KR102719216B1 - Depression diagnosis system using artificial intelligence chatbot and method thereof - Google Patents

Abstract

A depression diagnosis system using an artificial intelligence chatbot according to an embodiment of the present invention includes: a depression keyword classification unit which classifies depression keywords from the text of a received message received through the chatbot; a depression question generation unit which generates a question message for a depression questionnaire item related to the depression keyword when the received message is classified as a depression keyword; a depression score calculation unit which calculates a depression score for the depression questionnaire item from the text of a response message to the question message; a depression analysis engine which provides a depression analysis result based on the calculated depression score; and a database including first artificial intelligence model data learned so that the depression keyword classification unit can classify the depression keyword, and second artificial intelligence model data learned so that the depression score calculation unit can calculate a depression score.

Description

Depression diagnosis system using artificial intelligence chatbot and its method {DEPRESSION DIAGNOSIS SYSTEM USING ARTIFICIAL INTELLIGENCE CHATBOT AND METHOD THEREOF}

The present invention relates to a depression diagnosis system using an artificial intelligence chatbot, and more specifically, to a depression diagnosis system and method thereof that uses a chatbot that applies natural language processing to identify the mental health status of a patient through everyday conversations with the patient, perform an accurate diagnosis of the patient, and generate data for appropriate treatment.

Digital therapeutics are technologies that use advanced software (mobile applications, games, virtual reality, chatbots, etc.) to prevent, manage, and treat diseases or disorders. In other words, digital therapeutics are used for the purpose of diagnosing, treating, alleviating, and preventing diseases. Digital therapeutics include various non-face-to-face treatment methods.

Digital therapeutics do not require manufacturing, transportation, and storage like general drugs, and can be easily supplied in large quantities at low cost. Therefore, the use of digital therapeutics can have the effect of reducing medical costs by allowing a small number of doctors to manage a large number of patients.

In addition, digital therapeutics are relatively free from the quarantine measures that must be considered during face-to-face treatment. Therefore, digital therapeutics can be used continuously for treatment, and related technology development is actively underway. Some countries have started to apply national health insurance for digital therapeutics related to mental illness, and commercialization has reached a point where some face-to-face treatment for mental illness has been replaced with digital therapeutics.

To take advantage of these digital therapeutics technologies, conventional techniques have been developed to utilize software to diagnose and treat patients.

For example, in diagnosing depression, the doctor determines the degree of the patient's mental illness through patient information (language characteristics, speaking habits, etc.). Treatment for depression is based on the patient's response to the doctor's specific questions (past mental illness, lifestyle habits, environment, etc.). Outpatient treatment for many patients with depression who are not hospitalized is conducted at intervals of one month or more, and the doctor in charge checks the mental health status of the patient with depression based on the questions for diagnosing depression and the patient's answers at each repeated outpatient treatment.

On the other hand, unlike hospitalized depression patients, outpatient depression patients have to wait for a doctor's diagnosis until the next visit. Therefore, it is more difficult for outpatient depression patients to receive accurate depression diagnosis and treatment from doctors than inpatient depression patients. If the depression patient can convey the mental health status of the depression patient in their daily life to the attending physician between outpatient visits, the attending physician can provide more effective treatment than existing treatment methods.

Therefore, for patients with depression, it is necessary to have a technology that collects the mental health status of the patient in daily life through various methods before and after the patient's visit to the hospital and provides the collected results to the patient's attending physician.

On the other hand, many patients diagnosed with mental illness have difficulty telling people around them about their medical history. In addition, some patients diagnosed with mental illness refuse to receive help from medical staff. On the other hand, if mental illness diagnosis and treatment can be done non-face-to-face, patients who do not receive continuous treatment can also participate in diagnosis and treatment, and more patients can receive treatment than when using existing diagnosis and treatment methods. Therefore, technology that provides various non-face-to-face treatment methods is needed.

Meanwhile, digital therapeutics are also being applied to the treatment of mental illnesses such as depression. Specifically, conversations between chatbots and people using natural language processing can induce natural conversations between patients with depression and healthy people.

In addition, there are clear differences in the language used by patients with depression from the language used by healthy people. For example, it has been found that patients with depression use first-person singular pronouns a lot. Since speakers unconsciously use pronouns, analyzing the linguistic characteristics of speakers with a focus on pronouns can help us understand the characteristics of speakers with depression.

Chatbots are suitable for ongoing patient care after face-to-face consultations between patients and medical staff, as they can be operated without idle time. They can also be used for mental health management for people who have not been diagnosed with depression.

If medical staff can identify the mental health status of individual patients between outpatient visits, identify changes, manage patients, and provide counseling via chatbots, they can induce accurate diagnosis and treatment for patients. Therefore, a mental illness diagnosis system using chatbots that apply natural language processing is in demand.

Korean Patent Publication No. 10-2021-0061126 (May 27, 2021) Korean Patent Publication No. 10-2175490 (2020.11.06.)

The technical problem to be solved by the present invention relates to a depression diagnosis system and method thereof.

More specifically, the present invention provides a depression diagnosis system that uses a chatbot that applies natural language processing and a method thereof to classify depression keywords, generate questions based on a depression assessment scale, and provide a depression diagnosis system that can objectively determine mental health status.

In addition, the technical task to be achieved by the present invention is to provide a depression diagnosis system that can support accurate diagnosis and treatment of individual depression patients by using the depression diagnosis system.

In addition, the technical task to be achieved by the present invention is to provide a depression diagnosis system that can provide mental health management not only to depressed patients but also to people who are unaware of their depression symptoms by using the depression diagnosis system.

The technical problems to be achieved by the present invention are not limited to the technical problems mentioned above, and other technical problems not mentioned can be clearly understood by a person having ordinary skill in the technical field to which the present invention belongs from the description below.

In order to achieve the above technical task, a depression diagnosis system using an artificial intelligence chatbot according to an embodiment of the present invention includes: a depression keyword classification unit which classifies a depression keyword from a text of a received message received through the chatbot; a depression question generation unit which generates a question message for a depression questionnaire item related to the depression keyword when the received message is classified as a depression keyword; a depression score calculation unit which calculates a depression score for the depression questionnaire item from a text of a response message to the question message; a depression analysis engine which provides a depression analysis result based on the calculated depression score; and a database including first artificial intelligence model data learned so that the depression keyword classification unit can classify the depression keyword, and second artificial intelligence model data learned so that the depression score calculation unit can calculate a depression score.

Here, the database may further include data for generating depression questionnaires including depression questionnaire items associated with the depression keyword.

In addition, the database may further include a depression questionnaire list data in which cumulative data on depression questionnaires is stored for each user who accessed the chatbot.

Here, the depression analysis engine provides a depression analysis result by additionally reflecting linguistic expressions related to depression in the received message, and the database may further include depression analysis engine data in which depression scale data corresponding to the linguistic expressions related to depression are stored.

Here, the depression questionnaire may be at least one of BDI, HAM-D, and PHQ-9.

According to one embodiment of the present invention, a method for diagnosing depression using an artificial intelligence chatbot comprises the steps of: activating the chatbot; receiving a message from a user terminal by the chatbot; classifying depression keywords in the received message;

The method comprises the steps of: generating a question message for a depression questionnaire item associated with the classified depression keyword; transmitting the generated question message to a user terminal; calculating a depression score from a text of a response message to the question message; and outputting a depression analysis result of the user based on the calculated depression score, wherein the depression keyword classification step uses first artificial intelligence model data learned to be able to classify the depression keyword from a message, and the depression score calculation step uses second artificial intelligence model data learned to be able to calculate a depression score from a message.

Here, the depression question message generation step can use data for generating depression questions including depression questionnaire questions associated with the depression keyword.

Additionally, the depression analysis result output step may additionally reflect linguistic expressions related to depression in the received message.

Here, the depression questionnaire may be at least one of BDI, HAM-D, and PHQ-9.

According to an embodiment of the present invention, a depression diagnosis system and method using a chatbot that applies natural language processing can be used to classify depression keywords, generate questions based on a depression assessment scale, and identify the mental health status of individual depression patients during the period between outpatient visits.

In addition, according to an embodiment of the present invention, an accurate diagnosis and treatment of individual depression patients can be performed using a depression diagnosis system using a chatbot.

Additionally, according to an embodiment of the present invention, mental health care can be provided not only to patients with depression but also to people who are unaware of their depression symptoms.

The effects of the present invention are not limited to the effects described above, and should be understood to include all effects that can be inferred from the composition of the invention described in the description or claims of the present invention.

FIG. 1 is a diagram illustrating an overview of a depression diagnosis system according to an embodiment of the present invention.
FIG. 2 is a block diagram illustrating the configuration of a depression diagnosis system according to an embodiment of the present invention.
FIG. 3 is a block diagram illustrating the configuration of a database according to an embodiment of the present invention.
FIG. 4 is a diagram illustrating a depression keyword sentence classification process by a depression keyword classification unit according to an embodiment of the present invention.
FIG. 5 is a diagram illustrating a message transmission process of a chatbot by a depression question generation unit according to an embodiment of the present invention.
FIG. 6 is a diagram illustrating a depression score calculation process by a depression score calculation unit according to an embodiment of the present invention.
Figure 7 is a flowchart illustrating a method for diagnosing depression using a chatbot according to an embodiment of the present invention.
FIG. 8 is a diagram illustrating transmitted and received messages of a BDI questionnaire-based chatbot according to an embodiment of the present invention.

Hereinafter, the present invention will be described with reference to the attached drawings. However, the present invention can be implemented in various different forms, and therefore is not limited to the embodiments described herein. In addition, in order to clearly describe the present invention in the drawings, parts that are not related to the description are omitted, and similar parts are assigned similar drawing reference numerals throughout the specification.

Throughout the specification, when a part is said to be "connected (connected, contacted, joined)" to another part, this includes not only cases where it is "directly connected" but also cases where it is "indirectly connected" with another member in between. Also, when a part is said to "include" a certain component, this does not mean that other components are excluded, unless otherwise specifically stated, but that other components can be included.

The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the present invention. The singular expression includes the plural expression unless the context clearly indicates otherwise. As used herein, the terms "comprises" or "has" and the like are intended to specify the presence of a feature, number, step, operation, component, part or combination thereof described in the specification, but should be understood to not exclude in advance the possibility of the presence or addition of one or more other features, numbers, steps, operations, components, parts or combinations thereof.

In this specification, a "module" includes a unit composed of hardware, software or firmware, and may be used interchangeably with terms such as logic, logic block, component, or circuit. A module may be an integrally composed component or a minimum unit or part thereof that performs one or more functions. For example, a module may be composed of an application-specific integrated circuit (ASIC).

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

Figure 1 illustrates an overview of a depression diagnosis system according to an embodiment of the present invention.

The depression diagnosis system (100) according to an embodiment of the present invention transmits and receives messages with a user terminal (10) through a chatbot (110), and the system (100) can derive depression analysis results based on the transmitted and received messages.

The depression diagnosis system (100) can be implemented in the form of a server or cloud, and is equipped with or connected to an artificial intelligence model, a database, a natural language processing engine, etc.

The chatbot (110) operates under the control of the depression diagnosis system (100), but is implemented and operated in various forms such as a messenger program, virtual character, or voice call program of the user terminal (10).

When a user conducts a daily conversation with a chatbot (110) via text or voice, the chatbot performs natural language processing to understand the user's conversation intention and guides the conversation for diagnosing depression.

In the conducted conversation, a depression score is calculated as an objective depression diagnosis indicator, and this is used as data for depression diagnosis and treatment.

Below, the configuration of the depression diagnosis system (100) is described in detail with reference to Fig. 2.

FIG. 2 is a block diagram illustrating the configuration of a depression diagnosis system according to an embodiment of the present invention.

As illustrated in FIG. 2, the depression diagnosis system (100) may include a chatbot (110), a depression keyword classification unit (120), a natural language response generation unit (130), a depression question generation unit (140), a depression score calculation unit (150), a depression analysis engine (160), and a database (170).

The depression diagnosis system (100) sends and receives messages to and from a user terminal (10) through a messenger app or a chatbot (110) that is a virtual character and means. The depression diagnosis system (100) can be implemented as a server that multiple users can access, a stand-alone device that provides dedicated access, or a cloud system.

The user terminal (10) may be a device equipped with a processor, memory, communication, and voice recognition functions, such as a smart phone, tablet PC, notebook PC, or desktop PC. Or, it may be a dedicated device equipped with a display, input, and voice recognition functions, a kiosk, or a POC (Clinical point of care) device.

Text and voice can be input into the user terminal (10). Voice input into the user terminal (10) can be converted into text-type data by a voice recognition function included in the user terminal (10).

The received message received from the user terminal (10) to the chatbot may be text. The received message may be received from the user terminal (10) to the chatbot (110). In addition, the transmitted message may be transmitted from the chatbot (110) to the user terminal (10).

The chatbot (110) can transmit received messages to the depression keyword classification unit (120) and the depression score calculation unit (150). In addition, the transmission messages can be transmitted from the natural language response generation unit (130) and the depression question generation unit (140) through the chatbot (110). In addition, the chatbot (110) can store the transmitted and received received messages in the database (170).

The depression keyword classification unit (120) may be implemented as a natural language processing (NLP) model that classifies received messages. Specifically, the depression keyword classification unit (120) may be implemented as a natural language processing model that classifies texts of received messages that are related to depression (texts that include depression keywords or depression questionnaire items or response items) and those that are not related to depression. The depression keywords may be classified using the first artificial intelligence model described below.

In addition, if the depression keyword classification unit (120) classifies the received message as being related to depression, it can forward the received message to the depression question generation unit (140). In addition, if the depression keyword classification unit (120) classifies the received message as not being related to depression, it can forward the received message to the natural language response generation unit (130).

The natural language response generation unit (130) may be implemented as a natural language processing model that generates a transmission message corresponding to a received message transmitted to the natural language response generation unit (130) and transmits it to the chatbot (110). Specifically, the transmission message generated by the natural language response generation unit (130) may be a response selected from predefined data that elicits everyday conversation and emotional empathy.

The depression question generation unit (140) may be implemented as a natural language processing model that generates a question corresponding to a depression-related received message transmitted to the depression question generation unit (140) and transmits it to the chatbot (110). Specifically, the question message generated by the depression question generation unit (140) may include a question extracted from a depression questionnaire of a depression assessment scale (BDI, HAM-D, PHQ-9, etc.) and a question that best matches the received message based on information in the received message.

The depression score calculation unit (150) can be implemented as a natural language processing model that calculates a depression score corresponding to a received message transmitted to the depression score calculation unit (150). Specifically, a depression assessment scale corresponding to a questionnaire response item of a depression assessment scale (BDI, HAM-D, PHQ-9, etc.) is classified from a response message to a question, and a calculated depression score is calculated based on the depression assessment scale.

The depression analysis engine (160) can determine the depression status of a received message by synthesizing the depression score transmitted to the depression analysis engine (160) and the message from the chatbot.

Specifically, the depression analysis engine (160) diagnoses the level of depression revealed in the linguistic expression of the received message and outputs the depression analysis result. For example, by utilizing the characteristic that people with depression use 'first-person singular pronouns' more frequently in their linguistic expressions than healthy people, the depression analysis engine (160) calculates the frequency of 'first-person singular pronouns' used in the received message to measure the level of depression. In this way, the depression analysis engine (160) can derive the depression analysis result by synthesizing the generated depression score and the characteristics of the linguistic expression.

FIG. 3 is a block diagram illustrating the configuration of a database according to an embodiment of the present invention.

Referring to FIG. 3, the database (170) may include natural language processing model data (171), depression questionnaire list data (172), and depression analysis engine data (173).

Natural language processing model data (171) may include natural language response data (171a), first artificial intelligence model data (171b), data for generating depression questions (171c), and second artificial intelligence model data (171d).

Natural language response data (171a) may include data that the natural language response generation unit (130) of Fig. 2 views for natural language processing. Specifically, natural language response data (171a) may include everyday conversation data and response data with emotional empathy.

The first artificial intelligence model data (171b) is data about the first artificial intelligence model that is learned so that the depression keyword classification unit (120) of Fig. 2 can classify keywords related to depression in received messages. The first artificial intelligence model data (171b) can be learned through depression questionnaire data, recorded data with depression patients, academic materials related to depression, etc., and it is possible to provide a numerical value of the relevance to depression based on the relationship between the keywords included in the received message and the preceding and following contexts.

Data (171c) for generating a depression question may include data that the depression question generating unit (140) of Fig. 2 views for natural language processing. Specifically, data (171c) for generating a depression question may include question data for questionnaire items or questionnaire items of a depression diagnosis scale associated with a depression keyword of a received message.

The second artificial intelligence model data (171d) is data about an artificial intelligence model learned so that the depression score calculation unit (150) of Fig. 2 can calculate a score for a depression diagnosis scale from a received message. The second artificial intelligence model data (171d) can be learned through a list of answers to depression questionnaire items, diagnosis results of patients with pre-diagnosed depression, recorded data with patients with depression, academic materials related to depression scores and statistics, etc. The depression score calculation unit (150) reads the second artificial intelligence model data (170d) for natural language processing of the received message, extracts terms, keywords, and phrases related to depression scores from the received message, and derives a correlation with questionnaire items for measuring the depression scale to calculate an accurate depression score.

The depression questionnaire list data (172) can store accumulated data on depression questionnaires for each user account that accessed through the chatbot. More specifically, the depression questionnaire list data (172) can store messages sent and received by the chatbot, calculated depression scores, and depression analysis results for each user.

Depression analysis engine data (173) is data that the depression analysis engine (160) of Fig. 2 views to output the depression analysis results, and data on the calculated depression score and linguistic expressions related to depression may be stored. For example, depression analysis engine data (173) may store depression scale data that matches the frequency of use of the 'first-person singular pronoun' in the received message.

FIG. 4 is a diagram illustrating a depression keyword classification process by a depression keyword classification unit according to an embodiment of the present invention.

As shown in Fig. 4, the depression keyword classification unit (120) can view the first artificial intelligence model data (171b) during the classification process of the received message. In addition, the depression keyword classification unit (120) can extract the psychological type of the received message when classifying the received message as being related to depression.

For example, as illustrated in FIG. 4, the depression keyword classification unit (120) can classify a received message as related to depression by reviewing the depression keywords stored in the first artificial intelligence model data (171b). Specifically, the depression keyword classification unit (120) can classify a received message as a message related to depression related to changes in sleep patterns.

FIG. 5 is a diagram illustrating a message transmission process of a chatbot by a depression question generation unit according to an embodiment of the present invention.

As shown in Fig. 5, the depression question generation unit (140) can view the depression question generation data (171c) during the process of generating the transmission message. For example, if a depression keyword related to sleep pattern change is detected in the received message, as shown in Fig. 5, the depression question generation unit (140) can extract a questionnaire related to sleep pattern change from among the depression questionnaire items stored in the depression question generation data (171c). The depression questionnaire items correspond to questions for the depression questionnaire, and the chatbot's question message can be implemented in the form of a question corresponding to the depression questionnaire items.

FIG. 6 is a diagram illustrating a depression score calculation process by a depression score calculation unit according to an embodiment of the present invention.

As shown in Fig. 6, the depression score calculation unit (150) can view the second artificial intelligence model data (170d) in the process of calculating the calculated depression score. In addition, the depression score calculation unit (150) can calculate the depression score of the received message corresponding to the response to the transmitted message. The depression score calculation unit (150) can classify the response message into positive, medium, weak negative, and strong negative using the second artificial intelligence model data (171d) and match them with the scores of the depression questionnaire items.

For example, as illustrated in FIG. 6, the depression score calculation unit (150) can classify the received message, “That’s right. I can’t sleep at all, I’m dying.” into “3: I sleep almost all day/I wake up 1-2 hours earlier than before and have difficulty falling asleep again” of the BDI sleep pattern change included in the depression questionnaire stored in the second artificial intelligence model data (171d) and calculate the depression score as 3 points.

Figure 7 is a flowchart illustrating a method for diagnosing depression using a chatbot according to an embodiment of the present invention.

In step (S101), the depression diagnosis system activates a chatbot in response to a request from a user terminal. The chatbot is activated by an application or various types of programs on the user terminal, and identifies personal information through the user's account information. \

When the chatbot is activated, the depression diagnosis system maintains a state in which it can receive messages from the user terminal. The depression diagnosis system can be implemented as a server that multiple users can access, a stand-alone device that provides dedicated access, or a cloud system. The chatbot is connected to a wired or wireless network. The depression diagnosis system sends and receives messages to and from the user terminal through the chatbot. Text and voice can be input to the user terminal. Voice input to the user terminal can be converted into text-type data by a voice recognition function included in the user terminal.

In step (S102), the chatbot receives a message from the user terminal. The received message received from the user terminal to the chatbot may be text. The received message may be related to depression or may not be related to depression. If the received message is not related to depression, the depression diagnosis system uses natural language response data to induce a continuous conversation. In addition, the chatbot transmits the received message to the depression keyword classification unit and the depression score calculation unit.

In step (S103), the depression keyword classification unit within the depression diagnosis system classifies messages and keywords related to depression from the text of the received message. As described above, the depression keywords can be classified using the first artificial intelligence model that has been learned in advance. If the depression keyword classification unit classifies the received message as related to depression, the depression keyword classification unit can transmit the corresponding received message and keywords to the depression question generation unit. The depression keyword classification unit can be implemented as a natural language processing model that classifies received messages related to depression among the received messages.

In step (S104), the depression question generation unit within the depression diagnosis system generates a question message corresponding to the depression-related received message transmitted to the depression question generation unit. The generated question message is transmitted to the chatbot by the depression question generation unit. The question message generated by the depression question generation unit may include questions extracted from depression questionnaire items of a depression assessment scale (BDI, HAM-D, PHQ-9, etc.) and questions for depression diagnosis based on information in the received message. Specifically, the process of generating a transmission message by the depression question generation unit may use questionnaire items for measuring a plurality of depression assessment scales pre-stored in a database or questions extracted from questionnaire items.

In step (S105), a question message generated by a depression question generation unit within a depression diagnosis system is transmitted from the depression question generation unit to a chatbot, and the transmitted question message is transmitted to a user terminal via the chatbot.

In step (S106), the chatbot stores the received and transmitted messages in a database. Specifically, the message data transmitted from the chatbot to the user terminal and the message data received from the user terminal to the chatbot are stored in the depression questionnaire list data of the database.

In step (S107), the depression score calculation unit within the depression diagnosis system calculates a depression score using a response message to a question generated by the depression question generation unit. The depression score calculation unit can be implemented as a natural language processing model, and uses a second artificial intelligence model that learns a correlation with a depression scale from the processed natural language.

Specifically, the depression score calculation unit matches the questionnaire items of a depression assessment scale (BDI, HAM-D, PHQ-9, etc.) with the processing results of the received message, and calculates a depression score based on the depression assessment scale of the matched questionnaire items.

In step (S108), the depression analysis engine within the depression diagnosis system synthesizes the depression score transmitted to the depression analysis engine, the received message of the chatbot, and the transmitted message to output the depression analysis result of the received message.

The depression analysis engine diagnoses the level of depression revealed in the linguistic expression of the received message and additionally reflects it in the depression analysis results. For example, by utilizing the characteristic that people with depression use 'first-person singular pronouns' more in their linguistic expressions than healthy people, the depression analysis engine can measure the level of depression by calculating the frequency of 'first-person singular pronouns' used in the received message and reflect it in the depression analysis results.

In step (S109), the depression analysis engine within the depression diagnosis system stores the depression analysis results in the database. In addition, the depression score calculation unit stores the calculated depression scores in the database. In addition, the received messages and transmitted messages between the chatbot and the user terminal may be stored in the database. Specifically, the database may store the depression analysis results, the calculated depression scores, the received messages, and the transmitted messages for each user account.

Additionally, the database may include natural language processing model data, depression questionnaire list data, and depression analysis engine data. The natural language processing model data of the database may store natural language response data, first artificial intelligence model data, depression question generation data, and second artificial intelligence model data.

FIG. 8 is a diagram illustrating an example of transmitted and received messages of a BDI questionnaire-based chatbot according to an embodiment of the present invention.

As illustrated in Fig. 8, the system (not shown) can diagnose the entire BDI questionnaire based on the transmitted and received messages of the BDI questionnaire-based chatbot and output the depression analysis results.

For example, as illustrated in Fig. 8, among the received messages, a message corresponding to 'BDI item diagnosis: sleep pattern change' can be classified, and among the received messages, a message corresponding to the emotion of 'BDI item diagnosis irritation' can be classified.

In this way, once the score calculation for the questions and answers generated for the BDI questionnaire items is completed, the system (not shown) can diagnose the entire BDI items and provide results or improvement measures for the same.

The method according to the embodiment of the present invention described above may be implemented in the form of program commands that can be executed through various computer components and recorded on a computer-readable recording medium. The computer-readable recording medium may include program commands, data files, data structures, etc., alone or in combination. The program commands recorded on the computer-readable recording medium may be specially designed and configured for the embodiment of the present invention, or may be known and usable to those skilled in the art of computer software. The computer-readable recording medium includes hardware configured to store and execute program commands, such as magnetic recording media such as hard disks, floppy disks, and magnetic tapes, optical recording media such as CD-ROMs and DVDs, magneto-optical media such as floptical disks, ROMs, RAMs, and flash memories. The program commands include machine language codes generated by a compiler and high-level language codes that can be executed on a computer using an interpreter. The hardware may be configured to operate as one or more software modules to process the method according to the present invention, and vice versa.

The method according to an embodiment of the present invention can be executed in an electronic device in the form of a program command. The electronic device includes a portable communication device such as a smart phone or a smart pad, a computer device, a portable multimedia device, a portable medical device, a camera, a wearable device, and a home appliance device.

The method according to an embodiment of the present invention may be provided as included in a computer program product. The computer program product may be traded between sellers and buyers as a product. The computer program product may be distributed in the form of a machine-readable recording medium or online through an application store. In the case of online distribution, at least a part of the computer program product may be temporarily stored or temporarily generated in a storage medium such as a memory of a manufacturer's server, an application store's server, or an intermediary server.

Each component according to an embodiment of the present invention, such as a module or a program, may be composed of one or more sub-components, and some of these sub-components may be omitted, or other sub-components may be further included. Some of the components (modules or programs) may be integrated into a single entity and may perform the same or similar functions performed by each of the corresponding components prior to integration. Operations performed by a module, program, or other component according to an embodiment of the present invention may be executed sequentially, in parallel, repeatedly, or heuristically, or at least some of the operations may be executed in a different order, omitted, or other operations may be added.

The above description of the present invention is for illustrative purposes, and those skilled in the art will understand that the present invention can be easily modified into other specific forms without changing the technical idea or essential characteristics of the present invention. Therefore, it should be understood that the embodiments described above are exemplary in all respects and not restrictive. For example, each component described as a single component may be implemented in a distributed manner, and likewise, components described as distributed may be implemented in a combined form.

The scope of the present invention is indicated by the claims set forth below, and all changes or modifications derived from the meaning and scope of the claims and their equivalent concepts should be interpreted as being included in the scope of the present invention.

10: User terminal 100: Depression diagnosis system
110: Chatbot 120: Depression Keyword Classification Department
130: Natural language response generation unit 140: Depression question generation unit
150: Depression Score Calculator 160: Depression Analysis Engine
170: Database 171: Natural Language Processing Model Data
171a: Natural language response data 171b: First artificial intelligence model data
171c: Data for generating depression questions 171d: Data for the second artificial intelligence model
172: Depression questionnaire list data 173: Depression analysis engine data

Claims (9)

In a depression diagnosis system using an artificial intelligence chatbot,
A depression keyword classification unit that classifies depression keywords from the text of a received message received through the above chatbot;
A depression question generation unit that generates a question message for a depression questionnaire item associated with the depression keyword when the above received message is classified as a depression keyword;
A depression score calculation unit for calculating a depression score for the depression questionnaire items from the text of the response message to the above question message;
A depression analysis engine that provides depression analysis results based on the depression scores calculated above; and
A database including first artificial intelligence model data learned so that the depression keyword classification unit can classify the depression keyword, and second artificial intelligence model data learned so that the depression score calculation unit can calculate a depression score;
The above depression analysis engine additionally reflects linguistic expressions related to depression in the received message and derives a depression analysis result by synthesizing the characteristics of the depression score and linguistic expressions.
The above database further includes depression analysis engine data storing depression scale data corresponding to linguistic expressions related to the above depression.
Depression diagnostic system. In the first paragraph,
The above database is,
A depression diagnosis system further comprising data for generating depression questionnaires including depression questionnaire items associated with the above depression keywords.
In the second paragraph,
The above database is,
A depression diagnosis system further including a depression questionnaire list data in which cumulative data on depression questionnaires for each user who accessed through the above chatbot is stored.
delete In the second paragraph,
A depression diagnosis system in which the above depression questionnaire is at least one of the BDI, HAM-D, and PHQ-9.
In a method for diagnosing depression using an artificial intelligence chatbot in a depression diagnosis system,
Steps to activate the above chatbot;
A step of receiving a message from a user terminal by the above chatbot;
A step of classifying depression keywords from the text of the received message;
A step of generating a question message for a depression questionnaire item associated with the above classified depression keywords;
A step of transmitting the generated question message to a user terminal;
A step of calculating a depression score from the text of a response message to the above question message; and
A step of outputting the user's depression analysis results based on the above-mentioned calculated depression score,
The above depression keyword classification step uses the first artificial intelligence model data learned to classify the depression keyword from the message.
The above depression score calculation step uses the second artificial intelligence model data learned to calculate the depression score from the message.
The above depression analysis output step additionally reflects linguistic expressions related to depression in the received message and synthesizes the depression score and the characteristics of the linguistic expressions to derive the depression analysis results.
The above depression diagnosis system includes a database including the first artificial intelligence model data, the second artificial intelligence model data, and depression analysis engine data in which depression scale data corresponding to linguistic expressions related to depression are stored.
How to diagnose depression.
In Article 6,
A depression diagnosis method, wherein the depression question message generation step uses data for generating a depression question including depression questionnaire items associated with the depression keyword.
delete In Article 7,
A method for diagnosing depression, wherein the above depression questionnaire is at least one of the BDI, HAM-D, and PHQ-9.

Images