Book information management system and method based on cloud computing

Abstract

The invention discloses a book information management system and method based on cloud computing, and relates to the technical field of book management, and the method comprises the steps: judging whether a to-be-stored book is a super-standard book or not when a new book is stored, obtaining a reference storage position corresponding to the to-be-stored book of a non-super-standard book, and storing the reference storage position in a database; character conversion and quantization are carried out on content information of each book under different data types to generate a feature vector, an interaction range graph of a corresponding category is constructed in combination with a polar coordinate model, and a position vector is generated according to space information such as floors and bookshelf numbers of the books and is bound and stored. When a new book is put in storage, the system automatically carries out matching analysis on the feature vector of the new book and the interaction range of the corresponding category, judges whether the book is a super-standard book or not, provides an optimal reference storage position for a normal book, or gives an early warning prompt when an abnormality exists, so that the book classification accuracy is improved, and the put-in-storage decision process is simplified.

Description

Technical Field

[0001] The present invention belongs to the technical field of book management, and in particular relates to a book information management system and method based on cloud computing. Background Art

[0002] With the continuous growth of library collections and the development of digital technology, book information management faces numerous challenges. Traditional book information management methods often rely on a combination of manual classification and simple database storage, which suffers from low classification efficiency and poor retrieval accuracy. Although some libraries have introduced digital management systems during the digital transformation process, most existing book management systems use static classification or manual tagging, which cannot fully explore the characteristics of book content. They also lack the comprehensive processing capabilities to dynamically manage and accurately locate books based on multiple data types (such as text, images, audio, video, tables, etc.), making it difficult to accurately locate and efficiently manage book resources.

[0003] For example, when determining the storage location of books, a simple division based on book category is often used, without fully considering the differences in characteristics of books under different data types. This leads to unreasonable book storage locations and affects borrowing efficiency. At the same time, there is a lack of an effective judgment mechanism for handling newly arrived books, making it impossible to promptly detect data anomalies or books with content that deviates from their respective categories, resulting in a low level of intelligent management. Furthermore, the classification and storage of new books usually rely on manual judgment, lacking an automatic analysis and recommendation mechanism, which can easily lead to storage confusion or classification errors. Based on this, a cloud computing-based book information management system and method are proposed. Summary of the Invention

[0004] The purpose of the present invention is to provide a book information management system and method based on cloud computing, which solves the technical problem that when determining the storage location of books, a simple division is often made based on the book category, without fully considering the characteristic differences of books under different data types, resulting in unreasonable book storage locations and affecting borrowing efficiency.

[0005] A book information management method based on cloud computing includes the following steps: Step 1: Generate multiple root category numbers based on the book's major category and the subcategories corresponding to the major category; Step 2: Perform character conversion on the different book contents associated with the books under each root category number under different data types to obtain the feature values ​​corresponding to the different books under each root category number under different data types. The different data types refer to text, image, audio, video, and table data types. Step 3: Obtain the corresponding benchmark interaction range for each root category number based on the characteristic values ​​of different books under different data types under each root category number; Step 4: Obtain the location labels corresponding to each book according to the storage floor and shelf number of each book, and simultaneously obtain the book feature shape vector corresponding to each book, and bind it with the corresponding location label for storage; Step 5: When storing new books, compare and analyze the characteristic shape vector to be analyzed corresponding to the book to be stored with the corresponding benchmark interaction range to determine whether the book to be stored is an out-of-specification book. For books to be stored that are not out-of-specification books, compare and analyze the characteristic shape vector to be analyzed corresponding to the book to be stored with the book characteristic shape vectors of different books under its corresponding root category number to obtain the reference storage position corresponding to the book to be stored.

[0006] As a further solution of the present invention, the specific method of combining and generating multiple root category numbers is as follows: The book's major category XAx and the subcategory XBi corresponding to the major category are combined through / to generate the root category number Gn, where x refers to different major book categories, i refers to the subcategory corresponding to the major book category, n=1, 2,..., a, a refers to the number of root category numbers, a is a positive integer, and a is equal to the sum of the number of subcategories under all major categories.

[0007] As a further solution of the present invention, the specific method for obtaining the characteristic values ​​corresponding to different books under different data types under each root category number is as follows: First, a root category number is randomly selected from each root category number without replacement as the analysis category number; different book contents associated with different books belonging to the analysis category number under different data types are obtained; For text data types, the number of characters corresponding to the text content in different books is used as the feature value K1r corresponding to the text data type of different books; for image data types, the number of pixels corresponding to the image content in different books is used as the feature value K2r corresponding to the image data type of different books; for audio and video data types, the duration of audio and video in different books is used as the feature value K3r and K4r corresponding to the audio and video data types of different books respectively; For table data types, the number of rows corresponding to the tables in different books is used as the characteristic value K5r corresponding to the table data type of different books, and then the characteristic values ​​corresponding to different books under the analysis category number under different data types are obtained, where r refers to different books under the analysis category number. The same method is used to analyze each root category number one by one, and then the characteristic values ​​corresponding to different books under each root category number under different data types are obtained.

[0008] As a further solution of the present invention, the specific range of the benchmark interaction range corresponding to each root category number is obtained as follows: Select the same root category number as that in step 2 from each root category number as the target category number, mark the target category number as the origin O1, draw a circle C1 with a radius of 10 cm, rotate clockwise with the twelve o'clock direction as the starting point, and evenly divide the circle C1 into five areas through five dividing lines. At the same time, starting from the twelve o'clock direction, mark the five dividing lines as the feature lines corresponding to the data types of text, image, audio, video and table according to the clockwise direction, and mark the five dividing lines as the feature lines corresponding to the data types. According to the feature values ​​corresponding to different books under the analysis category number under different data types, each feature line is evenly divided into 50 unit nodes to obtain the analysis category number. The maximum values ​​K1r, K2r, K3r, K4r and K5r corresponding to the characteristic values ​​of different books under different data types are K1max, K2max, K3max, K4max and K5max, respectively, and they are marked on the corresponding characteristic lines, so as to obtain the boundary points corresponding to the different data types on each characteristic line under the analysis category number, connect each boundary point Jf in sequence, and take the range surrounded by each boundary point as the benchmark interaction range corresponding to the analysis category number, and use the same method to analyze the characteristic values ​​corresponding to the different books under each root category number under different data types one by one, so as to obtain the benchmark interaction range corresponding to each root category number.

[0009] As a further solution of the present invention, the specific method of binding and storing the book characteristic shape vectors corresponding to each book and the corresponding position labels is as follows: According to the storage floor of each book, the second node number D2k corresponding to each book is obtained, where k refers to different storage floors; according to the storage shelf number of each book, the third node number D3m corresponding to each book is obtained, where m refers to different storage shelf numbers; the second node number and the third node number corresponding to each book are combined to obtain the position label Wj corresponding to each book, where j refers to different books, and the characteristic values ​​corresponding to each book under different data types are obtained, and then the book characteristic shape vectors corresponding to each book are obtained, and the position label corresponding to each book and the corresponding book characteristic shape vector are bound and stored one by one.

[0010] As a further solution of the present invention: the specific method of obtaining the reference storage location corresponding to the book to be stored is: According to the characteristic values ​​corresponding to different data types of the books to be stored, the characteristic shape vector U corresponding to the books to be stored is obtained. new (K1 new , K2 new , K3 new , K4 new , K5 new ), obtain the mean of the absolute values ​​of the differences between the values ​​of each data type in the feature shape vector to be analyzed and the values ​​of each data type in the books to be stored. When the mean is greater than the preset threshold value Y1, the books to be stored are judged to be out-of-range books, otherwise they are judged to be non-out-of-range books. For out-of-range books, an early warning message is automatically generated to remind the administrator that the book may have data anomalies or the content deviates from the category to which it belongs; for non-out-of-range books, calculate the mean of the absolute values ​​of the differences between the values ​​of each data type in the feature shape vector to be analyzed and the values ​​of each data type in the feature shape vectors of other books under the corresponding root category number, select the position label corresponding to the book with the smallest mean, and use it as the reference storage position of the books to be stored, thereby determining the reference storage floor and shelf number.

[0011] A book information management system based on cloud computing, comprising: The root category number generating end generates multiple root category numbers based on the book's major category and the subcategories corresponding to the major category; The character conversion end obtains the characteristic values ​​corresponding to different books under different data types under each root category number; The benchmark interaction range acquisition terminal obtains the benchmark interaction range corresponding to each root category number; The book position label binding end obtains the position label corresponding to each book and the book feature shape vector corresponding to each book, and binds and stores them with the corresponding position label; The super-standard book determination terminal compares and analyzes the characteristic shape vector of the book to be stored with the corresponding reference interaction range to determine whether the book to be stored is a super-standard book; The reference storage location acquisition end compares and analyzes the feature shape vector to be analyzed corresponding to the book to be stored and the book feature shape vectors of different books under the corresponding root category number for the books to be stored that do not exceed the standard, and obtains the reference storage location corresponding to the book to be stored.

[0012] Compared with the prior art, the present invention has the following beneficial effects: (1) The present invention can timely detect books that do not meet the characteristic range of their categories through the out-of-category judgment mechanism, thus avoiding unreasonable storage. Once an out-of-category book is detected, the system automatically generates an early warning message to remind the administrator to conduct further inspection and processing of the book, thus ensuring the standardization of book management and the reliability of data; (2) The present invention converts and quantifies the content information of each book under different data types to generate feature vectors, and combines the polar coordinate model to construct an interaction range map of the corresponding category. Then, based on the spatial information such as the floor and shelf number of the book, a position vector is generated and bound for storage. When a new book enters the library, the system automatically matches its feature vector with the interaction range of the corresponding category to determine whether it is an out-of-specification book. It also provides the optimal reference storage location for normal books, or issues an early warning prompt when an anomaly occurs. This makes the library management process more scientific, improves the accuracy of book classification, and simplifies the library entry decision process. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 Schematic diagram of the framework structure of the method of the present invention; Figure 2 Schematic diagram of the system framework structure of the present invention; Figure 3 Schematic diagram of the structure of the benchmark interaction range of the present invention. DETAILED DESCRIPTION

[0014] The technical solutions of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the embodiments described are only some embodiments of the present invention, not all 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.

[0015] Example 1: Please refer to Figure 1 and Figure 3 , this application provides a book information management method based on cloud computing, comprising the following steps: Step 1: Generate multiple root category numbers based on the book's major category and the subcategories corresponding to the major category, so that each book can find a unique corresponding number identifier in the system, realizing systematic classification management of books; The specific method is: combine the book's major category XAx and the subcategory XBi corresponding to the major category through / to generate the root category number Gn, that is, Gn=XAx / XBi, where x refers to different major categories, i refers to the subcategory corresponding to the major category, n=1, 2, ..., a, a refers to the number of root category numbers, a is a positive integer, and a is equal to the sum of the number of subcategories under all major categories; For example, a major category is represented by XAx, where x refers to different major book categories and is a unique identifier. It is represented by XBi, where i refers to the subcategory corresponding to the major book category. When XA1 represents computer science and XB1 represents programming language, the root category number Gn generated by combining the major category and subcategory is Gn = XA1 / XB1, that is, computer science / programming language. It should be noted that the major categories of books and the subcategories corresponding to the major categories can be directly obtained from the library management system or obtained based on library management records. Both are existing and mature technologies, so no further explanation will be given here.

[0016] Compared with the traditional more general classification method, the root category number generated by combining major categories and subcategories is more detailed and accurate. However, this method allows users to quickly locate the required book category and improve book retrieval efficiency.

[0017] Step 2: Obtain the different book contents associated with different books under each root category number under different data types, and perform character conversion on different data types to obtain the feature values ​​corresponding to different books under each root category number under different data types; The specific method of performing character conversion on the different book contents associated with different books under different data types under each root category number to obtain the characteristic values ​​corresponding to different books under different data types under each root category number is as follows: First, a root category number is randomly selected from each root category number without replacement as the analysis category number; Obtain different book contents associated with different books under the analysis category number under different data types, where different data types refer to text, image, audio, video and table data types; The specific method of character conversion for different book contents associated with different books under different data types is as follows: For text data types, the number of characters corresponding to the text content in different books is used as the characteristic value K1r corresponding to the text data type of different books; For example, if the number of characters corresponding to the text content of a book is 22, then the characteristic value of the text data type of the book is 22; For image data types, the number of pixels corresponding to the image content in different books is used as the characteristic value K2r corresponding to the image data type of different books; For audio and video data types, the duration of audio and video in different books is used as the characteristic values ​​K3r and K4r corresponding to the audio and video data types of different books respectively; For table data types, the number of rows corresponding to the tables in different books is used as the characteristic value K5r corresponding to the table data type of different books; where r refers to the different books under the analysis category number, and then the characteristic values ​​corresponding to the different data types of different books under the analysis category number are obtained; The same method is used to analyze each root category number one by one, and then obtain the characteristic values ​​corresponding to different books under each root category number in different data types; Using special conversion methods for different data types can comprehensively and accurately capture the various content characteristics of books, measure text data types with the number of characters, and reflect image data types with the number of pixels, etc., so that the content characteristics of books can be presented in digital form. Compared with the traditional method of only focusing on basic information such as book titles and authors, it can more comprehensively reflect the actual content of books, and the obtained characteristic values ​​provide data support for in-depth analysis of books.

[0018] Step 3: Analyze the characteristic values ​​corresponding to different books under each root category number under different data types, and obtain the benchmark interaction range Mn corresponding to each root category number based on the analysis results. The specific method is as follows: Select the same root category number as that in step 2 from each root category number as the target category number; The target category number is marked as the origin O1. With the origin O1 as the circle point, a circle C1 with a radius of R1 is drawn, where R1 is a preset value, specifically 10 cm. The circle C1 is evenly divided into five areas by five dividing lines, starting from the 12 o'clock direction and rotating clockwise. At the same time, the five dividing lines are marked as feature lines corresponding to the data types of text, image, audio, video and table respectively, starting from the 12 o'clock direction and moving in a clockwise direction. At the same time, each feature line is evenly divided into 50 unit nodes, and the distance between each unit node is 10 cm / 50; Obtain the maximum values ​​K1r, K2r, K3r, K4r and K5r corresponding to the characteristic values ​​of different books under the analysis category number under different data types, and mark them on the corresponding characteristic lines respectively, and then obtain the boundary points Jf corresponding to different data types on each characteristic line under the analysis category number, connect each boundary point Jf in sequence, and use the range surrounded by each boundary point as the benchmark interaction range M1 (K1max, K2max, K3max, K4max, K5max) corresponding to the analysis category number, where f refers to different boundary points; The same method is used to analyze the characteristic values ​​corresponding to different books under each root category number under different data types one by one, and then obtain the benchmark interaction range Mn corresponding to each root category number; The benchmark interaction range determined for each root category number is equivalent to establishing a unified set of classification and evaluation standards. When new books are put into the library, they can be compared with this range to determine whether they meet the characteristic range of the category to which they belong, avoiding the chaos in book storage caused by ambiguous classification and improving the standardization and consistency of book classification. When determining the storage location of new books, the benchmark interaction range can help the system quickly determine the degree of feature matching between new books and similar books, provide decision support for the reasonable storage of new books, ensure that new books can be placed in areas that are suitable for their content characteristics, and optimize the library's space utilization and book layout.

[0019] Step 4: Obtain the location labels corresponding to each book based on the storage floor and shelf number of each book. Obtain the book feature shape vectors corresponding to each book based on the feature values ​​corresponding to different data types of different books under each root category number, and bind them to the corresponding location labels for storage. The specific method is as follows: According to the storage floor of each book, the second node number D2k corresponding to each book is obtained, where k refers to a different storage floor; according to the storage shelf number of each book, the third node number D3m corresponding to each book is obtained, where m refers to a different storage shelf number; Combine the second node number D2k and the third node number D3m corresponding to each book into D2kD3m to obtain the position number Wj corresponding to each book, where j represents a different book; Obtain the characteristic values ​​corresponding to each book under different data types, and then obtain the book characteristic shape vector Xj (K1j, K2j, K3j, K4j, K5j) corresponding to each book. Bind and store the corresponding position label Wj and the corresponding book characteristic shape vector Xj in a one-to-one correspondence; By binding the characteristic shape vector of the book with the position label, accurate positioning based on the content characteristics of the book is achieved.

[0020] Step 5: When storing new books, obtain the corresponding feature shape vector to be analyzed of the book to be stored according to the feature values ​​corresponding to the different data types of the book to be stored, and obtain the corresponding root category number according to the major category and subcategory of the book to be stored to obtain the corresponding benchmark interaction range of the book to be stored, compare and analyze the corresponding feature shape vector to be analyzed of the book to be stored with the corresponding benchmark interaction range to determine whether the book to be stored is an out-of-specification book. For books to be stored that are not out-of-specification books, compare and analyze the corresponding feature shape vector to be analyzed of the book to be stored with the book feature shape vectors of different books under the corresponding root category number to obtain the reference storage position corresponding to the book to be stored. The specific method is as follows: When storing new books, obtain the different book contents associated with the books to be stored under different data types, perform character conversion on different data types, obtain the feature values ​​corresponding to the books to be stored under different data types, and then obtain the feature shape vector U to be analyzed corresponding to the books to be stored. new (K1 new , K2 new , K3 new , K4 new , K5 new ), where K1 new 、K2 new 、K3 new 、K4 new and K5 new are the characteristic values ​​corresponding to different data types of the books to be stored, U new For the feature shape vector to be analyzed corresponding to the book to be stored, obtain the mean of the absolute values ​​of the differences between the values ​​of each data type in the feature shape vector to be analyzed and the values ​​of each data type in the book to be stored. When the mean is greater than a preset threshold value Y1, the book to be stored is determined to be an out-of-specification book; otherwise, it is determined to be a non-out-of-specification book. The preset threshold value Y1 is formulated by relevant personnel based on actual needs; For books that exceed the category, an early warning message is automatically generated to remind the administrator that the book may have data anomalies or the content may deviate from the category to which it belongs; The out-of-category identification mechanism promptly identifies books that do not meet the characteristics of their category, preventing them from being stored inappropriately. Once an out-of-category book is detected, the system automatically generates an early warning message, prompting administrators to conduct further inspection and processing of the book, ensuring standardized library management and data reliability.

[0021] For books that do not exceed the standard, calculate the mean of the absolute value of the difference between the numerical value of each data type in the feature shape vector to be analyzed and the numerical value of each data type in the feature shape vector of other books under the corresponding root category number. Select the location label corresponding to the book with the smallest mean value and use it as the reference storage location for the book to be stored, thereby determining the reference storage floor and shelf number. When actually storing, the book to be stored can be placed on the adjacent bookshelf on the same floor as the reference storage location, or on an empty space on the same bookshelf; By combining feature extraction and classification modeling for multimodal book data (text, images, audio, video, and tables), the system achieves standardized expression and dynamic categorization of book information, establishing a binding relationship between book feature vectors and location labels. During the storage of new books, the system automatically determines the rationality of the book classification and generates storage recommendations based on the comparison of book features with pre-set interaction ranges. This addresses the issues of inaccurate classification, manual content determination, and inefficient location allocation in traditional book management, effectively improving the intelligence level of book storage and the accuracy of information matching.

[0022] Example 2: As Example 2 of the present invention, please refer to Figure 2 , provides a book information management system based on cloud computing, which is used to implement the aforementioned disclosed book information management method based on cloud computing, specifically including; The root category number generating end generates multiple root category numbers based on the book's major category and the subcategories corresponding to the major category; The character conversion end performs character conversion on the different book contents associated with the books under each root category number under different data types, and obtains the characteristic values ​​corresponding to the different books under each root category number under different data types; The benchmark interaction range acquisition end obtains the benchmark interaction range corresponding to each root category number according to the characteristic values ​​corresponding to different books under each root category number under different data types; The book location label binding end obtains the location label corresponding to each book according to the storage floor and shelf number of each book, and obtains the book feature shape vector corresponding to each book, and binds it with the corresponding location label for storage; The super-standard book determination terminal, when storing new books, compares and analyzes the feature shape vector to be analyzed corresponding to the book to be stored with the corresponding benchmark interaction range to determine whether the book to be stored is a super-standard book; The reference storage location acquisition end compares and analyzes the feature shape vector of the to-be-stored book that does not exceed the standard, with the feature shape vectors of different books under the corresponding root category number, to obtain the reference storage location corresponding to the to-be-stored book. The out-of-specification determination mechanism can promptly detect books that do not conform to the characteristic range of their categories, thus avoiding unreasonable storage. Once an out-of-specification book is detected, the system automatically generates an early warning message, reminding the administrator to conduct further inspection and processing of the book, ensuring the standardization of book management and the reliability of data. For books that do not exceed the standard, based on the comparison results of the book characteristics with the preset interaction range, the system automatically determines the rationality of the book classification and generates storage suggestions, thus solving the problems of inaccurate classification, manual reliance on content determination, and low location allocation efficiency in traditional book management, and effectively improving the intelligence level of book storage and information matching accuracy. By converting and quantifying the content information of each book under different data types, a feature vector is generated. This is then combined with a polar coordinate model to construct an interaction range map for the corresponding category. Based on spatial information such as the book's floor and shelf number, a location vector is generated and bound for storage. When a new book enters the library, the system automatically matches its feature vector with the interaction range of the corresponding category to determine whether it is an out-of-specification book. It then provides the optimal reference storage location for normal books or issues warnings in the event of anomalies. This makes the library management process more scientific, improves the accuracy of book classification, and simplifies the decision-making process for warehousing.

[0023] Example 3: As Example 3 of the present invention, when this application is specifically implemented, compared with Example 1 and Example 2, the technical solution of this example is to combine the solutions of the above-mentioned Example 1 and Example 2 for implementation.

[0024] The above formulas are all dimensionless and numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters and thresholds in the formulas are set by technicians in this field according to actual conditions.

[0025] 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 book information management method based on cloud computing, characterized in that: The following steps are involved: Step 1: Generate multiple root category numbers based on the book's major category and the subcategories corresponding to the major category; Step 2: Perform character conversion on the different book contents associated with the books under each root category number under different data types to obtain the feature values ​​corresponding to the different books under each root category number under different data types. The different data types refer to text, image, audio, video, and table data types. Step 3: Obtain the corresponding benchmark interaction range for each root category number based on the characteristic values ​​of different books under different data types under each root category number; Step 4: Obtain the location labels corresponding to each book according to the storage floor and shelf number of each book, and simultaneously obtain the book feature shape vector corresponding to each book, and bind it with the corresponding location label for storage; Step 5: When storing new books, compare and analyze the characteristic shape vector to be analyzed corresponding to the book to be stored with the corresponding benchmark interaction range to determine whether the book to be stored is an out-of-specification book. For books to be stored that are not out-of-specification books, compare and analyze the characteristic shape vector to be analyzed corresponding to the book to be stored with the book characteristic shape vectors of different books under its corresponding root category number to obtain the reference storage position corresponding to the book to be stored.

2. A book information management method based on cloud computing according to claim 1, characterized in that: The specific method of combining and generating multiple root category numbers is as follows: The book's major category XAx and the subcategory XBi corresponding to the major category are combined through / to generate the root category number Gn, where x refers to different major book categories, i refers to the subcategory corresponding to the major book category, n=1, 2,..., a, a refers to the number of root category numbers, a is a positive integer, and a is equal to the sum of the number of subcategories under all major categories.

3. The book information management method based on cloud computing according to claim 2, characterized in that: The specific method to obtain the characteristic values ​​corresponding to different books under different data types under each root category number is: First, a root category number is randomly selected from each root category number without replacement as the analysis category number; different book contents associated with different books belonging to the analysis category number under different data types are obtained; For text data types, the number of characters corresponding to the text content in different books is used as the characteristic value K1r corresponding to the text data type of different books; For image data types, the number of pixels corresponding to the image content in different books is used as the feature value K2r corresponding to the image data type of different books; for audio and video data types, the duration of audio and video in different books is used as the feature value K3r and K4r corresponding to the audio and video data types of different books respectively; For table data types, the number of rows corresponding to the tables in different books is used as the characteristic value K5r corresponding to the table data type of different books, and then the characteristic values ​​corresponding to different books under the analysis category number under different data types are obtained, where r refers to different books under the analysis category number. The same method is used to analyze each root category number one by one, and then the characteristic values ​​corresponding to different books under each root category number under different data types are obtained.

4. The cloud computing-based book information management method according to claim 3, characterized in that: The specific ranges of the benchmark interaction ranges corresponding to each root category number are as follows: From each root category number, select the same root category number as that in step 2 as the target category number, mark the target category number as the origin O1, draw a circle C1 with a radius of 10 cm, divide the circle C1 evenly into five areas, and mark the five dividing lines as the characteristic lines corresponding to each data type. According to the characteristic values ​​corresponding to different books under the analysis category number under different data types, obtain the boundary points corresponding to different data types on each characteristic line under the analysis category number, connect each boundary point Jf in sequence, and use the range surrounded by each boundary point as the benchmark interaction range corresponding to the analysis category number. Use the same method to analyze the characteristic values ​​corresponding to different books under each root category number under different data types one by one, and then obtain the benchmark interaction range corresponding to each root category number.

5. The cloud computing-based book information management method according to claim 4, characterized in that: The specific method of marking the five dividing lines as the characteristic lines corresponding to each data type is: Starting from the 12 o'clock direction and rotating in a clockwise direction, the circle C1 is evenly divided into five areas by five dividing lines. At the same time, starting from the 12 o'clock direction and rotating in a clockwise direction, the five dividing lines are marked as feature lines corresponding to the data types of text, image, audio, video and table respectively.

6. The cloud computing-based book information management method according to claim 4, characterized in that: The specific method to obtain the boundary points corresponding to different data types on each characteristic line under the analysis category number is as follows: Each characteristic line is evenly divided into 50 unit nodes, and the maximum values ​​K1r, K2r, K3r, K4r and K5r corresponding to different books under the analysis category number in different data types are obtained, and they are marked on the corresponding characteristic lines respectively, so as to obtain the boundary points corresponding to different data types on each characteristic line under the analysis category number.

7. The cloud computing-based book information management method according to claim 4, characterized in that: The specific method of binding and storing the book feature shape vectors corresponding to each book and the corresponding position labels is as follows: According to the storage floor of each book, the second node number D2k corresponding to each book is obtained, where k refers to different storage floors; according to the storage shelf number of each book, the third node number D3m corresponding to each book is obtained, where m refers to different storage shelf numbers; the second node number and the third node number corresponding to each book are combined to obtain the position label Wj corresponding to each book, where j refers to different books, and the characteristic values ​​corresponding to each book under different data types are obtained, and then the book characteristic shape vectors corresponding to each book are obtained, and the position label corresponding to each book and the corresponding book characteristic shape vector are bound and stored one by one.

8. The cloud computing-based book information management method according to claim 7, characterized in that: The specific method for determining whether the books to be stored are out-of-specification books is as follows: According to the characteristic values ​​corresponding to different data types of the books to be stored, the characteristic shape vector U corresponding to the books to be stored is obtained. new (K1 new , K2 new , K3 new , K4 new , K5 new ), obtain the mean of the absolute values ​​of the differences between the values ​​of each data type in the feature shape vector to be analyzed and the values ​​of each data type in the books to be stored. When the mean is greater than the preset threshold value Y1, the books to be stored are judged to be out-of-specification books, otherwise they are judged to be non-out-of-specification books. For out-of-specification books, an early warning message is automatically generated to remind the administrator that the book may have data anomalies or the content deviates from the category to which it belongs.

9. The book information management method based on cloud computing according to claim 8, characterized in that: The specific method of obtaining the reference storage location corresponding to the book to be stored is: For books that do not exceed the standard, calculate the mean of the absolute value of the difference between the numerical value of each data type in the characteristic shape vector to be analyzed and the numerical value of each data type in the characteristic shape vector of other books under the corresponding root category number, select the position label corresponding to the book with the smallest mean, and use it as the reference storage location for the books to be stored, so as to determine the reference storage floor and shelf number.

10. A book information management system based on cloud computing, characterized in that: The system implements the cloud computing-based book information management method according to any one of claims 1 to 9, comprising: The root category number generating end generates multiple root category numbers based on the book's major category and the subcategories corresponding to the major category; The character conversion end obtains the characteristic values ​​corresponding to different books under different data types under each root category number; The benchmark interaction range acquisition terminal obtains the benchmark interaction range corresponding to each root category number; The book position label binding end obtains the position label corresponding to each book and the book feature shape vector corresponding to each book, and binds and stores them with the corresponding position label; The out-of-specification book determination terminal compares and analyzes the feature shape vector to be analyzed corresponding to the book to be stored with the corresponding reference interaction range to determine whether the book to be stored is an out-of-specification book; At the reference storage location acquisition end, for books to be stored that do not exceed the standard, the feature shape vector to be analyzed corresponding to the book to be stored is compared and analyzed with the book feature shape vectors of different books belonging to its corresponding root category number to obtain the reference storage location corresponding to the book to be stored.

Images