KR102665966B1 - Method and system for generating classification numbers using artificial intelligence to build book MARC DATA - Google Patents

Abstract

A method and system for generating classification numbers using artificial intelligence for building book list information are disclosed. A method of generating a classification number using artificial intelligence for building book list information according to one aspect of the present invention includes the steps of receiving book information about a target book; Determining a first key value through artificial intelligence analysis of the book name among the book information; Determining a second key value through artificial intelligence analysis of detailed book information; and generating a classification number for the target book using the first key value and the second key value.

Description

Method and system for generating classification numbers (KDC, DDC) using artificial intelligence to build book list information (MARC DATA) {Method and system for generating classification numbers using artificial intelligence to build book MARC DATA}

The present invention relates to a method and system for generating classification numbers using artificial intelligence for building book list information.

In order to manage a huge amount of books, systematic book classification is essential. In general, catalog information (MARC DATA) generated by classifying books is constructed according to certain rules. When constructing MARC DATA, classification numbers using the Korean Decimal Classification (KDC) and Dewey Decimal Classification (DDC) are used.

Conventionally, these classification numbers were manually created by people based on a certain manual. In this case, because the librarian's intuition is judged based on the manual, there is a possibility that the same subject and the same book may be assigned differently, which often results in errors in classification. In addition, because the books are sorted by looking at the manual, it takes a long time to sort only about 50 books a day. In addition, accurate classification may be difficult as it is difficult to understand the contents of the book due to the diversity of academic fields and languages.

Republic of Korea Patent No. 10-0991661 (DDC/KDC automatic classification system and method for books)

Therefore, the present invention was created to solve the above-mentioned problems, and is a classification number using artificial intelligence to build book list information (MARC DATA) that can be performed more accurately and easily by using artificial intelligence rather than manpower. (KDC, DDC) To provide a generation method and system.

In addition, the present invention is to provide a method and system for generating classification numbers using artificial intelligence for building book list information using the administrator's voice to minimize errors caused by artificial intelligence.

Other objects of the present invention will become clearer through the preferred embodiments described below.

According to one aspect of the present invention, determining a first key value through artificial intelligence analysis for the book name of the input target book; Acquiring detailed information using the book name of the target book and determining a second key value through the artificial intelligence analysis of the acquired detailed information; And a classification number generation method using artificial intelligence for building book list information, including the step of generating a classification number for the target book using the first key value and the second key value, and a program for performing the method. A recorded recording medium is provided.

Here, the detailed information is obtained from an external book database online.

Additionally, when determining the first key value or the second key value, the input voice is additionally analyzed and used together.

Additionally, when determining the first key value or the second key value, determining whether auxiliary information is needed; And only when it is determined that auxiliary information is needed, exposing the analyzed information to one or more managers and analyzing the voice input from the managers to generate auxiliary information.

Additionally, the method further includes updating the artificial intelligence using the auxiliary information.

In addition, the manager is identified through voice analysis of the voice, and the importance of the auxiliary information is determined according to expert information set for the identified manager.

Additionally, providing analysis information on the target book including the classification number to an administrator terminal; Receiving voice information input to the manager terminal; Recognizing auxiliary information about the target book by analyzing the voice information; and modifying the classification number by converting at least one of the first key value and the second key value by analyzing the auxiliary information.

In addition, providing the analysis information to the administrator terminal may include determining a specialized field corresponding to the target book; and determining one or more managers corresponding to the specialized field and providing the analysis information.

In addition, if the number of target books is more than the critical number and the number of times using voice-based auxiliary information is more than the critical ratio, after performing the classification number generation process for all target books, the target books are sequentially selected from the beginning. Re-perform the classification number creation process.

According to another aspect of the present invention, a storage unit for receiving and storing a book name for a target book; Based on information learned in advance, an artificial intelligence unit that determines a first key value by analyzing the book name of the input target book and determines a second key value by analyzing detailed information acquired using the book name of the target book; and a classification processing unit that generates a classification number for the target book using the first key value and the second key value. A classification number generation system using artificial intelligence for building book list information is provided.

Here, it further includes a voice recognition unit for analyzing input or received voice information, wherein the artificial intelligence unit further analyzes the voice recognition information recognized by the voice recognition unit and uses it to determine the first key value or the second key value. do.

In addition, if the number of target books is more than the critical number and the number of times using voice-based auxiliary information is more than the critical ratio, after performing the classification number generation process for all target books, the target books are sequentially selected from the beginning. It further includes a control unit that re-performs the classification number generation process.

According to the present invention, it is possible to generate classification numbers using artificial intelligence for building book list information more accurately and easily by using artificial intelligence rather than manpower.

In addition, according to the present invention, by assisting artificial intelligence with the manager's voice, errors caused by artificial intelligence can be minimized and artificial intelligence can be advanced in real time.

1 is a configuration diagram schematically showing the entire system for generating classification numbers using artificial intelligence for building book list information according to an embodiment of the present invention.
Figure 2 is a block diagram showing the configuration of a classification system that generates a classification number using artificial intelligence according to an embodiment of the present invention.
Figure 3 is a flow chart schematically showing the process of generating a classification number using artificial intelligence for building book list information according to an embodiment of the present invention.
Figures 4 and 5 are flowcharts showing the process of generating a classification number using voice according to each embodiment of the present invention.
Figure 6 is a flowchart showing a process of identifying a manager by voice and utilizing auxiliary information according to an embodiment of the present invention.
Figure 7 is a flowchart showing a process of re-performing book classification to increase accuracy according to an embodiment of the present invention.
Figure 8 is a flowchart showing a specific process of generating a classification number using artificial intelligence and voice according to an embodiment of the present invention.

Since the present invention can make various changes and have various embodiments, specific embodiments will be illustrated in the drawings and described in detail in the detailed description. However, this is not intended to limit the present invention to specific embodiments, and should be understood to include all changes, equivalents, and substitutes included in the spirit and technical scope of the present invention.

When a component is said to be "connected" or "connected" to another component, it is understood that it may be directly connected to or connected to the other component, but that other components may exist in between. It should be. On the other hand, when it is mentioned that a component is “directly connected” or “directly connected” to another component, it should be understood that there are no other components in between.

Terms such as first, second, etc. may be used to describe various components, but the components should not be limited by the terms. The above terms are used only for the purpose of distinguishing one component from another. For example, terms such as first threshold value and second threshold value, which will be described later, may be pre-designated as threshold values that are substantially different or partially the same, but may cause confusion when expressed with the same word threshold. Since there is room, for convenience of classification, terms such as first and second will be used together.

The terms used in this specification are merely used to describe specific embodiments and are not intended to limit the invention. Singular expressions include plural expressions unless the context clearly dictates otherwise. In this specification, terms such as “comprise” or “have” are intended to designate the presence of features, numbers, steps, operations, components, parts, or combinations thereof described in the specification, but are not intended to indicate the presence of one or more other features. It should be understood that this does not exclude in advance the possibility of the existence or addition of elements, numbers, steps, operations, components, parts, or combinations thereof.

In addition, the components of the embodiments described with reference to each drawing are not limited to the corresponding embodiments, and may be implemented to be included in other embodiments within the scope of maintaining the technical spirit of the present invention, and may also be included in separate embodiments. Even if the description is omitted, it is natural that a plurality of embodiments may be re-implemented as a single integrated embodiment.

In addition, when describing with reference to the accompanying drawings, identical or related reference numbers will be assigned to identical or related elements regardless of the drawing symbols, and overlapping descriptions thereof will be omitted. In describing the present invention, if it is determined that a detailed description of related known technologies may unnecessarily obscure the gist of the present invention, the detailed description will be omitted.

Figure 1 is a configuration diagram schematically showing the entire system for generating classification numbers using artificial intelligence for building book list information according to an embodiment of the present invention.

Referring to Figure 1, the entire system according to this embodiment includes a classification system 30 and one or more book DBs (50-1, ??, 50-m, hereinafter collectively referred to as 50), but the classification system 30 It may further include one or more manager terminals (10-1, ..., 10-n, hereinafter collectively referred to as 10) for managing.

The classification system 30 operates artificial intelligence and classifies books using artificial intelligence, and artificial intelligence uses a communication network such as the Internet network to use an external book database (50, for example, a database operated at a specific bookstore site). etc.) and use it to classify books.

In addition, the administrator can provide related information for auxiliary functions for stable operation when training the artificial intelligence of the classification system 30 or performing the classification function of books. For example, the manager may use an input means supported by the classification system 30 or use the manager terminal 10 to provide related information for book classification to the classification system 30 by voice.

Figure 2 is a block diagram showing the configuration of a classification system 30 that generates a classification number using artificial intelligence according to an embodiment of the present invention.

Referring to Figure 2, the classification system 30 includes an input unit 210, a communication unit 220, an output unit 230, a storage unit 240, and a control unit 250, and the control unit 250 is an artificial intelligence unit. (251), and may include a classification processing unit (252). It will be apparent to those skilled in the art that each component part 251 and 252 of the control unit 250 does not necessarily need to be implemented in hardware, but can be implemented in software like an application program.

The input unit 210 is an input means for receiving basic information (eg, book name, etc.) about a book to be classified (hereinafter referred to as a target book). According to one example, an administrator can input book names for multiple target books in a file (for example, an Excel file, etc.).

In addition, as described above, the input unit 210 further includes a means for receiving voice information from the manager (for example, a microphone as a voice input means, etc.). This will be explained in more detail later.

The communication unit 220 is a communication means for communicating with the book DB 50 and the administrator terminal 10, and since this will be obvious to those skilled in the art, further detailed description will be omitted. According to one example, the classification system 30 uses the communication unit 220, without the input unit 210, to acquire basic information and voice information of the target book from the administrator only through a communication network (for example, an internal network or an Internet network, etc.). It may be possible.

The output unit 230 is a means for outputting the generated classification number and may include, for example, a display. Additionally, notification information for the manager can be output through the output unit 230. For example, notification information due to an error in generating a classification number, notification information for requesting additional auxiliary information for classification, etc. may be output.

The storage unit 240 is a means for storing the book name of the acquired target book, and back data for performing a book classification function using artificial intelligence may be stored in the storage unit 240.

The control unit 250 performs the overall control function of each component.

In particular, the control unit 250 performs a book classification function using basic information such as the title of the target book. The artificial intelligence unit 251 of the control unit 250 classifies the input target book based on information learned in advance. The first key value is determined by analyzing the book name, and the second key value is determined by analyzing detailed information obtained using the book name of the target book. Then, the classification processing unit 252 of the control unit 250 generates a classification number for the target book using the first key value and the second key value. In this embodiment, the subjects of determining the key value and generating the classification number using the key value are different, but the artificial intelligence unit may perform both key value generation and classification number generation. Hereinafter, for convenience of explanation, the artificial intelligence unit generates both the key value and the classification number. Let's focus on explaining what to do.

In order to easily manage a vast amount of books, the classification system 30 classifies books and assigns classification numbers accordingly. Classification of books can be done based on various criteria, such as by subject, author, or country.

The artificial intelligence operated in the classification system 30 classifies books based on content learned using deep learning techniques, etc. According to one example, books can be classified using the following criteria.

- Identify the topic of the material from the signature, foreword, abstract, table of contents, and author’s field of study.

- Classify the data according to the discipline and then categorize it into format (e.g. Introduction to Biology - 1) Biology 2) Introduction)

- Equivalent multiple topics are classified as preceding topics in the classification table (e.g., Management and Economic Research - Economics, English Literature - English Literature)

- Correlated topics are classified into affected topics

- When dealing with two topics, classify them into a more complete topic

- When dealing with 3 or more topics, it is classified as a higher level field of study.

- Anything that can be subdivided by topic or geography is prioritized by topic.

- Biographical records are classified according to the era to which the person belongs if there is no prior classification in the subject's historical field (occupation, subject field).

-Two or more literary works are classified in the following order: DRAMA-POETTY-FICTION-ESSAY-SPEECHES-LETTERS-MISCELLANY

- Language is primarily a classification used as a heading.

- When two heading languages are used, they are classified as languages with less use.

- Language is classified in the following order: academic-language-language.

- Literature is classified according to the language used in the original work.

The artificial intelligence unit 251 generates a key value for the target book based on these preset and learned conditions, and uses the key value to generate a unique classification number.

According to the classification system 30 of this embodiment, it is possible to save time and provide efficiency in human resource management by automatically assigning classification numbers by artificial intelligence, and also provide uniformity by automatically assigning classification numbers, thereby ensuring uniformity of mark data for each institution. can be maintained.

Hereinafter, the classification number generation method performed in the classification system 30 will be described in more detail.

Figure 3 is a flow chart schematically showing the process of generating a classification number using artificial intelligence for building book list information according to an embodiment of the present invention.

Referring to Figure 3, book name information for the target book is acquired (S10).

As described above, there may be a plurality of target books, and the book name information may be entered one by one, but the administrator may input the book name of each target book in the form of a file such as an Excel file. Alternatively, you can enter the book name for each target book using voice.

The classification system 30 determines the first key value through artificial intelligence analysis of the book name of the acquired target book (S20). For example, the first key value (e.g., 813) is determined through classification into mainstream, lecture, and syllabus by analyzing the book name.

In addition, the classification system 30 searches and explores the external book DB 50 using the book name of the target book to provide detailed information (subtitle, table of contents, review, advertisement, author profile, index, opinion, summary, introduction, release, etc.) , epigraph, etc.) and determine the second key value through artificial intelligence analysis of the detailed information (S30). For example, the second key value [9] is determined through analysis of detailed information.

The classification system 30 generates a classification number (for example, 813.9) for the target book using the determined first and second key values (S40). In this embodiment, the method of generating a classification number by simply combining the first key value and the second key value is used as an example, but the two key values are used as the sum (or multiplication or division value) of the first key value and the second key value. You can also create a classification number.

According to this embodiment, if the administrator simply inputs the book name, artificial intelligence can automatically generate a classification number using the book name and the detailed information acquired accordingly.

According to another example, managers can provide auxiliary information for more accurate classification of artificial intelligence.

Figures 4 and 5 are flowcharts showing the process of generating a classification number using voice according to each embodiment of the present invention.

First, referring to FIG. 4, the classification system 30 generates a classification number for a target book and provides it to the manager along with analysis information (S410). For example, the book name, important information used in the analysis (table of contents, author name, etc.), and the generated classification number are output on a display provided for the administrator to check or transmitted in real time to the administrator terminal 10.

Afterwards, it is determined whether a voice is input from the manager (or received through a communication network) (S420), and if no voice is input after a certain period of time (e.g., 1 minute, etc.), the generated classification number is stored (S430).

In contrast, when voice is received, the voice information is analyzed (for example, converted to text using voice recognition technology and then analyzed) to recognize auxiliary information (S440). For example, if the administrator determines that there is a problem with the generation of classification numbers by artificial intelligence, additional information about the target book is input by voice.

When the auxiliary information according to the manager's voice is recognized, the auxiliary information is analyzed, the first key value and/or the second key value are converted, and the classification number is modified and stored using the converted key value (S450).

Afterwards, since the classification number (and key value) has been modified by the administrator's auxiliary information, the artificial intelligence performs an update through learning on its own so that the content is reflected in the classification process next time (S460).

This embodiment is an example of inputting a voice after generating a classification number, and according to another example, the voice from the administrator can also be used when determining each key value (first key value or second key value). To this end, the classification system 30 provides an interface that allows the administrator to input voice as additional information when generating each key value.

Referring to FIG. 5 according to another embodiment, it is determined whether analysis of the book name for the first key value or acquisition or analysis of detailed information for the second key value fails, or auxiliary information is needed due to insufficient information (S510 ).

According to the judgment result, the first or second key value is determined (S520), or if the analysis fails or auxiliary information is determined to be necessary as described above, notification information is provided to the administrator (S530). Notification information can be provided to the manager terminal 10 using the provided output means or through a communication network.

Thereafter, the first key value and/or the second key value are determined using auxiliary information according to the voice information acquired from the manager (S540).

That is, in this embodiment, only when it is determined that auxiliary information is necessary, the analyzed information is exposed to one or more managers and the auxiliary information is generated by analyzing the voice input from the manager.

Figure 6 is a flowchart showing a process of identifying a manager by voice and utilizing auxiliary information according to an embodiment of the present invention.

Referring to FIG. 6, the classification system 30 analyzes the voice of the input voice (S610) and identifies the manager corresponding to the voice (S620).

The importance of the voice information is determined according to the expert information set in the identified manager and reflected in determining the key value of the target book (S630).

For example, if the target book is in the science field, the importance is set to 100 for managers whose field of expertise is science, the importance is set to 90 if their field of expertise is mathematics, and the importance is set to 80 if their field of expertise is novels, and auxiliary information is reflected through voice. The ratio is applied differently depending on importance.

According to this embodiment, information from the manager is used to increase the accuracy of classification, but the occurrence of classification errors caused by indiscriminate application of information by the manager can also be reduced.

Likewise, when providing analysis information including the generated classification number to the manager as shown in Figure 4, the specialized field corresponding to the target book is recognized, and one or more managers corresponding to the specialized field are determined to provide the analysis information. It may be possible.

Generally, book classification work is performed on a large number of books. Therefore, the classification method may be advanced through self-learning as the artificial intelligence department classifies each target book. Using this point, a more accurate book classification process can be derived.

Figure 7 is a flowchart showing a process of re-performing book classification to increase accuracy according to an embodiment of the present invention.

Referring to Figure 7, when the generation of classification numbers for a plurality of target books is completed (S710), it is determined whether the number of times the voice information has been used is more than the threshold ratio (S720). For example, when performing a classification process for 10,000 target books, if the number of times auxiliary information was used by the manager's voice was 15, the ratio was 0.15%, which exceeds the critical ratio of 0.1%.

Here, the critical ratio may vary depending on the number of target books. For example, as the number of target books increases, the critical ratio may become somewhat lower. In addition, according to one example, comparison with the critical ratio can only be performed when the number of target books is more than the critical number (for example, 100, etc.), which means that re-performance of the classification process can only be done for classification of books exceeding the critical number. Because it can have meaning.

If the use of voice information exceeds the critical ratio, the classification of the target books is re-performed from the beginning using updated artificial intelligence (S730).

On the other hand, if the use of voice information is below the critical ratio, the classification process is re-performed only for the target books that use voice information (S740).

Figure 8 is a flowchart showing a specific process of generating a classification number using artificial intelligence and voice according to an embodiment of the present invention.

Referring to Figure 8, when the book name is entered as an Excel file, major classification of topics, etc. is performed using the signature (book name), and details are analyzed through search using the book DB 50 and voice recognition of the administrator. An example of generating a classification number is shown.

The method of generating a classification number using artificial intelligence for building book list information according to the present invention described above can be implemented as a computer-readable code on a computer-readable recording medium. Computer-readable recording media include all types of recording media storing data that can be deciphered by a computer system. For example, there may be Read Only Memory (ROM), Random Access Memory (RAM), magnetic tape, magnetic disk, flash memory, optical data storage device, etc. Additionally, computer-readable recording media can be distributed to computer systems connected through a computer communication network, and stored and executed as code that can be read in a distributed manner.

In addition, although the present invention has been described above with reference to preferred embodiments, those skilled in the art will understand the present invention without departing from the spirit and scope of the present invention as set forth in the claims below. You will understand that it can be modified and changed in various ways.

10: Administrator terminal
30: Classification system
50: Book DB

Claims (13)

In the classification number generation method performed by the classification system,
Determining a first key value through artificial intelligence analysis for the book name of the input target book;
Acquiring detailed information using the book name of the target book and determining a second key value through the artificial intelligence analysis of the acquired detailed information; and
A classification number generation method using artificial intelligence for building book list information, comprising the step of generating a classification number for the target book using the first key value and the second key value.
In claim 1,
A classification number generation method using artificial intelligence to build book list information, which acquires the above detailed information from an external book database online.
In claim 1,
When determining the first key value or the second key value, a classification number generation method using artificial intelligence for building book list information is used by additionally analyzing the input voice.
In claim 3,
When determining the first key value or the second key value,
Determining whether auxiliary information is needed; and
Classification using artificial intelligence to build book list information, including the step of exposing the analyzed information to one or more managers and generating auxiliary information by analyzing the voice input from the manager only when it is determined that auxiliary information is needed. How to create a number.
In claim 4,
A classification number generation method using artificial intelligence for building book list information, further comprising updating the artificial intelligence using the auxiliary information.
In claim 4,
A classification number generation method using artificial intelligence for building book list information, which identifies the administrator through voice analysis of the voice and determines the importance of the auxiliary information according to expert information set for the identified administrator.
In claim 1,
Providing analysis information on the target book including the classification number to an administrator terminal;
Receiving voice information input to the manager terminal;
Recognizing auxiliary information about the target book by analyzing the voice information; and
Method for generating a classification number using artificial intelligence for building book list information, further comprising modifying the classification number by converting at least one of the first key value and the second key value by analyzing the auxiliary information. .
In claim 7,
The step of providing the analysis information to the administrator terminal is,
Determining a specialized field corresponding to the target book; and
A classification number generation method using artificial intelligence for building book list information, including the step of determining one or more managers corresponding to the specialized field and providing the analysis information.
In claim 3,
If the number of target books is more than the threshold number and the number of times using auxiliary information by voice is more than the threshold ratio,
A classification number generation method using artificial intelligence to build book list information, which performs the classification number generation process for all target books and then re-performs the classification number generation process for target books in order from the beginning.
A recording medium containing instructions executable by a computer, such as an application or program module executed by a computer to perform the method of claim 1.
A storage unit for receiving and storing the book name for the target book;
Based on information learned in advance, an artificial intelligence unit that determines a first key value by analyzing the book name of the input target book and determines a second key value by analyzing detailed information acquired using the book name of the target book; and
A classification number generation system using artificial intelligence for building book list information, including a classification processing unit that generates a classification number for the target book using the first key value and the second key value.
In claim 11,
It further includes a voice recognition unit for analyzing input or received voice information,
The artificial intelligence unit further analyzes the voice recognition information recognized by the voice recognition unit and uses it to determine the first key value or the second key value. A classification number generation system using artificial intelligence for building book list information.
In claim 12,
If the number of target books is more than the threshold number and the number of times using auxiliary information by voice is more than the threshold ratio,
After performing the classification number generation process for all target books, the classification number generation system using artificial intelligence for building book list information further includes a control unit that re-performs the classification number generation process for target books in order from the beginning. .