Apparatus and method for user impulsivity analysis based on digital phenotyping

Abstract

The present invention relates to an apparatus and a method for user impulsivity analysis based on digital phenotyping, and the apparatus comprises: a data collection unit that collects multi-modal data regarding user behavior by monitoring a digital learning process on a user terminal; a data analysis unit that analyzes the multi-modal data to detect at least one digital index associated with the user behavior; an impulsivity measurement unit that measures, on the basis of the at least one digital index, impulsivity associated with user behavior in the digital learning process; and an impulsivity analysis unit that generates, on the basis of the measured impulsivity, a report analyzing least one of academic achievement, ability to pay attention, internet / game / smartphone, drug / drug addiction, anger management / violence, self-harming behavior, and impulsive suicide.

Description

Device and method for analyzing user impulsivity based on digital phenotyping

[0001] The present invention relates to a technology for measuring, evaluating and diagnosing user impulsivity, and more particularly, to a device and method for analyzing user impulsivity based on digital phenotyping, which can measure, evaluate and diagnose impulsivity related to a user's emotional or psychological problems and manage them by monitoring the user's daily life and analyzing various digital indicators collected from potential behaviors.

[0002]

[0003] Digital phenotyping can refer to the quantification of users' cognitive, emotional, behavioral, physiological, social, and environmental indicators collected momentarily in their daily lives using digital devices such as smartphones. Digital phenotyping is attracting attention as a new mental health measurement tool due to its ability to provide multidimensional and large-scale objective information. It is expected to be used in the future as a tool for personalized medicine (preventive medicine, predictive medicine, participatory medicine, and precision medicine), which aims to improve the diagnostic accuracy of psychiatry by reflecting individual patient data or establishing a new dimensional diagnostic system for RDoC.

[0004] Recently, there have been attempts to collect, analyze, and utilize users' biometric indicators, mobile phone usage patterns, and behavioral characteristics through mobile devices and wearable devices. However, there are limitations in that the scope of utilization is very limited in the collection and analysis of massive amounts of data.

[0005] In particular, public education settings like schools are highly sensitive to personal information, and data collection can be significantly restricted due to parental opposition. Therefore, digital phenotyping technology is needed to non-invasively collect and utilize information beyond sensitive personal information like face, facial expressions, physical behavior, words or sentences expressed in writing or speech, and social media posts, including touch, strokes, and stylus usage.

[0006]

[0007] [Prior Art Literature]

[0008] [Patent Document]

[0009] Korean Publication No. 10-2021-0076462 (June 24, 2021)

[0010]

[0011] One embodiment of the present invention provides a device and method for analyzing user impulsivity based on digital phenotyping, which can measure, evaluate, diagnose, and manage impulsivity related to a user's emotional or psychological problems by monitoring the user's daily life and analyzing various digital indicators collected from potential behaviors.

[0012]

[0013] Among the embodiments, the user impulsivity analysis device based on digital phenotyping includes: a data collection unit that monitors a digital learning process on a user terminal to collect multimodal data on user behavior; a data analysis unit that analyzes the multimodal data to detect at least one digital indicator associated with the user behavior; an impulsivity measurement unit that measures impulsivity on the user behavior in the digital learning process based on the at least one digital indicator; and an impulsivity analysis unit that generates an analysis report on at least one of academic achievement, attention, internet / game / smartphone, drug / drug addiction, anger management / violence, self-harming behavior, and impulsive suicide based on the measured impulsivity.

[0014] The above data collection unit collects the multimodal data through an application executed on the user terminal during the digital learning process, and the multimodal data may include action indicators based on the user's actions on the display screen of the user terminal.

[0015] The above data collection unit can collect the user's keyboard-related actions and stroke actions collected by the on-screen keyboard sensor and touchscreen sensor of the user terminal during the problem-solving process of the digital learning process as the multimodal data.

[0016] The data analysis unit can determine at least one digital indicator from among stroke acceleration, stroke speed, vertical distance, number of blank spaces, time interval, stroke length, and tap pressure.

[0017] The above impulsivity measurement unit can generate a feature vector regarding the at least one digital indicator and the number of incorrect answers during the problem-solving process, the user's emotional score, and the aggression score, and learn a correlation between the feature vector and impulsivity to build an impulsivity model.

[0018] The above impulsivity analysis unit can define each of the above academic achievement, attention, internet / game / smartphone, drug / drug addiction, anger management / violence, self-harming behavior, and impulsive suicide as independent dimensions and generate a grade for each dimension according to the above impulsivity.

[0019] The above impulsivity analysis unit can input the above dimension-specific grades into a pre-built impulsivity analysis model to generate the dimension-specific analysis results according to the above impulsivity in text format and add an academic achievement plan according to the dimension-specific analysis results to the above analysis report.

[0020] Among the embodiments, a method for analyzing user impulsivity based on digital phenotyping includes: a step of collecting multimodal data on user behavior by monitoring a digital learning process on a user terminal through a data collection unit; a step of analyzing the multimodal data through a data analysis unit to detect at least one digital indicator associated with the user behavior; a step of measuring impulsivity regarding the user behavior in the digital learning process based on the at least one digital indicator through an impulsivity measurement unit; and a step of generating an analysis report on at least one of academic achievement, attention, internet / game / smartphone, drug / drug addiction, anger management / violence, self-harming behavior, and impulsive suicide based on the measured impulsivity through an impulsivity analysis unit.

[0021]

[0022] The disclosed technology may have the following effects. However, this does not mean that a particular embodiment must include all or only the following effects, and therefore the scope of the disclosed technology should not be construed as being limited thereby.

[0023] A device and method for analyzing user impulsivity based on digital phenotyping according to one embodiment of the present invention can measure, evaluate, diagnose, and manage impulsivity related to a user's emotional or psychological problems by monitoring the user's daily life and analyzing various digital indicators collected from potential behaviors.

[0024] Additionally, the present invention can provide effective interventions for children, adolescents, and adults with impulsivity-related problems to address underlying emotional and psychological issues, improve emotional regulation skills, teach coping strategies, and promote healthier decision-making.

[0025]

[0026] Figure 1 is a drawing illustrating a user impulsivity analysis system according to the present invention.

[0027] Figure 2 is a drawing explaining the functional configuration of the user terminal of Figure 1.

[0028] Fig. 3 is a drawing explaining the system configuration of the impulse analysis device of Fig. 1.

[0029] Fig. 4 is a drawing explaining the functional configuration of the impulse analysis device of Fig. 1.

[0030] Figure 5 is a flowchart illustrating a user impulsivity analysis method based on digital phenotyping according to the present invention.

[0031] FIG. 6 is a diagram illustrating digital phenotype data for user impulsivity analysis according to the present invention.

[0032]

[0033] The description of the present invention is merely an example for structural and functional explanation, and therefore, the scope of the present invention should not be construed as being limited by the embodiments described in the text. That is, since the embodiments can be modified in various ways and can take various forms, the scope of the present invention should be understood to include equivalents that can realize the technical idea. In addition, the purposes or effects presented in the present invention do not mean that a specific embodiment must include all of them or only such effects, and therefore, the scope of the present invention should not be construed as being limited thereby.

[0034] Meanwhile, the meaning of the terms described in this application should be understood as follows.

[0035] Terms such as "first" and "second" are intended to distinguish one component from another, and the scope of the rights should not be limited by these terms. For example, the first component may be referred to as the second component, and similarly, the second component may also be referred to as the first component.

[0036] When a component is said to be "connected" to another component, it should be understood that while it may be directly connected to that other component, there may also be other components intervening. Conversely, when a component is said to be "directly connected" to another component, it should be understood that there are no other intervening components. Similarly, other expressions describing relationships between components, such as "between" and "directly between," or "adjacent to" and "directly adjacent to," should be interpreted similarly.

[0037] Singular expressions should be understood to include plural expressions unless the context clearly indicates otherwise, and terms such as "comprises" or "have" should be understood to specify the presence of a feature, number, step, operation, component, part or combination thereof, but not to exclude the possibility of the presence or addition of one or more other features, numbers, steps, operations, components, parts or combinations thereof.

[0038] For each step, the identifiers (e.g., a, b, c, etc.) are used for convenience of explanation and do not describe the order of the steps. The steps may occur in a different order than stated unless the context clearly dictates a specific order. That is, the steps may occur in the same order as stated, may be performed substantially simultaneously, or may be performed in the opposite order.

[0039] The present invention can be implemented as computer-readable code on a computer-readable recording medium. The computer-readable recording medium includes all types of recording devices that store data that can be read by a computer system. Examples of computer-readable recording media include ROM, RAM, CD-ROM, magnetic tape, floppy disk, and optical data storage devices. Furthermore, the computer-readable recording medium can be distributed across network-connected computer systems, so that the computer-readable code can be stored and executed in a distributed manner.

[0040] Unless otherwise defined, all terms used herein have the same meaning as commonly understood by those of ordinary skill in the art to which this invention pertains. Terms defined in commonly used dictionaries should be interpreted to be consistent with their meaning within the context of the relevant technology, and should not be interpreted as having an idealized or overly formal meaning unless explicitly defined herein.

[0041]

[0042] Figure 1 is a drawing illustrating a user impulsivity analysis system according to the present invention.

[0043] Referring to FIG. 1, a user impulsivity analysis system (100) may include a user terminal (110), an impulsivity analysis device (130), and a database (150).

[0044] A user terminal (110) may correspond to a terminal device operated by a user. In the embodiment of the present invention, a user may be understood as one or more users, and multiple users may be classified into one or more user groups. Each of the one or more users may correspond to one or more user terminals (110). That is, a first user may correspond to a first user terminal, a second user may correspond to a second user terminal, ..., an n-th user (where n is a natural number) may correspond to an n-th user terminal.

[0045] In addition, the user terminal (110) may correspond to a computing device that can participate in a digital learning process or a user impulsivity analysis process by linking with an impulsivity analysis device (130) as a device that constitutes the user impulsivity analysis system (100). Here, digital learning may correspond to a learning process in which the user participates online in an educational process conducted in an Internet space, such as non-face-to-face education or online education. The user terminal (110) may be implemented as a smartphone, laptop, or computer that is connected to and operable with the impulsivity analysis device (130), but is not necessarily limited thereto, and may also be implemented as various devices including tablet PCs.

[0046] In particular, the user terminal (110) can install and execute a dedicated program or application for interfacing with the impulsivity analysis device (130). For example, the user terminal (110) can participate in a dedicated online learning space provided by the impulsivity analysis device (130) to perform digital learning, and can provide multimodal data based on the user's behavior during the digital learning process to the impulsivity analysis device (130). In addition, the digital learning process and data collection operations can be performed through an interface provided by the dedicated program or application.

[0047] Meanwhile, the user terminal (110) can be connected to the impulsivity analysis device (130) through a network, and a plurality of user terminals (110) can be connected to the impulsivity analysis device (130) simultaneously.

[0048] The impulsivity analysis device (130) may be implemented as a server corresponding to a computer or program that performs the user impulsivity analysis method based on digital phenotyping according to the present invention. Furthermore, the impulsivity analysis device (130) may be connected to a user terminal (110) via a wired network or a wireless network such as Bluetooth, WiFi, or LTE, and may transmit and receive data with the user terminal (110) via the network.

[0049] Additionally, the impulsivity analysis device (130) may be implemented to operate in connection with an independent external system (not shown in FIG. 1) to perform the user impulsivity analysis method based on digital phenotyping according to the present invention. For example, the impulsivity analysis device (130) may operate in conjunction with a learning system that provides online learning, a learning management system that manages learning history, an artificial intelligence system that constructs an artificial intelligence model, and the like.

[0050] Meanwhile, for the convenience of explanation, the user terminal (110) and the impulse analysis device (130) are expressed here as independent devices, but this is not necessarily limited to the above, and it goes without saying that one device may be implemented by being included in the other device.

[0051] The database (150) may correspond to a storage device that stores various information required during the operation of the impulsivity analysis device (130). For example, the database (150) may store learning materials and learning management information for digital learning, or may store multimodal data collected during the digital learning process. However, the database is not necessarily limited thereto, and may store information collected or processed in various forms during the process of the impulsivity analysis device (130) performing the user impulsivity analysis method based on digital phenotyping according to the present invention.

[0052] In addition, in FIG. 1, the database (150) is depicted as a device independent of the impulse analysis device (130), but it is not necessarily limited thereto, and it can be implemented as a logical storage device included in the impulse analysis device (130).

[0053]

[0054] Figure 2 is a drawing explaining the functional configuration of the user terminal of Figure 1.

[0055] Referring to FIG. 2, the user terminal (110) can execute a dedicated program or application for digital learning and perform operations to collect various user behavioral data during the digital learning process. To this end, the user terminal (110) may be implemented with independent modules for monitoring user behavior and collecting data. Specifically, the user terminal (110) may include a multimodal data collection module (210), a foreground process monitoring module (230), and a web browser monitoring module (250).

[0056] Meanwhile, for the convenience of explanation, the user terminal (110) is described as being used in a digital learning process, but it is not necessarily limited to this, and it is obvious that the user terminal (110) can be used in a process of collecting various multimodal data related to the user's behavior in the user's daily life.

[0057] The multimodal data collection module (210) can collect various passive sensor data, keyboard input data, and multimodal data. To this end, the multimodal data collection module (210) can operate in conjunction with various sensors included in the user terminal (110). For example, the multimodal data collection module (210) can periodically collect data information from passive sensors such as angular velocity, acceleration, and light sensors. The multimodal data collection module (210) can collect data such as keyboard values, time, and tap pressure when a user inputs a keyboard, and can collect data when an event such as a user using a stylus or touching with a finger occurs. The data collected by the multimodal data collection module (210) can be stored and preserved in the internal memory, and can be periodically transmitted to the impulsivity analysis device (130) by the user terminal (110).

[0058] In one embodiment, the multimodal data collection module (210) may be implemented in an activity tracking device associated with a user, a smart garment with built-in sensors, a wireless scale that provides weight measurement, a blood glucose meter, a blood pressure monitor device, a heart rate monitor device, and one or more mobile devices running a mobile application, thereby collecting various forms of multimodal data associated with user behavior.

[0059] The foreground process monitoring module (230) can perform an operation to detect the execution of a process, and for this purpose, can include a command to check the package name of the foreground process. The foreground process monitoring module (230) can perform process monitoring as a periodic task, and can collect and record information about the foreground process using the display screen of the user terminal (110) at preset intervals.

[0060] The web browser monitoring module (250) can perform an operation to examine information of a web page that a user accesses through a web browser on a user terminal (110). The web browser monitoring module (250) can operate in an event-driven manner in which a processing function is executed whenever an event occurs, and can collect and record text information whenever a user interacts with a text input window (e.g., a search window, an address window, etc.) of a web browser.

[0061]

[0062] Fig. 3 is a drawing explaining the system configuration of the impulse analysis device of Fig. 1.

[0063] Referring to FIG. 3, the impulse analysis device (130) may include a processor (310), a memory (330), a user input / output unit (350), and a network input / output unit (370).

[0064] The processor (310) can execute a user impulsivity analysis procedure based on digital phenotyping according to an embodiment of the present invention, manage a memory (330) that is read or written in the process, and schedule a synchronization time between a volatile memory and a non-volatile memory in the memory (330). The processor (310) can control the overall operation of the impulsivity analysis device (130), and is electrically connected to the memory (330), the user input / output unit (350), and the network input / output unit (370) to control data flow therebetween. The processor (310) can be implemented as a CPU (Central Processing Unit) or a GPU (Graphics Processing Unit) of the impulsivity analysis device (130).

[0065] The memory (330) may include an auxiliary memory device implemented as a non-volatile memory such as an SSD (Solid State Disk) or an HDD (Hard Disk Drive) and used to store all data required for the impulse analysis device (130), and may include a main memory device implemented as a volatile memory such as a RAM (Random Access Memory). In addition, the memory (330) may store a set of commands that execute a user impulse analysis method based on digital phenotyping according to the present invention by being executed by an electrically connected processor (310).

[0066] The user input / output unit (350) includes an environment for receiving user input and an environment for outputting specific information to the user, and may include, for example, an input device including an adapter such as a touchpad, a touch screen, a visual keyboard, or a pointing device, and an output device including an adapter such as a monitor or a touch screen. In one embodiment, the user input / output unit (350) may correspond to a computing device connected via remote access, and in such a case, the impulsivity analysis device (130) may be performed as an independent server.

[0067] The network input / output unit (370) provides a communication environment for connecting to a user terminal (110) via a network, and may include, for example, an adapter for communication such as a Local Area Network (LAN), a Metropolitan Area Network (MAN), a Wide Area Network (WAN), and a Value Added Network (VAN). In addition, the network input / output unit (370) may be implemented to provide a short-range communication function such as WiFi or Bluetooth, or a wireless communication function of 4G or higher for wireless transmission of data.

[0068]

[0069] Fig. 4 is a drawing explaining the functional configuration of the impulse analysis device of Fig. 1.

[0070] Referring to FIG. 4, the impulsivity analysis device (130) can perform a user impulsivity analysis method based on digital phenotyping according to the present invention. To this end, the impulsivity analysis device (130) can include a data collection unit (410), a data analysis unit (430), an impulsivity measurement unit (450), an impulsivity analysis unit (470), and a control unit (not shown in FIG. 3).

[0071] At this time, the embodiments of the present invention do not necessarily include all of the above-described components simultaneously. Depending on the embodiment, some of the above-described components may be omitted, or some or all of the above-described components may be selectively included. The operation of each component will be described in detail below.

[0072] The data collection unit (410) can monitor the digital learning process on the user terminal (110) to collect multimodal data on user behavior. To this end, the data collection unit (410) can operate in conjunction with the user terminal (110) and receive multimodal data collected through a dedicated program or application running on the user terminal (110).

[0073] In one embodiment, the data collection unit (410) may collect multimodal data through an application running on the user terminal (110) during a digital learning process. Here, the multimodal data may include motion indicators resulting from user actions on the display screen of the user terminal (110). For example, the multimodal data may include data collected from touch or stroke actions by the user on a touchscreen. In particular, the data collection unit (410) may collect various behavioral information generated while the user uses a dedicated application for a specific purpose as multimodal data.

[0074] In one embodiment, the data collection unit (410) may collect multimodal data of the user's keyboard-related actions and stroke actions collected by the on-screen keyboard sensor and touchscreen sensor of the user terminal (110) during the problem-solving process in a digital learning course. Here, the problem-solving process may correspond to a process in which a problem is provided through the display screen of the user terminal (110) and the user reads the problem and enters the correct answer. At this time, the user may input the correct answer by touching the display screen or using the keyboard displayed on the screen, and the data collection unit (410) may collect multimodal data collected through the display screen among the user actions occurring during the problem-solving process or the correct answer input process as a motion index.

[0075] The data analysis unit (430) can analyze multimodal data to detect at least one digital indicator associated with user behavior. For example, the data analysis unit (430) can extract digital indicators highly correlated with impulsivity (impulsiveness) related to user behavior from multimodal data collected during a digital learning process, and can perform preprocessing operations such as missing data processing and denoising during the process.

[0076] In addition, the data analysis unit (430) can use z-score transformation, multiple regression model, etc. to analyze multimodal data. For example, the data analysis unit (430) can z-score transform data with mean m and standard deviation s for each item of multimodal data to compare indicators derived from different distributions. Thereafter, the data analysis unit (430) can perform multiple regression using a bootstrap technique. Bootstrapping can correspond to a method of estimating a sampling distribution by taking multiple samples with restoration from a single random sample. The data analysis unit (430) can build a multiple regression model through multiple regression and generate a final regression result by removing multicollinearity indicators.

[0077] In one embodiment, the data analysis unit (430) can determine at least one digital indicator from among stroke acceleration, stroke speed, vertical distance, number of blank spaces, time interval, stroke length, and tap pressure.

[0078] Specifically, stroke acceleration may correspond to the rate of change in velocity while making a stroke on the touchscreen, stroke speed may correspond to the number of pixels per second or distance, vertical distance may correspond to the distance from the top of the screen to the starting position during the stroke, number of spaces may correspond to the number of times the spacebar is pressed between letters, words, and sentences, time interval may correspond to the time (ms) between touching one key and touching another key, average stroke length may correspond to the average of stroke lengths, and tap pressure may correspond to the amount of force applied to a tap with a finger.

[0079] For example, in the correlation between user impulsivity and digital indicators of user behavior, user impulsivity may show a positive correlation with indicators such as stroke acceleration, stroke speed, vertical distance, and average stroke length, and may show a negative correlation with indicators such as number of spaces, time interval, and tap pressure. The data analysis unit (430) may determine digital indicators that have a high correlation with user impulsivity in the digital learning process through data analysis.

[0080] The impulsivity measurement unit (450) can measure impulsivity in user behavior during a digital learning process based on at least one digital indicator. Here, impulsivity in user behavior, or impulsiveness, can be a psychological trait that indicates a tendency to act without considering the potential consequences of the action. In other words, impulsivity is often driven by immediate desires or emotions rather than rational decision-making, and can involve acting quickly without prior thought. Furthermore, impulsivity can manifest itself in various ways, such as making hasty decisions, being unable to resist temptation, and exhibiting impatience.

[0081] In one embodiment, the impulsivity measurement unit (450) may generate a feature vector relating to at least one digital indicator, the number of incorrect answers during the problem-solving process, the user's emotional score, and the user's aggression score, and learn the correlation between the feature vector and the impulsivity to build an impulsivity model. Here, the impulsivity model may correspond to an artificial intelligence model designed to receive various indicators of the user's behavior as input and generate the user's impulsivity score as output. To this end, the impulsivity measurement unit (450) may build the impulsivity model based on a pre-built learning dataset, and may predict the user's impulsivity score through the impulsivity model by utilizing various digital indicators collected from the user.

[0082] Here, the input of the impulsivity model can be defined as a feature vector with various digital indicators and independent dimensions such as the number of incorrect answers, emotional scores, and aggression scores based on problem solving. The emotional score (emotion) is positive when + is positive, with higher values ​​indicating more positivity, neutral when 0, and negative when -, with lower values ​​indicating more negativity. The aggression score corresponds to a comorbid disease and can indicate cases where the client, patient, or user has anxiety. Furthermore, user impulsivity can exhibit a positive correlation with the number of incorrect answers and the aggression score, and a negative correlation with the emotional score.

[0083] The impulsivity analysis unit (470) can generate an analysis report on at least one of the following factors based on measured impulsivity: academic achievement, attention, internet / game / smartphone use, drug / drug addiction, anger management / violence, self-harm, and impulsive suicide. For example, a user's impulsivity can negatively impact academic achievement in various ways. Specifically, students with high impulsivity may have difficulty maintaining attention, concentration, and focus, which may interfere with completing assignments and studying effectively. Furthermore, impulsive behavior can lead to procrastination, resulting in incomplete or rushed work. Furthermore, impulsive students may have difficulty following instructions and adhering to study schedules, which can lead to lower grades and academic achievement.

[0084] As another example, individuals with high impulsivity may have difficulty regulating their emotions, particularly anger. That is, impulsive individuals may struggle to manage frustration and react quickly and aggressively to perceived provocations (even in situations where there is no actual threat or danger). This can lead to anger management failures, anger outbursts, physical aggression, or violent behavior. Consequently, these impulsive responses can lead to serious consequences, including legal trouble, strained relationships, and physical harm to oneself or others.

[0085] As another example, a user's impulsivity may be closely linked to self-harm, burning, or other forms of self-injurious behavior. Specifically, when an individual experiences overwhelming emotions or pain, their impulsive tendencies may lead them to self-harm as a way to cope with intense emotions. Therefore, self-harming behavior is dangerous and may be a sign of an underlying emotional or mental health issue that requires professional help.

[0086] As another example, a user's impulsivity may be a significant risk factor for impulsive suicide, which often involves an impulsive suicide attempt in response to acute emotional distress or distress. Furthermore, impulsive suicide may differ from planned suicide in that it involves little or no planning. Impulsive individuals may act on suicidal impulses without considering the consequences or long-term impact of their actions.

[0087] In one embodiment, the impulsivity analysis unit (470) can define academic achievement, attention, internet / game / smartphone use, drug / drug addiction, anger management / violence, self-harm behavior, and impulsive suicide as independent dimensions and generate a dimensional grade according to impulsivity. That is, the impulsivity analysis unit (470) can generate a graded analysis result for each item based on the measured impulsivity index. To this end, the impulsivity analysis unit (470) can utilize the regression analysis results performed by the data analysis unit (430) and, if necessary, can combine various analysis methods to generate a dimensional grade.

[0088] In one embodiment, the impulsivity analysis unit (470) may input the dimension-specific ratings into a pre-built impulsivity analysis model to generate the dimension-specific analysis results according to impulsivity in text format and add an academic achievement plan according to the dimension-specific analysis results to an analysis report. Here, the impulsivity analysis model may correspond to an artificial intelligence model designed to receive the dimension-specific ratings regarding the user's impulsivity as input and generate text regarding the analysis results for each dimension as output. To this end, the impulsivity analysis unit (470) may build the impulsivity analysis model based on a pre-built learning dataset, and may utilize the dimension-specific rating information measured by the impulsivity measurement unit (450) to generate the analysis results regarding the user's impulsivity in text format through the impulsivity analysis model.

[0089] For example, the impulsivity analysis unit (470) can generate analysis results on impulsivity and academic achievement based on the user's impulsivity, or on impulsivity and attention, or on impulsivity and the Internet / games / smartphones, or on impulsivity and drugs / drug addiction, or on impulsivity and anger management / violence, or on impulsivity and self-harming behavior, or on impulsivity and impulsive suicide, independently. In addition, the impulsivity analysis unit (470) can generate an analysis report that includes, as an analysis result, a plan to improve academic achievement by improving emotional control capabilities while solving psychological problems related to the user's impulsivity based on the dimensional analysis results.

[0090] In one embodiment, the impulsivity analysis model may be implemented as an artificial intelligence model built to predict a user's trajectory within a latent impulsivity-behavior space based on a pre-built learning dataset. Here, the latent impulsivity-behavior space may be implemented as a multi-dimensional data space that includes dimensions of digital indicators associated with user behavior and dimensions related to user impulsivity. Furthermore, the user's trajectory within the latent impulsivity-behavior space may be expressed as a shape or trajectory based on changes in the user's coordinates over a specific time interval.

[0091] In another embodiment, the dimensions of user impulsivity may include each dimension of academic achievement, attention, internet / game / smartphone use, drugs / drug addiction, anger management / violence, self-harm behavior, and impulsive suicide associated with user impulsivity. For example, the impulsivity analysis model may receive digital indicators detected from multimodal data on user behavior and predict and output the user's path within the latent impulsivity-behavior space. Accordingly, the impulsivity analysis unit (470) may generate analysis results (i.e., ratings or text) regarding academic achievement, attention, internet / game / smartphone use, drugs / drug addiction, anger management / violence, self-harm behavior, and impulsive suicide based on the user's predicted path within the latent impulsivity-behavior space through the impulsivity analysis model.

[0092] The control unit (not shown in FIG. 3) controls the overall operation of the impulse analysis device (130) and can manage the control flow or data flow between the data collection unit (410), the data analysis unit (430), the impulsivity measurement unit (450), and the impulsivity analysis unit (470).

[0093]

[0094] Figure 5 is a flowchart illustrating a user impulsivity analysis method based on digital phenotyping according to the present invention.

[0095] Referring to FIG. 5, the impulse analysis device (130) can collect multimodal data on user behavior by monitoring a digital learning process on a user terminal (110) via a data collection unit (410) (step S510). The impulse analysis device (130) can analyze the multimodal data via a data analysis unit (430) to detect at least one digital indicator associated with user behavior (step S530).

[0096] In addition, the impulsivity analysis device (130) can measure impulsivity regarding user behavior in a digital learning process based on at least one digital indicator through the impulsivity measurement unit (450) (step S550). The impulsivity analysis device (130) can generate an analysis report on at least one of academic achievement, attention, internet / games / smartphones, drugs / drug addiction, anger management / violence, self-harming behavior, and impulsive suicide based on the impulsivity measured through the impulsivity analysis unit (470) (step S570).

[0097]

[0098] FIG. 6 is a diagram illustrating digital phenotype data for user impulsivity analysis according to the present invention.

[0099] Referring to FIG. 6, the impulsivity analysis device (130) can measure impulsivity regarding user behavior by utilizing various indicators extracted from multimodal data regarding user behavior. That is, the impulsivity analysis device (130) can measure individual user impulsivity by estimating it using various digital phenotype (phenotype) data that can be routinely collected in daily life, rather than using a conventional questionnaire. The impulsivity analysis device (130) can collect acceleration, speed, average length of strokes, vertical coordinates of taps or strokes, number of spaces (number of spaces), time intervals, force of tapping with a finger, emotional score, number of incorrect answers, aggression score, etc. as digital phenotype data.

[0100] In addition, the impulsivity analysis device (130) can determine directionality by analyzing the correlation between impulsivity and each data. That is, digital phenotypic data indicating a positive correlation with impulsivity may include acceleration / speed / average length of stroke, vertical distance, number of incorrect answers, and aggression score, and digital phenotypic data indicating a negative correlation with impulsivity may include number of blank spaces, inter-key interval (time between pressing one key and pressing the next key), finger tapping force, and emotional score.

[0101] Specifically, the higher the stroke acceleration, the stronger the impulsivity, the higher the stroke speed, the higher the impulsivity, the more you use the bottom of the screen, the higher the impulsivity, the less the spacing, that is, the more the spacing is not used, the stronger the impulsivity, the shorter the time interval between pressing the keyboard buttons, that is, the faster the key pressing speed, the higher the impulsivity, the longer the stroke length, the lower the tapping force with your fingers, the higher the impulsivity, the more negative the emotion, the higher the impulsivity, the more incorrect problems, and the higher the aggression (i.e., the higher the anxiety), the higher the impulsivity tends to be.

[0102] In one embodiment, the impulsivity analysis device (130) can collect various digital phenotypic data regarding the user's behavior in an everyday living environment, analyze the digital phenotypic data to predict the user's impulsivity, and if impulsivity exceeding a preset threshold is detected, a notification can be provided to the user, guardian, and administrator so that appropriate measures can be taken for the user. In addition, the impulsivity analysis device (130) can generate various item-specific grades and texts related to the user's impulsivity, and if impulsivity exceeding a preset threshold for each item-specific grade is detected, a notification can be generated and provided.

[0103] Additionally, the impulsivity analysis device (130) can detect risk factors associated with user behavior early. That is, impulsivity can be a significant risk factor for various behavioral and mental health problems. By identifying impulsivity in children and adolescents early, individuals at risk for problems such as substance abuse, conduct disorders, or other impulsive behaviors can be effectively identified and notified.

[0104] Additionally, the impulsivity analysis device (130) can analyze the level and personality of impulsivity in children and adolescents, enabling professional intervention and treatment to be tailored to address specific needs. For example, professional intervention may include improving self-regulation skills, decision-making abilities, and emotional regulation abilities.

[0105] Additionally, the impulsivity analysis device (130) can improve a user's academic achievement. Specifically, impulsivity can negatively impact academic performance, and children and adolescents struggling with impulsivity may experience difficulties with concentration, hasty writing, organization, and task completion. The impulsivity analysis device (130) can identify children or adolescents with high impulsivity early on based on user behavior analysis and provide customized solutions, such as ways to improve academic achievement.

[0106] Additionally, the impulsivity analysis device (130) can support the user's development of harmonious social relationships. That is, impulsive behavior can sometimes lead to conflict with peers or authority figures, and impulsivity can also impact social relationships. Addressing impulsivity can help improve social skills and reduce interpersonal problems.

[0107] Additionally, the impulsivity analysis device (130) can provide insight into individual differences and provide appropriate customized strategies to promote healthy development and well-being by measuring impulsivity in children and adolescents through continuous measurement using digital phenotypes, given that impulsivity in childhood and adolescence is associated with long-term outcomes in adulthood.

[0108]

[0109] Although the present invention has been described above with reference to preferred embodiments thereof, it will be understood by those skilled in the art that various modifications and changes may be made to the present invention without departing from the spirit and scope of the present invention as set forth in the claims below.

[0110]

[0111] [Explanation of symbols]

[0112] 100: User Impulse Analysis System

[0113] 110: User terminal 130: Impulse analysis device

[0114] 150: Database

[0115] 210: Multimodal Data Collection Module

[0116] 230: Foreground Process Monitoring Module

[0117] 250: Web Browser Monitoring Module

[0118] 310: Processor 330: Memory

[0119] 350: User input / output section 370: Network input / output section

[0120] 410: Data Collection Department 430: Data Analysis Department

[0121] 450: Impulsivity Measurement Unit 470: Impulsivity Analysis Unit

Claims

1. A data collection unit that monitors the digital learning process on the user terminal and collects multimodal data on user behavior; A data analysis unit that analyzes the multimodal data to detect at least one digital indicator associated with the user behavior; An impulsivity measuring unit for measuring impulsivity regarding the user's behavior in the digital learning process based on at least one digital indicator; and A user impulsivity analysis device based on digital phenotyping, comprising an impulsivity analysis unit that generates an analysis report on at least one of academic achievement, attention, internet / game / smartphone, drug / drug addiction, anger management / violence, self-harming behavior, and impulsive suicide based on the measured impulsivity.

2. In paragraph 1, the data collection unit Collecting the multimodal data through an application running on the user terminal during the digital learning process; A user impulsivity analysis device based on digital phenotyping, characterized in that the multimodal data includes behavioral indicators based on the user behavior on the display screen of the user terminal.

3. In the second paragraph, the data collection unit A user impulsivity analysis device based on digital phenotyping, characterized in that the user's keyboard-related actions and stroke actions collected by the on-screen keyboard sensor and touchscreen sensor of the user terminal during the problem-solving process during the digital learning process are collected as the multimodal data.

4. In paragraph 1, the data analysis unit A user impulsivity analysis device based on digital phenotyping, characterized in that it determines at least one digital indicator from among stroke acceleration, stroke speed, vertical distance, number of blank spaces, time interval, stroke length, and tap pressure.

5. In the first paragraph, the impulsivity measurement unit A user impulsivity analysis device based on digital phenotyping, characterized in that it generates a feature vector regarding at least one digital indicator and the number of incorrect answers during the problem-solving process, the user's emotional score, and the user's aggression score, and learns the correlation between the feature vector and impulsivity to build an impulsivity model.

6. In paragraph 1, the impulsivity analysis unit A user impulsivity analysis device based on digital phenotyping, characterized in that the above academic achievement, attention, internet / game / smartphone, drug / drug addiction, anger management / violence, self-harm behavior, and impulsive suicide are each defined as independent dimensions and a dimensional grade is generated according to the above impulsivity.

7. In paragraph 6, the impulsivity analysis unit A user impulsivity analysis device based on digital phenotyping characterized in that the above dimension-specific grades are input into a pre-built impulsivity analysis model, the dimension-specific analysis results according to the above impulsivity are generated in text format, and the academic achievement plan according to the dimension-specific analysis results is added to the analysis report.

8. In the impulsivity analysis method performed in the impulsivity analysis device, A step of collecting multimodal data on user behavior by monitoring the digital learning process on the user terminal through a data collection unit; A step of analyzing the multimodal data through a data analysis unit to detect at least one digital indicator associated with the user behavior; A step of measuring impulsivity regarding the user's behavior in the digital learning process based on the at least one digital indicator through the impulsivity measurement unit; and A method for analyzing user impulsivity based on digital phenotyping, comprising: a step of generating an analysis report on at least one of academic achievement, attention, internet / game / smartphone, drug / drug addiction, anger management / violence, self-harming behavior, and impulsive suicide based on the measured impulsivity through an impulsivity analysis unit;

Images