How to provide customized consultations for each user type based on artificial intelligence

Abstract

A control method of an electronic device according to an embodiment of the present invention includes: a consultation step in which the electronic device provides a visualized image of a digital human and a voice of the digital human including at least one question and acquires a user's response to the question; a measurement step in which the electronic device acquires measurements for five measurement items including the user's disposition, virtue, personality, cognitive faculty, and personal environments in response to the response; and a classification step in which the electronic device identifies a type of the user associated with resistance to digital addiction based on the acquired measurements.

Description

[Technical Field]

[0001] The present invention relates to a method for classifying user types based on an artificial intelligence model and providing consultations according to the user types. [Background technology]

[0002] The problems that have emerged in research into behavioral addiction so far can be roughly divided into two categories: the first is the need to conceptualize behavioral addiction without distinguishing between online and offline, and the second is the problem of establishing behavioral addiction diagnoses and clinical intervention strategies based on diagnostic scales derived from existing substance (drug) addictions.

[0003] Due to differences in self-efficacy between the virtual world and the real world, research on behavioral addictions has been somewhat confusing, with behavioral addictions being viewed without distinguishing between offline and online. This phenomenon has been reported to be due to a lack of clear conceptualization due to insufficient research on the diagnostic criteria and components of offline and online behavioral addictions.

[0004] While substance addiction is directly affected by the frequency and amount of exposure to a mediator (such as a drug), behavioral addiction is greatly influenced by a person's behavioral and psychological characteristics, as well as social and environmental factors. Therefore, depending on the individual's characteristics, there are types that are more susceptible to addiction than types that are not, even with the same exposure time. Therefore, there is a need to move away from relying on existing diagnostic scales derived from drug addiction and to develop diagnostic and treatment strategies for behavioral addiction that are tailored to the individual's characteristics. Summary of the Invention [Problem to be solved by the invention]

[0005] The present invention is devised to diagnose behavioral addictions and establish response strategies that are tailored to the characteristics of each individual, rather than relying on existing diagnostic scales derived from drug addiction.

[0006] Embodiments of the present invention are designed to classify individuals into one of several types related to their resistance to behavioral addictions, so that diagnosis and counseling for behavioral addictions can be tailored to the individual's type.

[0007] The objects of the present disclosure are not limited to the objects mentioned above, and other unmentioned objects and advantages of the present disclosure can be understood from the following description and will become more clearly understood by the embodiments of the present disclosure. Furthermore, it will be easily understood that the objects and advantages of the present disclosure can be realized by the means recited in the claims and combinations thereof. [Means for solving the problem]

[0008] The method for consulting by user type of an electronic device according to an embodiment of the present invention can be performed by the electronic device performing a consultation step, a measurement step, a classification step, an intervention step, and a diagnosis step.

[0009] The consulting step may refer to a step in which the digital human provides a visualized image and a voice of the digital human including at least one question, and obtains a user's response to the question.

[0010] In addition, in the measurement stage, which is performed after the consultation stage, the electronic device can perform an operation of obtaining measurement values ​​for five measurement items including the user's disposition, virtue, personality, cognitive faculty, and personal environments in response to the user's responses.

[0011] The classification step may also involve the electronic device performing an operation to identify a type of the user associated with a resistance to digital addiction based on the acquired measurements.

[0012] In addition, in the intervention step, the electronic device may select a consultation content that matches the type of the user and provide the selected consultation content in the voice of the digital human (agent system).

[0013] The electronic device may also include a first dialogue model trained to generate questions and responses for the consultation step, and a plurality of second dialogue models trained to provide consultation content matching each of a plurality of types related to resistance to digital addiction. In the intervention step, the electronic device may acquire consultation content based on a second dialogue model that matches the user's type among the plurality of second dialogue models, and provide the acquired consultation content in the voice of the digital human (agent system).

[0014] In addition, the electronic device may be configured to obtain a measurement value for the personality based on the user's responses to questions corresponding to consistency and activity during the measurement stage, and the measurement value for personality may be increased in proportion to an increase in the degree of positivity for the consistency and activity.

[0015] In addition, the electronic device may be configured to obtain a measurement value for the virtues based on the user's responses to questions corresponding to ethical norms and good faith during the measurement stage, and the measurement value for the virtues may be increased in proportion to an increase in the degree of affirmation regarding the ability to put the ethical norms into practice and good faith.

[0016] In addition, the electronic device may be configured to obtain measurements for the body shape based on the user's responses to questions corresponding to tolerance and social adaptability during the measurement step, and the measurements for the body shape may be increased in proportion to an increase in the degree of positivity regarding tolerance and social adaptability.

[0017] In addition, in the measurement step, the electronic device can be configured to obtain a measurement value for the hearing and knowledge based on the user's responses to questions corresponding to problem-solving ability, and to increase the measurement value for the hearing and knowledge in proportion to an increase in the degree of positivity toward the problem-solving ability, and to obtain a measurement value for the hearing and knowledge based on the user's responses to questions corresponding to social support and social organizational ability, and to increase the measurement value for the hearing and knowledge in proportion to an increase in the degree of positivity toward the social support and social organizational ability.

[0018] In addition, in the classification step, the electronic device identifies the user type based on the acquired measurement values, and if the measurement values ​​for all of the five measurement items are below reference values, the electronic device can identify the user as an avoidant type, if the measurement values ​​for disposition and cognitive faculty among the five measurement items are below reference values, the electronic device can identify the user as a compromise type, and if the measurement values ​​for all of the five measurement items are above reference values, the electronic device can identify the user as a problem-solving type.

[0019] In addition, during the diagnostic stage, the electronic device can determine the degree of the user's digital addiction based on the user's exposure time to factors (e.g., digital content) that cause the user's digital addiction and the type of the user. [Effects of the Invention]

[0020] The embodiments of the present invention can diagnose and provide consultation on behavioral addictions (digital addictions) according to the characteristics of the user, and thus can help establish a response strategy customized for the user.

[0021] In addition, an embodiment of the present invention collects data on a user's personal characteristics through a question and answer process with an AI-based digital human, allowing for type identification of the user in an environment similar to that of a real consultation. Since a separate test paper need not be created, the resulting fatigue can be reduced, and the present invention has advantages in terms of therapeutic accessibility, efficiency, and anonymity.

[0022] In addition, the limitations in the effectiveness of treatment that have existed until now, which have arisen because clients experiencing addictions have been reluctant to openly discuss their problems with their families or offline counselors due to concerns about stigmatization, can be improved by constructing a client-centered counseling model based on interaction with clients, which is implemented by an AI-based digital human, which is an embodiment of the present invention, thereby maximizing clinical effectiveness. [Brief explanation of the drawings]

[0023] [Figure 1] 1 is a diagram illustrating a configuration of an electronic device according to an embodiment of the present invention. [Figure 2] FIG. 3 is a diagram illustrating a configuration of a user determination unit according to an embodiment of the present invention. [Figure 3] FIG. 2 is a diagram illustrating the configuration of a second dialogue model according to an embodiment of the present invention. [Figure 4] FIG. 1 is a diagram illustrating a method for controlling an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0024] The advantages and features of the present invention, as well as methods for achieving them, will become more apparent by reference to the following detailed description of the embodiments in conjunction with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, and can be embodied in various different forms. The present embodiments are provided solely to complete the disclosure of the present invention and to fully convey the scope of the present invention to those skilled in the art. The present invention is defined only by the claims.

[0025] The terms used in this specification are for the purpose of describing embodiments and are not intended to limit the present invention. In this specification, the singular includes the plural unless the context clearly dictates otherwise. As used in this specification, "comprises" and / or "comprising" do not exclude the presence or addition of one or more other elements in addition to the elements mentioned. The same reference numerals refer to the same elements throughout this specification, and "and / or" includes each and every combination of one or more of the elements mentioned. Although terms such as "first," "second," etc. are used to describe various elements, it goes without saying that these elements are not limited by these terms. These terms are used merely to distinguish one element from another. Therefore, it goes without saying that a first element referred to below may be a second element within the technical spirit of the present invention.

[0026] Unless otherwise defined, all terms (including technical and scientific terms) used herein may be used in the sense commonly understood by those skilled in the art to which the present invention pertains. Furthermore, terms defined in commonly used dictionaries should not be interpreted in an ideal or excessive manner unless specifically defined otherwise. do not have.

[0027] As used herein, the term "module" or "module" refers to software or hardware components such as FPGAs or ASICs, and the "module" or "module" performs some function. However, the term "module" or "module" is not limited to software or hardware. A "module" or "module" may be configured to reside on an addressable storage medium or to execute one or more processors. Thus, by way of example, a "module" or "module" includes components such as software components, object-oriented software components, class components, and task components, as well as processes, functions, attributes, procedures, subroutines, program code segments, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, and variables. The functionality provided within a component or "module" or "module" may be combined into fewer components and "modules" or "modules" or further separated into additional components and "modules" or "modules."

[0028] Spatially relative terms such as "below," "beneath," "lower," "above," and "upper" can be used to easily describe the relationship of one component to another, as shown in the figures. Spatially relative terms should be understood to include different orientations of components in use or operation in addition to the orientation shown in the figures. For example, if components shown in the figures were turned over, a component described as "below" or "beneath" another component could be placed "above" the other component. Thus, the exemplary term "below" can encompass both an orientation of below and above. Components can be oriented in other directions, allowing the spatially relative terms to be interpreted accordingly.

[0029] An electronic device 10 according to an embodiment of the present invention is capable of providing preventative, diagnostic, and therapeutic consultation for behavioral addictions.

[0030] Behavioral addictions are not like substance addictions (or drug addictions), in which tolerance and withdrawal factors are developed through a neurotransmitter adaptation stage caused by the action of a specific substance on the human brain, but rather are characterized by human behavior acting as the medium for addiction, and types of behavioral addictions include digital addiction, gambling addiction, love addiction, religion addiction, power addiction, sex addiction, food addiction, shopping addiction, and study addiction.

[0031] Such behavioral addictions are known to be significantly influenced by a person's behavior, psychological characteristics, social and environmental factors, etc., and as a result, depending on the individual's characteristics, there are samples that are sensitive to addiction and samples that are not, even when exposed to the same behavior for the same amount of time.

[0032] Due to the characteristics of such behavioral addictions, the electronic device 10 can classify users into types according to their characteristics through a consultation (first consultation) to determine the user's characteristics, and can proceed with user consultation (second consultation) based on the user's type.

[0033] In the following, the present specification will mainly describe embodiments relating to digital addiction among behavioral addictions. However, it should be understood that the targets of the preventive, diagnostic and therapeutic operations according to the embodiments of the present invention are not limited to digital addictions, but include all types of behavioral addictions, including the gambling addiction mentioned above.

[0034] Specific embodiments of the control operation of the electronic device 10 will be described in detail below with reference to the accompanying drawings.

[0035] First, the configuration and functions of an electronic device according to an embodiment of the present invention will be described with reference to FIGS.

[0036] FIG. 1 is a diagram showing the configuration of an electronic device according to an embodiment of the present invention.

[0037] FIG. 2 is a diagram showing the configuration of the user determination unit according to the embodiment of the present invention.

[0038] FIG. 3 is a diagram showing the configuration of a second dialogue model according to an embodiment of the present invention.

[0039] 1, an electronic device 10 according to an embodiment of the present invention may be configured to include a processor 100, a memory 200, and a communication unit 300. The processor 100 may be configured to include a learning execution unit 110, a user determination unit 120, and a consultation proceeding unit 130. The memory 200 may be configured to include a first dialogue model 210 and a second dialogue model 220. Although not shown, the memory 200 may further include an artificial intelligence model (e.g., a type determination model) that performs an operation of determining a user's type in addition to the dialogue models.

[0040] Thus, the electronic device 10 may be configured to include various components, each of which will be described in more detail below.

[0041] The processor 100 of the electronic device 10 may be configured to include the learning execution unit 110, the user determination unit 120, and the consultation progress unit 130, as described above.

[0042] Based on the person identification theory of the learning execution unit 110, the learning of the artificial intelligence model required for determining the user type and for performing consultation operations (secondary consultation) according to the user type can be executed.

[0043] First, the learning execution unit 110 can train an artificial intelligence model (first dialogue model) to generate questions and responses necessary for the first consultation action among the actions required to determine the user's type.

[0044] For example, the learning execution unit 110 may train an AI model to perform an operation of providing a visualized image of a digital human and a voice of the digital human including at least one question and answer. The digital human may refer to a virtual consultant who provides a consultation question to a user based on the trained AI model and answers in response to the user's response.

[0045] At this time, the digital human can provide questions to the user in the form of audio sounds so that the user can respond and ask questions in an environment similar to interacting with a real consultant.

[0046] In addition, the digital human may provide a visualized image to the user during the dialogue so that the user can more easily understand the digital human's question. The digital human may also provide a visualized image to the user during the process of confirming the content of the user's response, preventing misinterpretation of the user's response.

[0047] Furthermore, the learning execution unit 110 can train an artificial intelligence model (type determination model) that identifies the type of a user according to the user's response in the first consultation.

[0048] The learning execution unit 110 can train the artificial intelligence model (type determination model) to acquire measurements for five measurement items (disposition, virtue, personality, cognitive faculty, and personal environments) corresponding to the five aspects of the personality appraisal theory based on the user's responses to questions, and to identify the user's type as one of three types: avoidant, compromising, and problem-solving based on the measurements.

[0049] Furthermore, the learning execution unit 110 can execute learning of an artificial intelligence model (second dialogue model) that proceeds with the consultation according to the identified user type.

[0050] Specifically, the learning execution unit 110 can select a consultation content that matches the type of the user, and train an artificial intelligence model (second dialogue model) to provide the selected consultation content as at least one of the digital human's voice and text.

[0051] The user determination unit 120 may perform an operation for determining the type of the user based on the artificial intelligence model learned by the learning execution unit 110 .

[0052] The user determination unit 120 may perform a first consultation operation to collect user response content required for determining the user's type. The user determination unit 120 may classify the user into three types (e.g., avoidant type, compromise type, and problem-solving type) according to personality analysis theory, based on the user's response obtained through the first consultation.

[0053] For a more detailed explanation of the operation performed by the user determination unit 120, reference will be made to FIG.

[0054] As shown in FIG. 2, the user determination unit 120 may be configured to include a question generation unit 121, an item measurement unit 122, and a type identification unit 123.

[0055] The question generator 121 can generate questions required to proceed with a first consultation with a user by driving the first dialogue model stored in the memory 200 .

[0056] According to an embodiment, the question generation unit 121 may specify the same question to be initially presented to the user regardless of who the user is. Alternatively, the question generation unit 121 may generate the initial question according to basic personal information of the user (e.g., gender, age, occupation, etc.). The method is not limited to the above, and the question generation unit 121 may generate the initial question to be presented to the user starting the first consultation in various ways.

[0057] After generating an initial question and presenting it to the user, when the question generation unit 121 receives a corresponding response from the user, the question generation unit 121 can generate a subsequent question corresponding to the received user response and present it to the user.

[0058] At this time, the question generation unit 121 can generate questions for measuring five items (spirit, morals, physical appearance, hearing and seeing, and place) corresponding to the personality appraisal theory when generating questions.

[0059] Specifically, the method for generating questions to measure each of the above five items will be explained as follows.

[0060] First, the question generator 121 can generate a question for measuring "disposition" among the five items. "Disposition" is a latent variable that measures the strength and brightness of innate temperament. "Disposition" is an item designed to measure a person's consistency in terms of strength and brightness, and measure activity in terms of the degree of cheerfulness or gloominess. For example, in the present invention, the more a user is judged to be steady and devoted and have a cheerful temperament, the larger the value corresponding to "disposition" can be measured.

[0061] According to the characteristics of the item "spirit," the question generator 121 can generate questions for evaluating the user's consistency, such as the user's willingness to continue a plan that the user has made. For example, the question generator 121 can generate questions such as "Have you ever continued a planned exercise for more than one month?" and "Have you ever been evaluated as a cheerful person by others?" as questions for measuring the item "spirit."

[0062] Next, the question generator 121 can generate a question for measuring "virtue" among the five items. "Virtue" is a variable that measures an individual's ability to practice ethical standards and integrity (consistency between words and actions) that are established through the individual's acquired efforts, and the more an individual is judged to be ethical and integrity-oriented, the higher the "virtue" value can be measured.

[0063] According to the characteristics of such an item called "virtue," the question generation unit 121 can generate questions such as, "Are you normally moral, act in accordance with reason and principles, and have no falsehood?", "Are you normally lacking in humility and often place importance on appearances that are not in accordance with reason and principles?", "Are you the type of person who is very honest and consistent in what you say and do in all matters?", and "Are you the type of person who is not very honest and consistent in what you say and do in all matters?".

[0064] Next, the question generator 121 can generate a question for measuring "personality" among the five items. The "personality" is an item designed to measure consideration and catholicity for others and social adjustment, and the higher the user is determined to be in catholicity and social adjustment, the higher the value for "personality" can be measured.

[0065] Depending on the characteristics of the "physical appearance" item, the question generation unit 121 can generate questions such as, for example, "Are you usually very considerate and tolerant of others?", "Are you usually not very considerate and tolerant of others?", "Are you usually good at getting along with the people around you?", or "Are you usually not good at getting along with the people around you?".

[0066] Next, the question generator 121 can generate a question for measuring "cognitive faculty" among the five items. "Cognitive faculty" is a variable that measures a person's problem-solving ability, and the more a user is evaluated as having excellent problem-solving ability, the higher the value of "cognitive faculty" can be measured.

[0067] Depending on the characteristics of the "hearings and experiences" item, the question generation unit 121 can generate questions such as, "Are you someone who makes good use of your own experiential knowledge and advice from people around you?", "Have you ever experienced difficulties in the process of solving a problem despite relying on your own experiential knowledge and problem-solving ability?", "Do you prefer a rational and fundamental method of solving a problem?", and "Do you prefer a method that relies on improvised ideas rather than a rational and fundamental method of solving a problem?".

[0068] Finally, the question generator 121 can generate a question for measuring "location" among the five items. The "location" is a variable that measures a person's social position and the level of social activity. The "location" is also a variable that measures the level of social support from organizational members and surrounding people, and the social sphere that is emphasized in community activities (social achieved status and social sphere). The more a user is judged to have better social support or social sphere, the higher the value of the "location" item can be measured.

[0069] Depending on the characteristics of the "location" item, the question generation unit 121 can generate questions such as, for example, "Are you someone who is generally trusted and respected by members of your organization and the people around you?", "Are you someone who is generally not trusted and respected by members of your organization and the people around you?", "Are you someone who is usually proactive in helping the community and others?", or "Are you someone who is not usually proactive in helping the community and others?".

[0070] In addition, the question generation unit 121 determines whether an additional question can be generated and whether the topic of the additional question can be changed depending on the degree of completion of the item measurement determined by the item measurement unit 122, and can generate an additional question if the item measurement is not complete.

[0071] For example, if the item measurement unit 122 determines that measurements for all five items have been completed, it transmits a corresponding signal to the question generation unit 121, which allows the question generation unit 121 to end the first consultation without generating additional questions. Meanwhile, the question generation unit 121 can be controlled to change the topic of additional questions when it receives a notification from the item measurement unit 122 that only four of the five measurement items have been completed.

[0072] Furthermore, upon receiving the user's response, the question generator 121 can quantify the specificity of the response and determine the degree of specificity of the follow-up question according to the specificity value.

[0073] Methods for quantifying the specificity of the responses may include, for example, measuring the volume of the responses, measuring the variety of words contained in the responses, or measuring both the volume and variety of words contained in the responses.

[0074] The question generator 121 may generate a follow-up question with a higher degree of specificity if the acquired user response does not reach the specificity value of the response to be acquired.

[0075] For example, when the question generator 121 receives from the user an answer such as "yes" or "no" that is below a threshold (e.g., 10 characters or less) or that has a variety of words below a threshold (e.g., 3 types or less) in response to the question "Do you usually stick to your plans?", the question generator 121 may present a follow-up question on the same topic with an increased level of specificity, such as "Have you tried to put your plan into practice for more than a month?" Similarly, during subsequent consultations, if the question generator 121 determines that the acquired response does not reach a target specificity value, it may continue to generate follow-up questions with an increased level of specificity.

[0076] The item measurement unit 122 acquires the user's response obtained as the question is provided to the user through the question generation unit 121, and can measure five items (spirit, morals, physical appearance, hearing, views, and place) based on the user's response based on the theory of personality appraisal.

[0077] The item measurement unit 122 can input the user's response into the artificial intelligence model (type determination model) trained by the learning execution unit 110 to measure values ​​for the five measurement items.

[0078] Specifically, for example, the item measurement unit 122 may analyze each user's response input into the AI ​​model and write it on an n-dimensional (preferably, two-dimensional or three-dimensional) coordinate system according to the relevance value with the temperament traits represented by each of the five items. Then, the item measurement unit 122 may calculate the average of the coordinate values ​​of each point whose coordinate value is designated, and calculate a measurement value for each of the five items using the average of the calculated coordinate values ​​of each point. In this case, the axis of each coordinate system may be designated corresponding to a sub-item of the five items (for example, the sub-items of "temper" correspond to consistency and activity).

[0079] Next, a method in which the item measurement unit 122 calculates the measurement value for each of the five items in this manner will be described. First, the process in which the item measurement unit 122 calculates the measurement value for the "attitude" item is as follows. The item measurement unit 122 inputs a user's response and can calculate correlation values ​​for the user's tendency and "consistency" and "activity," which are sub-items corresponding to the "attitude" item. In this case, when the AI ​​model determines the correlation values ​​between the "attitude" item and the user's characteristics, the x-coordinate can be designed to increase in value corresponding to the degree of "consistency" (the stronger the consistency), and the y-coordinate can be designed to increase in value corresponding to the degree of "activity" (the stronger the activity and the brighter the activity).

[0080] According to various embodiments, the AI ​​model can be designed to designate each axis of a graph as a sub-item for each of the five items, and then record the relevance value between each item and user characteristics in a graph including an additional axis. The AI ​​model can then calculate and record a value for the reliability value of the user's response on the additional axis (e.g., z-axis). The reliability value can be a value determined by items such as the speed at which the user's response is entered and the degree of consistency between the user's responses.

[0081] The type identification unit 123 can determine the user type as one of three preset types based on the measured values ​​for each of the five items measured by the item measurement unit 122.

[0082] In this case, the type identification unit 123 can classify the user into one of three types (e.g., avoidant type, compromise type, and problem-solving type) according to personality assessment theory. The avoidant type is the type with the lowest initiative and willpower for problem-solving of behavioral addictions (e.g., digital addictions), while the problem-solving type is the type with the highest initiative and willpower for problem-solving of behavioral addictions and full of confidence in overcoming the behavioral addictions. The compromise type may be an intermediate type with higher initiative in problem-solving of behavioral addictions than the avoidant type but lower initiative than the problem-solving type. For example, a group that has the will to solve problems related to behavioral addictions but lacks confidence can be called the compromise type.

[0083] Specifically, the type identification unit 123 can identify the user as an avoidant type if the measured values ​​for all of the five measurement items are below the reference values, identify the user as a compromise type if the measured values ​​for disposition and cognitive faculty among the five measurement items are below the reference values, and identify the user as a problem-solving type if the measured values ​​for all of the five measurement items are above the reference values.

[0084] The consultation proceeding unit 130 of the processor 100 can provide a consultation (secondary consultation) for the behavioral habits of the user according to the type of the user identified by the user determining unit 120.

[0085] The consultation proceeding unit 130 may select a consultation content that matches the type of the user and provide the selected consultation content in the voice of a digital human.

[0086] In addition, the consultation proceeding unit 130 can utilize a plurality of second dialogue models trained to provide consultation content that matches each of a plurality of types related to resistance to behavioral addictions (e.g., digital addictions) in order to proceed with the consultation with consultation content that matches the user's type.

[0087] As shown in FIG. 3, the second dialogue model can be configured into three types, namely, an avoidance-type response model 221, a compromise-type response model 222, and a problem-solving-type response model 223, depending on the type of each user.

[0088] When providing a consultation on the behavioral addiction of an avoidant user using the avoidant-type response model 221, the consultation proceeding unit 130 can set the possibility and severity of the user's behavioral addiction to the highest value among the three types and generate questions and responses required for the consultation. Similarly, when providing a consultation on the behavioral addiction of a compromised user using the compromise-type response model 222, the consultation proceeding unit 130 can set the possibility and severity of the user's behavioral addiction to an intermediate value, and when providing a consultation using the problem-solving-type response model 223, the consultation proceeding unit 130 can set the possibility and severity of the user's behavioral addiction to the lowest value among the three types.

[0089] By classifying the possibility and severity of behavioral addiction by user type in this way, the consultation proceeding unit 130 can set the behavioral addiction risk level for an avoidant user with the same level of user behavior as three levels, and for a compromise user and a problem-solving user, classify them into two levels and one level, respectively. The consultation proceeding unit 130 can also classify the severity of behavioral addiction for the same level of user behavior into three levels, two levels, and one level for avoidant, compromise, and problem-solving types, respectively, and set the treatment level and the recommended level for behavioral improvement to increase as the level increases, and proceed with the consultation. For example, as the recommended level for behavioral improvement increases, the number of times a sentence recommending improvement of addiction symptoms is included during the consultation can be set to increase.

[0090] Furthermore, according to various embodiments, the consultation facilitating unit 130 may generate different consultation questions and responses corresponding to each type of user. When users who are determined to have the same level of addiction possibility and severity are identified as different user types, the consultation facilitating unit 130 may increase the treatment level and the degree of behavioral improvement recommendations for the user who has a lower tolerance for behavioral addiction (e.g., digital addiction) and proceed with the consultation. For example, an avoidant user, who has the lowest tolerance for addiction, may be required to make a higher level of behavioral improvement for the same level of addiction than a problem-solving user.

[0091] In addition, the consultation progress unit 130 may increase various other setting values ​​(such as the volume of the digital human's voice sound, the consultation progress time of the digital human, etc.) during the consultation process to strengthen the request for behavioral improvement, depending on the type of person who is less resistant to behavioral addictions (e.g., digital addiction).

[0092] The memory 200 may store instructions and algorithms required to perform overall operations according to an embodiment of the present invention. The memory 200 according to an embodiment of the present invention may store various artificial intelligence models required to identify a user type and to provide advice on the user's behavioral habits according to the identified user type.

[0093] The memory 200 may include a first dialogue model 210 trained to generate questions and responses for the consultation phase when the consultation phase is carried out to determine the user's type. The memory 200 may also include a second dialogue model 220 trained to provide consultation content that matches each of the user's types. The second dialogue model 220 may be an artificial intelligence model trained to provide consultation content that matches each of a plurality of types associated with resistance to behavioral addictions (e.g., digital addiction).

[0094] The second dialogue model 220 may be configured to include a plurality of models to match each user type. The second dialogue model 220 may be configured to include a response model for each of the user types, i.e., avoidant, compromise, and problem-solving. As shown in Fig. 3, the second dialogue model 220 may be configured to include an avoidant response model 221, a compromise response model 222, and a problem-solving response model 223.

[0095] The communication unit 300 can be used to communicate between the electronic device 10 of the present invention and a user terminal (not shown). The user terminal can be connected to the communication unit 300 and can receive user type-specific consultation operations based on the user type classification and behavioral habits provided by the electronic device 10.

[0096] FIG. 4 is a diagram illustrating a method for controlling an electronic device according to an embodiment of the present invention.

[0097] As shown in FIG. 4, the electronic device 10 can perform the following operations: 405, providing a question to a user; 410, acquiring a response from the user; 415, acquiring a measurement value for a measurement item based on the response from the user; 420, identifying a user type based on the measurement value; and 425, consulting a model corresponding to the user type.

[0098] Furthermore, the above 405 and 410 operations may correspond to a consultation phase, the 415 operation of obtaining measurements may correspond to a measurement phase, the 420 operation of identifying the user type may correspond to a classification phase, and the 425 operation of consulting with a model corresponding to the user type may correspond to an intervention phase.

[0099] Furthermore, the control method for the electronic device 10 according to an embodiment of the present invention may include a diagnostic step of determining the degree of a user's digital addiction based on the user's exposure time to factors (e.g., immersion in digital content) that cause the user's behavioral addiction (digital addiction) and the type of user.

[0100] In summary, the user type-specific consultation method of the electronic device according to one embodiment of the present invention can be achieved by the electronic device performing a consultation stage, a measurement stage, a classification stage, an intervention stage and a diagnosis stage.

[0101] The consultation step may refer to a step in which the digital human provides at least one of a voice and a text of the digital human including a visualized image and at least one question, and obtains a user's response to the question.

[0102] In addition, in the measurement stage, which is performed after the consultation stage, the electronic device can perform an operation of obtaining measurement values ​​for five measurement items including the user's disposition, virtue, personality, cognitive faculty, and personal environments in response to the user's responses.

[0103] The classification step may also involve the electronic device performing an operation to identify a type of the user associated with a resistance to digital addiction based on the acquired measurements.

[0104] In addition, in the intervention step, the electronic device may select a consultation content that matches the type of the user and provide the selected consultation content as at least one of the digital human's voice and text.

[0105] The electronic device may also include a first dialogue model trained to generate questions and responses for the consultation step, and a plurality of second dialogue models trained to provide consultation content matching each of a plurality of types related to resistance to digital addiction.The electronic device may acquire consultation content based on a second dialogue model that matches the user's type among the plurality of second dialogue models in the intervention step, and provide the acquired consultation content as at least one of the digital human's voice and text.

[0106] In addition, the electronic device may be configured to obtain a measurement value for the temperament based on the user's response to questions corresponding to consistency and activity during the measurement stage, and to increase the measurement value for the temperament in proportion to the degree of consistency and activity of the user determined from the response.

[0107] In addition, the electronic device can be configured to obtain a measurement value for the virtue based on the user's response to questions corresponding to ethical norms and good faith during the measurement stage, and to increase the measurement value for the virtue in proportion to the user's ability to practice ethical norms and degree of good faith as determined from the response.

[0108] In addition, the electronic device can be configured to obtain a measurement value for the body shape based on the user's response to questions corresponding to tolerance and social adaptability during the measurement stage, and to increase the measurement value for the body shape in proportion to the degree of tolerance and social adaptability of the user determined from the response.

[0109] In addition, in the measurement step, the electronic device can be configured to obtain a measurement value for the hearing and knowledge based on the user's response to questions corresponding to problem-solving ability, and to increase the measurement value for the hearing and knowledge in proportion to the level of the user's problem-solving ability determined from the response, and to obtain a measurement value for the hearing and knowledge based on the user's response to questions corresponding to social support and social organizational ability, and to increase the measurement value for the hearing and knowledge in proportion to the level of the user's social support and social organizational ability.

[0110] In addition, in the classification step, the electronic device identifies the user type based on the acquired measurement values, and if the measurement values ​​for all of the five measurement items are below reference values, the electronic device can identify the user as an avoidant type, if the measurement values ​​for disposition and cognitive faculty among the five measurement items are below reference values, the electronic device can identify the user as a compromise type, and if the measurement values ​​for all of the five measurement items are above reference values, the electronic device can identify the user as a problem-solving type.

[0111] In this case, the avoidant type refers to a group with weak willpower to solve behavioral addiction problems, the compromising type refers to a group with willpower to solve behavioral addiction problems but lacking confidence, and the problem-solving type refers to a group with full confidence in overcoming behavioral addictions and strong willpower to solve the problems.

[0112] As described above, in the classification step, the electronic device can determine the user's type as one of three types based on the measured values ​​for the five measurement items.

[0113] Meanwhile, according to various embodiments, the electronic device may classify the type according to the age and gender of the user in addition to the measured values ​​for the five measurement items in the classification step. For example, the electronic device may classify users into eight age groups (children, adolescents, and teenagers to those in their 10s to 70s) in the process of determining whether they are avoidant, compromised, or problem-solving types, and then apply different calculation methods for determining their type according to the attributes of each age group. Furthermore, the electronic device may classify users belonging to each age group into males and females and apply different calculation methods for determining their type according to their gender attributes.

[0114] After confirming the type of user, the electronic device can provide customized services according to the type of user.

[0115] Taking digital addiction, which is one type of behavioral addiction, as an example, in the diagnosis stage, the electronic device can derive the user's digital addiction state and addiction level (score) as data based on the user's exposure time to specific digital content, etc., and the user type classification, and can set an intervention method customized for each client type based on this.

[0116] The electronic device 10 according to an embodiment of the present invention may include a memory 200 , a communication unit 300 and a processor 100 .

[0117] The memory 200 may store various programs and data required for the operation of the electronic device, and may be implemented as a non-volatile memory, a volatile memory, a flash memory, a hard disk drive (HDD), or a solid state drive (SSD).

[0118] The communication unit 300 can communicate with external devices. In particular, the communication unit 300 can include various communication chips such as a Wi-Fi chip, a Bluetooth® chip, a wireless communication chip, an NFC chip, and a low-power Bluetooth® chip (BLE chip). The Wi-Fi chip, the Bluetooth® chip, and the NFC chip communicate via a LAN, a Wi-Fi, a Bluetooth®, and an NFC, respectively. When a Wi-Fi chip or a Bluetooth® chip is used, various connection information such as an SSID and a session key is first transmitted and received, and various information can be transmitted and received after establishing a communication connection using the information. The wireless communication chip refers to a chip that communicates according to various communication standards such as IEEE, ZigBee, 3G (3rd Generation), 3GPP (3rd Generation Partnership Project), and LTE (Long Term Evolution).

[0119] The processor 100 can control the overall operation of the user device using various programs stored in the memory 200. The processor can be composed of a RAM, a ROM, a graphics processing unit, a main CPU, 1st to nth interfaces, and a bus. In this case, the RAM, ROM, graphics processing unit, main CPU, 1st to nth interfaces, etc. can be connected to each other via the bus.

[0120] The RAM stores the operating system and application programs. Specifically, when the electronic device boots, the operating system is stored in the RAM, and various application data selected by the user can also be stored in the RAM.

[0121] The ROM stores an instruction set for system booting. When a turn-on command is input and power is supplied, the main CPU copies the O / S stored in memory 200 to RAM according to the commands stored in the ROM and runs the O / S to boot the system. Once booting is complete, the main CPU copies various application programs stored in memory 200 to RAM and runs the application programs copied to RAM to perform various operations.

[0122] The main CPU accesses the memory 200 and performs booting using the O / S stored in the memory 200. The main CPU also performs various operations using various programs, contents, data, etc. stored in the memory 200.

[0123] The first to nth interfaces are connected to the various components described above. One of the first to nth interfaces can be a network interface that is connected to an external device via a network.

[0124] Meanwhile, the processor may further control an artificial intelligence model, in which case it goes without saying that the control unit may include a dedicated graphics processor (e.g., a GPU) for controlling the artificial intelligence model.

[0125] Processor 100 may include one or more cores (not shown) and a graphics processing unit (not shown) and / or connecting paths (e.g., buses) for sending and receiving signals to and from other components.

[0126] In one embodiment, the processor executes one or more instructions stored in memory 200 to perform the methods described in connection with the present invention.

[0127] Meanwhile, the processor 100 may further include a random access memory (RAM, not shown) and a read only memory (ROM, not shown) for temporarily and / or permanently storing signals (or data) processed within the processor. The processor 130 may also be implemented as a system on a chip (SoC) including at least one of a graphics processing unit, a RAM, and a ROM.

[0128] The memory 200 can store a program (one or more instructions) for processing and controlling the processor 100. The program stored in the storage unit can be divided into a plurality of modules according to their functions.

[0129] The steps of a method or algorithm described in connection with the embodiments of the present invention may be embodied directly in hardware, in a software module executed by hardware, or in a combination thereof. The software module may reside in Random Access Memory (RAM), Read Only Memory (ROM), Erasable Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), Flash Memory, a hard disk, a removable disk, a CD-ROM, or any other form of computer-readable storage medium known in the art to which the present invention pertains.

[0130] The components of the present invention can be embodied as a program (or application) and stored on a medium for execution in conjunction with a computer (hardware). The components of the present invention can be implemented by software programming or software elements. Similarly, embodiments include various algorithms embodied in a combination of data structures, processes, routines, or other programming constructs, and can be implemented in programming or scripting languages ​​such as C, C++, Java, assembler, etc. Functional aspects can be embodied as algorithms executed by one or more processors 100.

[0131] Although the present invention has been described in detail with reference to the above-mentioned embodiments, those skilled in the art can make modifications, changes, and variations to the present embodiments without departing from the scope of the present invention. In short, in order to achieve the intended effects of the present invention, it is not necessary to separately include all of the functional blocks shown in the drawings or to follow all of the sequences shown in the drawings in the exact order shown, and it should be noted that even if they do not, they may still fall within the technical scope of the present invention as defined in the claims.

Claims

1. 1. A method for controlling an electronic device, comprising: a consultation step in which the electronic device provides a visualized image of the digital human and a voice of the digital human including at least one question, and obtains a user's response to the question; a measuring step in which the electronic device acquires measurements for five measurement items including the user's disposition, virtue, personality, cognitive faculty, and personal environments in response to the response; and The method of controlling an electronic device includes a classification step in which the electronic device identifies a type of the user associated with a resistance to digital addiction based on the acquired measurements.

2. The method for controlling an electronic device includes: The method of claim 1, further comprising: an intervention step in which the electronic device selects a consultation content that matches the type of the user and provides the selected consultation content in the voice of the digital human.

3. The electronic device is a first dialogue model trained to generate questions and responses for the consultation phase; and a plurality of second dialogue models trained to provide consultation content that matches each of a plurality of types associated with resistance to digital addiction; The intervention step comprises:

3. The method of claim 2, further comprising: acquiring a consultation content based on a second dialogue model that matches the user type among the plurality of second dialogue models; and providing the acquired consultation content in the voice of the digital human.

4. The measuring step comprises: Obtaining measures of said temperament based on user responses to questions corresponding to consistency and activity; 2. The method of claim 1, further comprising obtaining a measure of user's aptitude as a numerical value proportional to the user's degree of consistency and activity.

5. The measuring step comprises: obtaining a measure of the virtues based on the user's responses to questions corresponding to ethical standards and integrity; 2. The method of claim 1, further comprising obtaining a measure of morality as a numerical value proportional to the user's ability to practice and faithfulness to ethical standards.

6. The measuring step comprises: Obtaining measurements for said body shape based on the user's responses to questions corresponding to inclusiveness and social adaptability; 2. The method of claim 1, further comprising obtaining a measurement value for the user's body shape that is proportional to the user's tolerance and social adaptability.

7. The measuring step comprises: obtaining a measure of the perception based on the user's responses to questions corresponding to problem-solving ability; 2. The method of claim 1, further comprising obtaining a measurement value for the user's hearing and seeing in a numerical value proportional to the degree of the user's problem-solving ability.

8. The measuring step comprises: obtaining measurements for said locations based on user responses to questions corresponding to social support and social organizational strength; 2. The method of claim 1, further comprising obtaining a measurement value for the location that is proportional to the user's level of social support and social organization.

9. The classification step comprises: The user's type is identified based on the measurements of the five measurement items of temperament, morals, physical appearance, hearing, vision, and location. If all of the measured values ​​for the five measurement items are below the reference value, the user is identified as an avoidant type, which is defined as a group with low problem-solving willpower; If the measured values ​​for disposition and cognitive faculty among the five measurement items are below the reference value, the user is identified as a compromise type, which is defined as a group that has the willpower to solve problems but low confidence; 2. The method of claim 1, wherein if all the measured values ​​for the five measurement items are equal to or greater than the reference values, the user is identified as a problem-solving type, which is defined as a group filled with willpower and confidence in problem solving.

10. The method for controlling an electronic device includes:

2. The method of claim 1, further comprising a diagnostic step of determining the degree of the user's digital addiction based on the user's exposure time to factors that cause digital addiction and the type of the user.

11. memory; a communication unit for communicating with at least one user terminal; and a processor that provides a visualized image of the digital human and a voice of the digital human including at least one question via the communication unit, acquires a user's response to the question, acquires measurements for five measurement items including the user's disposition, virtue, personality, cognitive faculty, and personal environments in accordance with the response, and identifies a type of the user related to resistance to digital addiction based on the acquired measurements.

12. A non-transitory computer-readable medium having stored thereon at least one instruction that, when executed by a processor of an electronic device, causes the electronic device to perform the control method of claim 1.

Images