Method for performing customized consultation according to user types based on artificial intelligence

Abstract

A control method of an electronic device according to an embodiment of the present invention comprises: a consultation step in which the electronic device provides a digital person visual image and a voice of the digital person comprising at least one query, and obtains a response of a user to the query; a measurement step in which the electronic device obtains, on the basis of the response, measurement values of five measurement items, which include a display of the user, a virus of the user, a personality of the user, a cognitive competence of the user, and a context of the user, and a measurement step in which the electronic device obtains, on the basis of the response, measurement values of five measurement items, which include the display of the user, the virus of the user, the personality of the user, the cognitive competence of the user, and the context of the user; and a classification step in which the electronic device identifies the type of the user related to the tolerance of the digital addiction, based on the measured values that have been obtained.

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 Art

[0002] So far, the problems that have emerged in the study of behavioral addiction can be roughly divided into the following two points. First, the problem of conceptualizing behavioral addiction without distinguishing between online and offline; second, the problem of still formulating the diagnosis and clinical intervention strategies of behavioral addiction based on the existing diagnostic scales for substance (drug) addiction.

[0003] Due to the differences in self-efficacy between the virtual world and the real world, in the research related to behavioral addiction, regarding behavioral addiction as the same phenomenon without distinguishing between offline and online has led to a considerable degree of confusion. It is reported that this phenomenon occurs because the past research on the diagnostic criteria and components of offline and online behavioral addiction was weak, and the concept could not be clearly defined.

[0004] Substance addiction is directly affected by the number of exposures and the amount of the medium substance (such as drugs), while behavioral addiction is greatly affected by people's actions, psychological characteristics, and social environmental factors. Therefore, according to the characteristics of a person, even with the same exposure time, there will be types that are sensitive to addiction and types that are not sensitive to it. Therefore, it is necessary to avoid relying on and using the existing diagnostic scales for drug addiction, and to diagnose behavioral addiction and formulate coping strategies according to the characteristics of the person. Summary of the Invention

[0005] Problems to be Solved by the Invention

[0006] The embodiments of the present invention aim to formulate diagnostic and coping strategies suitable for the characteristics of a person when diagnosing behavioral addiction and formulating corresponding coping strategies, rather than adopting the existing diagnostic scales for drug addiction.

[0007] The embodiments of the present invention aim to classify a person into one of multiple types related to the tolerance of behavioral addiction, and diagnose and consult on behavioral addiction according to the type of the person.

[0008] The object of the present disclosure is not limited to the above-mentioned objects, and other objects and advantages of the present disclosure not mentioned can be understood through the following description, and will be more clearly understood through the embodiments of the present disclosure. In addition, it is obvious that the objects and advantages of the present disclosure can be achieved by the means and combinations listed in the claims.

[0009] Means for Solving the Problems

[0010] The consultation method according to the user type of the electronic device according to an embodiment of the present invention can be implemented through the consultation step, measurement step, classification step, intervention step, and diagnosis step by the electronic device.

[0011] The consultation step may refer to the step of providing a visual image of a digital human (AI Agent) and the voice of the digital human including at least one question, and obtaining a response from the user to the question.

[0012] In addition, in the measurement step performed after the consultation step, the electronic device may perform an operation of obtaining measurement values of five measurement items including the user's disposition, virtue, personality, cognitive faculty, and situation (personal environment) according to the response of the user.

[0013] In addition, in the classification step, the electronic device may perform an operation of identifying the type of the user related to the tolerance of digital addiction based on the obtained measurement values.

[0014] In addition, in the intervention step, the electronic device may select consultation content matching the type of the user, and provide the selected consultation content through the voice of the digital human.

[0015] In addition, the electronic device may include: a first dialogue model trained to be able to generate questions and responses for the consultation step; and a plurality of second dialogue models trained to be able to provide consultation content matching each of a plurality of types related to the tolerance of digital addiction. In addition, the electronic device may obtain consultation content according to the second dialogue model matching the type of the user among the plurality of second dialogue models in the intervention step, and provide the obtained consultation content through the voice of the digital human.

[0016] In addition, the electronic device may be set to obtain the measurement value of the disposition in the measurement step based on the response of the user to the questions corresponding to consistency and activity, wherein as the positive degree of the consistency and activity increases, the measurement value of the disposition increases proportionally.

[0017] In addition, the electronic device may be set to obtain the measurement value of the virtue in the measurement step based on the response of the user to the questions corresponding to ethical norms and integrity, wherein as the practical ability of the ethical norms and the positive degree of integrity increase, the measurement value of the virtue increases proportionally.

[0018] In addition, the electronic device may be set to obtain a measurement value of the personality based on a response of the user to a question corresponding to tolerance and social adaptability in the measurement step, wherein as the positivity of the tolerance and social adaptability increases, the measurement value of the personality increases in proportion to its establishment ratio.

[0019] In addition, the electronic device may be set to obtain a measurement value of the cognitive ability based on a response of the user to a question corresponding to problem-solving ability in the measurement step, wherein as the positivity of the problem-solving ability increases, the measurement value of the cognitive ability increases proportionally thereto, and may be set to obtain a measurement value of the personal environment based on a response of the user to a question corresponding to social support and social organizing ability, wherein as the positivity of the social support and social organizing ability increases, the measurement value of the personal environment increases proportionally thereto.

[0020] In addition, the electronic device may identify the type of the user based on the obtained measurement values in the classification step, and when the measurement values of all five measurement items are lower than the reference value, identify the user as an avoidant type, when the measurement values of disposition and cognitive faculty among the five measurement items are lower than the reference value, identify the user as a compromising type, and when the measurement values of all five measurement items are above the reference value, identify the user as a problem-solving type.

[0021] In addition, the electronic device may determine the degree of digital addiction of the user based on the time the user is exposed to factors (e.g., digital content) inducing digital addiction and the type of the user in the diagnosis step.

[0022] Effects of the Invention

[0023] Embodiments of the present invention can diagnose and counsel behavioral addiction (digital addiction) according to the characteristics of the user, and thus can contribute to formulating user-customized coping strategies.

[0024] In addition, embodiments of the present invention collect data on the personality characteristics of the user through the process of asking and answering with a digital human based on artificial intelligence, and thus can identify the type of the user in an environment similar to an actual counseling session. Also, since there is no need to prepare a separate test questionnaire, the resulting fatigue can be reduced, and there are advantages in terms of accessibility, efficiency, and anonymity protection for treatment.

[0025] In addition, due to the fear of stigma effects and other reasons, those who seek counseling for addiction problems are reluctant to disclose their problems to their families or offline counselors, resulting in limitations in the treatment effect. In the embodiments of the present invention, the above problems can be improved by constructing a digital human of artificial intelligence to establish a counselor-centered counseling model based on the interaction with the counselor, so that the clinical effect can be maximized. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 FIG. is a diagram showing the configuration of an electronic device according to an embodiment of the present invention.

[0027] Figure 2 FIG. is a diagram showing the configuration of a user judgment unit according to an embodiment of the present invention.

[0028] Figure 3 FIG. is a diagram showing the configuration of a second dialogue model according to an embodiment of the present invention.

[0029] Figure 4 FIG. is a diagram showing a control method of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0030] The advantages and features of the present invention and the methods for realizing them can be clarified through the drawings and the embodiments to be described in detail later. However, the present invention is not limited to the embodiments disclosed below, but can be implemented in various different forms, and the present embodiments are provided only to make the disclosure of the present invention complete and to enable those of ordinary skill in the art to fully understand the scope of the present invention. The present invention is defined only by the scope of the claims.

[0031] The terms used in this specification are for describing the embodiments and are not intended to limit the present invention. In this specification, unless otherwise specified, the singular form also includes the plural form. The terms "comprises" and / or "comprising" used in the specification do not exclude the presence or addition of one or more other components other than the components mentioned. Throughout the specification, the same reference numerals mean the same components, and "and / or" includes each and all combinations of the components mentioned. Although "first", "second", etc. are used to describe various components, these components are of course not limited by these terms. These terms are only used to distinguish one component from another. Therefore, of course, the first component mentioned below can also be the second component within the technical idea of the present invention.

[0032] Unless otherwise defined, all terms (including technical and scientific terms) used in this specification may be used with the meanings commonly understood by one of ordinary skill in the technical field to which this specification pertains. Additionally, unless otherwise specifically defined, terms defined in commonly used dictionaries will not be idealized or interpreted overly.

[0033] The terms "unit" or "module" used in this specification refer to hardware components, such as software, a Field Programmable Gate Array (FPGA), or an Application-Specific Integrated Circuit (ASIC), and the "unit" or "module" performs a specific role. However, the "unit" or "module" is not limited to software or hardware. The "unit" or "module" may be configured to be located on an addressable storage medium or may also be configured to operate on one or more processors. Thus, as an example, the "unit" 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 functions provided in the components and the "unit" or "module" may be combined into a smaller number of components and "unit" or "module", or further separated into additional components and "unit" or "module".

[0034] As shown in the figure, spatial relative terms such as "below", "beneath", "lower", "above", and "upper" can be used to conveniently describe the relative relationship between one component and another. The spatial relative terms should be understood to include terms in different directions of the components relative to each other when in use or operation, in addition to the directions shown in the drawings. For example, when flipping the component shown in the drawings, a component described as "below" or "beneath" another component may be located "above" the other component. Thus, the exemplary term "below" can include both the downward direction and the upward direction. The component can also face different directions, so the spatial relative terms can be interpreted according to its orientation.

[0035] The electronic device 10 according to an embodiment of the present invention can conduct counseling for the purpose of preventing, diagnosing, and treating behavioral addiction.

[0036] Substance addiction (or drug addiction) has a structure in which a specific substance acts on the human brain and undergoes a neural transmission adaptation process to produce manifestations of tolerance and withdrawal factors. Behavioral addiction is different from substance addiction and has the characteristic that human actions become the medium of addiction. Types of behavioral addiction include digital addiction, gambling addiction, love addiction, religious addiction, power addiction, sexual addiction, food addiction, shopping addiction, learning addiction, etc.

[0037] It is known that these behavioral addictions are largely influenced by human actions, psychological characteristics, social environmental factors, etc. Therefore, according to human characteristics, even when the exposure time to related behaviors is the same, there are samples that are sensitive to addiction and samples that are not sensitive.

[0038] Based on these characteristics of behavioral addictions, the electronic device 10 classifies users by type according to characteristics through a consultation (first consultation) for judging user characteristics, and can conduct user consultations (second consultation) according to user types.

[0039] Hereinafter, in the specification, mainly the embodiment of digital addiction among behavioral addictions is described. However, it should be understood that the objects of the prevention, diagnosis, and treatment actions according to the embodiments of the present invention are not limited to digital addiction, but also include various types of behavioral addictions such as the above-mentioned gambling addiction.

[0040] Specific embodiments of the control actions of the electronic device 10 will be described in detail with reference to the following drawings.

[0041] First, refer to Figures 1 to 3 The configuration and functions of the electronic device according to an embodiment of the present invention will be described.

[0042] Figure 1 FIG. is a diagram showing the configuration of an electronic device according to an embodiment of the present invention.

[0043] Figure 2 FIG. is a diagram showing the configuration of a user judgment unit according to an embodiment of the present invention.

[0044] Figure 3 FIG. is a diagram showing the configuration of a second dialogue model according to an embodiment of the present invention.

[0045] As Figure 1As shown, the electronic device 10 according to an embodiment of the present invention may include a processor 100, a memory 200, and a communication unit 300. Additionally, the processor 100 may include a learning execution unit 110, a user judgment unit 120, and a consultation execution unit 130. Further, the memory 200 may include a first dialogue model 210 and a second dialogue model 220. Additionally, although not illustrated, the memory 200 may include, in addition to the dialogue model, an artificial intelligence model (e.g., a type judgment model) for performing actions to judge the user type.

[0046] As described above, the electronic device 10 may include various components. Hereinafter, each component will be described in more detail.

[0047] As previously mentioned, the processor 100 of the electronic device 10 may include a learning execution unit 110, a user judgment unit 120, and a consultation execution unit 130.

[0048] The learning execution unit 110 may perform the learning of the artificial intelligence model required for the action of judging the user type based on the theory of character evaluation and the consultation action (second consultation) according to the user type.

[0049] First, in the learning execution unit 110, an artificial intelligence model (first dialogue model) may be trained to generate the questions and answer contents required for the first consultation action in the action of judging the user type.

[0050] For example, the learning execution unit 110 may train the artificial intelligence model to perform the action of providing a digital human visualization image and the voice of the digital human including at least one question. The digital human may refer to a virtual consultant that provides consultation questions to the user based on a pre-trained artificial intelligence model and answers according to the user's response.

[0051] At this time, the digital human may provide questions to the user in a voice form, enabling the user to respond and ask questions in an environment similar to having a conversation with an actual consultant.

[0052] In addition, the digital human may provide a visual image to the user during the conversation with the user, enabling the user to more easily understand the questions of the digital human. Further, the digital human may also provide a visual image to the user during the process of confirming the response content from the user to prevent misinterpreting the user's response.

[0053] In addition, the learning execution unit 110 may train the artificial intelligence model (type judgment model) to identify the user type based on the response of the user during the first consultation.

[0054] The learning and execution unit 110 can train an artificial intelligence model (type judgment model) to obtain, based on the user's response to an inquiry, measurement values of five measurement items corresponding to the five dimensions of the theory of character evaluation (disposition, virtue, personality, cognitive faculty, and person environments), and identify the user type as any one of three types: avoidant, compromising, and problem-solving based on the measurement values.

[0055] In addition, the learning and execution unit 110 can perform the learning of an artificial intelligence model (second dialogue model) for consultation according to the identified user type.

[0056] Specifically, the learning and execution unit 110 can train an artificial intelligence model (second dialogue model) to select consultation content matching the user's type and provide the selected consultation content in at least one of the voices and texts of the digital human.

[0057] The user judgment unit 120 can perform an action for judging the user type based on the artificial intelligence model learned by the learning and execution unit 110.

[0058] The user judgment unit 120 can perform a first consultation action to collect the user response content required for judging the user type. In addition, the user judgment unit 120 can classify the user by type based on the response of the user obtained through the first consultation, and can classify the user into one of three types (for example, avoidant, compromising, and problem-solving) according to the theory of character evaluation.

[0059] For a more detailed description of the actions performed by the user judgment unit 120, reference will be made to Figure 2 .

[0060] As Figure 2 shown, the user judgment unit 120 can include a question generation unit 121, an item measurement unit 122, and a type identification unit 123.

[0061] The question generation unit 121 can generate questions required for the first consultation with the user by driving the first dialogue model stored in the memory 200.

[0062] According to one embodiment, the question generation unit 121 may keep the questions initially presented to the user consistent regardless of who the user is. Alternatively, the question generation unit 121 may also generate initial questions based on the user's basic personal information (e.g., gender, age, occupation, etc.). Without being limited to the described method, the question generation unit 121 may generate the initial questions presented to the user who starts the first consultation through various methods.

[0063] After generating the initial questions and presenting them to the user, when receiving a response corresponding thereto from the user, the question generation unit 121 may generate subsequent questions corresponding to the received user response and present them to the user.

[0064] At this time, when generating questions, the question generation unit 121 may generate questions for measuring five-dimensional items (disposition, virtue, personality, cognitive ability, and situation) corresponding to the theory of person assessment.

[0065] Specifically, the method for generating questions for measuring each of the five items is as follows.

[0066] First, the question generation unit 121 may generate questions for measuring "disposition" among the five-dimensional items. The "disposition" is a latent variable for measuring the strength and brightness of congenital temperament. The "disposition" is an item designed to measure the consistency of a person through strength and the activity through the degree of brightness and darkness. For example, in the present invention, it is judged that the greater the value corresponding to the "disposition" measured for a user with a stronger continuous stability and a more cheerful personality.

[0067] According to the characteristics of the above "disposition" item, the question generation unit 121 may generate questions for evaluating consistency, such as the willpower of the user to adhere to the plan made by himself / herself. As questions for measuring the "disposition" item, the question generation unit 121 may generate questions such as "Do you have an experience of continuously performing the planned exercise for more than 1 month?" and "Are you often evaluated as having a cheerful personality by people around you?"

[0068] Next, the question generation unit 121 may generate questions for measuring "virtue" among the five-dimensional items. The "virtue" is a variable for measuring the daily practice ability of an individual's ethical norms and integrity (consistency between words and deeds) constructed through acquired efforts. It is judged that the greater the value corresponding to the "virtue" measured for a user with more ethical norms and integrity.

[0069] Based on the characteristics of the above-mentioned "morality" item, the question generation unit 121 can generate questions such as "Do you usually follow moral guidelines, act reasonably and honestly?"; "Is there a situation where you often ignore the principle of modesty, focus on superficial adornment and act unreasonably?"; "Do you usually maintain a high degree of consistency between words and deeds and faith in handling affairs?"; "Is there a situation of inconsistency between words and deeds and lack of faith in handling affairs?"

[0070] Next, the question generation unit 121 can generate questions for measuring "personality" in the five-dimensional item. The "personality" is an item designed to measure the caring and inclusiveness towards others and social adaptability. It is judged that the higher the inclusiveness and stronger the social adaptability of a user, the larger the value corresponding to the "personality" measured.

[0071] Based on the characteristics of the above-mentioned "personality" item, the question generation unit 121 can generate questions such as "Do you usually have a high degree of caring and inclusiveness towards others?"; "Do you usually lack caring and inclusiveness towards others?"; "Do you usually get along well with people around you?"; "Do you usually not get along well with people around you?"

[0072] Next, the question generation unit 121 can generate questions for measuring "cognitive faculty" in the five-dimensional item. The "cognitive faculty" is a variable used to measure a person's problem-solving ability. It is evaluated that the higher the excellent problem-solving ability of a user, the larger the value corresponding to the "cognitive faculty" measured.

[0073] Based on the characteristics of the "cognitive faculty" item, the question generation unit 121 can generate questions such as "Are you good at using your own experience and knowledge and the suggestions of people around you?"; "Do you often encounter difficulties in the problem-solving process because you are stubborn about your own experience and knowledge and problem-solving ability?"; "Do you prefer reasonable and fundamental problem-solving methods?"; "Compared with reasonable and fundamental problem-solving methods, do you tend to rely more on improvisational thinking in problem-solving?"

[0074] Finally, the question generation unit 121 can generate questions for measuring "personal environments" in the five-dimensional items. The "personal environments" is a variable for measuring a person's social status and degree of social activities. In addition, the "personal environments" is a variable for measuring the degree of social support from organizational members or people around, and social organizations (social achieved status and social sphere) that are valued in community activities. When it is judged that the social support or social organizational ability is more excellent, the value corresponding to the "personal environments" item measured can be larger.

[0075] According to the characteristics of the "personal environments" item, the question generation unit 121 can generate questions such as "Are you generally respected and admired among organizational members or people around?", "Do you generally fail to gain respect and trust among organizational members or people around?", "Do you usually actively participate in activities to help the community and others?", and "Do you usually not actively participate in activities to help the community and others?".

[0076] In addition, the question generation unit 121 can judge whether to generate additional questions and whether to change the theme of the additional questions according to the completion degree of the item measurement judged by the item measurement unit 122. If the item measurement is not completed, additional questions can be generated.

[0077] For example, when the item measurement unit 122 judges that the measurement of the five-dimensional item is all completed, a corresponding signal is transmitted to the question generation unit 121. Accordingly, the question generation unit 121 can not generate additional subsequent questions and end the first consultation. On the contrary, when the question generation unit 121 receives a signal that only four of the five measurement items are completed from the item measurement unit 122, it can control to change the theme of the additional questions.

[0078] In addition, when receiving a user response, the question generation unit 121 can numerically value the specificity of the response and determine the degree of specification of the additional questions according to the numerical value of the specificity.

[0079] As a method for numerically valuing the specificity of the response, it can include, for example, a method for measuring the weight of the response, a method for measuring the diversity of words included in the response, or a method for measuring the weight and diversity of words in the response.

[0080] When the obtained user response does not reach the specific numerical value of the response to be obtained, the question generation unit 121 can generate additional questions with enhanced specification.

[0081] For example, when, in response to a question "Do you usually follow the planned schedule?", an answer with a quantity below a reference value such as "yes" or "no" (e.g., with a word count of 10 words or less) or a word diversity below a reference value (e.g., three or less) is received from the user, the question generation unit 121 may present an additional question with enhanced degree of specification under the same theme, such as "Have you ever persisted in implementing a plan for more than one month?". Thereafter, also during the consultation process, when it is determined that the obtained response does not reach the target specificity value, the question generation unit 121 may continue to generate additional questions with enhanced degree of specification.

[0082] The item measurement unit 122 may provide questions to the user through the question generation unit 121 and obtain the user's responses, and measure five-dimensional items (character temperament, morality, personality, cognitive ability, and situation) based on the person assessment theory according to the user's responses.

[0083] The item measurement unit 122 may input the user's responses into an artificial intelligence model (type judgment model) trained by the learning execution unit 110 and measure the values of the five measurement items.

[0084] Specifically, for example, the item measurement unit 122 may analyze each response of the user input into the artificial intelligence model, and plot it on an n-dimensional (preferably two-dimensional or three-dimensional) coordinate according to the correlation value with the character traits represented by each item in the five-dimensional items. Thereafter, the item measurement unit 122 may calculate the average value of the coordinate values of each point for which the coordinate values are specified, and use the calculated average value of the coordinate values of each point to calculate the measurement value of each item in the five-dimensional items. At this time, the axis of each coordinate may be specified as a sub-item corresponding to the five-dimensional item (for example, the sub-items of "character temperament" correspond to consistency and activity).

[0085] Next, a method for the item measurement unit 122 to calculate the measurement value of each of the five items using the method described above will be described. First, the process for the item measurement unit 122 to calculate the measurement value of the "character temperament" item is as follows. The item measurement unit 122 may calculate the correlation values of the sub-items "consistency" and "activity" corresponding to the user's temperament and the "character temperament" item by inputting the user's responses. At this time, when determining the correlation value between the "character temperament" item and the user's characteristics, the artificial intelligence model may be designed such that the value of the x coordinate increases corresponding to the degree of "consistency" (the stronger the consistency), and the value of the y coordinate increases corresponding to the degree of "activity" (the more active and cheerful).

[0086] According to various embodiments, the artificial intelligence model can be designed such that after designating each axis of a graph with sub-items of each of the five-dimensional items, the artificial intelligence model further records the correlation values of each item and user characteristics on a graph including additional axes on this basis. In addition, the artificial intelligence model can calculate and record the reliability value of the user's response on an additional axis (e.g., the z-axis). The reliability value can be a value judged based on items such as the filling speed of the user's response and the degree of consistency between the user's responses.

[0087] Based on the measured value of each of the five items measured by the item measurement unit 122, the type identification unit 123 can determine the type of the user as one of three preset types.

[0088] At this time, the type identification unit 123 can classify the user into one of three types based on the theory of person assessment (e.g., avoidant, compromising, and problem-solving). The avoidant type has the lowest motivation and willpower for solving the problem of behavioral addiction (e.g., digital addiction). The problem-solving type has the highest motivation and willpower for solving the problem of behavioral addiction and has full confidence in overcoming behavioral addiction. In addition, the compromising type has a higher motivation for solving the problem of behavioral addiction than the avoidant type but lower than the problem-solving type and belongs to an intermediate type. For example, a group that has the willpower to solve questions about behavioral addiction but lacks confidence can be classified as the compromising type.

[0089] Specifically, when the measured values of all five measurement items are lower than the reference value, the type identification unit 123 identifies the user as the avoidant type. When the measured values of disposition and cognitive faculty among the five measurement items are lower than the reference value, the type identification unit 123 identifies the user as the compromising type. When the measured values of all five measurement items are above the reference value, the type identification unit 123 identifies the user as the problem-solving type.

[0090] The counseling performing unit 130 of the processor 100 can provide counseling (second counseling) on the user's behavioral addiction according to the type of the user identified by the user judgment unit 120.

[0091] The counseling performing unit 130 can select counseling content matching the type of the user and provide the selected counseling content through the voice of the digital human.

[0092] In addition, in order to provide consultation based on consultation content matching the user type, the consultation conducting unit 130 can utilize multiple second dialogue models, which are trained to provide consultation content matching each of multiple types related to tolerance to behavioral addiction (e.g., digital addiction).

[0093] like Figure 3 As shown, the second dialogue model can be composed of three types of avoidance corresponding model 221, compromise corresponding model 222, and problem-solving corresponding model 223 according to the type of each user.

[0094] When the consultation unit 130 uses the avoidance-type corresponding model 221 to provide consultation on the behavior addiction of the avoidance-type user, the possibility and severity of the user's behavior addiction can be set to the highest value among the three types and generate questions and answers required for consultation. Similarly, when the consultation unit 130 uses the compromise-type corresponding model 222 to provide consultation on the behavior addiction of the compromise-type user, the possibility and severity of the user's behavior addiction can be set to the middle value, and when the consultation is performed using the problem-solving corresponding model 223, the possibility and severity of the user's behavior addiction can be set to the lowest value among the three types.

[0095] As described above, when the possibility and severity of behavioral addiction are classified by user type, the consultation unit 130 can set the risk level of behavioral addiction to level 3 in the case of avoidant users for the same level of user behavior, and to level 2 and level 1 in the case of compromising users and problem-solving users, respectively. In addition, the consultation unit 130 can classify the same level of user behavior into level 3, level 2, and level 1 according to the severity of behavioral addiction, according to avoidant, compromising, and problem-solving types, respectively. The higher the level, the more the treatment level and the degree of exhortation for action improvement can be gradually improved and set, and then the consultation can be conducted. In addition, for example, when the degree of exhortation for action improvement increases, the number of appearances of articles advising on improving addiction symptoms during the consultation process can be set to increase.

[0096] In addition, according to various embodiments, the consultation unit 130 can generate different consultation questions and responses according to each type of user. Even if users are judged to have the same level of addiction possibility and severity, if they are identified as different user types, the consultation unit 130 will consult with users of the type with weaker tolerance to behavioral addiction (e.g., digital addiction) by increasing the level of treatment and the degree of exhortation for action improvement accordingly. For example, for the type with the weakest addiction tolerance, that is, avoidant users, compared with problem-solving users, for the same severity of addiction status, they may accept a higher level of action improvement requirements.

[0097] In addition, for types with weaker tolerance to behavioral addictions (e.g., digital addiction), the counseling performing unit 130 can strengthen the requirements for behavior improvement by correspondingly increasing various other setting values during the counseling process (such as the voice volume of the digital human, the counseling duration performed by the digital human, etc.).

[0098] The memory 200 can store commands and algorithms required to execute the overall operations according to the embodiments of the present invention. The memory 200 according to the embodiments of the present invention can store various artificial intelligence models for identifying the type of user and performing counseling on the user's behavioral addiction according to the identified user type.

[0099] The memory 200 can include a first dialogue model 210, which is trained to be able to generate inquiries and responses for the counseling step when counseling is performed to determine the type of user. In addition, the memory 200 can include a second dialogue model 220, which is trained to be able to provide counseling content matching each user type. The second dialogue model 220 can be an artificial intelligence model trained to be able to provide counseling content matching each of multiple types related to the tolerance of behavioral addiction (e.g., digital addiction).

[0100] The second dialogue model 220 can be configured in multiple numbers to respectively match each user type. The second dialogue model 220 can include corresponding models respectively corresponding to each type of user (avoidant type, compromising type, and problem-solving type). As Figure 3 shown, the second dialogue model 220 can include an avoidant type corresponding model 221, a compromising type corresponding model 222, and a problem-solving type corresponding model 223.

[0101] The communication unit 300 can be used to perform communication between the electronic device 10 of the present invention and a user terminal (not shown). The user terminal can achieve a communication connection through the communication unit 300 to receive user type classification provided by the electronic device 10 and counseling actions for behavioral addiction according to the user type.

[0102] Figure 4 It is a diagram showing a control method of an electronic device according to an embodiment of the present invention.

[0103] As Figure 4 shown, the electronic device 10 can perform an action 405 of providing an inquiry to the user, an action 410 of obtaining a user response, an action 415 of obtaining a measured value of a measurement item based on the user response, an action 420 of identifying the user type based on the measured value, and an action 425 of performing counseling using a model corresponding to the user type.

[0104] In addition, the operations 405 and 410 may correspond to a consultation step, the operation 415 of obtaining a measurement value may correspond to a measurement step, the operation 420 of identifying a user type may correspond to a classification step, and the operation 425 of performing a consultation using a model corresponding to the user type may correspond to an intervention step.

[0105] In addition, the control method of the electronic device 10 according to an embodiment of the present invention may further include: a diagnosis step of determining the degree of digital addiction of the user based on the time the user is exposed to factors (e.g., excessive addiction to digital content, etc.) that induce behavioral addiction (digital addiction) and the type of the user.

[0106] Briefly, the consultation method according to user type of the electronic device according to an embodiment of the present invention may be implemented by performing a consultation step, a measurement step, a classification step, an intervention step, and a diagnosis step through the electronic device.

[0107] The consultation step may refer to a step of providing at least one of a visual image of a digital human and speech and text of the digital human including at least one question and obtaining a response of the user to the question.

[0108] In addition, in the measurement step performed after the consultation step, the electronic device may perform an operation of obtaining measurement values of five measurement items including the disposition, virtue, personality, cognitive faculty, and personal environments of the user according to the response of the user.

[0109] In addition, in the classification step, the electronic device may perform an operation of identifying the type of the user related to the tolerance of digital addiction based on the obtained measurement values.

[0110] In addition, in the intervention step, the electronic device may select consultation content matching the type of the user and provide the selected consultation content through at least one of the speech and text of the digital human.

[0111] In addition, the electronic device may include: a first dialogue model trained to be able to generate questions and responses for the consultation step; and a plurality of second dialogue models trained to be able to provide consultation content matching each of a plurality of types related to the tolerance of digital addiction. In addition, the electronic device may obtain consultation content based on the second dialogue model matching the type of the user among the plurality of second dialogue models in the intervention step and provide the obtained consultation content through at least one of the speech and text of the digital human.

[0112] In addition, the electronic device may be set such that, in the measurement step, based on the user's responses to questions corresponding to consistency and activity, a measurement value of the personality trait is obtained, and the measurement value of the personality trait increases proportionally to the degrees of the user's consistency and activity judged according to the responses.

[0113] In addition, the electronic device may be set such that, in the measurement step, based on the user's responses to questions corresponding to ethical norms and integrity, a measurement value of the moral character is obtained, and the measurement value of the moral character increases proportionally to the degrees of the user's practical ability of ethical norms and integrity judged according to the responses.

[0114] In addition, the electronic device may be set such that, in the measurement step, based on the user's responses to questions corresponding to inclusiveness and social adaptability, a measurement value of the personality is obtained, and the measurement value of the personality increases proportionally to the degrees of the user's inclusiveness and social adaptability judged according to the responses.

[0115] In addition, the electronic device may be set such that, in the measurement step, based on the user's responses to questions corresponding to problem-solving ability, a measurement value of the cognitive ability is obtained, and the measurement value of the cognitive ability increases proportionally to the degree of the user's problem-solving ability judged according to the responses, and may be set such that, based on the user's responses to questions corresponding to social support and social organizing ability, a measurement value of the cognitive ability is obtained, and the measurement value of the cognitive ability increases proportionally to the degrees of the user's social support and social organizing ability.

[0116] In addition, the electronic device may, in the classification step, identify the type of the user based on the obtained measurement values, and when the measurement values of all five measurement items are lower than the reference value, identify the user as an avoidant type, when the measurement values of the personality trait (disposition) and the cognitive ability among the five measurement items are lower than the reference value, identify the user as a compromising type, and when the measurement values of all five measurement items are above the reference value, identify the user as a problem-solving type.

[0117] At this time, the avoidant type may refer to a group with weak willpower to solve behavioral addiction problems, the compromising type may refer to a group with the willpower to solve behavioral addiction problems but lacking self-confidence, and the problem-solving type may refer to a group with full confidence in overcoming behavioral addiction and strong willpower to solve problems.

[0118] As described above, in the classification step, the electronic device may classify the user's type into one of three types based on the measured values of the five measurement items.

[0119] On the other hand, according to various embodiments, in the classification step, the electronic device may, in addition to the measured values of the five measurement items, also perform an action of classifying the type according to the user's age and gender. For example, in the process of determining avoidant, compromising, and problem-solving types, the electronic device divides users into 8 groups of young children and adolescents and those aged 10 to 70 according to different age groups, and then adopts different calculation methods to determine the type according to the attributes of each age group. In addition, the electronic device may divide the users belonging to each age group into males and females, and then differently apply the calculation method for type judgment according to gender attributes.

[0120] After confirming the user type, the electronic device may provide customized services according to different user types.

[0121] Taking digital addiction, which is one form of behavioral addiction, as an example, in the diagnosis step, the electronic device may derive the user's digital addiction form and addiction level (score) as data based on the user's exposure time to specific digital content, etc. and the user type classification, and on this basis, set a customized intervention method according to the type of the counselor.

[0122] 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.

[0123] The memory 200 may store various programs and data required for the operation of the electronic device. The memory 200 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), etc.

[0124] The communication unit 300 can communicate with external devices. In particular, the communication unit 300 may include various communication chips, such as Wi-Fi chips, Bluetooth chips, wireless communication chips, near-field communication (NFC) chips, Bluetooth Low Energy (BLE) chips, etc. At this time, the Wi-Fi chip, Bluetooth chip, and NFC chip communicate via LAN, Wi-Fi, Bluetooth, and NFC respectively. When using a Wi-Fi chip or a Bluetooth chip, various connection information such as a service set identifier (SSID) and a session key is first sent and received, and after establishing a communication connection using this information, various information can be sent and received. A wireless communication chip refers to a chip that communicates according to various communication standards such as the Institute of Electrical and Electronics Engineers (IEEE), Zigbee, 3rd Generation (3G), 3rd Generation Partnership Project (3GPP), and Long Term Evolution (LTE).

[0125] The processor 100 can control the overall operation of the user device by using various programs stored in the memory 200. The processor may be composed of a RAM, a ROM, a graphics processing unit, a main central processing unit (CPU), first to nth interfaces, and a bus. At this time, the RAM, ROM, graphics processing unit, main central processing unit (CPU), first to nth interfaces, etc. can be connected to each other via the bus.

[0126] The RAM is used to store an operating system (O / S) and application programs. Specifically, when the electronic device is started, the operating system can be stored in the RAM, and various application program data selected by the user can be stored in the RAM.

[0127] The command set for system startup and the like are stored in the ROM. When a power-on command is input to supply power, the main Central Processing Unit (CPU) copies the operating system stored in the memory 200 to the RAM according to the instructions stored in the ROM, and starts the system by executing the operating system. When the startup is completed, the main Central Processing Unit (CPU) copies various application programs stored in the memory 200 to the RAM, and performs various actions by executing the application programs copied to the RAM.

[0128] The main Central Processing Unit (CPU) starts up by accessing the memory 200 and using the operating system stored in the memory 200. In addition, the main Central Processing Unit (CPU) performs various actions using various programs, contents, data, etc. stored in the memory 200.

[0129] The first to the nth interfaces are connected to the above various components. One of the first to the nth interfaces can also be a network interface connected to an external device through a network.

[0130] On the other hand, further, the processor can control an artificial intelligence model. In this case, the control unit can of course include a graphics processing unit (e.g., GPU) for controlling the artificial intelligence model.

[0131] The processor 100 can include one or more cores (not shown), a graphics processing unit (not shown), and / or a connection path (e.g., a bus, etc.) for receiving and transmitting signals to and from other components.

[0132] The processor according to one embodiment performs the method described in connection with the present invention by executing one or more instructions stored in the memory 200.

[0133] On the other hand, the processor 100 can also 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 inside the processor. In addition, the processor 130 can also be implemented in the form of a system on chip (SoC) including at least one of a graphics processing unit, a RAM, and a ROM.

[0134] The program (one or more instructions) for processing and controlling the processor 100 can be stored in the memory 200. The programs stored in the storage unit can be divided into multiple modules according to functions.

[0135] The steps of the method or algorithm described in connection with the embodiments of the present invention can be implemented directly in hardware, or by software modules executed by hardware, or by a combination of both. The software modules can also reside in a RAM, ROM, erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), flash memory, hard disk, removable disk, CD-ROM, or any other form of computer-readable recording medium known in the technical field to which the present invention pertains.

[0136] The elements of the present invention can be implemented as a program (or application program) and stored in a medium so as to be combined with a computer as hardware and executed. The elements of the present invention can be implemented by software programming or software elements, and similarly, the embodiments can include various algorithms implemented by a combination of data structures, procedures, routines, or other programming structures, and can be implemented by programming or scripting languages such as C, C++, Java, assembler, etc. The functional aspects can be implemented by algorithms executed on one or more processors 100.

[0137] The present invention has been described in detail with reference to the above examples. However, those of ordinary skill in the art to which the present invention pertains can make modifications, changes, and variations to the examples without departing from the scope of the present invention. In short, it is not necessary to separately include all the functional blocks shown in the drawings or to perform exactly in the order shown in the drawings to achieve the expected effects of the present invention. It should be noted that even if not, it may still fall within the technical scope of the present invention described in the claims.

Claims

1. A control method for an electronic device, characterized in that: Including: A consultation step, where the electronic device provides a digital human visualization image and the voice of the digital human including at least one question, and obtains a response from the user to the question; A measurement step, where the electronic device obtains measurement values of five measurement items including the user's personality traits, moral character, personality, cognitive ability, and situation based on the response; and A classification step, where the electronic device identifies the type of the user related to the tolerance of digital addiction based on the obtained measurement values.

2. The control method for an electronic device according to claim 1, characterized in that: The control method for the electronic device further includes: An intervention step, where the electronic device selects consultation content matching the type of the user and provides the selected consultation content through the voice of the digital human.

3. The control method for an electronic device according to claim 2, characterized in that: The electronic device includes: A first dialogue model trained to be able to generate questions and responses for the consultation step, and Multiple second dialogue models trained to be able to provide consultation content matching each of multiple types related to the tolerance of digital addiction; In the intervention step, Obtain consultation content according to the second dialogue model matching the type of the user among the multiple second dialogue models, and provide the obtained consultation content through the voice of the digital human.

4. The control method for an electronic device according to claim 1, characterized in that: In the measurement step, Based on the response of the user to questions corresponding to consistency and activity, obtain the measurement value of the personality traits, where the obtained measurement value of the personality traits is a value proportional to the degree of the user's consistency and activity.

5. The control method for an electronic device according to claim 1, characterized in that: In the measurement step, Based on the response of the user to questions corresponding to ethical norms and integrity, obtain the measurement value of the moral character, where the obtained measurement value of the moral character is a value proportional to the degree of the user's practical ability of ethical norms and integrity.

6. The control method for an electronic device according to claim 1, characterized in that: In the measurement step, Based on the response of the user to questions corresponding to inclusiveness and social adaptability, obtain the measurement value of the personality, where the obtained measurement value of the personality is a value proportional to the degree of the user's inclusiveness and social adaptability.

7. The control method for an electronic device according to claim 1, characterized in that: In the measurement step, Based on the response of the user to questions corresponding to problem-solving ability, obtain the measurement value of the cognitive ability, where the obtained measurement value of the cognitive ability is a value proportional to the degree of the user's problem-solving ability.

8. The control method for an electronic device according to claim 1, characterized in that: In the measurement step, Obtain a measurement value of the situation based on the user's response to questions corresponding to social support and social organizational ability, where the obtained measurement value of the situation is a value proportional to the degree of the user's social support and social organizational ability.

9. The control method of an electronic device according to claim 1, characterized in that In the classification step, Identify the type of user based on the measurement values of the five measurement items of the character, morality, personality, cognitive ability, and situation, where If the measurement values of all five measurement items are lower than the reference value, the user is identified as an avoidant type, and the avoidant type is defined as a group with weak willpower to solve problems. If the measurement values of the character (disposition) and cognitive ability (cognitive faculty) among the five measurement items are lower than the reference value, the user is identified as a compromising type, and the compromising type is defined as a group with weak self-confidence although having the willpower to solve problems. If the measurement values of all five measurement items are above the reference value, the user is identified as a problem-solving type, and the problem-solving type is defined as a group with full willpower and self-confidence to solve problems.

10. The control method of an electronic device according to claim 1, characterized in that The control method of the electronic device further includes: A diagnosis step of judging the degree of digital addiction of the user based on the time the user is exposed to factors inducing digital addiction and the type of the user.

11. An electronic device, characterized in that Comprising: A memory, A communication unit for communicating with at least one user terminal, and A processor that provides a digital human visualization image and the voice of the digital human including at least one question through the communication unit, obtains the user's response to the question, and based on the response, obtains the measurement values of five measurement items including the user's character, morality, personality, cognitive ability, and personal environment, and identifies the type of the user related to the tolerance of digital addiction based on the obtained measurement values.

12. A non-transitory computer-readable medium storing at least one instruction, wherein, The instructions are executed by the processor of the electronic device to cause the electronic device to execute the control method of the electronic device according to claim 1.

Images