Psychotherapy system based on mind theory

Abstract

The present invention relates to a psychotherapy system and, more specifically, to a system for analyzing a psychological state of a user on the basis of Mind Theory and Xesmind Theory on the basis of user input data, designing a personalized learning curriculum through an analyzed result, providing same as learning content, and analyzing progress of a learning process to provide feedback, thereby supporting treatment of depression and other psychological diseases.

Description

Psychotherapy system based on theory of mind

[0001] The present invention relates to a psychotherapy system, and more specifically, to a system that supports the treatment of depression and other psychological disorders by analyzing a user's psychological state based on theory of mind and sexual theory of mind, designing a personalized learning curriculum based on this, and providing feedback by analyzing the progress of the learning process.

[0002] In modern society, psychological disorders such as depression have become a major health issue. In particular, if left untreated, depression can significantly reduce an individual's quality of life and, in severe cases, lead to extreme consequences such as suicide.

[0003] Conventional psychotherapy methods typically include psychological counseling and medication, but they have limitations such as a lack of personalized approaches or difficulties in long-term management.

[0004] Recently, psychotherapy devices utilizing digital technology are being developed, but the technical implementation is insufficient to ensure the reliability of user data and provide personalized treatment processes.

[0005] In order to solve the above problem, the present invention aims to solve the following problems:

[0006] We provide a system that can reliably evaluate depressive states and psychological characteristics by quantitatively analyzing user input data.

[0007] Maximizes the personalization of psychotherapy by designing a user-customized learning curriculum based on Theory of Mind and Theory of the Mind regarding sexuality.

[0008] Implement technology that can dynamically adjust the treatment process by collecting and analyzing user feedback during the learning process.

[0009] It provides a system that provides motivation to help users continuously follow the learning process and efficiently manages learning content.

[0010] A psychotherapy system based on theory of mind according to an embodiment of the present invention for solving the above problem may include the features of analyzing a psychological state based on theory of mind and sexual theory of mind based on user input data for the treatment of depression and psychological disorders, designing a personalized learning curriculum based on the analyzed results, providing this as learning content, and collecting feedback to customize the learning process.

[0011] In one embodiment, a user terminal that collects user input data;

[0012] It may include a theory of mind analysis module and a theory of mind application module that quantitatively evaluate psychological states by performing theory of mind and theory of mind analysis; a curriculum generation module that generates a personalized learning plan based on the analysis results; a content management module that provides user-customized learning content based on the generated learning plan; a feedback provision module that adjusts the learning process by analyzing learning results and user feedback; and a server that processes and stores data by connecting the user terminal and each module.

[0013] In one embodiment, the theory of mind analysis module may be characterized by quantifying psychological state data input by a user to derive a depression score, calculating the ratio of the depression score to a normal state reference value, converting the ratio into a logarithmic function to mitigate the influence of excessive values, converting the reliability of the input data into a trigonometric function to reflect non-linear influences, calculating a psychological state score according to a formula, and setting the valid range of the ratio to 0 to 5, considering it a normal state when it is 1, deteriorating the psychological state compared to the reference when it exceeds 1, setting it as a range where the severity of the psychological state can be evaluated when it is 5 or less, and determining that a state requiring psychotherapy is required when it exceeds 1.

[0014] In one embodiment, the sexual theory of mind application module is characterized by analyzing personality trait data input by a user to derive a personality trait score, evaluating personality differences by comparing the derived personality trait score with a reference value, personalizing the learning direction according to personality traits such as introversion, extraversion, and emotional regulation ability, and improving the reliability of the learning design by analyzing the reliability of user data; and the curriculum generation module is characterized by designing a user-customized learning plan by combining data provided by the theory of mind analysis module and the sexual theory of mind application module, evaluating the performance rate based on the learning task performance rate and the learning goal reference value, proposing multiple learning activities including emotional stability training, writing an emotional journal, and meditation training considering learning efficiency, and dynamically adjusting the learning cycle and difficulty level to suit the user's condition.

[0015] In one embodiment, the content management module may be characterized by providing learning content according to a learning plan designed in the curriculum generation module, storing, managing, and distributing learning materials such as videos, text, and quizzes, dynamically curating additional materials according to the user's progress status, and being designed so that the learning content can enhance user learning efficiency.

[0016] In one embodiment, the feedback providing module may be characterized by collecting and analyzing learning task performance results and user feedback data, adjusting the learning process based on the analyzed data, providing positive reinforcement messages or suggestions to modify learning goals according to the user's performance and progress, and improving the user's learning experience and increasing learning persistence.

[0017] According to the present invention, by analyzing the user's psychological state and evaluating it with quantitative data, and designing a personalized learning curriculum based on this, it is possible to provide user-customized therapeutic effects that were lacking in existing psychotherapy methods.

[0018] In addition, the effectiveness of treatment can be maximized by dynamically adjusting the treatment process using learning progress and feedback data.

[0019] Furthermore, by efficiently managing and providing learning content, users' learning persistence can be enhanced and therapeutic effects maintained in the long term.

[0020] The effects according to the present invention are not limited to those exemplified above, and a wider variety of effects are included within the present invention.

[0021] Figure 1 illustrates an overall relationship diagram according to the present invention.

[0022] Hereinafter, various embodiments are described in more detail with reference to the attached drawings. The embodiments described in this specification may be modified in various ways. Specific embodiments may be depicted in the drawings and described in detail in the detailed description. However, specific embodiments disclosed in the attached drawings are intended only to facilitate understanding of various embodiments. Accordingly, the technical concept is not limited by specific embodiments disclosed in the attached drawings, and it should be understood that it includes all equivalents or substitutions that fall within the spirit and scope of the invention.

[0023] Terms including ordinal numbers, such as first, second, etc., may be used to describe various components, but these components are not limited by the aforementioned terms. The aforementioned terms are used solely for the purpose of distinguishing one component from another.

[0024] Functions related to artificial intelligence according to the present disclosure are operated through a processor and memory. The processor may be composed of one or more processors. In this case, the one or more processors may be general-purpose processors such as CPUs, APs, and DSPs (Digital Signal Processors), graphics-dedicated processors such as GPUs and VPUs (Vision Processing Units), or artificial intelligence-dedicated processors such as NPUs. The one or more processors control the processing of input data according to predefined operation rules or artificial intelligence models stored in memory. Alternatively, if the one or more processors are artificial intelligence-dedicated processors, the artificial intelligence-dedicated processors may be designed with a hardware structure specialized for processing a specific artificial intelligence model.

[0025] The predefined rules of operation or artificial intelligence models are characterized by being created through learning. Here, being created through learning means that a basic artificial intelligence model is trained using a number of training data by a learning algorithm, thereby creating predefined rules of operation or artificial intelligence models configured to perform desired characteristics (or objectives). Such learning may be performed on the device itself where the artificial intelligence according to the present disclosure is executed, or it may be performed through a separate server and / or system. Examples of learning algorithms include supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning, but are not limited to the examples described above.

[0026] An artificial intelligence model can be composed of multiple neural network layers. Each of the multiple neural network layers has multiple nodes and weight values, and performs neural network operations through calculations between the results of previous layers and the multiple weights. The multiple weights possessed by the multiple neural network layers can be optimized based on the learning results of the artificial intelligence model. For example, multiple weights can be updated so that the loss value or cost value obtained by the artificial intelligence model during the learning process is reduced or minimized. Additionally, to minimize the loss value or cost value, multiple weights can be updated in a direction that minimizes the gradient associated with the loss value or cost value. Artificial neural networks may include deep neural networks (DNNs), such as Convolutional Neural Networks (CNNs), Deep Neural Networks (DNNs), Recurrent Neural Networks (RNNs), Restricted Boltzmann Machines (RBMs), Deep Belief Networks (DBNs), Bidirectional Recurrent Deep Neural Networks (BRDNNs), or Deep Q-Networks, but are not limited to the examples mentioned above.

[0027] A network is a network that serves as a transmission path for web pages; it may be a closed network such as a LAN (Local Area Network) or WAN (Wide Area Network), but it is desirable for it to be an open network such as the Internet. The Internet refers to a global open computer network structure that provides the TCP / IP protocol and various services existing at its upper layers, namely HTTP (HyperText Transfer Protocol), Telnet, FTP (File Transfer Protocol), DNS (Domain Name System), SMTP (Simple Mail Transfer Protocol), SNMP (Simple Network Management Protocol), NFS (Network File Service), and NIS (Network Information Service).

[0028] Terminals can be implemented in various forms. For example, the terminals described in this specification may include mobile terminals such as smartphones, tablet PCs, PDAs, portable multimedia players, and MP3 players, as well as fixed terminals such as smart TVs and desktop computers.

[0029] In this specification, terms such as “comprising” or “having” are intended to specify the existence of the features, numbers, steps, actions, components, parts, or combinations thereof described in the specification, and should be understood as not precluding the existence or addition of one or more other features, numbers, steps, actions, components, parts, or combinations thereof. When a component is described as being “connected” or “connected” to another component, it should be understood that it may be directly connected to or connected to that other component, or that there may be other components in between. On the other hand, when a component is described as being “directly connected” or “directly connected” to another component, it should be understood that there are no other components in between.

[0030] Meanwhile, a "module" or "part" for a component as used in this specification performs at least one function or operation. Furthermore, a "module" or "part" may perform a function or operation by hardware, software, or a combination of hardware and software. Additionally, a plurality of "modules" or a plurality of "parts," excluding a "module" or "part" that must be performed on specific hardware or on at least one processor, may be integrated into at least one module. A singular expression includes a plural expression unless the context clearly indicates otherwise.

[0031] In addition, power, power transmission, and control therefor for the following assembly configurations and embodiments, including "by control," follow conventional technology including terminals, applications, hardware control modules, etc., so they are omitted to avoid redundancy.

[0032] In addition, the operation embodiments and configurations described in a general manner without being explained in detail below follow the prior art and are omitted in order to focus on describing the purpose of the present invention and the resulting effects.

[0033] Furthermore, in describing the present invention, if it is determined that a detailed description of related known functions or configurations may unnecessarily obscure the essence of the invention, such detailed description is abbreviated or omitted.

[0034] The system may include a theory of mind analysis module (10), a theory of mind application module (20), a curriculum creation module (30), a content management module (40), and a feedback provision module (50).

[0035] The theory of mind analysis module (10) is a module that performs the role of diagnosing an individual's psychological characteristics and current state by analyzing the user's psychological state, and analyzes user input data (emotion selection, state description, etc.) to quantify or classify the psychological state (e.g., depression, anxiety, anger, etc.), and derives psychological characteristics and social interaction states based on the theory of mind.

[0036] The sexual theory of mind application module (20) analyzes the user's sexual psychological state and provides personality traits linked to the theory of mind and personalized treatment plans. It analyzes the sexual psychological state based on user input data, derives psychological tendencies (personality type, social relationship dynamics, etc.) based on personality traits, and transmits them to the curriculum generation module (30).

[0037] The curriculum creation module (30) designs a learning process based on data transmitted from the theory of mind analysis module (10) and the theory of mind application module (20), establishes a personalized learning plan, determines the difficulty, duration, and learning cycle of the learning process, and subdivides tasks and learning goals.

[0038] The content management module (40) creates, stores, and distributes content necessary for learning, provides materials necessary for the learning curriculum in various formats, and dynamically updates and curates content according to the user's progress status.

[0039] The feedback provision module (50) collects and analyzes feedback entered by the user during the learning process to modify the learning direction or provide motivation, analyzes the feedback results to check learning performance and suggest improvements, and provides motivational materials to improve the user's learning experience.

[0040] The theory of mind analysis module (10) and the theory of mind application module (20) each analyze psychological states and personality traits and generate data.

[0041] The analysis results are passed to the curriculum creation module (30) to design a personalized learning process.

[0042] Based on the designed learning process, the content management module (40) provides suitable learning materials to the user.

[0043] Feedback entered by the user during learning is analyzed by the feedback provision module (50) to reflect improvements in the learning process or provide additional motivation.

[0044] In the overall flow of the data collection method, key factors are collected based on user input data through surveys, psychological diagnostic evaluations, and personality tests, and the data is transmitted to each module after undergoing a quantitative scoring process.

[0045] Reference values ​​are established by utilizing external databases such as demographic data, psychological research data, and average values ​​of personality traits.

[0046] It evaluates learning suitability and efficiency by analyzing behavioral data generated during the learning process.

[0047] Enhance data reliability through periodic surveys and feedback collection, and continuously update the module's results.

[0048] In one embodiment, the theory of mind analysis module (10), the sexual theory of mind application module (20), and the curriculum generation module (30) each calculate a score using the following mathematical formulas:

[0049] [Mathematical Formula 1]

[0050]

[0051] Here, S_m is a score for the user's psychological state in the theory of mind analysis module (10), K_m is a psychological sensitivity coefficient (set according to the user's response sensitivity), P_m is a weight representing the reliability of the user's input data, J_m is a quantitative indicator representing the psychological state entered by the user (e.g., level of depression), and T_m is the average reference value of a normal state value similar to the user's state.

[0052] The psychological sensitivity coefficient is calculated based on responses to specific items (e.g., frequency of emotional changes, level of stress response) in an initial survey or psychological diagnostic assessment.

[0053] For example, it reflects the response score to a question in the survey item, such as "How many times have you felt depressed in the last two weeks?"

[0054] Data reliability weighting evaluates the consistency and accuracy of the data entered by the user.

[0055] For example, the consistency of repeated responses to the same question is compared at time intervals, and if there are many conflicting responses to the same question, a low confidence weight is assigned.

[0056] Psychological state indicators are collected through multidimensional questionnaires that specify emotional states (e.g., depression, anxiety, anger, etc.).

[0057] For example, quantitative scores are derived using the PHQ-9 (Depression Screening Tool) or the GAD-7 (General Anxiety Disorder Assessment Tool).

[0058] Normal state reference values ​​are extracted from research data or databases based on the average values ​​of the same age group or demographic criteria.

[0059] For example, it reflects the average depression score set to the normal range (e.g., 0 to 4 points on the PHQ-9).

[0060] Specifically, J_m is a quantitative indicator of the psychological state entered by the user (e.g., depression score), and T_m is the reference value considered normal in the corresponding population.

[0061] Divide J_m by T_m to relatively express how much the user state differs from the normal range.

[0062] especially, In such cases, the user's psychological state is higher than normal (worsened), so there is a great need for treatment, In this case, the user falls within the normal range.

[0063] By taking the logarithm of the above ratio, the influence of excessively large values ​​is reduced and the data distribution is smoothed out.

[0064] In addition, the reason for adding 1 is to prevent the problem where the logarithm is undefined when the above ratio is 0.

[0065] In other words, it reflects the characteristic that the increase in the ratio is not linear but gradually decreases, and The smaller the value of , the smaller the log value becomes, indicating a state closer to normal.

[0066] Trigonometric functions are used to non-linearly reflect the reliability P_m of the input data; thus, it exerts a small influence when the value is small and reflects a larger influence as the reliability increases.

[0067] In other words, if user data has low reliability, it reduces the impact on score calculation and smoothly reflects extreme changes in P_m (between 0 and 1).

[0068] K_m is a coefficient used to reflect how sensitive a user's condition is to a specific disease—that is, the need to address it as a priority. A high value indicates that the user's psychological state is a priority for treatment.

[0069] [Mathematical Formula 2]

[0070]

[0071] Here, S_s represents the Theory of Mind Sexuality analysis score, K_s represents the analysis weighting coefficient of the psychological sexual state, P_s represents the reliability coefficient of the input personality data, E_s represents a quantitative indicator related to the user's personality traits, and R_s represents the analysis threshold (average personality trait value).

[0072] Sexual psychological state weighting coefficients are extracted through surveys or interviews analyzing the user's personal and personality traits, and can be combined with personality type tests (e.g., MBTI, Big Five, etc.).

[0073] For example, it reflects the score of items such as, "Do you tend to express your emotions honestly in your interpersonal relationships?"

[0074] The input reliability coefficient quantitatively analyzes the reliability of data entered by the user (e.g., checking whether the user repeatedly enters the same data or if the input is random).

[0075] For example, personality trait data is received over multiple time periods to review consistency.

[0076] Quantitative indicators related to personality traits are extracted from questionnaires related to personality traits, specifically quantified scores (e.g., sociability, extraversion, etc.).

[0077] For example, it reflects the score for "Are you good at understanding and empathizing with other people's emotions?"

[0078] The analysis threshold extracts the average value of personality traits by age, gender, or region from the database.

[0079] For example, it reflects the average extraversion score (based on age group and gender).

[0080] Specifically, E_s and R_s are separated and quantified to evaluate how different the user's personality is from the reference value.

[0081] By applying an inverse trigonometric function to the above ratio, a non-linear change is reflected that gradually increases the result as the ratio value increases.

[0082] Using inverse trigonometric functions, personality traits are expressed as changes in angle based on how much they differ from a reference value.

[0083] As personality traits differ from the baseline, S_s increases, and small changes are not excessively reflected.

[0084] It is designed to reflect reliability as an exponential function to exponentially amplify its influence, ensuring that high data reliability has a significant impact on the results.

[0085] In other words, the higher the reliability, the more accurate the user's data is considered to be, and the greater the impact on the analysis results.

[0086] The weighting coefficients adjust the influence of the Theory of Mind analysis results on the overall score.

[0087] In other words, it analyzes the correlation between personality traits and psychological states to reflect their importance.

[0088] [Mathematical Formula 3]

[0089]

[0090] Here, S_c represents the curriculum design score, K_c represents the coefficient of fit between the learning goal and the user state, P_c represents the weight for learning efficiency, L_c represents a quantitative indicator of user learning performance (learning task completion rate), and D_c represents the learning goal threshold (set average learning goal value).

[0091] The learning suitability coefficient calculates the suitability with learning goals by combining the user's psychological state and personality data.

[0092] For example, the necessity and priority of learning are calculated based on the results of theory of mind analysis and sexual theory of mind.

[0093] The learning task completion rate tracks the learning tasks (ratio or absolute amount) completed by the user.

[0094] For example, if 80% of the given tasks are completed, the learning task completion rate is set to 0.8.

[0095] The learning objective threshold is based on the performance of the set goals for each task (e.g., estimated time required for task completion, completion rate).

[0096] For example, set an absolute goal as a daily learning target, such as "complete at least 7 out of 10."

[0097] The reliability of learning efficiency calculates efficiency by tracking the user's concentration, study time, etc., during the learning process.

[0098] For example, reliability weights are set based on the "number of interruptions during learning" or "feedback scores after task completion."

[0099] Specifically, the extent to which a user has achieved each learning goal can be evaluated through the ratio of the performance rate to the target threshold.

[0100] In addition, the overall learning performance is evaluated by summing the performance rates of all n learning tasks through the cumulative summation of the performance rates for each task.

[0101] Each task has equal importance, and the level of performance of all tasks is comprehensively reflected.

[0102] The confidence level of the input data is processed using an inverse tangent function, increasing gradually when the value is small and rapidly when the value is large.

[0103] The inverse tangent function is used to maintain a limited effect even if the confidence level becomes too high.

[0104] In other words, if learning efficiency is low, it reduces the impact on the overall score, and if efficiency is high, it increases exponentially.

[0105] The learning fit coefficient is a measure indicating the alignment between a user's psychological state and learning goals, reflecting the importance of customized learning design for a specific user.

[0106] In other words, the suitability of the curriculum design is evaluated by reflecting the importance of the learning process in the score.

[0107] In one embodiment, the valid range and critical effect for each mathematical expression are as follows:

[0108] For [Mathematical Formula 1], set the valid range as follows:

[0109]

[0110] J_m / T_m = 1: considered a normal state, J_m / T_m > 1: psychological state deteriorates below the standard, and : Set the severity of the psychological state to an evaluable range, and values ​​of 5 or higher are extremely rare and can have a significant impact on the analysis.

[0111] J_m / T_m > 5: Due to the nature of the logarithmic function, the change becomes insignificant, so the effect of increasing the score is limited, and J_m / T_m < 0: is not meaningful, so it is excluded.

[0112] P_m reflects reliability, and since the value of sin(P_m) ranges from 0 to 1, it smoothly reflects the effect of changes in reliability.

[0113] P_m > π / 2 is considered an excessive confidence level and is deemed inappropriate.

[0114] P_m > π / 2: Due to the periodic nature of the sine, the value decreases or becomes negative, resulting in an inaccurate score.

[0115] The critical effect is as follows:

[0116] As J_m / T_m approaches 1, S_m decreases and is considered to be in a steady state, and as it exceeds 1, the score increases rapidly.

[0117] As P_m approaches 0, the influence on S_m decreases, and as it approaches π / 2, the confidence is maximized, having a significant impact on the score.

[0118] For [Mathematical Formula 2], set the valid range as follows:

[0119] E_s / R_s = 1: Normal state consistent with the threshold, E_s / R_s < 0.5: Low analytical value due to lack of trait, E_s / R_s > 1.5: Considered an extreme personality trait, and anything above this is deemed to require separate analysis.

[0120] E_s / R_s < 0.5: The inverse trigonometric function is undefined or the result is meaningless, and E_s / R_s > 1.5: There is a possibility that the reliability of the analysis result is low.

[0121] P_s exponentially reflects input confidence, and if the value is too large, it has an excessive effect on the result.

[0122] e^{P_s} increases exponentially for P_s > 2, which can compromise the stability of the calculation.

[0123] P_s > 2: The score is abnormally high, and P_s < 0: The reliability is considered negative and inappropriate.

[0124] The critical effect is as follows:

[0125] As E_s / R_s approaches 1, the score S_s is evaluated as normal, and if it exceeds or falls below 1, the score changes non-linearly due to the characteristics of the inverse trigonometric function.

[0126] As P_s increases, the effect of the exponential function e^{P_s} becomes significant, assigning greater weight to data with high confidence.

[0127] For [Mathematical Formula 3], set the valid range as follows:

[0128] L_c^{(i)} / D_c^{(i)} = 1: The learning goal has been achieved accurately, L_c^{(i)} / D_c^{(i)} < 0.5: The task performance rate is too low compared to the goal, so the analysis value is low, and L_c^{(i)} / D_c^{(i)} > 2: There is a possibility of deviating from the normal learning pattern due to exceeding the goal.

[0129] L_c^{(i)} / D_c^{(i)} < 0.5: The score is excessively low and is considered a failure of the learning process, and L_c^{(i)} / D_c^{(i)} > 2: Score distortion occurs.

[0130] P_c represents the reliability of learning efficiency, It increases linearly between 0 and 1, and when P_c > 1, the change becomes insignificant and the distinctiveness of the analysis results decreases.

[0131] P_c > 1: The effect of increasing confidence is almost non-existent, and P_c < 0: Negative values ​​are considered inappropriate and invalid.

[0132] The critical effect is as follows:

[0133] As L_c^{(i)} / D_c^{(i)} approaches 1, the achievement of the learning goal is considered normal, and if it falls outside the threshold range, it is evaluated as a failure or overachievement of the learning pattern.

[0134] As P_c approaches 1, confidence is maximized, which has a significant impact on S_c.

[0135] The above valid range is set so that the input values ​​of each formula are calculated within a realistic data range, thereby ensuring analysis stability.

[0136] In addition, extreme values ​​are restricted as they may have an excessive impact on the score or cause calculation errors.

[0137] If the data falls outside the valid range, abnormal results, calculation errors, or distortion of analysis results may occur, and data outside a specific range requires separate review or exception handling.

[0138] It is designed so that the proportion and effect of each factor contributing to the score change non-linearly or in steps within the established validity range for the critical effect.

[0139] In one embodiment, the device is performed as follows:

[0140] The user accesses the application for psychotherapy and enters initial survey data.

[0141] Input data includes recent depression frequency: 6-7 days / week, sleep disorder: occurs frequently, personality type: introverted, sensitive to stress, and learning goal: "I want to improve my emotional regulation skills and reduce depression."

[0142] The theory of mind analysis module (10) is executed to analyze the user's psychological state and evaluate the deviation between the current state and the normal state.

[0143] Regarding data and standard ranges, they are as follows:

[0144] The range of depressive state scores is 0 points (lowest) to 27 points (highest) (based on the PHQ-9 questionnaire), and the PHQ-9 questionnaire is a widely used tool for diagnosing depression, classifying mild, moderate, and severe based on the score.

[0145] The user score J_m is set to 16 as the input value (corresponding to moderate depression).

[0146] The normal state threshold range is 0 to 4 points, and a PHQ-9 score of 0 to 4 points is considered normal or mild.

[0147] Set the reference value to T_m=4.

[0148] The range of the psychological status score is 0 points (normal) to 5 points (severe depression), and based on the normal standard It is considered to be in a normal state.

[0149] As a result of the analysis, the calculated result is S_m=3.2 (the user's psychological state is 3.2 points worse than the normal standard), which is classified as "moderate depression," and treatment through emotional stability and learning emotional regulation is recommended.

[0150] Next, the Sexual Mind Theory application module (20) is executed to analyze the user's personality traits and derive a personalized treatment direction.

[0151] Regarding data and standard ranges, they are as follows:

[0152] The range of personality trait scores is 0.0 (lowest) to 1.5 (highest), and personality traits are quantified to analyze the deviation from the reference value.

[0153] The input value is set to the user score E_s=0.9 (average introversion).

[0154] The range of the personality threshold is 1.0 (average personality trait) and is set as the balance point between introversion and extraversion.

[0155] Set the reference value to R_s=1.0.

[0156] The range of personality analysis scores is set from 0 points (normal) to 3 points (large difference in personality traits).

[0157] The normal standard is It is considered a normal state.

[0158] The calculated result from the analysis is S_s=2.1 (indicating that the user's personality traits differ somewhat from the baseline); the user is introverted, sensitive to stress, and lacks emotional regulation skills, so it is necessary to focus on improving emotional stability and self-expression abilities when designing the learning curriculum.

[0159] Next, the curriculum generation module (30) is executed to design a learning plan based on the results of the theory of mind and sexual theory of mind analysis.

[0160] Regarding data and standard ranges, they are as follows:

[0161] The range of the learning task performance rate is 0.0 (lowest) to 1.0 (highest), and the performance rate of each learning task is quantified as 0~100%.

[0162] Set the initial value to L_c^{(i)} = 0.0 (not performed yet).

[0163] The range of the learning objective threshold is 1.0 (100% achievement of the learning objective), and the progress is evaluated by setting the learning objective to 100%.

[0164] The range of reliability for learning efficiency is 0.0 (lowest) to 1.0 (highest), and evaluates reliability and concentration on learning.

[0165] The initial value is set to P_c=0.85 (high confidence).

[0166] The result calculated from the analysis is S_c=2.5 (learning curriculum suitability evaluation score), and the designed learning plan is as follows:

[0167] Week 1 consists of writing an emotion journal (once a day) and emotional stability breathing exercises (10 minutes / session, 3 times a week).

[0168] Week 2 consists of simple meditation practice (15 minutes / session, 3 times a week) and watching educational videos on depression and emotion regulation (30 minutes / session, 2 times a week).

[0169] Next, the content management module (40) is executed to curate suitable content according to the learning plan and provide it to the user.

[0170] The provided content includes an emotion recording tool: an interface that allows users to simply record their emotions; emotional stability training videos: guide videos provided by psychotherapy experts; and educational materials: psychological educational materials on "the causes of depression and how to overcome it."

[0171] The feedback provision module (50) is executed to provide feedback on the results of the first week's progress, such as emotional record: completed on 5 / 7 days, and emotional stability training: completed 2 / 3 times.

[0172] For feedback, the user responded that "breathing training was effective in reducing stress," and the analysis results showed that the learning performance rate was 80%, and a positive reinforcement message was delivered saying, "Great! You are effectively managing stress through emotional stability training."

[0173] In addition, adjust next week's learning goals to increase breathing training time to 15 minutes and make emotion recording more specific.

[0174] As a result, after the first week of learning, users experience initial effects of reduced depression and emotional stability, and through continued learning, there is a high likelihood that their psychological state will recover to a normal range.

[0175] Although preferred embodiments of the present invention have been illustrated and described above, the present invention is not limited to the specific embodiments described above. Various modifications are possible by those skilled in the art without departing from the essence of the invention as claimed in the claims, and such modifications should not be understood individually from the technical spirit or perspective of the present invention.

Claims

1. A psychotherapy system based on theory of mind for the treatment of depression and psychological disorders, comprising the features of analyzing psychological states based on theory of mind and sexual theory of mind based on user input data, designing a personalized learning curriculum through the analyzed results, providing this as learning content, and collecting feedback to customize the learning process.

2. In Paragraph 1, A user terminal that collects user input data; A theory of mind analysis module and a sexual theory of mind application module that quantitatively evaluate psychological states by performing theory of mind and sexual theory of mind analysis; Curriculum generation module that generates personalized learning plans based on analysis results; A content management module that provides user-customized learning content based on a generated learning plan; A feedback provision module that adjusts the learning process by analyzing learning results and user feedback; A server that processes and stores data by connecting the above-mentioned user terminal and each module; A psychotherapy system based on theory of mind that includes 3. In Paragraph 2, The above theory of mind analysis module is, Quantifying psychological state data entered by the user to derive a depression score, and Calculates the ratio of the depressive state score to the normal state reference value, The above ratio is converted into a logarithmic function to mitigate the effect of excessive values, and The reliability of the input data is converted into a trigonometric function to reflect non-linear effects, and The psychological state score is calculated according to the formula, and The effective range of the above ratio is, Set to 0 to 5, and If it is 1, it is considered a normal state, and If it exceeds 1, the psychological state deteriorates compared to the standard, and If it is 5 or less, it is set to a range where the severity of the psychological state can be assessed, and A psychotherapy system based on theory of mind, characterized by determining that a state requiring psychotherapy is required when the value exceeds 1.

4. In Paragraph 2, The above-mentioned theory of the mind application module is, Analyzes personality trait data entered by the user to derive personality trait scores, and Evaluates personality differences by comparing derived personality trait scores with reference values, Personalize learning directions according to personality traits such as introversion, extraversion, and emotional regulation ability, and It is characterized by improving the reliability of the learning design by analyzing the reliability of user data, and The above curriculum generation module is, A user-customized learning plan is designed by combining the data provided by the above Theory of Mind analysis module and the above Theory of Mind application module, and Evaluate the performance rate based on the learning task performance rate and the learning objective criteria, Considering learning efficiency, multiple learning activities including emotional stability training, writing an emotional journal, and meditation training are proposed, A psychotherapy system based on theory of mind characterized by dynamically adjusting the learning cycle and difficulty level to suit the user's condition.

5. In Paragraph 2, The above content management module is, Learning content is provided according to the learning plan designed in the above curriculum creation module, and Store, manage, and distribute learning materials such as videos, text, and quizzes, and Dynamically curates additional materials based on the user's progress, A psychotherapy system based on theory of mind, characterized by learning content designed to enhance user learning efficiency.

6. In Paragraph 2, The above feedback providing module is, Collecting and analyzing learning task performance results and user feedback data, Adjust the learning process based on analyzed data, and It provides positive reinforcement messages or suggestions to modify learning goals based on the user's performance and progress, A psychotherapy system based on theory of mind characterized by improving the user's learning experience and increasing learning persistence.

Images