Artificial intelligence-based non-face-to-face psychological counseling service method through virtual character and system using the same

An AI-driven virtual character system addresses the challenges of high costs and accessibility in non-face-to-face counseling by establishing rapport and providing effective psychological counseling for children and adolescents, especially during outbreaks.

KR103042754B1Active Publication Date: 2026-11-06최인혁
View PDF 1 Cites 0 Cited by

Patent Information

Application Number
KR1020240010582
Authority / Receiving Office
KR · KR
Patent Type
Patents
Current Assignee / Owner
Priority Date
2023-01-25
Filing Date
2024-01-24
Publication Date
2026-11-06
Estimated Expiration
2044-01-24

AI Technical Summary

Technical Problem

Existing non-face-to-face psychological counseling services face challenges such as high costs, limited accessibility, and ineffective rapport-building due to personnel shortages, making it difficult to meet the increasing demand for non-face-to-face psychological counseling, especially for children and adolescents during outbreaks like COVID-19.

Method used

An AI-based non-face-to-face psychological counseling service mediated by a virtual character that generates a virtual character from user input, analyzes user responses and facial expressions using machine learning, and connects with professional counselors for effective counseling.

Benefits of technology

Provides high-quality, cost-effective psychological counseling by establishing rapport through virtual characters, effectively alleviating anxiety and treating depression in children, adolescents, and other demographics through AI-driven psychological analysis.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 112024009124848-PAT00003_ABST
    Figure 112024009124848-PAT00003_ABST
Patent Text Reader

Abstract

The present invention relates to an artificial intelligence-based non-face-to-face psychological counseling service method mediated by a virtual character and a system utilizing the same. A virtual character is generated from a drawing made directly by a user and reproduced on the display of a user terminal. Using the virtual character as a medium, artificial intelligence infers and determines the user's current psychological and emotional state based on the user's facial expressions and answers to pre-prepared questions.
Need to check novelty before this filing date? Find Prior Art

Description

Technology Field

[0001] The present invention relates to an artificial intelligence-based non-face-to-face psychological counseling service method mediated by a virtual character and a system using the same. Background Technology

[0002] The demand for non-face-to-face psychological counseling is surging. The demand for such services increases even more during outbreaks of infectious diseases like COVID-19. In particular, depression among children and adolescents has recently been increasing rapidly due to stress and anxiety.

[0003] Although there is a method for providing non-face-to-face psychological counseling via telephone, it could not meet demand due to a lack of personnel and infrastructure. Furthermore, existing non-face-to-face psychological counseling services were not easily accessible because they were expensive due to various incidental costs, and effective counseling outcomes could not be provided because it was difficult to build rapport between the counselor and the client. The problem to be solved

[0004] The present invention aims to solve the aforementioned necessities and / or problems.

[0005] The present invention provides an artificial intelligence-based non-face-to-face psychological counseling service method mediated by a virtual character that enables the provision of high-quality non-face-to-face counseling services using artificial intelligence (AI), and a system using the same.

[0006] The problems of the present invention are not limited to those mentioned above, and other problems not mentioned will be clearly understood by those skilled in the art from the description below. means of solving the problem

[0007] A method for an artificial intelligence-based non-face-to-face child psychological counseling service according to an embodiment of the present invention comprises: a step of generating a virtual character from a drawing directly drawn by a user and reproducing it on a display of a user terminal, and generating a voice signal corresponding to the virtual character and outputting it through a speaker of the user terminal; and a step of outputting a question through the user terminal via the virtual character, and inferring and determining the user's current psychological state and emotional state using machine learning that interprets the answer content obtained based on the user's voice signal received through the microphone of the user terminal and the user's facial expression obtained based on a video captured through the camera of the user terminal.

[0008] The above artificial intelligence-based non-face-to-face child psychological counseling service method may further include the step of transmitting a user's psychological analysis model, which reflects the user's current psychological and emotional states, to a professional counselor's terminal; and the step of conducting psychological counseling using the virtual character reproduced on the user terminal as a medium while the professional counselor's terminal and the user terminal are connected.

[0009] The above artificial intelligence-based non-face-to-face child psychological counseling service method may further include the step of providing at least one of a virtual world experience service, a PC game, and a mobile game through the user terminal. It may further include the step of providing when the virtual world experience service is executed so that the user's avatar enters a play space in the virtual world.

[0010] An artificial intelligence-based non-face-to-face child psychological counseling service system according to one embodiment of the present invention includes: a user terminal comprising a processor that executes an application for providing non-face-to-face psychological counseling services, the user terminal including a camera, a microphone, and a speaker; and a server that provides questions to the user terminal and infers and determines the user's current psychological state and emotional state received through the user terminal.

[0011] The above artificial intelligence-based non-face-to-face child psychological counseling service system may further include a terminal of a professional counselor that receives the user's psychological analysis model from the server and conducts psychological counseling using the virtual character reproduced on the user terminal while connected to the user terminal.

[0012] The above server can provide at least one of a virtual world experience service, a PC game, and a mobile game through the above user terminal.

[0013] The server may include a Natural Language Generation (NLG) module and a Text-to-Speech (TTS) module connected to the speaker of the user terminal; a face / expression recognition module and a computer vision module connected to the camera of the user terminal; and a Speech-to-Text (STT) module and a Natural Language Understanding (NLU) module connected to the microphone of the user terminal. The server may input features and labels indicating the user's expression input from the computer vision module and features and labels of the user's response input from the NLU module into the machine learning, and infer and determine the user's current psychological state and emotional state based on the results learned by the machine learning. Effects of the invention

[0014] According to an embodiment of the present invention, high-quality psychological counseling services can be provided at a low cost to meet the rapidly increasing demand for non-face-to-face psychological counseling based on artificial intelligence (AI) technology.

[0015] The present invention enables psychological analysis and appropriate treatment based on the results through a non-face-to-face app service, thereby effectively alleviating rapidly increasing anxiety symptoms and stress.

[0016] The present invention enables effective psychological analysis by artificial intelligence and obtains highly accurate psychological analysis results by generating a psychological analysis model of the interviewee after inducing rapport formation through a virtual character drawn or selected by the interviewee receiving psychological counseling, and then analyzing the interviewee's facial expressions and responses using artificial intelligence.

[0017] This invention can effectively analyze and treat depression, which becomes more severe during the spread of infectious diseases, through non-face-to-face psychological analysis mediated by friendly virtual characters. In particular, it is effective for alleviating anxiety symptoms and stress, and treating depression in children, adolescents, people with disabilities, patients, and the elderly.

[0018] The effects of the present invention are not limited to those mentioned above, and other unmentioned effects will be clearly understood by those skilled in the art from the description in the claims. Brief explanation of the drawing

[0019] FIG. 1 is a block diagram showing an artificial intelligence-based non-face-to-face psychological counseling service system according to one embodiment of the present invention. Figure 2 is a diagram showing the signal flow of the system illustrated in Figure 1. FIG. 3 is a flowchart illustrating an artificial intelligence-based non-face-to-face psychological counseling service method according to one embodiment of the present invention. Figure 4 is a diagram showing a question / answer processing device in an artificial intelligence-based non-face-to-face psychological counseling service system. Figure 5 is a diagram showing an example of a method for generating a psychoanalysis model using machine learning. Figure 6 is a diagram showing the steps of an artificial intelligence-based non-face-to-face psychological counseling service. FIGS. 7A and FIGS. 7B are drawings showing an example of a preliminary stage of the reception interview illustrated in FIGS. 6. Figures 8a and 8b are drawings showing an example of the play therapy steps illustrated in Figure 6. Figure 9 is a diagram showing an example of the consultation step illustrated in Figure 6. Specific details for implementing the invention

[0020] The advantages and features of the present invention and the methods for achieving them will become clear by referring to the embodiments described below in detail together with the accompanying drawings. The present invention is not limited to the embodiments disclosed below but may be implemented in various different forms; the embodiments are provided merely to ensure that the disclosure of the present invention is complete and to fully inform those skilled in the art of the scope of the invention, and the present invention is defined only by the scope of the claims.

[0021] The shapes, sizes, ratios, angles, numbers, etc. disclosed in the drawings for explaining embodiments of the present invention are exemplary, and therefore the present invention is not limited to the matters shown in the drawings. Throughout the specification, the same reference numerals refer to substantially the same components. Furthermore, in describing the present invention, detailed descriptions of related prior art are omitted if it is determined that such detailed descriptions may unnecessarily obscure the essence of the present invention.

[0022] Where terms such as “comprising,” “including,” “having,” “consisting of,” etc. are used in this specification, other parts may be added unless “~ only” is used. Where a component is expressed in the singular, it may be interpreted as plural unless specifically stated otherwise.

[0023] In interpreting the components, they are interpreted to include a margin of error even in the absence of a separate explicit statement.

[0024] Where positional and interconnected relationships are described between two components, such as 'on', 'above', 'below', 'next to', 'connect or couple', or 'crossing or intersecting', one or more other components may be interposed between those components unless otherwise noted, such as 'immediately' or 'directly'.

[0025] When temporal sequences are described using 'after', 'following', 'next', 'before', etc., they may not be continuous on the time axis unless 'immediately' or 'directly' is used.

[0026] First, second, etc. may be used to distinguish components, but the function or structure of these components is not limited by the ordinal number or component name preceding the component.

[0027] The following embodiments may be combined or combined with one another, either partially or wholly, and may technically enable various interlocking and operation. Each embodiment may be implemented independently of one another or together in an associated relationship.

[0028] In the following embodiments, the 'user' may be a child, adolescent, person with a disability, patient, elderly person, etc., for whom psychological counseling mediated by a virtual character is highly effective.

[0029] Hereinafter, various embodiments of the present invention will be described in detail with reference to the attached drawings.

[0030] FIG. 1 is a block diagram showing an artificial intelligence-based non-face-to-face child psychological counseling service system according to an embodiment of the present invention. FIG. 2 is a diagram showing the signal flow of the system illustrated in FIG. 1.

[0031] Referring to FIGS. 1 and 2, an artificial intelligence-based non-face-to-face child psychological counseling service system according to one embodiment of the present invention includes a server (200) connected to a user terminal (100) via the internet.

[0032] The user terminal (100) is a terminal that can be used by a user receiving a non-face-to-face psychological counseling service. The user terminal (100) is connected to a camera, microphone, speaker, communication module, display module, etc., and may be a terminal including a processor capable of running an application or software, such as a PC, smartphone, laptop, smart TV, etc. The user terminal (100) runs a non-face-to-face child psychological counseling service application received from the server (200) to create an AR virtual character, and asks a pre-set question to the user through the virtual character, and transmits the user's facial expression information along with the answer received from the user to the server (200).

[0033] The server (200) provides a non-face-to-face child psychological counseling service application to the user terminal (100). Based on the answers and facial expression information received from the user terminal (100), the server (200) generates a psychological analysis model that reflects the user's current psychological and emotional state using machine learning to learn the user's psychology. Machine learning includes deep learning. The server (200) can provide a virtual world experience service, such as a metaverse, in conjunction with the non-face-to-face child psychological counseling service application. The server (200) is connected to a database. The database can store pre-set question information and store user-specific psychological analysis models received from the server (200).

[0034] The server (200) transmits the result of the user's psychological analysis model (primary conclusion of psychological problem) obtained using machine learning to the professional counselor's terminal (300), and the professional counselor's terminal (300) can be connected to the user terminal (100) via the internet. The professional counselor conducts non-face-to-face psychological counseling by referring to the result of the psychological analysis model. The professional counselor is reproduced on the display of the user terminal (100) through a virtual character created or selected by the user, and the professional counselor's voice can also be modulated into a voice signal suitable for the virtual character and output through the speaker of the user terminal (100).

[0035] The communication module of the user terminal (100) can perform data communication with the server (200) using Wireless LAN (WLAN), Wi-Fi, Wireless Broadband (Wibro), World Interoperability for Microwave Access (Wimax), High Speed ​​Downlink Packet Access (HSDPA), IEEE 802.16, Long Term Evolution (LTE), Wireless Mobile Broadband Service (WMBS), etc. The communication module may further include Bluetooth, RFID (Radio Frequency Identification), Infrared Data Association (IrDA), Ultra Wideband (UWB), Zigbee, Near Field Communication (NFC), etc. The communication means may additionally support short-range communication methods such as USB communication, Ethernet, serial communication, and optical / coaxial cables, and may further include a communication module for providing location-based services, for example, a GPS (Global Positioning System) module.

[0036] The display module of the user terminal (100) may include at least one of a display such as a Liquid Crystal Display (LCD) or an Organic Light-Emitting Diode (OLED) display. The display module visually reproduces a virtual character created using Augmented Reality (AR) technology.

[0037] The camera of the user terminal (100) photographs the user's face to interpret the user's facial expression. The microphone of the user terminal (100) converts the voice signal into an electrical signal to interpret the user's answer, and the speaker converts the electrical signal into a voice signal to output the question to the user as a voice signal.

[0038] FIG. 3 is a flowchart illustrating an artificial intelligence-based non-face-to-face child psychological counseling service method according to an embodiment of the present invention. This service method can be performed by a non-face-to-face child psychological counseling service application running on a user terminal (100) and a server (200) linked thereto.

[0039] Referring to FIG. 3, the non-face-to-face child psychological counseling service method begins when a non-face-to-face counseling request is received. First, a virtual character is created from a drawing made by the user on a user terminal (100) or a server (200), or a virtual character selected by the user from among pre-set virtual characters is created (S1). The virtual character can be created as an augmented reality (AR) character and is created on the display of the user terminal (100).

[0040] Next, a reception interview is conducted using a virtual character (S2). During the reception interview, the user terminal (100) outputs questions for psychological analysis to the user in voice through the virtual character, receives answers to each question, converts them into digital signals, and transmits video data of the user's face captured in real time to the server (200). The server (200) generates a psychological analysis model of the user by interpreting the user's answers and facial expressions using machine learning.

[0041] As a result of interpreting the user's response and facial expression, if the credibility of the user's response is low or the user's anxiety level is high, a play therapy step may be performed (S3). In the play therapy step (S4), the user terminal (100) may enter a virtual world experience service, such as a metaverse, and provide the user with various play experience services in the virtual world to lower the user's anxiety level. In another embodiment, the play therapy step (S4) may run PC games and mobile games designed to obtain psychotherapy effects on the user's terminal (100).

[0042] When play therapy is finished, the server (200) connects the professional counselor's terminal (300) to the user terminal (100). The professional counselor is visually reproduced on the display of the user terminal (100) as a virtual character created in step S1, and the professional counselor's voice can be modulated and output as a voice suitable for the virtual character. In this way, the professional counselor conducts non-face-to-face psychological counseling for the user through the user terminal (100) using the virtual character as a medium (S5). Based on the professional counselor's judgment, the professional counselor may determine the psychological treatment method for the user as needed. For example, the professional counselor may request the server (200) to execute steps S3 and S4 to conduct play therapy for the user.

[0043] Figure 4 is a diagram showing a question / answer processing device in an artificial intelligence-based non-face-to-face child psychological counseling service system. Figure 5 is a diagram showing an example of a method for generating a psychological analysis model using machine learning.

[0044] Referring to FIGS. 4 and 5, the question / answer device includes a speaker, camera, and microphone of a user terminal (100), a Natural Language Generation (NLG) module and a Text To Speech (TTS) module connected to the speaker of the user terminal (100), a face / expression recognition module and a Computer Vision module connected to the camera of the user terminal (100), and a Speech To Text (STT) module and Natural Language Understanding (NLU) connected to the microphone of the user terminal (100).

[0045] The NLG module converts pre-set question keywords into natural language sentences, and the TTS module converts the natural language sentence text data generated by the NLG module into speech signals and outputs them to the speaker. The face / expression recognition module recognizes faces and expressions in user images received from the camera. The computer vision module generates feature points from the user's face and expression images. The STT module converts speech signals into text data. The NLU module interprets the text data from the STT module to generate answer data containing semantic information of the user's response.

[0046] Machine learning generates a current psychological analysis model of the user based on a learned psychological model, receiving features and labels indicating the user's facial expressions input from the computer vision module and features and labels of the user's response input from the NLU module. Here, the features and labels represent the user's voice response to a question and the facial expression interpretation results, as shown in the example of Fig. 5.

[0047] A user's psychological analysis model generated from machine learning may include primary psychological analysis results classified in detail in biological factors, psychological factors, social factors, and cultural and religious factors, respectively, as shown in the example of Fig. 5.

[0048] Figure 6 is a diagram showing the steps of an artificial intelligence-based non-face-to-face child psychological counseling service.

[0049] Referring to Fig. 6, the artificial intelligence-based non-face-to-face child psychological counseling service method can proceed in the order of the intake interview pre-stage, intake interview stage, play therapy stage, and counseling stage.

[0050] The pre-introduction interview stage includes a virtual character creation stage (S1) in Fig. 3, which can enhance the effectiveness of psychological counseling by forming rapport between the user and the virtual character. Since the virtual character is a virtual character created from a drawing made by the user, for example, a child, or a virtual character selected by the child, it can reduce the user's anxiety and stress before psychological counseling. For example, the virtual character may be an AR animal character.

[0051] The intake interview stage is a process of obtaining an AI-based primary psychological analysis model using machine learning as illustrated in Figs. 4 and 5. In the intake interview stage, pre-prepared examples of questions, such as those shown in Fig. 5, are asked to the user via a virtual character, and the user's facial expressions and responses are input into the machine learning to generate a primary psychological analysis model. Since the intake interview stage does not involve a counselor, there are no labor costs, and no separate equipment or counseling space is required.

[0052] The play therapy stage encourages users to engage in desired play in a virtual world or to play PC or mobile games designed to provide psychotherapeutic effects. In the play therapy stage, users express their psychological state, which can not only reduce their anxiety and stress but also help in assessing their psychological state.

[0053] In the counseling phase, a professional counselor conducts non-face-to-face counseling with the user using a virtual character as a medium. On the user's device, the counseling is conducted by a virtual character with whom rapport has already been established, rather than a professional counselor. Therefore, during this phase, the visual image and voice of the virtual character reproduced on the user's device serve as an avatar of the professional counselor. Because the professional counselor conducts psychological counseling through a virtual character with established rapport during this stage, the effectiveness of the counseling can be maximized by effectively drawing out the user's inner thoughts.

[0054] FIGS. 7A and 7B are drawings showing an example of a preliminary stage of the reception interview illustrated in FIG. 6. FIG. 7A is a drawing showing an example of a method for creating a virtual character. FIG. 7B is a screenshot showing an example of a virtual character being reproduced as an AR character on a display screen.

[0055] Referring to FIGS. 7a and 7b, the user can draw and color on a blank sheet of paper. When the user captures the drawing they have made with the user terminal (100), the application on the user terminal (100) can generate a virtual character, for example, an AR character, based on the captured image, reproduce the drawing on the display of the user terminal (100), and generate a voice signal corresponding to the generated virtual character and output it through a speaker. Meanwhile, the virtual character may be a virtual character selected by the user from among various characters provided by the application, or it may be a virtual character generated based on a real-life photographic image taken with the user terminal (100). The virtual character can effectively form rapport with the user before psychological counseling through interaction with the user.

[0056] Figures 8a and 8b are drawings showing an example of the play therapy steps illustrated in Figure 6.

[0057] Referring to Figures 8a and 8b, the play therapy stage allows the user to play as they wish, or play PC games or mobile games, in a virtual space built in a virtual world experience service, for example, a metaverse service. In offline play therapy, there are limitations to children freely expressing themselves. In contrast, when the user plays through their avatar in a virtual world or enjoys PC games or mobile games, anxiety and stress can be reduced without the risk of injury, and the effectiveness of psychotherapy can be enhanced because the user can freely express their psychological state.

[0058] Figure 9 is a diagram showing an example of the consultation step illustrated in Figure 6.

[0059] Referring to FIG. 9, the counseling stage involves a professional counselor conducting a non-face-to-face counseling session with the user through a virtual character. Since the user is conducting psychological counseling with a virtual character with whom rapport has already been established, they can express their psychological state more honestly. While conducting the non-face-to-face counseling session through the virtual character, the professional counselor can determine the child's answers, facial expressions, behaviors, and psychological state in real time through the user terminal (100).

[0060] The service method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and may be recorded on a computer-readable recording medium. In this case, the medium may continuously store a program executable by a computer, or temporarily store it for execution or download. Furthermore, the medium may be various recording or storage means in the form of a single or several hardware combined, and may not be limited to a medium directly connected to a computer system, but may exist distributed over a network. Examples of media may include magnetic 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; and media configured to store program instructions, including ROM, RAM, and flash memory. Additionally, other examples of media may include recording or storage media managed by app stores that distribute applications or sites and servers that supply or distribute various other software.

[0061] The term "part" as used in this embodiment refers to a software or hardware component, such as a field-programmable gate array (FPGA) or an ASIC, and the "part" performs certain roles. However, the meaning of "part" is not limited to software or hardware. The "part" may be configured to reside in an addressable storage medium or configured to run one or more processors. Thus, as an example, the "part" includes components such as software components, object-oriented software components, class components, and task components, as well as processes, functions, attributes, procedures, subroutines, segments of program code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, and variables. The functions provided within the components and "parts" may be combined into a smaller number of components and "parts" or further separated into additional components and "parts." In addition, the components and '~parts' may be implemented to play one or more CPUs within the device or secure multimedia card.

[0062] Since the contents of the specification described above regarding the problem to be solved, the means for solving the problem, and the effect do not specify the essential features of the claim, the scope of the claim is not limited by the matters described in the specification.

[0063] Although embodiments of the present invention have been described in more detail with reference to the attached drawings, the present invention is not necessarily limited to these embodiments and can be implemented with various modifications within the scope of the technical spirit of the present invention. Accordingly, the embodiments disclosed in the present invention are intended to explain, not limit, the technical spirit of the present invention, and the scope of the technical spirit of the present invention is not limited by these embodiments. Therefore, the embodiments described above should be understood as illustrative in all respects and not restrictive. Explanation of the symbols

[0064] 100: User terminal 200: Server 300: Professional counselor's terminal

Claims

Claim 1 A method for an artificial intelligence-based non-face-to-face psychological counseling service mediated by a virtual character, comprising: a step of generating a virtual character based on an image of a drawing directly drawn by a user captured through a camera of a user terminal and reproducing it on a display of the user terminal, and generating a voice signal suitable for the virtual character and outputting it through a speaker of the user terminal; and a step of outputting a question through the user terminal while inducing rapport formation between the user and the virtual character through the virtual character, and inferring and determining the user's current psychological state and emotional state using machine learning that interprets the answer content obtained based on the user's voice signal received through the microphone of the user terminal and the user's facial expression obtained based on an image captured through the camera of the user terminal. Claim 2 A method for an artificial intelligence-based non-face-to-face psychological counseling service according to claim 1, further comprising: a step of transmitting a user’s psychological analysis model reflecting the user’s current psychological and emotional state to a professional counselor’s terminal; and a step of converting the professional counselor’s voice into a voice signal suitable for the virtual character and providing it to the user terminal, thereby conducting psychological counseling through the virtual character reproduced on the user terminal. Claim 3 An artificial intelligence-based non-face-to-face psychological counseling service method, comprising: a step of providing at least one of a virtual world experience service, a PC game, and a mobile game through the user terminal in claim 1 or 2; and a step of the user's avatar entering a virtual world play space when the virtual world experience service is executed. Claim 4 A user terminal comprising a processor that executes an application for providing non-face-to-face psychological counseling services, including a camera, a microphone, and a speaker; and a server that provides a virtual character generated based on an image of a drawing directly drawn by a user captured through the camera of the user terminal, and a voice signal suitable for the virtual character to the user terminal, provides questions to the user terminal while inducing rapport formation between the user and the virtual character through the virtual character, and infers and determines the user's current psychological and emotional state using machine learning that analyzes the user's answers and facial expressions based on the image and voice signals received through the user terminal. Claim 5 In claim 4, the system further comprises a terminal of a professional counselor that receives a psychological analysis model of the user from the server and conducts psychological counseling through the virtual character reproduced on the user terminal while connected to the user terminal, and the server converts the voice of the professional counselor into a voice signal suitable for the virtual character and provides it to the user terminal, and provides at least one of a virtual world experience service, a PC game, and a mobile game through the user terminal. Claim 6 In claim 4 or 5, the server comprises: a Natural Language Generation (NLG) module and a Text-to-Speech (TTS) module connected to the speaker of the user terminal; a face / expression recognition module and a computer vision module connected to the camera of the user terminal; and a Speech-to-Text (STT) module and a Natural Language Understanding (NLU) module connected to the microphone of the user terminal, wherein the server inputs features and labels indicating the expression of the user input from the computer vision module and features and labels of the user's response input from the NLU module into the machine learning, and infers and determines the user's current psychological state and emotional state based on the results learned by the machine learning, thereby providing an artificial intelligence-based non-face-to-face psychological counseling service system mediated by a virtual character.

Citation Information

Patent Citations

  • Apparatus for assessing psychological state of user and method thereof

    KR1020220134715A