KR102507811B1 - User psychology management system through chatbot service based on empathic psychology - Google Patents

Abstract

One embodiment of the present invention relates to a user psychology management system using a chatbot service based on empathic psychology, which provides a chatbot service based on empathic psychology to improve the psychology of a user and accordingly, manages the status of users through characters and provides technology enabling practical and targeted psychological counseling and improvement through interaction with a psychological counselor. The user psychology management system of the present invention comprises: an empathic sentence provision unit generating and providing corresponding sentences for user input sentences, which include response keywords matching the input keyword, a keyword included in the user input sentence, wherein the corresponding sentences generated by using an automatic sentence generation algorithm generating sentences related to topics based on empathic psychology are generated and provided; a character management unit outputting a character representing the user's psychological state according to the user input sentence on the user interface where the corresponding sentence is provided, wherein the character whose appearance is transformed according to user status information, including input keywords included in input sentences and user information in a pre-entered state is outputted to enable the user's psychological state to be recognized through the user interface; and a psychological improvement induction unit providing user status information to an agent account to provide management content for improving the user's psychological state on the user interface based on request information entered from the counselor account.

Description

User psychology management system through chatbot service based on empathy psychology

The present invention relates to a chatbot service capable of conducting non-face-to-face psychological counseling with users based on empathy psychology and a technology for managing the psychological state of users using the chatbot service. Technology that provides a chatbot containing sentences and contents that empathize with, provides a psychological treatment effect through forming a consensus with users, and at the same time enables interaction with psychological counselors and intuitively recognizes users' conditions It is about.

Recently, artificial intelligence chatbots are used in a wide variety of fields, such as answering user queries, automatic ordering, and translation. In particular, thanks to the development of natural language analysis algorithms, artificial intelligence chatbots or artificial intelligence systems capable of conversing with users while providing the same effect as talking to natural people are being released.

Recently, artificial intelligence chatbots are used in a wide variety of fields, such as answering user queries, automatic ordering, and translation. In particular, thanks to the development of natural language analysis algorithms, artificial intelligence chatbots or artificial intelligence systems capable of conversing with users while providing the same effect as talking to natural people are being released.

This is particularly efficiently used in voice recognition and conversation systems such as Siri, Google Assistant, and Bixby. Users can input their needs by voice and execute what they want or get desired information in a natural conversation format. there is.

On the other hand, these artificial intelligence chatbots are pointed out as having great potential for use in terms of using professional services, such as user health management, which users have been able to use by visiting experts such as counselors and medical staff. Previously, it was possible to visit a hospital or counseling center run by a psychological counselor, psychiatric medical staff, etc., or consult through a wired phone. Accordingly, it was impossible for users who did not have enough money and time to receive such psychological counseling. This is because when implemented as an intelligent chatbot, the burden of consuming such time and money is greatly reduced.

In response to this need, technologies for coaching and counseling on the health status of users using artificial intelligence in coaching and counseling are being released. For example, in Korean Registered Patent No. 10-2421643, etc., a counseling system and robots such as chatbots and apps are linked to analyze the user's interest in psychotherapy scenarios, and through this Add a process to motivate users Thus, a technique for increasing the effect of psychotherapy by maintaining interest in a psychotherapy scenario is provided to the user.

As mentioned above, this technology, such as an artificial intelligence chatbot for psychotherapy, has the advantage of greatly reducing the burden of time and cost for psychotherapy, but despite using natural language processing technology, it is possible to accurately There is a shortage in providing a technique that can be of practical help in relieving depression and stress by analyzing and using it to obtain the best psychotherapeutic effect for the user.

In addition, since it is simply a non-face-to-face service that can improve the psychological state, continuity with expert consultation is not guaranteed, and synergy between the psychological improvement effect using the service and the expert consultation effect is not achieved. There is a problem in that reliability is greatly deteriorated.

Accordingly, the present invention provides a chatbot service based on a psychotherapeutic method that can induce positive psychology by sympathizing with users' states and reactions based on empathy psychology, so as to be optimized for depression and stress, in particular, to improve the state of each user. The purpose is to provide a customized treatment method for the treatment, but to provide a technology that can maximize the effect of treatment by creating a positive atmosphere.

In addition, the present invention shares the state of psychological improvement using a chatbot with a professional counselor and provides various additional contents that can be used for counseling by a counselor, thereby synergizing the psychological improvement effect using a chatbot and the psychotherapeutic effect by professional counseling. The other purpose is to maximize the chatbot service as well as to induce the participation of professional counselors, thereby increasing the effect of psychotherapy and at the same time providing technology that induces activation of the market.

In order to achieve the above object, a user psychology management system through a chatbot service based on empathy psychology according to an embodiment of the present invention generates and provides a corresponding sentence for a user's input sentence, but includes an empathetic sentence providing unit that includes a response keyword matched to an input keyword that is a keyword and generates and provides a corresponding sentence generated using an automatic sentence generation algorithm that generates a sentence related to a topic based on empathy psychology; A character representing the user's mental state according to the user's input sentence is output on the user interface provided with the corresponding sentence, but according to the user state information including the input keyword included in the input sentence and the user information of the previously input state A character management unit for outputting a character whose appearance is deformed so as to recognize a user's psychological state through a user interface; and a psychological improvement induction unit providing the user state information to the counselor's account and providing management contents for improving the user's mental state on a user interface based on the requested information input from the counselor's account.

The sympathy sentence providing unit, among the user state information, as user information in a pre-input state, user input information for menus for grasping the user's psychological state provided through a user interface and a sensor of a user terminal Provides an initial sentence generated using the automatic sentence generation algorithm based on a response keyword matched to an initial user state keyword, which is a keyword representing the user's psychological state identified based on the user's facial image and voice information input through first step; a second step of providing a plurality of response-type sentences according to a user's input sentence with respect to the initial sentence; and a third step of providing a closing sentence based on a response keyword matching the keyword corresponding to the user state information when the number of times the user's input sentence is received reaches a predetermined threshold number. It is possible to provide the initial sentence, the response sentence, and the closing sentence as the corresponding sentences.

In the first step, the sympathy sentence providing unit, as a menu output through the user interface, a first keyword input through a keyword selection menu capable of selecting at least one of a plurality of keywords and an input menu capable of character input An image matched with the second keyword and at least one keyword determined to be related through a correlation analysis technique with the input text is output, and an image matched to the image selected through an image selection menu capable of selecting some of the output images. A third keyword, which is a keyword, a fourth keyword, which is a keyword derived by analyzing voice information, which is at least one of words included in the user's voice input through the voice input unit, tone, frequency, and speech tempo of the voice information, and image capturing means It is possible to derive a user state keyword using at least one of the fifth keywords, which are keywords derived as a result of analyzing the user's facial image captured through the emotion analysis algorithm.

The empathy sentence provider may perform a first process of managing association information between an input keyword and a response keyword based on matching information input from a plurality of preset expert accounts and a response included in a sentence previously provided by the empathy sentence provider According to the degree of improvement in the psychological state of the user included in the user state information, using the keyword and the numerical influence of the response keyword on the psychological state of the user derived using the change information of the user state information by time period It is possible to manage a matching relationship between the input keyword and the response keyword by at least one of the second processes for managing correlation values of the input keyword and the response keyword included in the state information.

The sympathetic sentence providing unit can generate a corresponding sentence using an automatic sentence generation algorithm capable of reflecting the LSTM-based contextual meaning to the word vector expression.

The character management unit changes any one of the expression, motion, color, and accessory of the character according to the user's state information, but the character's expression, motion, color type, and accessory for each type of psychological state according to the user's state information. It is possible to make any one of the size of the character's motion, color saturation or brightness, and the size of the accessory different depending on the type and the severity of the mental condition.

The character management unit, after a sympathetic sentence providing unit provides a sympathetic sentence on the user interface, when receiving an input sentence corresponding to the empathic sentence of the user, during the time when the empathic sentence that caused the input sentence and the input sentence are output, or It is to output a character whose appearance is transformed according to the empathy sentence that caused the input sentence and the user state information according to the input keyword identified by the empathy sentence that caused the input sentence and the input sentence to the area where the input sentence is output. possible.

The character management unit may output different characters for each type of user's psychological state.

The psychological improvement induction unit may provide information on a measured value and a change pattern of user status information for a predetermined period to the counselor account.

The psychological improvement induction unit includes, as the management content, at least first mission content suggesting the number of uses of the sympathetic sentence providing unit, second mission content suggesting the use of a service related to mental state improvement on-line, and the counselor account; It is possible to provide, as the management content, a menu for using content including any one of the third mission content that proposes a mental state improvement activity by the interaction of the user interface.

According to the present invention, the state of users is comprehensively analyzed through keywords selected by users, inputted sentences, selected images or voices, etc., and sentences based on empathy psychology having matching keywords are provided to users. In particular, while providing a number of sentences and closing comments to users step by step, based on empathy psychology, very positive sentences are selected for users or generated through natural language processing algorithms and provided.

In this case, compared to simple basic psychotherapeutic techniques, the effect of relieving depression and stress is greatly increased, and optimally targeted psychotherapeutic effects can be provided to these users, enabling psychological treatment of focused users. It works.

In addition, since very positive emotions can be accurately reflected in the generation and provision of sentences, it is possible to provide focused sentences based on empathy psychology.

In addition, since keyword matching and provision are provided based on users' reactions and psychological improvement status, it greatly helps to improve users' psychological status, and sentences are created to have a sentence structure that can accurately improve users' status when generating sentences. can be created, which has the effect of maximizing the psychotherapeutic effect.

On the other hand, according to the present invention, since users can intuitively check their psychological state, which changes while using sympathetic sentences, through a change in the appearance of the character, they can feel new fun in using the service, and can clearly see their state. Therefore, there is an effect of improving reliability and improving utilization rate by intuitively grasping the effect of using the corresponding service.

In addition, according to the present invention, changes in the mental state of users while using the service are provided to the professional counselor account, and various additional contents based on the requested information received from the counselor account are provided. Since the synergy between the improvement effect of the psychological state according to use and the improvement effect of the psychological state by the professional counselor is maximized, and a new target market is provided to the professional counselor, the chatbot service of the present invention as well as the participation of the professional counselor is encouraged. However, it has the effect of increasing the effect of psychotherapy and at the same time inducing the vitalization of the market.

1 is a block diagram of a user psychology management system through a chatbot service based on empathy psychology according to an embodiment of the present invention.
2 is a diagram for explaining the function of a user input analysis unit according to an embodiment of the present invention;
3 is a diagram for explaining an example in which voice input is analyzed according to an embodiment of the present invention;
4 is a diagram for explaining the function of a keyword derivation unit according to an embodiment of the present invention;
5 is a diagram for explaining detailed functions of a sympathetic sentence providing unit according to an embodiment of the present invention;
6 and 7 are views for explaining the function of the character management unit according to an embodiment of the present invention.
8 is a diagram for explaining an example in which user state information is provided to a counselor account according to an embodiment of the present invention;
9 is a diagram for explaining an example in which management content is output to a user interface according to an embodiment of the present invention.
10 is an example of an internal configuration of a computing device according to an embodiment of the present invention.

In the following, various embodiments and/or aspects are disclosed with reference now to the drawings. In the following description, for purposes of explanation, numerous specific details are set forth in order to facilitate a general understanding of one or more aspects. However, it will also be appreciated by those skilled in the art that such aspect(s) may be practiced without these specific details. The following description and accompanying drawings describe in detail certain illustrative aspects of one or more aspects. However, these aspects are exemplary and some of the various methods in principle of the various aspects may be used, and the described descriptions are intended to include all such aspects and their equivalents.

References to “embodiment,” “example,” “aspect,” “example,” etc., used in this specification should not be construed as indicating that any aspect or design described is preferable to or advantageous over other aspects or designs. .

Also, the terms "comprises" and/or "comprising" mean that the feature and/or element is present, but excludes the presence or addition of one or more other features, elements and/or groups thereof. It should be understood that it does not.

In addition, terms including ordinal numbers such as first and second may be used to describe various components, but the components are not limited by the terms. These terms are only used for the purpose of distinguishing one component from another. For example, a first element may be termed a second element, and similarly, a second element may be termed a first element, without departing from the scope of the present invention. The terms and/or include any combination of a plurality of related recited items or any of a plurality of related recited items.

In addition, in the embodiments of the present invention, unless otherwise defined, all terms used herein, including technical or scientific terms, are those commonly understood by those of ordinary skill in the art to which the present invention belongs. have the same meaning. Terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with the meaning in the context of the related art, and unless explicitly defined in the embodiments of the present invention, an ideal or excessively formal meaning not be interpreted as

1 is a configuration block diagram of a user psychology management system through a chatbot service based on empathy psychology according to an embodiment of the present invention, and FIG. 2 is a diagram for explaining the function of a user input analysis unit according to an embodiment of the present invention. 3 is a diagram for explaining an example in which voice input is analyzed according to an embodiment of the present invention. 4 is a diagram for explaining the function of a keyword derivation unit according to an embodiment of the present invention, FIG. 5 is a diagram for explaining detailed functions of a sympathetic sentence providing unit according to an embodiment of the present invention, FIGS. 6 and 7 is a diagram for explaining the function of a character management unit according to an embodiment of the present invention, FIG. 8 is a diagram for explaining an example in which user state information is provided to a counselor account according to an embodiment of the present invention, and FIG. It is a diagram for explaining an example in which management content is output to a user interface according to an embodiment of the present invention. In the following description, one or more of the above drawings may be simultaneously referred to for detailed description of various embodiments and respective components of the present invention.

Based on the above description, the user psychology management system (10, hereinafter referred to as 'the system of the present invention') through a chatbot service based on empathy psychology according to an embodiment of the present invention is a sympathetic sentence providing unit (11 ), a character management unit 12 and a psychological improvement induction unit 13.

The system 10 of the present invention will be described as a separate configuration that works with the user terminal 20 and the database 30 in FIG. 1 . However, in various embodiments of the present invention, the system 10 of the present invention is configured to be included in the user terminal 20 and transmits and receives data performed according to the embodiment mentioned in the function of the present invention with a remote database 30 Alternatively, while the system 10 of the present invention interworks with the database 30 to configure a server that exists remotely from the user terminal 20, the user terminal 20 and data are transmitted through the interface of the user terminal 20. It can be configured to transmit and receive.

Based on this description, the sympathetic sentence providing unit 11, as shown in the drawings, generates and provides a corresponding sentence for the user's input sentence, but matches the input keyword, which is a keyword included in the user's input sentence. It performs a function of generating and providing a corresponding sentence generated using an automatic sentence generation algorithm that includes the given response keyword and generates a sentence related to a subject based on empathy psychology.

In the present invention, the user's input sentence is a group of interfaces including a plurality of menus and screens output by an online website, an application or software that is accessed to perform the function of the present invention in the user terminal 20. It refers to text-type input data received through a user's input through a menu output on a user interface.

In the user's input sentence, keywords are derived according to the structure of the sentence through a sentence analysis algorithm. This is referred to as an input keyword, and the input keyword includes a noun included in a user's input sentence or a keyword corresponding to emotion information derived through a sentiment analysis algorithm for the input sentence.

Sentiment analysis is a process of analyzing subjective information such as opinions, emotions, evaluations, and attitudes contained in text through a computer. Sentiment analysis consists of two main steps. The first step is to define which part of the document (sentence) contains an opinion (Opinion definition). Next, the opinions gathered through the first stage are summarized (Opinion summerization).

The methodology of sentiment analysis can be divided into lexicon-based sentiment analysis and ML-based sentiment analysis. Each method can be divided into more detailed methods, and recently, a transformer-based neural network model such as BERT has been widely used.

Through this, when an input keyword is derived, the sympathetic sentence providing unit 11 uses an automatic sentence generation algorithm that generates a sentence related to the subject based on empathy psychology based on the above-described corresponding sentence including a response keyword matched thereto, and uses the user interface. to be output in the form of an answer to the user's input sentence.

For example, automatic sentence generation algorithms can be described by being divided into passive algorithms and active algorithms.

The passive algorithm filters and provides sentences including response keywords in the form of a sentence bank generated and stored in advance by expert accounts, or includes response keywords among a large number of sentences already existing online and inputs keywords. and a process of generating matching sentences as corresponding sentences.

For example, among a plurality of sentences stored online, after crawling sentences related to improvement for each psychological state of the user, select and provide sentences including response keywords, but if the response keyword is selected from among the plurality of crawled sentences A process of selecting included sentences as candidate sentences is performed.

Afterwards, a sentence sentiment analysis algorithm based on empathy psychology is applied to the positive-negative state information of the sentence derived through the natural language processing algorithm for the candidate sentence, and the sentence that is judged to cause positive sympathy for the user's state among the candidate sentences It means the process of selecting as the final response sentence.

With the development of neuroscience, research results on cognitive psychology or the psychology of empathy are continuously being published. Joachim Bauer approaches from the psychiatric aspect and discovers 'mirror neurons' to enable emotional resonance with others. In order to know the intentions of the people around you, you can mobilize intuitive knowledge and provide a clue to understanding the phenomenon of sharing the joy and pain of others through empathy psychology.

This empathy psychology also includes the subject of positive psychology, which is a field of psychology that has recently been attracting attention to study the strengths and advantages that prosper individuals and societies. Research is being conducted to make a general life more fulfilling than just treating mental illness. In other words, positive psychology is more about medical conditions or clinical processes in the context that life for oneself and life for others in the same direction contributes to human life. It is a branch of psychology that places more importance on the development of individual spontaneous abilities.

Positive psychologists have suggested several ways in which personal happiness can be promoted. While social ties with spouse, family, friends, and wider networks through work, community, or social organization are particularly important, physical exercise and the practice of meditation can also contribute to happiness. Happiness in this context can increase, even if it stagnates as no further economic gains arise, or even if financial income declines.

Deriving keywords based on empathy psychology is a process performed for the purpose of empathizing with the subject's psychology and continuously giving positive stimulation to it. That is, for example, when a user condition keyword 'decline' is derived, keywords such as 'satisfaction', 'achievement', and 'rewarding', which are keywords judged to have an improvement effect, are derived as response keywords.

An active algorithm refers to an algorithm that automatically generates a sentence related to a topic from the beginning based on a response keyword, in addition to the above-described passive sentence selection algorithm.

For example, the sympathetic sentence providing unit 11 determines the priority of improving the psychological state of semantic information for each response keyword according to the arrangement order for each keyword derived through keyword analysis processing for a plurality of existing sentence information on-line. perform the function of This means the same process as the process of the same name for determining the output order of sentences in the above-described embodiment.

Thereafter, a plurality of sentences including response keywords are generated in a predetermined order through a natural language processing algorithm, but based on empathy psychology, the composition frame of the sentence set by the expert account and the emotional condition information of the sentence are applied to the natural language processing algorithm A process of generating a plurality of sentences is performed through a sentence generation algorithm.

The sentence generation algorithm is a natural language processing algorithm, and may include, for example, a sentence generation algorithm through an LSTM-based language learning model. In this case, an LSTM-based sentence generation algorithm capable of automatically generating sentences in consideration of the subject of the document may be used through a model capable of reflecting the contextual meaning of words in word vector representation. At this time, when considering the subject of the document, it is possible to set various themes for empathy and positive psychology.

For example, a many-to-one model is used to reflect the contextual information of a word, and a document vector can be additionally learned and used together with a word to reflect the subject of a document. Then, as described above, sentences are generated through the LSTM-based language learning model. At this time, word vectors are influenced by document vectors, so word expression according to the subject becomes possible.

Thereafter, a process of controlling the generated sentences to be output through the output unit of the user terminal 20 as corresponding sentences according to the order of the sentences determined by the above process is performed.

Meanwhile, the above passive algorithm and active algorithm may be used independently or in combination with each other. When used in combination, the active algorithm is preferentially applied so that the sentence provided by the active algorithm is stored in a space included in the online space that is the criterion for sentence selection in one embodiment, and the sentences stored in the online space When the number reaches a predetermined threshold number (eg, 10,000), a passive algorithm is applied, and other embodiments are continuously provided, but first provided to the counselor terminal 40, feedback from the expert account, and online By being stored in the space, it can be processed into a sentence that can be used in one embodiment.

According to various embodiments of the present invention, the state of users is comprehensively analyzed through keywords selected by users, inputted sentences, selected images or voices, etc., and sentences based on empathy psychology having matching keywords are provided to users. will do In particular, while providing a number of sentences and closing comments to users step by step, based on empathy psychology, very positive sentences are selected for users or generated through natural language processing algorithms and provided.

In this case, compared to simple basic psychotherapeutic techniques, the effect of relieving depression and stress is greatly increased, and optimally targeted psychotherapeutic effects can be provided to these users, enabling psychological treatment of focused users. It works.

In addition, since very positive emotions can be accurately reflected in the generation and provision of sentences, it is possible to provide focused sentences based on empathy psychology.

In addition, since keyword matching and provision are provided based on users' reactions and psychological improvement status, it greatly helps to improve users' psychological status, and sentences are created to have a sentence structure that can accurately improve users' status when generating sentences. can be created, which has the effect of maximizing the psychotherapeutic effect.

Meanwhile, in the present invention, corresponding sentences may be provided in a step-by-step structure for psychotherapy. For example, it may include an initial sentence for opening users' minds in starting psychological treatment, a response sentence according to users' full-fledged input sentences, and a closing sentence for finalizing psychological improvement.

At this time, as shown in FIG. 5, the sympathetic sentence providing unit 11 grasps the user's psychological state provided through the user interface as the user information D1 of the previously input state among the above-described user state information. Based on the response keyword matched to the initial user state keyword, which is a keyword representing the user's psychological state identified based on the user's input information for menus and the user's facial image and voice information input through the sensor of the user terminal. As a result, the first step (S10) of providing an initial sentence generated using the automatic sentence generation algorithm (SG) is first performed to provide an initial sentence (S11).

At this time, as user information in a pre-input state in the user state information, the user's input information, face image, voice information, etc. can be grasped through FIGS. 2 and 3 .

For example, as shown in FIG. 2 , an initial user state keyword is derived using at least one of the first to fifth keywords.

The first keyword is an interface for receiving user input and analyzing the user's psychological state, and is selected and input through the keyword selection menu 110 from which one of a plurality of keywords can be selected from among menus output through the user interface. A first keyword may be received. That is, the first keyword is a menu from which one of the user state keywords can be selected through the interface. At this time, a plurality of candidate keywords output to the keyword selection menu 110 may be specified according to step-by-step selection. That is, the keyword selection menu 110 may be provided as a group of menus for step-by-step selection so that keywords corresponding to higher concepts and lower concepts are embodied.

Alternatively, in the present invention, the second keyword is a keyword that is determined to be related to text input through the input menu 100 capable of text input through a correlation analysis technique. At this time, the second keyword may also function as one of the first to fourth keywords for deriving the user state keyword, but instead of performing a plurality of steps of selecting the first keyword, the selectable first keyword corresponding to the user state keyword It can also be used as a keyword that derives the mental state of a higher concept that filters 1 keyword.

At this time, the correlation analysis technique is an analysis algorithm that derives a keyword closest to the correlation between words and keywords included in the sentence through vector analysis between texts. For example, an association analysis algorithm between words through text mining may be used in the present invention, and an association analysis algorithm between various keywords may also be used.

Text mining is a tool for extracting and analyzing useful information from text data in electronic documents such as web pages, blogs, electronic journals, and e-mails. , text mining refers to an area in which various fields such as data mining, natural language processing, and information retrieval are converged.

In the text mining technique, the technique used as an algorithm for analyzing the association between words of the present invention is word cloud (extraction of main keywords), cluster analysis (cluster analysis between similar words (or documents) (community analysis)), Network analysis (extraction of related words or word network analysis), topic model (topic analysis, topic analysis) / topic trend analysis, outlier analysis (anormality), spam mail detection, plagiarism analysis (calculation of document similarity), classification The process of assigning a document to a predetermined subject is used.

When analysis data are crawled online or received directly from an administrator's terminal, analysis data are prepared by collecting them, and a corpus (a set of texts that form a structure in linguistics is used for statistical analysis, hypothesis verification, and language rule inspection). It is used in e.g., the corpus is usually composed of electronic documents), and after that, through the preprocessing process, the processing of stopwords, the processing of redundant words, etc. is performed, and then the correlation between words is analyzed through analysis of these.

In the present invention, the analysis of the correlation between keywords can be processed by integrating various online sites, but as described above for a plurality of online sites and spaces previously determined by the administrator terminal as they affect the psychological state of users, such as psychological treatment and video content. It can be performed by preparing the analysis data of

For example, when a user inputs the sentence "I'm in a cloudy mood today" through the input menu 100, for example, judged as various candidate keywords related to keywords such as "cloudy" and "mood" Keywords such as 'joy', 'sadness', 'anger', and 'surprise' are output to the keyword selection menu 110 as candidate keywords for the first keyword, or the keyword 'decline' with the highest correlation among them is selected as a candidate keyword for the first keyword. As the second keyword, it may be selected for derivation of the user state keyword.

In the present invention, the second keyword may be used as a filtering criterion for the first keyword as described above, and may also be used for selection of a third keyword to be described later. As shown in FIG. 2 , the third keyword means a keyword matched to an image selected through the image selection menu 120 capable of outputting images matched with at least one keyword and selecting some of the output images.

Since the third keyword is also selected through the same process as the first keyword, except that it is different in image selection, a selection menu is provided step by step as mentioned in the description of the first keyword, or the second keyword as described above. If some keywords are selected in advance by , images matched with detailed sub-keywords belonging thereto may be output through the image selection menu 120 .

Meanwhile, the fourth keyword means a keyword derived by analyzing the user's voice information 130 input through the voice input means. At this time, the fourth keyword may be generated by extracting candidate keywords of a plurality of user status keywords through a more detailed analysis algorithm.

For example, as shown in FIG. 3, when the user's voice information 130 is analyzed to derive the fourth keyword, the user's voice information 130 is obtained through, for example, sound to text conversion. 2 The keyword is converted into the same sentence 131 as the target of analysis, and accordingly, a number of keywords (K2) are derived through the analysis algorithm of the second keyword, that is, the word association analysis algorithm, or the user's standard voice frequency and input stored in advance The keyword K3 may be derived based on the user's emotional state analysis result through the frequency spectrum analysis derived through the comparison of the input voice frequency 132 derived through the frequency analysis of the generated voice.

In this case, the emotional state analysis through voice frequency analysis refers to analysis such as tone, pitch, and formant frequency analysis of the voice signal. Pitch refers to the pitch of a sound when a person hears it with the ear, or one cycle of a voiced sound that represents a periodic waveform. Just as human language has sociality, emotions in language also have sociality, so it is possible to grasp the person's emotions based on the pitch of language.

The formant frequency refers to a frequency at a position where certain overtones are strengthened among partial sounds and is referred to as a formant including frequencies in its vicinity. Accordingly, the change in frequency is linked to the change in energy distribution, and when a change in emotion occurs, a physical/physiological change occurs and a change in formant occurs in a chain, so analysis of this can also be used for emotion analysis. .

On the other hand, since frequency analysis means analyzing changes in frequency over time, detailed analysis of speech speed, tone, sound quality, words, etc., including the pitch and formant frequency analysis in a narrow sense, It will be appreciated that it can be used in the analysis of (130).

Meanwhile, the fifth keyword refers to a keyword derived as a result of analyzing a user's facial image captured through an image capture means such as a camera of the user terminal 20 through an emotion analysis algorithm.

An emotion analysis algorithm is an algorithm that infers a user's emotion from a user's facial image included in image data. An algorithm that infers can be used.

For example, algorithms for recognizing emotions using facial images using TensorFlow models and deep learning models, algorithms for extracting facial regions using fuzzy color filters, and facial component extraction using virtual face models Algorithm, facial image analysis, feature vector extraction and pattern recognition, fuzzy classifier method based on fuzzy theory suitable for emotion analysis, landmark detection of image through Active Appearance Model, and emotion by movement and change of other landmarks in facial expression bias The techniques for classifying may be used independently or in combination with each other.

When the first to fifth keywords are derived through the above process, one or more keywords representing the user's state are derived through frequency analysis or similarity and grouping analysis, and the above-described user state keyword will derive

On the other hand, when the initial sentence is provided, the sympathetic sentence providing unit 11 generates the response type sentence S12 by the above-described automatic sentence generation algorithm SG according to the user input sentences S21 and S22 for the initial sentence. , S13) is performed in the second step (S20) of providing a plurality of times. For this, the above-described active or passive algorithm is used, and a sentence is generated through the association information between the input keyword and the response keyword included in the input sentence. The correlation value between the input keyword and the response keyword is as shown in FIG. Managed by examples.

As shown in FIG. 4, the keyword derivation unit determines user status keywords (K1, K2, K3) and response keywords (M1, M2, M3) based on matching information input from the terminal 40 used by a plurality of preset expert accounts. , M4) of the user derived using the response keyword included in the sentence previously provided by the empathic sentence providing unit 13 and the time-specific change information of the user state keyword By at least one of the second processes for managing the correlation value between the user state keyword and the response keyword according to the degree of improvement of the user's psychological state included in the user state keyword using the influence value of the response keyword on the psychological state The related keyword derivation algorithm 300 may be managed.

The first process refers to a process of analyzing the correlation between user state keywords and response keywords based on user feedback and expert review results on keywords periodically performed by the administrator terminal 40 .

On the other hand, the second process, as shown in Figure 4, based on the result of analyzing the history information 400, that is, the improvement information of users' psychological states according to the use of the sentence previously provided by the sympathetic sentence providing unit 13 , means a feedback-based automation process that automatically manages correlation values according to improvement information for each user status keyword among response keywords.

In order to specifically perform the second process, the sympathetic sentence providing unit 11, for example, after providing the above-described response sentence, reacquires user state information of the user, and derives improved information about the user's psychological state. can do. The improvement information is used to determine to what extent the psychological state of the user has improved by using correlation information or error information between the user state keyword after using the corresponding sentence and the user state keyword used to provide the sentence. means information.

Thereafter, a function of managing the relevant keyword derivation algorithm is performed by updating the association relationship between the user status keyword and the response keyword based on the derived improvement information. That is, the above-described second process is directly performed.

When the second step (S20) is performed, the sympathetic sentence providing unit 11 performs the step S20, that is, when the number of times the user's input sentence is received reaches a preset threshold number, the user state re-measured at that time point. The final one-time psychological counseling process is completed by performing a third step (S30) of providing the closing sentence (S1(n+1)) based on the response keyword matched to the keyword corresponding to the information (S2n).

Through this, as a response sentence optimized for the user's state, there is an effect of automatically performing a scenario treatment step that can improve the user's psychological state.

On the other hand, the character management unit 11 outputs a character representing the user's psychological state according to the user's input sentence on a user interface provided with a corresponding sentence, but input keywords included in the input sentence and user information in a previously input state. It performs a function of recognizing the user's psychological state through the user interface by outputting a character whose appearance is deformed according to the included user state information.

For example, a character output area 600 as shown in FIG. 6 may exist on the user interface, and preferably, the character output area 600 exists near the output area of the response sentence and the output area of the input sentence. It would be preferable to allow the user to intuitively recognize the user's psychological state.

A character implemented as a human face is expressed through the character output area 600, and the character is expressed according to the current user's psychological state through facial expression 601, color 602, and accessory 603 elements. can be implemented

For example, the character's facial expression 601, motion, color type 602, and accessory 603 are different for each type of psychological state according to the user's state information, and the character's movement depends on the severity of the mental state. Any one of the size, color saturation or brightness, and the size of the accessory can be changed.

Meanwhile, as described above, the purpose of positioning the character output area 600 near the area where input sentences and corresponding sentences are output is to allow users to intuitively check their psychological state and use sympathetic sentences. Intuitively recognizing the effect of using such empathic sentences allows the user to immediately recognize the effect of improving the psychological state according to the use of empathetic sentences, thereby maximizing the synergistic effect of improving the psychological state of users, Users' reliability of the service provided by the system 10 of the present invention can be greatly improved.

To this end, in one embodiment of the present invention, the character management unit 12 receives an input sentence corresponding to the empathy sentence provided on the user interface by the empathy sentence providing unit, the cause of the input sentence User status information according to the input keyword identified by the sympathetic sentence and the input sentence that caused the input sentence in the area where the empathic sentence and the input sentence that caused the input sentence are output during the time when the sympathetic sentence and the input sentence are output Therefore, it is possible to output a character whose appearance is deformed.

In addition, as shown in FIG. 7, characters 611 having completely different appearances are output for each type 610 of mental state, so that users can more clearly understand what state they are in. can do.

Meanwhile, the psychological improvement induction unit 13 provides the user state information identified as described above to the counselor account, and provides management contents for improving the user's mental state on the user interface based on the request information input from the counselor account. perform a function

For example, when the psychological improvement induction unit 13 uses the plurality of corresponding sentences for each scenario provided by the sympathetic sentence providing unit 11, the corresponding corresponding sentence and detailed information on the input sentence are sent to the counselor terminal 40. , so that the counselor can analyze the psychological state of the user account in detail.

In addition, understanding the degree of change in the psychological state over time is also more important than understanding the psychological state at a specific point in time. To this end, the psychological improvement induction unit 13 may provide the counselor's account with information on the measurement value and change pattern of the user's state information for a predetermined period. For example, as shown in FIG. 8 , on the screen 620 output to the counselor terminal 40, user state information 621 indicating the type and degree of the psychological state of the user U1 and the user state A change trend 622 over time of the information may be provided. At this time, a plurality of user state information 621 and change trend 622 may be provided for each mental state type as shown in FIG. 8 .

On the other hand, as described above, the psychological improvement induction unit 13 not only provides the user's psychological state to the counselor's account, but also improves the user's psychology by providing empathic sentences and synergistically to improve interaction with the counselor more effectively. Contents related to coaching can be provided as feedback to the user account.

For example, as shown in FIG. 9 , the psychological improvement inducer 13 may provide management content to a user account through a user interface. Through the management screen 630 of management content, users can check and use the management content by using the request information input by the counselor's account, that is, selection information about the management content to improve the user's psychology.

Management content includes, for example, first mission content (M1) suggesting the number of uses of the sympathetic sentence providing unit, second mission content (M2) suggesting the use of a service related to online mental state improvement, and the counselor account and It may include any one of the third mission contents (M3) suggesting a mental state improvement activity by the interaction of .

Users check the type 631 and main content 632 of the management content through the screen 630, and check the use of the previously performed management content and use it in detail through the menu 633 to check whether each management content is used or not. can be performed.

10 illustrates an example of an internal configuration of a computing device according to an embodiment of the present invention, and in the following description, descriptions of unnecessary embodiments overlapping with those of FIGS. 1 to 9 will be omitted. do it with

As shown in FIG. 10, a computing device 10000 includes at least one processor 11100, a memory 11200, a peripheral interface 11300, an input/output subsystem ( It may include at least an I/O subsystem (11400), a power circuit (11500), and a communication circuit (11600). In this case, the computing device 10000 may correspond to a user terminal connected to the tactile interface device (A) or the aforementioned computing device (B).

The memory 11200 may include, for example, high-speed random access memory, magnetic disk, SRAM, DRAM, ROM, flash memory, or non-volatile memory. there is. The memory 11200 may include a software module, a command set, or other various data necessary for the operation of the computing device 10000.

In this case, access to the memory 11200 from other components, such as the processor 11100 or the peripheral device interface 11300, may be controlled by the processor 11100.

Peripheral interface 11300 may couple input and/or output peripherals of computing device 10000 to processor 11100 and memory 11200 . The processor 11100 may execute various functions for the computing device 10000 and process data by executing software modules or command sets stored in the memory 11200 .

Input/output subsystem 11400 can couple various input/output peripherals to peripheral interface 11300. For example, the input/output subsystem 11400 may include a controller for coupling a peripheral device such as a monitor, keyboard, mouse, printer, or touch screen or sensor to the peripheral interface 11300 as needed. According to another aspect, input/output peripherals may be coupled to the peripheral interface 11300 without going through the input/output subsystem 11400.

The power circuit 11500 may supply power to all or some of the terminal's components. For example, power circuit 11500 may include a power management system, one or more power sources such as a battery or alternating current (AC), a charging system, a power failure detection circuit, a power converter or inverter, a power status indicator or power It may contain any other components for creation, management and distribution.

The communication circuit 11600 may enable communication with another computing device using at least one external port.

Alternatively, as described above, the communication circuit 11600 may include an RF circuit and transmit/receive an RF signal, also known as an electromagnetic signal, to enable communication with another computing device.

The embodiment of FIG. 10 is just one example of the computing device 10000, and the computing device 11000 may omit some components shown in FIG. 10, further include additional components not shown in FIG. It may have a configuration or arrangement combining two or more components. For example, a computing device for a communication terminal in a mobile environment may further include a touch screen or a sensor in addition to the components shown in FIG. , Bluetooth, NFC, Zigbee, etc.) may include a circuit for RF communication. Components that may be included in the computing device 10000 may be implemented as hardware including one or more signal processing or application-specific integrated circuits, software, or a combination of both hardware and software.

Methods according to embodiments of the present invention may be implemented in the form of program instructions that can be executed through various computing devices and recorded in computer readable media. In particular, the program according to the present embodiment may be configured as a PC-based program or a mobile terminal-only application. An application to which the present invention is applied may be installed in a user terminal through a file provided by a file distribution system. For example, the file distribution system may include a file transmission unit (not shown) that transmits the file according to a request of a user terminal.

The device described above may be implemented as a hardware component, a software component, and/or a combination of hardware components and software components. For example, devices and components described in the embodiments may include, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate array (FPGA), It may be implemented using one or more general purpose or special purpose computers, such as a programmable logic unit (PLU), microprocessor, or any other device capable of executing and responding to instructions. A processing device may run an operating system (OS) and one or more software applications running on the operating system. A processing device may also access, store, manipulate, process, and generate data in response to execution of software. For convenience of understanding, there are cases in which one processing device is used, but those skilled in the art will understand that the processing device includes a plurality of processing elements and/or a plurality of types of processing elements. It can be seen that it can include. For example, a processing device may include a plurality of processors or a processor and a controller. Other processing configurations are also possible, such as parallel processors.

Software may include a computer program, code, instructions, or a combination of one or more of the foregoing, which configures a processing device to operate as desired or processes independently or collectively. You can command the device. Software and/or data may be any tangible machine, component, physical device, virtual equipment, computer storage medium or device, intended to be interpreted by or to provide instructions or data to a processing device. may be permanently or temporarily embodied in Software may be distributed on networked computing devices and stored or executed in a distributed manner. Software and data may be stored on one or more computer readable media.

The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer readable medium. The computer readable medium may include program instructions, data files, data structures, etc. alone or in combination. Program instructions recorded on the medium may be specially designed and configured for the embodiment, or may be known and usable to those skilled in computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks and magnetic tapes, optical media such as CD-ROMs and DVDs, and magnetic media such as floptical disks. - includes hardware devices specially configured to store and execute program instructions, such as magneto-optical media, and ROM, RAM, flash memory, and the like. Examples of program instructions include high-level language codes that can be executed by a computer using an interpreter, as well as machine language codes such as those produced by a compiler. The hardware devices described above may be configured to operate as one or more software modules to perform the operations of the embodiments, and vice versa.

As described above, although the embodiments have been described with limited examples and drawings, those skilled in the art can make various modifications and variations from the above description. For example, the described techniques may be performed in an order different from the method described, and/or components of the described system, structure, device, circuit, etc. may be combined or combined in a different form than the method described, or other components may be used. Or even if it is replaced or substituted by equivalents, appropriate results can be achieved. Therefore, other implementations, other embodiments, and equivalents of the claims are within the scope of the following claims.

Claims (10)

A user psychology management system through a chatbot service based on empathy psychology implemented as a computing device including one or more processors and one or more memories storing commands executable by the processors,
An automatic sentence generation algorithm that generates and provides corresponding sentences to the user's input sentences, includes response keywords matched to the input keywords included in the user's input sentences, and generates sentences related to the subject based on empathy psychology. An empathetic sentence providing unit for generating and providing a corresponding sentence generated by using;
A character representing the user's mental state according to the user's input sentence is output on the user interface provided with the corresponding sentence, but according to the user state information including the input keyword included in the input sentence and the user information of the previously input state A character management unit for outputting a character whose appearance is deformed so as to recognize a user's psychological state through a user interface; and
A psychological improvement induction unit providing the user state information to the counselor account and providing management contents for improving the user's psychological state on a user interface based on the request information input from the counselor account;
The empathy sentence providing unit,
Among the user state information, as user information in a pre-input state, the user's input information for menus for grasping the user's psychological state provided through the user interface and the user's face input through the sensor of the user terminal A first step of providing an initial sentence generated using the automatic sentence generation algorithm based on a response keyword matched to an initial user state keyword, which is a keyword representing a user's psychological state identified based on video and audio information;
a second step of providing a plurality of response-type sentences according to a user's input sentence with respect to the initial sentence; and
A third step of providing a closing sentence based on a response keyword matching the keyword corresponding to the user status information when the number of times the user's input sentence is received reaches a predetermined threshold number; Providing an initial sentence, a response sentence, and a closing sentence as the corresponding sentences;
The character management department,
Any one of the expression, motion, color, and accessory of the character is deformed according to the user state information,
Depending on the type of psychological state according to the user's state information, the character's expression, motion, color type, and accessory type are different. A user psychology management system through a chatbot service based on empathy psychology, characterized in that one changes.
delete According to claim 1,
The empathy sentence providing unit,
In the first step,
As a menu output through the user interface, a first keyword input through a keyword selection menu capable of selecting at least one of a plurality of keywords, a text input through an input menu capable of character input, and a correlation analysis technique a second keyword that is determined to be at least one keyword, a third keyword that is a keyword matched to an image selected through an image selection menu that outputs images matched with at least one keyword and selects some of the output images, and inputted through a voice input means A fourth keyword, which is a keyword derived by analyzing at least one of the words included in the user's voice, the tone, frequency, and speed of speech information of the voice information, and the user's facial image captured through the video recording means, using an emotion analysis algorithm. A user psychology management system through a chatbot service based on empathy psychology, characterized in that a user state keyword is derived using at least one of the fifth keywords, which are keywords derived as a result of analysis through the analysis.
According to claim 1,
The empathy sentence providing unit,
A first process for managing association information between input keywords and response keywords based on matching information input from a plurality of preset expert accounts, response keywords included in sentences provided by the sympathy sentence providing unit, and the user state Input included in the user state information according to the degree of improvement in the user's psychological state included in the user state information, using the influence value of the response keyword on the user's psychological state derived using the change information by time period of the information A user psychology management system through a chatbot service based on empathy psychology, characterized in that for managing the matching relationship between the input keyword and the response keyword by at least one of the second processes for managing the correlation value of the keyword and the response keyword.
According to claim 1,
The empathy sentence providing unit,
A user psychology management system through a chatbot service based on empathy psychology, characterized by generating corresponding sentences using an automatic sentence generation algorithm that can reflect LSTM-based contextual meaning to word vector expression.
delete According to claim 1,
The character management department,
After the empathy sentence providing unit provides the empathy sentence on the user interface, when receiving the corresponding input sentence from the user, during the time when the empathy sentence that caused the input sentence and the input sentence are output, or the cause of the input sentence Empathy psychology characterized by outputting a character whose appearance is transformed according to user state information according to the input keyword identified by the empathy sentence that caused the input sentence and the input sentence in the area where the empathy sentence and the input sentence are output. User psychology management system through based chatbot service.
According to claim 1,
The character management department,
A user psychology management system through a chatbot service based on empathy psychology, characterized in that different characters are output for each type of user's psychological state.
According to claim 1,
The psychological improvement induction unit,
User psychology management system through a chatbot service based on empathy psychology, characterized in that for providing information on the measurement value and change pattern of user state information during a predetermined period to the counselor account.
According to claim 1,
The psychological improvement induction unit,
As the management content,
At least the first mission contents suggesting the number of times of use of the sympathetic sentence providing unit, the second mission contents suggesting the use of services related to mental state improvement online, and the mental state improvement activity by interaction with the counselor's account. A user psychology management system through a chatbot service based on empathy psychology, characterized in that for providing a menu for using content including any one of the third mission content to the user interface as the management content.

Images