A digital library recommendation method and system based on knowledge hybrid recommendation

By building a book and borrower information database, using text mining and neural network technology, a system based on mixed knowledge recommendation is realized, the problem of massive book information retrieval is solved, the search efficiency and intelligence is improved, and books are carried out through terminal processing devices Classification and disinfection protect the books.

CN114996583BActive Publication Date: 2024-11-15JIANGXI UNIV OF TECH
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202210714698.8
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-06-23
Publication Date
2024-11-15
Estimated Expiration
2042-06-23

AI Technical Summary

Technical Problem

The existing technology is difficult to provide users with relevant content retrieval in a massive amount of book information efficiently, quickly and accurately, resulting in low intelligence in book management and it is difficult for users to quickly find the information they need.

Method used

By building a book database and borrower information database, using text mining and potential semantic analysis technology, combined with neural network methods, a borrower needs theme database and book performance feature database are established, a system based on knowledge mixed recommendations is realized, and a terminal processing device is used to carry out books Classification and disinfection.

Benefits of technology

It improves the efficiency and accuracy of book retrieval, optimizes recommendation strategies, enhances the intelligence of book management, and protects books through mechanical processing and disinfection technology.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114996583B_ABST
    Figure CN114996583B_ABST
Patent Text Reader

Abstract

A digital library recommendation method based on knowledge hybrid recommendation includes: a book database and a borrower information database, wherein: by inputting information on library books, book effectiveness data is obtained, by interacting with borrowers' school major information, the initial demand theme of the borrower in the initial state is obtained, and then the borrower's initial demand theme and the book effectiveness data are jointly entered into the library preference library. The invention constructs library effectiveness features through a large amount of public data and big data collection, analysis and mining technology, and constructs a subject library of borrowers' needs based on a subject model; then, through a neural network method, the data of libraries and borrowers in history are trained, the research theme and the library database are mapped to their potential association representations, and a borrower subject cooperation tendency model is established.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the field of digital library methods and systems, and in particular relates to a digital library recommendation method and system based on knowledge hybrid recommendation. Background Art

[0002] With the rapid development of the global information industry, the application of digital technology has become increasingly popular, and digital products have entered various fields. The use of computer technology in libraries has effectively improved the management level of books. However, with the development of the economy and the progress of society, people's demand for and accumulation of knowledge has continued to increase, the collection of books in libraries has continued to increase, and information has grown rapidly. Therefore, higher requirements have been put forward for the management of libraries. Not only does it need to further improve the level of book management, but more importantly, it is necessary to achieve the effective use of book information.

[0003] At present, most of the research on library book management focuses on management, and there are few studies on intelligent management that provides information analysis and decision support based on user needs. In addition, in the research and development of digital book management, there are still huge difficulties and obstacles, mainly in: how to effectively store, manage and utilize such a large amount of information, how to fully explore the information behind the information and its potential value. With the rapid expansion of the Internet and the explosive growth of information, people have found that although there are more and more data and information, knowledge, that is, orderly, effective and valuable information, is becoming less and less. Therefore, how to find the book content you need in many books, and at the same time be able to efficiently, quickly and accurately retrieve the relevant content, quickly obtain the basic information of the relevant books, and improve the degree of intelligent book management has become a problem that people pay close attention to.

[0004] With the development of big data technology, it is possible to establish efficient communication channels between the library system and borrowers. However, the development of big data is also accompanied by the disadvantages of "information explosion" and "information overload". It becomes extremely difficult for users who are covered by information to quickly find the information they really need in the massive amount of information. Therefore, how to build an efficient platform for information transmission and sharing between libraries and borrowers based on Internet big data technology, how to help borrowers choose books with relevant content, so as to better maximize the value of library book collections and provide solid guarantees for borrowers are the key directions of current research. Summary of the invention

[0005] The above-mentioned invention object of the present invention is achieved through the following technical solutions:

[0006] A digital library recommendation method based on knowledge hybrid recommendation includes: a book database and a borrower information database, wherein: by inputting information of library books, book performance data is obtained, by interacting with borrowers' school major information, the initial demand theme of the borrower in the initial state is obtained, and then the borrower's initial demand theme and the book performance data are entered into the library preference library together, and by searching the borrower's keywords in the book preference library, keyword feedback under the current preference theme is obtained, and the keyword data is fed back to the borrower's book preference library to obtain a new preference theme, and at the same time, the keyword search results are matched and sorted to obtain a list of related recommended books.

[0007] Preferably, the book performance data includes book field differentiation, book borrowing times, book content evaluation, and book content keyword records. The book performance data is obtained through public data and crawler data. The book introduction is analyzed by text mining technology to obtain high-frequency keywords, thereby obtaining a basic library of book content themes. The document-term matrix of the book introduction and the specific content of the book is decomposed into independent document-topic matrices and topic-term matrices using latent semantic analysis. The term frequency-inverse text frequency index is used to assign corresponding weights to term j in document i. The formula can be expressed as follows:

[0008]

[0009] Where: w represents the term frequency-inverse text frequency index score, tf represents the term that appears in the document, N represents all texts, and df represents the document containing the keyword.

[0010] Preferably, the borrower's initial demand theme is obtained through the information of relevant majors in school, as well as the preference for joining clubs and campus internal activities in school.

[0011] Preferably, the system background includes a book database; a mobile terminal, the mobile terminal includes a query module, an entry module, a borrowing module, and a book returning module, the query module is connected to the book database, and is used to query the books required by the borrower, and make a certain selection relevance sorting; the entry module is used to increase the content of the book database, and obtain book-related content through public data and crawler data; the borrowing module is used for borrowing operations, and is recorded in the borrower's personal information, and at the same time, the borrower's personal preference theme is changed according to the content of the borrowed book.

[0012] Preferably, the terminal processing device includes a terminal processing device and an input, sorting and classification device. The terminal processing device includes a base, a plane seat is arranged on the upper end of the base, a card reader, an RFID reading block and an information display screen are arranged on the plane seat, a circuit control board is also arranged inside the base, the circuit control board is connected and controlled with the card reader, the RFID reading block and the information display screen, and the circuit control board is also connected to the input, sorting and classification device.

[0013] Preferably, the data entry, sorting and classification device includes a base, the lower part of the base is evenly provided with collection bins through baffles, the middle part of the base is provided with a working room, a driving motor and a control circuit board are installed inside the working room, the driving motor is connected to a rotating disk, a chuck is provided on the rotating disk, the chuck is connected to the data entry device, the data entry device can be driven to rotate with the driving motor, a dustproof cloth is provided between the data entry device and the base, and low-concentration ozone is also provided in the collection bin.

[0014] Preferably, the data entry device includes an upper seat, the upper seat includes an upper seat one and an upper seat two, the upper seat one and the upper seat two are completely symmetrically arranged, a longitudinal fixing rod is arranged on the upper seat one, and a transverse fixing rod is arranged below, a lower seat is arranged below the upper seat, the lower seat includes a lower seat one and a lower seat two, a transverse fixing rod is arranged on the lower seat one, and a longitudinal fixing rod is arranged below the lower seat, a lower end of the lower seat is connected to the chuck, a gear bar is arranged on the left side of the chuck, a rotating shaft is arranged on the left side of the lower seat one, the rotating shaft matches the gear bar, the rotating shaft is connected to a micro motor, the micro motor drives the rotating shaft to rotate, a push block is also arranged on the rotating shaft, the rotating shaft drives the push block to rotate, and an ultraviolet light emitter is arranged between the upper seat and the lower seat.

[0015] In summary, the present invention includes at least one of the following beneficial technical effects:

[0016] 1. The invention constructs library performance characteristics through a large amount of public data and big data collection, analysis and mining technology, and at the same time builds a subject library of borrowers' needs based on the LDA subject model; then, through the neural network method, the historical data of libraries and borrowers are trained, the research topics and library databases are mapped to their potential association representations, and a borrower subject cooperation tendency model is established; finally, the TOP series of recommendations are given by combining search recommendations and subject similarity calculations, and then the recommendation strategy is continuously optimized based on user interaction feedback.

[0017] 2. By setting up a terminal processing device, the classification of books can be achieved by mechanical means, so that the librarian can limit the storage location of books to a smaller range, which can improve the work efficiency of the librarian. At the same time, ultraviolet light disinfection and ozone disinfection of books can play a certain role in the protection of books. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 It is a schematic flow chart of the method of the present invention;

[0019] Figure 2 It is a schematic diagram of the overall system of the present invention;

[0020] Figure 3 is a schematic diagram of a terminal processing device of the present invention;

[0021] Figure 4 is a cross-sectional schematic diagram of the data entry device of the present invention;

[0022] Figure 5 is an internal schematic diagram of the input device of the present invention;

[0023] Figure 6 It is a schematic diagram of the upper seat of the data entry device of the present invention;

[0024] Figure 7 It is a schematic diagram of the lower seat of the data entry device of the present invention;

[0025] Figure 8 It is an overall schematic diagram of the upper seat and the lower seat of the input device of the present invention.

[0026] In the figure: 1 terminal processing device, 101 base, 103 plane seat, 104 card reader, 105 RFID reading block, 106 information display screen, 107 circuit control board, 2 data entry sorting device, 201 base, 202 baffle, 203 collection bin, 204 studio, 205 drive motor, 206 rotating disk, 207 chuck, 3 data entry device, 301 upper seat 1, 302 upper seat 2, 303 longitudinal fixing rod, 304 transverse fixing rod, 305 lower seat 1, 306 lower seat 2, 307 rotating shaft, 308 push block. DETAILED DESCRIPTION

[0027] The above-mentioned inventive object of the present invention is achieved through the following technical scheme: a digital library recommendation method based on knowledge hybrid recommendation, including: a book database, a borrower information database, wherein: by entering the information of the library books, the book effectiveness data is obtained, by interacting with the borrower's school major information, the initial demand theme of the borrower in the initial state is obtained, and then the borrower's initial demand theme and the book effectiveness data are entered into the library preference library together, and through the borrower's keyword search in the book preference library, the keyword feedback under the current preference theme is obtained, and the keyword data is fed back to the borrower's book preference library to obtain a new preference theme, and at the same time, the keyword search results are matched and sorted to obtain a list of related recommended books.

[0028] Specifically, the book performance data includes book field differentiation, book borrowing times, book content evaluation, and book content keyword records. The book performance data is obtained through public data and crawler data. The book introduction is analyzed through text mining technology to obtain high-frequency keywords, thereby obtaining a basic library of book content themes. Using latent semantic analysis, the document-term matrix of the book introduction and the specific content of the book is decomposed into independent document-topic matrices and topic-term matrices. The term frequency-inverse text frequency index is used to assign corresponding weights to term j in document i. The formula can be expressed as follows:

[0029]

[0030] Where: w represents the term frequency-inverse text frequency index score, tf represents the term that appears in the document, N represents all texts, and df represents the document containing the keyword.

[0031] Specifically, the borrower's initial demand theme is derived through the information of relevant majors in school, as well as the preference for joining clubs and campus internal activities.

[0032] Specifically, the system background includes a book database; a mobile terminal, which includes a query module, an input module, a borrowing module, and a book returning module. The query module is connected to the book database, and is used to query the books required by the borrowers, and make certain selection and relevance sorting; the input module is used to increase the content of the book database, and obtain book-related content through public data and crawler data; the borrowing module is used for borrowing operations, and is recorded in the borrower's personal information, and at the same time, the borrower's personal preference theme is changed according to the content of the borrowed book.

[0033] Specifically, the terminal processing device includes a terminal processing device 1 and an input, sorting and classification device 2. The terminal processing device includes a base 101, a plane seat 103 is arranged on the upper end of the base 101, a card reader 104, an RFID reading block 105, and an information display screen 106 are arranged on the plane seat 103, and a circuit control board is also arranged inside the base 101. The circuit control board is connected and controlled with the card reader 104, the RFID reading block 105, and the information display screen 106, and the circuit control board 107 is also connected to the input, sorting and classification device 2.

[0034] Specifically, the data entry, sorting and classification device 2 includes a base 201, a collection bin 203 is evenly arranged at the lower part of the base 201 through a baffle 202, a working room 204 is arranged in the middle part of the base 201, a driving motor 205 and a control circuit board 206 are installed inside the working room 204, the driving motor 205 is connected to the rotating disk 206, a chuck 207 is arranged on the rotating disk 206, the chuck 207 is connected to the data entry device 3, the data entry device 3 can be driven to rotate with the driving motor 205, a dustproof cloth is arranged between the data entry device 3 and the base 201, and low-concentration ozone is also arranged in the collection bin 203.

[0035] Specifically, the input device 3 includes an upper seat, the upper seat includes an upper seat 1 301 and an upper seat 2 302, the upper seat 1 301 and the upper seat 2 302 are completely symmetrically arranged, the upper seat 1 301 is provided with a longitudinal fixing rod 303, and a transverse fixing rod 304 is arranged below, a lower seat is arranged below the upper seat, the lower seat includes a lower seat 1 305 and a lower seat 2 306, the lower seat 1 305 is provided with a transverse fixing rod 304, and the lower seat 1 305 is provided with a longitudinal fixing rod 3 03, the lower end of the lower seat 305 is connected to the chuck 207, the chuck 207 on the left side is provided with a gear bar, the left side of the lower seat 305 is provided with a rotating shaft 307, the rotating shaft 307 matches the gear bar, the rotating shaft 307 is connected with a micro motor, the micro motor drives the rotating shaft 307 to rotate, and a push block 308 is also provided on the rotating shaft 307, the rotating shaft 307 drives the push block 308 to rotate, and an ultraviolet light emitter is provided between the upper seat and the lower seat.

[0036] Working principle: When the book is affixed with RFID tags and entered into the library system, the upper seat 1 and the upper seat 2 are opened to each other, and the entered book is placed between the upper seat and the lower seat. At this time, the upper seat 1 and the upper seat 2 are closed, and the drive motor rotates to make the gap of the lower seat align with the corresponding collection bin of the book. At the same time, the ultraviolet light disinfects the book. At this time, the micro motor starts, driving the rotating shaft and the gear bar to move, so that the lower seat 1 and the lower seat 2 are opened and the pushing movement is driven. At this time, the push block pushes the book out of the gap and makes it fall into the corresponding collection bin. At the same time, because ozone is higher than air, ozone gathers at the bottom of the collection bin and continues to disinfect the book. After that, books of different types or different storage areas can be transported to different areas according to the different collection bins pushed into them, reducing the workload of the staff.

[0037] Finally, it should be noted that the above is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, it is still possible for those skilled in the art to modify the technical solutions described in the aforementioned embodiments or to make equivalent substitutions for some of the technical features therein. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A digital library recommendation device based on knowledge hybrid recommendation, Features: The invention comprises a terminal processing device (1) and an inputting, sorting and classification device (2), wherein the terminal processing device comprises a base (101), a plane seat (103) is arranged on the upper end of the base (101), a card reader (104), an RFID reading block (105) and an information display screen (106) are arranged on the plane seat (103), a circuit control board is also arranged inside the base (101), the circuit control board is connected and controlled with the card reader (104), the RFID reading block (105) and the information display screen (106), and the circuit control board (107) is also connected to the inputting, sorting and classification device (2); The data entry, sorting and classification device (2) comprises a base (201), a collecting bin (203) is evenly arranged at the bottom of the base (201) via a baffle (202), a working chamber (204) is arranged in the middle of the base (201), a driving motor (205) and a control circuit board (206) are installed inside the working chamber (204), the driving motor (205) is connected to a rotating disk (206), a chuck (207) is arranged on the rotating disk (206), the chuck (207) is connected to the data entry device (3), the data entry device (3) can be driven to rotate with the driving motor (205), a dustproof cloth is arranged between the data entry device (3) and the base (201), and low-concentration ozone is also arranged in the collecting chamber (203); The input device (3) includes an upper seat, the upper seat includes an upper seat 1 (301) and an upper seat 2 (302), the upper seat 1 (301) and the upper seat 2 (302) are completely symmetrically arranged, the upper seat 1 (301) is provided with a longitudinal fixing rod (303), and a transverse fixing rod (304) is arranged below, a lower seat is arranged below the upper seat, the lower seat includes a lower seat 1 (305) and a lower seat 2 (306), the lower seat 1 (305) is provided with a transverse fixing rod (304), and the lower seat 1 (305) is provided with a longitudinal fixing rod (30 3), the lower end of the lower seat (305) is connected to the chuck (207), the chuck (207) is provided with a gear bar on the left side, the left side of the lower seat (305) is provided with a rotating shaft (307), the rotating shaft (307) matches the gear bar, the rotating shaft (307) is connected to a micro motor, the micro motor drives the rotating shaft (307) to rotate, the rotating shaft (307) is also provided with a push block (308), the rotating shaft (307) drives the push block (308) to rotate, and an ultraviolet light emitter is provided between the upper seat and the lower seat.