KR20230137228A - Method, apparatus and program for providing artificial intelligence book recommendation service using psychological state information - Google Patents

Abstract

The present invention provides a method, device, and method for providing an artificial intelligence book recommendation service using psychological state information that obtains text and pictures about the emotions felt after reading a book from a user, analyzes the obtained text and pictures, and recommends books suitable for the user. It's about the program.
A method of providing an artificial intelligence book recommendation service using psychological state information according to an embodiment of the present invention includes the steps of obtaining text and pictures about the emotions felt after reading a book from a user, and using the obtained text and pictures to It includes analyzing a psychological state and recommending a book suitable for the user based on the results of analyzing the psychological state.

Description

Method, device and program for providing artificial intelligence book recommendation service using psychological state information {METHOD, APPARATUS AND PROGRAM FOR PROVIDING ARTIFICIAL INTELLIGENCE BOOK RECOMMENDATION SERVICE USING PSYCHOLOGICAL STATE INFORMATION}

The present invention relates to a method, device, and program for providing an artificial intelligence book recommendation service using psychological state information. More specifically, the present invention relates to a method, device, and program for providing an artificial intelligence book recommendation service, and more specifically, to obtain text and pictures about the emotions felt after reading a book from a user and to analyze the obtained text and pictures. It relates to a method, device, and program for providing an artificial intelligence book recommendation service using psychological state information to recommend books suitable for users.

Recently, depression has been occurring among the public due to COVID-19. As a result, public interest in mental health management is increasing, and the public is actively reading books such as literature and essays to manage mental health.

In this process, large online book distributors and related platforms utilize artificial intelligence recommendation algorithms to provide services that recommend books suited to consumers' tastes in order to meet consumers' needs.

However, because these platforms simply use the user's purchase history as data, there are limitations in analyzing the consumer's unique personality and psychological state. They cannot help manage mental health by analyzing the consumer's unique personality and psychological state. There is a need for a service that recommends accessible books.

The problem that the present invention aims to solve is an artificial intelligence book recommendation service using psychological state information that obtains text and pictures about the emotions felt after reading a book from the user, analyzes the obtained text and pictures, and recommends books suitable for the user. Provides methods, devices, and programs.

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

A method of providing an artificial intelligence book recommendation service using psychological state information according to an embodiment of the present invention to solve the above-described problem includes the steps of acquiring text and pictures about the emotions felt after reading the book from the user, the obtained text and It may include analyzing the user's psychological state using a picture, and recommending a book suitable for the user based on the results of analyzing the psychological state.

In addition, the step of analyzing the user's psychological state includes processing the obtained text in natural language and analyzing the meaning of the sentence, extracting a sentence containing emotion based on the analysis result, and It may include analyzing the user's psychological state based on the included emotions.

In addition, the step of recommending a book suitable for the user includes extracting similar readers who are analyzed as having a similar psychological state to the user among readers who have read the book, and extracting books read by the similar readers. , including the step of recommending the extracted book to the user, wherein the step of recommending the extracted book to the user recommends to the user books with a large number of overlaps among books read by the similar reader, or recommending the extracted book to the user. The method may further include recommending to the user a book for which the reader reads the book and is judged to have positive feelings, or recommending a book in a field corresponding to the user's taste among books read by similar readers.

In addition, the step of analyzing the user's psychological state includes providing the user with an event memory log that records events remembered after reading the book, and receiving information about each item included in the event memory log from the user. It may include a step of receiving an answer, and, based on the input answer, recording events that occurred in each period of the user's life according to a preset life stage to create a life memory archive.

In addition, the step of recommending books suitable for the user includes selecting similar readers with similar experience levels for events that occurred in each period of the user's life based on the user's lifetime memory archive, and books read by the similar readers. It may include the step of extracting and recommending the extracted book to the user.

In addition, the step of selecting similar readers with similar experience points includes determining characteristics of each life stage based on the lifetime memory archive of the user, and determining characteristics of each life stage of the user based on the lifetime memory archive of the readers. It may include calculating the degree of similarity between the user's experience and the experience of the readers by comparing the determined characteristics of each life stage, and selecting the reader with the highest calculated similarity as a similar reader.

In addition, the step of selecting similar readers with similar experience points includes determining the types of events that occurred in each life stage based on the user's lifetime memory archive, and the user's psychology using the types of events determined. It may include a step of determining the state, and a step of selecting a similar reader having a psychological state similar to the user's psychological state among the readers.

In addition, the step of analyzing the user's psychological state includes extracting input data by determining the color, line thickness, object location, and object size of the obtained picture, and inputting the input data into a previously learned artificial intelligence model. It may include the step of obtaining an output of the artificial intelligence model, and determining the psychological state of the user based on the output.

An artificial intelligence book recommendation service providing device using psychological state information according to an embodiment of the present invention to solve the above-described problem includes a memory that stores one or more instructions, and a processor that executes the one or more instructions stored in the memory. Including, the processor may perform a method of providing an artificial intelligence book recommendation service using psychological state information by executing the one or more instructions.

In order to solve the above-described problem, the artificial intelligence book recommendation service providing program using psychological state information according to an embodiment of the present invention combines with a computer, which is hardware, to provide a method of providing an artificial intelligence book recommendation service using psychological state information. It can be stored on a computer-readable recording medium so that it can be performed.

Other specific details of the invention are included in the detailed description and drawings.

The present invention can obtain text and pictures about the emotions felt after reading a book from a user, analyze the obtained text and pictures, and recommend a book suitable for the user.

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 description below.

Figure 1 is a diagram illustrating a system for providing an artificial intelligence book recommendation service using psychological state information according to an embodiment of the present invention.
Figure 2 is a hardware configuration diagram of a provision device according to an embodiment of the present invention.
Figure 3 is a diagram showing a method of providing an artificial intelligence book recommendation service using psychological state information according to an embodiment of the present invention.
Figure 4 is a diagram illustrating a method of analyzing a user's psychological state and recommending a book suitable for the user according to the first embodiment of the present invention.
Figure 5 is a diagram illustrating a method of analyzing a user's psychological state and recommending a book suitable for the user according to a second embodiment of the present invention.
Figure 6 is a diagram illustrating a method of selecting similar readers based on the user's lifetime memory archive according to the first embodiment of the present invention.
Figure 7 is a diagram illustrating a method of selecting similar readers based on a user's lifetime memory archive according to a second embodiment of the present invention.

The advantages and features of the present invention and methods for achieving them will become clear by referring to the embodiments described in detail below along with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below and may be implemented in various different forms. The present embodiments are merely provided to ensure that the disclosure of the present invention is complete and to provide a general understanding of the technical field to which the present invention pertains. It is provided to fully inform the skilled person of the scope of the present invention, and the present invention is only defined by the scope of the claims.

The terminology used herein is for describing embodiments and is not intended to limit the invention. As used herein, singular forms also include plural forms, unless specifically stated otherwise in the context. As used in the specification, “comprises” and/or “comprising” does not exclude the presence or addition of one or more other elements in addition to the mentioned elements. Like reference numerals refer to like elements throughout the specification, and “and/or” includes each and every combination of one or more of the referenced elements. Although “first”, “second”, etc. are used to describe various components, these components are of course not limited by these terms. These terms are merely used to distinguish one component from another. Therefore, it goes without saying that the first component mentioned below may also be a second component within the technical spirit of the present invention.

Unless otherwise defined, all terms (including technical and scientific terms) used in this specification may be used with meanings commonly understood by those skilled in the art to which the present invention pertains. Additionally, terms defined in commonly used dictionaries are not interpreted ideally or excessively unless clearly specifically defined.

As used in the specification, the term “unit” or “module” refers to a hardware component such as software, FPGA, or ASIC, and the “unit” or “module” performs certain roles. However, “part” or “module” is not limited to software or hardware. A “unit” or “module” may be configured to reside on an addressable storage medium and may be configured to run on one or more processors. Thus, as an example, a “part” or “module” refers to components such as software components, object-oriented software components, class components, and task components, processes, functions, properties, Includes procedures, subroutines, segments of program code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, and variables. The functionality provided within components and “parts” or “modules” can be combined into smaller components and “parts” or “modules” or into additional components and “parts” or “modules”. Could be further separated.

In this specification, a computer refers to all types of hardware devices including at least one processor, and depending on the embodiment, it may be understood as encompassing software configurations that operate on the hardware device. For example, a computer can be understood to include, but is not limited to, a smartphone, tablet PC, desktop, laptop, and user clients and applications running on each device.

Hereinafter, embodiments of the present invention will be described in detail with reference to the attached drawings.

Each step described in this specification is described as being performed by a computer, but the subject of each step is not limited thereto, and depending on the embodiment, at least part of each step may be performed in a different device.

Figure 1 is a diagram illustrating a system for providing an artificial intelligence book recommendation service using psychological state information according to an embodiment of the present invention.

Referring to FIG. 1, an artificial intelligence book recommendation service providing system using psychological state information according to an embodiment of the present invention may include a providing device 100, a user terminal 200, and an external server 300.

Here, the artificial intelligence book recommendation service providing system using psychological state information shown in FIG. 1 is according to an embodiment, and its components are not limited to the embodiment shown in FIG. 1, and may be added as needed, It may be changed or deleted.

The providing device 100 acquires text and pictures about the emotions felt after reading a book from the user, analyzes the user's psychological state using the acquired text and pictures, and provides an appropriate solution for the user based on the results of analyzing the psychological state. I can recommend books.

The user terminal 200 can access a website through a network and receive an artificial intelligence book recommendation service using psychological state information from the provision device 100.

The user terminal 200 may include at least one of a smartphone, a tablet PC, a desktop, and a laptop having a display on at least a portion of the user terminal 200, and may be used by the provision device 100 in the process of running the browser. You can receive an artificial intelligence book recommendation service using the provided psychological state information. However, it is not limited to this.

The user terminal 200 can receive various services provided by the providing device 100 through the applications by downloading, installing, and executing applications related to various services and platforms provided by the providing device 100. To this end, the user terminal 200 may be equipped with an operating system capable of running applications, like a smartphone. However, the user terminal 200 is not limited to this, and other general-purpose devices capable of running applications may be applied.

In various embodiments, the user terminal 200 may provide a web-based service in addition to an application, and the method by which the user terminal 200 provides the service is not limited to a specific format.

The external server 300 can be connected to the provision device 100 through a network, and the provision device 100 can store and manage various information to perform a method of providing an artificial intelligence book recommendation service using psychological state information. there is.

Additionally, the external server 300 may receive and store various information and data generated as the providing device 100 performs a method of providing an artificial intelligence book recommendation service using psychological state information. For example, the external server 300 may be a storage server separately provided outside the provision device 100. With reference to FIG. 2, the hardware configuration of the provision device 100 will be described.

Figure 2 is a hardware configuration diagram of a provision device according to an embodiment of the present invention.

Referring to FIG. 2, the provision device 100 (hereinafter referred to as computing device) according to an embodiment of the present invention loads one or more processors 110 and a computer program 151 executed by the processor 110. It may include a memory 120, a bus 130, a communication interface 140, and a storage 150 that stores a computer program 151. Here, only components related to the embodiment of the present invention are shown in Figure 2. Accordingly, anyone skilled in the art to which the present invention pertains will know that other general-purpose components may be included in addition to the components shown in FIG. 2.

The processor 110 controls the overall operation of each component of the computing device 100. The processor 110 includes a Central Processing Unit (CPU), Micro Processor Unit (MPU), Micro Controller Unit (MCU), Graphic Processing Unit (GPU), or any other type of processor well known in the art of the present invention. It can be.

Additionally, the processor 110 may perform operations on at least one application or program for executing methods according to embodiments of the present invention, and the computing device 100 may include one or more processors.

In various embodiments, the processor 110 includes random access memory (RAM) (not shown) and read memory (ROM) that temporarily and/or permanently store signals (or data) processed within the processor 110. -Only Memory, not shown) may be further included. Additionally, the processor 110 may be implemented in the form of a system on chip (SoC) that includes at least one of a graphics processing unit, RAM, and ROM.

Memory 120 stores various data, commands and/or information. Memory 120 may load a computer program 151 from storage 150 to execute methods/operations according to various embodiments of the present invention. When the computer program 151 is loaded into the memory 120, the processor 110 can perform the method/operation by executing one or more instructions constituting the computer program 151. The memory 120 may be implemented as a volatile memory such as RAM, but the technical scope of the present disclosure is not limited thereto.

Bus 130 provides communication functionality between components of computing device 100. The bus 130 may be implemented as various types of buses, such as an address bus, a data bus, and a control bus.

The communication interface 140 supports wired and wireless Internet communication of the computing device 100. Additionally, the communication interface 140 may support various communication methods other than Internet communication. To this end, the communication interface 140 may be configured to include a communication module well known in the technical field of the present invention. In some embodiments, communication interface 140 may be omitted.

Storage 150 may store the computer program 151 non-temporarily. When performing a method of providing an artificial intelligence book recommendation service using psychological state information through the computing device 100, the storage 150 stores various information necessary to provide a method of providing an artificial intelligence book recommendation service using psychological state information. can be saved.

The storage 150 is a non-volatile memory such as Read Only Memory (ROM), Erasable Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), flash memory, a hard disk, a removable disk, or a device well known in the technical field to which the present invention pertains. It may be configured to include any known type of computer-readable recording medium.

The computer program 151, when loaded into the memory 120, may include one or more instructions that cause the processor 110 to perform methods/operations according to various embodiments of the present invention. That is, the processor 110 can perform the method/operation according to various embodiments of the present invention by executing the one or more instructions.

In one embodiment, the computer program 151 includes the steps of acquiring text and pictures about the emotions felt after reading a book from the user, analyzing the psychological state of the user using the obtained text and pictures, and the psychological state. It may include one or more instructions for performing a method of providing an artificial intelligence book recommendation service using psychological state information, including the step of recommending a book suitable for the user based on a result of analyzing the state.

The steps of the method or algorithm described in connection with embodiments of the present invention may be implemented directly in hardware, implemented as a software module executed by hardware, or a combination thereof. The software module may be RAM (Random Access Memory), ROM (Read Only Memory), EPROM (Erasable Programmable ROM), EEPROM (Electrically Erasable Programmable ROM), Flash Memory, hard disk, removable disk, CD-ROM, or It may reside on any type of computer-readable recording medium well known in the art to which the present invention pertains.

The components of the present invention may be implemented as a program (or application) and stored in a medium in order to be executed in conjunction with a hardware computer. Components of the invention may be implemented as software programming or software elements, and similarly, embodiments may include various algorithms implemented as combinations of data structures, processes, routines or other programming constructs, such as C, C++, , may be implemented in a programming or scripting language such as Java, assembler, etc. Functional aspects may be implemented as algorithms running on one or more processors. Hereinafter, with reference to FIG. 3, a method of providing an artificial intelligence book recommendation service using psychological state information provided by the computing device 100 will be described.

Figure 3 is a diagram showing a method of providing an artificial intelligence book recommendation service using psychological state information according to an embodiment of the present invention.

Referring to FIG. 3, the computing device 100 may obtain text and pictures from the user about the emotions felt after reading the book (S100). The computing device 100 can provide instructions for inputting text and pictures to the user terminal 200, and the user follows the instructions provided by the computing device 100 to create text and pictures about the emotions felt after reading the book. You can enter .

Users can record what they felt while reading a book in the form of an essay and express the emotions felt in the text in the form of a visual picture. A picture may express a specific object, landscape, person, etc., or may be expressed in a metaphorical form, but is not limited to this.

The computing device 100 may provide an input window for writing text or drawing a picture, and may also obtain text and drawings written or drawn on paper by the user as images. For example, a user can write on paper about the emotions felt after reading a book, draw a picture, photograph the paper with the picture on it, and input the photographed image according to instructions provided by the computing device 100. can do.

The computing device 100 may analyze the user's psychological state using the acquired text and pictures (S200). The computing device 100 may perform NLP (Natural Language Processing) analysis based on the acquired text and analyze the user's psychological state through the analysis results.

NLP uses technologies such as natural language analysis, natural language understanding, and natural language generation, as well as morphological analysis, syntactic analysis, semantic analysis that interprets the sentence based on its meaning, and sentence analysis. You can analyze a text through pragmatic analysis, which determines what it actually means.

Additionally, the computing device 100 may perform Convolutional Neural Network (CNN) analysis based on the acquired picture and analyze the user's taste through the analysis results.

CNN is a Neural Network model that is mainly used to process image or video data in deep learning and involves preprocessing called convolution. It receives the image as is and analyzes the image by building a layer of features while maintaining spatial/regional information. can do.

Specifically, the computing device 100 can determine the color, line thickness, object position, and object size of the acquired picture and convert it into a set input data form, and input the input data into a previously learned artificial intelligence model. there is. The computing device 100 may obtain the output of the artificial intelligence model and determine the user's psychological state based on the output. The artificial intelligence model may output an output value for the input data according to the learned results, and the computing device 100 may determine the user's psychological state based on the output value.

In various embodiments, the computing device 100 may not only analyze the user's taste by preprocessing and analyzing a picture in a metaphorical form by the user, but also generate an image that can well represent the user's taste, or You can also search and match. For example, the computing device 100 may convert an image drawn by a user into a finished picture using GAN (Adversarial Neural Network) technology and use it to analyze the user's taste pattern based on this.

According to an embodiment of the present invention, the computing device 100 can complete the user's psychological state analyzed through the acquired text and pictures into one work. The computing device 100 can extract a picture containing an object that appears in a text or picture or a picture representing an analyzed psychological state from existing works and select it as a work representing the psychological state of the user. there is. Additionally, the computing device 100 may create a new picture representing the analyzed psychological state of the user and complete it as a work of art. The computing device 100 may save the completed work as a user's pattern. For example, the computing device 100 may generate and store a pattern including the user's emotional data and taste data.

The computing device 100 may recommend a book suitable for the user based on the results of analyzing the psychological state (S300). The computing device 100 may store several book lists, and each book list may be stored in a manner that matches a psychological state. The computing device 100 may extract a list of books corresponding to the user's psychological state and recommend them to the user. Here, the list of books corresponding to the psychological state may be books that provide stability depending on the user's psychological state, but is not limited thereto. Additionally, the computing device 100 may recommend not only books but also cultural content such as movies and music suitable for the user's unique personality and psychological state.

A specific method of analyzing the user's psychological state using the obtained text and pictures and recommending a book suitable for the user based on the results of analyzing the psychological state will be described with reference to FIGS. 4 to 7.

Figure 4 is a diagram illustrating a method of analyzing a user's psychological state and recommending a book suitable for the user according to the first embodiment of the present invention.

Referring to FIG. 4, the computing device 100 can process the acquired text into natural language and analyze the meaning of the sentence (S210). As described above, the computing device 100 can process text obtained through NLP analysis in natural language and analyze the meaning of the sentence.

The computing device 100 may extract sentences containing emotions based on the analysis results (S211). The computing device 100 may extract a sentence containing an emotion from among a plurality of sentences, and extracting a sentence containing an emotion may be a sentence containing a word representing a pre-stored emotion or a sentence that semantically expresses an emotion. It may be extracting sentences.

The computing device 100 may analyze the user's psychological state based on the emotions included in the extracted sentence (S212). The computing device 100 may classify the emotions included in the sentence into a preset classification list. For example, the classification list may include depression, joy, stability, sadness, worry, etc., and emotions can be classified by determining the classification list to which the emotions included in the sentence correspond. That is, the computing device 100 can classify the emotions in the sentence using the results of analyzing the meaning of the words and sentences included in the sentence, and can analyze the user's psychological state based on the classified results. For example, among the classification lists, the list with the largest number of sentences may be determined to be the psychological state of the user. Meanwhile, the classification list is not limited to the listed list and may include a wider variety of psychological states, and it may also be possible to include only two lists, positive or negative. Additionally, the method of analyzing the user's psychological state based on the emotions included in the extracted sentence may not be limited to this.

The computing device 100 may extract similar readers who are analyzed as having a similar psychological state to the user among readers who have read a specific book (S213). The computing device 100 can obtain text and pictures about a book from several readers and analyze the psychological state of each reader using the text and pictures. The computing device 100 may match and store information about a reader whose psychological state has been analyzed for each book and a result of analyzing the reader's psychological state. Using this, the computing device 100 may extract as similar readers a user whose psychological state is similar to the user's psychological state as a result of analyzing the psychological state stored by matching the book read by the user. For example, the psychological state of readers analyzed through text and pictures about the emotions felt after reading a specific book is compared with the psychological state of users analyzed through text and pictures about the emotions felt after reading a specific book, and the user's psychological state is compared. Readers with the same psychological state as the psychological state can be extracted as similar readers.

The computing device 1000 may extract books read by similar readers (S214). The computing device 100 can extract books that have a history of obtaining text and pictures from similar readers, and further extract books that have a history of being searched by similar readers, books that have been purchased, and books of interest.

The computing device 100 may recommend the extracted book to the user (S215). On the other hand, there may be a large number of similar readers extracted, and if books read by a large number of similar readers are recommended, not only may too many books be recommended, but the possibility of recommending books that are not suitable for the user may also increase. .

Accordingly, the computing device 100 recommends to the user books that have a large overlap among books read by similar readers, books that are judged to have positive emotions after reading them by similar readers, or books that are judged to have positive emotions after reading them by similar readers. Among the books you have read, you can recommend books in fields that match your tastes. Additionally, the computing device 100 may recommend books by combining the book recommendation methods described above. For example, among books that similar readers have positive feelings about after reading them, books with a large number of overlaps from similar readers can be recommended to the user.

Figure 5 is a diagram illustrating a method of analyzing a user's psychological state and recommending a book suitable for the user according to a second embodiment of the present invention.

Referring to FIG. 5, the computing device 100 can provide the user with an event memory log that records events remembered after reading a book (S200), and receives answers to each item included in the event memory log from the user. Can be obtained (S221).

The event memory log is a record used to collect subjective metadata about the user's emotions and memories, including the title, date and time of occurrence, period, period of life, related (appearing) characters, emotions at the time, reasons for overall emotions, and evaluation from the current perspective. , it may include the reason for the evaluation from the current perspective, the motive of the incident, the impact on me currently, background space, related organizations, story content, and topic, and the computing device 100 provides information on each item included in the event memory log. Instructions for entering answers can be provided to the user. The user can enter answers to each item by following instructions provided by the computing device 100 through the user terminal 200.

For example, for the title item, the user can enter a title that describes the work, for the date of occurrence item, the user can enter the date and time when the actual experience (event) of the keyword in the work occurred, and for the period item, the user can enter a title that describes the work. You can enter the period that lasted from the beginning to the end of the experience (event), and select one of the following life period items: early childhood, middle childhood, adolescence, adult preparation, early adulthood, early middle age, late middle age, and late adulthood. You can enter it. At this time, the computing device 100 provides instructions to select at least one of early childhood, middle childhood, adolescence, adult preparation, early adulthood, early middle age, late middle age, and late adulthood, or provides a view of the life period, , it is possible to provide at least one instruction that can be input.

In addition, the user can enter the characters of the incident for the related (appearing) character items, and for the emotional items at the time, they can include hardship, sadness, anger, joy, love, happiness, joy, fear/horror, sorry, betrayal, etc. You can select at least one of these and enter it. At this time, the computing device 100 provides an instruction to select at least one of suffering, sadness, anger, joy, love, happiness, joy, fear/horror, sorry, betrayal, and others, or an instruction to input an emotion. can be provided.

In addition, the user can enter the reason for the user's feelings at the time for the experience (event) remembered for the overall emotional items, and the evaluation items from the current perspective can be success, failure, regret, joy, sadness, hardship, crisis, and opportunity. You can select and input at least one of , and others. At this time, the computing device 100 may provide an instruction for selecting at least one of success, failure, regret, joy, sadness, hardship, crisis, opportunity, and the like, or may provide an instruction for inputting an emotion.

In addition, the user can enter the reason for evaluating the event based on the current basis for the evaluation reason item from the current perspective, and for the motivation item of the event, jealousy, love, anger, deficiency, duty, recognition, compassion, curiosity, and achievement. You can select at least one of , vanity, coincidence, and other to enter. At this time, the computing device 100 provides an instruction to select at least one of jealousy, love, anger, deficiency, duty, recognition, compassion, curiosity, achievement, vanity, coincidence, and others, or an instruction to input an emotion. can be provided.

In addition, the user can enter the impact that the event had on me for the current impact item, enter the spatial background where the event occurred for the background space item, and enter the company, society, and affiliation for the related organization item. You can enter organizations, trends/alumni associations, etc., you can enter story content about actual events in the story content section, and you can enter topics about memory of events such as employment, marriage, school, fraud, etc. in the topic section. there is.

Based on the input answer, the computing device 100 may record events that occurred in each period of the user's life according to the preset life stage and create a life memory archive (S222). Preset life stages may include early childhood, middle childhood, adolescence, adult preparation, early adulthood, early middle age, late middle age, and late adulthood, and events that occurred in each life period can be recorded according to the user's answers. Here, the computing device 100 may additionally record answers to each item included in the event memory log obtained for various books in the life record archive.

Based on the user's lifetime memory archive, the computing device 100 may select similar readers with similar experience levels for events that occurred in each period of the user's life (S223).

The computing device 100 may select readers with experiences most similar to the user's lifetime memory archive as similar readers, based on lifetime memory archives created for each reader. The specific method of selecting similar readers will be explained in Figures 6 and 7.

The computing device 1000 may extract books read by similar readers (S224). The computing device 100 can extract books that have a history of obtaining text and pictures from similar readers, and also extract books that have a history of being searched by similar readers and books of interest.

The computing device 100 may recommend the extracted book to the user (S225). On the other hand, there may be a large number of similar readers extracted, and if books read by a large number of similar readers are recommended, not only may too many books be recommended, but the possibility of recommending books that are not suitable for the user may also increase. .

Accordingly, the computing device 100 recommends to the user books that have a large overlap among books read by similar readers, books that are judged to have positive emotions after reading them by similar readers, or books that are judged to have positive emotions after reading them by similar readers. Among the books you have read, you can recommend books in fields that match your tastes. Additionally, the computing device 100 may recommend books by combining the book recommendation methods described above. For example, among books that similar readers have positive feelings about after reading them, books with a large number of overlaps from similar readers can be recommended to the user.

Figure 6 is a diagram illustrating a method of selecting similar readers based on the user's lifetime memory archive according to the first embodiment of the present invention.

Referring to FIG. 6, the computing device 100 may determine characteristics for each life stage based on the user's lifetime memory archive (S2230). The computing device 100 may determine characteristics of each life stage based on experiences recorded for each life stage, and the characteristics of each life stage may indicate a psychological state. For example, characteristics such as joy, sadness, rebellion, stability, instability, worry, obsession, and confusion can be determined depending on experiences at each life stage. On the other hand, it may also be possible for the characteristics of each life stage to be determined to have multiple characteristics.

The computing device 100 may calculate the similarity between the user's experience and the reader's experience by comparing the user's life stage characteristics with the life stage characteristics determined based on the reader's life memory archive (S2232).

The computing device 100 may determine characteristics of each life stage, as performed in step S2230, based on the life memory archives of several readers. The computing device 100 can compare the characteristics of each user's life stage and the characteristics of each reader's life stage. Here, it may be desirable to compare the extracted features for each life stage, but the computing device 100 may compare only the extracted features. The computing device 100 can calculate a high degree of similarity for readers with similar characteristics by life stage, but is not limited to this. For example, if the user has characteristics of anger and rebellion in adolescence, the first reader has characteristics of anger and rebellion in adolescence, and the second reader has characteristics of anger and rebellion in adolescence, The similarity of the second reader may be calculated to be higher than that of the first reader. In addition, if the first reader has characteristics of anger and rebellion in the adult preparation period, and the second reader has characteristics of anger and rebellion in adolescence, the similarity of the second reader is higher than that of the first reader. can be calculated.

The computing device 100 may select the reader with the highest calculated similarity as a similar reader (S2234).

Figure 7 is a diagram illustrating a method of selecting similar readers based on a user's lifetime memory archive according to a second embodiment of the present invention.

Referring to FIG. 7, the computing device 100 may determine the type of event that occurred at each life stage based on the user's lifetime memory archive (S2231). The computing device 100 may determine the type of event that occurred in each life stage based on the recorded experience for each life stage, and the type of event that occurred in each life stage may mean the type of experience. For example, types of events that occurred at each stage of life may include study experiences, travel experiences, employment experiences, etc., and may further include experiences of being scolded, experiences of being praised, and experiences of fighting. On the other hand, it may also be possible to determine the types of each life stage to have multiple types.

The memories that users or readers recall after reading a book may be different. For example, when reading the same book, a first reader may recall an experience of being scolded, while a second reader may recall an experience of being praised. This may reflect the current psychological state. In the case of the first reader, negative memories may be recalled as the current psychological state is unstable, and in the case of the second reader, positive memories may be recalled as the current psychological state is stable. there is. Additionally, if your current psychological state is stable, you may react positively to past negative events even if you recall negative memories. In this way, determining the type of event that occurred by life stage for each user or reader can be an important factor in determining psychological state.

The computing device 100 may determine the user's tendency using the type of the determined event (S2233). For example, if there are many types of activities related to external activities, the user may be identified as having an extroverted tendency, and if there are many types of activities related to internal activities, the user may be identified as having an introverted tendency. In addition, if there are many types of goals, success, self-development, etc., the user can be understood as having a tendency to value social success, and if there are many types of dating, marriage, etc., the user can be understood as having a tendency to value marriage.

The computing device 100 may select similar readers who have similar tendencies to the user's tendencies among readers (S2235).

The computing device 100 determines the type of event that occurred in each life stage, as performed in step S2231, based on the lifetime memory archives of several readers, and uses the type of event as performed in step S2233. You can understand the user's tendencies. The computing device 100 can compare the user's propensity for each life stage with the reader's propensity for each life stage. The computing device 100 can calculate a high degree of similarity for readers who have tendencies similar to those of each life stage, but is not limited to this. For example, the user has an extroverted tendency and a tendency to value social success in the adult preparation stage. The first reader has an extroverted tendency in the adult preparation stage, and the second reader has an extroverted tendency and social success in the adult preparation stage. If one has a tendency to value , the similarity of the second reader may be calculated to be higher than that of the first reader. In addition, if the first reader has an extroverted tendency and a tendency for social success in early adulthood, and the second reader has an extroverted tendency and a tendency for social success in the adult preparation stage, the similarity of the second reader is the first reader. The similarity can be calculated to be higher than that of one reader.

The computing device 100 may select the reader with the highest similarity calculated as a similar reader, and may select readers up to a preset rank in order of high similarity as similar readers. However, the user's tendency and similar tendency may be selected as similar readers. The method of selecting similar readers is not limited to this.

As described above, according to an embodiment of the present invention, text and pictures about the emotions felt after reading a book are obtained from the user, and the obtained text and pictures are analyzed to recommend a book suitable for the user using psychological state information. Methods, devices and programs for providing intelligent book recommendation services can be realized.

Above, embodiments of the present invention have been described with reference to the attached drawings, but those skilled in the art will understand that the present invention can be implemented in other specific forms without changing its technical idea or essential features. You will be able to understand it. Therefore, the embodiments described above should be understood in all respects as illustrative and not restrictive.

100: computing device
200: user terminal
300: external server

Claims (10)

In a method performed by a computing device,
Obtaining text and pictures from the user about the emotions felt after reading the book;
Analyzing the user's psychological state using the obtained text and pictures; and
A method of providing an artificial intelligence book recommendation service using psychological state information, comprising: recommending a book suitable for the user based on a result of analyzing the psychological state.
According to paragraph 1,
The step of analyzing the user's psychological state is,
Processing the obtained text in natural language and analyzing the meaning of the sentence;
extracting sentences containing emotions based on the analysis results; and
A method of providing an artificial intelligence book recommendation service using psychological state information, including the step of analyzing the user's psychological state based on the emotions included in the extracted sentence.
According to paragraph 2,
The step of recommending a book suitable for the user is,
extracting similar readers who are analyzed as having a similar psychological state as the user from among readers who have read the book;
Extracting books read by the similar readers; and
Comprising: recommending the extracted book to the user,
The step of recommending the extracted book to the user is,
Among the books read by the similar readers, books with a large number of overlaps are recommended to the user, or books for which the similar readers read the books and are judged to have positive emotions are recommended to the user, or books read by the similar readers are recommended to the user. A method of providing an artificial intelligence book recommendation service using psychological state information, further comprising: recommending books in a field corresponding to the user's taste.
According to paragraph 1,
The step of analyzing the user's psychological state is,
Providing the user with an event memory log to record events remembered after reading the book;
Receiving answers for each item included in the event memory log from the user; and
Based on the inputted answer, recording events that occurred in each period of the user's life according to preset life stages to create a life memory archive; A method of providing an artificial intelligence book recommendation service using psychological state information, including.
According to paragraph 4,
The step of recommending a book suitable for the user is,
Based on the user's lifetime memory archive, selecting similar readers with similar experience levels for events that occurred in each period of the user's life;
Extracting books read by the similar readers; and
A method of providing an artificial intelligence book recommendation service using psychological state information, including the step of recommending the extracted book to the user.
According to clause 5,
The step of selecting similar readers with similar experience points is,
Determining characteristics of each life stage based on the user's lifetime memory archive;
Comparing the characteristics of each life stage of the user with characteristics of each life stage determined based on the readers' life memory archives, and calculating a degree of similarity between the user's experience and the readers'experience; and
A method of providing an artificial intelligence book recommendation service using psychological state information, including the step of selecting the reader with the highest calculated similarity as a similar reader.
According to clause 5,
The step of selecting similar readers with similar experience points is,
Determining the type of event that occurred at each life stage based on the user's lifetime memory archive;
Identifying the user's psychological state using the type of determined event; and
A method of providing an artificial intelligence book recommendation service using psychological state information, including the step of selecting a similar reader having a psychological state similar to that of the user among the readers.
According to paragraph 1,
The step of analyzing the user's psychological state is,
Extracting input data by determining the color, line thickness, object location, and object size of the acquired picture;
Inputting the input data into a previously learned artificial intelligence model;
Obtaining an output of the artificial intelligence model, and determining the psychological state of the user based on the output; A method of providing an artificial intelligence book recommendation service using psychological state information, including.
A memory that stores one or more instructions; and
A processor executing the one or more instructions stored in the memory,
The processor executes the one or more instructions,
An apparatus for performing the method of claim 1.
A computer program combined with a computer as hardware and stored on a computer-readable recording medium so as to perform the method of claim 1.