Data management method for book publishing industry

Abstract

The invention provides a data management method for a book publishing industry, relates to the technical field of data management, and solves the problems that the current book publishing industry has the conditions of inconsistent data calibers, inaccurate data, repeated data and the like, and the book data lacks a unified data standard. The method comprises the following steps: analyzing historical book data, and establishing a book sub-data table according to the analyzed book sub-data; performing duplicate record detection on the first book sub-data, merging duplicate book sub-data obtained by duplicate record detection, and obtaining an original field according to the merged book sub-data; respectively mapping the original fields into corresponding standard fields, and establishing a standard field table through the original fields and the corresponding standard fields; and combining the standard field tables into a book data set, inputting the book data set into a deep learning model for training, and converting real-time book data into standard book data, so that data management of the book publishing industry is realized, and standardization of data use is ensured.

Description

Technical Field

[0001] The present invention belongs to the technical field of data management, and specifically relates to a data management method for the book publishing industry. Background Art

[0002] Data governance is to ensure that data within an organization is effectively managed, protected, and used by developing policies, standards, and processes. It covers data quality control, privacy protection, data security, compliance, and data lifecycle management. The goal of data governance is to ensure the accuracy, consistency, availability, compliance, and security of data, thereby providing reliable information support for decision-making and improving the efficiency and transparency of the organization's use of data.

[0003] In the existing technology, the book publishing industry usually has multiple independent systems and platforms. There is a lack of effective data sharing and collaboration between these systems, resulting in data islands, which leads to data missing, inconsistent data, inaccurate data and data duplication in the book publishing industry, and further leads to the lack of unified data standards for book data. To this end, the present invention proposes a data governance method for the book publishing industry. Summary of the invention

[0004] The purpose of the present invention is to propose a data governance method for the book publishing industry to solve the problems raised in the above background technology.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions: A data governance method for the book publishing industry, the method is as follows: Step S1, obtaining historical book data of a book publisher, and then analyzing the historical book data to obtain book sub-data, and establishing a book sub-data table based on the book sub-data; Step S2, performing duplicate record detection on the first book sub-data, merging duplicate book sub-data obtained by the duplicate record detection, and obtaining the original field according to the merged book sub-data; Step S3, mapping different original fields to corresponding standard fields respectively, and establishing a standard field table according to the different original fields and the corresponding standard fields; Step S4, merging each standard field table into a book data set, and inputting the book data set into a deep learning model for training, collecting real-time book data from book publishers, and converting the real-time book data into standard book data through the deep learning model; Step S5, mapping the standard book data to the book data management platform.

[0006] Furthermore, the historical book data includes the title, first author, ISBN and publication date of the books published by the book publisher.

[0007] Furthermore, the step S1 includes the following sub-steps: Step S11, dividing the historical book data of the book publisher into a plurality of book sub-data according to the book data attributes corresponding to the historical book data, wherein the book data attributes corresponding to the historical book data of the book publisher include a book title attribute, a first author attribute, an ISBN attribute, and a publication date attribute; Step S12, establishing a book sub-data table according to the book sub-data.

[0008] Furthermore, the division process of the book sub-data is as follows: Step S111, dividing the historical book data into first book sub-data, second book sub-data, third book sub-data and fourth book sub-data according to the book data attributes corresponding to the historical book data; Step S112, dividing the first book sub-data according to the book title attribute, wherein the fields in the first book sub-data include the book title, the book name and the book title; Step S113, dividing the second book sub-data according to the author attribute, the fields in the second book sub-data include the first author, the first writer and the first editor; Step S114, dividing the third book sub-data according to the ISBN attribute, wherein the fields in the third book sub-data include the international standard book number and the ISBN number; Step S115, dividing the fourth book sub-data according to the publication date attribute, the fields in the fourth book sub-data include the publication date and the release date.

[0009] Furthermore, the step S2 includes the following sub-steps: Step S21, performing data preprocessing on the first book sub-data, removing symbols and spaces in the first book sub-data, and splitting the fields in the first book sub-data into multiple words; Step S22, calculating the text similarity of the first book sub-data; Step S23, when it is calculated that the repetition value of the field in the first book sub-data is less than the repetition value threshold, no operation is performed; when it is calculated that the repetition value of the field in the first book sub-data is greater than or equal to the repetition value threshold, it is determined that the current book title and another book title are duplicate records, and the first book sub-data corresponding to the current book title and another book title are marked as duplicate book sub-data, and then the next step is entered; Step S24, comparing the ISBN of the current book title with the ISBN of another book title, if the ISBN of the current book title is different from the ISBN of another book title, no operation is performed; If the ISBN of the current title is the same as the ISBN of another title, proceed to the next step; Step S25, merging the second book sub-data, the third book sub-data and the fourth book sub-data corresponding to the repeated book sub-data; Step S26, after the book sub-data are merged, the fields in the first book sub-data are recorded as the first original fields, the fields in the second book sub-data are recorded as the second original fields, the fields in the third book sub-data are recorded as the third original fields, and the fields in the fourth book sub-data are recorded as the fourth original fields.

[0010] Furthermore, the calculation process of text similarity is as follows: Convert the fields in the first book sub-data into word vectors one by one, and use the formula to calculate the repeated values ​​between the fields one by one; Convert one book title into a word vector vA, convert another book title into a word vector vB, and use the formula to calculate the repetition value between the book title and the other book title. The formula is as follows: CS(vA, vB) = (vA×vB) / (||vA||×||vB||); where CS represents cosine similarity.

[0011] Furthermore, the step S3 includes the following sub-steps: Step S31, mapping the first original field in the first book sub-data to the first standard field; Step S32, mapping the second original field in the second book sub-data into a second standard field; Step S33, mapping the third original field in the third book sub-data into a third standard field; Step S34, mapping the fourth original field in the fourth book sub-data to the fourth standard field.

[0012] Furthermore, the step S4 includes the following sub-steps: Step S41, merging the standard field tables, and then using the third standard field table as the primary key, the first standard field table, the second standard field table and the fourth standard field table are matched and merged one by one through the third standard field table, and a book data set is obtained after matching and merging; Step S42, inputting the book data set as a training sample into the deep learning model for training; Step S43, dividing the collected real-time book data of the book publisher into multiple real-time book sub-data, constructing a real-time book sub-data table, and inputting the real-time book sub-data table into the trained deep learning model.

[0013] Furthermore, the step S4 further includes the following sub-steps: Step S44, when any original field is missing in the real-time book sub-data table, the deep learning model fills in the missing original field; Step S45, the deep learning model converts each original field in the real-time book data into a corresponding standard field, and then outputs it as standard book data; Step S46, the deep learning model outputs standard book data and stores it.

[0014] Furthermore, the filling process of the original field is as follows: When the deep learning model detects that any original field is missing in the real-time book sub-data table, the missing original field is marked as a missing field, and other original fields corresponding to the missing field are obtained; The missing field data is inferred based on other original fields corresponding to the missing field, and the inferred missing field data is filled into the missing field.

[0015] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are: 1. The present invention analyzes historical book data to obtain book sub-data, establishes a book sub-data table based on the book sub-data, performs duplicate record detection on the book sub-data, merges the duplicate book sub-data obtained by the duplicate record detection, obtains original fields based on the merged book sub-data, and then maps the original fields to corresponding standard fields respectively, and finally establishes a standard field table based on the original fields and the corresponding standard fields; 2. The present invention merges the standard field tables into a book data set, inputs the book data set into a deep learning model for training, inputs the real-time book data of the book publisher, and converts the real-time book data into standard book data through the deep learning model. The present invention realizes data governance for the book publishing industry, ensures the standardization of data use, standardizes data standards and improves data use efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to facilitate understanding by those skilled in the art, the present invention is further described below with reference to the accompanying drawings.

[0017] Figure 1 is a flow chart of the method of the present invention; Figure 2 is a method flow chart of the sub-steps corresponding to step S1 in the present invention; Figure 3 is a method flow chart of the sub-steps corresponding to step S3 in the present invention; Figure 4 It is a schematic diagram of the structure of the computer device in the present invention. DETAILED DESCRIPTION

[0018] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0019] Example 1: Please refer to Figure 1-Figure 3 As shown, the technical solution provided by the present invention is: a data governance method for the book publishing industry, which is mainly used to supplement the missing data in the book data and store the book data in a standardized manner. The method is specifically as follows: Step S1, obtaining historical book data of a book publisher, and then analyzing the historical book data to obtain book sub-data, and establishing a book sub-data table based on the book sub-data; It should be specifically stated that the data sources for collecting historical book data include but are not limited to e-book platforms and book publishers; historical book data include the titles, first authors, ISBNs and publication dates of books published by book publishers. Each book is uniquely associated with a title, a first author, an ISBN and a publication date; ISBN is an international standard book number, which is an international number designed specifically for identifying books and other documents. Each ISBN corresponds to a unique book. In this embodiment, step S1 includes the following sub-steps: Step S11, dividing the historical book data of the book publisher into a plurality of book sub-data according to the book data attributes corresponding to the historical book data; It should be specifically explained that the book data attributes corresponding to the historical book data of the book publisher include the book title attribute, the first author attribute, the ISBN attribute and the publication date attribute; the book sub-data is a set consisting of fields with the same book data attributes in the historical book data, and the fields are used to describe the specific content corresponding to the set with the same book data attributes; Step S111, dividing the historical book data into first book sub-data, second book sub-data, third book sub-data and fourth book sub-data according to the book data attributes corresponding to the historical book data; Step S112, dividing the first book sub-data according to the book title attribute, wherein the fields in the first book sub-data include the book title, the book name and the book title; Step S113, dividing the second book sub-data according to the author attribute, the fields in the second book sub-data include the first author, the first writer and the first editor; Step S114, dividing the third book sub-data according to the ISBN attribute, wherein the fields in the third book sub-data include the international standard book number and the ISBN number; Step S115, dividing the fourth book sub-data according to the publication date attribute, wherein the fields in the fourth book sub-data include the publication date and the release date; Step S12, establishing a book sub-data table according to the book sub-data.

[0020] Exemplarily, the book sub-data table is shown in Table 1, and the details of Table 1 are as follows:

[0021] The book titles and ISBN numbers in Table 1 are examples; Step S2, performing duplicate record detection on the first book sub-data, merging duplicate book sub-data obtained by the duplicate record detection, and obtaining the original field according to the merged book sub-data; In this embodiment, step S2 includes the following sub-steps: Step S21, performing data preprocessing on the first book sub-data, removing symbols and spaces in the first book sub-data, and splitting the fields in the first book sub-data into multiple words; Step S22, calculating the text similarity of the first book sub-data; Specifically, the fields in the first book sub-data are converted into word vectors one by one, and the repeated values ​​between the fields are calculated one by one using the formula; For example, convert the book title A into a word vector vA, convert the book title B into a word vector vB, and use the formula to calculate the repetition value between the book title A and the book title B. The formula is as follows: CS(vA, vB) = (vA×vB) / (||vA||×||vB||), where CS represents cosine similarity; Step S23, when it is calculated that the repetition value of the field in the first book sub-data is less than the repetition value threshold, no operation is performed; when it is calculated that the repetition value of the field in the first book sub-data is greater than or equal to the repetition value threshold, it is determined that the current book title and another book title are duplicate records, and the first book sub-data corresponding to the current book title and another book title are marked as duplicate book sub-data, and then the next step is entered; Step S24, comparing the ISBN of the current book title with the ISBN of another book title, if the ISBN of the current book title and the ISBN of another book title are different, no operation is performed; if the ISBN of the current book title and the ISBN of another book title are the same, proceeding to the next step; Step S25, merging the second book sub-data, the third book sub-data and the fourth book sub-data corresponding to the repeated book sub-data; Step S26, after the book sub-data are merged, the fields in the first book sub-data are recorded as the first original fields, the fields in the second book sub-data are recorded as the second original fields, the fields in the third book sub-data are recorded as the third original fields, and the fields in the fourth book sub-data are recorded as the fourth original fields.

[0022] Step S3, mapping different original fields to corresponding standard fields respectively, and establishing a standard field table according to the different original fields and the corresponding standard fields; In this embodiment, step S3 includes the following sub-steps: Step S31, mapping the first original field in the first book sub-data to the first standard field; Exemplarily, the book title, book name and book title corresponding to the first original field in the first book sub-data are mapped to Title, and Title is the first standard field. The user or staff changes the first standard field according to their own needs, and establishes a first standard field table based on the first standard field. The first standard field table is shown in Table 2, and Table 2 is specifically as follows:

[0023] Step S32, mapping the second original field in the second book sub-data into a second standard field; Exemplarily, the first author, the first writer and the first editor corresponding to the second original field in the second book sub-data are mapped to Author, and Author is the second standard field. The user or staff changes the second standard field according to their own needs, and establishes a second standard field table based on the second standard field. The second standard field table is shown in Table 3, and Table 3 is specifically as follows:

[0024] Step S33, mapping the third original field in the third book sub-data into a third standard field; Exemplarily, the international standard book number and ISBN number corresponding to the third original field in the third book sub-data are mapped to ISBN, and ISBN is the third standard field. The user or staff changes the third standard field according to their own needs, and establishes a third standard field table based on the third standard field. The third standard field table is shown in Table 4, and Table 4 is specifically as follows:

[0025] Step S34, mapping the fourth original field in the fourth book sub-data to a fourth standard field; Exemplarily, the publication date and release date corresponding to the fourth original field in the fourth book sub-data are mapped to Date, which is the fourth standard field, and the format of Date is adjusted to YYYY-MM-DD. The user or staff can change the fourth standard field and the format of the fourth standard field according to their own needs; It should be noted that in the Date format, YYYY represents the year, MM represents the month, and DD represents the day.

[0026] The fourth standard field table is shown in Table 5, and Table 5 is specifically as follows:

[0027] Step S4, merging each standard field table into a book data set, and inputting the book data set into a deep learning model for training, collecting real-time book data from book publishers, and converting the real-time book data into standard book data through the deep learning model; In this embodiment, step S4 includes the following sub-steps: Step S41, merging the standard field tables, and then using the third standard field table as the primary key, the first standard field table, the second standard field table and the fourth standard field table are matched and merged one by one through the third standard field table, and a book data set is obtained after matching and merging; It should be specifically noted that the ISBN in the third standard field table uniquely corresponds to a Title, an Author, and a publication date; the primary key is the unique identifier of the book; Step S42, inputting the book data set as a training sample into the deep learning model for training; It should be specifically noted that deep learning models include sequence-based models, BERT models, multimodal deep learning models, etc. In this embodiment, the BERT model is preferred. The BERT model is more excellent when processing texts containing a large number of synonyms and spelling errors; Step S43, dividing the collected real-time book data of the book publisher into a plurality of real-time book sub-data, constructing a real-time book sub-data table, and inputting the real-time book sub-data table into the trained deep learning model; Step S44, when any original field is missing in the real-time book sub-data table, the deep learning model fills in the missing original field; Specifically, when the deep learning model detects that a certain original field is missing in the real-time book sub-data table, the missing original field is marked as a missing field, and other original fields corresponding to the missing field are obtained; Infer the missing field data based on other original fields corresponding to the missing field, and fill the missing field with the inferred missing field data; Step S45, the deep learning model converts each original field in the real-time book data into a corresponding standard field, and then outputs it as standard book data; The process of obtaining the real-time book sub-data table is the same as that of obtaining the book sub-data table. Step S46, the deep learning model outputs standard book data and stores it; Step S5, mapping the standard book data to the book data management platform; Among them, the book data management platform is an existing technology, and the book data management platform can refer to the book data management system and obtain the book data management platform by modification; In this application, if corresponding calculation formulas appear, the above calculation formulas are all dimensionless and take their numerical calculations. The weight coefficients, proportional coefficients and other coefficients in the formulas are set to a result value obtained by quantifying each parameter. The size of the weight coefficient and the proportional coefficient can be determined as long as it does not affect the proportional relationship between the parameter and the result value.

[0028] Embodiment 2: Figure 4 The following is a schematic diagram of the structure of a computer device, such as Figure 4 As shown, the computer device may include: a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus. The processor may call the logic instructions in the memory to execute a data governance method for the book publishing industry, the method comprising: obtaining the historical book data of the book publisher, and then analyzing the historical book data to obtain book sub-data through analysis, and establishing a book sub-data table based on the book sub-data; performing duplicate record detection on the first book sub-data, merging the duplicate book sub-data obtained by the duplicate record detection, and obtaining the original field according to the merged book sub-data; mapping different original fields to corresponding standard fields respectively, and establishing a standard field table according to different original fields and corresponding standard fields; merging each standard field table into a book data set, and inputting the book data set into a deep learning model for training, collecting the real-time book data of the book publisher, and converting the real-time book data into standard book data through the deep learning model; mapping the standard book data to the book data management platform.

[0029] In addition, the logic instructions in the above-mentioned memory can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0030] On the other hand, the present application also provides a computer program product, which includes a computer program stored on a computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute a data governance method for the book publishing industry provided by the above methods, the method including: obtaining historical book data of a book publisher, and then analyzing the historical book data to obtain book sub-data through analysis, and establishing a book sub-data table based on the book sub-data; performing duplicate record detection on the first book sub-data, merging the duplicate book sub-data obtained by the duplicate record detection, and obtaining the original field based on the merged book sub-data; mapping different original fields to corresponding standard fields respectively, and establishing a standard field table based on different original fields and corresponding standard fields; merging each standard field table into a book data set, and inputting the book data set into a deep learning model for training, collecting real-time book data of book publishers, and converting the real-time book data into standard book data through a deep learning model; mapping the standard book data to a book data management platform.

[0031] On the other hand, the present application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute a data governance method for the book publishing industry provided above, the method comprising: obtaining historical book data of a book publisher, and then analyzing the historical book data to obtain book sub-data through analysis, and establishing a book sub-data table based on the book sub-data; performing duplicate record detection on the first book sub-data, merging the duplicate book sub-data obtained through the duplicate record detection, and obtaining the original field based on the merged book sub-data; mapping different original fields to corresponding standard fields respectively, and establishing a standard field table based on different original fields and corresponding standard fields; merging the standard field tables into a book data set, and inputting the book data set into a deep learning model for training, collecting real-time book data of book publishers, and converting the real-time book data into standard book data through a deep learning model; mapping the standard book data to a book data management platform.

[0032] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0033] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0034] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A data governance method for the book publishing industry, characterized in that: The specific method is as follows: Step S1, obtaining historical book data of a book publisher, and then analyzing the historical book data to obtain book sub-data, and establishing a book sub-data table based on the book sub-data; Step S2, performing duplicate record detection on the first book sub-data, merging duplicate book sub-data obtained by the duplicate record detection, and obtaining the original field according to the merged book sub-data; Step S3, mapping different original fields to corresponding standard fields respectively, and establishing a standard field table according to the different original fields and the corresponding standard fields; Step S4, merging each standard field table into a book data set, and inputting the book data set into a deep learning model for training, collecting real-time book data from book publishers, and converting the real-time book data into standard book data through the deep learning model; Step S5, mapping the standard book data to the book data management platform.

2. A data management method for the book publishing industry according to claim 1, characterized in that: Historical book data includes the title, first author, ISBN, and publication date of books published by book publishers.

3. A data management method for the book publishing industry according to claim 2, characterized in that: The step S1 includes the following sub-steps: Step S11, dividing the historical book data of the book publisher into a plurality of book sub-data according to the book data attributes corresponding to the historical book data, wherein the book data attributes corresponding to the historical book data of the book publisher include a book title attribute, a first author attribute, an ISBN attribute, and a publication date attribute; Step S12, establishing a book sub-data table according to the book sub-data.

4. A data management method for the book publishing industry according to claim 3, characterized in that: The division process of the book sub-data is as follows: Step S111, dividing the historical book data into first book sub-data, second book sub-data, third book sub-data and fourth book sub-data according to the book data attributes corresponding to the historical book data; Step S112, dividing the first book sub-data according to the book title attribute, wherein the fields in the first book sub-data include the book title, the book name and the book title; Step S113, dividing the second book sub-data according to the author attribute, the fields in the second book sub-data include the first author, the first writer and the first editor; Step S114, dividing the third book sub-data according to the ISBN attribute, wherein the fields in the third book sub-data include the international standard book number and the ISBN number; Step S115, dividing the fourth book sub-data according to the publication date attribute, the fields in the fourth book sub-data include the publication date and the release date.

5. A data management method for the book publishing industry according to claim 4, characterized in that: The step S2 includes the following sub-steps: Step S21, performing data preprocessing on the first book sub-data, removing symbols and spaces in the first book sub-data, and splitting the fields in the first book sub-data into multiple words; Step S22, calculating the text similarity of the first book sub-data; Step S23, when it is calculated that the repetition value of the field in the first book sub-data is less than the repetition value threshold, no operation is performed; when it is calculated that the repetition value of the field in the first book sub-data is greater than or equal to the repetition value threshold, it is determined that the current book title and another book title are duplicate records, and the first book sub-data corresponding to the current book title and another book title are marked as duplicate book sub-data, and then the next step is entered; Step S24, comparing the ISBN of the current book title with the ISBN of another book title, if the ISBN of the current book title is different from the ISBN of another book title, no operation is performed; If the ISBN of the current title is the same as the ISBN of another title, proceed to the next step; Step S25, merging the second book sub-data, the third book sub-data and the fourth book sub-data corresponding to the repeated book sub-data; Step S26, after the book sub-data are merged, the fields in the first book sub-data are recorded as the first original fields, the fields in the second book sub-data are recorded as the second original fields, the fields in the third book sub-data are recorded as the third original fields, and the fields in the fourth book sub-data are recorded as the fourth original fields.

6. A data management method for the book publishing industry according to claim 5, characterized in that: The calculation process of text similarity is as follows: Convert the fields in the first book sub-data into word vectors one by one, and use the formula to calculate the repeated values ​​between the fields one by one; Convert one book title into a word vector vA, convert another book title into a word vector vB, and use the formula to calculate the repetition value between the book title and the other book title. The formula is as follows: CS(vA, vB) = (vA×vB) / (||vA||×||vB||); where CS represents cosine similarity.

7. A data management method for book publishing industry according to claim 1, characterized in that: The step S3 includes the following sub-steps: Step S31, mapping the first original field in the first book sub-data to the first standard field; Step S32, mapping the second original field in the second book sub-data into a second standard field; Step S33, mapping the third original field in the third book sub-data into a third standard field; Step S34, mapping the fourth original field in the fourth book sub-data into the fourth standard field.

8. A data management method for the book publishing industry according to claim 1, characterized in that: The step S4 includes the following sub-steps: Step S41, merging the standard field tables, and then using the third standard field table as the primary key, the first standard field table, the second standard field table and the fourth standard field table are matched and merged one by one through the third standard field table, and a book data set is obtained after matching and merging; Step S42, inputting the book data set as a training sample into the deep learning model for training; Step S43, dividing the collected real-time book data of the book publisher into multiple real-time book sub-data, constructing a real-time book sub-data table, and inputting the real-time book sub-data table into the trained deep learning model.

9. A data management method for the book publishing industry according to claim 8, characterized in that: The step S4 also includes the following sub-steps: Step S44, when any original field is missing in the real-time book sub-data table, the deep learning model fills in the missing original field; Step S45, the deep learning model converts each original field in the real-time book data into a corresponding standard field, and then outputs it as standard book data; Step S46, the deep learning model outputs standard book data and stores it.

10. A data management method for book publishing industry according to claim 9, characterized in that: The original field filling process is as follows: When the deep learning model detects that any original field is missing in the real-time book sub-data table, the missing original field is marked as a missing field, and other original fields corresponding to the missing field are obtained; The missing field data is inferred based on other original fields corresponding to the missing field, and the inferred missing field data is filled into the missing field.

Images