Psychological state estimation and customized meditation program recommendation system using artificial intelligence

Abstract

The present invention relates to a psychological state analysis and recommendation system using artificial intelligence, and, more specifically, to a system which analyzes questionnaire responses and feedback data collected from a user so as to estimate a psychological state using an artificial intelligence model, and which recommends a customized meditation program suitable for the estimated state, thereby supporting the psychological stability and mental health management of the user.

Description

Psychological state estimation and personalized meditation program recommendation system using artificial intelligence

[0001] The present invention relates to a psychological state analysis and recommendation system using artificial intelligence, and more specifically, to a system that supports the psychological stability and mental health management of a user by analyzing survey responses and feedback data collected from the user, estimating the psychological state through an artificial intelligence model, and recommending a customized meditation program suitable for the estimated state.

[0002] In modern society, psychological anxiety and stress are problems experienced by many people, making effective management of them an important task.

[0003] Existing meditation programs often failed to meet the need for personalized programs by generally providing the same program to a wide range of users.

[0004] Furthermore, existing psychological state analysis systems had limitations in that they could not provide customized meditation programs suitable for an individual's specific psychological state, as they simply scored the user's psychological state based on questionnaire responses or recommended programs using general recommendation algorithms.

[0005] Therefore, a system is needed that accurately analyzes each individual's psychological state and provides a meditation program tailored to it.

[0006] In particular, technological advancements are required to effectively provide customized meditation programs by utilizing artificial intelligence technology to conduct in-depth analysis of user survey data and reflecting the various characteristics of the meditation program and user feedback.

[0007] The objective of the present invention is to provide a more effective mental health management solution to users by accurately estimating the user's psychological state and providing a customized meditation program based on each individual's psychological characteristics and changes in state.

[0008] To this end, we aim to train an artificial intelligence model capable of precisely estimating psychological states based on user response data, and to implement a system that recommends suitable meditation programs based on the psychological states estimated by the model.

[0009] The present invention aims to provide a system that can effectively contribute to psychological stability and stress management by continuously monitoring the user's psychological state and recommending suitable programs in real time according to changes.

[0010] The problems of the present invention are not limited to those mentioned above, and other problems not mentioned will be clearly understood by those skilled in the art from the description below.

[0011] A system for estimating a psychological state and recommending a customized meditation program using artificial intelligence according to an embodiment of the present invention for solving the above problem may include a system server (100) characterized by estimating the psychological state of a user based on data input through a user terminal, collecting and analyzing survey response and feedback data to recommend a customized meditation program tailored to the estimated psychological state, and providing a meditation program based on the psychological state estimated through artificial intelligence.

[0012] In one embodiment, the system server (100) comprises: a data collection module (10) that collects survey responses entered through a user terminal and feedback after performing a meditation program; a psychological state estimation module (20) that learns an artificial intelligence model to estimate a psychological state based on the survey and feedback data collected by the data collection module (10) and derives a user-customized psychological state score; a meditation program recommendation module (30) that stores meditation program information and recommends a meditation program according to the user's psychological state based on the result data of the psychological state estimation module (20); a data management module (40) that centrally manages user responses, feedback, psychological state data, and meditation program information, encrypts and stores data, and controls access to necessary data for each module; and a user interface module (50) that provides functions including creating a survey, confirming meditation program recommendations, providing feedback, and tracking changes in the user's psychological state for interaction with the user terminal. The system includes a data collection module (10) which collects survey responses regarding the user's stress level, anxiety level, happiness, concentration, and sleep quality, and collects feedback such as stress relief effects, improved concentration, and mood improvement after performing a meditation program, and the collected data is transmitted to and stored in a data management module (40) within a system server (100). The data management module (40) is characterized by encrypting and storing the collected user survey responses and feedback data using an AES-256 encryption algorithm, enabling each module to safely access the necessary data, and protecting the user's personal information.

[0013] In one embodiment, the psychological state estimation module (20) is characterized by calculating the user's psychological state score S using [Equation 1], wherein ω is a response item weight, a value representing the influence of each survey response item on the psychological state; x_i is the user input value of the i-th response item; θ is an angle representing the interaction period between response items; t_ω is a weight that varies depending on the time at which the survey response is made; λ is a time decay coefficient, a value determining the rate of decrease in importance over time; and c_ω is a user reliability weight, a weight that reflects the user's response reliability.

[0014] [Mathematical Formula 1]

[0015]

[0016] In one embodiment, the psychological state estimation module (20) has a proportional relationship between each factor in [Equation 1], the survey response weight ω_i is proportional to the importance of the response item, the time weight t_ω is different depending on the time when the user responds to the survey, the time decay coefficient λ has a proportional relationship that reduces importance over time, and the user's response reliability c_ω is proportional to the consistency of the response, so the higher the reliability, the more it contributes to the psychological state estimation, and the psychological state score reflecting the user's current state can be derived using the proportional relationship.

[0017] [Mathematical Formula 1]

[0018]

[0019] In one embodiment, the psychological state estimation module (20) may include features such that each factor in [Equation 1] is in a functional relationship, the time weight t_ω gradually decreases over time through e^(-λt_j), the survey response value x_i mitigates large fluctuations through ln(1+|x_i|), the large fluctuations refer to extreme changes in the psychological state score S caused by extreme fluctuations in the response, the user's response reliability c_ω reflects the response reliability through tanh(c_ω*x_j), and the psychological state estimation result reflects the user's state change through the functional relationship.

[0020] [Mathematical Formula 1]

[0021]

[0022] In one embodiment, the psychological state estimation module (20) may include the features of estimating the user's psychological state by calculating the user's psychological state score S using [Equation 1], wherein ω_i is a weight of each survey response item and varies according to the importance of the response item, x_i is a survey response value entered by the user, cos(θ_i) is a periodic function representing the interaction between response items and reflecting the correlation between survey responses, t_ω is a time weight and varies according to the time of the survey response, e^(-λt_j) is a function of the time decay coefficient and causes the importance of the response data to decrease as time passes, ln(1+|x_i|) mitigates changes in large response values ​​and reduces the influence of such changes on the psychological state score S as the response value increases, and tanh(c_ω*x_j) is a function of response reliability and adjusts the influence given to the psychological state score S.

[0023] [Mathematical Formula 1]

[0024]

[0025] In one embodiment, the meditation program recommendation module (30) is characterized by recommending a meditation program to a user using [Equation 2] according to the psychological state score S and the meditation program characteristic value M, wherein α_j is a unique weight of the meditation program that reflects the influence of each meditation program on improving the psychological state, M_j is the characteristic value of the j-th meditation program, β is an angle representing the interaction between meditation programs, p_ω is a weight that considers the probability of a specific psychological state appearing, ||S-M_j|| is the difference between the psychological state score S and the meditation program characteristic value M_j, and σ_j is the variability weight of the program.

[0026] [Mathematical Formula 2]

[0027]

[0028] In one embodiment, the data management module (40) may be characterized by encrypting and storing collected user survey responses and feedback data using an AES-256 encryption algorithm, enabling each module to securely access necessary data, and protecting the user's personal information.

[0029] The present invention utilizes artificial intelligence technology to accurately estimate a user's psychological state and recommends a customized meditation program based on the estimated state, thereby providing an effect that helps the user achieve psychological stability and manage mental health.

[0030] Since this system enables an AI model to estimate psychological states based on survey responses and feedback data collected from users, it allows for more precise analysis than the existing simple scoring of psychological states.

[0031] In addition, the present invention enables mental health management tailored to the individual psychological needs of users by providing real-time program recommendations based on changes in the user's psychological state.

[0032] In addition, by incorporating user-provided feedback data into the analysis, continuous improvement and optimized meditation program recommendations are possible.

[0033] This customized approach is differentiated from the existing uniform program delivery method and contributes to improving the user experience and maximizing the effectiveness of mental health care.

[0034] 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.

[0035] Figure 1 illustrates an overall relationship diagram according to the present invention.

[0036] Figure 2 illustrates a relationship diagram of a system server according to the present invention.

[0037] FIGS. 3 to 7 illustrate embodiments according to the present invention.

[0038] 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.

[0039] 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.

[0040] 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.

[0041] 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.

[0042] 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.

[0043] 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).

[0044] 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.

[0045] 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.

[0046] 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.

[0047] 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.

[0048] 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.

[0049] 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.

[0050] Figure 1 illustrates an overall relationship diagram according to the present invention.

[0051] This embodiment is a system that estimates a user's psychological state based on AI and recommends a meditation program suitable for it. It includes three main modules: a data collection module (10), a psychological state estimation module (20), a meditation program recommendation module (30), a data management module (40), and a user interface module (50), and all modules operate organically within a system server (100). The system server (100) controls and manages the functions of each module to provide the user with an optimal mental health management solution.

[0052] Figure 2 illustrates a relationship diagram of a system server according to the present invention.

[0053] In the data collection module (10), the user answers questions related to their current psychological state through an initial survey.

[0054] The questions mainly consist of items measuring stress levels, anxiety, satisfaction, etc., and are answered using a Likert scale (1–5).

[0055] After the user performs the recommended meditation program, feedback is provided to evaluate the satisfaction and effectiveness of the program.

[0056] At this time, feedback items include the program's focus, comfort, and improvement effects.

[0057] All collected response and feedback data are transmitted to a data management module (40) and stored so that they can be used for analysis and estimation.

[0058] In the data management module (40), user response and feedback data are safely stored and managed in a centrally managed database within the system server (100).

[0059] All data is encrypted to enhance security.

[0060] The psychological state estimation module (20) and the meditation program recommendation module (30) can access necessary data to perform analysis and transmit data in real time to reflect changes in the user's state.

[0061] The psychological state estimation module (20) plays the role of estimating the psychological state based on user survey data. It derives a user psychological state score by reflecting the weight of each item, the user's reliability, response time, etc.

[0062] For example, high response values ​​and responses within a short time can indicate a high level of anxiety.

[0063] The psychological state estimation module (20) estimates the user's psychological state S through the following [Equation 1].

[0064] The estimated psychological state S is transmitted to the meditation program recommendation module (30) via the system server (100) and used for personalized recommendations.

[0065] [Mathematical Formula 1]

[0066]

[0067] ω_i is the response item weight, a value representing the influence of each survey response item on the psychological state.

[0068] A value between 0 and 1 is set according to the importance of the response item, and higher weights are assigned to more important items.

[0069] x_i is the user input value for the i-th response item, which is typically provided as an integer or real number, and can have values ​​from 1 to 5 on a Likert scale, for example.

[0070] θ_i is an angle representing the interaction period between response items and is used to reflect the periodic characteristics of the response items. For example, it can reflect the degree to which each item interacts according to a psychological state that fluctuates periodically. The angle can be set to a value between 0 and 2π.

[0071] t_ω is a weight that varies depending on the time at which the survey response is made, serving to reinforce the influence of the most recent response. As time passes, e is set so that the importance of the response decreases. -λt It is set in the form.

[0072] λ is a time decay coefficient that determines the rate of importance decline over time; the higher the value, the more rapidly the importance of the response decreases over time. In cases where psychological states change rapidly, a high λ can be applied to set a more sensitive level.

[0073] c_ω is a user confidence weight that reflects the reliability of a user's response, assigning a higher weight to consistent responses. The larger this value, the greater the influence of the user's response on the estimation of their psychological state.

[0074] In one example, when ω=[0.8, 0.6, 0.9, 0.7, 0.5] , x=[3, 5, 4, 2, 1] , θ=[pi / 6, pi / 4, pi / 3, pi / 2, pi], t_ω=1.0, λ=0.1, t=[0, 1, 2, 3, 4], and c_ω=0.85,

[0075] When i=1, S=3.43; when i=2, S=5.35; when i=3, S=4.67; when i=4, S=0.51; and when i=5, S=-2.96.

[0076] The total estimate S is 11.01, which indicates that the user's psychological state is highly anxious or under high stress.

[0077] The impact was significantly reflected when response items and confidence weights were high and user responses were recent.

[0078] In another embodiment, the user inputs survey responses through a user terminal such as a smartphone or a computer. The survey items consist of various items designed to measure psychological states, such as stress levels, anxiety, happiness, concentration, and sleep quality.

[0079] Survey responses are collected by the data collection module, and feedback data provided after performing the meditation program is also collected through the same module.

[0080] The collected data is transmitted to and stored in the data management module, and is encrypted using the AES-256 encryption algorithm to protect users' personal information.

[0081] This safely protects user data while controlling access to the data that each module needs.

[0082] The psychological state estimation module estimates the user's psychological state based on the survey responses entered by the user.

[0083] The psychological state estimation module calculates a psychological state score S by considering the response value and weight of each item using [Equation 1].

[0084] ω_i is the weight of each survey response item, reflecting the importance of that item in estimating the psychological state. For example, if the weight of the stress item is high, the response to that item will have a greater impact on the estimation of the psychological state.

[0085] x_i is the value the user responded to for the item. This varies depending on user input and, for example, can be a Likert scale value from 1 to 5.

[0086] θ_i is an angle representing the interaction period between survey response items, reflecting how related items interact.

[0087] t_ω is a time weight based on the time of the survey response, with higher weights assigned to more recent responses, and its influence decreases over time.

[0088] λ is the time decay factor, which determines the rate at which the importance of the response decreases over time.

[0089] ln(1+|x_i|) uses a logarithmic function to mitigate large variations in response values. This serves to prevent extreme large response values ​​from having an excessive impact on the estimation of the psychological state.

[0090] tanh(c_ω*x_j) is a function that reflects the reliability of user responses, assigning higher reliability to more consistent responses.

[0091] For example, if a user responds that the stress level is 5 points, the concentration is 3 points, and the quality of sleep is 2 points, a psychological state score S is calculated through the weights set for each item and a logarithmic function.

[0092] In the meditation program recommendation module (30), a database containing various meditation program information is used to store characteristics such as the type of program (breathing meditation, music meditation, etc.), difficulty level, and effectiveness.

[0093] Specifically, users gave 5 points to the question about stress levels and 2 points to the question about concentration.

[0094] The weights and response values ​​of each item are applied to [Equation 1], and a psychological state score of S=8.5 is derived.

[0095] The meditation program recommendation module recommends programs effective for relieving the user's stress based on the S value.

[0096] The user performs the program and provides feedback after execution, and that feedback is stored in the system and reflected in the next recommendation.

[0097] If users enter extreme response values ​​in survey items and these values ​​are directly reflected in the psychological state score, there is a possibility that the estimation results will be distorted.

[0098] For example, on a Likert scale of 1 to 5, there can be extreme differences in values ​​between when 5 points are entered and when 1 point is entered.

[0099] To prevent this, ln(1+|x_i|) is used to mitigate extreme fluctuations.

[0100] The larger the response value x_i, the greater the influence on the estimation of the psychological state.

[0101] However, ln(1+|x_i|) moderates the rate of change as the input value increases, adjusting to prevent large response values ​​from being excessively reflected in the estimation result.

[0102] For example, when the response value is small (x_i=1), the small response value is hardly modified and is reflected close to the original value (ln(1+|x_i|)=0.693).

[0103] When the response value is extremely large (x_i=5), it is reflected as 1.792, which is much more mitigated than using the large response value as is (ln(1+|5|)=1.792).

[0104] If a user enters x_i=5 for the stress item and x_i=1 for the happiness item in the survey, and ln(1+|x_i|) is not applied, S=ω_1*5+ω_2*1, the stress item has an excessively large influence, which can distort the estimation of the psychological state.

[0105] However, when ln(1+|x_i|) is applied, S=ω_1*ln(1+5)+ω_2*ln(1+1), and extreme response values ​​are mitigated.

[0106] Based on the psychological state S estimated by the above [Equation 1], a suitable meditation program is recommended through the following [Equation 2].

[0107] [Mathematical Formula 2]

[0108]

[0109] α_j is an intrinsic weight of the meditation program that reflects the influence each meditation program has on improving psychological state. A high value is assigned if a specific program is particularly effective for a specific psychological state.

[0110] M_j is the characteristic value of the j-th meditation program and can include various characteristics such as the program's difficulty, type, and effectiveness. For example, if a particular program is suitable for stress reduction, this value may be high.

[0111] β_j is an angle representing the interaction between meditation programs and is used to reflect periodic characteristics when program characteristics can influence each other according to periodic fluctuations. For example, a meditation music program can provide an effect that repeats at regular intervals.

[0112] p_ω is a weight that considers the probability of a specific psychological state occurring, adjusting the fit between the program and the psychological state. Through this, a high probabilistic weight is assigned when there is a high correlation between the user's state and the corresponding program.

[0113] ||S-M_j|| represents the difference between the psychological state score S and the meditation program characteristic value M_j. It is a factor that lowers the goodness of fit as the difference increases, and raises the goodness of fit as the difference decreases.

[0114] σ_j is a volatility weight of the program, a value used to adjust the impact on the results based on the characteristics of the program. It has a large value for programs with high volatility.

[0115] For example, in the case where α=[0.78, 0.85, 0.9, 0.8], M=[2.5, 3.0, 4.0, 3.5], β=[pi / 4, pi / 3, pi / 6, pi / 2], p_ω=0.65, σ=[1.2, 1.1, 1.0, 1.3],

[0116] P_r=0.0 when j=1, P_r=0.0 when j=2, P_r=0.0 when j=3, and P_r=0.0 when j=4.

[0117] The total value of P_r is 1.35 x 10 -21 It was derived as a value close to 0. The above value indicates that there is a large difference between the meditation program characteristic value M and the user's psychological state S, and it can be interpreted that the provided meditation programs are not suitable for the user's psychological state in the current state.

[0118] The optimal meditation program is recommended to the user based on the P_r value. For example, if a high stress level is estimated, a program effective for relaxation and stress reduction is recommended.

[0119] When a user responds to an initial survey, the data is transmitted to and stored in the data management module (40) via the data collection module (10).

[0120] The psychological state estimation module (20) retrieves and analyzes the stored data and calculates the psychological state score S.

[0121] The meditation program recommendation module (30) selects a program based on the estimated S value and recommends the most suitable program to the user.

[0122] After the user performs the program and provides feedback, the system server (100) manages this again through the data collection module (10) and reflects it in future analysis.

[0123] In one embodiment, in collecting survey responses, the user responds to items such as stress level, anxiety level, happiness, concentration, and sleep quality.

[0124] Each item is answered on a Likert scale (1 to 5), for example, regarding “How stressed were you today?”, you are asked to choose from 1 (almost none) to 5 (very high).

[0125] Examples of response items may include "What is your current stress level?", "How much anxiety did you feel today?", "How happy did you feel?", "Was your concentration good?", and "How was the quality of your sleep?".

[0126] In collecting feedback phrases, users provide feedback on the effectiveness of the program after performing the recommended meditation program.

[0127] Examples of feedback phrases that may be provided include: "Did the meditation program help relieve stress?", "Were you able to concentrate well while performing the program?", "Did you feel better after the program?", and "Would you like to perform this program again?"

[0128] Each feedback item is also answered using a Likert scale (1–5), and the results are subsequently used to evaluate the suitability of the meditation program.

[0129] In the data encryption method, all survey responses and feedback data provided by the user are transmitted to the data management module (40) and are securely stored in the database within the system server (100).

[0130] The data is encrypted using the AES-256 encryption algorithm.

[0131] AES-256 is a highly secure symmetric key method that encrypts each data item using a 256-bit key.

[0132] Encrypted data can only be accessed by administrators with restricted server access rights via the decryption key, and decryption is performed only during analysis.

[0133] In deriving the psychological state score result, the response data transmitted from the data collection module (10) is processed in the psychological state estimation module (20).

[0134] Based on the user's response data, the psychological state score S is calculated through the above [Mathematical Formula 1].

[0135] The value derived as S=11.01 in the above calculation process indicates a state of high stress and anxiety.

[0136] In the meditation program recommendation module (30), based on the psychological state score S, P_r is calculated through the above [Equation 2] to recommend the program most suitable for the user's state in the meditation program recommendation module (30).

[0137] In the above calculation process, P_r=1.35X10 -21 Since this was found, it is determined that the currently provided programs are not suitable for the psychological state of the user in question.

[0138] Based on this, to recommend a better program, additional programs with higher characteristic values ​​can be selected.

[0139] In the user interface module (50), the user can answer questions related to their psychological state every day through a simple survey interface, and the interface is optimized for mobile and web environments.

[0140] The system server (100) recommends the optimal program to the user based on the calculated P_r value.

[0141] Users can view meditation program recommendations along with descriptions, duration, and difficulty levels, and can immediately run the selected program.

[0142] After performing the meditation program, a feedback screen is automatically displayed, and users can simply leave feedback.

[0143] In addition, users can check changes in their psychological state through past feedback records.

[0144] 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 system server characterized by estimating the user's psychological state based on data input through a user terminal, collecting and analyzing survey response and feedback data to recommend a customized meditation program tailored to the estimated psychological state, and providing a meditation program based on the estimated psychological state through artificial intelligence; A psychological state estimation and customized meditation program recommendation system using artificial intelligence, including 2. In Paragraph 1, The above system server is, A data collection module that collects survey responses entered through a user terminal and feedback after performing a meditation program; A psychological state estimation module that trains an artificial intelligence model to estimate psychological state based on survey and feedback data collected by the above data collection module, and derives a user-customized psychological state score; A meditation program recommendation module that stores meditation program information and recommends a meditation program according to the user's psychological state based on the result data of the psychological state estimation module; A data management module that centrally integrates and manages user responses, feedback, psychological state data, and meditation program information, encrypts and stores data, and controls access to necessary data for each module; A user interface module that provides functions including survey completion, confirmation of meditation program recommendations, provision of feedback, and tracking of changes in the user's psychological state for interaction with a user terminal; Includes, The above data collection module is, It is characterized by collecting survey responses regarding content including the user's stress level, anxiety, happiness, concentration, and sleep quality, collecting feedback such as stress relief effects, improved concentration, and mood improvement after performing a meditation program, and transmitting the collected data to a data management module within a system server for storage. The above data management module is, An AI-based psychological state estimation and personalized meditation program recommendation system characterized by encrypting and storing collected user survey responses and feedback data using the AES-256 encryption algorithm, enabling each module to securely access necessary data, and protecting users' personal information.

3. In Paragraph 2, The above psychological state estimation module is, It is characterized by calculating the user's psychological state score S using the following [Mathematical Formula 1], and [Mathematical Formula 1] Here, ω is a response item weight, a value representing the influence of each survey response item on the psychological state; x_i is the user input value of the i-th response item; θ is an angle representing the interaction period between response items; t_ω is a weight that varies depending on the time at which the survey response is made; λ is a time decay coefficient, a value determining the rate of decrease in importance over time; and c_ω is a user confidence weight, a weight reflecting the user's response confidence, a psychological state estimation and customized meditation program recommendation system using artificial intelligence.

4. In Paragraph 3, The above psychological state estimation module is, In [Mathematical Equation 1], each factor is in a proportional relationship with one another, and [Mathematical Formula 1] A system for estimating a psychological state and recommending a customized meditation program using artificial intelligence, wherein the survey response weight ω_i is proportional to the importance of the response item, the time weight t_ω changes depending on the time when the user responds to the survey, the time decay coefficient λ has a proportional relationship that reduces importance over time, the user's response reliability c_ω is proportional to the consistency of the response so that higher reliability contributes to the estimation of the psychological state, and the system can derive a psychological state score reflecting the user's current state using the above proportional relationship.

5. In Paragraph 4, The above psychological state estimation module is, In [Mathematical Equation 1], each factor is in a functional relationship, and [Mathematical Formula 1] A system for estimating a psychological state and recommending a customized meditation program using artificial intelligence, comprising the features that the time weight t_ω gradually decreases over time through e^(-λt_j), the survey response value x_i mitigates large fluctuations through ln(1+|x_i|), said large fluctuations refer to extreme changes in the psychological state score S caused by extreme fluctuations in the response, the user's response reliability c_ω reflects the response reliability through tanh(c_ω*x_j), and the psychological state estimation result reflects the user's state change through the said functional relationship.

6. In Paragraph 5, The above psychological state estimation module is, Calculate the user's psychological state score S using [Mathematical Formula 1], and [Mathematical Formula 1] A system for estimating a psychological state and recommending a personalized meditation program using artificial intelligence, comprising the features that estimate the user's psychological state by adjusting the influence of the psychological state score S as a function of response reliability, wherein ω_i is a weight of each survey response item that varies according to the importance of the response item, x_i is a survey response value entered by the user, cos(θ_i) is a periodic function representing the interaction between response items that reflects the correlation between survey responses, t_ω is a time weight that varies according to the time of the survey response, e^(-λt_j) is a function of the time decay coefficient that causes the importance of the response data to decrease as time passes, ln(1+|x_i|) mitigates large changes in response values, and as the response value increases, the influence of such changes on the psychological state score S is reduced, and tanh(c_ω*x_j) is a function of response reliability.

Images