KR102232957B1 - Library member customized book recommendation kiosk device and system using emotion recognition - Google Patents

Abstract

The present invention relates to a library member-customized book recommendation kiosk device which recognizes emotions from library members and reviews and utilizes the same, and a system therefor, and more specifically, to a library member-customized book recommendation kiosk device using emotion recognition, which extracts emotion-related words described in the reviews of books and extracts emotions from book information database weighting the degree of emotion for each emotion, library member information, and expressions of the library members recognized at the kiosk, and a system therefor.

Description

Library member customized book recommendation kiosk device and system using emotion recognition}

The present invention relates to a library member-customized book recommendation kiosk device and system that recognizes emotions from library members and reviews, and utilizes them, and in more detail, extracts words related to emotions described in book reviews, and increases the level of emotion for each emotion. About a library member customized book recommendation kiosk device and system using emotion recognition that can provide customized books using emotions by extracting emotions from the library member's facial expressions recognized in a book information database and library member information and kiosks. will be.

In general, there are a large number of books in the library, and since it has the advantage that ordinary citizens can easily access and rent books for free or inexpensively, it has a large number of members.

These library members have different tastes and interests, so the types of books they want to read may be different for each user. However, since the book information and recommendation services provided by conventional library related companies are limited to providing evaluations for specific book contents written by renowned people or other writers, or simply providing a storyline, the position of library members who wish to read books There is a problem in that it is difficult to easily determine whether the book is suitable for you.

In addition, in order to determine the suitability between the book and the member, there are a large number of reviews about the book, and because the feelings of each user are different, it is difficult to find a review that is suitable for the person, and it is difficult to check all the reviews. There is discomfort.

Republic of Korea Patent Publication No. 10-2017-0087423 "Book recommendation method and system for personalized book recommendation" Korean Patent Application Publication No. 10-2020-0057209 "Method and device for recommending customized books using K-means Clustering"

The present invention is to solve the above-described problem, by recognizing the emotions of books and library members, and by providing recommended books using them, it is possible to improve the satisfaction of library members by providing them more tailored to members than the existing list of recommended books. Its purpose is to provide a library member customized book recommendation kiosk device and system using emotion recognition.

In addition, the weight of each word including emotion is determined differently, and the emotion level of each book can be classified according to the emotion, so that the weight can be weighted to correspond to the emotion type of the library member. Its purpose is to provide a library member-customized book recommendation kiosk device and system that utilizes emotion recognition in which the list of recommended books can change.

The problems to be solved by the present invention are not limited to the problems mentioned above, and other problems that are not mentioned will be clearly understood by those skilled in the art from the following description.

In order to solve the above-described problem, in the library member customized book recommendation kiosk system using this by recognizing emotions from library members and reviews according to the present invention,

Stores an emotion word set in which emotion classification and emotion level for each word are built, and generates book information including emotion classification and emotion level for each book by comparing the text data for each book with the emotion word included in the emotion word set, and Book information management server to store; A member information database storing library member information for each library member; A kiosk that photographs the facial expressions of library members and provides a list of recommended books for each library member; And a recommended book providing server that interlocks with the book information management server, the member information database, and the kiosk to generate a list of recommended books for each library member.

In addition, the book information management server includes: an emotional word set database in which the emotional word set consisting of emotional words having an emotional classification and an emotional degree is pre-stored; A text data generation unit that collects review information for each book and generates the text data for each book; An emotion information generation unit for extracting the emotion words included in the text data for each book, classifying the emotion classification and the emotion level for each emotion word for each book, and generating emotion information for each book; And a book information database for storing books including the emotion information for each book.

In addition, the member information database stores personal information and loan history of library members, and the personal information consists of the gender, age, and field of interest of the library member, and the loan history includes books borrowed from the library by the library member. And, the recommended book providing server excludes books included in the loan history when generating the recommended book list.

In addition, the kiosk includes a photographing unit capable of photographing facial expressions of library members; And a member identification unit capable of identifying the library member, wherein the photographing unit includes an emotion recognition module capable of grasping the level of emotion of the library member by using an image photographed of the expression of the library member. The member identification unit may identify a library membership card possessed by the library member, and retrieve member information connected to the library membership card from the member information database.

In a kiosk device capable of performing a kiosk system,

The kiosk device includes an inlet port through which a library member's finger can be inserted at the front, and includes a heart rate check unit capable of checking the heart rate of the library member, and the heart rate check unit is identified by the heart rate check unit. Emotion measurement module for measuring emotions based on the heart rate of library members; A cradle provided inside the inlet and on which fingers of the library member are mounted; A pivot shaft provided below the cradle and capable of rotating the cradle; A first sensor provided on an upper surface of the inner end of the holder and in close contact with a finger provided on the upper surface of the holder to check a heart rate; A cylinder provided on a side opposite to the first sensor about the rotation shaft to raise and lower the outer end of the cradle; A second sensor located on the same vertical line as the cylinder and in close contact with the upper side of the finger to check heart rate; A UV sterilization lamp provided on the upper inner end of the cradle and irradiating ultraviolet rays toward the top of the cradle; And a moving rail provided at both ends of the holder and connected to the UV sterilization lamp to move the UV sterilization lamp along the extension direction.

As described above, the present invention recognizes the emotions of books and library members, and uses them to provide recommended books, so that the list of recommended books is tailored to members, thereby improving the satisfaction of library members.

In addition, the weight of each word including emotion is determined differently, and the emotion level of each book can be classified according to the emotion, so that the weight can be weighted to correspond to the emotion type of the library member. Since the list of recommended books can change, it has the effect of improving the satisfaction of library members with recommended books.

The effects of the present invention are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the following description.

1 shows the configuration of a library member customized book recommendation kiosk system using emotion recognition according to the present invention.
2 shows a book information management server according to the present invention.
3 is a flow chart showing the steps of generating and storing book information according to the present invention.
Figure 4 shows a library member customized book recommendation kiosk device using emotion recognition according to the present invention.
5 shows the configuration of a library member customized book recommendation kiosk device using emotion recognition according to the present invention.
6 and 7 show the configuration and embodiment of the heart rate check unit according to the present invention.
8 shows a recommended book providing server according to the present invention.

In the present invention, various modifications may be made and various embodiments may be provided, and specific embodiments will be illustrated in the drawings and described in detail.

However, this is not intended to limit the present invention to a specific embodiment, it should be understood to include all changes, equivalents, and substitutes included in the spirit and scope of the present invention. In describing each drawing, similar reference numerals have been used for similar elements.

When a component is referred to as being "connected" or "connected" to another component, it is understood that it may be directly connected or connected to the other component, but other components may exist in the middle. It should be. On the other hand, when a component is referred to as being "directly connected" or "directly connected" to another component, it should be understood that there is no other component in the middle.

The terms used in the present application are only used to describe specific embodiments, and are not intended to limit the present invention. Singular expressions include plural expressions unless the context clearly indicates otherwise. In the present application, terms such as "comprise" or "have" are intended to designate the presence of features, numbers, steps, actions, components, parts, or combinations thereof described in the specification, but one or more other features. It is to be understood that the presence or addition of elements or numbers, steps, actions, components, parts, or combinations thereof does not preclude in advance.

Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings. The same reference numerals shown in each drawing indicate the same member. In describing the present invention, detailed descriptions of related known functions or configurations are omitted so as not to obscure the subject matter of the present invention.

1 shows the configuration of a library member customized book recommendation kiosk system using emotion recognition according to the present invention, FIG. 2 shows a book information management server according to the present invention, and FIG. 3 is a diagram of book information according to the present invention. It is a flow chart showing the steps of creation and storage, and FIG. 4 shows a library member customized book recommendation kiosk device using emotion recognition according to the present invention, and FIG. 5 is a library member customized book recommendation using emotion recognition according to the present invention. It shows the configuration of the kiosk device, Figures 6 and 7 shows the configuration and embodiment of the heart rate check unit according to the present invention, Figure 8 shows a recommended book providing server according to the present invention.

The present invention relates to a library member customized book recommendation kiosk device and system that recognizes emotions from library members and reviews and utilizes them, and the library member customized book recommendation kiosk system (1) using emotion recognition according to the present invention is a book It includes an information management server 100, a member information DB 200, a kiosk 300, and a recommended book providing server 400.

Prior to the description, it is stated in advance that'DB' described in this specification represents'database'.

The book information management server 100 includes an emotional word set DB 110 for generating and storing the built emotional word set, a text data generating unit 120 for generating text data containing information related to the book for each book from the outside, An emotion information generation unit 130 for generating emotion information by extracting a word corresponding to a person's emotion from text data for each book, and assigning the extracted emotion word and an emotion level corresponding to the emotion word pre-stored in the emotion word set for each book. ) And a book information DB 140 that builds and stores emotion information for each book generated by the emotion information generation unit 130.

The emotion word set DB 110 is a place to generate and store an emotion word set that generates a list of words for each emotion field, and an emotion information generation unit using the emotion word set previously stored in the emotion word set DB 110 In (130), emotion information can be extracted for each book by extracting emotion words from text data.

This method of constructing an emotion word set includes an emotion word extraction step (S1) of extracting an emotion word from a dictionary, a mapping and scoring step (S2) of mapping and scoring the emotion word extracted in the emotion word extraction step (S1), and the mapping. And the emotional word set storage step (S4) of storing the generated emotional word set by performing the emotional word set building step (S3) of constructing an emotional word set by using the average value of the emotional level scored in the emotional level scoring step (S2). ).

In the emotion word set generated through the above-described method, the emotion level of the emotion word is quantified for each emotion field. For example, in the emotion field, each word for six emotions for joy, sadness, disgust, anger, fear, and surprise. A list is created, and the emotional level of each word is a full score of 10, and the closer to 10 points, the greater the intensity of the emotion is felt.The generated emotional word set is shown in Table 1 below. same.

Emotional word Emotion category Emotion Spectacle aversion 4.95 It is easy pleasure 5.36 Wonderful surprised 7.77

Therefore, by using the emotion word set stored in the emotion word set DB 110, the emotion word is extracted from the text data described later, and the emotion category and emotion level corresponding thereto are correlated from the emotion word set, You can measure the level of emotion by category.

In this case, the emotion word may be stored in clusters with the emotion word, synonyms, synonyms, etc. built in the emotion word set in addition to the words stored in the emotion word set. For example, the word'surprise', the synonym for'wonderful', also has the same emotional category and level of emotion as'wonderful' and can be built together in an emotional word set.

The text data generation unit 120 extracts information data of general books and generates text data for each book, and the books corresponding to the text data generation unit 120 are general books or major institutions within 5 years of publication. It may be a recommended book, but is not limited thereto.

The text data generation unit 120 collects text data that may include human emotions in the book to generate text data, that is, book introduction, SNS reviews, blog review data, recommendation reviews, review data, etc. from internet bookstores and portal sites. Thus, text data corresponding to each book is created.

The emotion information generation unit 130 extracts emotion words from text data generated for each book, corresponds to and compares the sameness and similarity with the emotion words included in the emotion word set to generate emotion information that each book has, The text data generating unit 120 extracts words including emotions from the mapped text data, and compares the emotion words included in the text data for each book with the emotion words included in the emotion word set.

First, a word is extracted from text data corresponding to one book, and the correlation between the extracted word and the emotional word included in the emotional word set is calculated and scored, and emotional information for each book is generated as shown in Table 2 below.

Book name Happiness sadness surprised aggro aversion fear Book 1 A1 B1 C1 D1 E1 F1 Book 2 A2 B2 C2 D2 E2 F2

At this time, the total number of words extracted in one book is considered, and the level of emotion for each book is calculated as the sum of the level of emotions built into the set of emotion words.

The book information DB 140 stores the book-specific emotion information generated by the above-described emotion information generation unit 130, and the degree of emotion for each book stored in the book information DB 140 is a recommended book providing server 400 to be described later. It is used in the primary list generation unit 410 of, and is used to create and provide a list of recommended books to be recommended to library members.

The update unit 150 performs the process of storing the book information generated through the above-described text data generation unit 120 and the emotion information generation unit 130 in the book information DB 140 for each preset period and automatically By performing the process, the book information DB 140 continuously stores book information.

This update unit 150 automatically drives the text data generation unit 120 and the emotion information generation unit 130 once a day to build book information for a new book, and stores it in the book information DB 140 Make it possible.

Therefore, through the update unit 150, the administrator can automatically build new book information every day without separate management and update it in the book information DB 140, so that recently released books can also be easily recommended. .

In addition, the update unit 150 may be set to automatically discard book information for books released before a preset period of publication year among book information previously stored in the book information DB 140. For example, only book information published within the last 5 years can be stored, so if the period after publication exceeds 5 years, it is automatically discarded, and books that are somewhat older than the publication year may be automatically set not to be recommended, but this is not limited thereto.

The member information DB 200 is a server that manages information related to library members, and stores information of library members, and can provide a list of recommended books customized for each library member by interlocking with the recommended book providing server 400 described later. To be there.

The member information DB 200 stores the library members' personal information and loan history, and the personal information can be gender, age, interests, etc., and the loan history stores the loan history of members in the library to make existing loans. You can prevent a book from being presented in the list of recommended books.

In addition, the member information DB 200 may be additionally given a weight in comparison with other library members by using the loan history of the library member.

For example, if there is a history of lending book 1 by a first library member, the above book is recommended when recommending a book to a first library member by using the lending history of another second library member lending Book 2 along with Book 1 Book 2 borrowed with 1 can be additionally weighted.

The kiosk 300 is provided in the library to perform functions such as searching for books in the library, availability of reading, lending books, and checking library-related information, and is linked with the recommended book providing server 400 to provide the recommended book providing server. You can get a list of recommended books for each library member from (400).

The front of the kiosk 300 is provided with a photographing unit 310 capable of photographing the expression of a library member, and a member identification unit 320 provided in front of the kiosk 300 to identify the member's membership card and membership card. .

The photographing unit 310 includes an emotion recognition module 311 capable of recognizing a member's emotion with a photographed image, and the emotion recognition module 311 may derive an emotion recognition result from the photographed image, and the current member A weight may be additionally given by the primary list generator 410 described later for each emotion field corresponding to the emotion state of.

For example, if the expression of a library member photographed through the photographing unit 310 corresponds to'joy' among the emotion classifications classified in the emotion book set, books with a high emotional level corresponding to'joy' are listed in the recommended book list. You can induce it to be more recommended.

On the contrary, if the expression of a library member photographed through the photographing unit 310 corresponds to'sadness' among the emotion classifications classified in the emotion book set, books with a large emotional level corresponding to the opposite emotion,'joy' are listed in the recommended book list. It can also evoke the mood of library members by inducing them to be more recommended.

The emotion recognition results for library members through the emotion recognition module 311 are shown in Table 3 below.

Member Name Happiness sadness surprised aggro aversion fear Sum Kim Chaeum a b c d e f 100

That is, as shown in Table 3, emotions can be classified through images of library members photographed through the photographing unit 310, and the sum of the classified emotions (a+b+c+d+e+f) is set to 100. You can measure the degree of each emotion as a percentage.

The member identification unit 320 recognizes the membership card, and the library member recognizes the membership card without performing a separate login process to identify the library member, and automatically provides the corresponding member information to the recommended book providing server 400. To be able to.

The member identification unit 320 may be a card reader, a QR code reader, etc., but is not limited thereto.

On the other hand, the kiosk 300 can recognize the expression of the library member through the photographing unit 310 to recognize the emotion of the library member. There is a concern that it is somewhat difficult to extract the emotions that become.

Accordingly, the kiosk 300 according to the present invention may further include a heart rate check unit 330 capable of checking the heart rate of a library member.

The heart rate check unit 330 checks the heart rate of the library member for a certain period of time through the finger inserted through the input port 301 when a library member inserts a finger through the inlet 301 provided in the front of the kiosk 300 The emotion measurement module 331 included in the heart rate check unit 330 can recognize the emotional state of the library member.

The emotion measurement module 331 may measure the heart rate of a library member for a preset time through a pre-stored program, and recognize the emotion of the library member based on this.

In addition, the heart rate check unit 330, as shown in Figure 6, the cradle 332, the rotation shaft 333, the first sensor 334, the cylinder 335, the second sensor 336, a UV sterilization lamp 337 and It may include a moving rail (338).

First, a finger inserted through the inlet 301 is provided on the upper surface of the cradle 332. A pivot shaft 333 is provided at the lower end of the cradle 332 so that the cradle 332 may be inclined downward with an inner end centered on the upper end of the pivot shaft 333. In addition, a first sensor 334 is provided at the inner end of the cradle 332 so that the first sensor 334 can check the heart rate felt at the fingertips of the library member.

On the other hand, since library members directly put their fingers, there is a concern that children may not be able to reach the inner end of the cradle 332 equipped with the first sensor 334 due to the short finger length. There is a concern that it is difficult to check the heart rate.

Accordingly, a cylinder 335 is provided at the lower end of the holder 332 on the side opposite to the first sensor 334 around the rotation shaft 333, and is located on the same vertical line as the cylinder 335 and the kiosk 300 A second sensor 336 is provided on the inner surface of the.

As shown in FIG. 7, when the second sensor 336 detects that the library member's finger is inserted into the inlet 301, the cylinder 335 rises, and the cylinder 335 rises around the rotation shaft 333. The upper side of the cradle 332 provided with 335 is raised, and the inner end of the cradle 332 provided with the first sensor 334 is lowered.

When the cylinder 335 rises and the library member's finger comes into contact with the second sensor 336, the cylinder 335 automatically stops extending, and the second sensor 336 touches the finger skin of the library member in close contact. You can check your heart rate.

When the first and second sensors 334 and 336 check the heart rate of the library member for a certain period of time, the cylinder 335 is automatically compressed so that the member can easily remove a finger.

In addition, moving rails 338 are provided on both sides of the cradle 332, and UV sterilization lamps 337 connected to the moving rails 338 and both ends are provided on the upper side of the cradle 332 so that library members can remove their fingers. After that, the UV sterilization lamp 337 moves along the moving rail 338 provided at the side end of the cradle 332 to disinfect the upper surface of the cradle 332, so that the kiosk 300 used by a number of library members can be hygienically used. To be there.

In addition, the kiosk 300 is connected to the wireless Internet and is linked with the member information DB 200 and the recommended book providing server 400, as well as a site linking unit 340 that can be linked with other libraries and book sales sites. It may contain additionally.

The site linking unit 340 automatically links with the member information previously stored in the member information DB 200 when a library member first accesses (logs in) other library sites and book sales sites through the display of the kiosk 300. , The loan history of lending books from other library sites and the history of books purchased from book sales sites can be stored together in the member information DB (200).

That is, the list of final recommended books that may be provided by the recommended book providing server 400 may include books that a library member has purchased personally or books with a history that have already been lent out from other libraries. Therefore, the site linking unit 340 allows the member information to be linked with the member information of other sites to prevent this problem from being provided as recommended books by library members from other libraries and book purchasing sites. I can.

The recommended book providing server 400 provides a customized list of recommended books to library members accessed through the kiosk 300, and the primary list generation unit 410, the secondary list generation unit 420, and the final list are generated. It includes a unit 430 and a feedback generation unit 440.

The primary list generation unit 410 generates the first recommended book list through the book information stored in the book information DB 140 and the emotion recognition result of the library member extracted through the emotion recognition module 311 of the kiosk 300. Can be generated.

In other words, the first recommended book list can be created by the number of pre-stored book volumes through the summation of all the books previously stored in the book information DB 140 by summing the emotion recognition results of the library members as weights. It is shown in Table 4.

Book name Happiness sadness surprised aggro aversion fear Appraisal sum Book 1 A1*a B1*b C1*c D1*d E1*e F1*f SUM 1 Book 2 A2*a B2*b C2*c D2*d E2*e F2*f SUM 2

Therefore, the first recommended book that extracted only the highest recommended books as much as the number of volumes in the pre-stored first recommended book list through the sum n multiplied by the n number of book information stored in the book information DB 140 and the emotions of the library members as weights. The list may be generated by the primary list generation unit 410.

The secondary list generation unit 420 utilizes the loan history for each library member, the loan history of other libraries, and the book purchase history of the book purchasing site through the member information DB 200 and the kiosk 300, and the primary list generation unit 410 ), a screening process of removing books already read by library members from the first recommended book list created in () is performed to create a second recommended book list.

In other words, only recommended books that have been removed from the first recommended book list may be generated as the second recommended book list so that the books already read by the library member are not displayed in the second recommended book list.

In addition, the secondary list generation unit 420 may check the age of the library member among the member information transmitted from the member information DB 200, and books that do not match the age of the member can be automatically removed from the secondary recommended book list. .

For example, if you are a library member, children's books are automatically removed so that children's books are not built in the second recommended book list, and if you are a minor, you can remove books that are not allowed for minors to be included in the second recommended book list. .

The final list generation unit 430 re-assigns a weight for each area of interest among member information received from the member information DB 200 among recommended books corresponding to the second recommended book list generated by the second list generation unit 420. Create a list of final recommended books.

In other words, by assigning a weight of 1.2 for the field of interest, and multiplying it by 1.0 for other fields and not giving it a weight, it is possible to weight the books corresponding to the field of interest among recommended books according to the field of interest for each library member. Examples of weighting are shown in Table 5 below.

Book name Appraisal sum Book field Final appraised sum Book 1 SUM 1 Economy/Management SUM 1*1.2 Book 2 SUM 2 parenting SUM 2*1.0

That is, as shown in Table 5, for library members who are interested in the field of'economics/management', a weight can be added to Book 1 in the field of economy/management.

Accordingly, as in the above-described method, a list of final recommended books having a preset number of volumes is generated according to the final emotion match and provided to the kiosk 300 to display it on the screen of the kiosk 300.

The feedback generation unit 440 stores the list of final recommended books provided by the final list generation unit 430 to the kiosk 300 by the library member through the kiosk 300 and receives feedback through the library member. The satisfaction level of the member's final recommended book list can be investigated.

Therefore, the library member-customized book recommendation kiosk system (1) using emotion recognition recognizes the emotions of books and library members, and provides recommended books using this, so that the list of recommended books is tailored to members rather than the existing list of recommended books. It has the effect of improving satisfaction.

Optimal embodiments have been disclosed in the drawings and specification. Here, specific terms have been used, but these are only used for the purpose of describing the present invention, and are not used to limit the meaning or the scope of the present invention described in the claims. Therefore, those of ordinary skill in the art will understand that various modifications and equivalent other embodiments are possible therefrom. Therefore, the true technical scope of the present invention should be determined by the technical spirit of the appended claims.

1. Library member customized book recommendation kiosk system using emotion recognition
100. Book Information Management Server
200. Member Information Database
300. Kiosk
400. Recommended Book Providing Server

Claims (5)

In the library member customized book recommendation kiosk system that recognizes and uses emotions from library members and reviews,
It stores the emotional word set in which the emotion classification and emotion level for each word is built, and generates book information including the emotion classification and emotion level for each book by comparing the text data for each book and the emotion word included in the emotion word set. Book information management server to store;
A member information database storing library member information for each library member;
A kiosk that photographs the facial expressions of library members and provides a list of recommended books for each library member; And
A recommended book providing server for generating a list of recommended books for each library member by interlocking with the book information management server, the member information database, and the kiosk; and
The member information database stores personal information and loan history of library members,
The above personal information is made up of the gender, age and field of interest of the library member,
The loan history includes books borrowed from the library by the library member,
The recommended book providing server excludes books included in the loan history when generating the recommended book list,
The kiosk includes a photographing unit capable of photographing an expression of a library member; And a member identification unit capable of identifying the library member,
The photographing unit includes an emotion recognition module capable of grasping the level of emotion of the library member by using an image photographed of the expression of the library member,
The member identification unit identifies a library membership card possessed by the library member, and loads member information connected to the library membership card from the member information database,
The kiosk,
A slot in front of the library member's fingertips; And a heart rate check unit capable of determining the heart rate of the library member;
The heart rate check unit,
An emotion measurement module for measuring emotions based on the heart rate of the library member identified by the heart rate check unit;
A cradle provided inside the inlet and on which fingers of the library member are mounted;
A rotation shaft provided below the cradle and capable of rotating the cradle;
A first sensor provided on an upper surface of an inner end of the cradle and in close contact with a finger provided on the upper surface of the cradle to check a heart rate;
A cylinder provided on a side opposite to the first sensor about the rotation shaft to raise and lower the outer end of the cradle;
A second sensor located on the same vertical line as the cylinder and in close contact with the upper side of the finger to check heart rate;
A UV sterilization lamp provided on the upper inner end of the holder and irradiating ultraviolet rays toward the upper surface of the holder; And
A library member customized book recommendation kiosk system using emotion recognition, characterized in that it is provided at both ends of the cradle and is connected to the UV sterilization lamp to move the UV sterilization lamp along the extension direction. .
The method of claim 1,
The book information management server,
An emotion word set database in which the emotion word set consisting of emotion words having emotion classification and emotion level is pre-stored;
A text data generation unit that collects review information for each book and generates the text data for each book;
An emotion information generation unit for extracting the emotion words included in the text data for each book, classifying the emotion classification and the emotion level of each emotion word for each book, and generating emotion information for each book; And
Book information database for storing books containing the emotion information for each book; Library member customized book recommendation kiosk system using emotion recognition, characterized in that it comprises a.
delete delete delete

Images