Electronic device, method, and storage medium for stress management

Abstract

In the present disclosure, an electronic device may comprise: at least one sensor; a memory including one or more storage media storing instructions; and at least one processor including a processing circuit. The instructions may, when individually or collectively executed by the at least one processor, cause the electronic device to perform at least one operation. The at least one operation may comprise an operation of acquiring a biometric signal by using the at least one sensor. The at least one operation may comprise an operation of identifying a stress level at least partially on the basis of the acquired biometric signal. The at least one operation may comprise an operation of determining a conversation topic at least partially on the basis of the identified stress level satisfying a specific stress range. The at least one operation may comprise an operation of outputting a plurality of messages corresponding to the determined conversation topic as at least a part of an interactive conversation with a user through a specific application.

Description

Electronic devices, methods, and storage media for stress management

[0001] The present disclosure relates to electronic devices, methods, and storage media for managing stress.

[0002] The complex social structure resulting from advanced industrialization creates an environment that can impact both physical and mental health. Mental health can often be neglected compared to physical health. Mental health can be significantly affected by stress, which can arise from internal tension, so managing stress on a daily basis is crucial. When stressful situations persist for a long time or occur repeatedly, it can lead to mental and even physical damage.

[0003] Electronic devices are providing healthcare services utilizing sensing technologies and applications. For example, electronic devices can utilize sensing technologies to provide healthcare services that manage users' stress levels by utilizing their biosignals.

[0004] The above information may be provided as background information to aid in understanding this document. None of the above is claimed to be prior art related to this document or can be used to determine prior art.

[0005] According to one embodiment, an electronic device may include at least one sensor. The electronic device may include a memory including one or more storage media for storing instructions. The electronic device may include at least one processor including a processing circuit. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to perform at least one operation. The at least one operation may include obtaining a biosignal using the at least one sensor. The at least one operation may include determining a stress level based at least in part on the obtained biosignal. The at least one operation may include determining a conversation topic based at least in part on whether the determined stress level satisfies a specific stress range. The at least one operation may include outputting a plurality of messages corresponding to the determined conversation topic as at least part of an interactive conversation with a user through a specific application.

[0006] According to one embodiment, a storage medium may store computer-readable instructions. The instructions, when executed by at least a portion of at least one processor of an electronic device, may cause the electronic device to perform at least one operation. The at least one operation may include obtaining a biosignal using at least one sensor. The at least one operation may include determining a stress level based at least in part on the obtained biosignal. The at least one operation may include determining a conversation topic based at least in part on whether the determined stress level satisfies a specific stress range. The at least one operation may include outputting a plurality of messages corresponding to the determined conversation topic as at least a part of an interactive conversation with a user through a specific application.

[0007] According to one embodiment, a method of operating an electronic device may include acquiring a biosignal using at least one sensor. The method may include determining a stress level based at least in part on the acquired biosignal. The method may include determining a conversation topic based at least in part on whether the identified stress level satisfies a specific stress range. The method may include outputting a plurality of messages corresponding to the determined conversation topic as at least a part of an interactive conversation with a user through a specific application.

[0008] In connection with the description of the drawings, the same or similar reference numerals may be used for the same or similar components.

[0009] FIG. 1 is a block diagram of an exemplary electronic device capable of performing the operations described herein.

[0010] FIG. 2 is an exemplary block diagram for providing a generative artificial intelligence (AI) model in an electronic device according to one embodiment.

[0011] FIG. 3 is a block diagram of an exemplary AI system capable of performing the operations described in this document.

[0012] Figure 4 is a configuration diagram of a stress management system according to one embodiment.

[0013] FIG. 5 is a control flowchart for providing a personalized stress management service in an electronic device according to one embodiment.

[0014] FIG. 6 is a control flowchart for providing a personalized stress management service in an electronic device according to one embodiment.

[0015] Figure 7a, Figure 7b or Figure 7c is a drawing for exemplarily explaining that the user's stress index changes in real time.

[0016] FIG. 8 is a diagram illustrating an example of a user interface that provides a conversation with a user in an electronic device according to one embodiment.

[0017] Figure 9a or Figure 9b is a drawing for explaining detection of an abnormal situation in which the conversation of Figure 8 is performed.

[0018] FIG. 10 is a diagram illustrating an example of a user interface that provides a conversation with a user in an electronic device according to one embodiment.

[0019] Figure 11a or Figure 11b is a drawing for explaining detection of an abnormal situation in which the conversation of Figure 10 is performed.

[0020] Figure 12 is a configuration diagram of an Internet of Things platform according to various embodiments.

[0021] FIG. 13 is a block diagram of an electronic device within a network environment according to various embodiments.

[0022] 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.

[0023] FIG. 1 is a block diagram of an exemplary electronic device (100) capable of performing the operations described in this document.

[0024] Referring to FIG. 1, the electronic device (100) may be one of various forms of electronic devices, such as a notebook (190), smartphones (191) having various form factors (e.g., a bar-type smartphone (191-1), a foldable-type smartphone (191-2), or a sliderable (or rollable) type smartphone (191-3)), a tablet (192), a cellular phone (not shown), and other similar computing devices (not shown). The components, their relationships, and their functions illustrated in FIG. 1 are exemplary only and do not limit the implementations described or claimed in this document. The electronic device (100) may be referred to as a mobile device, a user device, a multi-function device, a portable device, or a server.

[0025] The electronic device (100) may include components including at least one processor (110) (hereinafter, referred to as 'processor (110)'), at least one memory (120) (hereinafter, referred to as 'memory (120)'), at least one display (140) (hereinafter, referred to as 'display (140)'), at least one image sensor (150) (hereinafter, referred to as 'image sensor (150)'), at least one communication circuit (160) (hereinafter, referred to as 'communication circuit (160)'), and / or at least one sensor (170) (hereinafter, referred to as 'sensor (170)'). The components are merely exemplary. For example, the electronic device (100) may include other components (e.g., power management integrated circuitry (PMIC), audio processing circuitry, an antenna, a rechargeable battery, or an input / output interface). For example, some components may be omitted from the electronic device (100). For example, several components may be integrated into a single component. For example, the electronic device (100) may further include at least some of the configurations and / or functions not shown. At least some of the respective components of the electronic device shown (or not shown) may be operatively, functionally, and / or electrically connected to each other.

[0026] The processor (110) may be implemented as one or more IC (integrated circuit (or circuitry)) chips and may perform various data processing. The processor (110) may include at least one electrical circuit and may individually or collectively perform distributed processing of instructions (or programs, data) stored in the memory (120). The processor (110) may include a processor assembly including one or more processing circuits. The processor (110) may include any processing circuit operative to control the performance and operations of one or more components (e.g., the memory (120), the display (140), the image sensor (150), the communication circuit (160), and / or the sensor (170)) of the electronic device (100). For example, the processor (110) (e.g., the application processor (AP)) may be implemented as a system on chip (SoC) (e.g., a single chip or chipset). For example, the processor (110) may be implemented with multiple cores (or at least one core circuit), multiple chips, or multiple chipsets. For example, the processor (110) may include one or more processing circuits. For example, the processor (110) may include one or more processing circuits configured to individually and / or collectively perform various functions of the present disclosure. As a non-limiting example, at least a portion of the processor (110) may be included in a first chip of the electronic device (100), and at least another portion of the processor (110) may be included in a second chip of the electronic device (100) that is different from the first chip of the electronic device (100).

[0027] For example, the processor (110) may include a central processing unit (CPU) (311), a graphics processing unit (GPU) (112), a neural processing unit (NPU) (113), an image signal processor (ISP) (114), a display controller (115), a memory controller (116), a storage controller (117), a communication processor (CP) (118), and / or a sensor interface (119). These components of the processor (110) are merely exemplary. For example, the processor (110) may further include other components. For example, some components of the processor (110) may be omitted from the processor (110). For example, some components of the processor (110) may be included as separate components of the electronic device (100) outside the processor (110). For example, some components of the processor (110) (e.g., memory controller (116)) may be included within other components (e.g., at least a portion of memory (120), an interface (e.g., available for connection to at least one component of the electronic device (100)), a display (140) and / or an image sensor (150)).

[0028] The number of processors (110) may be one or more. For example, the processor (110) may have a multi-core processor structure such as a dual core, quad core, or hexa core.

[0029] The processor (110) can control the operations of the electronic device (100) by executing instructions stored in the memory (120). For example, the processor (110) can correspond to a plurality of processors that collectively perform a plurality of operations by dividing them among the processors.

[0030] The processor (110) may cause other components of the electronic device (100) to perform various operations by executing instructions stored in the memory (120). The CPU (111) (or central processing circuit) may be configured to control components of the processor (110) based on the execution of instructions stored in the memory (120) (e.g., volatile memory (121) and / or non-volatile memory (122)). The GPU (112) (or graphics processing circuit) may be configured to execute parallel operations (e.g., rendering). The NPU (113) (or neural processing circuit, or artificial intelligence (AI) chip) may be configured to execute operations for an AI model (e.g., convolution computation). The ISP (114) (or image signal processing circuit) may be configured to process a raw image acquired through the image sensor (150) into a format suitable for a component within the electronic device (100) or a component of the processor (110). The display controller (115) (or display control circuit, or DPU (display processing unit)) may be configured to process an image acquired from the CPU (111), GPU (112), ISP (114), or memory (120) (e.g., volatile memory (121)) into a format suitable for the display (140). The memory controller (116) (or memory control circuit) may be configured to control reading data from the volatile memory (121) and writing data to the volatile memory (121). The above storage controller (117) (or storage control circuit) may be configured to control reading data from the non-volatile memory (122) and writing data to the non-volatile memory (122).The CP (118) (communication processing circuit) may be configured to process data acquired from a component of the processor (110) into a format suitable for transmitting to another electronic device via the communication circuit (160), or to process data acquired from another electronic device via the communication circuit (160) into a format suitable for processing by a component of the processor (110). For example, the communication circuit (160) may include one or more communication circuits. The sensor interface (119) (or sensing data processing circuit, sensor hub) may be configured to process data on the state of the electronic device (100) and / or the state of the surroundings of the electronic device (100), acquired via the sensor (170), into a format suitable for a component of the processor (110).

[0031] The memory (120) may include one or more storage media (or one or more storage devices). For example, the memory (120) may include a memory assembly including one or more storage media. For example, the one or more storage media may include permanent memory (e.g., non-volatile memory (122)) such as a hard drive, flash memory, read-only memory (ROM), semi-permanent memory (e.g., volatile memory (121)) such as random access memory (RAM), any other suitable type of storage (or storage assembly), or any combination thereof. The memory (120) may include a cache memory, which is one or more different types of memory used to temporarily store data for a function or feature of the electronic device (100). As a non-limiting example, the cache memory may be included within the processor (110). The memory (120) may be fixedly embedded within the electronic device (100) or incorporated into one or more suitable types of components (e.g., a subscriber identity module (SIM) card and / or a secure digital (SD) card) that may be repeatedly inserted into and removed from the electronic device (100).

[0032] For example, the memory (120) may store one or more software applications, such as an operating system (or system) software application, a firmware software application, a driver software application, a plug-in (e.g., add-in, add-on, and / or applet) software application, and / or any other suitable software applications. For example, the one or more software applications may include instructions executable by the processor (110). For example, the memory (120) may store instructions callable by an application programming interface (API). For example, the memory (120) may store instructions within a library.

[0033] According to one example, the electronic device (100) can execute at least one instance of an AI model. The instance may be an object corresponding to a program (or application), such as an AI model, for example. The instance may be named a replica, a pod, a container, or a virtual machine, and there is no limitation on the name thereof. The number of instances may correspond to the size of a resource (e.g., a GPU (112) or an NPU (113)), and accordingly, the number of instances may be used interchangeably with the size of the resource, or the instances may be used interchangeably with the resource.

[0034] As an example, a plurality of user requests may be input to the electronic device (100). The user requests may be associated with a service. The user request may be processed by a first instance of a first AI model, and a first processing result may be provided from the first instance of the first AI model. The first processing result may be processed by a first instance of a second AI model, and accordingly, a second processing result may be provided by the first instance of the second AI model. By serial processing of the processing results, the first instance of the M-th AI model may receive and process the N-1-th processing result. The first instance of the M-th AI model may provide the N-th processing result as a response. Accordingly, a response corresponding to the user request may be provided.

[0035] Based on the above-described process, responses corresponding to each of a plurality of user requests may be provided. Meanwhile, since processing must be performed by an instance, the time for providing responses corresponding to each of a plurality of user requests (hereinafter referred to as “response time”) may take a relatively long time. The response time may affect the latency of the instance. In order to reduce the response time, the electronic device (100) may increase the number of instances of at least one AI model, which may be referred to as scaling out. However, there may be a limit to increasing the number of instances due to hardware and / or software constraints of the electronic device (100) and / or parameter restrictions of the AI ​​model (e.g., large language model (LLM)).

[0036] FIG. 2 is an exemplary block diagram for providing a generative artificial intelligence (AI) model in an electronic device (e.g., electronic device (100) of FIG. 1) (hereinafter referred to as 'electronic device (100)') according to one embodiment.

[0037] Referring to FIG. 2, the electronic device (100) may include a processor (110) (e.g., the processor (110) of FIG. 1), a memory (120) (e.g., the memory (120) of FIG. 1), and / or an interface (I / F) (220). According to one example, all or part of the operations executed in the electronic device (100) may be executed in one or more external electronic devices. For example, when the electronic device (100) needs to perform a certain function or service automatically or in response to a request from a user or another device, the electronic device (100) may, instead of executing the function or service on its own or in addition, request one or more external electronic devices to execute at least a part of the function or service. The one or more external electronic devices that receive the request may execute at least a part 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 (100). The electronic device (100) may process the above results as is or additionally and provide them as at least part of a response to the request.

[0038] According to one example, an electronic device (100) can perform a service by linking with at least one AI system (200) (hereinafter referred to as 'AI system (200)'). The electronic device (100) may be implemented as, for example, a single entity, or may be implemented as a plurality of entities. For example, the electronic device (100) may operate an AI system (200) that can operate in an on-device environment, and there is no limitation on the form of implementation thereof. The AI ​​system (200) operated in the electronic device (100) in the on-device environment may include one or more AI models using machine learning and / or neural networks. For example, the AI ​​system (200) may execute an instance of at least one AI model. An instance can be an object corresponding to a program (or application), such as an AI model, for example, and can be named a replica, a pod, a container, or a virtual machine, and there is no limitation on the name. The number of instances can correspond to the size of a resource (e.g., a GPU), and accordingly, the number of instances can be used interchangeably with the size of the resource, or the instances can be used interchangeably with the resource. In the description to follow, it is assumed that, for example, one instance is executed for each of at least one AI models. As an instance corresponding to a specific AI model is executed, a resource of a predetermined size can be used. The resource of a predetermined size can mean, for example, a portion of a processor (110), a memory (120), and / or an I / F (220).

[0039] The AI ​​system (200) may be based on natural language processing (NLP). NLP is a technology that allows an electronic device (200) to understand or process natural language input (hereinafter referred to as a "prompt") that can be expressed in the form of voice and / or text. The electronic device (200) can understand natural language through NLP and, based on this, determine human intention or convey information in a language that humans can understand. To understand human language, NLP can learn the order of words or tokens and predict the probability of the next word or token in a given text. A token is a basic unit for processing or understanding a prompt in an AI model. Key technologies of NLP include tokenization, part-of-speech tagging, syntax analysis, named entity recognition, or sentiment analysis for prompts corresponding to user input.

[0040] The I / F (220) can input a query (230) and transmit the input query (230) to the processor (110). The query (230) may correspond to, for example, one or more user requests. The query (230) may be a medium that guides the AI ​​system (200) to perform a task or generate a result in a desired direction. The query (230) may be the only window through which the user can communicate with the AI ​​system (200). The query (230) needs to be clear and specific in order to obtain an answer close to the desired result from the AI ​​system (200). According to one example, the I / F (220) may receive a response (240) (e.g., a summary message and / or a response message) processed by the AI ​​system (200) based on a query (230) (e.g., received messages), and output a response (240) converted into a natural language in a form that can be recognized by humans (e.g., text, image, audio, or video). The I / F (220) may receive or output natural language in the form of voice and / or text through at least one component such as a keyboard, a touch panel, a display, and / or a speaker, for example.

[0041] The processor (110) may execute software (e.g., a program) to control at least one other component (e.g., a hardware or software component) of the electronic device (100) to which it is electrically connected. The processor (110) may perform various data processing or operations. As at least a part of the data processing or operations, the processor (110) may store instructions or data received from another component (e.g., an I / F (220)) in the memory (120) (e.g., a volatile memory, but without limitation). As at least a part of the data processing or operations, the processor (110) may process instructions or data stored in the memory (120) (e.g., a volatile memory, but without limitation). As at least a part of the data processing or operations, the processor (110) may store data resulting from processing instructions or data in the memory (120) (e.g., a non-volatile memory, but without limitation).

[0042] The memory (120) may store various data used by at least one component (e.g., processor (110) and / or I / F (220)) of the electronic device (100). The data may include, for example, software (e.g., program) and input data or output data for commands related thereto. The memory (120) may also store at least one AI model (e.g., sLM (small LM), LLM, LVM (large vision models), LMM (large multimodal models)) for executing one or more instances.

[0043] The memory (120) can store at least one instruction. The processor (110) can execute at least one instruction stored in the memory (120). When the at least one instruction is executed by the processor (110), the at least one instruction can cause the electronic device (100) to perform at least one operation. For example, as the at least one instruction is executed by the processor (110), at least one other component can be controlled, and / or various data processing or calculations can be performed. The performance of one operation by the processor (110) can mean, for example, that the operation is performed by (or under the control of) one entity included in the processor (110) (for example, the main processor, but without limitation). The performance of one operation can mean, for example, that a specific operation is performed by (or under the control of) multiple entities (for example, multiple processors). The fact that multiple operations are performed may mean, for example, that all of the multiple operations are performed by (or under the control of) one entity (e.g., but not limited to, a main processor (e.g., CPU (111) of FIG. 1).). The fact that multiple operations are performed may mean, for example, that some of the multiple operations are performed by at least one entity, and some of the remaining operations are performed by at least one other entity. At least one instruction causing the performance of one or more operations may be stored, for example, in one memory, or may be stored distributedly in each of a plurality of memories.

[0044] In the electronic device (100), the AI ​​system (200) may share resources (e.g., data processing or computational power) corresponding to part or all of at least one processor included in the processor (110) and / or resources (e.g., data recording area) corresponding to part or all of the memory (120). For example, the AI ​​system (200) may be operated by at least one of the CPU (111), the GPU (112), or the NPU (113). The AI ​​system (200) may be performed solely by the CPU (111), for example, by being assigned at least a portion of the memory (120). The AI ​​system (200) may be performed solely by the GPU (112), for example, by being assigned at least a portion of the memory (120). The AI ​​system (200) may be performed solely by the NPU (113), for example, by being assigned at least a portion of the memory (120). The AI ​​system (200) can be performed by a CPU (111) and a GPU (112) in cooperation, for example, by being assigned at least a portion of the memory (120). The AI ​​system (200) can be performed by a CPU (111) and an NPU (113) in cooperation, for example, by being assigned at least a portion of the memory (120). The AI ​​system (200) can be performed by a GPU (112) and an NPU (113) in cooperation, for example, by being assigned at least a portion of the memory (120). The AI ​​system (200) can be performed by a CPU (111), a GPU (112), and an NPU (113) in cooperation, for example, by being assigned at least a portion of the memory (120). The various embodiments to be described later in the present disclosure are not limited to the combination of components for performing the AI ​​system (200), and can be implemented and / or applied based on any combination.

[0045] FIG. 3 is a block diagram of an exemplary AI system (300) capable of performing the operations described in this document. The AI ​​system (300) may be a generative AI system, but will be referred to as the "AI system (300)" hereinafter.

[0046] Referring to FIG. 3, the AI ​​system (300) may include a User Query / Response Interface (310) (e.g., I / F (220) of FIG. 2) (hereinafter, referred to as 'I / F (310)'), an AI framework (320), a generative AI model (330), a database (340), or an Application / Service Component (350).

[0047] The I / F (310) can receive data or user input acquired or generated by an electronic device (e.g., the electronic device (100) of FIG. 1). The data acquired or generated by the electronic device (100) may include image or video data generated using a processor (e.g., the processor (110) of FIG. 1), values ​​transmitted through a sensor or sensor hub (e.g., external illuminance, an angle of the terminal, a display (e.g., the display (140) of FIG. 1) or the temperature of the electronic device (100), display (140) size or expansion / reduction information, an image captured by an image sensor (e.g., the image sensor (150) of FIG. 1)). The user input may be in the form of natural language, touch coordinates or stylus coordinates acquired through a touch panel or digitizer included in the display (140), images, and / or videos, but is not limited thereto. In addition, context information may also be transmitted when transmitting the user input. Contextual information can include various additional information at the time of user input. For example, this additional information may include information about the application the user is currently using or the user's location. Furthermore, user input may also be a mixture of natural language, images, sounds, and contextual information described above. Furthermore, user input may also be non-natural, such as selecting a menu.

[0048] The I / F (310) can output the results of analyzing the output and / or input of the AI ​​system (300). The output may be in the form of natural language or specific content. The output may also be provided in the form of an action requested by the user. The output may also be provided in the form of a specific value specified by the user. The I / F (310) can output the results of the generative AI system (300) to the user. The output may be in the form of natural language or specific content. The output may also be provided in the form of an action requested by the user.

[0049] The AI ​​framework (320) can receive user input and coordinate and control each component necessary to carry out the user's intention based on the user's query. For example, the AI ​​framework (320) may include a prompt design component (321), an API / plug-in management component (323), or an output modification component (or refiner component) (325).

[0050] User input received from I / F (310) can be transmitted to a prompt design component (321). The prompt design component (321) can be used to generate a prompt suitable for inputting the user input into a generative AI model (330) (e.g., LLM, LVM, or LMM). The prompt design component (321) 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 (321) can access user preference data (343), a prompt library (341), and a knowledge component including prompt examples based on the user input to generate a prompt, and can transmit the generated prompt to the generative AI model (330), which is an LLM or LMM.

[0051] The API / plugin management component (323) may communicate with external information when a request for additional information is made when passing user input as input to the generative AI model (330). The API / plugin management component (323) establishes a channel for communicating with the outside of the AI ​​interface through the API, and enables access to various data sources (e.g., knowledge repositories (345)) through the established channel.

[0052] The API / plugin management component (323) may request the application / service component (323) to perform an action that ultimately requires user input, rather than an intermediate result, through an API when the action needs to be performed by the application or service. Information obtained from an external source may be used to generate a prompt in the prompt design component (321) along with user input, or may be passed as input to a generative AI model (330).

[0053] The output tuning component (325) (also referred to as a refiner component) can fine-tune or reprocess the output from the generative AI model (330). The output tuning component (325) can verify, for example, whether the content generated by the generative AI model (330) is irrelevant, biased, or harmful. The output tuning component (325) can determine to what extent the content matches the user's desired result and, if additional processing is required, can proceed with the process. The output tuning component (325) can additionally configure and provide the user with hints to avoid unwanted output.

[0054] A generative AI model (330) may generally refer to an AI neural network that creates new types of data based on user input information. A generative AI model (330) may include a model that generates images and / or a model that generates language. The model that generates images may include, for example, a generative adversarial network (GAN) or a variational autoencoder (VAE). The model that generates images may be, for example, a diffusion-based AI model that uses a VAE and a transformer structure. The model that generates language may be a model trained to output the most statistically appropriate output value based on input values. Representative examples include models such as CHAT-GPT 3 and CHAT-GPT 4. In addition, there is also an LMM as an AI model (330) that can recognize various types of data input, such as text, images, voice, and video, and generate new data corresponding thereto.

[0055] According to one example, the electronic device (100) may include a natural language recognition module, a natural language processing (NLP) module, or a planner module for conducting a conversation with a user using natural language. The NLP module may be an AI model that has been pre-trained to enable the machine called the electronic device (100) to conduct a conversation with a user using natural language. The NLP module may be, for example, a software module implemented by executing instructions by at least one processor (e.g., the processor (110) of FIG. 2). Hereinafter, operations performed by the NLP module may be referred to as operations that may be caused to be performed by the electronic device (100) when the instructions are individually or collectively executed by at least one processor (110). The NLP module may, for example, obtain a character recognition result (e.g., data converted from one or more phonemes included in a sentence input by a user). The NLP module may provide a processing result of the character recognition result to the planner module. The processing result according to character recognition may include an intent, a target device (e.g., information about the target device), a capsule, or a combination thereof.

[0056] For example, an NLP module can determine a user's intent by interpreting a natural language recognition result (e.g., syntactic analysis and / or semantic analysis). A natural language understanding model can use linguistic features (e.g., grammatical elements) of morphemes or phrases to understand the meaning of words extracted from the natural language recognition result, and determine the user's intent based on the meaning of the understood words and / or other parameters (e.g., domains or categories associated with the words). Grammatical analysis may include dividing user input (e.g., user's text input) into grammatical units (e.g., words, phrases, and / or morphemes) and identifying grammatical elements of the divided units. Semantic analysis may be performed through semantic matching, rule matching, and / or formula matching. Here, data converted from one or more phonemes may represent one or more words included in a sentence input by the user, and / or tokens of each of one or more words. An intent can be data used by a natural language platform to generate a plan. An intent can include a goal and / or parameters. A goal can be used by the planner module to specify the final goal of the plan. A parameter can be a value input to one or more actions included in the plan.

[0057] Figure 4 is a configuration diagram of a stress management system (400) according to one embodiment.

[0058] In the present disclosure, which will be described with reference to FIG. 4, the stress management system (400) may obtain stress factors and / or events that become factors based on a personalized stress model, and provide a service for managing the user's stress at an appropriate time with a topic suitable for managing the user's stress. The stress management system (400) may be included in or executed by an electronic device (e.g., the electronic device (100) of FIG. 1). According to an example, the stress management system (400) may be an intelligent AI model that is generated and pre-trained for the user's stress management. For example, the stress management system (400) may prepare a generative AI model for managing the user's stress, and select an appropriate subject at an appropriate time to provide a conversation with the user. The stress management system (400) may train the generative AI model so that the generative AI model can be optimized for the user by applying information obtained through the conversation to the generated generative AI model. Through this, the stress management system (400) can manage the user's stress level in daily life, and as experiences overlap, improved stress management can be achieved through background knowledge about the user that is fed back through the service. In one example, the stress management system (400) may be an intelligent AI model that has been created and pre-trained to manage the user's stress.

[0059] In one example, the stress management system (400) may correspond to an AI system (e.g., the AI ​​system (200) of FIG. 2) for providing customized care regarding stress management of a user in an on-device environment by an electronic device (100). For example, the stress management system (400) may generate one or more AI models for providing customized care regarding stress management in an on-device environment, or may perform pre-training. The AI ​​system (200) may include, for example, one or more AI models, each of which may perform a unique instantiation.

[0060] In one example, the stress management system (400) may correspond to an AI system (e.g., the AI ​​system (200) of FIG. 2), such as a large model (e.g., LLM) for providing customized care regarding stress management of a user in a cloud environment. For example, the stress management system (400) may generate or pre-train one or more AI models for providing customized care regarding stress management in a cloud environment. The AI ​​system (200) may, for example, include one or more AI models, each capable of performing a unique instantiation.

[0061] For example, the stress management system (400) can identify a user's stress level and perform stress management to alleviate chronic stress. For example, if the stress management system (400) determines that the user's stress level is high, it can initiate a conversation at an appropriate time to reduce the user's stress level using a conversation topic that matches the cause inferred to be causing the high stress. The appropriate timing may be determined by a time and place where the user can comfortably converse, such as on a day when the user's stress level is particularly high. The conversation topic that matches the cause of the stress may be generated based on background knowledge about the user based on the time of the user's stress onset. In this way, the stress management system (400) can relieve the user's tension and reduce their stress level based on personalized timing and conversation topics.

[0062] According to one example, the stress management system (400) may include a collection module (410), an analysis module (420), a mapping module (430), an extraction module (440), a processing module (450), and / or a storage module (460). Each of the collection module (410), the analysis module (420), the mapping module (430), the extraction module (440), the processing module (450), and / or the storage module (460) included in the stress management system (400) may be implemented by at least one AI model.

[0063] The collection module (410) included in the stress management system (400) can collect various types of emotional data related to the user's mental health as available data. Emotional data can be an important factor that can affect human mental health. For example, emotional data can include data closely related to the user's stress, such as emotion, sentiment, and / or mood. Emotion can refer to a mental and / or physiological emotional state, such as temporary anger, fear, joy, sadness, and / or surprise, caused by a relatively strong, short-term, and persistent stimulus. Emotion can be, for example, related to mood, temperament, and / or personality as a subjective experience. Affect or mood can refer to a mental and / or physiological emotional state, such as exhilaration or depression, caused by a relatively weak, persistent stimulus, although not direct.

[0064] According to an example, the collection module (410) may include a biometric data collection module (411), a movement data collection module (413), or a personal data collection module (415). The collection module (410) may collect data related to the user's stress (hereinafter referred to as "available data"). The available data may include at least one piece of information that may influence the user's stress or predict the level of stress. The available data may include, for example, at least one of biometric data, reaction data, or personal data.

[0065] The biometric data collection module (411) included in the collection module (410) can collect biometric data related to the user's stress. The biometric data may be data regarding various types of physiological responses exhibited by the user according to emotional states such as emotions, moods, and / or feelings. The biometric data may be one of the vital activities occurring inside the body, and may be an electrical signal in the form of current or voltage generated by nerve cells or muscle cells. The biometric data may be data related to the user's biometric characteristics that may change due to stress, such as, for example, heart rate (HR), heart rate variability (HRV), electroencephalogram (EEG), electrocardiogram (ECG), skin conductance, electrooculogram (EEG), electromyogram (EMG), magnetoencephalogram (MEG), pulse, blood pressure, heartbeat sound, stress index, or oxygen saturation. For example, the collection module (410) can collect / acquire available data using at least one sensor (e.g., the sensor (170) of FIG. 1 or the sensor module (1376) of FIG. 13). For example, the collection module (410) can collect / acquire available data through at least one external electronic device (e.g., the electronic device (1302) of FIG. 13). The at least one external electronic device (1302) can be a wearable device and / or a hearable device. The wearable device and / or hearable device can be worn by a user on the wrist, finger, or head to measure data related to biological responses or movements. The wearable device can include a smart watch or a smart ring. The hearable device can include a smart headset or a virtual reality (VR) headset. For example, the stress management system (400) can collect / acquire available data through at least one sensor (1376) and at least one external electronic device (1302).

[0066] The movement data collection module (413) included in the collection module (410) can collect response data related to the user's behavior related to stress. For example, the collection module (410) can collect data on movements corresponding to actions such as throwing an object, swinging an arm, or kicking a foot as response data. The collection module (410) can collect response data on behaviors that may change due to stress, such as gait, walking speed, running speed, sleep, or exercise intensity. The collection module (410) can obtain the response data from various types of sensors. The collection module (410) can collect data on movements during daily life through at least one sensor (1376), a wearable device, and / or a hearable device. The collection module (410) can collect language data that may change due to stress, such as intonation, word usage, trembling, or speech rate when speaking for a call or conversation. The collection module (410) can collect text data that may change due to stress, such as sentence structures or word usage input by a user in an application that provides services such as chatting, text transmission, or memo. The collection module (410) can obtain voice data from the user's voice input through a microphone provided in the electronic device (100). The collection module (410) can obtain text data from characters input through an input means (e.g., a touch panel, a keypad) provided in the electronic device (100).

[0067] The personal data collection module (415) included in the collection module (410) can collect personal data about the user, such as age, occupation, or family relationships. The personal data collection module (415) can update the personal data based on information obtained through conversations with the user, depending on the stress management service. For example, the personal data collection module (415) can collect personal data, such as the user's personal music or exercise preferences, personality traits of preferred individuals, or favorite foods.

[0068] The collection module (410) can acquire creative data. The creative data may be data related to records (e.g., photos, videos, or diaries) that may reflect the user's emotional state, such as emotions, sentiments, and / or moods. The collection module (410) can acquire creative data from an application (e.g., a gallery application) running on the electronic device (100) that can create creative works, such as photos, videos, or writings.

[0069] The analysis module (420) included in the stress management system (400) can analyze available data collected by the collection module (410) to model a personalized stress model, obtain a user's stress level in real time (hereinafter referred to as 'real-time stress level'), or obtain data related to a situational event that may affect the user's stress level (hereinafter referred to as 'event situation data').

[0070] The analysis module (420) can analyze and / or process the available data collected by the collection module (410) to determine the user's stress level and create a personalized stress model based on the data. The analysis module (420) can create a personalized stress model by modeling the user's stress level that changes over a specific time period. For example, the personalized stress model can be created daily, daily, or monthly. The following description will assume a daily (24-hour) personalized stress model for convenience, but is not necessarily limited thereto. The analysis module (420) can continuously monitor the user's stress level and determine whether the real-time monitored stress level corresponds to an abnormal event based on the personalized stress model. For example, the analysis module (420) can determine that an abnormal event has occurred when the real-time stress level deviates from a stress level that can be expected based on the personalized stress model by exceeding a threshold level. In one example, the analysis module (420) may include a stress modeling module (421), a real-time stress tracking module (423), or an event detection module (425).

[0071] The stress modeling module (421) included in the analysis module (420) can create a personalized stress model for the user. For example, the stress modeling module (421) can create a stress model (hereinafter referred to as a “personalized stress model”) that models the user’s stress trend that changes over time. The stress management system (400) can, for example, create a personalized stress model by modeling changes in stress levels by time zone (hereinafter referred to as “real-time stress levels”) over time. The personalized stress model can model stress levels by reflecting the user’s characteristics by day of the week, hour of the day, or a longer period. The personalized stress model modeled in this way can be utilized to check the user’s stress trend and level. The stress management system (400) can improve the personalized performance of the personalized stress model based on the result data obtained through the stress management service for the user.

[0072] For example, the stress modeling module (421) can create a personalized stress model by modeling the user's stress level based on the real-time stress level accumulated over time during a modeling period (e.g., 24 hours (0:00 to 24:00)). For example, if there is a periodic change in stress level depending on the time zone, the stress modeling module (421) needs to first determine the real-time stress level at that time. For example, it can be assumed that the real-time stress level has a pattern of being high between 9:00 and 12:00 every day, decreasing between 12:00 and 1:00, and then increasing again between 1:00 and 5:00. For example, even if the stress level is detected to be slightly higher than usual around 11:00, which is a time zone when the stress level is usually high, it is difficult to definitively conclude that the user's stress level is high. Rather, a situation where a stress level of around 70 is detected at approximately 12:30, which is a time zone when the stress level is usually low, can be determined to be a stressful situation. In the personalized stress model, the user's usual stress is quantified and modeled based on the user's stress level accumulated to date.

[0073] As described above, the generated personalized stress model can monitor stress trends over time within the model section. For example, the personalized stress model can be used as a basis for determining whether a user's stress level, which can be monitored in real time through the collection module (410), is relatively high or low compared to normal. The personalized stress model can become more accurate as the user's stress level is measured more frequently.

[0074] The real-time stress tracking module (423) included in the analysis module (420) can estimate the user's stress level by quantifying the user's real-time stress level based on the available data acquired through the collection module (410). The available data considered for quantifying the user's real-time stress level may include, for example, biometric data, reaction data, or personal data collected by the biometric data collection module (411), the movement data collection module (413), or the personal data collection module (415) included in the collection module (410). The real-time stress level estimated by the real-time stress tracking module (423) can be utilized to determine the user's stress state by comparing it with a personalized stress model generated by the stress modeling module (421).

[0075] The real-time stress tracking module (423) can predict and / or infer a real-time stress level closely related to a user's emotional state or mental health state based on, for example, biometric data collected by the biometric data collection module (411). For example, to analyze biometric data, the real-time stress tracking module (423) can apply an AI model trained based on deep learning and / or machine learning. As an example, the real-time stress tracking module (423) can analyze biometric data to extract keywords for inferring a user's real-time stress level.

[0076] The real-time stress tracking module (423) can predict and / or infer the user's real-time stress level based on, for example, the reaction data collected by the movement data collection module (413). The reaction data may include, for example, data regarding the characteristics of language, such as words used in speech, intonation, or tremors. The reaction data may include, for example, data regarding the characteristics of characters, such as words used in characters input by the user through a specific application, or sentence structure. For example, the real-time stress tracking module (423) may apply an AI model trained based on deep learning and / or machine learning to analyze the reaction data. For example, the analysis module (420) may analyze the reaction data to extract keywords for inferring the stress level.

[0077] For example, the real-time stress tracking module (423) can determine a reference stress level based on an average of real-time stress levels acquired over a predetermined time period. The real-time stress tracking module (423) can acquire a stress level based on, for example, heart rate (HR) and heart rate variability (HRV), which can change over time. The real-time stress tracking module (423) can detect the occurrence of an abnormal situation by comparing the reference stress level determined for each predetermined time period with the average stress level acquired over the same time period in a personalized stress model.

[0078] The real-time stress tracking module (423) can detect an abnormal situation based on the real-time stress level. For example, the stress management system (400) can detect the occurrence of an abnormal situation based on the user's real-time stress level, which may change due to a situational event. The stress management system (400) can detect the occurrence of an abnormal situation based on the result of comparing the real-time stress level with a personalized stress model. For example, the stress management system (400) can determine that an abnormal situation has occurred when the real-time stress level falls outside the range predictable by the personalized stress model. The stress management system (400) can determine that an abnormal situation has occurred when a situation occurs in which the real-time stress level changes abnormally. For example, the stress management system (400) can determine that an abnormal situation has occurred if the real-time stress level is maintained above a specific threshold level for a certain period of time (e.g., 10 minutes). For example, the stress management system (400) may determine that an abnormal situation has occurred if the average real-time stress level continues above a certain threshold level for a certain period of time (e.g., 30 minutes).

[0079] The real-time stress tracking module (423) can obtain situation data (hereinafter referred to as “abnormal situation data”) in response to an abnormal situation. For example, the stress management system (400) can obtain time information corresponding to the time or time period when the abnormal situation is detected as abnormal situation data. For example, the stress management system (400) can obtain information corresponding to the place and / or location where the abnormal situation is detected as abnormal situation data. For example, the stress management system (400) can obtain information related to the user’s behavior in an abnormal situation as abnormal situation data. For example, the stress management system (400) can obtain information about the other party the user was dealing with in the abnormal situation as abnormal situation data. In the above description, information that can be obtained as abnormal situation data is listed in fragments, but the stress management system (400) can also obtain a combination of at least two of the listed pieces of information as abnormal situation data.

[0080] As described above, the real-time stress tracking module (423) can classify a stress situation, i.e., an abnormal situation, when the real-time stress level acquired at a specific time period is abnormally high compared to the usual stress level acquired from the personalized stress model, or when an absolutely high level persists for a certain period of time. For example, if the user's real-time average stress level is 90 or higher for a certain period of time or is 30 or higher than the usual average stress level, the real-time stress tracking module (423) can determine that it is an abnormal situation. At this time, the certain period of time can be, for example, 30 minutes set as a standard time for collecting health data in a specific application. The real-time stress tracking module (423) can classify a stress situation if the user's real-time stress level gradually increases or remains high for 30 minutes. The user's stress level can be set in consideration of the user's personal characteristics. The personalized stress model applied to detect the user's abnormal situation can be continuously updated by the stress modeling module (421) over time. This allows for the establishment of criteria for most accurately assessing a user's abnormal situation. If a situation in which the user's stress level is determined to be high persists for a certain period of time, the real-time stress tracking module (423) stores the time and / or location of the user's high real-time stress level, allowing it to be considered when determining conversation topics and timing.

[0081] The event detection module (425) included in the analysis module (420) can detect the occurrence of specific situational events that may affect the user's stress level. Specific situational events may include, for example, situational events such as class, work, meeting, exam, exercise, game, conversation, meal, or sleep. The event detection module (425) can detect the occurrence of an event based on available data collected by the collection module (410) from at least one internal sensor (e.g., sensor (170) of FIG. 1 ), a wearable device, a hearable device, or at least one application. For example, available data to be considered for detecting the occurrence of an event may include data estimating the location of the user, the people with whom the user is present, or the actions performed. The event detection module (425) can detect the occurrence of an event more specifically and accurately as the system becomes more personalized due to the user's frequent use.

[0082] For example, the event detection module (425) can predict the occurrence of a specific situational event based on sensing data from at least one sensor (1376) or data (e.g., schedule data) generated or managed by an application. For example, if a user is using a game application on the electronic device (100), the event detection module (425) can predict that the user is playing a game. For example, the event detection module (425) can predict that the user is currently taking a test based on scheduling information obtained from a specific application (e.g., a diary or calendar). For example, the event detection module (425) can predict that the user is currently meeting with a client based on scheduling information obtained from a specific application (e.g., a diary or calendar). For example, the event detection module (425) can predict that the user is currently working based on day of the week and time information. For example, the event detection module (425) can predict that the user is exercising, such as jogging or swimming, based on biometric data obtained from at least one sensor (1376). For example, the event detection module (425) can extract and analyze natural language from ambient noise acquired from at least one sensor (1376) to predict that the user is shopping at a department store. For example, it can be assumed that the user has saved "Itaewon lunch appointment" on the calendar. In this case, the event detection module (425) can activate Bluetooth when the user arrives near Itaewon during the day based on the global positioning system (GPS) location to identify the companion who is closest to the user and has been with the user for the longest time. The event detection module (425) can obtain more accurate results as personalized results are achieved based on the feedback provided based on the stress management service.

[0083] The event detection module (425) can obtain event situation data related to a specific detected situation event. For example, the event detection module (425) can obtain information related to the time, time period, location, position, or person encountered when the specific situation event is detected as event situation data corresponding to the specific situation event. For example, the event detection module (425) can obtain time information corresponding to the time or time period when the specific situation event is detected as event situation data. For example, the event detection module (425) can obtain information corresponding to the place and / or position where the specific situation event occurred as event situation data based on location information where the specific situation event is detected. For example, the event detection module (425) can obtain information related to the user's behavior at the time or time period when the specific situation event is detected as event situation data. For example, the event detection module (425) can obtain information about the other party the user was interacting with in relation to the specific situation event as event situation data.

[0084] In one example, the event detection module (425) can identify people encountered by the user through a communication circuit (160) included in the electronic device (100) (e.g., a short-range communication network such as Bluetooth, WiFi (wireless fidelity) direct, or IrDA (infrared data association)). Through this, the event detection module (425) can obtain event situation data based on information about people encountered by the user.

[0085] For example, the event detection module (425) can sense the user's movements via the sensor (170) and determine whether the user is performing a specific activity. For example, if the user is detected running, the event detection module (425) can determine that a running event has occurred at that point in time.

[0086] For example, the event detection module (425) can obtain user event information from various applications used by the user. For example, the event detection module (425) can obtain information regarding content viewing by the user through a video service application (e.g., YouTube or Netflix). For example, the event detection module (425) can obtain information regarding what events occurred to the user at a specific time based on information entered by the user through a schedule management application (e.g., diary and calendar).

[0087] The mapping module (430) included in the stress management system (400) can store event mapping data corresponding to a specific situational event. For example, the mapping module (430) can map the event situation data obtained in response to a specific situational event to the real-time stress level obtained in response to the specific situational event and store the mapped data as event mapping data in a specific storage space. The event mapping data can associate an event situation currently occurring to the user with a stress level. For example, when a specific situational event occurs, the mapping module (430) can store event mapping data linking the real-time stress level with the specific situational event in the storage space. All event mapping data can basically be stored together with the stress level when the specific situational event first occurs.

[0088] For example, if a specific situational event is repeated at a specific time or the acquired real-time stress level remains constant each time a specific situational event occurs, the reliability of the stress level for the specific situational event can be improved. In this case, the mapping module (430) can store event mapping data corresponding to the specific situational event separately from event mapping data for stress levels with relatively low reliability.

[0089] More specifically, the mapping module (430) can classify and store event mapping data by considering whether the situation event persists. For example, the mapping module (430) can assign a relatively high priority to a persistent situation event and a relatively low priority to a non-persistent situation event. A persistent situation event may be, for example, an event that can have a positive or negative impact on a user's stress on an ongoing basis, such as work or study. A non-persistent situation event may be, for example, a one-time event that can have a positive or negative impact on a user's stress, such as exercise, a game, an exam, a presentation, or a meeting. The mapping module (430) can store event mapping data assigned a high priority in a storage space assigned a relatively high importance. The mapping module (430) can store event mapping data assigned a low priority in a storage space assigned a relatively low importance. For example, the importance of a storage space may be classified based on the level of security or ease of access. Event mapping data may be stored only on the device and may not be uploaded to a cloud server to prevent personal information leakage. For example, a user's stress level may be significantly reduced immediately after exercising at 7 PM. If this event occurs only once, the mapping module (430) may record the event mapping data as "Low stress immediately after exercising at 7 PM" in the default storage space. However, if this event occurs repeatedly, such as three times a week, the mapping module (430) may record the event mapping data as "Low stress immediately after exercising at 7 PM" in a storage space with a relatively high priority.Event mapping data stored in a relatively high-importance storage space can be considered to have a high level of reliability between the corresponding situational event and stress level due to relatively high repetition.

[0090] For example, event mapping data, which correlates real-time stress levels with specific situational events via the mapping module (430), can be utilized to identify the cause of an abnormal event. The event mapping data can also be utilized to determine recommended activities to alleviate user stress in response to the occurrence of an abnormal situation.

[0091] The extraction module (440) included in the stress management system (400) may, when an abnormal situation is detected, determine a conversation topic and / or an appropriate timing for attempting to have a conversation with the user to alleviate the stress level according to the abnormal situation. In one example, when the abnormal situation is detected by the real-time stress tracking module (423), the extraction module (440) may determine a personalized conversation topic and / or conversation timing for the user's stress management based on the correlation between the situational event corresponding to the abnormal situation and the personalized stress model. In one example, the extraction module (440) may include a topic determination module (441) or a timing determination module (443).

[0092] The topic determination module (441) included in the extraction module (440) can select a conversation topic to use in generating a conversation to alleviate stress when an abnormal situation is detected. For example, the topic determination module (441) can infer the cause of stress by considering the time and location of the abnormal situation where the user's stress level was high, and determine a conversation subject based on the results.

[0093] For example, the topic determination module (441) can analyze the event mapping data stored by the event detection module (425) based on the time and location at which the abnormal situation is detected, and infer the cause of stress corresponding to the abnormal situation based on the analysis result. The topic determination module (441) can extract event situation data corresponding to the abnormal situation data from the event mapping data stored in advance. The stress management system (400) can infer the cause of stress that caused the abnormal situation by further considering the extracted event situation data. The stress management system (400) can determine a more appropriate conversation topic to stabilize stress by further considering the event mapping data prepared in advance and inferring the cause of stress.

[0094] As described above, if the topic determination module (441) determines an abnormal situation, it can infer the cause of stress based on the time and location at that point in time and the user's previous data, and determine a conversation topic related to the inferred cause of stress. The user's previous data may include data such as the user's age, family relationships, occupation, and stressors from previous conversations. The more conversations the user has with the user, the more information and accuracy the user's previous data has, making it increasingly personalized. Here, personalization may mean diversifying or improving the accuracy of the user's previous data that the topic determination module (441) considers to infer the cause of stress. For example, information such as hobbies, work, or address may be added to the user's previous data. For example, the user's previous age data may be updated. For example, if the user is stressed at work on Tuesday at 2:00 PM, the cause of stress may be inferred to be work-related. Alternatively, if the user is stressed at home on Saturday at 8:00 PM, the cause of stress may be inferred to be family and / or household chores.

[0095] For example, prior to personalization, the topic determination module (441) can determine a conversation topic based solely on location information and / or time information. For example, if a record indicates that stress was measured high near ** Station at 00:00 on 00 / 00, the topic determination module (441) can determine a conversation topic to start the next conversation by asking the user if they had a difficult time at that time and place. As the user talks about what happened on that day, the stress management system (400) can connect various times and places. For example, if the user talks about having a burdensome report at work that day, the stress management system (400) can infer that the location is likely the user's workplace. As conversations with the user are repeated, the topic determination module (441) can understand the user's basic living radius or activity cycle, and can provide more appropriate conversation topics to the user based on previous stressors. Basically, the topic determination module (441) can infer the cause of stress based on various data at the time of the stressful situation. However, if there is event mapping data stored in a high importance storage space in the mapping module (430), a more accurate conversation topic can be derived by using the corresponding situation event and the reliability of the corresponding situation event as input.

[0096] For example, prior to personalization, the topic determination module (441) may, if an event that positively impacts the user's stress level occurs, consider the event when determining a conversation topic when talking with the user. For example, if the stress index stabilized during a friend gathering at ** restaurant at 00:00 on 00 / 00, the topic determination module (441) may determine that the event had a positive impact on the stress index and determine a conversation topic based on information about the event.

[0097] For example, prior to personalization, the topic determination module (441) may generate a prompt related to a determined conversation topic. The topic determination module (441) may transmit the generated prompt to the processing module (450). The processing module (450) may be a generative AI model, such as an LLM, capable of processing the prompt. It may be important that the conversation generated by the processing module (450) in response to the prompt not only generates a conversation log on a specific topic, but also aims to reduce the user's stress. To this end, the topic determination module (441) may prompt not only the conversation topic but also stress response values ​​for the conversation topic. For example, the topic determination module (441) may digitize the user's stress level and event-related values, and generate a prompt to select a conversation topic determined based on the data. For example, the topic determination module (441) may issue a command to the processing module (450), such as "Generate a conversation to reduce the user's stress." For example, the topic determination module (441) can generate a prompt to be provided to the processing module (450), such as “Find an event that occurred when the user’s stress level was high and select it as a conversation topic” or “Recommend an event that occurred when the user’s stress level was low to lower the user’s stress level.”

[0098] Table 1 below shows an example of mapping situational events and stress levels.

[0099] Event Stress LevelsWork CallsHigh Mobile GamingLow RunningVery Low… ..… .

[0100] According to the above , the topic determination module (441) can generate prompts to determine conversation topics and suggestions that reflect situational events that caused high stress and situational events that could maintain relatively low stress levels. For example, the topic determination module (441) can determine conversation topics that can lead to a conversation about what stressed the user out during a work call, reflecting that the user's stress level was high during a work call. The topic determination module (441) can request the processing module (450) to suggest situational events (e.g., mobile games or running) that had a low stress level during the conversation with the user. For example, if the conversation timing is set to immediately after the end of a work call, the topic determination module (441) can request the processing module (450) to recommend running, a situational event mapped to a very low stress level, during the conversation with the user.

[0101] The timing determination module (443) included in the extraction module (440) can determine the timing for initiating a conversation with the user on a determined topic. It may be desirable to initiate a conversation with the user at a time when the conversation can be conducted efficiently on the determined topic, rather than immediately upon determining the topic. To this end, the timing determination module (443) may determine the timing for the conversation based on the user's current location, movements, and / or usual lifestyle patterns. For example, the timing determination module (443) may also determine an efficient timing by considering the user's events and stress fluctuations.

[0102] For example, the timing determination module (443) can determine a suitable time for conversation based on the user's usual lifestyle patterns, such as the current time, the user's current location, whether the user is moving, and the user's wake-up or bedtime. For example, if a user whose bedtime is expected to be 12:00 AM is not moving at home at 11:00 PM, the timing determination module (443) can determine that the current time is an appropriate time for conversation. For example, if a user whose bedtime is not regular is moving a lot in a place other than home at 11:00 PM, the timing determination module (443) can determine that the current time is not an appropriate time for conversation. The timing determination module (443) can determine a conversation timing based only on simple information, such as simple location information, time information, or movement information, before personalization. If a user is resting still in a space presumed to be home at 11:00 PM, a time generally considered to be a time for resting at home, the timing determination module (443) can determine that the current time is an appropriate time for attempting a conversation with the user. As this becomes personalized, the timing determination module (443) can be trained to initiate conversations at times that suit each individual's lifestyle and preferences. If the timing is determined to be appropriate for conversation, the timing determination module (443) can call the processing module (450) and request the user to engage in a conversation using text-to-speech (TTS).

[0103] For example, when determining the timing of a conversation, the timing determination module (443) may trigger a conversation attempt in response to simple situations such as “when the user is resting and has low real-time stress” or “when the user’s real-time stress level has increased sharply”, or may operate as a prompt. For example, when operating using a prompt, the timing determination module (443) may configure the prompt as follows: “Refer to a conversation in which the user’s satisfaction level was high among previous conversation records and determine the conversation timing by referring to a conversation in which the user’s stress level was the lowest among previous conversation records and determine the conversation timing.”

[0104] The processing module (450) included in the stress management system (400) can conduct a conversation with a user on a conversation topic determined by the topic determination module (441) at a timing determined by the timing determination module (443). The processing module (450) may, for example, attempt to engage in a conversation with the user to lower the user's stress level related to a specific situational event. In one example, the processing module (450) may include a feedback module (451).

[0105] For example, if the processing module (450) determines that a conversation is in progress, it may provide the user with a notification for conversation at that point. The processing module (450) may conduct a conversation with the user using TTS. Before conducting an actual conversation with the user, the processing module (450) may inquire about the user's availability for conversation, permission regarding the conversation topic, or a change in the conversation topic. The processing module (450) may, for example, convey the inquiry to the user using a voice assistant, an interface within the application, or a voice call.

[0106] The feedback module (451) included in the processing module (450) can analyze the conversation with the user and transmit new data acquired so that it can be reused by the topic determination module (441) or the timing determination module (443). The data transmitted by the feedback module (451) may include, for example, data related to the accuracy of the inferred conversation timing and / or conversation topic. The data transmitted by the feedback module (451) may be used by the topic determination module (441) or the timing determination module (443) to improve the degree of personalization. The feedback module (451) can update existing data based on the newly acquired data acquired by the processing module (450) through analysis of the conversation with the user.

[0107] For example, the processing module (450) may engage in a conversation with a user about a stressful situation with the goal of alleviating the user's stress. During the conversation, the processing module (450) may provide answers obtained through questions about the user's likes and dislikes to be used to improve the relevant AI model to increase the accuracy of future conversation topics and timing. Based on event mapping data stored in a storage space with relatively high importance by the mapping module (430), the processing module (450) may suggest stress-reducing measures (e.g., jogging) to the user through the conversation. For example, if the user's stress level decreases every time they activate the YouTube app, the processing module (450) may suggest watching YouTube during the conversation with the user. In this case, the persona of the model conducting the conversation may vary depending on the user.

[0108] For example, the processing module (450) can analyze the conversation with the user to identify the user's preferred conversation partner and change the conversation style based on the identified results. For example, for a user who desires a high level of empathy, the processing module (450) can increase the frequency of empathy during the conversation. For example, for a user who demands realistic solutions, the processing module (450) can change the conversation style from a simple empathetic dialogue to one that presents a variety of possible alternatives to solve the problem.

[0109] For example, the personalization of the stress management system (400) can be achieved through data fed back by the feedback module (451). During or after a conversation, the feedback model (451) can check the user's stress level in real time and provide feedback on changes in the user's stress level in response to the conversation content. In this case, the AI ​​model that processes the conversation with the user can be personalized to optimize the user. For example, if the user's stress level increases due to continuous inquiries about a specific issue, the processing module (450) can determine that the user feels burdened by being asked questions about the specific issue and focus on expressing empathy and providing answers.

[0110] For example, the feedback module (451) may feed back the user's response to the query of the processing module (450) to the topic determination module (441) and / or the timing determination module (443). For example, if the user answers that they are unable to have a conversation in response to the query of the processing module (450) inquiring about their availability for conversation, the feedback module (451) may feed back to the timing determination module (443) that a timing adjustment is necessary. In this case, the timing determination module (443) may lower the importance of the time zone corresponding to the timing. For example, if the user answers that they are able to have a conversation in response to the query of the processing module (450) inquiring about their availability for conversation, the feedback module (451) may feed back to the timing determination module (443) that a conversation will proceed at the timing. In this case, the timing determination module (443) may increase the importance of the time zone corresponding to the timing. For example, if the user responds to the query of the processing module (450) regarding the appropriateness of a conversation topic by stating that the conversation topic is inappropriate for the stressor, the feedback module (451) may feedback to the topic determination module (441) that the conversation topic should be moved to a storage space with a lower importance. In this case, the topic determination module (441) may move the storage location of the conversation topic to a storage space with a lower importance than the current importance and lower the importance of the conversation topic. For example, if the user does not respond to the conversation request of the processing module (451), the feedback module (451) may transmit a request corresponding to the reason for the user's refusal of the conversation to the topic determination module (441) or the timing determination module (443). For example, if the reason the user refused the conversation was due to timing, the feedback module (451) may feedback to the timing determination module (443) that timing adjustment is necessary.In this case, the timing determination module (443) can adjust the importance of the time zone corresponding to the timing downward, thereby avoiding selection of the timing in subsequent conversation attempts. This is to reduce the possibility of rejection by the user. For example, if the reason the user declined the conversation was due to the conversation topic, the feedback module (451) can feedback to the topic determination module (441) to move the conversation topic to a storage space with a lower importance. In this case, the topic determination module (441) can move the storage location of the conversation topic to a storage space with a lower importance than the current importance and lower the importance of the conversation topic, thereby avoiding selection of the conversation topic in subsequent conversation attempts. This is to reduce the possibility of rejection by the user.

[0111] For example, if the processing module (450) acquires new personal data about the user while conducting a conversation with the user, the feedback module (451) may update the user data with the acquired personal data. The personal data may include, for example, personal data about the user, such as the user's family relationships, residence, workplace, and close acquaintances. For example, updating the user data with personal data may be performed by the personal data collection module (415) included in the collection module (410).

[0112] For example, when the processing module (450) obtains data about the user's preferred conversation partner (e.g., conversation style) while conducting a conversation with the user, the feedback module (451) can update the obtained data about the preferred conversation partner.

[0113] For example, if the processing module (450) conducts a conversation with a user and the user responds late, fails to respond, or shows signs of discomfort, the processing module (450) may identify the user's discomfort in the conversational style. Upon receiving a response from the user, the processing module (450) may reduce the weight of the factors deemed to require resolution.

[0114] As described above, judgments regarding conversation topics and / or timing may be based on monitoring changes in the user's stress level. For example, even if the user is interested in a conversation topic, if the timing is poor, the stress-lowering effect of the conversation may be reduced. Therefore, determining the timing of conversation on that topic can aid in stress management. In addition to providing the user with direct feedback on the conversation from the AI ​​module, the stress management system (400) may be able to continuously personalize conversation topics and timing based on changes in the user's stress level.

[0115] The storage module (460) included in the stress management system (400) can store biometric data, behavioral data, personal data, and / or creative data collected by the collection module (410). The storage module (460) can store a stress model generated by the stress modeling module (421) of the analysis module (420). The storage module (460) can store data on real-time stress levels and / or abnormal situations acquired by the real-time stress tracking module (423) of the analysis module (420). The storage module (460) can receive event mapping data from the event detection module (425) of the analysis module (420) and store the data in consideration of importance. The storage module (460) can store conversation topics determined by the topic determination module (441) of the extraction module (440) in consideration of importance. The storage module (460) can store timing data determined by the timing determination module (443) of the extraction module (440) in consideration of importance.

[0116] For example, the event detection module (425) that detects situational events occurring to the user can be expanded into a recommendation service. For example, the mapping module (430) can generate event mapping data by linking situational events to real-time stress levels. In this case, the event detection module (425) can use the event mapping data to distinguish between preferred and unpreferred events for the user. The user's preferences can be used as input for recommendation algorithms in various services. For example, based on the user's preferences, the electronic device (100) can display content of interest to the user on the main screen of a portal. Alternatively, the electronic device (100) can recommend applications preferred by people with similar tastes to the user based on the user's preferences. The electronic device (100) can also use the user's preferences to select a time point for providing the recommendation service to the user. The electronic device (100) can also provide a recommendation service that is relevant to the user's preferred conversation time zone and conversation topic based on the user's personal model.

[0117] For example, stress management services can be expanded and applied to various non-mobile devices as various form factors become more sophisticated. For example, using augmented reality (AR), it may be possible to visualize a model of a conversation within a stress management service as if it were a real conversation with a virtual character. To this end, the behavior proposed in this disclosure for inferring conversation topics and / or timing can be utilized. In addition to natural language, various senses can be integrated to immerse the user in the conversation. For example, the stress management system (400) can not only reduce the user's stress through conversation, but also manage or reduce the user's stress level by visualizing specific topics. Furthermore, a physical element for the stress management service can be added using a robot. This addition of a physical element can expand beyond suggesting alternatives through natural language to inducing movement. For example, the stress management service can be expanded to include stress relief solutions based on factors other than conversation, such as having a robot deliver necessary items during a conversation.

[0118] FIG. 5 is a control flowchart for providing a personalized stress management service in an electronic device (e.g., the electronic device (100) of FIG. 1) according to one embodiment.

[0119] 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.

[0120] The personalized stress management service proposed in FIG. 5 may be provided by a stress management system (e.g., the stress management system (400) of FIG. 4) that may be included in or executed by the electronic device (100). The stress management system (400) may correspond to an AI system (e.g., the AI ​​system (200) of FIG. 2) for providing customized care regarding mental health in an on-device environment by the electronic device (100). For example, the stress management system (400) may generate or pre-train one or more AI models for providing customized care regarding mental health in an on-device environment. The AI ​​system (200) may include, for example, one or more AI models, each of which may perform unique instantiation.

[0121] Referring to FIG. 5, the electronic device (100) may perform, in operation 510, creation and / or update of a personalized stress model. The electronic device (100) may monitor changes in a user's stress level to create a personalized stress model. The electronic device (100) may collect available data that may affect the user's stress. For example, the data collection operation may be performed by a collection module (410) included in a stress management system (e.g., the stress management system (400) of FIG. 4) running in the electronic device (100). According to an example, the electronic device (100) may collect the available data using at least one sensor (e.g., the sensor (170) of FIG. 1 or the sensor module (1376) of FIG. 13) and / or through an external electronic device (e.g., the electronic device (1302) of FIG. 13). Available data collected from at least one sensor (1376) and / or external electronic device (1302) may be data that can be referenced to measure the user's stress. For example, the available data may include biometric data, movement data, or schedule data.

[0122] The electronic device (100) can analyze and / or process collected available data to determine the user's stress level and create a personalized stress model based on this. The electronic device (100) can create a personalized stress model by modeling the user's stress level as it changes over a specific period of time.

[0123] For example, the electronic device (100) can generate a personalized stress model by modeling the user's stress trend that changes over time. For example, the electronic device (100) can generate a personalized stress model by modeling changes in real-time stress levels by time zone according to the passage of time. The personalized stress model can model stress levels by reflecting the user's characteristics by day of the week, hour of the day, or a longer period. The personalized stress model modeled in this way can be utilized to identify the user's stress trend and stress level. The electronic device (100) can improve the personalized performance of the personalized stress model based on the result data obtained through the user's stress management service.

[0124] In operation 520, if an event corresponding to an abnormal situation is detected, the electronic device (100) may analyze data regarding the abnormal situation to determine a conversation topic and / or an appropriate timing for attempting to engage in conversation with the user to alleviate the user's stress level. In one example, if an abnormal situation is detected based on a real-time stress level, the electronic device (100) may determine a personalized conversation topic and / or conversation timing for the user's stress management based on a correlation between a situational event corresponding to the abnormal situation and a personalized stress model.

[0125] According to one example, the electronic device (100) can detect the occurrence of an abnormal situation based on the user's real-time stress level. The electronic device (100) can estimate the user's stress level by quantifying the user's real-time stress level based on available data. The electronic device (100) can detect the occurrence of an abnormal situation based on the result of comparing the real-time stress level with a personalized stress model. For example, the electronic device (100) can determine that an abnormal situation has occurred when the real-time stress level is outside a range predictable by the personalized stress model. For example, the electronic device (100) can determine that an abnormal situation has occurred if the real-time stress level is maintained above a specific threshold level for a certain period of time (e.g., 10 minutes). For example, the electronic device (100) can determine that an abnormal situation has occurred if the average of the real-time stress level is maintained above a specific threshold level for a certain period of time (e.g., 30 minutes).

[0126] The electronic device (100) may, at operation 530, conduct a conversation with the user based on a specific conversation topic at a specific conversation point in time. For example, the electronic device (100) may conduct a conversation with the user using voice or text. The following description assumes that the electronic device (100) conducts a conversation with the user using text, but is not limited thereto. For example, the electronic device (100) may conduct a conversation with the user based on virtually any interaction method other than text, such as voice, and / or motion, such as gestures.

[0127] According to one example, the electronic device (100) may include a natural language recognition module, an NLP module, or a planner module for conducting a conversation with a user using natural language. The NLP module may be an AI model that has been pre-trained to enable the machine called the electronic device (100) to conduct a conversation with a user using natural language. The NLP module may be, for example, a software module implemented by executing instructions by at least one processor (e.g., the processor (110) of FIG. 2). Hereinafter, operations performed by the NLP module may be referred to as operations that may be caused to be performed by the electronic device (100) when the instructions are individually or collectively executed by at least one processor (110). The NLP module may, for example, obtain a character recognition result (e.g., data converted from one or more phonemes included in a sentence input by a user). The NLP module may provide a processing result of the character recognition result to the planner module. The processing result according to character recognition may include an intent, a target device (e.g., information about the target device), a capsule, or a combination thereof.

[0128] The electronic device (100) may, at step 540, analyze changes in the user's responses, conversation content, and / or stress level, and reuse the analysis results as input for generating conversation topics and / or determining timing for stress management, thereby performing learning to enhance the degree of personalization. The electronic device (100) may analyze the conversation content to acquire the user's intent and / or new user data. The electronic device (100) may use the user's intent and / or the newly acquired user data to update data for personalization.

[0129] FIG. 6 is a control flowchart for providing a personalized stress management service in an electronic device (e.g., the electronic device (100) of FIG. 1) according to one embodiment.

[0130] 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.

[0131] In the description with reference to FIG. 6 in the present disclosure, it will be described that an operation according to a control flow is performed by an electronic device (100), but with respect to which component the operation is performed, reference may be made to the description with reference to FIG. 4.

[0132] Referring to FIG. 6, the electronic device (100) may measure a real-time stress level, model a personalized stress model, or generate / store event mapping data in operations 611 to 617.

[0133] According to one example, the electronic device (100) may, in operation 611, measure the user's stress level in real time and accumulate the measured real-time stress level by specific time intervals (e.g., daily, weekly, monthly) to model a personalized stress model for the user. An example of the electronic device (100) accumulating the real-time stress level to model a personalized stress model will be described with reference to FIGS. 7A to 7C.

[0134] According to an example, the electronic device (100) may continuously measure a real-time stress level even after the personalized stress model is modeled in operation 613. For example, the electronic device (100) may measure the real-time stress level based on collected available data. The electronic device (100) may collect the available data by using, for example, at least one sensor (e.g., the sensor 170 of FIG. 1 or the sensor module 1376 of FIG. 13) and / or an external electronic device (e.g., the electronic device 1302 of FIG. 13). The available data collected from the at least one sensor (1376) and / or the external electronic device (1302) may include, for example, biometric information, exercise information, or schedule information. The electronic device (100) may measure the real-time stress level at specific time intervals. According to an example, the real-time stress level may be measured at specific time intervals. For example, the electronic device (100) can measure the real-time stress level at a specified time interval, such as 10 minutes, 30 minutes, or 1 hour. In one example, the real-time stress level can be measured at a relatively long time interval during a time period when stress changes are not severe, and can be measured at a short time interval during a time period when stress changes are severe. For example, the electronic device (100) can measure the real-time stress level at a time interval of 1 hour or more during a time period when stress changes are not severe (e.g., at night), and can measure the real-time stress level at a time interval of 10 minutes or 30 minutes during a time period when stress changes are not severe (e.g., during the day). Here, measuring the real-time stress level by dividing it into two time intervals is only an exemplary suggestion, and it would also be possible to measure the real-time stress level at different time intervals by dividing it into more time intervals.

[0135] According to an example, the electronic device (100) may, in operation 615, generate event mapping data in response to detection of a situational event and store the generated event mapping data in a user data storage space.

[0136] The electronic device (100) can determine the user's current situation using at least one sensor (170, 1376), at least one application, or at least one support function, and detect the occurrence of a situational event based on the determination. The electronic device (100) can acquire situational events related to the user's stress level in various ways. For example, the electronic device (100) can detect a situational event using data that can be provided by at least one application (e.g., a schedule management application, a workout management application). For example, the electronic device (100) can detect a situational event based on the usage time of an application that monitors the user's activity or an application used in a specific situation. For example, the electronic device (100) can detect a situational event corresponding to the user monitoring his / her running status through a health application or watching specific content through an application that provides video content. For example, the electronic device (100) may detect a situational event based on schedule data in a calendar, flight schedules registered in an application for reserving airplane tickets, images containing meta information in a gallery, or content registered in a diary application. For example, the electronic device (100) may also detect a situational event using information acquired through at least one sensor (170, 1376).

[0137] The electronic device (100) can generate event mapping data in the form of tagging the real-time stress level and event information at the time when a situation event is detected. For example, the electronic device (100) can generate event mapping data by mapping the continuous stress level of the user and information about the detected situation event. Accordingly, the event information about the corresponding situation event can be associated with the real-time stress level at the time when the situation event is detected through the event mapping data. The electronic device (100) can, for example, obtain data in which the detected situation event is continuously tagged as information about the situation event. The electronic device (100) can obtain data in which there is a meaningful stress section and event information mapped to the stress section as information about the situation event. For example, when the electronic device (100) detects a section in which the user's real-time stress level rapidly increases, the electronic device (100) can detect a situation event in the section and tag information about the detected situation event. The electronic device (100) can continuously acquire information about situational events, for example, even in a meaningless stress period, and store the acquired information about situational events.

[0138] For example, the electronic device (100) may separate storage spaces based on the priority of event mapping data. For example, the electronic device (100) may store event mapping data assigned a high priority in a storage space assigned a relatively high importance. The electronic device (100) may assign a high priority to event mapping data corresponding to situational events that occur periodically or repeatedly. For example, the electronic device (100) may store event mapping data assigned a low priority in a default storage space assigned a relatively low importance. The electronic device (100) may assign a low priority to event mapping data corresponding to situational events that occur only once. For example, the importance of storage spaces may be classified based on the level of security or ease of access.

[0139] The electronic device (100) may update the database by storing a personalized stress model, real-time stress level, or event mapping data in the storage space at operation 617.

[0140] The electronic device (100) may determine, in operation 619, whether an abnormal situation is detected. The electronic device (100) may detect the abnormal situation by comparing the real-time stress level with the user's usual stress level obtained from the personalized stress model. For example, the electronic device (100) may determine that a situation in which the real-time stress level is higher than the usual stress level is an abnormal situation. The electronic device (100) may store the time and / or location at which the abnormal situation is detected in response to the abnormal situation. For example, the electronic device (100) may determine that an abnormal situation is detected when the real-time stress level for a certain period of time is 90 or higher or the average real-time stress level for a certain period of time is continuously 30 or higher than the average stress level for a certain period of time.

[0141] If the electronic device (100) does not detect an abnormal situation, it may return to operation 611 and continue performing personalized stress modeling.

[0142] When the electronic device (100) detects an abnormal situation, in operation 621, the electronic device (100) may infer a timing (or point in time) and a conversation topic to initiate a conversation in response to the abnormal situation. For example, the electronic device (100) may determine the timing and conversation topic by considering the time, location, and / or personal data at the time the abnormal situation was detected. For example, the electronic device (100) may analyze the time, location, and / or personal data at which the abnormal situation was detected to infer the cause of the real-time stress level in the abnormal situation. The electronic device (100) may determine a conversation topic that can alleviate the inferred stress cause and lower the stress level. The electronic device (100) may determine in real time a timing to initiate a conversation that may be preferred by the user based on the time, location, and / or personal data at which the abnormal situation was detected.

[0143] The electronic device (100) may determine, at operation 623, whether the timing is suitable for initiating a conversation. For example, the electronic device (100) may determine whether a conversation is possible by considering the user's current location, movements, and usual lifestyle patterns. If the electronic device (100) determines that the timing is not suitable for initiating a conversation, it may wait until a suitable timing for initiating a conversation arrives.

[0144] If the electronic device (100) determines that the timing is appropriate for attempting a conversation, it may call the user at operation 625 and initiate a conversation about the inferred conversation topic. The electronic device (100) may conduct a conversation with the user based on text or voice, for example.

[0145] The electronic device (100) can determine, at operation 627, whether the conversation has ended. The electronic device (100) can receive various feedback from the user while the conversation is in progress. For example, the electronic device (100) can analyze the conversation with the user and, based on the analysis results, determine whether the timing of the conversation was appropriate, whether the conversation subject reflects a source of stress, whether the preferred persona for the conversation is appropriate, or obtain other personal data. The electronic device (100) can reuse the acquired new information to personalize the model for determining the conversation topic or timing.

[0146] If the conversation is not terminated, the electronic device (100) may proceed to operation 625 to continue the conversation on the conversation topic.

[0147] When the conversation ends, the electronic device (100) may analyze and store information received as feedback from the user through the conversation at operation 629. The electronic device (100) may reuse the analyzed and stored information for determining the conversation topic or timing, or for personalizing a personalized stress model.

[0148] Figure 7a, Figure 7b or Figure 7c is a drawing for exemplarily explaining that the user's stress index changes in real time.

[0149] Referring to FIG. 7a, FIG. 7b, or FIG. 7c, an electronic device (e.g., the electronic device (100) of FIG. 1) may provide a graph showing changes in real-time stress levels over time. For example, changes in real-time stress levels from 0:00 to 9:00 may refer to a graph (710a) included in FIG. 7a, changes in real-time stress levels from 0:00 to 10:00 may refer to a graph (710b) included in FIG. 7b, and changes in real-time stress levels from 0:00 to 11:00 may refer to a graph (710c) included in FIG. 7c.

[0150] The electronic device (100) can provide an identification mark that can distinguish the intensity of the real-time stress level (see 720a of FIG. 7a, 720b of FIG. 7b, or 720c of FIG. 7c).

[0151] The electronic device (100) can provide a graph of the intensity of real-time stress levels by time. For example, the intensity of real-time stress levels from 0:00 to 9:00 can refer to the graph (730a) included in FIG. 7a, the intensity of real-time stress levels from 0:00 to 10:00 can refer to the graph (730b) included in FIG. 7b, and the intensity of real-time stress levels from 0:00 to 11:00 can refer to the graph (730c) included in FIG. 7c.

[0152] The electronic device (100) can, for example, accumulate real-time stress levels for 24 hours corresponding to one day to create a personalized stress model (see FIG. 9a).

[0153] FIG. 8 is a diagram illustrating an example of a user interface that provides a conversation with a user in an electronic device (e.g., the electronic device (100) of FIG. 1) according to one embodiment.

[0154] In Fig. 8, it is assumed that the electronic device (100) (or stress management system (e.g., stress management system (400) of Fig. 4)) detects an abnormal situation and conducts a conversation with the user due to a situational event of a meeting with a business partner.

[0155] Referring to FIG. 8, the user interface (UI) displayed through the display of the electronic device (100) may include time information (811) corresponding to the timing of initiating the conversation (e.g., 10:00 PM on May 29) and conversation content (820). The time information (811) corresponding to the timing of initiating the conversation displayed on the user interface may indicate that the user has determined that a time at which they can comfortably have a conversation is 10:00 PM before going to bed.

[0156] The conversation content (820) included in the user interface may display conversation content output by a stress management system (e.g., the stress management system (400) of FIG. 4) on the left, and conversation content input by the user on the right. The conversation content included in the user interface may indicate that the conversation topic is about “meeting with a business partner.” The electronic device (100) may output the following conversation content (821) to determine whether the user is currently available for conversation and wants to talk about the topic: “It seems like you had a difficult meeting with the business partner this afternoon… Would you like to talk about it if you have time?” In response, the user inputs the following response (823): “Actually… I really had to sign this contract, but the pressure was too great.” Based on the content of the user’s response (823), the electronic device (100) may predict that the user agrees to continue the conversation on the topic, and thus may continue the conversation.

[0157] The electronic device (100) can transmit the user's response to the topic determination model (e.g., the topic determination module (441) of FIG. 4) and the timing determination module (443) through the feedback model (e.g., the feedback module (451) of FIG. 4) to update related data. For example, the electronic device (100) can recognize that the user "has promotion-related stress" through the user's response (825) "I absolutely need to get promoted this year..." The electronic device (100) can update the recognized stress cause in the user data storage space (e.g., the storage module (460) of FIG. 4).

[0158] The electronic device (100) may analyze the event mapping data stored by the mapping module (e.g., the mapping module (430) of FIG. 4) to suggest to the user a way to alleviate the user's stress. For example, if the electronic device (100) analyzes the event mapping data and determines that the user has experienced a decrease in stress levels after running, the electronic device (100) may determine that running is an event that can positively affect the user's stress index. Accordingly, the electronic device (100) may make a suggestion (827) such as, "How about taking a good rest today and going for a run tomorrow morning without thinking about anything?" In response to the suggestion, the electronic device (100) may update the user data storage (450) with information on the user's preferred model style through the user's positive or negative feedback (829).

[0159] If the user responds positively to a conversation about empathy, the electronic device (100) can store the user's preference for empathy in personal data. This stored personal data can be used by the stress management system (400) to learn how to frequently express empathy in future conversations.

[0160] Figure 9a or Figure 9b is a drawing for explaining detection of an abnormal situation in which the conversation of Figure 8 is performed.

[0161] The stress level change graph (910) illustrated in Fig. 9a corresponds to a personalized stress model generated by modeling changes in real-time stress levels acquired throughout the day. According to the stress change graph (910) corresponding to the personalized stress model, users generally exhibit high stress levels in the morning, decrease during lunchtime, increase again in the afternoon, and show a tendency for stress levels to decrease rapidly after work.

[0162] In Fig. 9b, a real-time stress level change graph (920) and a stress change graph (910) corresponding to a personalized stress model are illustrated together. According to the real-time stress level change graph (920), the user's real-time stress level remains similar to normal until after lunch. However, at around 1:00 PM, an abnormal situation (930) is detected in which the real-time stress level becomes excessively higher than the normal stress level. In response, the stress management system (e.g., the stress management system (400) of Fig. 4) analyzes available data (e.g., location information, call history, schedule information) to infer that the cause of the abnormal situation is a meeting with a business partner. For example, the stress management system (400) can infer that the abnormal situation is caused by a meeting with a business partner based on the fact that the user's location is not registered as the workplace, that the user spoke with a business partner based on the call history, and that there is a schedule called "4 o'clock business partner" in the schedule application.

[0163] FIG. 10 is a diagram illustrating an example of a user interface that provides a conversation with a user in an electronic device (e.g., the electronic device (100) of FIG. 1) according to one embodiment.

[0164] In Fig. 10, it is assumed that the electronic device (100) (or stress management system (e.g., stress management system (400) of Fig. 4)) detects an abnormal situation and conducts a conversation with the user due to a situational event called an English word test.

[0165] Referring to FIG. 10, the user interface displayed through the display of the electronic device (100) may include time information (1011) corresponding to the timing of initiating the conversation (e.g., 5:00 PM on May 29) and conversation content (1020). It can be seen that the time information (1011) corresponding to the timing of initiating the conversation displayed on the user interface is determined to be 5:00 PM, which is before 6:00 PM, considering that the user's stress level repeatedly increases at 6:00 PM, when referring to the personalized stress model (stress level change graph (1110) of FIG. 11A).

[0166] The conversation content (1020) included in the user interface may be displayed on the left side as a conversation content output by a stress management system (e.g., the stress management system (400) of FIG. 4), and the conversation content input by the user may be displayed on the right side.

[0167] The conversation content included in the user interface can be seen to indicate that the conversation topic is about “English vocabulary test.” The stress management system (400) can output the following conversation content (1021) to determine whether the user is currently available for conversation and wants to talk about the topic: “It’s almost time to go to the English academy. If you have time, would you like to talk for a moment?” In response, the user inputs the answer (1023), “Yes, I’m memorizing vocabulary right now, but if you have time, would you mind?” Based on the content of the user’s answer (1023), the stress management system (400) can predict that the user agrees to continue the conversation on the topic, and thus can continue the conversation.

[0168] The stress management system (400) can transmit the user's answer to the topic determination model (e.g., the topic determination module (441) of FIG. 4) and the timing determination module (443) through the feedback model (e.g., the feedback module (451) of FIG. 4) to update related data. For example, the stress management system (400) can infer that there is a vocabulary test at the English academy based on the user's answer that he or she is memorizing English words. In addition, the stress management system (400) can analyze the event mapping data stored by the mapping module (e.g., the mapping module (430) of FIG. 4) to infer that watching Netflix would be desirable as a way to relieve the user's stress. The stress management system (400) can provide the user with a question (1025) that reflects the inference result, such as, "You seem to be feeling pressured because of the English vocabulary test... I'll help you memorize English words! It seems like you like watching Netflix. Have you seen any interesting dramas recently?" In response, the user inputs a positive response (1027), "Hmm... squid game?" The stress management system (400) can then consider the additional information provided by the user, "squid game," and continue the conversation (1029) with, "Make a sentence related to the squid game using the words you've just memorized. I'll edit it for you."

[0169] The stress management system (400) can store personal data related to the user's preferred content preferences based on the results of the conversation analysis. The stress management system (400) can learn from this stored personal data to encourage more empathy in future conversations.

[0170] Figure 11a or Figure 11b is a drawing for explaining detection of an abnormal situation in which the conversation of Figure 10 is performed.

[0171] The stress level change graph (1110) illustrated in Figure 11a corresponds to a personalized stress model generated by modeling changes in real-time stress levels acquired throughout the day. According to the stress change graph (1110) corresponding to the personalized stress model, the user shows a tendency for their stress level to repeatedly increase around 6 PM (1111).

[0172] In this way, if a user is repeatedly stressed due to a specific event, the stress management system (400) can actively intervene in the user before the stress occurs and provide a stress management service to lower the user's stress level.

[0173] For example, the stress management system (400) detects an abnormal situation (1111) in which the user's stress level repeatedly increases around 6 PM. In response, the stress management system (400) can analyze available data (e.g., conversation content, event mapping data) to infer the cause of the abnormal situation. For example, the stress management system (400) can analyze the conversation content with the user or the event mapping data stored by the mapping module (430) to infer that the abnormal situation (1111) is due to an English vocabulary test. For example, the stress management system (400) can recognize that the user's stress level decreases while watching Netflix through the event mapping data.

[0174] In Figure 11b, a real-time stress level change graph (1120) and a stress change graph (1110) corresponding to a personalized stress model are shown together. According to the real-time stress level change graph (1120), it can be seen that the stress management system (400) preemptively lowered the stress level before an abnormal situation occurred through a conversation with the user (1121).

[0175] FIG. 12 is a configuration diagram of an Internet of Things platform (1200) according to various embodiments.

[0176] Referring to FIG. 12, the Internet of Things platform (1200) may include an indoor network (1260) through which home appliances (1241, 1242, 1243, 1244, 1245, 1246, 1247, 1248, 1249) may communicate with each other via an access point (AP) (1250). In the Internet of Things platform (1200), home appliances (1241, 1242, 1243, 1244, 1245, 1246, 1247, 1248, 1249) may access an external network, the Internet (1230), through an access point (AP) (1250).

[0177] The home appliances (1241, 1242, 1243, 1244, 1245, 1246, 1247, 1248, 1249) may include a communication module capable of communicating with each other, a user device (1210), or a server (1220), a user interface for receiving user input or outputting information to a user, at least one processor for controlling operations, and at least one memory storing a program.

[0178] Each of the appliances (1241, 1242, 1243, 1244, 1245, 1246, 1247, 1248, 1249) may be at least one of various types of appliances. For example, the home appliances (1241, 1242, 1243, 1244, 1245, 1246, 1247, 1248, 1249) may include, but are not limited to, a refrigerator (1241), a dishwasher (1242), an electric range (1243), an electric oven (1244), an air conditioner (1245), a clothes manager (1246), a washing machine (1247), a dryer (1248), and a microwave oven (1249) as illustrated, and may include, for example, various types of home appliances not illustrated in the drawing, such as a cleaning robot, a vacuum cleaner, and a television.

[0179] The server (1220) may include a communication module capable of communicating with other servers, home appliances (1241, 1242, 1243, 1244, 1245, 1246, 1247, 1248, 1249) or user devices (1210), at least one processor capable of processing data received from other servers, home appliances (1241, 1242, 1243, 1244, 1245, 1246, 1247, 1248, 1249) or user devices (1210), and at least one memory capable of storing a program for processing data or processed data. The server (1220) may be implemented as various computing devices such as a workstation, a cloud, a data drive, or a data station. The server (1220) may be implemented as one or more servers physically or logically separated based on function, detailed configuration of function, or data, and may transmit and receive data and process the transmitted and received data through communication between each server.

[0180] The server (1220) can perform functions such as managing user accounts, registering home appliances (1241, 1242, 1243, 1244, 1245, 1246, 1247, 1248, 1249) associated with user accounts, and managing or controlling the registered home appliances (1241, 1242, 1243, 1244, 1245, 1246, 1247, 1248, 1249). For example, a user can access the server (1220) via a user device (1210) and create a user account. The user account can be identified by an ID and password set by the user. The server (1220) can register home appliances (1241, 1242, 1243, 1244, 1245, 1246, 1247, 1248, 1249) to a user account according to a set procedure. For example, the server (1220) can register, manage, and control home appliances (1241, 1242, 1243, 1244, 1245, 1246, 1247, 1248, 1249) by linking identification information (e.g., serial number or MAC (media access control) address) of the home appliances (1241, 1242, 1243, 1244, 1245, 1246, 1247, 1248, 1249) to a user account.

[0181] The user device (1210) may include a communication module capable of communicating with home appliances (1241, 1242, 1243, 1244, 1245, 1246, 1247, 1248, 1249) or a server (1220), a user interface for receiving user input or outputting information to the user, at least one processor for controlling the operation of the user device (1210), and at least one memory for storing a program for controlling the operation of the user device (1210).

[0182] The user device (1210) may be carried by the user or placed in the user's home or office. The user device (1210) may include, but is not limited to, a personal computer, a terminal, a portable telephone, a smart phone, a handheld device, or a wearable device. The memory of the user device (1210) may store programs, i.e., applications, for controlling home appliances (1241, 1242, 1243, 1244, 1245, 1246, 1247, 1248, 1249). The applications may be sold installed on the user device (1210) or downloaded and installed from an external server.

[0183] A user can access a server (1220) by executing an application installed on a user device (1210), create a user account, and perform communication with the server (1220) based on the logged-in user account to register home appliances (1241, 1242, 1243, 1244, 1245, 1246, 1247, 1248, 1249). For example, if the home appliances (1241, 1242, 1243, 1244, 1245, 1246, 1247, 1248, 1249) are manipulated so that the home appliances (1241, 1242, 1243, 1244, 1245, 1246, 1247, 1248, 1249) can be connected to the server (1220) according to the procedure guided by the application installed on the user device (1210), the server (1220) registers the identification information (e.g., serial number or MAC address) of the home appliances (1241, 1242, 1243, 1244, 1245, 1246, 1247, 1248, 1249) in the corresponding user account, You can register home appliances (1241, 1242, 1243, 1244, 1245, 1246, 1247, 1248, 1249) to your user account.

[0184] A user can control home appliances (1241, 1242, 1243, 1244, 1245, 1246, 1247, 1248, 1249) using an application installed on a user device (1210). For example, when a user logs in to a user account with an application installed on a user device (1210), home appliances (1241, 1242, 1243, 1244, 1245, 1246, 1247, 1248, 1249) registered to the user account appear, and when a control command for the home appliances (1241, 1242, 1243, 1244, 1245, 1246, 1247, 1248, 1249) is input, the control command can be transmitted to the home appliances (1241, 1242, 1243, 1244, 1245, 1246, 1247, 1248, 1249) through the server (1220).

[0185] A network can include both wired and wireless networks. Wired networks include cable networks or telephone networks, while wireless networks can include any network that transmits and receives signals via radio waves. Wired and wireless networks can be interconnected.

[0186] The network may include a wide area network (WAN) of the Internet, a local area network (LAN) formed around an access point (AP) (1250), and a short-range wireless network that does not pass through an access point (AP) (1250). Short-range wireless networks may include, but are not limited to, Bluetooth (Bluetooth™ IEEE 802.15.1), ZigBee (ZigBee, IEEE 802.15.4), Wi-Fi Direct, near field communication (NFC), and Z-wave.

[0187] An access point (AP) (1250) can connect home appliances (1241, 1242, 1243, 1244, 1245, 1246, 1247, 1248, 1249) or user devices (1210) to a wide area network (WAN) to which a server (1220) is connected. Home appliances (1241, 1242, 1243, 1244, 1245, 1246, 1247, 1248, 1249) or user devices (1210) can be connected to the server (1220) via the wide area network (WAN).

[0188] The access point (AP) (1250) can communicate with home appliances (1241, 1242, 1243, 1244, 1245, 1246, 1247, 1248, 1249) or user devices (1210) using wireless communication such as Wi-Fi (Wi-Fi™ IEEE 802.11), Bluetooth (Bluetooth™ IEEE 802.15.1), ZigBee (IEEE 802.15.4), and can connect to a wide area network (WAN) using wired communication, but is not limited thereto.

[0189] According to various embodiments, the home appliances (1241, 1242, 1243, 1244, 1245, 1246, 1247, 1248, 1249) may be directly connected to the user device (1210) or the server (1220) without going through an access point (AP) (1250). The home appliances (1241, 1242, 1243, 1244, 1245, 1246, 1247, 1248, 1249) may be connected to the user device (1210) or the server (1220) through a long-range wireless network or a short-range wireless network. For example, the home appliances (1241, 1242, 1243, 1244, 1245, 1246, 1247, 1248, 1249) may be connected to the user device (1210) via a short-range wireless network (e.g., Wi-Fi Direct). As an example, the home appliances (1241, 1242, 1243, 1244, 1245, 1246, 1247, 1248, 1249) may be connected to the user device (1210) or the server (1220) via a wide area network (WAN) using a long-range wireless network (e.g., a cellular communication module). For example, home appliances (1241, 1242, 1243, 1244, 1245, 1246, 1247, 1248, 1249) can connect to a wide area network (WAN) using wired communication and be connected to a user device (1210) or a server (1220) through the wide area network (WAN).

[0190] When the home appliances (1241, 1242, 1243, 1244, 1245, 1246, 1247, 1248, 1249) can access a wide area network (WAN) using wired communication, they may also function as access relays (1250). Accordingly, the home appliances (1241, 1242, 1243, 1244, 1245, 1246, 1247, 1248, 1249) can connect other home appliances to the wide area network (WAN) to which the server (1220) is connected. Additionally, other appliances may connect appliances (1241, 1242, 1243, 1244, 1245, 1246, 1247, 1248, 1249) to a wide area network (WAN) to which the server (1220) is connected.

[0191] Home appliances (1241, 1242, 1243, 1244, 1245, 1246, 1247, 1248, 1249) can transmit information about their operation or status to other home appliances, user devices (1210), or servers (1220) via a network. For example, home appliances (1241, 1242, 1243, 1244, 1245, 1246, 1247, 1248, 1249) may transmit information about their operation or status to another home appliance, user device (1210), or server (1220) when a request is received from the server (1220), when a specific event occurs in the home appliances (1241, 1242, 1243, 1244, 1245, 1246, 1247, 1248, 1249), or periodically or in real time. When information about operation or status is received from home appliances (1241, 1242, 1243, 1244, 1245, 1246, 1247, 1248, 1249), the server (1220) can update the information about operation or status of the home appliances (1241, 1242, 1243, 1244, 1245, 1246, 1247, 1248, 1249) that has been stored, and transmit the updated information about operation and status of the home appliances (1241, 1242, 1243, 1244, 1245, 1246, 1247, 1248, 1249) to the user device (1210) via the network. Here, updating information may include various actions that change existing information, such as adding new information to existing information or replacing existing information with new information.

[0192] Home appliances (1241, 1242, 1243, 1244, 1245, 1246, 1247, 1248, 1249) can obtain various information from other home appliances, user devices (1210), or servers (1220), and provide the obtained information to the user. For example, home appliances (1241, 1242, 1243, 1244, 1245, 1246, 1247, 1248, 1249) can obtain information related to the functions of the home appliances (1241, 1242, 1243, 1244, 1245, 1246, 1247, 1248, 1249) (e.g., cooking recipes, washing instructions) and various environmental information (e.g., weather, temperature, humidity) from the server (1220), and output the obtained information through a user interface.

[0193] The home appliances (1241, 1242, 1243, 1244, 1245, 1246, 1247, 1248, 1249) can operate according to control commands received from other home appliances, user devices (1210), or servers (1220). For example, if the home appliances (1241, 1242, 1243, 1244, 1245, 1246, 1247, 1248, 1249) obtain prior approval from the user so that they can operate according to the control commands of the server (1220) even without user input, the home appliances (1241, 1242, 1243, 1244, 1245, 1246, 1247, 1248, 1249) can operate according to the control commands received from the server (1220). Here, the control commands received from the server (1220) may include, but are not limited to, control commands input by the user through the user device (1210) or control commands based on preset conditions.

[0194] The user device (1210) can transmit information about the user to home appliances (1241, 1242, 1243, 1244, 1245, 1246, 1247, 1248, 1249) or a server (1220) via a communication module. For example, the user device (1210) can transmit information about the user's location, the user's health status, the user's preferences, and the user's schedule to the server (1220). The user device (1210) can transmit information about the user to the server (1220) with the user's prior consent.

[0195] The home appliances (1241, 1242, 1243, 1244, 1245, 1246, 1247, 1248, 1249), user device (1210) or server (1220) can determine control commands using technologies such as artificial intelligence. For example, the server (1220) may receive information about the operation or status of home appliances (1241, 1242, 1243, 1244, 1245, 1246, 1247, 1248, 1249) or information about the user of the user device (1210), process the information using a technology such as artificial intelligence, and transmit the processing result or control command to the home appliances (1241, 1242, 1243, 1244, 1245, 1246, 1247, 1248, 1249) or the user device (1210) based on the processing result.

[0196] For example, a stress management system (e.g., the stress management system (400) of FIG. 4) can obtain data from multiple devices to infer topics and timings appropriate for a user on the Internet of Things platform (1200). For example, if the stress management system (400) infers that an abnormal situation is caused by a situational event within the company based on the location or previous data where the abnormal situation occurred, it can additionally utilize data from a personal computer (PC) to infer the cause of the situational event that caused the abnormal situation.

[0197] For example, the stress management system (400) can observe the user's movements and attempt to have a conversation with the user when it detects that the TV is turned on at a timing determined for conversation, such as continuously changing channels.

[0198] For example, the stress management system (400) can utilize the Internet of Things platform (1200) to create a more comfortable conversational environment with the user, even during conversations. For example, the stress management system (400) can check the indoor temperature or analyze the content of the conversation with the user to control the air conditioner. For example, if the stress management system (400) detects that a conversation is taking place while the user is preparing for bed, it can control the lighting to suit the user's condition.

[0199] For example, when the user's stress level changes through a conversation with the user, the stress management system (400) can control the operation of at least one of the home appliances (1241, 1242, 1243, 1244, 1245, 1246, 1247, 1248, 1249) in response to the change. For example, when the user's stress is relieved through the conversation, the stress management system (400) can control an audio device based on an IoT (Internet of Things) environment to play the user's preferred music. For example, when the stress management system (400) recognizes that the user's mind and body are stabilized through the conversation, it can control the lighting based on the IoT environment to create an atmosphere in which the user can comfortably rest.

[0200] For the above-described purpose, when providing a stress management service in the Internet of Things platform (1200), the stress management system (400) may apply a setting value in a general user environment or may apply a setting value reflecting the user's personal preference or stress level.

[0201] FIG. 13 is a block diagram of an electronic device (1301) (e.g., the electronic device (100) of FIG. 1) within a network environment (1300) according to various embodiments.

[0202] Referring to FIG. 13, in a network environment (1300), an electronic device (1301) may communicate with an electronic device (1302) via a first network (1398) (e.g., a short-range wireless communication network), or may communicate with at least one of an electronic device (1304) or a server (1308) via a second network (1399) (e.g., a long-range wireless communication network). According to one embodiment, the electronic device (1301) may communicate with the electronic device (1304) via the server (1308). According to one embodiment, the electronic device (1301) may include a processor (1320), a memory (1330), an input module (1350), an audio output module (1355), a display module (1360), an audio module (1370), a sensor module (1376), an interface (1377), a connection terminal (1378), a haptic module (1379), a camera module (1380), a power management module (1388), a battery (1389), a communication module (1390), a subscriber identification module (1396), or an antenna module (1397). In some embodiments, the electronic device (1301) may omit at least one of these components (e.g., the connection terminal (1378)), or may have one or more other components added. In some embodiments, some of these components (e.g., sensor module (1376), camera module (1380), or antenna module (1397)) may be integrated into a single component (e.g., display module (1360)).

[0203] The processor (1320) may, for example, execute software (e.g., a program (1340)) to control at least one other component (e.g., a hardware or software component) of the electronic device (1301) connected to the processor (1320) and perform various data processing or operations. According to one embodiment, as at least a part of the data processing or operations, the processor (1320) may store commands or data received from other components (e.g., a sensor module (1376) or a communication module (1390)) in a volatile memory (1332), process the commands or data stored in the volatile memory (1332), and store result data in a non-volatile memory (1334). According to one embodiment, the processor (1320) may include a main processor (1321) (e.g., a central processing unit or an application processor) or a secondary processor (1323) (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 (1321). For example, when the electronic device (1301) includes the main processor (1321) and the secondary processor (1323), the secondary processor (1323) may be configured to use less power than the main processor (1321) or to be specialized for a given function. The secondary processor (1323) may be implemented separately from the main processor (1321) or as a part thereof.

[0204] The auxiliary processor (1323) may control at least a portion of functions or states associated with at least one component (e.g., the display module (1360), the sensor module (1376), or the communication module (1390)) of the electronic device (1301), for example, on behalf of the main processor (1321) while the main processor (1321) is in an inactive (e.g., sleep) state, or together with the main processor (1321) while the main processor (1321) is in an active (e.g., application execution) state. In one embodiment, the auxiliary processor (1323) (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 (1380) or a communication module (1390)). In one embodiment, the auxiliary processor (1323) (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 (1301) where the artificial intelligence model is executed, or can be performed through a separate server (e.g., server (1308)). 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.

[0205] The memory (1330) can store various data used by at least one component (e.g., the processor (1320) or the sensor module (1376)) of the electronic device (1301). The data can include, for example, software (e.g., the program (1340)) and input data or output data for commands related thereto. The memory (1330) can include volatile memory (1332) or non-volatile memory (1334).

[0206] The program (1340) may be stored as software in memory (1330) and may include, for example, an operating system (1342), middleware (1344), or an application (1346).

[0207] The input module (1350) can receive commands or data to be used in a component of the electronic device (1301) (e.g., a processor (1320)) from an external source (e.g., a user) of the electronic device (1301). The input module (1350) 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).

[0208] The audio output module (1355) can output audio signals to the outside of the electronic device (1301). The audio output module (1355) 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.

[0209] The display module (1360) can visually provide information to an external device (e.g., a user) of the electronic device (1301). The display module (1360) 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 (1360) 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.

[0210] The audio module (1370) can convert sound into an electrical signal, or vice versa. According to one embodiment, the audio module (1370) can acquire sound through the input module (1350), output sound through the sound output module (1355), or an external electronic device (e.g., electronic device (1302)) (e.g., speaker or headphone) directly or wirelessly connected to the electronic device (1301).

[0211] The sensor module (1376) can detect the operating status (e.g., power or temperature) of the electronic device (1301) 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 (1376) 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.

[0212] The interface (1377) may support one or more designated protocols that may be used to directly or wirelessly connect the electronic device (1301) with an external electronic device (e.g., the electronic device (1302)). In one embodiment, the interface (1377) may include, for example, a high definition multimedia interface (HDMI), a universal serial bus (USB) interface, an SD card interface, or an audio interface.

[0213] The connection terminal (1378) may include a connector through which the electronic device (1301) may be physically connected to an external electronic device (e.g., the electronic device (1302)). According to one embodiment, the connection terminal (1378) may include, for example, an HDMI connector, a USB connector, an SD card connector, or an audio connector (e.g., a headphone connector).

[0214] The haptic module (1379) 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 (1379) can include, for example, a motor, a piezoelectric element, or an electrical stimulation device.

[0215] The camera module (1380) can capture still images and videos. According to one embodiment, the camera module (1380) may include one or more lenses, image sensors, image signal processors, or flashes.

[0216] The power management module (1388) can manage power supplied to the electronic device (1301). According to one embodiment, the power management module (1388) can be implemented, for example, as at least a part of a power management integrated circuit (PMIC).

[0217] A battery (1389) may power at least one component of the electronic device (1301). In one embodiment, the battery (1389) may include, for example, a non-rechargeable primary battery, a rechargeable secondary battery, or a fuel cell.

[0218] The communication module (1390) may support the establishment of a direct (e.g., wired) communication channel or a wireless communication channel between the electronic device (1301) and an external electronic device (e.g., electronic device (1302), electronic device (1304), or server (1308)), and the performance of communication through the established communication channel. The communication module (1390) may operate independently from the processor (1320) (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 (1390) may include a wireless communication module (1392) (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 (1394) (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 (1304) via a first network (1398) (e.g., a short-range communication network such as Bluetooth, wireless fidelity (WiFi) direct, or infrared data association (IrDA)) or a second network (1399) (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 (1392) may use subscriber information (e.g., an international mobile subscriber identity (IMSI)) stored in the subscriber identification module (1396) to verify or authenticate the electronic device (1301) within a communication network such as the first network (1398) or the second network (1399).

[0219] The wireless communication module (1392) 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 (URLLC (ultra-reliable and low-latency communications)). The wireless communication module (1392) can support a high-frequency band (e.g., mmWave band) to achieve a high data transmission rate, for example. The wireless communication module (1392) can 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 (1392) can support various requirements specified in the electronic device (1301), an external electronic device (e.g., the electronic device (1304)), or a network system (e.g., the second network (1399)). According to one embodiment, the wireless communication module (1392) may support a peak data rate (e.g., 20 Gbps or more) for eMBB realization, a loss coverage (e.g., 164 dB or less) for mMTC realization, 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 realization.

[0220] The antenna module (1397) 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 (1397) 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 (1397) 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 (1398) or the second network (1399), may be selected from the plurality of antennas by, for example, the communication module (1390). A signal or power may be transmitted or received between the communication module (1390) and an 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 (1397).

[0221] According to various embodiments, the antenna module (1397) may form a mmWave antenna module. According to 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) of the printed circuit board and capable of transmitting or receiving signals in the designated high frequency band.

[0222] 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)).

[0223] According to one embodiment, commands or data may be transmitted or received between the electronic device (1301) and an external electronic device (1304) via a server (1308) connected to a second network (1399). Each of the external electronic devices (1302 or 1304) may be the same or a different type of device as the electronic device (1301). According to one embodiment, all or part of the operations executed in the electronic device (1301) may be executed in one or more of the external electronic devices (1302, 1304, or 1308). For example, when the electronic device (1301) is to perform a certain function or service automatically or in response to a request from a user or another device, the electronic device (1301) 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 (1301). The electronic device (1301) 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 (1301) may provide an ultra-low latency service by using distributed computing or mobile edge computing, for example. In one embodiment, the external electronic device (1304) may include an Internet of Things (IoT) device. The server (1308) may be an intelligent server utilizing machine learning and / or a neural network.In one embodiment, an external electronic device (1304) or server (1308) may be included in the second network (1399). The electronic device (1301) 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.

[0224] Although not included in the scenario described above, if a user wearing AR glasses receives a real-time surrounding image generation service based on a cloud environment and then enters a location with poor network communication conditions, such as underground, the model transition method proposed in this document may be utilized to provide uninterrupted service.

[0225] The technical problems to be achieved in the present disclosure are not limited to the technical problems mentioned above, and other technical problems not mentioned will be clearly understood by a person having ordinary knowledge in the technical field to which the present disclosure pertains.

[0226] According to an example, an electronic device (100) may include at least one sensor (170). The electronic device (100) may include a memory (120) including one or more storage media for storing instructions. The electronic device (100) may include at least one processor (110) including a processing circuit. When the instructions are individually or collectively executed by the at least one processor (110), the instructions may cause the electronic device (100) to perform at least one operation. The at least one operation may include an operation of acquiring a biosignal using the at least one sensor (170). The at least one operation may include an operation of determining a stress level based at least in part on the acquired biosignal. The at least one operation may include an operation of determining a conversation topic based at least in part on whether the identified stress level satisfies a specific stress range. The at least one action may include outputting a plurality of messages corresponding to the determined conversation topic as at least part of an interactive conversation with the user through a specific application.

[0227] In one example, the instructions, when individually or collectively executed by at least one processor (110), may cause the electronic device (100) to perform an operation of identifying at least one event associated with a stress level to be considered for determining the conversation topic from one or more events that occurred in connection with the user.

[0228] For example, when the instructions are individually or collectively executed by at least one processor (110), they may cause the electronic device (100) to perform an operation of determining a first topic corresponding to the first event as the conversation topic, if the at least one confirmed event is a first event.

[0229] For example, when the instructions are individually or collectively executed by at least one processor (110), they may cause the electronic device (100) to perform an operation of determining a second topic corresponding to the second event as the conversation topic, if the at least one confirmed event is a second event different from the first event.

[0230] In one example, when the instructions are individually or collectively executed by at least one processor (110), they may cause the electronic device (100) to perform an operation of identifying at least one event from the one or more events based on at least one of the user's location, movement, schedule, or encountered person.

[0231] For example, when the instructions are individually or collectively executed by at least one processor (110), they may cause the electronic device (100) to perform an operation of determining the stress level based on a bio-signal acquired within a predetermined time range from the occurrence of the at least one event.

[0232] For example, when the instructions are individually or collectively executed by at least one processor (110), they may cause the electronic device (100) to perform an operation of acquiring a biosignal change in a predetermined time interval using the acquired biosignal.

[0233] For example, when the instructions are individually or collectively executed by at least one processor (110), they may cause the electronic device (100) to perform an operation of determining the specific stress range based at least in part on the acquired biosignal change.

[0234] In one example, when the instructions are individually or collectively executed by at least one processor (110), they may cause the electronic device (100) to perform an operation of checking the stress level at a first point in time.

[0235] In one example, the instructions, when individually or collectively executed by at least one processor (110), may cause the electronic device (100) to perform an action of initiating at least one message of the plurality of messages as part of the interactive conversation at a second time point that is substantially later than the first time point, determined based on at least one of a location, movement, schedule, or behavioral pattern associated with the user.

[0236] In one example, the instructions, when individually or collectively executed by at least one processor (110), may cause the electronic device (100) to perform an operation that determines the first point in time differently, at least in part, based on a previous event determined to be associated with the stress level.

[0237] According to one example, the electronic device (100) may further include a display. When the instructions are individually or collectively executed by at least one processor (110), they may cause the electronic device (100) to perform an operation of displaying at least a portion of the interactive conversation through the display.

[0238] According to one example, the electronic device (100) may further include a speaker. When the instructions are individually or collectively executed by at least one processor (110), they may cause the electronic device (100) to perform an operation of providing at least a portion of the interactive conversation as a voice message through the speaker.

[0239] In one example, the instructions, when individually or collectively executed by at least one processor (110), may cause the electronic device (100) to perform an action of identifying a change in the stress level of the user during at least a portion of the interactive conversation that is in progress through the specific application.

[0240] In one example, the instructions, when individually or collectively executed by at least one processor (110), may cause the electronic device (100) to perform an action of outputting a message corresponding to a change in the stress level through the specific application as part of the interactive conversation.

[0241] According to one example, a storage medium (120) storing computer-readable instructions may cause the instructions, when executed by at least a portion of at least one processor (110) of the electronic device (100), to cause the electronic device (100) to perform at least one operation. The at least one operation may include an operation of acquiring a biosignal using at least one sensor. The at least one operation may include an operation of determining a stress level based at least in part on the acquired biosignal. The at least one operation may include an operation of determining a conversation topic based at least in part on the determined stress level satisfying a specific stress range. The at least one operation may include an operation of outputting a plurality of messages corresponding to the determined conversation topic as at least a part of an interactive conversation with a user through a specific application.

[0242] In one example, the at least one action may include identifying at least one event related to a stress level to be considered for determining the conversation topic from one or more events that occurred in connection with the user.

[0243] In one example, the at least one action may include an action of determining a first topic corresponding to the first event as the conversation topic when the at least one confirmed event is a first event.

[0244] In one example, the at least one action may include an action of determining a second topic corresponding to the second event as the conversation topic when the at least one confirmed event is a second event different from the first event.

[0245] In one example, the at least one action may include an action of identifying the at least one event from the one or more events based on at least one of the user's location, movement, schedule, or person encountered.

[0246] In one example, the at least one action may include an action of determining the stress level based on a biosignal acquired within a predetermined time range from the occurrence of the at least one event.

[0247] According to an example, the at least one operation may include an operation of obtaining a change in a biosignal in a predetermined time interval using the obtained biosignal.

[0248] In one example, the at least one action may include an action of determining the specific stress range based at least in part on the acquired biosignal change.

[0249] In one example, the at least one action may include an action of checking the stress level at a first point in time.

[0250] In one example, the at least one action may include initiating at least one message of the plurality of messages as part of the interactive conversation at a second time that is substantially later than the first time, determined based on at least one of a location, movement, schedule, or behavioral pattern associated with the user.

[0251] In one example, the at least one action may include determining the first point in time differently based at least in part on a previous event determined to be associated with the stress level.

[0252] In one example, the at least one action may include displaying at least a portion of the interactive conversation via a display.

[0253] In some embodiments, the at least one action may include providing at least a portion of the interactive conversation as a voice message via a speaker.

[0254] In one example, the at least one action may include an action of identifying a change in the stress level of the user during at least a portion of the interactive conversation through the particular application.

[0255] In one example, the at least one action may include outputting a message corresponding to a change in the stress level through the particular application as part of the interactive conversation.

[0256] According to one example, a method of operating an electronic device (440) may include an operation of acquiring a biosignal using at least one sensor. The method may include an operation of determining a stress level based at least in part on the acquired biosignal. The method may include an operation of determining a conversation topic based at least in part on whether the identified stress level satisfies a specific stress range. The method may include an operation of outputting a plurality of messages corresponding to the determined conversation topic as at least a part of an interactive conversation with a user through a specific application.

[0257] In one example, the method may include identifying at least one event associated with a stress level to be considered for determining the conversation topic from one or more events that occurred in connection with the user.

[0258] According to an example, the operation of determining the topic of the contest may include an operation of determining a first topic corresponding to the first event as the topic of conversation, if the at least one event identified is a first event.

[0259] According to an example, the operation of determining the topic of the competition may include an operation of determining a second topic corresponding to the second event as the topic of conversation, if the at least one confirmed event is a second event different from the first event.

[0260] In one example, the act of identifying at least one event may include an act of identifying at least one event from the one or more events based on at least one of the user's location, movement, schedule, or person encountered.

[0261] In one example, the operation of determining the stress level may include determining the stress level based on a biosignal acquired within a predetermined time range from the occurrence of the at least one event.

[0262] According to an example, the operation of checking the above stress level may include an operation of obtaining a change in a biosignal over a predetermined time period using the obtained biosignal.

[0263] In one example, the operation of determining the stress level may include an operation of determining the specific stress range based at least in part on the acquired biosignal change.

[0264] In one example, the method may include an operation of checking the stress level at a first point in time.

[0265] In one example, the method may include initiating at least one message of the plurality of messages as part of the interactive conversation at a second time that is substantially later than the first time, the second time determined based on at least one of a location, movement, schedule, or behavioral pattern associated with the user.

[0266] In one example, the method may include determining the first point in time differently based at least in part on a previous event determined to be associated with the stress level.

[0267] In one example, the act of outputting at least a portion of the interactive conversation with the user may include the act of displaying at least a portion of the interactive conversation via a display.

[0268] In one example, the act of outputting at least a portion of the interactive conversation with the user may include the act of providing at least a portion of the interactive conversation as a voice message via a speaker.

[0269] In one example, the method may include an action of determining a change in the stress level of the user during at least a portion of the interactive conversation that is in progress through the particular application.

[0270] In one example, the method may include outputting a message corresponding to a change in the stress level through the particular application as part of the interactive conversation.

[0271] The effects that can be obtained from the present disclosure are not limited to the effects mentioned above, and other effects that are not mentioned will be clearly understood by a person having ordinary skill in the art to which the present disclosure pertains.

[0272] It should be understood that the embodiments of this document and the terminology used herein are not intended to limit the technical features described in this document to a specific embodiment, but rather to encompass various modifications, equivalents, or substitutes of the embodiment. 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 item, 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.

[0273] The term "module" used in one embodiment 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).

[0274] An embodiment of the present document may be implemented as software including one or more instructions stored in a storage medium (e.g., memory (120)) readable by a machine (e.g., electronic device (440)). For example, a processor (e.g., processor (110)) of the machine (e.g., electronic device (440)) 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.

[0275] According to one embodiment, the method according to one embodiment disclosed in the present document may be provided as a computer program product. The computer program product may be traded as a product between a seller and a buyer. The computer program product may be distributed in the form of a machine-readable storage medium (e.g., compact disc read-only memory (CD-ROM)), or may be distributed online (e.g., downloaded or uploaded) via an application store (e.g., Play Store™) or directly between two user devices (e.g., smart phones). In the case of online distribution, at least a portion of the computer program product may be temporarily stored or temporarily generated in a machine-readable storage medium, such as the memory of a manufacturer's server, an application store's server, or an intermediary server.

[0276] According to one embodiment, 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 separated and placed in other components. According to one embodiment, 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 one embodiment, 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. In an electronic device (100), At least one sensor; A memory (120) including one or more storage media for storing instructions; and At least one processor (110) including a processing circuit, When the above instructions are executed individually or collectively by at least one processor (110), they cause the electronic device (100) to perform at least one operation, At least one of the above actions, An operation of acquiring a biosignal using at least one sensor; An action of determining a stress level based at least in part on the acquired bio-signals; An action for determining a conversation topic based at least in part on the above-determined stress level satisfying a specific stress range; and An action of outputting a plurality of messages corresponding to the determined conversation topic as at least part of an interactive conversation with a user through a specific application. An electronic device (100) comprising:

2. In paragraph 1, When the above instructions are individually or collectively executed by at least one processor (110), the electronic device (100) causes: An action to identify at least one event related to a stress level to be considered in determining the conversation topic from one or more events that occurred in relation to the user. An electronic device (100) that causes the device to perform a function.

3. In paragraph 2, When the above instructions are individually or collectively executed by at least one processor (110), the electronic device (100) causes: If at least one of the confirmed events is a first event, an operation of determining a first topic corresponding to the first event as the conversation topic; and If at least one of the confirmed events is a second event different from the first event, an action of determining a second topic corresponding to the second event as the conversation topic An electronic device (100) that causes the device to perform a function.

4. In paragraph 2, When the above instructions are individually or collectively executed by at least one processor (110), the electronic device (100) causes: An action of identifying at least one event from the one or more events based on at least one of the user's location, movement, schedule, or person encountered. An electronic device (100) that causes the device to perform a function.

5. In paragraph 2, When the above instructions are individually or collectively executed by at least one processor (110), the electronic device (100) causes: An operation of determining the stress level based on a biosignal acquired within a predetermined time range from the occurrence of at least one of the above events. An electronic device (100) that causes the device to perform a function.

6. In paragraph 1, When the above instructions are individually or collectively executed by at least one processor (110), the electronic device (100) causes: An operation of obtaining a change in a biosignal over a predetermined time period using the biosignal obtained above; and An operation of determining the specific stress range based at least in part on the acquired biosignal changes. An electronic device (100) that causes the device to perform a function.

7. In paragraph 1, When the above instructions are individually or collectively executed by at least one processor (110), the electronic device (100) causes: An action to check the stress level at the first point in time; and An action of initiating at least one message among the plurality of messages as part of the interactive conversation at a second time point that is substantially later than the first time point, determined based on at least one of a location, movement, schedule, or behavior pattern associated with the user. An electronic device (100) that causes the device to perform a function.

8. In paragraph 7, When the above instructions are individually or collectively executed by at least one processor (110), the electronic device (100) causes: An action of determining said first time point differently based at least in part on a previous event determined to be associated with said stress level. An electronic device (100) that causes the device to perform a function.

9. In paragraph 1, Including more displays, When the above instructions are individually or collectively executed by at least one processor (110), the electronic device (100) causes: An action of displaying at least a portion of the interactive conversation through the display. An electronic device (100) that causes the device to perform a function.

10. In paragraph 1, Including more speakers, When the above instructions are individually or collectively executed by at least one processor (110), the electronic device (100) causes: An action of providing at least a portion of the interactive conversation as a voice message through the speaker. An electronic device (100) that causes the device to perform a function.

11. In paragraph 1, When the above instructions are individually or collectively executed by at least one processor (110), the electronic device (100) causes: An action of determining a change in the stress level of the user during at least a portion of the interactive conversation through the specific application; and An action of outputting a message corresponding to a change in the above stress level through the specific application as part of the above interactive conversation. An electronic device (100) that causes the device to perform a function.

12. In a storage medium (120) that stores instructions that can be read by a computer, The above instructions, when executed by at least a part of at least one processor (110) of the electronic device (100), cause the electronic device (100) to perform at least one operation; At least one of the above actions: An act of acquiring a biosignal using at least one sensor; An action of determining a stress level based at least in part on the acquired bio-signals; An action for determining a conversation topic based at least in part on the above-determined stress level satisfying a specific stress range; and An action of outputting a plurality of messages corresponding to the determined conversation topic as at least part of an interactive conversation with a user through a specific application. A storage medium (120) including:

13. A storage medium (120) that, when executing the instructions stored in the storage medium (120) according to Article 12, causes the electronic device (100) to perform one or more operations performed by the electronic device (100) described in at least one of Articles 2 to 11.

14. In the operating method of an electronic device (440), An act of acquiring a biosignal using at least one sensor; An action of determining a stress level based at least in part on the acquired bio-signals; An action for determining a conversation topic based at least in part on the above-determined stress level satisfying a specific stress range; and An action of outputting a plurality of messages corresponding to the determined conversation topic as at least part of an interactive conversation with a user through a specific application. A method of operation, comprising:

15. A method of operating an electronic device (100) described in claim 14, wherein the method includes one or more operations performed by the electronic device (100) described in at least one of claims 2 to 11.

Images