Electronic device, method, program, and storage medium for estimating cause of user stress

Abstract

Provided are a method, an electronic device, a program, and a storage medium for estimating a cause of user stress. The method for estimating a cause of user stress may comprise the operations of: during a first period, recording first logging data for a user on the basis of an interaction between the user and an electronic device; during the first period, acquiring first biometric data recorded by a wearable device worn by the user; acquiring first information including a first stress cause related to stress of the user by applying a first input including the first logging data and the first biometric data to an artificial intelligence model; providing a query related to the first stress cause of the user on the basis of the first information; receiving the user's response to the query; during a second period after the first period, recording second logging data for the user and acquiring second biometric data from the wearable device; and acquiring second information including a second stress cause elaborating the first stress cause, by applying the response and a second input including the second logging data and the second biometric data to the artificial intelligence model, wherein the second stress cause is dependent on the first stress cause.

Description

Electronic device, method, program and storage medium for estimating the cause of user's stress

[0001] The present disclosure relates to an electronic device and method for estimating a user's stressor, and more particularly, to estimating a user's stressor using biometric data recorded by a wearable device of the user.

[0002] As the number of users wearing wearable devices increases, efforts to innovate and improve the user experience with them continue. This is being achieved through more sophisticated sensor technology, AI-powered data analysis, and improved user interfaces, further expanding the utility of wearable devices across various sectors, such as healthcare, fitness, and entertainment.

[0003] Recently, artificial intelligence systems that achieve human-level intelligence are being utilized in various fields. Unlike existing rule-based smart systems, AI systems are machines that learn, make decisions, and become intelligent on their own. As AI systems become more used, their recognition rates improve and their ability to understand user preferences more accurately is increasing. As a result, existing rule-based smart systems are gradually being replaced by deep learning-based AI systems.

[0004] The above information may be provided as background art to aid in understanding the present disclosure. No claim or determination is made as to whether any of the above-described matters constitute prior art related to the present disclosure.

[0005] In one embodiment, a method may include recording first logging data for a user based on an interaction between the user and an electronic device during a first period. The method may include obtaining first biometric data recorded by a wearable device worn by the user during the first period. The method may include obtaining first information including a first stress cause related to stress of the user by applying a first input including the first logging data and the first biometric data to an artificial intelligence model. The method may include providing a query related to the first stress cause of the user based on the first information. The method may include receiving a response from the user to the query. The method may include recording second logging data for the user during a second period after the first period and obtaining second biometric data from the wearable device. The method may include obtaining second information including a second stress cause elaborating the first stress cause by applying a second input including the second logging data and the second biometric data and the response to the artificial intelligence model. In one embodiment, the second stress cause may be dependent on the first stress cause.

[0006] An electronic device according to one embodiment may include a memory storing instructions; and one or more processors. The instructions, when individually or collectively executed by the one or more processors, may cause the electronic device to record first logging data for a user based on an interaction between the user and the electronic device during a first period of time. The instructions, when individually or collectively executed by the one or more processors, may cause the electronic device to obtain first biometric data recorded by a wearable device worn by the user during the first period of time. The instructions, when individually or collectively executed by the one or more processors, may cause the electronic device to obtain first information including a first stress cause related to stress of the user by applying a first input including the first logging data and the first biometric data to an artificial intelligence model. The instructions, when individually or collectively executed by the one or more processors, may cause the electronic device to provide a query related to the first stress cause of the user based on the first information. The above instructions, when individually or jointly executed by the one or more processors, may cause the electronic device to receive the user's response to the query. The above instructions, when individually or jointly executed by the one or more processors, may cause the electronic device to record second logging data about the user and obtain second biometric data from the wearable device during a second period after the first period.The instructions, when individually or jointly executed by the one or more processors, may cause the electronic device to obtain second information including a second stress cause elaborating the first stress cause by applying the second input and the response including the second logging data and the second biometric data to the artificial intelligence model. In one embodiment, the second stress cause may be subordinate to the first stress cause.

[0007] According to one embodiment, the method comprises: recording first logging data for a user based on an interaction between the user and an electronic device during a first period; obtaining first biometric data recorded by a wearable device worn by the user during the first period; obtaining first information including a first stress cause related to stress of the user by applying a first input including the first logging data and the first biometric data to an artificial intelligence model; providing a query related to the first stress cause of the user based on the first information; receiving a response from the user to the query; recording second logging data for the user during a second period after the first period and obtaining second biometric data from the wearable device; and obtaining second information including a second stress cause elaborating the first stress cause by applying a second input including the second logging data and the second biometric data and the response to the artificial intelligence model. A computer-readable recording medium having recorded thereon a program for executing a method, wherein the second stress cause is dependent on the first stress cause, may be provided.

[0008] A non-transitory computer-readable recording medium according to one embodiment of the present invention may store at least one command and / or instruction that, when executed, causes an electronic device to perform the above-described method or operation of the electronic device.

[0009] In connection with the description of the drawings, the same or similar reference numerals may be used for the same or similar components.

[0010] FIG. 1 is a diagram illustrating an overview of an electronic device according to one embodiment that predicts a user's stress cause using a wearable device.

[0011] FIG. 2 is a flowchart of a method for an electronic device to output a stress source according to one embodiment.

[0012] FIG. 3 is a diagram illustrating an example of an artificial intelligence model generating output based on input according to one embodiment.

[0013] FIG. 4 is a diagram showing an example in which an artificial intelligence model according to one embodiment reflects a user's response.

[0014] FIG. 5 is a diagram illustrating an example of an electronic device providing a query related to a stress source according to one embodiment.

[0015] Figure 6 is a diagram illustrating an example of specifying a stress cause according to one embodiment.

[0016] FIG. 7 is a diagram illustrating an example in which an electronic device according to one embodiment outputs a stress cause according to a stress category.

[0017] FIG. 8 is a diagram illustrating an example of an electronic device providing guidance in response to a stress source according to one embodiment.

[0018] FIG. 9 is a diagram showing an example of an artificial intelligence model generating output using various data according to one embodiment.

[0019] FIG. 10 is a diagram illustrating an example of a wearable device according to one embodiment.

[0020] FIG. 11 is a diagram illustrating an example of a hardware structure of a wearable device according to one embodiment.

[0021] Figure 12 is a block diagram of a software structure of a wearable device according to one embodiment.

[0022] Figure 13 is a block diagram of a software structure of an electronic device according to one embodiment.

[0023] Figure 14 is a block diagram of an electronic device according to one embodiment.

[0024] FIG. 15 is a diagram illustrating an example of a system including a generative artificial intelligence model according to one embodiment.

[0025] Below, embodiments of the present disclosure are described in detail with reference to the attached drawings so that those skilled in the art can easily implement the present disclosure. However, the present disclosure may be implemented in various different forms and is not limited to the embodiments described herein. In addition, for the purpose of clearly explaining the present disclosure in the drawings, parts irrelevant to the description are omitted, and similar parts are designated with similar reference numerals throughout the specification.

[0026] The terms used in this disclosure are described using commonly used terms, taking into account the functions described herein. However, these terms may refer to various other terms depending on the intentions of those skilled in the art, precedents, or the emergence of new technologies. Therefore, the terms used in this disclosure should not be interpreted solely based on their names, but rather based on the meanings of the terms and the overall content of this disclosure.

[0027] Additionally, terms such as first, second, third, ..., Nth may be used to describe various components, but the components should not be limited by these terms. These terms are used to distinguish one component from another.

[0028] Throughout the specification, when a part is said to be "connected" to another part, this includes not only the cases where the parts are "directly connected" but also the cases where the parts are "electrically connected" with other elements intervening. Furthermore, when a part is said to "include" a component, this does not exclude other components, but rather includes other components, unless otherwise stated.

[0029] The appearance of phrases such as “in one embodiment” in various places throughout this disclosure are not necessarily all referring to the same embodiment.

[0030] An embodiment of the present disclosure may be represented by functional block configurations and various processing steps. Some or all of these functional blocks may be implemented by various hardware and / or software configurations that perform specific functions. For example, the functional blocks of the present disclosure may be implemented by one or more microprocessors or by circuit configurations for a given function. Furthermore, for example, the functional blocks of the present disclosure may be implemented in various programming or scripting languages. The functional blocks may be implemented by algorithms that execute on one or more processors. Furthermore, the present disclosure may employ conventional techniques for electronic configuration, signal processing, and / or data processing. Terms such as “mechanism,” “element,” “means,” and “configuration” may be used broadly and are not limited to mechanical and physical configurations.

[0031] Additionally, the connecting lines or connecting members between components depicted in the drawings are merely exemplary representations of functional connections and / or physical or circuit connections. In an actual device, connections between components may be represented by various functional connections, physical connections, or circuit connections that may be replaced or added.

[0032] Artificial intelligence technology consists of machine learning (e.g., deep learning) and elemental technologies that utilize machine learning.

[0033] Machine learning is an algorithm technology that classifies / learns the characteristics of input data on its own, and the element technology is a technology that uses the machine learning algorithm of deep learning to imitate the functions of the human brain, such as cognition and judgment, and is composed of the technical fields of linguistic understanding, visual understanding, inference / prediction, knowledge representation, and motion control.

[0034] The various fields in which AI technology is applied are as follows. Linguistic understanding refers to the technology that recognizes, applies, and processes human language / text, including natural language processing, machine translation, dialogue systems, question-answering, and speech recognition / synthesis. Visual understanding refers to the technology that recognizes and processes objects similar to human vision, including object recognition, object tracking, image search, person recognition, scene understanding, spatial understanding, and image enhancement. Inference prediction refers to the technology that logically infers and predicts information by judging it. It includes knowledge / probability-based inference, optimization prediction, preference-based planning, and recommendation. Knowledge representation refers to the technology that automatically processes human experience information into knowledge data, including knowledge construction (data creation / classification) and knowledge management (data utilization). Motion control refers to the technology that controls the movement of autonomous vehicles and robots, including motion control (navigation, collision, driving), and manipulation control (behavior control).

[0035] People living in modern society are exposed to a variety of stressors. These stressors stem from diverse sources, such as work, financial pressures, interpersonal relationships, and health issues. This negatively impacts many people's physical and mental health, making it increasingly important to find effective stress management methods to improve mental health.

[0036] By monitoring users' biosignals using wearable devices, users can effectively manage stress.

[0037] According to one embodiment, the logging data may be data recorded or generated by an electronic device related to the user's daily activities and behaviors. The logging data may be recorded by the electronic device based on interactions between the user and the electronic device and may be expressed as a history. For example, the logging data may include, but is not limited to, location history, activity history, exercise history, application usage history, search history, call history, message history, social network service (SNS) usage history, sleep history, and environmental history. For example, location data such as the user's location, movement path, and visited places may be measured or recorded by a map application, a navigation application, a health application, or a health application to create a location history. For example, sleep information such as the user's bedtime, sleep onset time, wake-up time, total sleep time, and sleep state may be measured or recorded by a sleep management application or a health application to create a sleep history. For example, indoor environmental data such as noise, temperature, humidity, illuminance, fine dust, the user's presence, and the user's indoor location around the user can be measured or recorded by a home management application or an Internet of Things (IoT) application to create an environmental history. For example, activity data such as a user's walking, running, driving, and sports activities can be measured or recorded by a workout application, map application, navigation application, or health application to create an activity history.For example, application usage history, search history, call history, message history, and social network service (SNS) usage history can be generated by a screen time application, an internet browser, a phone application, a messaging application, and an SNS application, respectively. In one embodiment, the logging data can be archived by the application that measures the logging data, but is not limited thereto, and can be archived by a specific application that comprehensively stores various types of data. In one embodiment, a health application can store logging data including biometric data measured by a wearable device, location history, and activity history, and ambient noise data generated based on acoustic data, and the data stored in the health application can be transmitted to a stress management application. Access to data of the health application can be granted to the stress management application to retrieve from a specific application, for example, to retrieve biometric data, location data, activity data, or ambient noise data stored by the health application. In one embodiment, the stress management application of the electronic device can be a part of the health application. In one embodiment, the home management application may store voice and audio data recorded by IoT devices, proximity-based indoor location data of the user, and indoor environmental data such as temperature and humidity. The data stored in the home management application may be transmitted to the stress management application. For example, the stress management application may be granted access to data stored in the home management application to retrieve voice data, audio data, location data, or indoor environmental data stored by the home management application.

[0038] For example, the logging data may include, but is not limited to, location data of an electronic device indicating information related to the user's location, such as the user's movement path and / or the places the user visited, data about the user's activities (e.g., walking, running, driving) collected through the electronic device, data about programs or applications used by the user, data about keywords or search results searched by the user, data about calls made or received by the user, data about messages sent or received by the user, data about SNS accessed and used by the user, the user's biometric data (e.g., heart rate, electrocardiogram, body composition, blood oxygen, blood pressure, and amount of exercise), the user's sleep data (e.g., bedtime, falling asleep time, waking up time, sleep time, and sleep status), and / or sensing data about the environment around the electronic device carried by the user (e.g., ambient temperature, humidity, noise level, fine dust, lighting conditions, and whether the user is present). Data about programs or applications used by a user may include content entered by the user into the program or application or content generated by the program or application, and data about social networking services may include content entered by the user into the social networking service or content generated by the social networking service. For example, if a user uses a calendar application, the logging data may include information about calendar events entered by the user into the calendar application. For example, if a user uses a mail application, the logging data may include information about emails sent or received by the user. For example, if a user accesses a social networking service, the logging data may include information about posts uploaded by the user through the social networking service, posts interacted with by pressing buttons such as "Like" or "Dislike" on the social networking service, and posts shared by the user on the social networking service.

[0039] According to one embodiment, the logging data may include user status data. The user status data according to one embodiment may be generated at least partially based on the user's logging data and may represent the user's status. For example, the user status data may include, but is not limited to, the user's current status, activity status, activity level, health status, psychological status, sleep status, lifestyle habits, behavioral patterns, and environmental conditions.

[0040] Biometric data according to one embodiment may include a biosignal detected by a biosignal sensor of a wearable device and may indicate a biological state of a user wearing the wearable device. The biosignal sensor of the wearable device may detect the user's biosignal through non-invasive measurement, but is not limited thereto. The biosignal may be directly detected from the biosignal sensor or may be derived from a signal detected by the biosignal sensor. For example, the biosignal sensor may include, but is not limited to, a photoplethysmography (PPG) sensor, an electrodermal activity (EDA) sensor, an electrocardiogram (ECG) sensor, a heart rate (HR) sensor, a blood glucose sensor, an alcohol sensor, an advanced glycation end products (AGEs) sensor, an antioxidant sensor, and an oxygen saturation of partial pressure oxygen (SpO2) sensor.

[0041] An AI model according to one embodiment may be an AI model trained to generate information related to a user's stress based on inputs including logging data and biometric data. For example, the AI ​​model may be an AI model trained to generate information including a user's stress cause, stress category, stress cause type, stress level, and guidance corresponding to the user's stress cause and / or stress level based on analysis results of inputs including logging data and biometric data. The AI ​​model according to one embodiment may be a multimodal model that learns and processes relationships between data of various modalities. The multimodal model may learn relationships between logging data and biometric data of different modalities to generate information related to the user's stress.

[0042] According to one embodiment, a stressor is a cause that causes user stress, and can be output by applying user-related input to a pre-trained artificial intelligence model. The input may include, but is not limited to, the user's logging data and biometric data, and the input may further include acoustic data, motion data, and environmental data. The acoustic data may include voice data, and the logging data may include user status data.

[0043] In one embodiment, a stressor may be associated with a stressor that elaborates the stressor. In the present disclosure, a stressor that elaborates the stressor may be referred to as a subordinate stressor, and a stressor elaborated by a subordinate stressor may be referred to as a superordinate stressor. It should be understood that the terms superordinate and subordinate are terms used to distinguish between the stressor being elaborated and the stressor that elaborates the stressor, and are not terms used to specify the stressor. A stressor may be associated with a stressor that elaborates the stressor. Stressors may be referred to as a first-level stressor, a second-level stressor, ..., an nth-level stressor, depending on the hierarchy. A second-level stressor may elaborate the first-level stressor and be subordinate to the first-level stressor. An nth-level stressor may elaborate the n-1st-level stressor and be subordinate to the n-1st-level stressor.

[0044] According to one embodiment, stress categories serve as criteria for classifying stress. For example, stress may be classified into positive stress categories and negative stress categories, but is not limited thereto. Positive stress may be eustress, and negative stress may be distress.

[0045] According to one embodiment, the stress type is a criterion for classifying a stress cause. For example, the stress cause may be classified into stress types such as physical stress type, mental stress type, and environmental stress type, but is not limited thereto. For example, the stress cause may be classified into social stress type, spiritual stress type, and occupational stress type. The stress type may include at least one of physical stress type, mental stress type, and environmental stress type, but is not limited thereto. The stress type may include at least one of physical stress type, mental stress type, environmental stress type, social stress type, spiritual stress type, and occupational stress type. The stress type may be a criterion for classifying a negative stress cause.

[0046] According to one embodiment, motion data may be detected by a motion sensor of a wearable device and may represent motions of a user wearing the wearable device. The motion data may also be detected by a motion sensor of an electronic device.

[0047] Hereinafter, various embodiments of the present disclosure will be described with reference to the attached drawings. However, this is not intended to limit the present disclosure to specific embodiments, and it should be understood that various modifications, equivalents, and / or alternatives of the embodiments of the present disclosure are included.

[0048] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the drawings so that those skilled in the art can easily implement the present disclosure. However, the present disclosure may be implemented in various different forms and is not limited to the embodiments described herein. In connection with the description of the drawings, the same or similar reference numerals may be used for identical or similar components. Furthermore, in the drawings and related descriptions, descriptions of well-known functions and configurations may be omitted for clarity and conciseness.

[0049] FIG. 1 is a diagram illustrating an overview of an electronic device according to one embodiment that predicts a user's stress cause using a wearable device.

[0050] Referring to FIG. 1, an electronic device (2000) according to one embodiment may communicate with a wearable device (1000) and receive a user's biometric data from the wearable device (1000). According to one embodiment, the electronic device (2000) may display information about the user's stress based on the biometric data received from the wearable device (1000).

[0051] In one embodiment, the electronic device (2000) may generate logging data about the user based on interactions with the user. The electronic device (2000) may record and analyze the logging data to display information related to the user's activities. In one embodiment, the electronic device (2000) may display information about the user's stress level based on the user's logging data.

[0052] According to one embodiment, the electronic device (2000) can display information related to the user's stress based on the user's logging data and biometric data. The user's logging data may be generated and recorded by the electronic device (2000), but is not limited thereto. For example, the logging data may also be generated and recorded by the wearable device (1000). The user's biometric data may be generated and recorded by the wearable device (1000), but is not limited thereto. For example, if the electronic device (2000) includes a biometric sensor, the electronic device (2000) can generate the user's biometric data using the biometric sensor. According to one embodiment, the electronic device (2000) can store biometric data directly input by the user.

[0053] Referring to FIG. 1, information about a user's stress can be displayed on an electronic device (2000) through a graphical user interface (GUI) (100). The GUI (100) may be a GUI (100) of a stress management application. According to one embodiment, when a wearable device (1000) includes a display, information about a user's stress can also be displayed on the wearable device (1000) through the GUI (100).

[0054] Information related to the user's stress may be expressed through the GUI (100), but is not limited thereto. For example, information regarding the user's stress may be provided to the user through voice.

[0055] Information related to a user's stress may include the user's stress level (120). For example, as illustrated in FIG. 1, the user's stress level (120) may be represented as a line graph. Through the stress level (120) represented as a line graph, the user may recognize the daily fluctuations of his or her stress level (120) at a glance. According to one embodiment, information related to the user's stress may include the user's stress level (121) at a specific point in time. For example, as illustrated in FIG. 1, the user's stress level (121) at a specific point in time, for example, today's stress level, may be represented as a semicircular gauge graph and a numerical value, and the difference in value from yesterday and the current value status (e.g., "Too High") may be represented. Data points of the line graph may be represented differently depending on the stress level. For example, as illustrated in FIG. 1, data points for days with relatively high stress levels may be represented in black, data points for days with relatively low stress levels may be represented in white, and data points for days with stress levels in between may be represented in gray. According to one embodiment, a user's stress level (120) may be represented as a bar graph (620, 622, and 624 of FIG. 6). Through the stress level represented as a bar graph, the user can recognize at a glance the factors that constitute his or her stress or the categories that distinguish his or her stress.

[0056] According to one embodiment, the stress cause (110) may be classified by stress type. For example, the stress cause (110) may be classified into a first stress type (111), a second stress type (113), and a third stress type (not shown). The first, second, and third stress types may be, but are not limited to, a physical stress type, a mental stress type, and an environmental stress type, respectively. Referring to FIG. 1, when sufficient data to estimate the stress cause is applied to the artificial intelligence model, the stress causes (a1 stress, a2 stress, and b1 stress) classified into each stress type may be displayed on the GUI (100). Referring to FIG. 1, the stress level due to the stress cause (a1 stress, a2 stress, or b1 stress) may be expressed as a bar gauge graph and a state of the level (e.g., “Low”). The bar gauge graph can be expressed differently depending on the stress level, and for example, as shown in Figure 1, the bar gauge graph of a stress cause with a relatively high stress level can be expressed in black, the bar gauge graph of a stress cause with a relatively low stress level can be expressed in white, and the bar gauge graph of a stress cause with a stress level in between can be expressed in gray.

[0057] According to one embodiment, the electronic device may include an interface element (140) that switches between content, pages, or screens displayed in the GUI (100). For example, the interface element (140) may be a bar (140) listing objects such as tabs, icons, menus, or buttons. A stress management application may present information about a user's stress in various formats or perspectives, and the bar (140) may include objects that switch between the respective formats. For example, information about stress may be presented in a 'summary' format as illustrated in FIG. 1, a 'detailed' format as illustrated in FIG. 6, or a 'guide' format as illustrated in FIG. 8. Referring to FIG. 1, the bar (140) may include three objects corresponding to each format, and an object corresponding to a section for managing the user's profile or customization.

[0058] In one embodiment, the stressor may be represented as an object. The object may include text describing the stressor. The object may be implemented to have a circular shape, but is not limited thereto. In one embodiment, the object may be represented as a two-dimensional shape, for example, the object may be a two-dimensional shape such as a triangle or a square. In one embodiment, the object may be represented as a three-dimensional shape, for example, the object may be a sphere or a three-dimensional shape such as a cube.

[0059] In one embodiment, objects representing stressors may be represented with a size proportional to the level of stress they cause. For example, an object corresponding to the stressor that contributes the most to a user's stress may be larger than objects corresponding to other stressors. Thus, the user can readily grasp the contribution of each stressor to their stress level.

[0060] In one embodiment, stressors can be represented differently depending on the stress type. For example, objects representing stressors can be displayed in different colors depending on the stress type. Therefore, users can easily identify the stress type of a stressor at a glance.

[0061] According to one embodiment, the electronic device can provide a guide (130) corresponding to a stress cause and / or stress level. If the stress cause that contributes the most to the user's stress is 'work', the guide (130) can be a guide corresponding to 'work', such as, for example, "Prioritize your work." The electronic device (2000) according to one embodiment can be, but is not limited to, a smartphone, a tablet PC (personal computer), a PC, a smart TV, a mobile phone, a PDA (personal digital assistant), a laptop, a media player, a micro server, a GPS (global positioning system) device, an e-book reader, a digital broadcasting terminal, a navigation device, a kiosk, an MP3 player, a digital camera, home appliances, and other mobile or non-mobile computing devices. The electronic device (2000) can include any type of device that can obtain data from the wearable device (1000) and display information about the user's stress.

[0062] A wearable device (1000) according to one embodiment is illustrated as a smart ring in FIG. 1, but is not limited thereto. The wearable device (1000) is a device that can be worn by a user, and may be a smart watch, smart glasses, a smart hat, smart clothing, smart shoes, smart socks, a smart mask, a smart eye mask, or a smart band. The wearable device (1000) has a communication function and a data processing function, and can communicate with an electronic device (2000). The wearable device (1000) may include any type of device that can be worn by a user and detect a user's bio-signal.

[0063] FIG. 2 is a flowchart of a method for an electronic device to output a stress source according to one embodiment.

[0064] In the following examples, the operations may be performed sequentially, but are not necessarily sequential. For example, the order of the operations may be changed, and at least two operations may be performed in parallel.

[0065] According to one embodiment, operations 210 to 260 may be understood to be performed in a processor (not shown) of an electronic device (e.g., electronic device (2000) of FIG. 1).

[0066] According to one embodiment, in operation 210, the electronic device may acquire first logging data and first biometric data. The electronic device may record and acquire the first logging data about the user based on interactions between the user and the electronic device during a first period of time. The first period may be any period of time, but is not limited thereto. For example, the first period may be a preset period of time, and may be set to a period of time required to sufficiently collect user data to display information about the user's stress level. The first period of time may be 12 hours, one day, or one week.

[0067] According to one embodiment, the first logging data may be data generated or recorded by the electronic device related to the daily activities and behaviors of a user using the electronic device. According to one embodiment, the first logging data may include first user status data generated based on the first logging data. The first user status data may indicate the status of the user. According to one embodiment, the first user status data may include, but is not limited to, the user's current status, activity status, activity level, health status, psychological status, sleep status, lifestyle habits, behavioral patterns, and surrounding environmental status during a first period.

[0068] In one embodiment, the first biometric data may be recorded by a wearable device worn by the user during the first period. The first biometric data may be detected and recorded by a biometric signal sensor of the wearable device worn by the user during the first period.

[0069] In one embodiment, an electronic device can communicate with a wearable device and obtain the user's first biometric data from the wearable device. In one embodiment, the electronic device can obtain the user's first biometric data from multiple wearable devices. In one embodiment, the electronic device can obtain the first biometric data from a server that stores the user's biometric data.

[0070] According to one embodiment, in operation 220, the electronic device may obtain first information including a first stress cause. The electronic device may obtain first information including a first stress cause related to the user's stress by applying a first input including first logging data and first biometric data to an artificial intelligence model. A method of generating stress-related information by applying the input to the artificial intelligence model will be further described with reference to FIG. 3.

[0071] According to one embodiment, the first input may further include first acoustic data, first motion data, and first environmental data acquired during a first period. According to one embodiment, the first logging data may include first user status data. According to one embodiment, the first acoustic data may include first voice data.

[0072] According to one embodiment, based on the user's biometric data, the point in time when the user experiences stress, the duration of the stress, and the magnitude of the stress can be determined. For example, the point in time when the user experiences stress, the duration of the stress, and the magnitude of the stress can be determined based on the point in time and the extent of the fluctuations in heart rate (HR) data, resting heart rate (RHR) data, and heart rate variability (HRV) data included in the biometric data outside a threshold range.

[0073] In one embodiment, a user's context can be determined when the user is stressed based on the user's biometric data and logging data. For example, a user may be stressed primarily when talking to others using a phone application, and based on the user's biometric data and logging data, it can be estimated that the user is stressed when using the phone application. An AI model can analyze inputs including the user's biometric data and logging data to recognize the user's context when the user is stressed. The user's context can include the occurrence of a stressor. In one embodiment, a user's context can be determined when the user is stressed based on the user's biometric data, logging data, and motion data. In one embodiment, a user's context can be determined when the user is stressed based on the user's biometric data, logging data, and motion data. In one embodiment, a user's context can be determined when the user is stressed based on the user's biometric data, logging data, motion data, and audio data. In one embodiment, a user's context can be determined when the user is stressed based on the user's biometric data, logging data, motion data, audio data, and environmental data. In one embodiment, the logging data can include user status data. According to one embodiment, the acoustic data may include voice data.

[0074] In one embodiment, an AI model can be trained to integrate and analyze received input data to output information about the user's stress level. The stress information may include, but is not limited to, stress causes related to the user's stress level. The stress information may further include at least one of the following: the type of stressor, the user's stress level, and guidance corresponding to the user's stress cause and / or stress level.

[0075] In one embodiment, by applying a first input including a user's first biometric data and first logging data to an artificial intelligence model, the artificial intelligence model can analyze the first input and output first information including a first stress cause related to the user's stress. For example, a user may feel stressed when communicating with others using a phone application. When the user is stressed, the user's situation can be estimated by the artificial intelligence model, and the first information output by the artificial intelligence model may include 'interpersonal conflict' as the first stress cause. In one embodiment, the artificial intelligence model can analyze a first input including first biometric data and first logging data acquired during a first period and output first information including a plurality of first stress causes. For example, a user may feel stressed due to work, and this can be estimated from a work-related schedule entered by the user into a calendar application and biometric data measured during a time period corresponding to the schedule. The first information output by the artificial intelligence model may further include 'work' as the first stress cause.

[0076] In one embodiment, the AI ​​model may analyze the first input and classify the first stressor into stress categories. The stress categories may include positive stress categories and negative stress categories. The AI ​​model may analyze the first input and identify "work" as the first stressor related to the user's stress, and identify the stress category of "work." The identified stress category of "work" may be a negative stress category.

[0077] In one embodiment, the AI ​​model may analyze the first input and classify the first stressor by stress type. The stress types may include, but are not limited to, physical stress, mental stress, and environmental stress, as criteria for classifying stressors. The AI ​​model may analyze the first input and identify "work" as the first stressor related to the user's stress, and classify "work" as a physical stress type.

[0078] In one embodiment, the AI ​​model can analyze the first input to classify the stress category of the first stressor. The stress type, as a criterion for classifying the stressor, may include, but is not limited to, physical stress type, mental stress type, and environmental stress type. The AI ​​model can analyze the first input to identify "work" as the first stressor related to the user's stress and classify "work" as a physical stress type.

[0079] According to one embodiment, the first information related to the user's stress, generated by the artificial intelligence model, may include at least one of a first stress cause causing the user's stress, a stress type of the first stress cause, a stress category of the first stress cause, and a stress level of the first stress cause. According to one embodiment, the first information may further include a query for describing the first stress cause. According to one embodiment, the first information may further include a first guide corresponding to the first stress cause. The guide corresponding to the stress cause will be further described with reference to FIG. 8.

[0080] In one embodiment, first information, including a first stress cause related to the user's stress, may be displayed on an electronic device via a GUI. The GUI may be a GUI of a stress management application. In one embodiment, if the wearable device includes a display, information regarding the user's stress may also be displayed on the wearable device via the GUI. The first information may be expressed via the GUI, but is not limited thereto. For example, the first information may be provided to the user via voice.

[0081] In one embodiment, at operation 230, the electronic device may provide a query related to the first stressor. In one embodiment, the query may be provided to identify a sub-stressor that further describes the first stressor. For example, if 'interpersonal conflict' is included in the first information as the first stressor, a query may be generated to specify 'interpersonal conflict'. In one embodiment, the query may be generated by an artificial intelligence model. For example, the query may be included in the first information generated by the artificial intelligence model. The query may be generated by the artificial intelligence model separately from the first information. A method of generating a query by the artificial intelligence model will be further described with reference to FIG. 4.

[0082] In one embodiment, the query may be displayed on the electronic device in text format, but is not limited thereto. For example, the query may be played back on the electronic device in audio format. In one embodiment, the electronic device may provide the query to the user via a notification.

[0083] In one embodiment, the query may include subordinate stressors subordinate to the first stressor. For example, if the first information includes "interpersonal conflict" as the first stressor, the query may include subordinate stressors that can explain "interpersonal conflict." The method of generating a query using an artificial intelligence model will be further described with reference to FIG. 4.

[0084] According to one embodiment, at operation 240, the electronic device may receive a user's response to the query.

[0085] According to one embodiment, the user's response may be an input for selecting one of a plurality of sub-stressors included in the query, but is not limited thereto. The electronic device may receive the user's voice response or a text response. To process the user's voice response, the electronic device may convert the voice response into text using automatic speech recognition (ASR) technology and / or speech-to-text (STT) technology, or using an artificial intelligence model trained to convert voice into text. The electronic device may input text data into an artificial intelligence model trained for natural language interpretation to interpret the user's text response or the text converted from the voice response, thereby obtaining an output value representing the meaning of the text data. The artificial intelligence model for natural language interpretation may include, but is not limited to, a natural language understanding (NLU) model and a large language model (LLM) model, for example.

[0086] In one embodiment, the user's response may be applied to an AI model. The user's response may be applied to the AI ​​model before the second logging data and second biometric data acquired during a second period following the first period are applied to the AI ​​model. The method of applying the user's response to the AI ​​model will be further described with reference to Figure 4.

[0087] According to one embodiment, in operation 250, the electronic device may acquire second logging data and second biometric data. The electronic device may record and acquire the second logging data about the user based on interactions between the user and the electronic device during a second period. The second period may be a period after the first period. The second period may be any period, but is not limited thereto. For example, the second period may be a preset period and may be set to a period of time sufficient to collect sufficient data to specify information about the user's stress level.

[0088] In one embodiment, the first period and the second period may have substantially the same length. For example, the first period and the second period may be, but are not limited to, 12 hours, one day, or one week.

[0089] According to one embodiment, the second logging data may be data generated or recorded by the electronic device related to the daily activities and behaviors of the user using the electronic device. According to one embodiment, the second logging data may include second user status data generated based on the second logging data. The second user status data may indicate the status of the user. According to one embodiment, the second user status data may include, but is not limited to, the user's current status, activity status, activity level, health status, psychological status, sleep status, lifestyle habits, behavioral patterns, and surrounding environmental status during the second period.

[0090] In one embodiment, the second biometric data may be recorded by a wearable device worn by the user during the second period. The second biometric data may be detected and recorded by a biometric signal sensor of the wearable device worn by the user during the second period.

[0091] In one embodiment, the electronic device can communicate with a wearable device and obtain the user's second biometric data from the wearable device. In one embodiment, the electronic device can obtain the user's second biometric data from multiple wearable devices. In one embodiment, the electronic device can obtain the second biometric data from a server that stores the user's biometric data.

[0092] In one embodiment, at operation 260, the electronic device may obtain second information including a second stress cause. The electronic device may obtain second information including a second stress cause related to the user's stress by applying the user's response to the second input and query including the second logging data and the second biometric data to an artificial intelligence model.

[0093] In one embodiment, the second information, including the second stressor, may be displayed on the electronic device via a GUI. The GUI may be a GUI of a stress management application. In one embodiment, if the wearable device includes a display, information about the user's stress may be displayed on the wearable device via the GUI. The second information may be expressed via the GUI, but is not limited thereto. For example, the second information may be provided to the user via voice.

[0094] In one embodiment, the user's response may be applied to the AI ​​model before the second input, which includes the second logging data and the second biometric data, is applied to the AI ​​model. If the user's response is not applied to the AI ​​model, the AI ​​model may simply output the same information as before, for example, the first information including the first stressor, if it recognizes a situation similar to the situation involving the occurrence of the first stressor. On the other hand, if the user's response is applied to the AI ​​model, the AI ​​model may output the second information including the second stressor, which is more specific than the first stressor, if it recognizes a situation similar to the situation involving the occurrence of the first stressor. Therefore, the user can identify a more specific stressor causing their stress, thereby effectively managing their stress.

[0095] In one embodiment, when a query includes a plurality of sub-stress causes dependent on a first stress cause, and a user's response of selecting one of the plurality of sub-stress causes is applied to an artificial intelligence model, the selected sub-stress cause may be included in the second information as a second stress cause.

[0096] In one embodiment, the second stressor may elaborate on the first stressor. Because people have different sensitivities to stress and the stressors that cause stress vary, it can be difficult for users to recognize when they are stressed, and even when they believe they are stressed, they may not actually be. Furthermore, users who believe they are stressed by work may have difficulty recognizing which specific aspects of their work are causing them stress. In one embodiment, by informing the user of the second stressor that elaborates on the first stressor, the user can identify when they are stressed and, furthermore, the specific causes of their stress without the help of a medical professional. In one embodiment, as data accumulates, the stressor becomes more specific, and specific guidance in response to the specified stressor can be provided to the user, thereby providing the user with effective stress relief methods that take into account the user's individual environment and lifestyle habits. The method for specifying the stressor will be further described with reference to FIG. 6.

[0097] In one embodiment, a stressor may have a stress category. For example, the stress category of a stressor may be a positive stress category or a negative stress category. The classification of stressors based on stress categories will be further explained with reference to Figure 7.

[0098] In one embodiment, the second information may further include a second stressor causing the user's stress and the level of that stress. In one embodiment, the second information may further include a second guide corresponding to the second stressor, and the guide corresponding to the stressor will be further described with reference to FIG. 8.

[0099] In one embodiment, the AI ​​model can learn from other data, in addition to biometric data and logging data. For example, the AI ​​model can simultaneously learn motion data, acoustic data, environmental data, voice data, and user status data, thereby outputting information about the user's stress level. An AI model utilizing various data will be further described with reference to Figure 9.

[0100] In one embodiment, an electronic device may acquire a user's biometric data from multiple wearable devices. Acquiring the user's biometric data from multiple wearable devices will be further described with reference to FIG. 10.

[0101] In one embodiment, the AI ​​model may be deployed and utilized in an electronic device, but is not limited thereto. For example, the AI ​​model may be deployed on a server, the electronic device may transmit inputs including biometric data and logging data to the server, the AI ​​model deployed on the server may analyze the inputs and output stress-related information, and the electronic device may receive stress-related information from the server. To secure the user's sensitive biometric information, at least some of the data communicated between the server and the electronic device may be encrypted. For example, the electronic device may encrypt the user's biometric data and transmit it to the server.

[0102] In one embodiment, the AI ​​model may be distributed and deployed across electronic devices and servers. For example, the AI ​​model may consist of multiple layers, with an input layer for extracting features from inputs including biometric data and logging data being deployed on the electronic device, and the remaining layers being deployed on the server.

[0103] In one embodiment, the AI ​​model may be distributed and deployed across electronic devices and wearable devices. For example, the AI ​​model may include multiple parallel input layers, each of which is differentiated by modality. An input layer for extracting features from data collected from a wearable device may be deployed on the wearable device, and an input layer for extracting features from data collected from the electronic device may be deployed on the electronic device. The electronic device may receive feature data extracted by the wearable device from the wearable device.

[0104] FIG. 3 is a diagram illustrating an example of an artificial intelligence model generating output based on input according to one embodiment.

[0105] According to one embodiment, the artificial intelligence model (320) may be an artificial intelligence model (320) pre-trained based on data from multiple users.

[0106] In one embodiment, the AI ​​model (320) can simultaneously learn data of different modalities. For example, the AI ​​model (320) can generate appropriate representations for each modality and learn a common representation that can integrate data of different modalities.

[0107] In one embodiment, the artificial intelligence model (320) may be trained to integrate and analyze received input data to generate information about the user's stress as output (322). The information about stress may include, but is not limited to, stress causes related to the user's stress. The information about stress may further include a query detailing the user's stress causes. The information about stress may further include the user's stress level. The information about stress may further include guidance corresponding to the user's stress causes.

[0108] According to one embodiment, the data applied to the artificial intelligence model (320) may include, but is not limited to, biometric data (312) and logging data (314). According to one embodiment, the input data applied to the artificial intelligence model (320) may further include motion data. The motion data may be recorded by, but is not limited to, a wearable device worn by the user, and may be recorded by an electronic device carried by the user. The electronic device may communicate with the wearable device to obtain motion data recorded by the wearable device.

[0109] According to one embodiment, the input data applied to the artificial intelligence model (320) may further include acoustic data. The acoustic data may be recorded by a wearable device worn by the user, but is not limited thereto, and may be recorded by an electronic device carried by the user. The electronic device may communicate with the wearable device to obtain the acoustic data recorded by the wearable device.

[0110] According to one embodiment, the input data applied to the artificial intelligence model (320) may further include environmental data. The environmental data relates to the user's surroundings and may include, for example, information on weather, temperature, humidity, air quality, fine dust concentration, wind speed, wind direction, precipitation probability, precipitation amount, and spatial congestion. The electronic device may receive environmental data from an external source, such as a provider providing the data, such as a portal site or the Korea Meteorological Administration.

[0111] According to one embodiment, the input data applied to the artificial intelligence model (320) may further include voice data. The voice data may be recorded by a wearable device worn by the user, but is not limited thereto, and may be recorded by an electronic device carried by the user. The electronic device may communicate with the wearable device to obtain the voice data recorded by the wearable device. The voice data and audio data may be recorded through a microphone of the electronic device or wearable device, and the audio data may include voice data.

[0112] According to one embodiment, the data applied to the artificial intelligence model (320) may further include user status data. The status data may be generated at least partially based on the user's logging data (314) and may represent the user's status. For example, the user status data may include, but is not limited to, the user's current status, activity status, activity level, health status, psychological status, sleep status, lifestyle habits, behavioral patterns, and surrounding environmental conditions.

[0113] According to one embodiment, the AI ​​model (320) may be a multimodal model that learns and processes relationships between data of various modalities. The multimodal model may learn relationships between data of different modalities to generate information related to the user's stress. According to one embodiment, the AI ​​model (320) may include multiple layers. For example, the AI ​​model (320) may include, but is not limited to, an input layer, an encoder layer, and an output layer.

[0114] According to one embodiment, the input layer may include a feature extraction layer. The feature extraction layer may extract features from input data received by the feature extraction layer. The extracted features may be expressed as multidimensional vectors. The feature extraction layer may extract features from preprocessed data or features from raw data. The features extracted from the feature extraction layer may be passed on to the next layer, for example, an encoder layer.

[0115] According to one embodiment, the input layer may include a plurality of parallel input layers that are distinguished according to modality. For example, input data applied to the artificial intelligence model (320) may include biometric data (312), logging data (314), motion data, acoustic data, environmental data, voice data, and user status data, and the input layer of the artificial intelligence model (320) may include an input layer for biometric data (312), an input layer for logging data (314), an input layer for motion data, an input layer for acoustic data, an input layer for environmental data, an input layer for voice data, and an input layer for user status data. Each input layer may extract features from each input data. According to one embodiment, each input layer may be disposed in an electronic device, but is not limited thereto. For example, the input layers for biometric data (312), motion data, and acoustic data may be disposed in a wearable device, and the input layers for logging data (314), environmental data, and user status data may be disposed in an electronic device.

[0116] According to one embodiment, the AI ​​model (320) may further include a positional encoding layer. The positional encoding layer may be located between the input layer and the encoder layer, belong to the input layer, or belong to the encoder layer. The positional encoding layer may provide information about time or order to the extracted features.

[0117] According to one embodiment, the encoder layer may receive each feature extracted from each input layer, perform fusion considering the importance, weight, or correlation of each data, and generate a fused feature as an output.

[0118] In one embodiment, the encoder layer may be implemented as a transformer layer. The transformer may consist of an encoder, or an encoder and a decoder.

[0119] In one embodiment, the output layer may generate the final output of the artificial intelligence model (320). The output layer may output information related to the user's stress based on integrated multimodal data. The output layer may be implemented as a dense layer.

[0120] In one embodiment, the output layer receives data generated from the encoder layer and generates information about the user's stress.

[0121] According to one embodiment, the encoder layer may receive and analyze each feature extracted from each input data through each input layer, and output information related to the user's stress.

[0122] According to one embodiment, the artificial intelligence model (320) may be trained to integrate and analyze received input data to generate information about the user's stress as output. The information about stress may include, but is not limited to, stress causes related to the user's stress. According to one embodiment, the artificial intelligence model (320) may analyze the received input to determine whether the stress cause falls into the positive stress category or the negative stress category. According to one embodiment, the artificial intelligence model (320) may analyze the received input to identify the stress type of the stress cause, and the information about stress may include the stress type of the identified stress cause. The stress type may include, but is not limited to, physical stress type, mental stress type, and environmental stress type as criteria for classifying stress causes. The information about stress may further include a query for describing the user's stress cause in detail. The information about stress may further include the user's stress level. The information about stress may further include a guide corresponding to the user's stress cause. Referring to FIG. 3, the artificial intelligence model (320) can receive the user's biometric data (312) and logging data (314) as input and generate output. The output can include information related to the user's stress.

[0123] FIG. 4 is a diagram showing an example in which an artificial intelligence model according to one embodiment reflects a user's response to a query.

[0124] In one embodiment, the artificial intelligence model (420) may be trained to integrate and analyze received input data to generate information about the user's stress as output (422). The information about stress may include, but is not limited to, stress causes related to the user's stress. The information about stress may further include a query (424) generated to elaborate on the output stress causes. In one embodiment, the artificial intelligence model (420) may generate the query (424) separately from the information about stress.

[0125] In one embodiment, the AI ​​model (420) can identify stressors related to a user's stress and generate a query (424) related to the stressor. The query (424) can be generated together with information about the user's stress or generated separately. The query (424) can be generated to further identify sub-stressors that describe the identified stressor.

[0126] In one embodiment, a query (424) may be associated with the identified stressor. For example, if the identified stressor is "interpersonal conflict," a query (424) such as "Do you have conflict with others?" may be generated. If the user responds "yes" to a closed question such as "Do you have conflict with others?", "interpersonal conflict" may be identified as the stressor, and a query may be generated to identify a stressor that further describes the identified stressor. If the user responds "no," another stressor may be identified, and a query related to the identified stressor may be generated.

[0127] In one embodiment, the query (424) may include words highly correlated with the identified stressor. For example, if the identified stressor is "interpersonal conflict," the query (424) may include at least one word highly correlated with the term "interpersonal conflict," such as "family conflict," "work," "friend," or "lover." Words highly correlated with the stressor may be sub-stressors. Words highly correlated with the stressor may be associated with sub-stressors.

[0128] In one embodiment, the query (424) may include sub-stressors that are dependent on the identified stressor. For example, if the output (422) includes 'interpersonal conflict' as a stressor, the query (424) may include sub-stressors that can describe 'interpersonal conflict'. In one embodiment, the sub-stressor may be at least one of the activities that may be a stressor in the user's daily life, and a sub-stressor that has a high correlation with the identified stressor may be selected and provided as the query (424).

[0129] According to one embodiment, the user's response (442) may be an input for selecting one of a plurality of sub-stressors included in the query, but is not limited thereto. The electronic device may receive the user's voice response (442) or a text response (442). To process the user's voice response (442), the electronic device may use automatic speech recognition (ASR) technology and / or speech-to-text (STT) technology, or may convert the voice response (442) into text using an artificial intelligence model (420) trained to convert voice into text. In order to interpret the user's text response (442) or the text converted from the voice response (442), the electronic device may input text data into an artificial intelligence model (420) trained for natural language interpretation, thereby obtaining an output value representing the meaning of the text data. The artificial intelligence model (420) for natural language interpretation may include, but is not limited to, a natural language understanding (NLU) model and a large language model (LLM) model, for example.

[0130] In one embodiment, an output value representing the meaning of a user's response (442) may be obtained, and the output value may be applied to an adaptation model (440). The adaptation model (440) may receive the user's response (442) or the output value representing the meaning as input.

[0131] According to one embodiment, the adaptive model (440) can adjust weights through reinforcement learning, and when a user's response (442) is received by the adaptive model (440), the adaptive model (440) can output weight information. The output weight information can be linked to the artificial intelligence model (420), thereby allowing the user's response (442) to be reflected in the artificial intelligence model (420).

[0132] FIG. 5 is a diagram illustrating an example of an electronic device providing a query related to a stress source according to one embodiment.

[0133] In one embodiment, the query may be displayed on the electronic device in text format, but is not limited thereto. For example, the query may be played back on the electronic device in audio format. In one embodiment, the electronic device may provide the query to the user via a notification.

[0134] Referring to FIG. 5, a GUI (500) for providing a query to a user may be displayed via an electronic device. The GUI (500) may include a sentence (520) related to a stressor. For example, a sentence (520) such as "Please select the one related to your recent activity" may be displayed. The sentence (520) may directly refer to a stressor. For example, a sentence (520) such as "You are experiencing interpersonal conflict. Please select the one related to your recent activity" may be displayed.

[0135] According to one embodiment, the GUI (500) may display information (510) including multiple sub-stressors dependent on a stressor. For example, if the stressor is 'interpersonal conflict,' the sub-stressors dependent on the stressor may be 'coworker (A),' 'friend (B),' and 'family (C).' According to one embodiment, the sub-stressors may be pre-generated as terms representing activities that may be stressors in the user's daily life.

[0136] According to one embodiment, the GUI (500) may include buttons (530) that request a user's confirmation or cancellation. FIG. 6 is a diagram illustrating an example of specifying a stress cause according to one embodiment.

[0137] Referring to FIG. 6, information regarding a user's stress may be displayed via a GUI (600). Information regarding the user's stress may include the user's stress level (620, 622, 624). For example, as illustrated in FIG. 6, the user's stress level (620, 622, 624) may be represented as a bar graph, and may be represented as a sum of stress levels according to each stress cause. In one embodiment, the stress level may be represented by stress type. In one embodiment, the stress level may be represented by stress cause.

[0138] According to one embodiment, the bar graph may be expressed as being divided into two or more parts so that the user can recognize at a glance the elements that constitute his or her stress or the categories that distinguish his or her stress, which will be further explained with reference to FIG. 7.

[0139] According to one embodiment, information related to a user's stress may include information (610, 612, 614) on a stressor causing the user's stress. The stressor may be output by an artificial intelligence model based on data acquired over an arbitrary or predetermined period of time. For example, referring to FIG. 6, information (610) on a stressor as of 2 / 27 may be information generated by applying data acquired up to 2 / 27 as input to an artificial intelligence model. Information (612) on a stressor as of 2 / 28 may be information generated by applying data acquired up to 2 / 28 as input to an artificial intelligence model. Information (614) on a stressor as of 2 / 29 may be information generated by applying data acquired up to 2 / 29 as input to an artificial intelligence model. Information (610, 612, 614) may include multiple stressors. The multiple stressors may be classified by stress type (Stress A, Stress B, Stress C). For example, referring to FIG. 6, multiple stress causes can be classified into, but are not limited to, 'physical stress type' (Stress A), 'mental stress type' (Stress B), and 'environmental stress type' (Stress C).

[0140] In one embodiment, the stress-related information initially provided to the user on the electronic device may include the stress level and not the stress cause. For example, if the AI ​​model is not equipped with sufficient data to estimate the stress cause, the information generated by the AI ​​model may include the stress level and not the stress cause. Referring to FIG. 6, the stress cause information (610) dated February 27 may not include stress causes classified into stress types (Stress A, Stress B, and Stress C) because sufficient data has not been accumulated to estimate the stress cause.

[0141] Referring to FIG. 6, when sufficient data to estimate the cause of stress is applied to the artificial intelligence model, information (612) on the cause of stress as of 2 / 28 may include stress causes (a1 stress, b1 stress, c1 stress) classified by stress type (A stress, B stress, and C stress). For example, information (612) may include 'work stress' (a1 stress) classified as 'physical stress type' (A stress), 'interpersonal conflict stress' (b1) classified as 'mental stress type' (B stress), and 'noise stress' (c1) classified as 'environmental stress type' (C stress).

[0142] In one embodiment, when sufficient data is applied to an AI model to estimate sub-stress causes that describe the cause of stress, information generated by the AI ​​model may include sub-stress causes that describe the cause of stress. Referring to FIG. 6, when sufficient data is applied to an AI model to estimate sub-stress causes that describe 'work stress' (a1 stress), information may be generated by the AI ​​model that includes sub-stress causes such as 'long working hours' (a11 stress) and 'frequent business trips' (a12 stress) that describe 'work stress' (a1 stress).

[0143] In one embodiment, if sufficient data is applied to the AI ​​model to estimate the next sub-stress cause that describes the estimated sub-stress cause, the information generated by the AI ​​model may include the next sub-stress cause that describes the sub-stress cause. For example, if sufficient data is applied to the AI ​​model to estimate the next sub-stress cause that describes "long working hours," the AI ​​model may generate information that includes the next sub-stress cause, such as "overtime," that describes "long working hours."

[0144] In one embodiment, the stressor, the sub-stressor, and the next sub-stressor may be referred to as a first level stressor, a second level stressor, and a third level stressor, respectively.

[0145] In one embodiment, stressors such as work, study, or commuting may be categorized as physical stress types. In one embodiment, sub-stressors may be more specific than super-stressors. For example, a work stressor may be associated with sub-stressors that embody the stressor, such as excessive workload, excessive work immersion, the work environment, or frequent business trips. A study stressor may be associated with sub-stressors that embody the stressor, such as excessive academic workload, lack of concentration, anxiety about exams, uncertainty about career paths, or the study environment. A commuting stressor may be associated with sub-stressors that embody the stressor, such as length of commuting time, heavy traffic congestion, inconvenient transportation, traffic accidents, or delays.

[0146] In one embodiment, stressors such as allergies due to weather, noise, air quality, insufficient natural light, crowded environments (space crowding), or excessive electromagnetic field exposure can be classified as environmental stress types. In one embodiment, sub-stressors can be more specific than super-stressors. A weather stressor can be associated with sub-stressors that embody the stressor, such as temperature, humidity, snow, or rain. A noise stressor can be associated with sub-stressors that embody the stressor, such as traffic noise, industrial noise, neighbor noise, natural noise, social noise, or electronic noise. An allergy stressor due to air quality can be associated with sub-stressors that embody the stressor, such as pollen allergies or fine dust allergies. A stressor due to insufficient natural light can be associated with sub-stressors that embody the stressor, such as seasonal affective disorder or vitamin D deficiency. Overcrowding can be linked to sub-stressors that embody the stressor itself, such as urban overcrowding, traffic congestion, overcrowded work environments, or overcrowded public spaces. Excessive electromagnetic field exposure can be linked to sub-stressors that embody the stressor itself, such as prolonged smartphone use or computer use.

[0147] In one embodiment, stressors such as adapting to a new environment, interpersonal conflict, or anxious psychological state can be classified as psychological stress types. Stressors due to adapting to a new environment can be associated with sub-stressors such as moving, changing jobs, retirement, or breakups that specify the stressor. Interpersonal conflict stressors can be associated with sub-stressors such as conflicts with family members, coworkers, bosses, friends, romantic partners, or domestic conflicts. Anxious psychological state stressors can be associated with sub-stressors such as generalized anxiety disorder (GAD), panic disorder, social anxiety disorder, obsessive compulsive disorder (OCD), post-traumatic stress disorder (PTSD), specific phobias, health anxiety disorder, or separation anxiety disorder.

[0148] FIG. 7 is a diagram illustrating an example in which an electronic device according to one embodiment outputs a stress cause according to a stress category.

[0149] In one embodiment, stress can be divided into positive stress and negative stress. Positive stress can be eustress, and negative stress can be distress.

[0150] Positive stress is a pleasant tension, such as the thrill or excitement that a person feels while doing an activity they enjoy. It has beneficial effects, such as increasing concentration by motivating and encouraging a person's desire for achievement.

[0151] Referring to FIG. 7, information regarding a user's stress may be displayed via a GUI (700). Information regarding the user's stress may include the user's stress level (720). For example, as illustrated in FIG. 7, the user's stress level (720) may be represented as a bar graph and as a sum of stress levels for each stress cause.

[0152] According to one embodiment, the bar graph may be displayed as divided into two or more sections so that the user can recognize at a glance the factors that constitute his or her stress or the categories that classify his or her stress. For example, referring to FIG. 7, in the stress level (720) of the bar graph, the upper section represents the proportion of stressors belonging to the negative stress category that contribute to the overall stress, and the lower section represents the proportion of stressors belonging to the positive stress category that contribute to the overall stress.

[0153] According to one embodiment, information related to a user's stress may include information (710) on a stressor causing the user's stress. The stressor may be output by an artificial intelligence model based on data acquired over an arbitrary or predetermined period of time. For example, referring to FIG. 7, information (710) on a stressor as of 2 / 29 may be information generated by applying data acquired up to 2 / 29 as input to an artificial intelligence model. The information (710) may include multiple stressors. The stressors may be classified by stress category. Referring to FIG. 7, stressors may be classified into eustress and distress. Referring to FIG. 7, stressors belonging to the distress category may be classified by stress type (A stress and B stress). For example, referring to Figure 7, the stressors can be classified into, but are not limited to, 'physical stress type' (A stress) and 'mental stress type' (B stress), and can be further classified into 'environmental stress type' (C stress).

[0154] FIG. 8 is a diagram illustrating an example of an electronic device providing guidance in response to a stress source according to one embodiment.

[0155] According to one embodiment, information related to user's stress generated by the artificial intelligence model may include a stressor causing the user's stress, a stress category of the stressor, a stress type of the stressor, a stress level of the stressor, and a guide corresponding to the stressor and / or the stress level.

[0156] Referring to FIG. 8, information about a user's stress may be displayed through a GUI (800). The GUI (800) may include information (850) and comments (860) about stress causes. The information (850) may include stress causes (A stress, B stress, C stress, and eustress) classified into positive stress categories and negative stress categories. According to one embodiment, the stress level of the stress cause may be expressed in text. For example, the information (850) may include the stress level (high, medium, low) of the stress cause. The information (850) may include guides (a1, a2, a3, b1, b2, c1) corresponding to the stress cause. The guides (a1, a2, a3, b1, b2, c1) corresponding to the stress cause may include a method of coping with the corresponding stress cause, a method of reducing stress caused by the corresponding stress cause, and benefits of the corresponding eustress. Comment (860) may be a summary of the guide to responding to stressors, or may be a guide to responding to the stressor with the highest stress level.

[0157] In one embodiment, a guide responding to a stressor may include a guide suggesting the use of a specific application or device to effectively monitor the stressor. For example, if a stressor classified as an environmental stressor is suspected to be causing the user's stress, the guide may suggest the use of an application or device capable of monitoring the user's surroundings. For example, a guide may be displayed suggesting connecting an IoT device to a home management application to measure indoor temperature, humidity, and noise. For example, if a stressor classified as a mental stressor is suspected to be causing the user's stress, the guide may suggest the use of an application or device capable of accurately and continuously monitoring the user to more specifically estimate the user's mental stressor. For example, a guide may be displayed suggesting the use of a smart ring capable of monitoring sleep by being worn for extended periods on a single charge.

[0158] FIG. 9 is a diagram showing an example of an artificial intelligence model generating output using various data according to one embodiment.

[0159] In one embodiment, the artificial intelligence model may receive and analyze inputs including biometric data (912), logging data (914), motion data (911), acoustic data (913), environmental data (915), and voice data (916). The acoustic data (913) and the voice data (916) may be generated via a microphone of a wearable device and / or an electronic device, and the voice data (916) may be included in the acoustic data (913), or the acoustic data (913) may be included in the voice data (916). In FIG. 9, the acoustic data (913) and the voice data (916) are illustrated as being received by different feature extraction layers (923 and 926), but may be received by the same feature extraction layer (923 or 926). In one embodiment, the user state data may be generated based on the logging data (914), and the logging data (914) may not be applied to the feature extraction layer, and the user state data may be applied to the feature extraction layer. In one embodiment, logging data (914) and user state data can each be applied to a feature extraction layer, and can be applied to one feature extraction layer.

[0160] An artificial intelligence model according to one embodiment may include, but is not limited to, an input layer, an encoder layer, and an output layer.

[0161] According to one embodiment, the input layer may include a feature extraction layer. The input layer may include a plurality of feature extraction layers (922, 924, 921, 923, 925, 926) depending on the modality. The feature extraction layers (922, 924, 921, 923, 925, 926) may extract features from input data (912, 914, 911, 913, 915, 916) received therein, respectively. The extracted features may be expressed as multidimensional vectors. The feature extraction layer may extract features of preprocessed data or extract features of raw data. The features extracted from the feature extraction layer may be passed to the next layer, for example, the encoder layer (930).

[0162] In one embodiment, each input layer of the AI ​​model may be located on an electronic device, but is not limited thereto. For example, input layers for biometric data, motion data, and acoustic data may be located on a wearable device, and input layers for logging data, environmental data, and user status data may be located on an electronic device.

[0163] In one embodiment, the AI ​​model may further include a positional encoding layer. The positional encoding layer may be located between the input layers (922, 924, 921, 923, 925, 926) and the encoder layer (930), or may belong to the input layers (922, 924, 921, 923, 925, 926), or may belong to the encoder layer (930). The positional encoding layer may impart information about time or order to the extracted features.

[0164] According to one embodiment, the encoder layer (930) may receive each feature extracted from each input layer (922, 924, 921, 923, 925, 926), perform fusion considering the importance, weight, or correlation of each data, and generate a fused feature as an output.

[0165] According to one embodiment, the encoder layer (930) may be implemented as a transformer layer. The transformer may be composed of an encoder, or an encoder and a decoder.

[0166] In one embodiment, the output layer (940) can generate the final output of the artificial intelligence model. The output layer (940) can output information related to the user's stress based on integrated multimodal data. The output layer (940) can be implemented as a dense layer.

[0167] In one embodiment, the output layer (940) receives data generated from the encoder layer (930) and generates an output (942) containing information about the user's stress.

[0168] According to one embodiment, the encoder layer (930) may receive and analyze each feature extracted from each input data (912, 914, 911, 913, 915, 916) through each input layer (922, 924, 921, 923, 925, 926) to generate an output (942) including information related to the user's stress.

[0169] According to one embodiment, the artificial intelligence model may be trained to integrate and analyze received input data (922, 924, 921, 923, 925, 926) to generate information about user's stress as output (942). The information about stress may include, but is not limited to, a stress cause related to the user's stress. According to one embodiment, the artificial intelligence model may analyze the received input to include at least one of a stress cause, a stress category of the stress cause, a stress type of the stress cause, a query (944) for describing the stress cause, a stress level of the stress cause, and a guide corresponding to the stress cause and / or the stress level.

[0170] In one embodiment, the user's response (946) to the query (944) may be a voice response (946), and the voice response (946) may have features extracted through a feature extraction layer of the voice data and applied to an artificial intelligence model. The method of applying the response (946) to the artificial intelligence model has been described with reference to FIG. 4, and thus, a redundant description thereof will be omitted.

[0171] In one embodiment, based on the user's data (912, 914, 911, 913, 915, 916), the user's context can be determined when the user is stressed. For example, the user may be primarily stressed when talking to others using a phone application, and based on the user's biometric data and logging data, it can be inferred that the user is stressed when using the phone application. The artificial intelligence model can analyze the input data (912, 914, 911, 913, 915, 916) to recognize the user's context when the user is stressed. The user's context can include the occurrence of a cause of stress.

[0172] In one embodiment, the user's context may include, but is not limited to, a physical context indicating the user's location or surroundings, a temporal context indicating a time zone or duration, a social context indicating the presence of others or social interactions, a personal context indicating the user's preferences, behavior history, and emotional state, a work context indicating the user's current task and task complexity, and a cultural context indicating the language used by the user and cultural norms that influence the user's behavior or preferences.

[0173] FIG. 10 is a diagram illustrating an example of a wearable device according to one embodiment.

[0174] According to one embodiment, the electronic device can obtain biometric data, motion data, and acoustic data from a plurality of wearable devices (1010 and 1020).

[0175] According to one embodiment, the wearable device (1010) can function as the electronic device described above, and the wearable device (1010) can obtain biometric data, motion data, and acoustic data from another wearable device (1020).

[0176] FIG. 10 illustrates a smartwatch (1010) and a smartring (1020) as wearable devices, but is not limited thereto. The wearable devices (1010 and 1020) may include a biosignal sensor for detecting the biosignals of a user wearing the devices.

[0177] Wearable devices (1010 and 1020) according to one embodiment may correspond to the wearable device (1000) of FIGS. 1 to 9, and the wearable devices (1010 and 1020) may perform the operations of the wearable device (1000) of FIGS. 1 to 9.

[0178] FIG. 11 is a diagram illustrating an example of a hardware structure of a wearable device according to one embodiment.

[0179] A wearable device (1100) according to one embodiment may be a smart ring.

[0180] A wearable device (1100) may include a processor (1120), a memory (1130), a communication module (1190), and sensors (1171, 1172, 1173, 1174, 1175, 1176). The wearable device (1100) may include an antenna (1197), a battery (1180), and a charging interface (1182). A communication module (1190) for communicating with other devices may be, but is not limited to, a Bluetooth module.

[0181] A wearable device (1100) may include a biosignal sensor. For example, the wearable device may include a photoplethysmography (PPG) sensor (1171, 1172), which may be divided into a light-emitting unit (1171) and a light-receiving unit (1172).

[0182] The wearable device (1100) may include a heart rate (HR) sensor (1173), an electrodermal activity (EDA) sensor (1174), and a temperature sensor (1176). The wearable device is not limited thereto and may further include other types of biosignal sensors.

[0183] A wearable device (1100) may include a motion sensor (1175) for measuring the motion of a user wearing the device. The motion sensor may be an inertial measurement unit (IMU) that measures motion using the law of inertia. For example, the motion sensor may include, but is not limited to, a gyroscope that measures the rotational speed of an object, an accelerometer that measures the acceleration of an object, and a magnetometer that measures the Earth's magnetic field to determine direction.

[0184] The wearable device (1100) may include a microphone for collecting the wearer's surrounding voice or sound signals.

[0185] A wearable device (1100) according to one embodiment may correspond to the wearable devices (1000, 1010, and 1020) of FIGS. 1 to 10, and the wearable device (1100) may perform the operations of the wearable devices (1000, 1010, and 1020) of FIGS. 1 to 10.

[0186] Figure 12 is a block diagram of a software structure of a wearable device according to one embodiment.

[0187] A wearable device (1200) may include a processor (1220) and a sensor (1270). The processor (1220) may be a microcontroller unit (MCU). The processor (1220) of the wearable device (1200) may control the sensor (1270).

[0188] The sensor (1270) may include a motion sensor, a biosignal sensor, and an environmental sensor. The motion sensor may be an inertial measurement unit (IMU) that measures movement using the law of inertia. The motion sensor may include, but is not limited to, a gyroscope that measures the rotational speed of an object, an accelerometer that measures the acceleration of an object, and a magnetometer that measures the Earth's magnetic field to determine direction.

[0189] The biosignal sensors may include, but are not limited to, a photoplethysmography (PPG) sensor, an electrodermal activity (EDA) sensor, an electrocardiogram (ECG) sensor, a heart rate (HR) sensor, a blood glucose sensor, an alcohol sensor, an advanced glycation end products (AGEs) sensor, an antioxidant sensor, and an oxygen saturation of partial pressure oxygen (SpO2) sensor.

[0190] Environmental sensors may include, but are not limited to, temperature sensors, barometers, noise sensors (microphones), and GPS sensors.

[0191] By the processor (1220), a network manager (1221), a sensor algorithm (1222), a system manager (1223), an AI library (1224), a service manager (1225), a driver (1226), and a sensor interface (1227) can be driven.

[0192] A network manager (1221) running on a wearable device (1200) can set up and monitor network connections of the wearable device (1200), for example, wired and wireless network connections.

[0193] A sensor interface (1227) driven by a wearable device (1200) collects sensing data from a sensor (1270) and transmits it to a processor (1220), and the processor (1220) can control the sensor (1270) through the sensor interface (1227).

[0194] A sensor algorithm (1222) running on a wearable device (1200) can analyze sensing data collected from a sensor (1270) and extract necessary information. For example, the sensor algorithm (1222) can derive biosignal data by analyzing sensing data collected from a sensor (1270).

[0195] A system manager (1223) running on a wearable device (1200) can monitor and manage the system status of the wearable device (1200).

[0196] The AI ​​library (1224) driven by the wearable device (1200) is a software library for supporting artificial intelligence functions in the wearable device (1200). For example, the AI ​​library (1224) may include, but is not limited to, AI models for performing health monitoring, exercise tracking, and voice recognition.

[0197] A service manager (1225) running on a wearable device (1200) can manage services by controlling the start, stop, or restart of various services within the wearable device (1200).

[0198] A driver (1226) driven by a wearable device (1200) can control the operation of the hardware by allowing the hardware and software of the wearable device (1200) to communicate with each other.

[0199] A wearable device (1200) according to one embodiment may correspond to the wearable devices (1000, 1010, 1020, and 1100) of FIGS. 1 to 11, and the wearable device (1200) may perform the operations of the wearable devices (1000, 1010, 1020, and 1100) of FIGS. 1 to 11.

[0200] Figure 13 is a block diagram of a software structure of an electronic device according to one embodiment.

[0201] An electronic device (1300) may include a processor (1320), an application processor (1321), and a sensor (1370). The processor (1220) may be a microcontroller unit (MCU). The processor (1320) of the electronic device (1300) may control the sensor (1370).

[0202] According to one embodiment, the calculation of the artificial intelligence model may be performed by at least one of a processor (1320) of the electronic device (1300), for example, a central processing unit (CPU), a graphical processing unit (GPU), or a neutral processing unit (NPU), but is not limited thereto. For example, the calculation of the artificial intelligence model may also be performed by another device and / or a server. In this case, data for the calculation of the artificial intelligence model may be provided from the electronic device (1300) to the other device and / or the server.

[0203] Sensors (1370) may include motion sensors and environmental sensors. Motion sensors may include, but are not limited to, a gyroscope that measures the rotational speed of an object, an accelerometer that measures the acceleration of an object, and a magnetometer that measures the Earth's magnetic field to determine direction. Environmental sensors may include, but are not limited to, a temperature sensor, a barometer, a noise sensor (microphone), and a GPS sensor.

[0204] By the processor (1320), a network manager (13201), a sensor algorithm (13202), a system manager (13203), an AI library (13204), a service manager (13205), a driver (13206), and a sensor interface (13207) can be driven.

[0205] A network manager (13201) running on an electronic device (1300) can set up and monitor network connections of the electronic device (1300), for example, wired and wireless network connections.

[0206] A sensor interface (13207) driven by an electronic device (1300) collects sensing data from a sensor (1370) and transmits it to a processor (1320), and the processor (1320) can control the sensor (1370) through the sensor interface (13207).

[0207] A sensor algorithm (13202) driven by an electronic device (1300) can analyze sensing data collected from a sensor (1370) to extract necessary information. For example, the sensor algorithm (13202) can derive biosignal data by analyzing sensing data collected from a sensor (1370). The sensor algorithm (13202) can also extract necessary information by analyzing sensing data collected from a sensor (1370) of a wearable device as well as a sensor of an electronic device (1300) (e.g., 1270).

[0208] A system manager (13203) running on an electronic device (1300) can monitor and manage the system status of the electronic device (1300).

[0209] The AI ​​library (13204) driven by the electronic device (1300) is a software library for supporting artificial intelligence functions in the electronic device (1300). For example, the AI ​​library (13204) may include, but is not limited to, AI models for performing health monitoring, exercise tracking, and voice recognition. The AI ​​library (13204) may include AI models trained to generate information related to user stress (e.g., 320 of FIG. 3 , 420 and 440 of FIG. 4 , 921, 922, 923, 924, 925, 926, 930, and 940 of FIG. 9 ).

[0210] A service manager (13205) running on an electronic device (1300) can manage services by controlling the start, stop, or restart of various services within the electronic device (1300).

[0211] A driver (13206) driven by an electronic device (1300) can control the operation of the hardware by allowing the hardware and software of the electronic device (1300) to communicate with each other.

[0212] The sensing data collected from the sensor (1370) is transmitted to the sensor algorithm module (13202) through the sensor interface (13207), and the sensor algorithm module (13202) can extract feature information from the transmitted sensing data and transmit it to the AI ​​library (13204). The transmitted feature information can be used as an input value of an artificial intelligence model installed in the AI ​​library (13204), for example, a machine learning (ML) model or a deep learning (DL) model. According to one embodiment, the sensor data transmitted to the sensor algorithm module (13202) is transmitted as is to the AI ​​library (13204), and the feature information is extracted from the AI ​​library (13204) and used as an input value of the artificial intelligence model. According to one embodiment, a wearable device (1200) can transmit sensing information such as biometric information, motion information, and acoustic information, or feature information extracted therefrom, to an electronic device (1300) through a network manager (1221).

[0213] The AI ​​model in the AI ​​library (13204) can learn data online or offline, depending on its purpose. Once the recognition results are output from the AI ​​model, they are then transmitted to the sensor algorithm module (13202) for processing according to subsequent algorithms or operational scenarios.

[0214] An application (13211), a framework (13213), a library (13214), a module (13216), and an interface (13217) may be driven by the application processor (13211). The library (13214) may include an AI library for computing an artificial intelligence model in the application (13211), and may include an AI model (e.g., 320 of FIG. 3, 420 and 440 of FIG. 4, and 921, 922, 923, 924, 925, 926, 930, and 940 of FIG. 9) trained to generate information related to user stress.

[0215] An application (13211) is a software program designed to perform a specific task and may include various applications such as, for example, a health application, a stress management application, a home management application, an exercise application, and a wearable device management application.

[0216] A module (13216) is an independent software component that performs a specific function, and may include, for example, a camera.

[0217] The interface (13217) can mediate communication between the application (13211), the framework (13213), the library (13214), and the module (13216), thereby enabling data exchange between the respective components. The framework (13213) of the electronic device (1300) can provide a structure and rules so that the application (13211) can easily use various functions of the electronic device (1300), and the framework (13213) can include a sensor manager, a location manager, a wearable manager, and a context manager. The application (13211) of the electronic device (1300) can include an application for controlling the wearable device (1200) and a health application for managing the health status of the user. Sensing information or characteristic information transmitted from the wearable device (1200) can be received through the application for controlling the wearable device (1200). The received information can be transmitted to the context manager via the wearable manager. The wearable manager can process information related to wearable devices (1200) connected to the electronic device (1300), and the context manager can recognize the context based on information collected from the wearable devices (1200) and information collected from the electronic device (1300) by running a context recognition algorithm.

[0218] An electronic device (1300) according to one embodiment may correspond to the electronic device (2000) of FIGS. 1 to 12, and the electronic device (1300) may perform the operations of the electronic device (2000) of FIGS. 1 to 12.

[0219] According to one embodiment, a method for estimating a user's stress may include recording first logging data for the user based on an interaction between the user and an electronic device (e.g., the electronic device 2000 of FIG. 1 , the electronic device 1300 of FIG. 13 , and the electronic device 1401 of FIG. 14 ) during a first period of time. The method may include obtaining first biometric data recorded by a wearable device worn by the user (e.g., the wearable device 1000 of FIG. 1 , the wearable devices 1010 and 1020 of FIG. 10 , the wearable device 1100 of FIG. 11 , and the wearable device 1200 of FIG. 12 ) during the first period of time. The method may include an operation of obtaining first information including a first stress cause related to the user's stress by applying a first input including the first logging data and the first biometric data to an artificial intelligence model (e.g., the artificial intelligence model (320) of FIG. 3, the artificial intelligence model (420) of FIG. 4, the Generative AI model (1550) of FIG. 15). The method may include an operation of providing a query (e.g., the query (424) of FIG. 4, the query (944) of FIG. 9) related to the first stress cause of the user based on the first information. The method may include an operation of receiving a response (e.g., the response (442) of FIG. 4, the response (946) of FIG. 9) from the user to the query (e.g., the query (424) of FIG. 4, the query (944) of FIG. 9). The method may include recording second logging data for the user during a second period after the first period and obtaining second biometric data from the wearable device (e.g., the wearable device (1000) of FIG. 1, the wearable devices (1010, 1020) of FIG. 10, the wearable device (1100) of FIG. 11, and the wearable device (1200) of FIG. 12).The method may include obtaining second information including a second stress cause elaborating the first stress cause by applying the second input including the second logging data and the second biometric data and the response (e.g., response (442) of FIG. 4, response (946) of FIG. 9) to the artificial intelligence model (e.g., artificial intelligence model (320) of FIG. 3, artificial intelligence model (420) of FIG. 4, Generative AI model (1550) of FIG. 15), wherein the second stress cause may be dependent on the first stress cause.

[0220] According to one embodiment, the method may include an operation of acquiring first acoustic data and first motion data recorded by the wearable device (e.g., wearable device (1000) of FIG. 1, wearable devices (1010, 1020) of FIG. 10, wearable device (1100) of FIG. 11, wearable device (1200) of FIG. 12) worn by the user during the first period. The method may further include an operation of acquiring second acoustic data and the second motion data during the second period. According to one embodiment, the first input may further include the first acoustic data and the first motion data, and the second input may further include the second acoustic data and the second motion data.

[0221] In one embodiment, the method may include collecting first environmental data regarding the environment surrounding the user during the first period. The method may further include collecting second environmental data regarding the environment surrounding the user during the second period. In one embodiment, the first input may further include the first environmental data, and the second input may further include the second environmental data.

[0222] According to one embodiment, the first logging data may include first user status data generated based on the first logging data during the first period, and the second logging data may include second user status data generated based on the second logging data during the second period.

[0223] In one embodiment, when the query (e.g., query (424) of FIG. 4, query (944) of FIG. 9) includes a plurality of sub-stress causes dependent on the first stress cause, and the response (e.g., response (442) of FIG. 4, response (946) of FIG. 9) includes at least one sub-stress cause among the plurality of sub-stress causes, the second stress cause may be directly or indirectly associated with the at least one sub-stress cause.

[0224] In one embodiment, by subordinating the response (e.g., response (442) of FIG. 4, response (946) of FIG. 9) to the first stressor, the second stressor may be subordinate to the first stressor, and the second stressor may be directly or indirectly associated with the response (e.g., response (442) of FIG. 4, response (946) of FIG. 9).

[0225] According to one embodiment, the weight data obtained by applying the response (e.g., the response (442) of FIG. 4, the response (946) of FIG. 9) to an adaptation model (e.g., the adaptation model (440) of FIG. 4)) to the artificial intelligence model (e.g., the artificial intelligence model (320) of FIG. 3, the artificial intelligence model (420) of FIG. 4, the Generative AI model (1550) of FIG. 15) may be applied to the artificial intelligence model (e.g., the artificial intelligence model (320) of FIG. 3, the artificial intelligence model (420) of FIG. 4, the Generative AI model (1550) of FIG. 15).

[0226] According to one embodiment, in response to inputting the first input including the first logging data and the first biometric data into the artificial intelligence model (e.g., the artificial intelligence model (320) of FIG. 3, the artificial intelligence model (420) of FIG. 4, the Generative AI model (1550) of FIG. 15), and when at least the artificial intelligence model (e.g., the artificial intelligence model (320) of FIG. 3, the artificial intelligence model (420) of FIG. 4, the Generative AI model (1550) of FIG. 15) can output the first information including the first stress cause, the query (e.g., the query (424) of FIG. 4, the query (944) of FIG. 9)) may be provided.

[0227] In one embodiment, the first information may further include a first stress level of the user, and the second information may further include a second stress level of the user.

[0228] In one embodiment, when the first stress level falls outside the threshold range, the query (e.g., query (424) of FIG. 4, query (944) of FIG. 9) may be provided.

[0229] According to one embodiment, the method may further include an operation of sending a notification to a preset contact in the electronic device (e.g., electronic device (2000) of FIG. 1, electronic device (1300) of FIG. 13, electronic device (1401) of FIG. 14) when the first stress level falls outside a threshold range.

[0230] In one embodiment, the method may include providing a first guide corresponding to the first stress source. The method may further include providing a second guide corresponding to the second stress source.

[0231] In one embodiment, the query (e.g., query (424) of FIG. 4, query (944) of FIG. 9) may be a first query, and the response (e.g., response (442) of FIG. 4, response (946) of FIG. 9) may be a first response. The method may include providing a second query based on the second stressor. The method may include receiving a second response from the user to the second query. The method may include recording third logging data for the user for a third period after the second period and obtaining third biometric data. The method may include an operation of obtaining third information including a third stress cause that describes the second stress cause by applying the second logging data and the third input including the second biometric data and the second response to the artificial intelligence model (e.g., the artificial intelligence model (320) of FIG. 3, the artificial intelligence model (420) of FIG. 4, the Generative AI model (1550) of FIG. 15).

[0232] According to one embodiment, the weights applied to the artificial intelligence model (e.g., the artificial intelligence model (320) of FIG. 3, the artificial intelligence model (420) of FIG. 4, the Generative AI model (1550) of FIG. 15) may be periodically adjusted according to the periodic fluctuations in the sex hormone concentration of the user.

[0233] In one embodiment, the first stressor and the second stressor may have a positive stress category or a negative stress category.

[0234] According to one embodiment, the response (e.g., response (442) of FIG. 4, response (946) of FIG. 9) may be applied to the artificial intelligence model (e.g., artificial intelligence model (320) of FIG. 3, artificial intelligence model (420) of FIG. 4, Generative AI model (1550) of FIG. 15) before the second input.

[0235] Figure 14 is a block diagram of an electronic device according to one embodiment.

[0236] FIG. 14 is a block diagram of an electronic device (1401) within a network environment (1400) according to various embodiments. Referring to FIG. 14, in the network environment (1400), the electronic device (1401) may communicate with the electronic device (1402) via a first network (1498) (e.g., a short-range wireless communication network), or may communicate with the electronic device (1404) or a server (1408) via a second network (1499) (e.g., a long-range wireless communication network). In one embodiment, the electronic device (1401) may communicate with the electronic device (1404) via the server (1408). According to one embodiment, the electronic device (1401) may include a processor (1420), a memory (1430), an input module (1450), an audio output module (1455), a display module (1460), an audio module (1470), a sensor module (1476), an interface (1477), a connection terminal (1478), a haptic module (1479), a camera module (1480), a power management module (1488), a battery (1489), a communication module (1490), a subscriber identification module (1496), or an antenna module (1497). In some embodiments, the electronic device (1401) may omit at least one of these components (e.g., the connection terminal (1478)), or may have one or more other components added. In some embodiments, some of these components (e.g., sensor module (1476), camera module (1480), or antenna module (1497)) may be integrated into a single component (e.g., display module (1460)).

[0237] The processor (1420) may, for example, execute software (e.g., a program (1440)) to control at least one other component (e.g., a hardware or software component) of the electronic device (1401) connected to the processor (1420) and perform various data processing or operations. According to one embodiment, as at least a part of the data processing or operations, the processor (1420) may store commands or data received from other components (e.g., a sensor module (1476) or a communication module (1490)) in a volatile memory (1432), process the commands or data stored in the volatile memory (1432), and store result data in a non-volatile memory (1434). According to one embodiment, the processor (1420) may include a main processor (1421) (e.g., a central processing unit or an application processor) or an auxiliary processor (1423) (e.g., a graphics processing unit, a neural processing unit (NPU), an image signal processor, a sensor hub processor, or a communication processor) that can operate independently or together with the main processor (1421). For example, when the electronic device (1401) includes the main processor (1421) and the auxiliary processor (1423), the auxiliary processor (1423) may be configured to use less power than the main processor (1421) or to be specialized for a given function. The auxiliary processor (1423) may be implemented separately from the main processor (1421) or as a part thereof.

[0238] The auxiliary processor (1423) may control at least a portion of functions or states associated with at least one component (e.g., the display module (1460), the sensor module (1476), or the communication module (1490)) of the electronic device (1401), for example, on behalf of the main processor (1421) while the main processor (1421) is in an inactive (e.g., sleep) state, or together with the main processor (1421) while the main processor (1421) is in an active (e.g., application execution) state. In one embodiment, the auxiliary processor (1423) (e.g., an image signal processor or a communication processor) may be implemented as a part of another functionally related component (e.g., a camera module (1480) or a communication module (1490)). In one embodiment, the auxiliary processor (1423) (e.g., a neural network processing unit) may include a hardware structure specialized for processing artificial intelligence models. The artificial intelligence models may be generated through machine learning. This learning can be performed, for example, on the electronic device (1401) where the artificial intelligence is performed, or can be performed through a separate server (e.g., server (1408)). The learning algorithm can include, for example, supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning, but is not limited to the examples described above. The artificial intelligence model can include multiple artificial neural network layers.The artificial neural network may be one of a deep neural network (DNN), a convolutional neural network (CNN), a recurrent neural network (RNN), a restricted Boltzmann machine (RBM), a deep belief network (DBN), a bidirectional recurrent deep neural network (BRDNN), a deep Q-network, or a combination of two or more of the above, but is not limited to the examples described above. In addition to, or alternatively to, a hardware structure, an artificial intelligence model may include a software structure.

[0239] The number of processors (1420) may be one or more. For example, the processor (1420) may have a multi-core processor structure such as a dual core, quad core, or hexa core.

[0240] The processor (1420) can control the operations of the electronic device (1401) by executing instructions stored in the memory (1430). For example, the processor (1420) can correspond to a plurality of processors that collectively perform a plurality of operations by dividing them among the processors.

[0241] The memory (1430) can store various data used by at least one component (e.g., the processor (1420) or the sensor module (1476)) of the electronic device (1401). The data can include, for example, software (e.g., the program (1440)) and input data or output data for commands related thereto. The memory (1430) can include volatile memory (1432) or non-volatile memory (1434).

[0242] The program (1440) may be stored as software in memory (1430) and may include, for example, an operating system (1442), middleware (1444), or an application (1446).

[0243] The input module (1450) can receive commands or data to be used in a component of the electronic device (1401) (e.g., a processor (1420)) from an external source (e.g., a user) of the electronic device (1401). The input module (1450) can include, for example, a microphone, a mouse, a keyboard, a key (e.g., a button), or a digital pen (e.g., a stylus pen).

[0244] The audio output module (1455) can output audio signals to the outside of the electronic device (1401). The audio output module (1455) can include, for example, a speaker or a receiver. The speaker can be used for general purposes, such as multimedia playback or recording playback. The receiver can be used to receive incoming calls. In one embodiment, the receiver can be implemented separately from the speaker or as part of the speaker.

[0245] The display module (1460) can visually provide information to an external party (e.g., a user) of the electronic device (1401). The display module (1460) may include, for example, a display, a holographic device, or a projector, and a control circuit for controlling the device. In one embodiment, the display module (1460) may include a touch sensor configured to detect a touch, or a pressure sensor configured to measure the intensity of a force generated by the touch.

[0246] The audio module (1470) can convert sound into an electrical signal, or vice versa. According to one embodiment, the audio module (1470) can acquire sound through the input module (1450), output sound through the sound output module (1455), or an external electronic device (e.g., electronic device (1402)) (e.g., speaker or headphone) directly or wirelessly connected to the electronic device (1401).

[0247] The sensor module (1476) can detect the operating status (e.g., power or temperature) of the electronic device (1401) or the external environmental status (e.g., user status) and generate an electrical signal or data value corresponding to the detected status. According to one embodiment, the sensor module (1476) can include, for example, a gesture sensor, a gyro sensor, a barometric pressure sensor, a magnetic sensor, an acceleration sensor, a grip sensor, a proximity sensor, a color sensor, an IR (infrared) sensor, a biometric sensor, a temperature sensor, a humidity sensor, or an illuminance sensor.

[0248] The interface (1477) may support one or more designated protocols that may be used to directly or wirelessly connect the electronic device (1401) with an external electronic device (e.g., the electronic device (1402)). In one embodiment, the interface (1477) may include, for example, a high definition multimedia interface (HDMI), a universal serial bus (USB) interface, an SD card interface, or an audio interface.

[0249] The connection terminal (1478) may include a connector through which the electronic device (1401) may be physically connected to an external electronic device (e.g., the electronic device (1402)). In one embodiment, the connection terminal (1478) may include, for example, an HDMI connector, a USB connector, an SD card connector, or an audio connector (e.g., a headphone connector).

[0250] The haptic module (1479) can convert electrical signals into mechanical stimuli (e.g., vibration or movement) or electrical stimuli that a user can perceive through tactile or kinesthetic sensations. In one embodiment, the haptic module (1479) may include, for example, a motor, a piezoelectric element, or an electrical stimulation device.

[0251] The camera module (1480) can capture still images and videos. In one embodiment, the camera module (1480) may include one or more lenses, image sensors, image signal processors, or flashes.

[0252] The power management module (1488) can manage the power supplied to the electronic device (1401). According to one embodiment, the power management module (1488) can be implemented as, for example, at least a part of a power management integrated circuit (PMIC).

[0253] A battery (1489) may power at least one component of the electronic device (1401). In one embodiment, the battery (1489) may include, for example, a non-rechargeable primary battery, a rechargeable secondary battery, or a fuel cell.

[0254] The communication module (1490) may support the establishment of a direct (e.g., wired) communication channel or a wireless communication channel between the electronic device (1401) and an external electronic device (e.g., electronic device (1402), electronic device (1404), or server (1408)), and the performance of communication through the established communication channel. The communication module (1490) may operate independently from the processor (1420) (e.g., application processor) and may include one or more communication processors that support direct (e.g., wired) communication or wireless communication. According to one embodiment, the communication module (1490) may include a wireless communication module (1492) (e.g., a cellular communication module, a short-range wireless communication module, or a global navigation satellite system (GNSS) communication module) or a wired communication module (1494) (e.g., a local area network (LAN) communication module, or a power line communication module). Any of these communication modules may communicate with an external electronic device (1404) via a first network (1498) (e.g., a short-range communication network such as Bluetooth, wireless fidelity (WiFi) direct, or infrared data association (IrDA)) or a second network (1499) (e.g., a long-range communication network such as a legacy cellular network, a 5G network, a next-generation communication network, the Internet, or a computer network (e.g., a local area network or a wide area network)). These various types of communication modules may be integrated into a single component (e.g., a single chip) or implemented as multiple separate components (e.g., multiple chips). The wireless communication module (1492) may use subscriber information (e.g., an international mobile subscriber identity (IMSI)) stored in the subscriber identification module (1496) to verify or authenticate the electronic device (1401) within a communication network such as the first network (1498) or the second network (1499).

[0255] The wireless communication module (1492) can support 5G networks and next-generation communication technologies following the 4G network, such as NR access technology (new radio access technology). NR access technology can support high-speed transmission of high-capacity data (eMBB (enhanced mobile broadband)), minimizing terminal power and connecting multiple terminals (mMTC (massive machine type communications)), or high reliability and low latency communications (URLLC (ultra-reliable and low-latency communications)). The wireless communication module (1492) can support, for example, a high-frequency band (e.g., mmWave band) to achieve a high data transmission rate. The wireless communication module (1492) may support various technologies for securing performance in high-frequency bands, such as beamforming, massive multiple-input and multiple-output (MIMO), full dimensional MIMO (FD-MIMO), array antenna, analog beam-forming, or large scale antenna. The wireless communication module (1492) may support various requirements specified in the electronic device (1401), an external electronic device (e.g., the electronic device (1404)), or a network system (e.g., the second network (1499)). According to one embodiment, the wireless communication module (1492) may support a peak data rate (e.g., 20 Gbps or more) for eMBB implementation, a loss coverage (e.g., 164 dB or less) for mMTC implementation, or a U-plane latency (e.g., 0.5 ms or less for downlink (DL) and uplink (UL), or 1 ms or less for round trip) for URLLC implementation.

[0256] The antenna module (1497) can transmit or receive signals or power to or from an external device (e.g., an external electronic device). In one embodiment, the antenna module (1497) may include an antenna including a radiator formed of a conductor or a conductive pattern formed on a substrate (e.g., a PCB). In one embodiment, the antenna module (1497) may include a plurality of antennas (e.g., an array antenna). In this case, at least one antenna suitable for a communication method used in a communication network, such as the first network (1498) or the second network (1499), may be selected from the plurality of antennas by, for example, the communication module (1490). A signal or power may be transmitted or received between the communication module (1490) and the external electronic device via the selected at least one antenna. In some embodiments, in addition to the radiator, another component (e.g., a radio frequency integrated circuit (RFIC)) may be additionally formed as a part of the antenna module (1497).

[0257] According to various embodiments, the antenna module (1497) may form a mmWave antenna module. In one embodiment, the mmWave antenna module may include a printed circuit board, an RFIC disposed on or adjacent a first side (e.g., a bottom side) of the printed circuit board and capable of supporting a designated high frequency band (e.g., a mmWave band), and a plurality of antennas (e.g., an array antenna) disposed on or adjacent a second side (e.g., a top side or a side side) of the printed circuit board and capable of transmitting or receiving signals in the designated high frequency band.

[0258] At least some of the above components can be interconnected and exchange signals (e.g., commands or data) with each other via a communication method between peripheral devices (e.g., a bus, GPIO (general purpose input and output), SPI (serial peripheral interface), or MIPI (mobile industry processor interface)).

[0259] According to one embodiment, commands or data may be transmitted or received between the electronic device (1401) and an external electronic device (1404) via a server (1408) connected to a second network (1499). Each of the external electronic devices (1402 or 1404) may be the same or a different type of device as the electronic device (1401). According to one embodiment, all or part of the operations executed in the electronic device (1401) may be executed in one or more of the external electronic devices (1402, 1404, or 1408). For example, when the electronic device (1401) is to perform a certain function or service automatically or in response to a request from a user or another device, the electronic device (1401) may, instead of or in addition to executing the function or service itself, request one or more external electronic devices to perform the function or at least a part of the service. One or more external electronic devices that receive the request may execute at least a portion of the requested function or service, or an additional function or service related to the request, and transmit the result of the execution to the electronic device (1401). The electronic device (1401) may process the result as is or additionally and provide it as at least a portion of a response to the request. For this purpose, cloud computing, distributed computing, mobile edge computing (MEC), or client-server computing technology may be used, for example. The electronic device (1401) may provide an ultra-low latency service using, for example, distributed computing or mobile edge computing. In another embodiment, the external electronic device (1404) may include an Internet of Things (IoT) device. The server (1408) may be an intelligent server utilizing machine learning and / or a neural network.According to one embodiment, an external electronic device (1404) or server (1408) may be included within the second network (1499). The electronic device (1401) may be applied to intelligent services (e.g., smart homes, smart cities, smart cars, or healthcare) based on 5G communication technology and IoT-related technology.

[0260] An electronic device (1401) according to one embodiment may correspond to the electronic devices (1300, 2000) of FIGS. 1 to 13, and the electronic device (1401) may perform the operations of the electronic devices (1300, 2000) of FIGS. 1 to 13.

[0261] FIG. 15 is a diagram illustrating an example of a system including a generative artificial intelligence model according to one embodiment.

[0262] Referring to FIG. 15, the User Query / Response Interface (1510) can receive user input. The user input may be in the form of bio-signals, natural language, images, and / or videos. Additionally, context information may also be transmitted when the user input is transmitted. Context information may include various additional information at the time of user input. For example, information on the application currently being used by the user or information on the user's location. Furthermore, the user input may be in a mixed form of the bio-signals, natural language, images, sounds, and context information described above. Furthermore, the user input may also be in a non-natural language form, such as selecting a menu. The User Query / Response Interface (1510) can output the results of a generative artificial intelligence system to the user. The output may be in the form of natural language or specific content, and may also be provided in the form of an action requested by the user. For example, the output may include information related to the user's stress. The output may include at least one of a stressor related to the user's stress, a stress category of the stressor, a stress type of the stressor, a level of stress caused by the stressor, a question associated with the stressor, and a guide corresponding to the stressor and / or stress level.

[0263] The AI ​​framework (1520) can receive user input and coordinate and control each component necessary to perform the user's intention based on the user's query.

[0264] User input received from the User Query / Response Interface (1510) can be transmitted to the Prompt design component (1521). The Prompt design component (1521) can be used to generate prompts suitable for inputting the user input into a Large Language Model (LLM) or a Large Multimodal Model (LMM). The Prompt design component (1521) can be an AI component that uses a machine learning algorithm or a neural network to develop better prompts over time. The Prompt design component (1521) can access a knowledge component (e.g., knowledge repositories (1540)) containing user preference data, a prompt library, and prompt examples based on the user input to generate a prompt, and transmit the generated prompt to the LLM or LMM.

[0265] The API / Plug-in management component (1523) can communicate with external information when there is a request for additional information when passing user input as input to a generative model. The API / Plug-in management component (1523) can establish a channel for communicating with the outside of the AI ​​Interface through the API, and can enable access to various data sources (e.g., knowledge repositories (1540)) through the established channel. In addition, if the API / Plug-in management component (1523) needs to perform an action that performs the user input as a final result rather than an intermediate result in an application or service, it can request the action to the application / service component (1530) through the API. Information obtained from an external source can be used to generate a prompt in the prompt design component (1521) together with the user input, or can be passed as input to the generative model.

[0266] The Refiner component (e.g., the output modification component (1525)) can fine-tune the output from a generative model. For example, the Refiner component can verify that the content generated by the LLM and / or LMM is not irrelevant, biased, or harmful. Furthermore, the Refiner component can determine the degree to which the output matches the user's desired result and, if necessary, initiate additional processing. The Refiner component can also configure and provide hints to the user to avoid undesirable output.

[0267] Generative AI Model (1550) can generally refer to an artificial intelligence neural network that generates new types of data based on user input information. Generative AI Model (1550) can include an image-generating model and / or a language-generating model. Representative image-generating models include a generative adversarial network (GAN) and a variational autoencoder (VAE), and examples include a diffusion-based generative model that uses a VAE and a transformer structure. A language-generating model is a model trained to statistically output the most appropriate output value based on input values, and representative examples include models such as CHAT-GPT 3 and CHAT-GPT 4. In addition, there are LMMs that can recognize various types of data input, such as biosignals, text, images, and voice, and generate new data corresponding to them.

[0268] According to one embodiment, the electronic devices (1300, 1401, and 2000) of FIGS. 1 to 14 may be configured to include at least a portion of the User Query / Response Interface (1510), the AI ​​framework (1520), the application / service component (1530), the knowledge repositories (1540), or the Generative AI Model (1550) of FIG. 15. According to one embodiment, at least a portion of the User Query / Response Interface (1510), the AI ​​framework (1520), the application / service component (1530), the knowledge repositories (1540), or the Generative AI Model (1550) of FIG. 15 may be included in another electronic device (e.g., another user's electronic device, wearable devices (1000, 1010, 1020, 1100, and 1200), and / or a server).

[0269] According to one embodiment, an electronic device for estimating a user's stress (e.g., the electronic device (2000) of FIG. 1, the electronic device (1300) of FIG. 13, the electronic device (1401) of FIG. 14) may include a memory (e.g., the memory (1430) of FIG. 14) for storing instructions; and one or more processors (e.g., the processor (1320) of FIG. 13, the processor (1420) of FIG. 14). The instructions, when individually or jointly executed by the one or more processors, may cause the electronic device to record first logging data for the user based on an interaction between the user and the electronic device (e.g., the electronic device (2000) of FIG. 1, the electronic device (1300) of FIG. 13, the electronic device (1401) of FIG. 14)) during a first period of time. The above instructions, when individually or jointly executed by the one or more processors, may cause the electronic device to obtain first biometric data recorded by a wearable device worn by the user during the first period (e.g., the wearable device (1000) of FIG. 1 , the wearable devices (1010, 1020) of FIG. 10 , the wearable device (1100) of FIG. 11 , the wearable device (1200) of FIG. 12 ). The above instructions, when individually or jointly executed by the one or more processors, may cause the electronic device to obtain first information including a first stress cause related to stress of the user by applying a first input including the first logging data and the first biometric data to an artificial intelligence model (e.g., the artificial intelligence model (320) of FIG. 3 , the artificial intelligence model (420) of FIG. 4 , the Generative AI model (1550) of FIG. 15 ).The above commands, when individually or jointly executed by the one or more processors, may cause the electronic device to provide a query (e.g., query (424) of FIG. 4 , query (944) of FIG. 9 ) related to the first stress cause of the user based on the first information. The above commands, when individually or jointly executed by the one or more processors, may cause the electronic device to receive a response (e.g., response (442) of FIG. 4 , response (946) of FIG. 9 ) from the user to the query (e.g., query (424) of FIG. 4 , query (944) of FIG. 9 ). The above instructions, when individually or jointly executed by the one or more processors, may cause the electronic device to record second logging data for the user during a second period after the first period and to obtain second biometric data from the wearable device (e.g., the wearable device (1000) of FIG. 1, the wearable devices (1010, 1020) of FIG. 10, the wearable device (1100) of FIG. 11, and the wearable device (1200) of FIG. 12). The instructions, when individually or jointly executed by the one or more processors, may cause the electronic device to obtain second information including a second stress cause elaborating the first stress cause by applying the second input including the second logging data and the second biometric data and the response (e.g., response (442) of FIG. 4, response (946) of FIG. 9) to the artificial intelligence model (e.g., artificial intelligence model (320) of FIG. 3, artificial intelligence model (420) of FIG. 4, Generative AI model (1550) of FIG. 15). In one embodiment, the second stress cause may be subordinate to the first stress cause.

[0270] According to one embodiment, the instructions, when individually or jointly executed by the one or more processors, may cause the electronic device to obtain first acoustic data and first motion data recorded by the wearable device (e.g., the wearable device 1000 of FIG. 1 , the wearable devices 1010 and 1020 of FIG. 10 , the wearable device 1100 of FIG. 11 , and the wearable device 1200 of FIG. 12 ) worn by the user during the first period. The instructions, when individually or jointly executed by the one or more processors, may cause the electronic device to obtain second acoustic data and the second motion data during the second period. According to one embodiment, the first input may further include the first acoustic data and the first motion data, and the second input may further include the second acoustic data and the second motion data.

[0271] In one embodiment, the instructions, when individually or jointly executed by the one or more processors, may cause the electronic device to collect first environmental data about an environment around the user during the first period of time. The instructions, when individually or jointly executed by the one or more processors, may cause the electronic device to collect second environmental data about an environment around the user during the second period of time. In one embodiment, the first input may further include the first environmental data, and the second input may further include the second environmental data.

[0272] According to one embodiment, the first logging data may include first user status data generated based on the first logging data during the first period. According to one embodiment, the second logging data may include second user status data generated based on the second logging data during the second period.

[0273] In one embodiment, the query (e.g., query (424) of FIG. 4, query (944) of FIG. 9) may include a plurality of sub-stress causes that are dependent on the first stress cause. In one embodiment, when the response (e.g., response (442) of FIG. 4, response (946) of FIG. 9) includes at least one sub-stress cause among the plurality of sub-stress causes, the second stress cause may be directly or indirectly associated with the at least one sub-stress cause.

[0274] In one embodiment, by subordinating the response (e.g., response (442) of FIG. 4, response (946) of FIG. 9) to the first stressor, the second stressor may be subordinate to the first stressor, and the second stressor may be directly or indirectly associated with the response (e.g., response (442) of FIG. 4, response (946) of FIG. 9).

[0275] According to one embodiment, the weight data obtained by applying the response (e.g., the response (442) of FIG. 4, the response (946) of FIG. 9) to an adaptation model (e.g., the adaptation model (440) of FIG. 4)) to the artificial intelligence model (e.g., the artificial intelligence model (320) of FIG. 3, the artificial intelligence model (420) of FIG. 4, the Generative AI model (1550) of FIG. 15) may be applied to the artificial intelligence model (e.g., the artificial intelligence model (320) of FIG. 3, the artificial intelligence model (420) of FIG. 4, the Generative AI model (1550) of FIG. 15).

[0276] According to one embodiment, in response to inputting the first input including the first logging data and the first biometric data into the artificial intelligence model (e.g., the artificial intelligence model (320) of FIG. 3, the artificial intelligence model (420) of FIG. 4, the Generative AI model (1550) of FIG. 15), and when at least the artificial intelligence model (e.g., the artificial intelligence model (320) of FIG. 3, the artificial intelligence model (420) of FIG. 4, the Generative AI model (1550) of FIG. 15) can output the first information including the first stress cause, the query (e.g., the query (424) of FIG. 4, the query (944) of FIG. 9)) may be provided.

[0277] In one embodiment, the first information may further include a first stress level of the user, and the second information may further include a second stress level of the user.

[0278] In one embodiment, when the first stress level falls outside the threshold range, the query (e.g., query (424) of FIG. 4, query (944) of FIG. 9) may be provided.

[0279] According to one embodiment, the instructions, when individually or jointly executed by the one or more processors, may cause the electronic device to send a notification to a preset contact when the first stress level falls outside a threshold range.

[0280] In one embodiment, the instructions, when individually or jointly executed by the one or more processors, may cause the electronic device to provide a first guide corresponding to the first stress source. The instructions, when individually or jointly executed by the one or more processors, may cause the electronic device to provide a second guide corresponding to the second stress source.

[0281] In one embodiment, the query (e.g., query (424) of FIG. 4, query (944) of FIG. 9) is a first query, the response (e.g., response (442) of FIG. 4, response (946) of FIG. 9) is a first response, and the instructions, when individually or jointly executed by the one or more processors, may cause the electronic device to provide a second query based on the second stressor. The instructions, when individually or jointly executed by the one or more processors, may cause the electronic device to receive a second response from the user to the second query. The instructions, when individually or jointly executed by the one or more processors, may cause the electronic device to record third logging data for the user for a third period after the second period and to obtain third biometric data. The above instructions, when individually or jointly executed by the one or more processors, may cause the electronic device to obtain third information including a third stress cause that describes the second stress cause by applying the third input including the second logging data and the second biometric data and the second response to the artificial intelligence model (e.g., the artificial intelligence model (320) of FIG. 3, the artificial intelligence model (420) of FIG. 4, the Generative AI model (1550) of FIG. 15).

[0282] According to one embodiment, the weights applied to the artificial intelligence model (e.g., the artificial intelligence model (320) of FIG. 3, the artificial intelligence model (420) of FIG. 4, the Generative AI model (1550) of FIG. 15) may be periodically adjusted according to the periodic fluctuations in the sex hormone concentration of the user.

[0283] In one embodiment, the first stressor and the second stressor may have a positive stress category or a negative stress category.

[0284] According to one embodiment, the response (e.g., response (442) of FIG. 4, response (946) of FIG. 9) may be applied to the artificial intelligence model (e.g., artificial intelligence model (320) of FIG. 3, artificial intelligence model (420) of FIG. 4, Generative AI model (1550) of FIG. 15) before the second input.

[0285] Electronic devices according to the various embodiments disclosed in this document may take various forms. Electronic devices may include, for example, portable communication devices (e.g., smartphones), computer devices, portable multimedia devices, portable medical devices, cameras, wearable devices, or home appliances. Electronic devices according to the embodiments of this document are not limited to the aforementioned devices.

[0286] The various embodiments of this document and the terminology used therein are not intended to limit the technical features described in this document to specific embodiments, but should be understood to include various modifications, equivalents, or substitutes of the embodiments. In connection with the description of the drawings, similar reference numerals may be used for similar or related components. The singular form of a noun corresponding to an item may include one or more of the items, unless the context clearly indicates otherwise. In this document, each of the phrases "A or B", "at least one of A and B", "at least one of A or B", "A, B, or C", "at least one of A, B, and C", and "at least one of A, B, or C" can include any one of the items listed together in the corresponding phrase among those phrases, or all possible combinations thereof. Terms such as "first," "second," or "first" or "second" may be used merely to distinguish one component from another, and do not limit the components in any other respect (e.g., importance or order). When a component (e.g., a first component) is referred to as "coupled" or "connected" to another (e.g., a second component), with or without the terms "functionally" or "communicatively," it means that the component can be connected to the other component directly (e.g., wired), wirelessly, or through a third component.

[0287] The term "module" used in various embodiments of this document may include a unit implemented in hardware, software, or firmware, and may be used interchangeably with terms such as logic, logic block, component, or circuit. A module may be an integral component, or a minimum unit or part of such a component that performs one or more functions. For example, according to one embodiment, a module may be implemented in the form of an application-specific integrated circuit (ASIC).

[0288] Various embodiments of the present document may be implemented as software (e.g., a program (1840)) including one or more instructions stored in a storage medium (e.g., an internal memory (1836) or an external memory (1838)) readable by a machine (e.g., an electronic device (1801)). For example, a processor (e.g., a processor (1820)) of the machine (e.g., an electronic device (1801)) may call at least one instruction among the one or more instructions stored from the storage medium and execute it. This enables the machine to operate to perform at least one function according to the at least one called instruction. The one or more instructions may include code generated by a compiler or code executable by an interpreter. The machine-readable storage medium may be provided in the form of a non-transitory storage medium. Here, 'non-transitory' simply means that the storage medium is a tangible device and does not contain signals (e.g., electromagnetic waves), and the term does not distinguish between cases where data is stored semi-permanently or temporarily on the storage medium.

[0289] According to one embodiment, the method according to various embodiments disclosed in this document may be provided as a computer program product. The computer program product may be traded between sellers and buyers as a product. The computer program product may be distributed in the form of a device-readable storage medium (e.g., compact disc read-only memory (CD-ROM)) or may be provided through an application store (e.g., Play Store). TM ) or directly between two user devices (e.g., smart phones), online distribution (e.g., downloading or uploading). In the case of online distribution, at least a portion of the computer program product may be at least temporarily stored or temporarily created in a machine-readable storage medium, such as the memory of a manufacturer's server, an application store's server, or an intermediary server.

[0290] According to various embodiments, each component (e.g., a module or a program) of the above-described components may include one or more entities, and some of the entities may be separately arranged in other components. According to various embodiments, one or more components or operations of the aforementioned components may be omitted, or one or more other components or operations may be added. Alternatively or additionally, a plurality of components (e.g., a module or a program) may be integrated into a single component. In such a case, the integrated component may perform one or more functions of each of the plurality of components identically or similarly to those performed by the corresponding component among the plurality of components prior to the integration. According to various embodiments, the operations performed by a module, program, or other component may be executed sequentially, in parallel, iteratively, or heuristically, or one or more of the operations may be executed in a different order, omitted, or one or more other operations may be added.

Claims

1. An action of recording first logging data for a user based on an interaction between the user and the electronic device during a first period; An operation of acquiring first biometric data recorded by a wearable device worn by the user during the first period; An operation of obtaining first information including a first stress cause related to the user's stress by applying a first input including the first logging data and the first biometric data to an artificial intelligence model; An action of providing a query related to the first stress cause of the user based on the first information; An action of receiving a response from the user to the above query; An operation of recording second logging data for the user and obtaining second biometric data from the wearable device during a second period after the first period; and An operation of obtaining second information including a second stress cause elaborating the first stress cause by applying a second input including the second logging data and the second biometric data and the response to the artificial intelligence model; Includes, A method wherein the second stressor is dependent on the first stressor.

2. In paragraph 1, An operation of acquiring first sound data and first motion data recorded by the wearable device worn by the user during the first period; and Further comprising an operation of acquiring second sound data and second motion data during the second period, A method wherein the first input further includes the first acoustic data and the first motion data, and the second input further includes the second acoustic data and the second motion data.

3. In paragraph 1, An operation of collecting first environmental data regarding the environment around the user during the first period; and Further comprising an action of collecting second environmental data about the environment around the user during the second period, A method wherein the first input further includes the first environmental data, and the second input further includes the second environmental data.

4. In paragraph 1, The first logging data includes first user status data generated based on the first logging data during the first period, A method wherein the second logging data includes second user status data generated based on the second logging data during the second period.

5. In paragraph 1, The above query includes multiple sub-stress causes dependent on the first stress cause, A method wherein the second stress cause is directly or indirectly associated with the at least one sub-stress cause, when the response includes at least one sub-stress cause among the plurality of sub-stress causes.

6. In paragraph 1, By subordinating the above response to the first stressor, the second stressor becomes subordinate to the first stressor, A method wherein the second stressor is directly or indirectly associated with the response.

7. In paragraph 1, A method wherein the query is provided when, in response to inputting the first input including the first logging data and the first biometric data into the artificial intelligence model, at least the artificial intelligence model can output the first information including the first stress cause.

8. In paragraph 1, The first information further includes the first stress level of the user, The second information further includes a second stress level of the user, A method wherein the query is provided when the first stress level falls outside the critical range.

9. In paragraph 8, A method further comprising the action of sending a notification to a preset contact from the electronic device when the first stress level falls outside a threshold range.

10. In paragraph 1, An action providing a first guide corresponding to the first stressor; and A method further comprising an action of providing a second guide corresponding to the second stressor.

11. In paragraph 1, The above query is the first query, and the above response is the first response, An action of providing a second query based on the second stress cause; An action of receiving a second response from the user to the second query; An operation of recording third logging data for the user and obtaining third biometric data during a third period after the second period; and A method further comprising the action of obtaining third information including a third stress cause describing the second stress cause by applying a third input including the third logging data and the third biometric data and the second response to the artificial intelligence model.

12. In paragraph 1, A method wherein the first stressor and the second stressor have a positive stress category or a negative stress category.

13. In paragraph 1, A method wherein the above response is applied to the artificial intelligence model before the second input.

14. In electronic devices, memory that stores commands; and Containing one or more processors, The above instructions, when individually or collectively executed by the one or more processors, cause the electronic device to: Record first logging data about the user based on the interaction between the user and the electronic device during the first period; Obtaining first biometric data recorded by a wearable device worn by the user during the first period; By applying the first input including the first logging data and the first biometric data to an artificial intelligence model, first information including a first stress cause related to the user's stress is obtained, Provide a query related to the first stress cause of the user based on the first information, Receive the user's response to the above query, During a second period after the first period, second logging data for the user is recorded and second biometric data is acquired from the wearable device; By applying the second input including the second logging data and the second biometric data and the response to the artificial intelligence model, second information including a second stress cause elaborating the first stress cause is obtained, An electronic device wherein the second stress cause is dependent on the first stress cause.

15. An action of recording first logging data for a user based on an interaction between the user and the electronic device during a first period; An operation of acquiring first biometric data recorded by a wearable device worn by the user during the first period; An operation of obtaining first information including a first stress cause related to the user's stress by applying a first input including the first logging data and the first biometric data to an artificial intelligence model; An action of providing a query related to the first stress cause of the user based on the first information; An action of receiving a response from the user to the above query; An operation of recording second logging data for the user and obtaining second biometric data from the wearable device during a second period after the first period; and An operation of obtaining second information including a second stress cause elaborating the first stress cause by applying a second input including the second logging data and the second biometric data and the response to the artificial intelligence model; Includes, A computer-readable recording medium having recorded thereon a program for executing a method, wherein the second stress cause is dependent on the first stress cause.

Images