Big data analysis-based digital management system for whole process of publication

Abstract

The invention relates to the technical field of digital management, and particularly discloses a publishing house full-process digital management system based on big data analysis, which comprises a publishing house topic selection planning module, a topic selection content determination module, a publishing house order management module, a book inventory monitoring module, a book quality evaluation module and a book copyright management module. According to the method, a topic selection feasibility evaluation model is established through book multi-source data fusion, topic selection accuracy is improved, production and printing management is intelligently planned through a paper format optimization algorithm, a book inventory prediction model is established through fusion of sales and inventory data, inventory allocation management is realized, and the production and printing efficiency is improved. The printing quality problem is automatically identified through standardized deviation analysis, copyright key links are subjected to uplink evidence storage, a press is promoted to transform from experience driving to data driving through a big data analysis technology, and scientization of topic selection decision, refinement of production management, standardization of quality management and control and full chain of copyright protection are achieved.

Description

Technical Field

[0001] The present invention relates to the field of digital management technology, and in particular to a publishing house full-process digital management system based on big data analysis. Background Art

[0002] With the rapid development of information technology and the rise of the digital publishing industry, publishers are facing an urgent need to transition from traditional paper publishing to full-process digital management. The mature application of technologies such as big data, artificial intelligence, and blockchain provides technical support for the intelligent upgrade of the publishing industry in topic planning, content production, printing and distribution, and copyright management.

[0003] Traditional publishing management systems are centered around process-based operations, dividing operations into independent modules such as topic selection, editing, printing, distribution, and copyright. However, data interaction between these modules is weak, and there are numerous shortcomings. First, traditional management systems lack the ability to integrate multi-source data and make topic selection decisions. The feasibility assessment of topic selection relies on editorial experience, resulting in a low hit rate for topic selection and inefficient resource allocation. Second, in order management, paper format selection and printing plan formulation rely on manual experience. There is no inventory forecasting model that integrates sales data and market trends, making it impossible to provide early warning of out-of-stock or backlog risks, which can easily lead to paper waste and low inventory turnover efficiency. Furthermore, book printing quality assessments rely on manual spot checks and empirical judgment, lacking standardized deviation analysis models, making it difficult to accurately locate printing defects and resulting in a high rate of missed detections. Furthermore, copyright management is primarily based on offline registration and manual verification, failing to achieve digital management of copyright resources and on-chain evidence storage of key links. Furthermore, there is a lack of real-time monitoring and intelligent early warning mechanisms. Summary of the Invention

[0004] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a publishing house full-process digital management system based on big data analysis to solve the problems raised in the above-mentioned background technology.

[0005] To achieve the above-mentioned purpose, the present invention provides the following technical solutions: a publishing house full-process digital management system based on big data analysis, including a publishing house topic planning module, a topic content determination module, a publishing house order management module, a book inventory monitoring module, a book quality assessment module, and a book copyright management module; Publishing house topic planning module: used to obtain multi-source heterogeneous data of books, establish a feasibility assessment model for each topic based on the multi-source heterogeneous data of books, and output the feasibility coefficient of each topic as the effective topic information of the target publishing house; Topic content determination module: based on the valid topic information, obtains the topic content of the target publisher, and determines the topic content of the book published by the corresponding target publisher according to the topic content; Publishing house order management module: used to receive actual book order information from the target publishing house's corresponding order management platform, and manage the production and printing of book orders in combination with the paper format optimization algorithm; Book inventory monitoring module: used to monitor the book inventory of the target publishing house in real time, obtain the book sales data and inventory data corresponding to the target publishing house, establish a book inventory forecast index model, and allocate and manage the book inventory based on the book inventory forecast index; Book quality assessment module: used to analyze the deviation between the printing quality of the books to be tested and the standard books, mark the books with unqualified printing quality according to the deviation analysis results, upload the information of the books with unqualified printing quality to the digital management center, and notify the management personnel to carry out book printing quality management; Book copyright management module: used to manage the target publisher’s book copyright resources, store key copyright links on the chain, monitor copyright usage in real time, and issue infringement warnings.

[0006] Preferably, the specific content of the publisher's topic planning module acquiring multi-source heterogeneous data of books is as follows: The API interface is used to connect to the data source to obtain multi-source heterogeneous data of books, including market sales data, reader evaluation data, social media popularity data, academic citation index and competitive product analysis data.

[0007] Preferably, the specific steps of establishing a feasibility evaluation model for each topic based on multi-source heterogeneous data of books are as follows: Clean and preprocess the acquired multi-source heterogeneous data of books to obtain book text data; Use natural language processing technology to perform topic extraction, sentiment analysis, and keyword extraction on the book text data to build a multi-dimensional evaluation index system; Based on the multi-dimensional evaluation index system, a feasibility evaluation model for each topic is established, and the standardized scores of each evaluation index corresponding to each topic and the weights corresponding to each evaluation index are input into the feasibility evaluation model of each topic to calculate the feasibility coefficient of each topic.

[0008] Preferably, the execution mode of the topic content determination module is as follows: Receive the feasibility coefficient data of each topic output from the topic planning module, use the preset feasibility coefficient threshold screening mechanism to obtain the target reference topic information; Screening the target reference topic information, wherein the specific content of the screening is: obtaining the historical publishing data, professional field advantages, existing author resources and market positioning of the target publishing house, and screening in combination with the target reference topic information; Performing a topic duplication check on the target reference topic information. The specific content of the topic duplication check is: comparing the target reference topic information with the content of books published by the publisher in the past three years through a text similarity algorithm, marking topics with a similarity of more than 70% as potential duplicate topics, and automatically lowering the recommendation priority of the topic; Based on the screening of the target reference topic information and the checking of topic duplication, a topic content recommendation report for the target publishing house is automatically generated, and the topic content recommendation report for the target publishing house is uploaded to the digital management center, which is reviewed and reviewed online by the publishing house editorial committee. The editorial committee members vote and comment on each topic, and the digital management center counts the review results in real time, and determines the topic content of the target publishing house's books based on the review results.

[0009] Preferably, the specific content of the target reference topic information is as follows: Read the feasibility coefficient of each topic, compare the feasibility coefficient of each topic with the preset feasibility coefficient threshold, screen out topics whose feasibility coefficient is greater than the preset feasibility coefficient threshold, automatically mark the topics greater than the preset feasibility coefficient threshold as target reference topic information, obtain the topic number, transmit the corresponding topic number to the digital management center, and the management personnel obtain the topic content corresponding to the topic number.

[0010] Preferably, the execution method of the production and printing management of book orders in combination with the paper size optimization algorithm is as follows: Obtaining original paper size information and book size information, wherein the original paper size information includes the length and width of the original paper, and the book size information includes the length and width of a single finished book; Establishing a paper utilization coefficient model based on the original paper size information and the book size information, inputting the original paper size information and the book size information into the paper utilization coefficient model, and calculating the paper utilization coefficient; Based on the paper size optimization algorithm, by maximizing the paper utilization coefficient, the paper size optimization value is output, and the paper size optimization value is uploaded to the digital management center. The production management personnel will manage the production and printing of book orders based on the paper size optimization value.

[0011] Preferably, the execution mode of the book inventory monitoring module is as follows: Obtain book sales data and inventory data corresponding to the target publisher. The book sales data includes book sales volume, return rate, and repurchase rate. The inventory data includes the number of books in stock and the number of books in transit. Preprocess the acquired book sales data and inventory data; Extracting corresponding characteristic factors from the book sales data and inventory data, wherein the characteristic factor corresponding to the book sales data is an effective demand factor, and the characteristic factor corresponding to the inventory data is an available inventory factor; Based on the effective demand factor and available inventory factor, a book inventory forecasting index model is established; Calculate the mean of the effective demand factor and standard deviation , the mean of the available inventory factor and standard deviation ; The effective demand factor and available inventory factor, the mean and standard deviation of the effective demand factor, and the mean and standard deviation of the available inventory factor are respectively input into the book inventory forecast index model to calculate the book inventory forecast index; The book inventory forecast index is uploaded to the digital management center, and the inventory management personnel allocate and manage the book inventory based on the book inventory forecast index.

[0012] Preferably, the extraction process of the effective demand factor is specifically as follows: obtaining the thirty-day book sales volume Sv corresponding to the target publisher, obtaining the thirty-day corresponding return rate Cr and repurchase rate Rr from the backend data of the order management platform, importing the thirty-day book sales volume, return rate and repurchase rate into the calculation model of the effective demand factor, and calculating the effective demand factor EDF; The extraction process of the available inventory factor is specifically as follows: adding the number of books in stock and the number of books in transit corresponding to the target publishing house to obtain the available inventory factor AIF.

[0013] Preferably, the execution method of the book quality assessment module is as follows: Obtain books with acceptable printing quality and mark them as standard books; Mark the books whose printing quality is to be tested by the target publisher as books to be tested; Collect quality data of the books to be tested and the standard books; The quality data of the books to be tested and the standard books are respectively processed in a standardized format; Match the quality data of the book to be tested with the standard book according to the page order and chapter structure of the book; For each set of quality parameters after matching, the corresponding parameter values ​​of the standard book are subtracted from the parameter values ​​of the book to be tested to generate a quality deviation data set; Set the reasonable deviation range allowed for printing quality, and classify and convert each parameter deviation value in the quality deviation data set: if the deviation value exceeds the reasonable range, it is marked as a failed point; if it is within the reasonable range, it is marked as a qualified point; The proportion of unqualified points in the total number of inspection points is calculated and recorded as the quality deviation ratio; When the quality deviation ratio exceeds the pre-set quality threshold, the printing quality of the book is judged to be unqualified, and the book number, deviation location, and deviation type information are packaged and uploaded to the digital management center, and the early warning mechanism is triggered to notify the management personnel to intervene in the printing quality control; if it does not exceed the threshold, the printing quality is judged to be qualified and enters the normal circulation link.

[0014] As described above, the present invention provides a publishing house full-process digital management system based on big data analysis, which has at least the following beneficial effects: The present invention provides a digital management system for the entire process of a publishing house based on big data analysis. The system integrates multi-source heterogeneous data through the publishing house topic planning module, establishes a topic feasibility assessment model, and realizes data-driven scientific topic selection. The topic content determination module accurately anchors the publishing direction based on effective topic information. The publishing house order management module intelligently plans the production and printing process in combination with the paper size optimization algorithm. The book inventory monitoring module integrates sales and inventory data to build a dynamic prediction model to achieve accurate inventory allocation and risk warning. The book quality assessment module automatically identifies printing quality problems and triggers the management process through a standardized deviation analysis model. The book copyright management module stores key copyright links on the chain, monitors copyright usage status in real time, and provides infringement warnings. The present invention, with the help of big data analysis and intelligent technology, promotes the transformation of publishing houses from experience-driven to data-driven, realizes scientific topic selection decision-making, refined production management, standardized quality control, and full-chain copyright protection, effectively breaks the data silos of business links, improves the collaborative efficiency of the entire process, and builds a digital management system for publishing houses that integrates resource optimization, risk prevention and control, and agile operation, significantly enhancing the overall efficiency and market competitiveness of the publishing industry chain. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The present invention is further described with reference to the accompanying drawings. However, the embodiments in the accompanying drawings do not constitute any limitation to the present invention. A person skilled in the art can obtain other drawings based on the following drawings without inventive effort.

[0016] Figure 1 This is a structural diagram of a publishing house full-process digital management system based on big data analysis according to the present invention. DETAILED DESCRIPTION

[0017] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0018] See also Figure 1 As shown, the present invention provides a publishing house full-process digital management system based on big data analysis, including a publishing house topic planning module, a topic content determination module, a publishing house order management module, a book inventory monitoring module, a book quality assessment module, and a book copyright management module; Publishing house topic planning module: used to obtain multi-source heterogeneous data of books, establish a feasibility assessment model for each topic based on the multi-source heterogeneous data of books, and output the feasibility coefficient of each topic as the effective topic information of the target publishing house; In this embodiment, it should be specifically explained that the specific content of the publisher's topic selection and planning module acquiring the multi-source heterogeneous data of books is as follows: By connecting to data sources through APIs, we can obtain multi-source heterogeneous book data, including market sales data, reader reviews, social media buzz, academic citation indices, and competitive analysis. Specifically, market sales data can be obtained from major book retail platforms (such as Dangdang and JD Books); reader reviews can be captured from platforms like Douban and Amazon; social media buzz data can be obtained by monitoring the volume of relevant topic discussions on platforms like Weibo and WeChat public accounts; and academic citation indices can be obtained from academic databases like CNKI and Web of Science.

[0019] In this embodiment, it should be specifically explained that the specific steps of establishing the feasibility evaluation model for each topic based on the multi-source heterogeneous data of books are as follows: Cleaning and preprocessing the acquired multi-source heterogeneous book data to obtain book text data; the preprocessing includes operations such as deduplication, denoising, and format unification; Use natural language processing technology to perform topic extraction, sentiment analysis, and keyword extraction on the book text data to construct a multi-dimensional evaluation index system; the multi-dimensional evaluation index includes but is not limited to market demand index, competition situation index, cost-effectiveness index, author resource index, and social media popularity index; Establish a feasibility evaluation model for each topic based on the multi-dimensional evaluation index system, input the standardized score of each evaluation index corresponding to each topic and the weight corresponding to each evaluation index into the feasibility evaluation model for each topic, and calculate the feasibility coefficient of each topic; The calculation formula of the feasibility coefficient of each topic is as follows: ,in, FC i represents the feasibility coefficient of the i-th topic, represents the standardized score of the jth evaluation indicator corresponding to the i-th topic, represents the weight value corresponding to the jth evaluation indicator, i represents the number of each topic, i=1, 2, 3, ..., n, n is the total number of topics, j is the number of each evaluation indicator, j=1, 2, 3, ..., m, m is the total number of evaluation indicators; It should be specifically noted that the weights corresponding to the various indicators are determined using the entropy weight method.

[0020] Topic content determination module: based on the valid topic information, obtains the topic content of the target publisher, and determines the topic content of the book published by the corresponding target publisher according to the topic content; In this embodiment, it should be specifically explained that the execution method of the topic content determination module is as follows: Receive the feasibility coefficient data of each topic output from the topic planning module, use the preset feasibility coefficient threshold screening mechanism to obtain the target reference topic information; It should be noted that the specific content of the target reference topic information is as follows: Read the feasibility coefficient of each topic, compare the feasibility coefficient of each topic with the preset feasibility coefficient threshold, screen out topics whose feasibility coefficient is greater than the preset feasibility coefficient threshold, automatically mark the topics greater than the preset feasibility coefficient threshold as target reference topic information, obtain the topic number, transmit the corresponding topic number to the digital management center, and the management personnel obtain the topic content corresponding to the topic number; Screening the target reference topic information, wherein the specific content of the screening is: obtaining the historical publishing data, professional field advantages, existing author resources and market positioning of the target publishing house, and screening in combination with the target reference topic information; In this embodiment, a specific embodiment is provided. For example, for a publishing house that focuses on science and technology books, the system will give priority to recommending topics with high feasibility coefficients in the field of science and technology; at the same time, the system will also consider the publishing plan and resource allocation of the publishing house in that year. For example, if a publishing house plans to publish no more than 10 medical books per year, the system will only recommend the top 10 topics in the medical category with the highest feasibility coefficients.

[0021] Performing a topic duplication check on the target reference topic information. The specific content of the topic duplication check is: comparing the target reference topic information with the content of books published by the publisher in the past three years through a text similarity algorithm, marking topics with a similarity of more than 70% as potential duplicate topics, and automatically lowering the recommendation priority of the topic; Based on the screening of the target reference topic information and the checking of topic duplication, a topic content recommendation report for the target publishing house is automatically generated, and the topic content recommendation report for the target publishing house is uploaded to the digital management center, which is reviewed and reviewed online by the publishing house editorial committee. The editorial committee members vote and comment on each topic, and the digital management center counts the review results in real time, and determines the topic content of the target publishing house's books based on the review results.

[0022] Publishing house order management module: used to receive actual book order information from the target publishing house's corresponding order management platform, and manage the production and printing of book orders in combination with the paper format optimization algorithm; In this embodiment, it should be specifically explained that the specific content of the actual book order information received by the publisher order management module from the order management platform corresponding to the target publisher is as follows: Establish data interfaces between the publisher's ERP system and major sales channels (such as online bookstores and offline distributors) to receive book order information in real time, including but not limited to the book's ISBN, order quantity, delivery date, and special printing requirements; Performing preliminary processing on the book order information, the preliminary processing including order legitimacy verification, order priority allocation, and order classification, wherein the order priority allocation is determined based on factors such as customer level, order quantity, and delivery deadline; In this embodiment, it should be specifically explained that the execution method of the production and printing management of book orders in combination with the paper size optimization algorithm is as follows: Obtaining original paper size information and book size information, wherein the original paper size information includes the length and width of the original paper, and the book size information includes the length and width of a single finished book; Establishing a paper utilization coefficient model based on the original paper size information and the book size information, inputting the original paper size information and the book size information into the paper utilization coefficient model, and calculating the paper utilization coefficient; It should be noted that the calculation formula of the paper utilization coefficient is as follows: ,in, U represents the paper utilization coefficient, L Indicates the length of the original paper, W Indicates the width of the base paper. Indicates the width of a single finished book. Indicates the length of a single book. p Indicates the number of books that can be typeset on a single sheet of paper in the length direction, that is, the number of books that can be typeset horizontally. It is an integer. k Indicates the number of books that can be typeset on a single sheet of paper in the width direction, that is, the number of vertical typeset pages, and is an integer.

[0023] Based on the paper size optimization algorithm, by maximizing the paper utilization coefficient, the paper size optimization value is output, and the paper size optimization value is uploaded to the digital management center. The production management personnel will manage the production and printing of book orders based on the paper size optimization value.

[0024] Book inventory monitoring module: used to monitor the book inventory of the target publishing house in real time, obtain the book sales data and inventory data corresponding to the target publishing house, establish a book inventory forecast index model, and allocate and manage the book inventory based on the book inventory forecast index; In this embodiment, it should be specifically explained that the execution method of the book inventory monitoring module is as follows: Obtain book sales data and inventory data corresponding to the target publisher. The book sales data includes book sales volume, return rate, and repurchase rate. The inventory data includes the number of books in stock and the number of books in transit. The acquired book sales data and inventory data are preprocessed; the preprocessing includes cleaning, processing missing values, outliers and data standardization to ensure data quality and consistency.

[0025] Extracting corresponding characteristic factors from the book sales data and inventory data, wherein the characteristic factor corresponding to the book sales data is an effective demand factor, and the characteristic factor corresponding to the inventory data is an available inventory factor; It should be noted that the extraction process of the effective demand factor is as follows: obtain the thirty-day book sales volume Sv corresponding to the target publisher, obtain the thirty-day corresponding return rate Cr and repurchase rate Rr from the backend data of the order management platform, import the thirty-day book sales volume, return rate and repurchase rate into the calculation model of the effective demand factor, and calculate the effective demand factor EDF; The calculation formula of the effective demand factor is as follows: ,in, EDF represents the effective demand factor.

[0026] The extraction process of the available inventory factor is specifically as follows: adding the number of books in stock and the number of books in transit corresponding to the target publishing house to obtain the available inventory factor AIF; Based on the effective demand factor and available inventory factor, a book inventory forecasting index model is established; Calculate the mean of the effective demand factor and standard deviation , the mean of the available inventory factor and standard deviation ; The effective demand factor and available inventory factor, the mean and standard deviation of the effective demand factor, and the mean and standard deviation of the available inventory factor are respectively input into the book inventory forecast index model to calculate the book inventory forecast index; The calculation formula of the book inventory forecast index is as follows: ,in, IPI represents the book inventory forecast index, MIF Indicates the market trend influencing factor; The method for obtaining the market trend impact factor MIF is as follows: Obtain the target book's sales volume and the sales volume of competing products during the same period, and divide the competing product's sales volume during the same period by the sum of the target book's sales volume and the competing product's sales volume during the same period to obtain the competition intensity index; Obtain the target book market growth rate, subtract the competition intensity index from one, and then multiply the value by the target book market growth rate to calculate the market trend impact factor; The book inventory forecast index is uploaded to the digital management center, and the inventory management personnel allocate and manage the book inventory based on the book inventory forecast index.

[0027] Book quality assessment module: used to analyze the deviation between the printing quality of the books to be tested and the standard books, mark the books with unqualified printing quality according to the deviation analysis results, upload the information of the books with unqualified printing quality to the digital management center, and notify the management personnel to carry out book printing quality management; In this embodiment, it should be specifically explained that the execution method of the book quality assessment module is as follows: Obtain books with acceptable printing quality and mark them as standard books; Mark the books whose printing quality is to be tested by the target publisher as books to be tested; Collecting quality data of the books to be tested and standard books, the quality data including but not limited to text clarity parameters, color reproduction index, and ink dot distribution density; The quality data of the books to be tested and the standard books are formatted and processed separately to eliminate irrelevant noise information; Match the quality data of the book to be tested with that of the standard book according to the book's page sequence and chapter structure to ensure that the quality parameters of each page and each paragraph are in the corresponding analysis dimension; For each set of quality parameters after matching, the corresponding parameter values ​​of the standard book are subtracted from the parameter values ​​of the book to be tested to generate a quality deviation data set; Set the reasonable deviation range allowed for printing quality, and classify and convert each parameter deviation value in the quality deviation data set: if the deviation value exceeds the reasonable range, it is marked as a failed point; if it is within the reasonable range, it is marked as a qualified point; The proportion of unqualified points in the total number of inspection points is calculated and recorded as the quality deviation ratio; When the quality deviation ratio exceeds the pre-set quality threshold, the printing quality of the book is judged to be unqualified, and the book number, deviation location, and deviation type information are packaged and uploaded to the digital management center, and the early warning mechanism is triggered to notify the management personnel to intervene in the printing quality control; if it does not exceed the threshold, the printing quality is judged to be qualified and enters the normal circulation link.

[0028] Book copyright management module: used to manage the target publisher’s book copyright resources, store key copyright links on the chain, monitor copyright usage in real time, and issue infringement warnings.

[0029] In this embodiment, it should be specifically explained that the execution method of the book copyright management module is as follows: By building a structured copyright resource database, we can achieve refined management of book copyright subject information, rights content, certification documents and rights chain relationships. Combined with blockchain technology, we can hash and store evidence on the chain for the six key links of creation completion, authorization signing, administrative registration, authorization license, rights change and infringement evidence collection, ensuring that the rights chain is traceable and cannot be tampered with.

[0030] Finally: 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, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

[0031] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A publishing house full-process digital management system based on big data analysis, characterized by: include: Publishing house topic planning module: used to obtain multi-source heterogeneous data of books, establish a feasibility assessment model for each topic based on the multi-source heterogeneous data of books, and output the feasibility coefficient of each topic as the effective topic information of the target publishing house; Topic content determination module: based on the valid topic information, obtains the topic content of the target publisher, and determines the topic content of the book published by the corresponding target publisher according to the topic content; Publishing house order management module: used to receive actual book order information from the target publishing house's corresponding order management platform, and manage the production and printing of book orders in combination with the paper format optimization algorithm; Book inventory monitoring module: used to monitor the book inventory of the target publishing house in real time, obtain the book sales data and inventory data corresponding to the target publishing house, establish a book inventory forecast index model, and allocate and manage the book inventory based on the book inventory forecast index; Book quality assessment module: used to analyze the deviation between the printing quality of the books to be tested and the standard books, mark the books with unqualified printing quality according to the deviation analysis results, upload the information of the books with unqualified printing quality to the digital management center, and notify the management personnel to carry out book printing quality management; Book copyright management module: used to manage the target publisher’s book copyright resources, store key copyright links on the chain, monitor copyright usage in real time, and issue infringement warnings.

2. The publishing house full-process digital management system based on big data analysis according to claim 1 is characterized by: The specific content of the publisher's topic planning module acquiring multi-source heterogeneous data of books is as follows: The API interface is used to connect to the data source to obtain multi-source heterogeneous data of books, including market sales data, reader evaluation data, social media popularity data, academic citation index and competitive product analysis data.

3. The publishing house full-process digital management system based on big data analysis according to claim 1 is characterized by: The specific steps of establishing the feasibility evaluation model for each topic based on the multi-source heterogeneous data of books are as follows: Clean and preprocess the acquired multi-source heterogeneous data of books to obtain book text data; Use natural language processing technology to perform topic extraction, sentiment analysis, and keyword extraction on the book text data to build a multi-dimensional evaluation index system; Based on the multi-dimensional evaluation index system, a feasibility evaluation model for each topic is established, and the standardized scores of each evaluation index corresponding to each topic and the weights corresponding to each evaluation index are input into the feasibility evaluation model of each topic to calculate the feasibility coefficient of each topic.

4. The publishing house full-process digital management system based on big data analysis according to claim 1 is characterized by: The execution mode of the topic content determination module is as follows: Receive the feasibility coefficient data of each topic output from the topic planning module, use the preset feasibility coefficient threshold screening mechanism to obtain the target reference topic information; Screening the target reference topic information, wherein the specific content of the screening is: obtaining the historical publishing data, professional field advantages, existing author resources and market positioning of the target publishing house, and screening in combination with the target reference topic information; Performing a topic duplication check on the target reference topic information. The specific content of the topic duplication check is: comparing the target reference topic information with the content of books published by the publisher in the past three years through a text similarity algorithm, marking topics with a similarity of more than 70% as potential duplicate topics, and automatically lowering the recommendation priority of the topic; Based on the screening of the target reference topic information and the checking of topic duplication, a topic content recommendation report for the target publishing house is automatically generated, and the topic content recommendation report for the target publishing house is uploaded to the digital management center, which is reviewed and reviewed online by the publishing house editorial committee. The editorial committee members vote and comment on each topic, and the digital management center counts the review results in real time, and determines the topic content of the target publishing house's books based on the review results.

5. The publishing house full-process digital management system based on big data analysis according to claim 4 is characterized by: The specific content of the target reference topic information is as follows: Read the feasibility coefficient of each topic, compare the feasibility coefficient of each topic with the preset feasibility coefficient threshold, screen out topics whose feasibility coefficient is greater than the preset feasibility coefficient threshold, automatically mark the topics greater than the preset feasibility coefficient threshold as target reference topic information, obtain the topic number, transmit the corresponding topic number to the digital management center, and the management personnel obtain the topic content corresponding to the topic number.

6. The publishing house full-process digital management system based on big data analysis according to claim 1 is characterized by: The execution method of the production and printing management of book orders in combination with the paper size optimization algorithm is as follows: Obtaining original paper size information and book size information, wherein the original paper size information includes the length and width of the original paper, and the book size information includes the length and width of a single finished book; Establishing a paper utilization coefficient model based on the original paper size information and the book size information, inputting the original paper size information and the book size information into the paper utilization coefficient model, and calculating the paper utilization coefficient; Based on the paper size optimization algorithm, by maximizing the paper utilization coefficient, the paper size optimization value is output, and the paper size optimization value is uploaded to the digital management center. The production management personnel will manage the production and printing of book orders based on the paper size optimization value.

7. The publishing house full-process digital management system based on big data analysis according to claim 1 is characterized by: The execution mode of the book inventory monitoring module is as follows: Obtain book sales data and inventory data corresponding to the target publisher. The book sales data includes book sales volume, return rate, and repurchase rate. The inventory data includes the number of books in stock and the number of books in transit. Preprocess the acquired book sales data and inventory data; Extracting corresponding characteristic factors from the book sales data and inventory data, wherein the characteristic factor corresponding to the book sales data is an effective demand factor, and the characteristic factor corresponding to the inventory data is an available inventory factor; Based on the effective demand factor and available inventory factor, a book inventory forecasting index model is established; Calculate the mean of the effective demand factor and standard deviation , the mean of the available inventory factor and standard deviation ; The effective demand factor and available inventory factor, the mean and standard deviation of the effective demand factor, and the mean and standard deviation of the available inventory factor are respectively input into the book inventory forecast index model to calculate the book inventory forecast index; The book inventory forecast index is uploaded to the digital management center, and the inventory management personnel allocate and manage the book inventory based on the book inventory forecast index.

8. The publishing house full-process digital management system based on big data analysis according to claim 7 is characterized by: The specific process of extracting the effective demand factor is as follows: obtaining the thirty-day book sales volume Sv corresponding to the target publisher, obtaining the thirty-day corresponding return rate Cr and repurchase rate Rr from the backend data of the order management platform, importing the thirty-day book sales volume, return rate and repurchase rate into the calculation model of the effective demand factor, and calculating the effective demand factor EDF; The extraction process of the available inventory factor is specifically as follows: adding the number of books in stock and the number of books in transit corresponding to the target publishing house to obtain the available inventory factor AIF.

9. The publishing house full-process digital management system based on big data analysis according to claim 1 is characterized by: The execution method of the book quality assessment module is as follows: Obtain books with acceptable printing quality and mark them as standard books; Mark the books whose printing quality is to be tested by the target publisher as books to be tested; Collect quality data of the books to be tested and the standard books; The quality data of the books to be tested and the standard books are respectively processed in a standardized format; Match the quality data of the book to be tested with the standard book according to the page order and chapter structure of the book; For each set of quality parameters after matching, the corresponding parameter values ​​of the standard book are subtracted from the parameter values ​​of the book to be tested to generate a quality deviation data set; Set the reasonable deviation range allowed for printing quality, and classify and convert each parameter deviation value in the quality deviation data set: if the deviation value exceeds the reasonable range, it is marked as a failed point; if it is within the reasonable range, it is marked as a qualified point; The proportion of unqualified points in the total number of inspection points is calculated and recorded as the quality deviation ratio; When the quality deviation ratio exceeds the pre-set quality threshold, the book's printing quality is judged to be unqualified, and the book's number, deviation location, and deviation type information are packaged and uploaded to the digital management center. The early warning mechanism is triggered to notify management personnel to intervene in printing quality control; If the threshold is not exceeded, the printing quality is judged to be qualified and enters the normal circulation link.

Images