirements, and provides a comprehensive requirement description set to provide a complete and accurate reference for subsequent typesetting design, ensuring that all user requirements are systematically recorded and considered, reducing the possibility of omissions or misunderstandings.

[0034] Preferably, the step of extracting the feature of the description mode and converting the feature of the guide value of the demand description set to obtain the high-dimensional guide feature distribution of the demand description set corresponding to the target finished product printing typesetting includes: S21: extracting features of the description pattern of the requirement description set to obtain description pattern features of the requirement description set; S22: Performing feature conversion of the description pattern features of the requirement description set to guide value, so as to obtain a high-dimensional guiding feature distribution of the requirement description set corresponding to the target finished product printing typesetting.

[0035] Specifically, feature extraction of description patterns is performed on each requirement description information in the requirement description set, including the information type ratio of each requirement description information in the requirement description set and the emotional color of each requirement description information, and description pattern features of the requirement description set are generated based on the information type ratio of each requirement description information in the requirement description set and the emotional color of each requirement description information.

[0036] More specifically, the requirement description set is the user's expectations for the printing and typesetting of the target finished product, and the description pattern characteristics are the combination of requirement descriptions, that is, the form in which the expectations proposed by the user are proposed. Based on this form, the requirement description set, that is, the interpretation method of the expectations proposed by the user can be derived. Based on this interpretation method, the requirement description set can be interpreted to obtain a high-dimensional directional feature distribution of the directional value of the feedback requirement description set.

[0037] More specifically, in the technical solution of the present invention, a machine learning model is applied to generate the target finished product printing layout, so it is necessary to input a directional feature value machine learning model to provide a generation direction for the model, and this generation direction is the high-dimensional directional feature distribution obtained in the above steps.

[0038] Preferably, the step of extracting features of the description pattern of the requirement description set to obtain the description pattern features of the requirement description set includes: S211: performing multi-dimensional information characteristic analysis on each demand description information in the demand description set to obtain type characteristics and emotional characteristics of each demand description information in the demand description set; wherein the type characteristics include text type and image type; S212: performing an overview analysis of type distribution of the requirement description set according to type characteristics of each requirement description information in the requirement description set to obtain a description set type distribution of the requirement description set; S213: performing overall sentiment tendency analysis on the demand description set according to sentiment characteristics of each demand description information in the demand description set, so as to obtain a description set sentiment tendency of the demand description set; S214: The description set type distribution and the description set sentiment tendency together constitute the description pattern characteristics of the demand description set.

[0039] Specifically, parse each requirement description in the requirement description set and extract different information dimensions: Type characteristics: determine the type of each requirement description information based on the content of the description, and distinguish between text type and image type; Emotional characteristics: analyze the emotional tendency in the requirement description, determine whether the description content is positive, negative or neutral, and the degree of conformity with various design styles.

[0040] More specifically, sentiment analysis models (such as models based on sentiment dictionaries, deep learning models, etc.) are used to classify the sentiment in each demand description and give the sentiment tendency of each description. Multi-dimensional information feature analysis enables a more comprehensive understanding of the demand description, which is not limited to the literal meaning, but also involves deeper information such as emotions and categories. Sentiment analysis enables the system to understand the emotional direction of user needs, which is instructive for the choice of design layout style (such as simplicity, luxury, creativity, etc.).

[0041] More specifically, according to the type characteristics (text type and image type) of each requirement description information, the entire requirement description set is counted and analyzed, the proportion of each type of requirement description in the set is analyzed, and a type distribution diagram is generated. For example, the proportion of text type and image type in the requirement description set can be determined. The distribution of each type of requirement in the set can be identified through frequency analysis or classification algorithms (such as K-means clustering, etc.), providing data support for subsequent typesetting design, understanding users' demand preferences for text and images, so as to arrange the focus of typesetting in a targeted manner. Type distribution analysis can help the system determine which design elements (text or images) dominate the requirements, and help designers or systems give priority to corresponding design elements.

[0042] More specifically, the emotional characteristics of each requirement description information are analyzed, the emotional tendency of each requirement is given, the emotional tendencies of all requirement descriptions are summarized, and an overall emotional tendency analysis is performed to determine the overall emotional trend of the requirement set. For example, the proportion of positive emotions, negative emotions, and neutral emotions in the requirement set is calculated, and a comprehensive analysis is performed using emotional tendency scores (such as emotional intensity, emotional labels, etc.) to generate an emotional tendency distribution map. The overall emotional tendency analysis helps to identify the user's emotional expectations for the finished design (such as whether they prefer simplicity and modernity, or complexity and luxury), which is of great significance for determining the final typesetting design style. Emotional analysis can help identify potential negative emotional needs and adjust the design direction to avoid design outputs that do not meet user expectations.

[0043] More specifically, the analysis results of type distribution (the ratio of text type and image type) and sentiment tendency (positive, negative, and neutral distribution of sentiment) are integrated to generate a descriptive pattern feature. Finally, these features are merged into a high-dimensional feature representation to form a descriptive pattern feature of the demand description set for subsequent typesetting design or optimization.

[0044] Preferably, the step of performing a feature conversion of the description mode features of the requirement description set to guide the value so as to obtain a high-dimensional guiding feature distribution of the requirement description set corresponding to the target finished product printing typesetting includes: S221: performing a meaning parsing pointing analysis on the requirement description set according to the description set type distribution in the description mode feature, so as to obtain a first meaning parsing vector of each requirement description information in the requirement description set; S222: performing a meaning parsing and pointing analysis on the requirement description set according to the description set sentiment tendency in the description pattern feature, so as to obtain a second meaning parsing vector of each requirement description information in the requirement description set; S223: performing a directional value analysis of each of the requirement description information according to the first meaning analysis vector and the second meaning analysis vector corresponding to each of the requirement description information in the requirement description set, so as to obtain a benchmark directional value feature of each of the requirement description information; S224: Based on a preset association database, a correlation expansion analysis of potential guiding value is performed on the description set type distribution in the description mode feature and the description set sentiment tendency, so as to obtain the expanded guiding value feature of the description simulation feature; S225: Analyze the degree of fit between the baseline guiding value feature and the extended guiding value feature, and select the extended guiding value feature according to the analysis result to obtain the additional guiding value feature whose degree of fit meets the predetermined standard among the extended guiding value features; S226: Combining and weighting the baseline guiding value features and the additional guiding value features to obtain a high-dimensional guiding feature distribution for the target finished product printing layout.

[0045] Specifically, according to the description set type distribution (the ratio of text type to image type) extracted in the previous step, each requirement description information in the requirement description set is classified, and for each requirement description, the meaning is parsed in combination with its type (text or image) to identify the specific design elements and their functions pointed to by the requirement description.

[0046] More specifically, for text types, the semantics of the text is analyzed to identify the key design requirements of the description (such as text size, font, typesetting, etc.); for image types, the content of the image description is analyzed to determine its related design elements (such as image size, position, style, etc.); based on the analysis results of the description set type distribution, the first meaning parsing vector of each requirement description information is generated, which contains the design requirements and goals related to the description content.

[0047] More specifically, by classifying the requirement description information through type distribution and parsing its meaning, we can more accurately capture the specific design requirements of each requirement, improve analysis efficiency, and ensure that the information described in each requirement can effectively point to its corresponding design goals and elements.

[0048] More specifically, according to the emotional tendency of the description set in the description pattern characteristics, the meaning parsing direction analysis is performed on the requirement description set. According to the emotional tendency distribution in the description set, the emotional analysis is performed on each requirement description in the requirement description set to determine the emotional type (positive, negative or neutral) of the requirement description. Based on the analysis results of the emotional tendency, each requirement description is subjected to emotion-driven meaning parsing. For example, positive emotion may mean the demand for simplicity and beauty, while negative emotion may indicate criticism of complex or unexpected design elements. According to the emotional tendency of each requirement description, a second meaning parsing vector related to the emotional feature is generated, which represents the emotional goal and emotion-oriented design requirement in the requirement description.

[0049] More specifically, meaning analysis combined with emotional characteristics can help the system identify users' emotional expectations, so that the design can better cater to users' emotional needs (such as a preference for simple or complex design styles), provide emotional guidance for subsequent design decisions, and ensure that the design works can resonate with users emotionally.

[0050] More specifically, the demand description information is analyzed for orientation value according to the first meaning analysis vector and the second meaning analysis vector, and each demand description information is analyzed for orientation value according to the first meaning analysis vector (type orientation) and the second meaning analysis vector (emotion orientation). The orientation value analysis focuses on the degree and direction of the impact of each demand description on the target finished product, which is usually closely related to the practicality, emotional appeal, creativity and other factors of the design. A baseline orientation value feature is generated for each demand description information, which represents the contribution of the demand to the target design layout. Through orientation value analysis, the system can quantify the influence of each demand description on the target design, provide a quantitative basis for subsequent optimization, improve the matching degree between demand and design finished product, and ensure that the design can effectively respond to the actual value appeal in the demand description.

[0051] More specifically, based on the preset associative database, the description set type distribution and sentiment tendency distribution in the description pattern features are subjected to a correlation expansion analysis of potential leading value. The preset associative database is used to conduct a correlation expansion analysis of potential leading value. This database contains a large amount of historical data, which describes how demands of different types and sentiment tendencies are associated with specific design elements or layout effects. Through the historical data model in the database, the potential correlation between the type distribution and sentiment tendency in the description set is analyzed to expand possible design solutions and optimization directions. Through the correlation analysis, a set of potential extended leading value features are obtained, which represent possible design optimization directions or added value under the current description mode.

[0052] More specifically, using relational databases to expand descriptive pattern features can discover potential design optimization space, improve the innovation and practicality of the design, and expand value-oriented features to provide more feasibility analysis support for the design process, helping to avoid being limited to the initial demand scope.

[0053] More specifically, the fit between the baseline guiding value features and the extended guiding value features is analyzed, and the extended guiding value features are selected based on the analysis results. The fit between the baseline guiding value features and the extended guiding value features is evaluated through numerical analysis (such as cosine similarity, correlation coefficient, etc.). The higher the fit, the more the extended guiding value features meet the actual needs, and the additional guiding value features that meet the predetermined standards are selected: according to the results of the fit analysis, those extended guiding value features with a fit higher than the predetermined standards are selected as additional guiding value features.

[0054] More specifically, fit analysis helps to screen out the guiding value features that best meet the needs, ensuring that the final effect of the design maximizes the match with the needs. By reasonably selecting additional guiding value features, it can avoid the design from deviating too much from the actual needs and ensure that the design optimization meets user expectations.

[0055] More specifically, the baseline guiding value features and the additional guiding value features are combined and weighted to obtain the high-dimensional guiding feature distribution of the target finished product printing layout. More specifically, the baseline guiding value features and the additional guiding value features are merged to form a unified feature vector, and weights are assigned to each feature according to its importance. The weight assignment can be based on factors such as the specific content of the demand description, the priority of market demand, and the actual feasibility of the design. The final feature combination forms a high-dimensional guiding feature distribution of the target finished product printing layout, which can accurately reflect the design requirements, emotional appeals, and actual layout requirements of the demand description set.

[0056] More specifically, feature combination and weight distribution ensure the comprehensiveness and pertinence of the target finished product printing layout design, so that design decisions can be adjusted according to the user's actual needs and emotional preferences. The high-dimensional guided feature distribution provides precise guidance for printing layout, ensuring that the final design not only meets the technical requirements, but also maximizes the user's emotional needs and design goals.

[0057] Preferably, the step of performing meaning parsing pointing analysis on the requirement description set according to the description set type distribution in the description mode feature to obtain a first meaning parsing vector of each requirement description information in the requirement description set includes: S2211: Performing a ratio analysis and weight conversion of text type and image type on the description set type distribution, so as to obtain a printing typesetting image parsing weight of the text type requirement description information and the image type requirement description information in the requirement description set corresponding to the description set type distribution; S2212: performing overall meaning property analysis on the text-type requirement description information and the image-type requirement description information in the requirement description set to obtain the overall meaning proportion of the text-type requirement description information and the image-type requirement description information in the requirement description set to the target finished product printing typesetting; S2213: Based on the printing layout image analysis weights of the text-type requirement description information and the image-type requirement description information in the requirement description set corresponding to the type distribution of the description set, and the overall meaning proportions of the text-type requirement description information and the image-type requirement description information in the requirement description set for the printing layout of the target finished product, the typesetting image conversion forms of each of the requirement description information for the printing layout of the target finished product are analyzed to obtain the typesetting image conversion forms of each of the requirement description information as the first meaning analysis vectors of each of the requirement description information.

[0058] Specifically, first, it is necessary to analyze the distribution of description set types in the demand description set, specifically identify whether each demand description is of text type or image type, and convert it into the print typesetting image parsing weights of different types of descriptions by analyzing the ratio of text type to image type. The weight here mainly represents the importance of each type of description information in the target typesetting image, which is usually set based on the priority of design requirements and user preferences. For example, if the image description requirement is more important, the image type has a higher weight. Assuming that the text type accounts for 70% and the image type accounts for 30%, the print typesetting image parsing weight can be calculated based on these two ratios, and the weighted average method and other methods may be used.

[0059] More specifically, by analyzing the ratio of text to image types, we can quantify the importance of different types of descriptions in the design process and ensure that reasonable weights are given to different types of requirements during the typesetting process. The weight conversion provides a more precise basis for subsequent steps, allowing the system to automatically adjust the priority of each element in the typesetting design.

[0060] More specifically, the overall meaning of the text type and image type requirement description information in the requirement description set is analyzed based on the information of the text type and image type in the requirement description set. This step mainly extracts the overall meaning impact on the target product printing layout design by semantically analyzing each type of requirement description (text and image).

[0061] More specifically, for text type requirements, analyze their impact on text typesetting, font selection, line spacing, etc. For image type requirements, analyze how image size, position, style, etc. affect typesetting design. According to the nature of each requirement description, calculate the proportion of the impact of text type and image type on the overall design to form the meaning proportion of text type and the meaning proportion of image type. This analysis can help identify the design intent of each element in the requirement description information and ensure that the design can accurately reflect these intentions. By calculating the meaning proportion, it can provide a basis for subsequent typesetting image conversion and help the system better understand the comprehensive design requirements of different descriptions.

[0062] More specifically, combined with the print typesetting image analysis weight and overall meaning proportion in the above steps, the typesetting image conversion form is analyzed for each requirement description. Specifically, the conversion form of text type requirements may be manifested as an impact on the typesetting structure (such as paragraphs, text size, font style, etc.), while image type requirements may involve image layout, size, alignment, etc. Through weight and meaning proportion, the design goal of each requirement description information is converted into a corresponding typesetting image element, that is, the elements of the typesetting form are adjusted by weight weighting and meaning proportion (such as mixed typesetting of images and texts, coordination between images and texts, etc.). Based on the above analysis, a typesetting image conversion form is generated for each requirement description, which serves as the first meaning analysis vector of the requirement description information. These vectors contain the degree and direction of impact on the target finished product print typesetting design. This step can convert abstract requirement descriptions (such as "text should appear concise and modern" or "images need to highlight the visual focus") into specific typesetting design elements and formats, providing clear guidance for the final design typesetting. The generated first meaning analysis vector provides content-based multi-dimensional guidance for typesetting image conversion, making the typesetting design more in line with the requirement description.

[0063] It is understandable that by conducting a detailed proportional analysis and weight conversion of the description set type distribution, combined with the meaning analysis of the requirement description, it is possible to accurately grasp the weight and influence of each requirement description in the typesetting design. This process converts the requirement description information into specific typesetting image design requirements, and provides detailed and precise guidance for subsequent typesetting image conversion, so that the typesetting design of the target product is more in line with actual needs. By combining the analysis of text and image types, it can not only meet the needs functionally, but also respond to users' expectations of typesetting style from an emotional level, thereby improving the overall quality of the final design.

[0064] Preferably, the step of performing meaning parsing and pointing analysis on the requirement description set according to the description set sentiment tendency in the description pattern feature to obtain a second meaning parsing vector of each requirement description information in the requirement description set includes: S2221: generating key description tags for target finished product printing and typesetting based on the description set sentiment tendency, so as to obtain a plurality of key description tags for the description set sentiment tendency for target finished product printing and typesetting; S2222: Perform label pointing analysis on each requirement description information in the requirement description set according to each of the key description labels to obtain a second meaning analysis vector of each of the requirement description information.

[0065] Specifically, first, we need to conduct a comprehensive analysis of the sentiment tendency in the demand description set. Sentiment tendency refers to the emotional attitude expressed by each demand description, such as positive, negative, neutral, etc. This analysis usually relies on natural language processing technology (such as sentiment analysis models) to determine the emotional color of the text.

[0066] More specifically, based on sentiment tendency analysis, several key descriptive tags are generated for the design requirements of the target finished product printing layout. These tags may include a combination of emotions and design requirements, such as "strong sense of modernity", "warm and friendly", "simple and bright", etc. A mapping relationship is established between the sentiment tendency distribution and these key descriptive tags, so that each label corresponds to a certain emotion and design direction, which helps to better express the design intention. Through in-depth analysis of sentiment tendencies, the potential emotional colors in the demand description can be identified, providing emotional guidance for subsequent design. The generated key descriptive tags help the system to clarify the emotional orientation of each design element (such as layout, font, color tone, etc.) in subsequent steps, ensuring that the design can meet the expected emotional expression in terms of visual effects.

[0067] More specifically, for each requirement description information, label pointing analysis of sentiment orientation is performed. Specifically, the system needs to check the sentiment content of each requirement description and match it with the generated key description tags. For example, a requirement description may be "the font needs to be simple and generous". If the sentiment analysis shows that the sentiment orientation of the description is "modern and concise", then the matching key tag may be "simple and bright". Through label pointing analysis, each requirement description information is matched with the corresponding sentiment orientation label, thereby generating a second meaning analysis vector for each requirement description. This vector will contain the sentiment orientation of the description information and its association with the design goal.

[0068] It is understandable that through label pointing analysis, the emotional tendency of the demand description can be further refined to ensure that the design solution not only meets the functional requirements but also accurately conveys the required emotional effects. The generated second meaning analysis vector can provide richer emotional information for typesetting design, allowing designers to accurately control the emotional atmosphere of the design during actual typesetting, such as soft, lively, solemn, etc.

[0069] More specifically, based on the analysis of emotional tendencies, the typographical elements are adjusted to reflect the emotional needs of the target finished product's printed layout. For example, if a label points to "simple and bright", the typographical design may adopt clear and concise fonts and graphic elements; if the label points to "warm and friendly", the design may adopt soft colors, rounded fonts and a warmer image style. Through the second meaning analysis vector, the emotional expression orientation of typographical elements such as text, images, color matching, and layout can be determined, and design decisions can be optimized in the typographical process. The close combination of emotional tendencies and typographical design ensures that the final design results not only meet the needs in form, but also resonate with users or target audiences on the emotional level. The second meaning analysis vector enables the design to be consistent in emotion and vision, and ultimately achieves a typographical effect that is more in line with the emotional needs of the target market or target group.

[0070] It is understandable that through the analysis of sentiment tendency and the generation of key description tags, the emotional color of each demand description can be clarified, and these emotional needs can be converted into specific design elements through label pointing analysis. This not only improves the accuracy of the design, but also ensures that the design results can achieve the expected effect at the emotional level. The generated second meaning analysis vector, as a multi-dimensional emotional information carrier, enables the design to accurately convey emotional intentions and improves the personalization and accuracy of the layout design. Overall, the combination of emotional tendency and design requirements improves the emotional conformity of the design results, so that the final layout design not only meets the functional requirements, but also effectively conveys the required emotional atmosphere.

[0071] It should be noted that the analysis of emotional tendencies is not limited to emotional dimensions such as positive and negative, but also includes tendencies in more emotional dimensions such as simplicity and complexity. At the same time, it should be noted that the analysis of emotional dimensions is not only limited to the analysis of the emotional tendencies of the words themselves, but also includes the analysis of the emotional tendencies of the vocabulary attributes, that is, the emotional tendencies hidden in the act of using a certain word itself. Furthermore, emotional tendencies are not limited to a single word, but also include a holistic analysis of multiple words.

[0072] Preferably, the pre-training step of the intelligent printing typesetting model includes: S31: Collect printing and typesetting samples to construct a historical data set; wherein the printing and typesetting samples have corresponding sample construction feature distributions, and the sample construction feature distributions correspond to the high-dimensional guided feature distributions; S32: Divide the historical data set into a training data set, a verification data set, and a test data set; S33: construct a convolutional neural network model consisting of a convolutional layer, an activation function layer, a pooling layer, a fully connected layer and an output layer as the intelligent printing typesetting model to be trained; S34: Substituting the training data set into the convolutional neural network model, so that the convolutional neural network model performs back propagation algorithm learning according to the training data set, obtains the mapping relationship between the printing typesetting sample and the sample construction feature distribution, and optimizes the convolutional neural network model according to the mapping relationship; S35: In the process of training the convolutional neural network model using the training data set, the verification data set is substituted into the convolutional neural network model, and the convolutional neural network model is made to perform verification processing on the verification data set, so as to evaluate the model performance of the convolutional neural network model during the training process, and tune the model hyperparameters according to the evaluation results; wherein the model hyperparameters include a learning rate and a regularization parameter; S36: After completing the model training of the training data set, substitute the test data set into the convolutional neural network model, and let the convolutional neural network model perform test processing on the test data set to make a final evaluation of the model performance of the convolutional neural network model to determine whether to end the model training.

[0073] Specifically, first, a large number of printing and typesetting samples need to be collected. These samples should cover various typesetting styles, design elements (such as fonts, typesetting structure, mixed text and image typesetting, etc.) and different design requirements. Each sample should have a corresponding sample construction feature distribution, which includes all key design elements in printing and typesetting (such as text layout, font selection, image size and layout, color usage, etc.). The feature distribution of these typesetting samples will correspond to the high-dimensional guided feature distribution, which means that the typesetting samples will be mapped to the target space of model learning, and the output of the model will be compared with these features for optimization. By collecting and organizing typesetting samples, the model can obtain rich input data, which provides diverse examples and design elements for subsequent training. This correspondence between sample feature distribution and high-dimensional guided features enables the model to understand and capture the diversity and complexity of typesetting design during training.

[0074] More specifically, the collected printing and typesetting samples are divided into three different subsets: a training data set, a validation data set, and a test data set. Usually, the training set accounts for about 70-80%, the validation set accounts for 10-15%, and the test set accounts for 10-15%. The training set is used to train the model, the validation set is used to evaluate the model performance and adjust the hyperparameters, and the test set is used for the final model evaluation to ensure that the model has good generalization ability. The division of the data set ensures that the model can accept different types of evaluation and optimization at different stages, thereby improving the generalization ability of the model. The reasonable division of the training set, validation set, and test set helps to avoid overfitting problems and ensure the performance of the model on unseen data.

[0075] More specifically, convolutional layer: extract local features of the input layout image through the convolutional layer. These features can reflect the basic information such as texture and edge in the image. Activation function layer: usually use ReLU (Rectified Linear Unit) activation function to introduce nonlinearity and increase the expression ability of the model. Pooling layer: pooling layer (such as maximum pooling layer) is used to reduce the spatial dimension of the feature map while retaining important feature information and reducing the amount of calculation. Fully connected layer: map the pooled features to the final output space through the fully connected layer, so that the model can perform complex feature combinations. Output layer: the output layer is usually a softmax layer for classification tasks, outputting a probability distribution corresponding to the sample category (or design element category). Through hierarchical feature learning, the convolutional neural network can gradually extract key information from the printed layout sample from low to high levels. This hierarchical structure enables the model to process image features at different scales and ultimately learn how to perform effective layout design.

[0076] More specifically, the training data set is input into the constructed convolutional neural network model, and the convolutional neural network learns through the back propagation algorithm. According to the error between the output and the target label, the parameters of each layer in the network are adjusted. The model learns the mapping relationship between the printing typesetting samples and the feature distribution of the sample construction through training, that is, it learns how to extract features from the input typesetting samples and generate the corresponding typesetting design. According to the results of back propagation, the weight parameters of the network are adjusted, and the model is gradually optimized. Through back propagation and gradient descent, the model can efficiently learn the characteristics of the typesetting design and continuously adjust during the training process, so that the output of the model is closer and closer to the target design requirements. By continuously optimizing the model, the accuracy and generalization ability of the model are improved, and it can better adapt to various design needs.

[0077] More specifically, during the model training process, the validation dataset is substituted into the convolutional neural network model. For each iterative training, the validation dataset is used to evaluate the performance of the model, and the hyperparameters (such as learning rate, regularization parameters, etc.) are adjusted according to the performance of the model on the validation set. For example, by adjusting the learning rate, the rate of model learning is controlled to avoid too fast or too slow convergence; the regularization parameters are used to control the complexity of the model and prevent overfitting. The use of the validation set ensures that the model does not overfit the training data during the training process. At the same time, the hyperparameters can be continuously optimized according to the performance on the validation set to improve the model performance. Appropriate hyperparameter tuning can significantly improve the learning efficiency and final performance of the model.

[0078] More specifically, after the model training is completed, the test data set is substituted into the convolutional neural network model for testing. By evaluating the test set, the performance of the model on unseen data is checked to ensure that it can be effectively generalized to practical applications. If the test results show that the model performance meets the expected standards, the training can be terminated. If it does not meet expectations, it may be necessary to return and adjust the training set, hyperparameters, or model structure. Through the final evaluation on the test data set, it can be determined whether the model has sufficient generalization ability and practical application value. The evaluation of the test set is a key step in the model training process, which can effectively verify every decision in the training process.

[0079] It is understandable that through the training process of the convolutional neural network (CNN), the model can automatically extract features from typesetting samples and perform effective optimization. The final convolutional neural network model has strong adaptability and can provide high-quality design suggestions in different printing typesetting tasks. Reasonable data set division, back propagation optimization and hyperparameter tuning enable the model to effectively avoid overfitting and ensure good generalization ability. Through the cyclic evaluation and optimization of the three data sets of training, verification and testing, the performance of the model is ensured to be stable, and its ability to adapt to different design scenarios has been verified.

[0080] Preferably, the step of modifying the high-dimensional guided feature distribution according to the optimization suggestion comprises: S51: parsing the optimization suggestion for direct correction features to obtain direct correction features based on the optimization suggestion; S52: performing sentiment tendency analysis on the optimization suggestion to obtain potential correction features fed back by the optimization suggestion, and performing correlation analysis on the potential correction features according to the direct correction features to obtain correlation analysis results between the potential correction features and the direct correction features; S53: selecting the potential correction features according to the correlation analysis result to obtain additional correction features; S54: weighting the direct correction feature and the additional correction feature, and correcting the high-dimensional guided feature distribution based on the weighted direct correction feature and the additional correction feature.

[0081] Specifically, the optimization suggestions are analyzed step by step to identify the direct correction features therein. These features are usually extracted from actual feedback and are elements that directly affect the typesetting design effect. For example, a suggestion may involve directly adjustable typesetting attributes such as text font size, line spacing, paragraph alignment, etc. Specific adjustment items are extracted from the optimization suggestions. These items are usually specific and clear and can directly affect the visual effect of the typesetting sample. The direct correction features provide a clear guiding direction for subsequent feature corrections, ensuring that the model optimization process is targeted at actual needs and is practical. This parsing process enables the model to accurately extract the key features that need to be corrected from the optimization suggestions without having to rely too much on guesswork or irrelevant features.

[0082] More specifically, sentiment analysis is performed on the optimization suggestions to identify potential emotional information, such as whether the optimization suggestions tend to favor a certain typesetting style (such as modernity, simplicity, etc.) or express a certain design concept (such as high-end, ease, etc.). Through sentiment analysis, potential correction features in the optimization suggestions can be obtained. These features may not be intuitive modifications, but they reflect the design intent or sensory needs behind the optimization suggestions. For example, if an optimization suggestion mentions "I hope to increase the sense of modernity in typesetting", then sentiment analysis may identify the design goal of "modernity" and associate it with some potential correction features, such as font selection, typesetting structure, color matching, etc.

[0083] More specifically, through sentiment analysis, the model can understand the implicit intentions and design feelings behind the optimization suggestions, thereby not only correcting surface features but also optimizing the overall style and emotional experience of the typography design. This analysis ensures that the model can better meet the user's emotional needs when optimizing typography, thereby enhancing the design's affinity and user experience.

[0084] More specifically, the direct correction features extracted from the optimization suggestions are analyzed for correlation with the potential correction features obtained through sentiment analysis. By calculating the correlation between these two types of features, the strength and relationship of their interaction during the correction process can be determined. Statistical methods (such as Pearson correlation coefficient, cosine similarity, etc.) or machine learning methods can be used to measure the relationship between features. For example, the correlation between the direct correction feature "font size" and the potential correction feature "modernity" may indicate that the adjustment of font size has a greater impact on conveying a sense of modernity. Through correlation analysis, it is found which potential correction features have a strong correlation with the adjustment of direct correction features, which helps to select and optimize features more accurately during the correction process. Correlation analysis can reveal the relationship between different features, thereby guiding the priority and importance ranking of features, ensuring that the correction process is both accurate and efficient. This analysis ensures the rationality of the correction process, avoids redundant adjustments, and optimizes the overall strategy of feature correction.

[0085] More specifically, based on the results of the correlation analysis, those features that have a high correlation with the direct correction features are selected from the potential correction features. These features will be used as additional correction features to further improve the correction plan. The additional correction features may include detail adjustments related to emotion, design style, typesetting structure, etc. These adjustments can not only correct the technical problems of the typesetting itself, but also further improve the overall design effect. If the direct correction feature includes "paragraph spacing", and the potential correction feature "sense of simplicity" has a high correlation with "paragraph spacing", then the additional correction feature of "sense of simplicity" may be reflected by further adjusting the paragraph spacing.

[0086] More specifically, by selecting additional correction features, the correction process becomes more comprehensive. It is not only limited to directly visible correction features, but also goes deeper into aspects such as design style and emotional expression, making the typesetting design more delicate and in line with user needs. This selection process improves the intelligence of the correction plan, enabling the model to better understand user feedback and perform multi-dimensional optimization.

[0087] More specifically, weights are assigned to direct correction features and additional correction features according to the contribution of each correction feature to the correction of the high-dimensional guided feature distribution. These weights may be determined based on factors such as the results of correlation analysis, the priority of design intent, and the urgency of optimization suggestions. In the actual optimization process, these weights may need to be dynamically adjusted to ensure the optimal correction effect. For example, if the direct correction feature has a greater impact on the typesetting effect, it can be given a higher weight, while the additional correction features are appropriately weighted according to their impact on the overall effect.

[0088] More specifically, weight allocation ensures the rational role of different features in the correction process, avoids excessive or insufficient correction, and achieves the optimal correction effect. Dynamic weight adjustment makes the model more flexible and can optimize the accuracy and effect of feature correction according to different typesetting tasks or user needs.

[0089] More specifically, the high-dimensional guided feature distribution is actually modified according to the previously determined direct correction features, additional correction features and their weights. This step usually modifies the input features of the model, adjusts the distribution of feature vectors, and makes them more consistent with the optimized design goals. The modified features are applied to the input of the model for prediction and output. The modified feature distribution will guide the model to generate layout results that are more consistent with the optimization suggestions. This step ensures that the correction of the high-dimensional guided feature distribution can directly affect the output of the model, and ultimately improve the quality and effect of the layout design. Through the precise correction of the feature distribution, the model can generate design outputs that are more in line with user needs, improving the accuracy and personalization of the design.

[0090] Reference Figure 2 As shown, in a second aspect, the present invention provides an intelligent printing typesetting device based on machine learning, which is used to implement an intelligent printing typesetting method based on machine learning as described in any one of the first aspects, including: A demand acquisition module is used to acquire a user's demand description set for printing and typesetting of a target finished product; wherein the demand description set includes a plurality of demand description information, and the demand description information is used to describe the user's typesetting demand for printing and typesetting of the target finished product; A guidance analysis module, used for extracting the features of the description mode and converting the features of the guidance value of the demand description set to obtain a high-dimensional guidance feature distribution of the demand description set corresponding to the target finished product printing typesetting; A preliminary simulation module, used for performing multiple data simulations on the high-dimensional guiding feature distribution according to a pre-trained intelligent printing typesetting model, so as to obtain a plurality of original versions of printing typesetting corresponding to the high-dimensional guiding feature distribution; An optimization feedback module, used to construct a user feedback channel based on each of the original version printing layouts, and accept optimization suggestions from users on each of the original version printing layouts through the user feedback channel; The typesetting correction module is used to correct the high-dimensional guiding feature distribution according to the optimization suggestion, and perform data simulation on the corrected high-dimensional guiding feature distribution according to the pre-trained intelligent printing typesetting model to obtain the target finished product printing typesetting.

[0091] In this embodiment, for the specific implementation of each module in the above-mentioned device embodiment, please refer to the above-mentioned method embodiment, which will not be described in detail here.

[0092] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. An intelligent printing typesetting method based on machine learning, characterized in that: include: Obtaining a user's requirement description set for printing and typesetting of a target finished product; wherein the requirement description set includes a plurality of requirement description information, and the requirement description information is used to describe the user's typesetting requirements for printing and typesetting of the target finished product; Extracting the feature of the description mode and converting the feature of the guiding value on the demand description set, so as to obtain the high-dimensional guiding feature distribution of the demand description set corresponding to the target finished product printing typesetting; Performing multiple data simulations on the high-dimensional guiding feature distribution according to a pre-trained intelligent printing typesetting model to obtain a plurality of original version printing typesets corresponding to the high-dimensional guiding feature distribution; Building a user feedback channel based on each of the original version printing layouts, and accepting user optimization suggestions for each of the original version printing layouts through the user feedback channel; The high-dimensional guiding feature distribution is modified according to the optimization suggestion, and data simulation is performed on the modified high-dimensional guiding feature distribution according to the pre-trained intelligent printing typesetting model to obtain the target finished product printing typesetting.

2. The intelligent printing typesetting method based on machine learning according to claim 1, characterized in that: The steps of obtaining a set of user's requirement descriptions for the target finished product printing and typesetting include: Receive the required description information of the target finished product printing and typesetting provided by the user through the information interaction port; Evaluate the completeness and rationality of the requirement description information provided by the user, and mark the vulnerabilities of the requirement description information according to the evaluation results to obtain a correction mark based on the requirement description information; Receiving information correction processing corresponding to the correction mark from the user through the information interaction port, so as to correct the vulnerability of the requirement description information and obtain the final version of the requirement description information; All final versions of the requirement description information provided by the user through the information interaction port are combined to obtain the requirement description set.

3. The intelligent printing typesetting method based on machine learning according to claim 1, characterized in that: The steps of extracting the feature of the description mode and converting the feature of the guidance value of the demand description set to obtain the high-dimensional guidance feature distribution of the demand description set corresponding to the target finished product printing typesetting include: Extracting features of description patterns from the requirement description set to obtain description pattern features of the requirement description set; The description pattern features of the demand description set are subjected to feature conversion leading to value, so as to obtain a high-dimensional feature distribution leading to the target finished product printing layout corresponding to the demand description set.

4. The intelligent printing typesetting method based on machine learning as claimed in claim 3, characterized in that: The step of extracting the features of the description pattern of the requirement description set to obtain the description pattern features of the requirement description set includes: Performing multi-dimensional information characteristic analysis on each demand description information in the demand description set to obtain type characteristics and emotional characteristics of each demand description information in the demand description set; wherein the type characteristics include text type and image type; Performing an overview analysis of type distribution of the requirement description set according to type characteristics of each requirement description information in the requirement description set to obtain a description set type distribution of the requirement description set; Performing an overall sentiment tendency analysis on the demand description set according to the sentiment characteristics of each demand description information in the demand description set to obtain a description set sentiment tendency of the demand description set; The description set type distribution and the description set sentiment tendency together constitute the description pattern characteristics of the demand description set.

5. The intelligent printing typesetting method based on machine learning as claimed in claim 4, characterized in that: The step of performing a feature conversion of the description mode features of the demand description set to guide the value, so as to obtain a high-dimensional guiding feature distribution of the demand description set corresponding to the target finished product printing typesetting includes: Performing a meaning parsing pointing analysis on the requirement description set according to the description set type distribution in the description mode feature to obtain a first meaning parsing vector of each requirement description information in the requirement description set; Performing a meaning parsing and pointing analysis on the requirement description set according to the description set sentiment tendency in the description pattern feature to obtain a second meaning parsing vector of each requirement description information in the requirement description set; According to the first meaning parsing vector and the second meaning parsing vector corresponding to each of the requirement description information in the requirement description set, each of the requirement description information is respectively subjected to orientation value parsing to obtain a benchmark orientation value feature of each of the requirement description information; Based on a preset association database, a potential value-oriented correlation expansion analysis is performed on the description set type distribution in the description pattern feature and the description set sentiment tendency, so as to obtain an expansion-oriented value feature of the description pattern feature; Analyzing the degree of fit between the benchmark guiding value feature and the extended guiding value feature, and selecting the extended guiding value feature according to the result of the analysis, so as to obtain the additional guiding value feature whose degree of fit meets the predetermined standard among the extended guiding value features; The baseline guiding value features and the additional guiding value features are combined and weighted to obtain a high-dimensional guiding feature distribution of the target finished product printing layout.

6. The intelligent printing typesetting method based on machine learning as claimed in claim 5, characterized in that: The step of performing meaning parsing and pointing analysis on the requirement description set according to the description set type distribution in the description mode feature to obtain a first meaning parsing vector of each requirement description information in the requirement description set includes: Performing a ratio analysis and weight conversion of text type and image type on the description set type distribution to obtain a printing typesetting image parsing weight of the text type requirement description information and the image type requirement description information in the requirement description set corresponding to the description set type distribution; Performing overall meaning property analysis on the text-type requirement description information and the image-type requirement description information in the requirement description set to obtain the overall meaning proportion of the text-type requirement description information and the image-type requirement description information in the requirement description set to the target finished product printing typesetting; Based on the printing and typesetting image analysis weights of the text-type requirement description information and the image-type requirement description information in the requirement description set corresponding to the description set type distribution, and the overall meaning proportion of the text-type requirement description information and the image-type requirement description information in the requirement description set to the target finished product printing and typesetting, the typesetting image conversion form of each requirement description information for the target finished product printing and typesetting is analyzed to obtain the typesetting image conversion form of each requirement description information as the first meaning analysis vector of each requirement description information.

7. The intelligent printing typesetting method based on machine learning as claimed in claim 5, characterized in that: The step of performing a meaning parsing and pointing analysis on the requirement description set according to the description set sentiment tendency in the description pattern feature to obtain a second meaning parsing vector of each requirement description information in the requirement description set includes: Generate key description tags for target finished product printing and typesetting based on the description set sentiment tendency, so as to obtain several key description tags for the description set sentiment tendency for target finished product printing and typesetting; Label pointing parsing is performed on each requirement description information in the requirement description set according to each of the key description labels to obtain a second meaning parsing vector of each of the requirement description information.

8. The intelligent printing typesetting method based on machine learning as claimed in claim 1, characterized in that: The pre-training steps of the intelligent printing typesetting model include: Collect printing and typesetting samples to construct a historical data set; wherein the printing and typesetting samples have corresponding sample construction feature distributions, and the sample construction feature distributions correspond to the high-dimensional guided feature distributions; Dividing the historical data set into a training data set, a verification data set and a test data set; Construct a convolutional neural network model consisting of a convolutional layer, an activation function layer, a pooling layer, a fully connected layer, and an output layer as the intelligent printing typesetting model to be trained; Substituting the training data set into the convolutional neural network model, so that the convolutional neural network model performs back propagation algorithm learning according to the training data set, obtains the mapping relationship between the printing typesetting sample and the sample construction feature distribution, and optimizes the convolutional neural network model according to the mapping relationship; In the process of training the convolutional neural network model using the training data set, the verification data set is substituted into the convolutional neural network model, and the convolutional neural network model is made to perform verification processing on the verification data set, so as to evaluate the model performance of the convolutional neural network model during the training process, and tune the model hyperparameters according to the evaluation results; wherein the model hyperparameters include a learning rate and a regularization parameter; After completing the model training of the training data set, the test data set is substituted into the convolutional neural network model, and the convolutional neural network model is made to perform test processing on the test data set to make a final evaluation of the model performance of the convolutional neural network model to determine whether to end the model training.

9. The intelligent printing typesetting method based on machine learning as claimed in claim 1, characterized in that: The step of modifying the high-dimensional guided feature distribution according to the optimization suggestion comprises: parsing the optimization suggestion for direct correction features to obtain direct correction features based on the optimization suggestion; Performing sentiment analysis on the optimization suggestion to obtain potential correction features fed back by the optimization suggestion, and performing correlation analysis on the potential correction features according to the direct correction features to obtain correlation analysis results between the potential correction features and the direct correction features; Selecting the potential correction features according to the association analysis result to obtain additional correction features; The direct correction feature and the additional correction feature are weighted, and the high-dimensional guided feature distribution is corrected based on the weighted direct correction feature and the additional correction feature.

10. An intelligent printing and typesetting device based on machine learning, characterized in that: A method for intelligent printing typesetting based on machine learning for implementing any one of claims 1 to 9, comprising: A demand acquisition module is used to acquire a user's demand description set for printing and typesetting of a target finished product; wherein the demand description set includes a plurality of demand description information, and the demand description information is used to describe the user's typesetting demand for printing and typesetting of the target finished product; A guidance analysis module, used for extracting the features of the description mode and converting the features of the guidance value of the demand description set to obtain a high-dimensional guidance feature distribution of the demand description set corresponding to the target finished product printing typesetting; A preliminary simulation module, used for performing multiple data simulations on the high-dimensional guiding feature distribution according to a pre-trained intelligent printing typesetting model, so as to obtain a plurality of original versions of printing typesetting corresponding to the high-dimensional guiding feature distribution; An optimization feedback module, used to construct a user feedback channel based on each of the original version printing layouts, and accept optimization suggestions from users on each of the original version printing layouts through the user feedback channel; The typesetting correction module is used to correct the high-dimensional guiding feature distribution according to the optimization suggestion, and perform data simulation on the corrected high-dimensional guiding feature distribution according to the pre-trained intelligent printing typesetting model to obtain the target finished product printing typesetting.

Images