JP7786775B1 - Information processing device, information processing method, and information processing program - Google Patents

Abstract

An object of the present invention is to provide an information processing device, an information processing method, and an information processing program that can improve a user's physical condition by encouraging the user to take actions according to the user's condition.
[Solution] The information processing device includes a heart rate variability acquisition unit (110A) that acquires the user's heart rate variability, and a presentation unit (110B) that presents improvement actions to improve the heart rate variability based on the acquired heart rate variability.
[Selected Figure] Figure 6

Description

The disclosed technology relates to an information processing device, an information processing method, and an information processing program.

Patent Document 1 discloses an information processing device that improves the accuracy of abnormality detection based on data related to a user's body compared to conventional devices. This information processing device includes an acquisition unit that acquires measurement data including data measured on the user's body; an estimation unit that uses the acquired measurement data and a model generated for each user to estimate the user's heart rate from the measurement data to estimate the user's heart rate at a future time point and a normal range that is a normal range of heart rates for the user at that future time point; a notification unit that issues a notification if the estimated heart rate at the future time point or the user's heart rate measured when that future time point arrives is outside the normal range of estimated heart rates at the future time point; and an update unit that updates the model using the acquired measurement data.

Japanese Patent Application Laid-Open No. 2020-119175

It is known that people are more likely to experience negative emotions when their physical condition (for example, the balance of the autonomic nervous system) becomes unhealthy due to factors such as hyperconcentration. However, people often do not realize that their own physical condition is unwell, and they may end up experiencing negative emotions without realizing it. For this reason, there is room for improvement in allowing people to rest and improve their physical condition before they realize that they are unwell.

The disclosed technology aims to provide an information processing device, information processing method, and information processing program that can improve a user's physical condition by encouraging them to take actions appropriate to their condition.

The information processing device according to the first aspect includes a heart rate variability acquisition unit that acquires the user's heart rate variability, and a presentation unit that presents improvement actions to improve the heart rate variability based on the acquired heart rate variability.

The information processing device according to the second aspect is the information processing device according to the first aspect, and further includes a setting unit that sets rest timings at predetermined time intervals, and the heart rate variability acquisition unit acquires heart rate variability measured at the set rest timings.

The information processing device according to the third aspect is the information processing device according to the second aspect, and further includes a plan acquisition unit that acquires a work plan including at least information related to the work time input by the user, and the setting unit sets the rest timing according to the acquired work plan.

The information processing device according to the fourth aspect is the information processing device according to the second aspect, and further includes an evaluation unit that evaluates the psychological state of the user when a predetermined number of rest timings have passed based on measured values including at least one of the user's heart rate measured by a heart rate sensor and the user's acquired heart rate variability, and the presentation unit presents resting actions to encourage the user to rest based on the evaluation by the evaluation unit.

In an information processing device according to a fifth aspect, in the information processing device according to the fourth aspect, when presenting the resting behavior, the presentation unit presents the resting behavior output from a trained model that has been trained to output the resting behavior by inputting the evaluation using training data including feedback information from the user.

The information processing device according to the sixth aspect is the information processing device according to the fourth aspect, further comprising an achievement receiving unit that receives from the user an achievement record of the work performed by the user, and the evaluation unit evaluates the user's emotions based on the achievement record received by the achievement receiving unit in addition to the measurement value.

In a seventh aspect of the information processing device, in the sixth aspect, the presentation unit presents the reflection content generated by inputting a prompt sentence to the generation AI instructing the AI to estimate the reflection content based on the measurement values, the performance record, and the user's emotions when accepting the reflection content for the work.

The information processing device according to the eighth aspect is the information processing device according to the sixth or seventh aspect, further comprising a recording unit that records responses from the user to predetermined questions based on the user's psychological state, and the presentation unit presents the user's mental state generated by inputting a prompt sentence to the generation AI that instructs the AI to estimate the user's mental state based on the measured values and the recorded responses.

In a ninth aspect of the information processing device, in the information processing device of any one of the first to seventh aspects, the presentation unit presents the improvement action output from a trained model that has been trained to output the improvement action by inputting the heart rate variability using training data including feedback information from the user.

The information processing device according to a tenth aspect is an information processing device according to any one of the first to eighth aspects, and includes a selection receiving unit that, when presenting the improvement action, receives a selection from the user as to whether or not to implement the improvement action.

An information processing device according to an eleventh aspect is the information processing device according to the tenth aspect, wherein the presentation unit, when presenting the improvement action, presents a plurality of the improvement actions, and the selection receiving unit, when accepting a selection to implement the improvement action, accepts an improvement action selected from the plurality of improvement actions.

In the information processing device of a twelfth aspect, in the information processing device of any one of the first to eleventh aspects, if the heart rate variability is not improved by the improvement action, the presentation unit presents the improvement action until a predetermined number of times set for each improvement action is reached.

In the information processing device of a thirteenth aspect, in the information processing device of any one of the first to twelfth aspects, the presentation unit presents the improvement behavior of the user that is set based on the measured electroencephalogram information of the user.

In an information processing method according to a fourteenth aspect, a computer executes a process of acquiring a user's heart rate variability and, based on the acquired heart rate variability, suggesting an improvement action to improve the heart rate variability.

The information processing program according to the fifteenth aspect causes a computer to execute a process of acquiring a user's heart rate variability and, based on the acquired heart rate variability, presenting improvement actions to improve the heart rate variability.

The disclosed technology can improve a user's physical condition by encouraging them to take actions appropriate to their condition.

1 is a diagram illustrating an outline of the configuration of a rest suggestion system according to a first embodiment. FIG. 2 is a block diagram illustrating an example of a hardware configuration of the wearable terminal according to the first embodiment. FIG. 2 is a diagram schematically illustrating an example of a configuration of a storage according to the first embodiment. FIG. 2 is a block diagram illustrating an example of a hardware configuration of a center server according to the first embodiment. FIG. 2 is a block diagram illustrating an example of the configuration of a trained model storage unit according to the first embodiment. FIG. 2 is a block diagram illustrating an example of a functional configuration of the wearable terminal according to the first embodiment. 10 is a flowchart illustrating an example of a rest suggestion process according to the first embodiment. 4 is an example of a display screen of the wearable terminal according to the first embodiment. 10 is an example of a display screen of an auxiliary terminal according to a modified example of the first embodiment. 10 is a flowchart illustrating an example of an improvement action suggestion process according to the first embodiment. 4 is an example of a display screen of the wearable terminal according to the first embodiment. 10 is a flowchart illustrating an example of a rest action suggestion process according to the first embodiment. 4 is an example of a display screen of the wearable terminal according to the first embodiment. 10 is a flowchart illustrating an example of the flow of a review process according to the first embodiment. 4 is an example of a display screen of the wearable terminal according to the first embodiment. 10 is a diagram illustrating an example of a flow of a rest action suggestion process according to the second embodiment. 10 is a flowchart showing an example of the flow of a questioning process according to the second embodiment.

The rest suggestion system 10 according to this embodiment will be described below with reference to the drawings. Note that in each drawing, the same or equivalent components are assigned the same reference numerals. Furthermore, the dimensional proportions in the drawings have been exaggerated for the sake of explanation and may differ from the actual proportions. Furthermore, the present disclosure is in no way limited to the following embodiment, and can be implemented with appropriate modifications within the scope of the purpose of the present disclosure.

<Outline of this embodiment>
People with developmental disorders such as ASD (Asperger's syndrome) and ADHD (attention deficit hyperactivity disorder), or who are perfectionists, workaholics, or highly sensitive people (HSPs), tend to be more susceptible to burnout due to hyperfocus.

When hyperfocus puts you in a poor state of mind, you can suffer from a variety of cognitive distortions. For example, you may equate "not being able to do something perfectly" with "not being able to do it at all," or you may overgeneralize a single failure. You may also tend to focus on negative information and overlook the positive aspects, falling into black-and-white thinking that sees things in extremes.

In this embodiment, the system is configured to suggest optimal rest based on measured heart rate variability (HRV). This helps restore the user's physical condition to a state where they can make appropriate decisions.

Heart rate variability here refers to a value that represents the variation in the time interval between heartbeats (RRI: R-R Interval). Specifically, heart rate variability is expressed as the standard deviation of the RRI over a predetermined period (SDNN: Standard Deviation of the R-R interval) and/or the square root of the mean square of the differences between two consecutive RRIs (rMSSD: root Mean Square of Successive R-R interval Differences). In this embodiment, the guidelines for evaluating the user's physical condition based on heart rate variability are determined using SDNN, as shown in Table 1 below. Note that in the following description, good heart rate variability refers to a heart rate variability value of 40 ms or more.

[First embodiment]
(Rest suggestion system)
FIG. 1 is a diagram illustrating an outline of the configuration of a rest suggestion system 10 according to a first embodiment. As illustrated in FIG. 1, the rest suggestion system 10 of this embodiment includes a wearable device 100, a center server 200, and an auxiliary device 300. The wearable device 100, the center server 200, and the auxiliary device 300 are connected via a network N. The network N may be, for example, the Internet, a local area network (LAN), or a wide area network (WAN). In this embodiment, a case will be described in which a user uses the wearable device 100, the center server 200, and the auxiliary device 300. Note that multiple users may use their own wearable devices 100 and auxiliary devices 300 to use the rest suggestion system 10. In other words, there may be multiple wearable devices 100 and multiple auxiliary devices 300 for the center server 200. The wearable terminal 100 is an example of an "information processing device."

The wearable device 100 is a portable device worn by the user. Examples of wearable devices 100 include wristband-type devices, watch-type devices, clip-type devices, eyeglass-type devices, and finger-type devices, all of which are equipped with a heart rate sensor and capable of wireless communication. The following describes the application of a smartwatch, an example of a watch-type device, as the wearable device 100.

The center server 200 is a server that manages user information. As an example, the center server 200 is a device managed by the operating company of the rest suggestion system 10. Examples of the center server 200 include general-purpose information processing devices such as personal computers and server computers.

The auxiliary terminal 300 is an information terminal owned by the user that can input and output various information. Examples of the auxiliary terminal 300 include smartphones, tablet terminals, and personal computers. The auxiliary terminal 300 is used to input information that is difficult to input from the wearable terminal 100, or to display information that is difficult to display on the wearable terminal 100. The following describes the case where a smartphone is used as the auxiliary terminal 300.

(wearable device)
FIG. 2 is a block diagram showing an example of the hardware configuration of the wearable terminal 100 according to the first embodiment.
The wearable terminal 100 of this embodiment includes a CPU (Central Processing Unit) 110, a ROM (Read Only Memory) 120, a RAM (Random Access Memory) 130, a storage 140, a communication I/F 150, and an input/output I/F 160. Each component is connected to each other via a bus 170 so as to be able to communicate with each other.

The CPU 110 is a central processing unit that executes various programs and controls each component. The ROM 120 stores various programs and data. In this embodiment, the ROM 120 stores data including the proposed program 121. The proposed program 121 may also be stored in the storage 140, which will be described later. The RAM 130 temporarily stores programs or data as a working area. In other words, the CPU 110 reads a program from the ROM 120 or storage 140, and executes the program using the RAM 130 as a working area.

The suggestion program 121 is a program that executes processes including the rest suggestion process (see FIG. 7) and the review process (see FIG. 13), which will be described later. When the suggestion program 121 is executed, the wearable device 100 uses various hardware resources to execute processes based on the suggestion program 121.

Storage 140 is configured using flash memory, an SSD (Solid State Drive), etc., and stores various programs and data. Figure 3 is a diagram showing an example of the configuration of storage 140 according to the first embodiment. Storage 140 stores data including heart rate data 141, heart rate variability data 142, response data 143, work plan data 144, and performance record data 145.

Heart rate data 141 is data indicating the user's heart rate measured by a heart rate sensor 161 (described below). As an example, the heart rate data 141 stores data indicating the user's heart rate for one week.

Heart rate variability data 142 is data indicating the user's heart rate variability calculated based on heart rate data 141. As an example, heart rate variability data 142 stores data indicating the user's heart rate variability for one week.

Response data 143 is data indicating responses received from the user. Response data 143 is, for example, data on a questionnaire answered about the user's activities during rest time. Data indicating responses received from the user is an example of "feedback information."

Work plan data 144 is data on work plans entered by the user. Specifically, the work plan is data that indicates the user's work plan, including the work start time, work end time, and work content. As an example, work plan data 144 stores the work content for each hour of working hours.

The performance record data 145 is data that indicates the performance of the daily work plan entered by the user. Specifically, the performance record data is data entered by the user, such as the progress of the work at the time of recording, the type of emotion the user is feeling, the level of emotion, text, and audio. Note that the performance record data only needs to record the performance of the work performed by the user, and does not necessarily need to include a work plan.

The communication I/F 150 is an interface for communicating with other devices. Specifically, the communication I/F 150 communicates with various devices, such as the center server 200 and the auxiliary terminal 300, via a network. This communication uses wireless communication standards such as 4G, 5G, Wi-Fi (registered trademark), or Bluetooth (registered trademark). Note that the wearable terminal 100 may also communicate with the center server 200 via the auxiliary terminal 300.

The input/output I/F 160 is an interface for connecting to input/output devices and is used to input and output various types of information. In this embodiment, the input/output I/F 160 is connected to a heart rate sensor 161, an audio sensor 162, and a display 163.

The heart rate sensor 161 is a sensor that measures the heart rate of the user wearing the wearable device 100. The heart rate sensor 161 may be any type of heart rate sensor, such as an optical type, a capacitance type, or an electrical type. The heart rate measured by the heart rate sensor 161 is stored in the heart rate data 141.

The audio sensor 162 detects the user's voice and accepts audio input from the user. The audio sensor 162 is, for example, a small microphone installed in a smartwatch.

The display 163 is a liquid crystal display, organic EL (Electro Luminescence) display, or the like that displays various information. In addition, the display 163 of this embodiment is equipped with a touch panel, such as a resistive or capacitive type, and instructions from the user are input by touching the panel.

(Center server)
4 is a block diagram showing an example of the hardware configuration of the center server 200 according to the first embodiment. The center server 200 is a so-called computer. The functions of the CPU 210, ROM 220, RAM 230, storage 240, communication I/F 250, input/output I/F 260, and bus 270 of the center server 200 are similar to the functions of the CPU 110, ROM 120, RAM 130, storage 140, communication I/F 150, input/output I/F 160, and bus 170 of the wearable terminal 100 described above. Differences from the wearable terminal 100 described above will be described below.

ROM 220 stores data including a server program 221. The server program 221 is a program that executes various processes. For example, the server program executes a process to train a machine learning model stored in a trained model storage unit 242 (described later) using data stored in a user database 241 (described later) as training data.

Storage 240 is composed of a hard disk drive (HDD), SSD, etc., and stores data including a user database 241, a trained model storage unit 242, and a large-scale language model 243.

The user database 241 is a database that stores user information. Specifically, the user database 241 stores user information transmitted from the wearable terminal 100 and the auxiliary terminal 300. In this embodiment, the user database 241 accumulates various types of data stored in the storage 140 described above.

The user database 241 also stores activities that promote at least one of alpha waves and theta waves, which are determined by measuring the user's brain waves. Examples of activities that promote at least one of alpha waves and theta waves include deep breathing, meditation, listening to music, and light exercise. The user database 241 stores, as an example, actions based on the user's brain wave data measured at a medical institution, at home, etc. Specifically, the user database 241 stores actions that have been shown to promote at least one of alpha waves and theta waves when the user performs the above-mentioned actions while measuring the user's brain waves. The user database 241 also stores the above-mentioned actions categorized according to the level of heart rate variability. As an example, "slow abdominal breathing through the nose" is stored as an action when heart rate variability is "20 ms or more but less than 30 ms," and "close your eyes and slowly abdominal breathing through the nose" is stored as an action when heart rate variability is "less than 20 ms." Hereinafter, activities that promote alpha waves will also be referred to as alpha wave-promoting activities, and activities that promote theta waves will also be referred to as theta wave-promoting activities. Note that, although this embodiment describes an example in which alpha wave promoting activities are applied, the technology disclosed herein may be applied to at least one of alpha wave promoting activities and theta wave promoting activities. Alpha wave promoting activities and theta wave promoting activities are examples of "improvement behaviors." Electroencephalogram data is an example of "electroencephalogram information."

The trained model storage unit 242 stores trained models that are trained using training data including various data stored in the user database 241. The training data includes, for example, data recording users' responses to questionnaires stored in the response data 143.

Figure 5 is a block diagram showing an example of the configuration of the trained model storage unit 242 according to the first embodiment. The trained model storage unit 242 stores an improvement behavior suggestion model 242A and a rest behavior suggestion model 242B.

The improvement behavior suggestion model 242A is a trained model that inputs the user's heart rate variability and outputs alpha wave promoting activities recommended for the user. The rest behavior suggestion model 242B is a trained model that inputs an evaluation of the user's emotional state and outputs rest behaviors recommended for the user. Examples of rest behaviors include Zen meditation, consulting, and emotional input. The trained models stored in the trained model storage unit 242 may be deep-learned neural networks, as well as known learning methods such as support vector machines (SVMs), convolutional neural networks (CNNs), and recurrent neural networks (RNNs).

The large-scale language model 243 stores a large-scale language model (LLM) constructed based on known technology. The large-scale language model 243 outputs a generated sentence in response to an input command sentence (hereinafter also referred to as a prompt sentence). In this embodiment, the large-scale language model 243 generates the generated sentence by referencing data stored in the user database 241. Note that the center server 200 may also use a large-scale language model owned by an external server. The large-scale language model is an example of "generative AI (Artificial Intelligence)."

(auxiliary terminal)
Like the center server 200, the auxiliary terminal 300 is configured to include a CPU, ROM, RAM, storage, an input/output interface, a display, and the like, all of which are not shown.

In this embodiment, the auxiliary terminal 300 accepts input of a work plan from the user and transmits work plan data indicating the accepted work plan to the center server 200. Note that the auxiliary terminal 300 may also transmit the work plan data to the wearable terminal 100.

(Functional configuration of wearable device)
Fig. 6 is a block diagram showing an example of the functional configuration of the wearable device 100 according to the first embodiment. As shown in Fig. 6, the CPU 110 executes the proposal program 121 to cause the wearable device 100 according to this embodiment to function as a heart rate variability acquisition unit 110A, a presentation unit 110B, a plan acquisition unit 110C, a setting unit 110D, an evaluation unit 110E, a performance acceptance unit 110F, a selection acceptance unit 110G, and a recording unit 110H.

The heart rate variability acquisition unit 110A has the function of acquiring heart rate variability. In this embodiment, the heart rate variability acquisition unit 110A calculates heart rate variability from heart rate data 141 stored in storage 140 and acquires the calculated heart rate variability. The heart rate variability acquisition unit 110A also stores the acquired heart rate variability in heart rate variability data 142.

The presentation unit 110B has a function of presenting alpha wave promoting activities. The presentation unit 110B presents alpha wave promoting activities selected based on the heart rate variability acquired by the heart rate variability acquisition unit 110A. In this embodiment, the presentation unit 110B displays on the display 163 a proposal for an alpha wave promoting activity output by inputting the acquired heart rate variability into the improvement action proposal model 242A. The presentation unit 110B may also present alpha wave promoting activities selected on a rule basis. For example, the presentation unit 110B proposes alpha wave promoting activities that are determined to have high alpha wave values when measuring brain waves.

The presentation unit 110B also has a function of presenting resting behaviors. The presentation unit 110B presents resting behaviors determined based on the evaluation by the evaluation unit 110E, which will be described later. In this embodiment, the presentation unit 110B inputs the evaluation by the evaluation unit 110E into the resting behavior proposal model 242B, and displays the proposed resting behaviors on the display 163. Note that the presentation unit 110B may also present resting behaviors selected on a rule-based basis. For example, the presentation unit 110B proposes resting behaviors categorized by the evaluation of the emotional state.

The presentation unit 110B also has the function of presenting the review content. In this embodiment, the presentation unit 110B inputs a predetermined prompt sentence into the large-scale language model 243, which generates an answer by referencing user information stored in the user database 241, and displays the generated review content on the display 163.

The plan acquisition unit 110C has the function of acquiring a work plan. In this embodiment, the plan acquisition unit 110C acquires work plan data from the center server 200. Note that the plan acquisition unit 110C may acquire work plan data input to the wearable device 100, or may acquire work plan data input to the auxiliary device 300 from the auxiliary device 300.

The setting unit 110D has a function for setting rest timing. The setting unit 110D sets rest timing for each predetermined time period according to the work plan acquired by the plan acquisition unit 110C. The setting unit 110D also issues a rest notification at the set timing. In this embodiment, the setting unit 110D issues a rest notification 25 minutes after the start of work. 25 minutes after the start of work is an example of a "predetermined time."

The evaluation unit 110E has a function of evaluating the emotional state of the user. In this embodiment, the evaluation unit 110E evaluates the emotional state of the user based on the heart rate stored in the heart rate data 141 and the heart rate variability acquired by the heart rate variability acquisition unit 110A. Emotional states include, for example, elation, anger, and sadness. Emotional states are an example of "psychological states."

The performance record receiving unit 110F has the function of receiving performance record data. In this embodiment, the performance record receiving unit 110F receives performance record data through voice input from the audio sensor 162 and touch operations on the touch panel provided on the display 163. The performance record receiving unit 110F may also receive performance record data from the auxiliary terminal 300.

The selection receiving unit 110G receives a selection of whether or not to engage in alpha wave promoting activities. In this embodiment, the selection receiving unit 110G receives a selection of whether or not to engage in alpha wave promoting activities through voice input from the audio sensor 162 and touch operations on the touch panel provided on the display 163.

The recording unit 110H has the function of recording the user's responses. In this embodiment, the recording unit 110H stores the questionnaire data answered by the user in the response data 143.

<Effect>
Next, a process of suggesting a rest to the user based on heart rate variability will be described with reference to FIGS. 7 to 11. FIG.

(Rest suggestion processing)
7 is a flowchart showing an example of rest suggestion processing according to the first embodiment. The rest suggestion processing according to this embodiment is executed by the CPU 110 of the wearable device 100 reading out the suggestion program 121 from the ROM 120 or the storage 140, deploying it in the RAM 130, and executing it. The rest suggestion processing is repeatedly executed until a predetermined work time defined in the work plan has elapsed. The rest suggestion processing is processing that suggests improvement actions during short rests and suggests resting actions during long rests. Here, a short rest is a rest of about 1 to 10 minutes that is set between work tasks. A long rest is a rest of about 10 to 25 minutes that is set after multiple short rests have been set.

In step S100 of FIG. 7, the CPU 110 acquires a work plan. Specifically, the CPU 110 acquires work plan data indicating the work plan from the center server 200.

In step S101, the CPU 110 sets the timing of a short rest. In accordance with the work plan data acquired in step S100, the CPU 110 sets a schedule for taking a short rest of a predetermined length of time (e.g., 5 minutes) when 25 minutes of work time has elapsed.

In step S102, the CPU 110 notifies the user to take a short rest at the timing set in step S101. The CPU 110 notifies the user to take a short rest at the timing set in step S101. For example, the CPU 110 displays a message on the display 163 saying, "Try breathing slowly using your diaphragm through your nose."

In step S103, the CPU 110 acquires heart rate variability. The CPU 110 acquires heart rate variability from the heart rate measured over a predetermined period of time (e.g., one minute) from the timing of the short rest notification in step S102.

In step S104, the CPU 110 determines whether the heart rate variability value is good. If the CPU 110 determines that the heart rate variability value is good (step S104: YES), the process proceeds to step S106. On the other hand, if the CPU 110 determines that the heart rate variability value is not good (step S104: NO), the process proceeds to step S105. If the CPU 110 determines that the heart rate variability value is good, it displays the message "Good! Enjoy your time." on the display 163. Here, the CPU 110 determines that the heart rate variability is good if it is 40 ms or more, and not good if it is less than 40 ms, for example.

In step S105, the CPU 110 executes the improvement action suggestion process described below.

In step S106, the CPU 110 accepts the questionnaire. Specifically, the CPU 110 accepts the questionnaire after the predetermined time set in step S101 has elapsed. The CPU 110 accepts the questionnaire responses from the user, for example, regarding their evaluation of the alpha wave promoting activity they performed, their behavior during short rest periods, etc., and stores the responses in the response data 143.

In step S107, the CPU 110 accepts the performance record. Specifically, the CPU 110 accepts the user's voice regarding the progress of the work plan using the audio sensor 162, and accepts the user's emotional state displayed on the display 163 using the touch panel. The CPU 110 accepts the performance record, for example, by displaying the screen shown in FIG. 8A (described later) on the display 163. Note that the CPU 110 may also accept performance record data from the auxiliary terminal 300 by displaying the screen shown in FIG. 8B (described later) on a display provided in the auxiliary terminal 300. Similarly, information accepted by the wearable terminal 100 may be accepted from the auxiliary terminal 300.

In step S108, the CPU 110 determines whether the number of short rests has reached a predetermined number. For example, the CPU 110 determines whether the number of short rests has reached four. If the CPU 110 determines that the number of short rests has reached the predetermined number (step S108: YES), the CPU 110 proceeds to step S109. On the other hand, if the CPU 110 determines that the number of short rests has not reached the predetermined number (step S108: NO), the CPU 110 returns to step S102.

In step S109, the CPU 110 issues a notification of a long rest. Specifically, the CPU 110 issues a notification of a long rest after a predetermined work time has elapsed. For example, the CPU 110 displays a message on the display 163 saying "Take a long rest" when a predetermined work time has elapsed after the number of short breaks has reached a predetermined number.

(display screen)
Fig. 8A shows an example of a display screen of the wearable terminal 100 according to the first embodiment. As shown in Fig. 8A, a notification area G10, an emotion selection area G11, an emotion degree designation area G12, and a recording button G13 are displayed on the display 163 of the wearable terminal 100. The entire display screen of the display 163 is displayed against a light red background.

The content of the instruction is displayed in the notification area G10. As an example, the message "Please record your achievements" is displayed in the notification area G10.

Emotion selection area G11 displays icons from which emotions can be selected. The user can select the icon that most closely matches the user's current emotion by tapping on the displayed icon, etc. In this embodiment, icons indicating emotional states are displayed on a five-level scale, ranging from icons indicating positive emotions to icons indicating negative emotions.

The emotion level specification area G12 displays a slide bar that allows the user to specify the emotion level numerically. The user can specify the number that most closely matches the emotion level by sliding the displayed slide bar. In this embodiment, numbers between 1 and 100 can be specified.

The record button G13 is a button for starting recording. The user can record audio by tapping the displayed record button. After the record button G13 is pressed, the record button G13 may be changed to a stop button for stopping recording.

(Modification)
8B is an example of a display screen of the auxiliary terminal 300 according to a modification of the first embodiment. In this modification, an achievement record input from the auxiliary terminal 300 is accepted. As shown in FIG. 8B , an emotion selection area G11, an emotion degree designation area G12, a recording button G13, a notification area G20, a heart rate variability display area G21, and a character input area G22 are displayed on the display of the auxiliary terminal 300. Note that the emotion selection area G11, the emotion degree designation area G12, and the recording button G13 are the same as those in FIG. 8A , and therefore detailed description thereof will be omitted.

The content of the instruction is displayed in notification area G20 in Figure 8B. As an example, notification area G20 displays the message "Take a break" superimposed on a red background.

The heart rate variability display area G21 displays the user's measured heart rate variability value and a circular outline around the heart rate variability. As shown in FIG. 8B, the heart rate variability display area G21 displays "19" as the heart rate variability value, with a red circular outline around the "19."

The character input area G22 is an area where text can be input. The user can input characters from a character input screen that is displayed by tapping on the character input area G22, for example. The input characters may be displayed in the character input area G22. Note that the character input area G22 may also be used to input text that is a transcription of the user's recorded voice.

In this way, the background color of the notification area G20 is displayed in red, and the circular outline of the heart rate variability display area G21 is displayed in red, indicating that the heart rate variability value of "19" is a value that requires caution. In this embodiment, the heart rate variability value of "19" is a value that is evaluated as being "very unwell." Furthermore, the background color of the notification area G20 and the color used for the circular outline of the heart rate variability display area G21 may be changed depending on the heart rate variability value or the notification message. Examples of colors used include blue, yellow, green, and white.

In step S110 of FIG. 7, the CPU 110 executes the rest action suggestion process described below. Then, the CPU 110 returns to step S101. Note that when a predetermined work time has elapsed, the CPU 110 may end the rest suggestion process and proceed to the review process (see FIG. 13) described below.

(Improvement action proposal processing)
Next, an improvement action suggestion process for suggesting an improvement action to improve the user's heart rate variability during a short rest will be described. Fig. 9 is a flowchart showing an example of the improvement action suggestion process according to the first embodiment. The improvement action suggestion process according to this embodiment is a process executed in step S105 (see Fig. 7).

In step S200 of FIG. 9, the CPU 110 proposes alpha wave promoting activities set based on the brain waves. Specifically, the CPU 110 inputs the heart rate variability acquired in step S103 (see FIG. 7) into the improvement action proposal model 242A stored in the trained model storage unit 242 of the center server 200. The CPU 110 then acquires the alpha wave promoting activities output from the improvement action proposal model 242A. The CPU 110 then displays the acquired proposal for alpha wave promoting activities on the display 163.

In step S201, the CPU 110 accepts a selection of whether or not to carry out alpha wave promoting activities. The CPU 110 causes the display 163 to display, for example, the screens shown in Figures 10(A) and 10(B) described below. If the CPU 110 accepts a selection to carry out alpha wave promoting activities (step S201: Yes), the process proceeds to step S202. On the other hand, if the CPU 110 accepts a selection not to carry out alpha wave promoting activities (step S201: No), the process ends the improvement action suggestion process and proceeds to step S106 (see Figure 7).

(display screen)
10A shows an example of a display screen that is displayed when the measured heart rate variability is "20 ms or more and less than 30 ms." A notification area G30 and a selection area G31 are displayed on the display 163 of the wearable device 100. The entire display screen of the display 163 is displayed with a yellow background.

A message suggesting alpha wave promotion activities is displayed in the notification area G30. As an example, the message displayed in the notification area G30 is, "Try breathing slowly and abdominally through your nose."

Displayed in the selection area G31 are an implementation button G32 for selecting whether to perform alpha wave promoting activities and a skip button G33 for selecting not to perform alpha wave promoting activities. The implementation button G32 displays the word "breathe," and the user can select to perform alpha wave promoting activities by tapping the implementation button G32, etc. The skip button G33 displays the word "skip," and the user can select not to perform alpha wave promoting activities by tapping the skip button G33, etc.

Figure 10(B) is an example of a display screen that is displayed when the measured heart rate variability is "less than 20 ms." The differences from Figure 10(A) are explained below. The display screen of display 163 in Figure 10(B) is displayed entirely against a light red background.

As an example, the notification area G30 displays the message "Close your eyes and take slow, abdominal breaths through your nose."

As shown in Figures 10(A) and 10(B), the suggested alpha wave promoting activities are changed and displayed according to the measured heart rate variability values. In addition, the background color is changed and displayed according to the measured heart rate variability values. In this way, by changing the background color according to the measured heart rate variability, the need for rest can be conveyed to the user, and the user can be encouraged to take a rest. The color used as the background color of the display screen of display 163 may be changed according to the heart rate variability values or the notification message, etc. Colors used include, for example, light green, orange, light blue, and white.

In step S202 of FIG. 9, the CPU 110 acquires heart rate variability after a predetermined time has elapsed. Specifically, the CPU 110 acquires heart rate variability after a time set for each type of alpha wave promoting activity has elapsed. For example, the CPU 110 acquires heart rate variability after one minute has elapsed since starting abdominal breathing through the nose.

In step S203, the CPU 110 determines whether the heart rate variability values are good. If the CPU 110 determines that the heart rate variability values are good (step S203: YES), it terminates the improvement action suggestion process and proceeds to step S106 (see Figure 7). On the other hand, if the CPU 110 determines that the heart rate variability values are not good (step S203: NO), it proceeds to step S204. If the CPU 110 determines that the heart rate variability values are good, it displays the message "Good! Enjoy your time" on the display 163.

In step S204, the CPU 110 determines whether the number of times alpha wave promoting activities have been suggested has reached a predetermined number. The CPU 110 determines whether the number of times set for each type of alpha wave promoting activity (e.g., three times) has been reached. If the CPU 110 determines that the number of times alpha wave promoting activities have been suggested has reached the predetermined number (step S204: YES), the improvement action suggestion process ends and proceeds to step S106 (see Figure 7). On the other hand, if the CPU 110 determines that the number of times alpha wave promoting activities have been suggested has not reached the predetermined number (step S204: NO), the process returns to step S200. The predetermined number may be set based on past data, expert knowledge, etc.

(Rest action suggestion processing)
Next, a rest action suggestion process for suggesting rest actions according to the user's heart rate variability during a long rest will be described. Fig. 11 is a flowchart showing an example of the rest action suggestion process according to the first embodiment. The rest action suggestion process of this embodiment is executed in step S110 (see Fig. 7).

In step S300 of FIG. 11, the CPU 110 acquires the heart rate and heart rate variability. Specifically, the CPU 110 acquires the most recent heart rate from the heart rate data 141 stored in the storage 140, and acquires the most recent heart rate variability from the heart rate variability data 142. The CPU 110 may also measure the heart rate for a predetermined period of time and acquire the heart rate variability from the measured heart rate. The acquired heart rate and heart rate variability are examples of "measured values."

In step S301, the CPU 110 evaluates the emotional state based on the heart rate and heart rate variability. Here, the emotional state indicates the emotional tendency associated with the physical state (e.g., autonomic nervous balance). Specifically, the CPU 110 evaluates the user's emotional state based on the heart rate and heart rate variability acquired in step S300.

In this embodiment, the user's emotional state is evaluated based on the heart rate and heart rate variability values. For example, if the user's monthly average heart rate variability is 50 ms or greater, the evaluation is determined as shown in Table 2 below.

For example, if the user's heart rate is "95" and the heart rate variability value is "28," the CPU 110 evaluates the user's emotional state as "sad."

In step S302, the CPU 110 suggests resting behavior based on the evaluation results. Specifically, the CPU 110 inputs the evaluation results of step S301 into the resting behavior suggestion model 242B stored in the learned model storage unit 242 of the center server 200. The CPU 110 then acquires the resting behavior output from the resting behavior suggestion model 242B. The CPU 110 then displays the acquired resting behavior suggestion on the display 163. For example, the CPU 110 displays the screens shown in Figures 12(A) to 12(D) described below on the display 163.

(display screen)
12A to 12D are examples of display screens that are displayed on the display 163 of the wearable terminal 100 based on the evaluation results.

Figure 12 (A) is an example of a display screen that is displayed when the emotional state is evaluated as "good." The background color of the display screen of display 163 is displayed in light green. Also, display 163 displays a message saying "Good! Take a 10-minute break at your leisure." In this way, a suggestion is made for the user to take a break at their own leisure.

Figure 12 (B) shows an example of a display screen that is displayed when the emotional state is evaluated as "elated, excited, and high tension." The background color of the display screen of display 163 is displayed in orange. Also, display 163 displays a message saying, "Try zazen for 10 minutes." In this way, a resting action that will calm the user down a bit is suggested.

Figure 12 (C) is an example of a display screen that is displayed when the emotional state assessment is "indignation, anger, rage." The background color of the display screen of display 163 is displayed in light red. Also, display 163 displays a message saying, "Try zazen for 25 minutes." In this way, it is suggested that the user take a restful action that will thoroughly calm them down.

Figure 12 (D) is an example of a display screen that is displayed when the emotional state is evaluated as "sadness, dejection, loneliness, disappointment." The background color of the display screen of display 163 is displayed in light blue. Also displayed on display 163 is a message that reads "Record your emotions" and a recording button G13. In this way, it is indicated that actions that will allow the user to release their emotions are being suggested.

As shown in Figures 12(A) to 12(C), by displaying different messages depending on the evaluation results, it is possible to suggest resting behaviors that are in line with the user's emotional state. Furthermore, as shown in Figure 12(D), instead of resting behaviors, the user may be asked to release their emotions.

In step S303 of FIG. 11, the CPU 110 accepts a questionnaire. The CPU 110 accepts, for example, responses to the questionnaire regarding the user's evaluation of the resting behavior performed, behavior during long rests, etc., and stores the responses in the response data 143. The CPU 110 then ends the resting behavior suggestion process and returns to step S102 (see FIG. 7).

(Review processing)
Next, a review process for accepting a review of the day when a predetermined work time has elapsed will be described. Fig. 13 is a flowchart showing an example of the flow of the review process according to the first embodiment.

In step S400 of FIG. 13, the CPU 110 displays the heart rate variability and emotion history. Specifically, the CPU 110 displays the heart rate variability stored in the heart rate variability data 142 and the user's emotion history recorded in the performance record data 145 on the display 163. The CPU 110, for example, displays the screen shown in FIG. 14 (described below) on the display 163.

Figure 14 shows an example of the display screen of the wearable device 100 according to the first embodiment. As shown in Figure 14, a time series graph G40 of heart rate variability and multiple emotion icons G41 are displayed.

The time series graph G40 is a graph that connects the heart rate variability values stored in the heart rate variability data 142 in a chronological order.

The emotion icon G41 is an icon that indicates the emotional state. In this embodiment, the emotion icon G41, which indicates the user's emotional state at the time the performance record was recorded, is displayed along the trajectory of the time series graph G40.

In this way, by displaying the time series graph G40 and multiple emotion icons G41, the user can see at a glance the changes in their heart rate variability and their emotional state throughout the day. Furthermore, the user can observe the relationship between changes in heart rate variability and changes in their emotional state, allowing them to improve their own emotional state.

In step S401 of FIG. 13, the CPU 110 acquires the reflection content generated based on the user's information. Specifically, the CPU 110 acquires the reflection content generated by inputting a prompt sentence into the large-scale language model 243. For example, the CPU 110 acquires the generated sentence by inputting a prompt sentence such as "Please infer the reflection content (thanks, praise, improvement) based on the work plan, measurement results, performance records, emotional input, etc." into the large-scale language model 243. Note that the prompt sentence does not have to include the work plan.

In step S402, the CPU 110 displays an input field into which the acquired reflection content has been entered. Specifically, the CPU 110 causes the display 163 to display an input field into which the reflection content acquired in step S401 has been entered. In this embodiment, the reflection content consists of three items: "Things to be grateful for," "Things to praise yourself for," and "Things to improve." Note that the reflection content is not limited to the items described above. The user can also edit the content of the input field.

In step S403, the CPU 110 accepts the review content. Specifically, the CPU 110 accepts the review content entered in the input field displayed in step S402. The CPU 110 then terminates the review process.

(Summary of the first embodiment)
The wearable device 100 of the first embodiment presents alpha wave promoting activities based on the acquired heart rate variability. Therefore, the wearable device 100 of the present embodiment can improve the user's physical condition by encouraging the user to take actions appropriate to their condition. In other words, it can improve breathing disorder caused by the sympathetic nervous system becoming dominant due to overconcentration, etc., and restore the user's physical condition (e.g., balance of the autonomic nervous system).

The wearable device 100 of the first embodiment acquires heart rate variability measured at set rest timings at predetermined intervals in accordance with the acquired work plan. Therefore, the wearable device 100 of this embodiment can encourage the user to take planned rest and improve the user's physical condition before the user begins to feel unwell.

The wearable device 100 of the first embodiment suggests resting behaviors based on an evaluation of the user's emotional state according to their heart rate and heart rate variability. Therefore, the wearable device 100 of this embodiment can effectively improve the user's physical condition.

The wearable device 100 of the first embodiment presents resting behaviors output from the resting behavior suggestion model 242B, which is trained using training data including questionnaire responses from users stored in the response data 143. Therefore, the wearable device 100 of this embodiment can improve the accuracy of suggesting resting behaviors.

The wearable device 100 of the first embodiment presents the reflection content generated by the large-scale language model 243 when accepting the reflection content from the user by inputting a prompt sentence including a work plan, measurement results, performance records, and emotional input, etc. Therefore, the wearable device 100 of this embodiment allows the user to understand their own physical condition from an objective perspective, and can encourage improvements in the user's physical condition, thought patterns, behavior patterns, etc.

The wearable device 100 of the first embodiment presents alpha wave promoting activities output from the improvement action suggestion model 242A, which is trained using training data including questionnaire responses from users stored in the response data 143. Therefore, the wearable device 100 of this embodiment can improve the accuracy of suggesting alpha wave promoting activities.

When presenting an alpha wave promoting activity, the wearable device 100 of the first embodiment accepts the user's choice of whether or not to perform the alpha wave promoting activity. Therefore, according to the wearable device 100 of this embodiment, if the presented alpha wave promoting activity does not suit the user's situation or preferences, the user can choose not to perform the presented alpha wave promoting activity.

In the first embodiment, if the heart rate variability values are not determined to be good as a result of the presented alpha wave promoting activity, the wearable device 100 presents the alpha wave promoting activity until the predetermined number of times set for each alpha wave promoting activity is reached. Therefore, the wearable device 100 of this embodiment can effectively implement alpha wave promoting activities while preventing them from being implemented indefinitely, thereby preventing pressure on the user's work time.

The wearable device 100 of the first embodiment presents alpha wave promoting activities that have higher alpha wave measurement results than other alpha wave promoting activities, which are set in advance by measuring the user's brain waves while performing each alpha wave promoting activity. Therefore, the wearable device 100 of this embodiment can suggest alpha wave promoting activities that are effective for the user.

Second Embodiment
The wearable device 100 of the second embodiment evaluates the emotional state of the user using the performance record when suggesting resting behavior. The wearable device 100 also provides coaching according to the emotional state of the user. Differences from the first embodiment will be described below.

The presentation unit 110B has the function of presenting a question. The presentation unit 110B presents a question that corresponds to the user's emotional state.

The presentation unit 110B also has the function of presenting the psychological state. In this embodiment, the presentation unit 110B inputs a predetermined prompt sentence into the large-scale language model 243, which generates an answer by referencing user information stored in the user database 241, and displays the generated reflection content on the display 163.

The evaluation unit 110E evaluates the user's emotional state based on the heart rate and heart rate variability, as well as on performance records. In this embodiment, the evaluation unit 110E estimates the user's emotional state from the voice, text, emotional level, etc. received by the performance reception unit 110F. Note that known technology may be used to estimate the user's emotional state from the voice and text.

The recording unit 110H has the function of recording responses to questions. In this embodiment, the recording unit 110H stores the user's responses to questions presented by the presentation unit 110B in response data 143.

(Rest action suggestion processing)
15 shows an example of the flow of the rest action suggestion process according to the second embodiment. The rest action suggestion process according to this embodiment is a process executed in step S110 (see FIG. 7).

In step S500 of FIG. 15, the CPU 110 estimates the user's emotions from the performance records. Specifically, the CPU 110 estimates the user's emotions from the performance records stored in the performance record data 145.

In step S501, the CPU 110 acquires the heart rate and heart rate variability. Step S501 is similar to step S300 (see Figure 11), so a detailed description will be omitted.

In step S502, the CPU 110 evaluates the user's emotional state based on the user's emotion, heart rate, and heart rate variability. Specifically, the CPU 110 evaluates whether the user's emotion estimated in step S500 matches the emotional state based on the heart rate and heart rate variability. For example, if the estimated user's emotion matches the emotional state based on the heart rate and heart rate variability, the CPU 110 evaluates the matching user's emotion as the user's true emotion. Furthermore, if the estimated user's emotion does not match the emotional state based on the heart rate and heart rate variability, the CPU 110 evaluates that the user may be experiencing cognitive distortion. Note that if the CPU 110 evaluates that the user may be experiencing cognitive distortion, it may perform the same processing as when the emotional state is evaluated as "anger." This makes it possible to prevent the user from experiencing cognitive distortion and becoming unaware of stress, which could lead to overwork or burnout.

In step S503, CPU 110 determines whether the level of the user's emotion is equal to or greater than a threshold. Specifically, CPU 110 determines whether the most recent level of the user's emotion recorded in performance record data 145 is equal to or greater than a threshold (e.g., 70 or greater). If CPU 110 determines that the level of the user's emotion is equal to or greater than the threshold (step S503: YES), it proceeds to step S504. On the other hand, if CPU 110 determines that the level of the user's emotion is not equal to or greater than the threshold (step S503: NO), it proceeds to step S505.

In step S504, the CPU 110 performs the query processing described below. The CPU 110 then proceeds to step S505.

In step S505, the CPU 110 suggests resting behaviors based on the results of the evaluation. For example, the CPU 110 suggests resting behaviors such as those shown in Table 3 below.

For example, if the user's emotional state is evaluated as "anger" and the emotion level is "65," the CPU 110 displays the message "Take a deep breath."

In step S506, the CPU 110 accepts the questionnaire. Step S506 is the same process as step S303 (see Figure 11), so a detailed description will be omitted. The CPU 110 then ends the resting action suggestion process and returns to step S102 (see Figure 7).

Next, we will explain the questioning process that provides simple coaching to the user. Figure 16 is a flowchart showing an example of the flow of the questioning process according to the second embodiment. One example of the questioning process is the process executed in step S504 (see Figure 15). Note that the questioning process may also be executed at the user's discretion.

In step S600 of FIG. 16, the CPU 110 displays a question corresponding to the emotional state. Specifically, the CPU 110 causes the display 163 to display a question corresponding to the emotional state evaluated in step S502. The CPU 110, for example, displays a question such as that shown in Table 4 below. Note that in Table 4, a circle symbol indicates that a question is to be displayed, and a triangle symbol indicates that a question may be displayed.

For example, if the user's emotional state is evaluated as "sad," the CPU 110 will ask questions such as "What happened?" and "What were you thinking?", and if the emotional level is 90 or higher, it will ask questions such as "What actions did you take?"

In step S601, the CPU 110 records the response to the question. For example, the CPU 110 displays the recording button G13 on the display 163 and records the user's voice response.

In step S602, the CPU 110 acquires the user's psychological state generated based on the user's information and responses. Specifically, the CPU 110 acquires the generated psychological state by inputting a prompt sentence into the large-scale language model 243. For example, the CPU 110 acquires the generated sentence by inputting a prompt sentence such as "Please infer my current mental state based on the work plan, measurement results, performance records, emotional input, responses to inquiries, etc." into the large-scale language model 243. Note that the prompt sentence only needs to include at least the measurement results and responses to inquiries.

In step S603, the CPU 110 displays the acquired psychological state. Specifically, the CPU 110 displays the generated sentence acquired in step S602 on the display 163. The CPU 110 then ends the questioning process.

(Summary of the second embodiment)
The wearable device 100 of the second embodiment evaluates the emotional state of the user from the heart rate and heart rate variability of the user, as well as from the performance record stored in the performance record data 145. Therefore, the wearable device 100 of the present embodiment can more accurately capture the emotional state of the user.

The wearable device 100 of the second embodiment presents the user's mental state generated by the large-scale language model 243 by inputting prompt sentences including work plans, measurement results, performance records, emotional input, and responses to inquiries. Therefore, the wearable device 100 of this embodiment allows the user to objectively understand their own condition and encourages improvements to the user's physical condition, thought patterns, behavior patterns, etc.

[Other embodiments]
In the above embodiment, the center server 200 is described as being equipped with a trained model and a large-scale language model, but this is not limited to this. The trained model and large-scale language model may be equipped in the wearable terminal 100 or the auxiliary terminal 300. For example, if the wearable terminal 100 is equipped with a trained model and a large-scale language model, communication is not required when executing the various processes described above, and the processes can function even when the communication environment is not in place. Note that instead of being equipped with a large-scale language model, the wearable terminal 100 or the auxiliary terminal 300 may be equipped with a small language model (SLM) trained by distilling the large-scale language model 243.

In the above embodiment, a case has been described in which the user checks the reflection content. However, this is not limited to this, and the user's supporter (for example, a counselor, coach, etc.) may be able to check the user's reflection content, performance record data, etc. The supporter can view the reflection content and performance record data for each user by communicating with the center server 200 from their own terminal. Therefore, the rest suggestion system 10 of this embodiment allows the supporter to effectively support the user.

The wearable device 100 may also be configured to notify the supporter when the user's physical condition is poor. For example, the wearable device 100 notifies the supporter when the user's physical condition is evaluated as "very poor." Therefore, the wearable device 100 of this embodiment can notify the supporter when the user needs support from the supporter, allowing the supporter to provide support to the user at an appropriate time.

In the above embodiment, the wearable device 100 sets rest timings in accordance with the acquired work plan. However, this is not limited to this, and the wearable device 100 may set rest timings at predetermined time intervals from the start of work. Therefore, the wearable device 100 of this embodiment can periodically monitor the user's physical condition, allowing the user's physical condition to be improved before the user feels unwell.

In the above embodiment, the wearable device 100 suggested a long rest, such as "do 25 minutes of zazen," when the emotional state was evaluated as "indignant, angry, or upset" or when the emotional level was high. However, this is not limited to this. The wearable device 100 may also suggest resting activities that adjust the time, such as "do 5 minutes of zazen and 5 minutes of free time" or "do 10 minutes of zazen," depending on the user's needs, so as not to disrupt the work plan. The wearable device 100 of this embodiment allows users to rest without disrupting the work plan, thereby reducing the psychological burden on the user of sticking to the work plan.

In the above embodiment, the wearable device 100 accepted a selection of whether or not to perform an alpha wave-promoting activity in step S201 (see FIG. 9 ) of the improvement action suggestion process. However, this is not limited to this. When accepting the selection of the alpha wave-promoting activity in step S201, the wearable device 100 of this embodiment may accept an alpha wave-promoting activity selected from multiple alpha wave-promoting activities. The multiple alpha wave-promoting activities are, for example, activities such as those shown in Table 3 above. The wearable device 100 may also present the alpha wave-promoting activities in order of their suitability for the user. For example, the wearable device 100 may first suggest an activity that is set to maximize at least one of the user's alpha waves and theta waves. The alpha wave-promoting activities suggested to the auxiliary device 300 may also be displayed as a list. When the alpha wave-promoting activities suggested to the auxiliary device 300 are displayed as a list, the alpha wave-promoting activities may be displayed in order of their suitability for the user from the top, or the most suitable alpha wave-promoting activity may be highlighted. The wearable device 100 of this embodiment allows the user to select an alpha wave promoting activity that suits the user's situation.

In addition, the configurations of the rest suggestion system 10, wearable device 100, center server 200, and auxiliary device 300 described in the above embodiment are merely examples, and may be changed according to the situation without departing from the spirit of the invention.

Furthermore, the processing flow of the program described in the above embodiment is merely an example, and unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the program.

Furthermore, the processes executed by the CPU after reading the software (program) in the above embodiments may be executed by various processors other than the CPU. Examples of processors in this case include PLDs (Programmable Logic Devices) such as FPGAs (Field-Programmable Gate Arrays), whose circuit configuration can be changed after manufacture, and dedicated electrical circuits such as ASICs (Application Specific Integrated Circuits), which are processors with circuit configurations designed specifically to execute specific processes.

Furthermore, the processor operations in the above embodiments may not only be performed by a single processor, but may also be performed by multiple processors located in physically separate locations working together. Furthermore, the order of the processor operations is not limited to the order described in the above embodiments, and may be changed as appropriate.

In addition, while the above embodiment describes an embodiment in which the information processing program is pre-stored (installed) in ROM, this is not limiting. The program may be provided in a form recorded on a recording medium such as a CD-ROM (Compact Disc Read Only Memory), a DVD-ROM (Digital Versatile Disc Read Only Memory), or a USB (Universal Serial Bus) memory. The program may also be downloaded from an external device via a network. This disclosure is applicable to programs and program products.

10 Rest suggestion system 100 Wearable terminal 110A Heart rate variability acquisition unit 110B Presentation unit 110C Plan acquisition unit 110D Setting unit 110E Evaluation unit 110F Performance reception unit 110G Selection reception unit 110H Recording unit 121 Proposal program 140 Storage 141 Heart rate data 142 Heart rate variability data 143 Response data 144 Work plan data 145 Performance record data 161 Heart rate sensor 162 Voice sensor 163 Display 200 Center server 221 Server program 240 Storage 241 User database 242 Model storage unit 242A Improvement action suggestion model 242B Rest action suggestion model 243 Large-scale language model 300 Auxiliary terminal

Claims (18)

a heart rate variability acquisition unit that acquires the heart rate variability of a user;
a presentation unit that presents an improvement action that promotes a predetermined electroencephalogram , the improvement action being output by inputting the acquired heart rate variability;
Equipped with
The improvement behavior is the behavior set in advance by measuring electroencephalogram information when the user performs a predetermined behavior .
Information processing device. a setting unit that sets rest timing for each predetermined time period;
a heart rate variability acquisition unit that acquires the heart rate variability of the user measured at the set rest timing;
a suggestion unit that suggests an improvement action to improve the heart rate variability based on the acquired heart rate variability;
an evaluation unit that evaluates a psychological state of the user when a predetermined number of rest timings have passed based on a measurement value including at least one of the heart rate of the user measured by a heart rate sensor and the acquired heart rate variability of the user; and
Equipped with
the presenting unit presents a resting action to cause the user to rest based on the evaluation by the evaluating unit.
Information processing device. A setting unit is provided for setting rest timings for each predetermined time period,
the heart rate variability acquisition unit acquires the heart rate variability measured at the set rest timing.
The information processing device according to claim 1 . The information processing device according to claim 2 , further comprising: a plan acquisition unit that acquires a work plan including at least information regarding a work time input by the user; and wherein the setting unit sets the rest timing according to the acquired work plan. an evaluation unit that evaluates a psychological state of the user when a predetermined number of rest timings have passed based on a measurement value including at least one of the heart rate of the user measured by a heart rate sensor and the acquired heart rate variability of the user;
the presenting unit presents a resting action to cause the user to rest based on the evaluation by the evaluating unit.
The information processing device according to claim 3 . the presentation unit, when presenting the resting behavior, presents the resting behavior output from a trained model trained using training data including feedback information from the user, so that the resting behavior is output in response to input of the evaluation;
The information processing device according to claim 2 or 5. a performance record receiving unit that receives from the user a performance record of the work performed by the user;
the evaluation unit evaluates the emotion of the user based on the performance record received by the performance receiving unit in addition to the measurement value.
The information processing device according to claim 2 or 5. The presentation unit
The reflection content generated by inputting a prompt sentence instructing the generation AI to estimate the reflection content based on the measurement value, the performance record, and the user's emotion is presented when the reflection content of the work is accepted.
The information processing device according to claim 7 . a recording unit that records responses from the user to predetermined questions based on the psychological state of the user;
The presentation unit presents the user's mental state generated by inputting a prompt sentence to a generation AI instructing the AI to estimate the user's mental state based on the measured value and the recorded answer.
The information processing device according to claim 2 or 5. the presentation unit, when presenting the improvement action, presents the improvement action output from a trained model that has been trained using training data including feedback information from the user, so that the improvement action is output by inputting the heart rate variability.
3. The information processing device according to claim 1 or 2. a selection receiving unit that receives a selection from the user as to whether or not to implement the improvement action when the improvement action is presented;
3. The information processing device according to claim 1 or 2. the presentation unit presents a plurality of the improvement actions when presenting the improvement actions;
the selection receiving unit receives an improvement action selected from the plurality of improvement actions when receiving a selection to implement the improvement action;
The information processing device according to claim 11. the presenting unit presents the improvement action until a predetermined number of times set for each improvement action is reached when the heart rate variability is not improved by the improvement action;
3. The information processing device according to claim 1 or 2. The improvement behavior is the behavior set in advance by measuring electroencephalogram information when the user performs a predetermined behavior .
The information processing device according to claim 2 . Obtaining the user's heart rate variability;
presenting an improvement action that is output by inputting the acquired heart rate variability, the improvement action promoting a predetermined electroencephalogram;
The improvement behavior is the behavior set in advance by measuring electroencephalogram information when the user performs a predetermined behavior .
An information processing method in which processing is performed by a computer. Obtaining the user's heart rate variability;
presenting an improvement action that is output by inputting the acquired heart rate variability, the improvement action promoting a predetermined electroencephalogram;
The improvement behavior is the behavior set in advance by measuring electroencephalogram information when the user performs a predetermined behavior .
An information processing program that causes a computer to execute a process. Set rest timings at specified intervals,
acquiring the user's heart rate variability measured at the set rest timing;
suggesting an improvement action to improve the heart rate variability based on the acquired heart rate variability;
evaluate a psychological state of the user when a predetermined number of rest timings have elapsed based on a measurement value including at least one of the heart rate of the user measured by a heart rate sensor and the acquired heart rate variability of the user;
presenting a resting action to the user based on an evaluation of the user's psychological state;
An information processing method in which processing is performed by a computer. Set rest timings at specified intervals,
acquiring the user's heart rate variability measured at the set rest timing;
suggesting an improvement action to improve the heart rate variability based on the acquired heart rate variability;
evaluate a psychological state of the user when a predetermined number of rest timings have elapsed based on a measurement value including at least one of the heart rate of the user measured by a heart rate sensor and the acquired heart rate variability of the user;
presenting a resting action to the user based on an evaluation of the user's psychological state;
An information processing program that causes a computer to execute a process.