Bathing navigation program, bathing navigation system, bathing navigation method, and bathing navigation device

Abstract

To propose a technology that uses a simple prediction model to accurately predict when deep body temperature rises above a target amount, and advises bathers to exit the bath before it deviates from a physiologically safe timing. [Solution] A bathing navigation device that executes a bathing navigation program 30 acquires bather's physical information 33 in addition to biometric information 32 and bathing environment information 31. The bathing navigation device 2 extracts feature data x that is significant for an increase in core body temperature based on the biometric information 32, bathing environment information 31, and bather's physical information 33. The bathing navigation device 2 substitutes the extracted feature data x into a prediction model to calculate a predicted probability that the bather's core body temperature will exceed a target increase amount, and if the calculated predicted probability is equal to or greater than a cutoff value cv, advises the bather to exit the bath.

Description

[Technical Field]

[0001] The technical field disclosed in this specification relates to a bathing navigation program, a bathing navigation system, a bathing navigation method, and a bathing navigation device that provide information related to bathing. [Background technology]

[0002] In Japan, there has been a culture of bathing in a bathtub since ancient times. Bathing is done for the purposes of warming the body, cleansing, and relaxation. However, bathing accidents have been increasing year by year. Although warnings about bathing accidents have been issued through various media since the beginning of autumn, there is no sign of the number decreasing. Therefore, there is a need for technology that encourages bathers to exit the bathtub at a physiologically safe time.

[0003] Two timings are known as guidelines for suggesting a physiologically safe time to exit the bath. The first timing is when core body temperature rises by 0.5°C. Core body temperature is the temperature at the center of the body (hereinafter referred to as the "core"). Core body temperature is measured, for example, by ear temperature, tympanic temperature, sublingual temperature, esophageal temperature, or rectal temperature. The second timing is when the bather subjectively feels sweaty (when there is a subjective sense of sweating). Although these two timings are known to occur at roughly the same time during bathing, it is difficult to constantly measure core body temperature while bathing, making it difficult to express the subjective sense of sweating as an objective index. For this reason, technologies have been proposed that predict core body temperature itself and prompt the bather to exit the bath.

[0004] For example, the bathing navigation system in Patent Document 1 uses a prediction formula to estimate the bather's core temperature or the amount of change in core temperature from the bather's tympanic temperature (an example of core temperature, deep body temperature) at the start of bathing (beginning to immerse in the water) and bathing environment data that will increase the bather's tympanic temperature (for example, bathing time (time spent immersed in the water), water temperature, submerged body surface area, non-submerged body surface area, bathroom temperature).Based on the estimated core temperature or amount of change in core temperature, the bathing navigation system uses a display and speaker to prompt the bather to exit the bath before the amount of change in core temperature reaches a predetermined amount.

[0005] For example, Patent Document 2 discloses a bath device that uses a human body thermal model to estimate the bather's deep body temperature based on the temperature (bath temperature) of the water stored in the bathtub, and issues an alert based on the estimated deep body temperature.

[0006] For example, Patent Document 3 discloses an alarm system that detects physical quantities of the bather related to their core body temperature (e.g., skin temperature, heart rate, respiratory rate), calculates an estimate of the core body temperature based on the rate or amount of change of the detected physical quantities, the temperature (water temperature) and amount of water in the bathtub, and the duration of bathing, and issues an alarm based on the estimated value.

[0007] For example, the deep body temperature estimation device in Patent Document 4 acquires water temperature data from a water temperature sensor installed in the bathtub. The deep body temperature estimation device estimates the deep body temperature based on the acquired water temperature data and a body model that calculates the amount of heat in the whole body bath. The deep body temperature estimation device issues an external alert when the deep body temperature exceeds a predetermined value. [Prior art documents] [Patent documents]

[0008] [Patent Document 1] Patent No. 4522755 [Patent Document 2] Japanese Patent Publication No. 2023-115825 [Patent Document 3] Patent No. 7238596 [Patent Document 4] Japanese Patent Application Publication No. 2023-50891 Summary of the Invention [Problem to be solved by the invention]

[0009] Deep body temperature during bathing is influenced not only by bathing environment information such as water temperature, bathroom temperature, water level, and bathing time, but also by physical decline due to aging and gender differences. Therefore, when estimating deep body temperature, it is necessary to take into account the bather's physical information such as age, height, weight, and build.

[0010] The technologies in Patent Documents 1 to 4 estimate core body temperature by taking into account biological information and bathing environment information, but do not take into account the bather's physical information. Therefore, for example, given the same bathing environment information, the prediction results could be the same regardless of whether the bather is young or elderly. In other words, there is a possibility that the predictions will not take into account elderly people, who are at high risk of bathing accidents. As a result, for example, if the bather is elderly, the timing to prompt the bather to "drain" the water from the bathtub may deviate from a physiologically safe timing.

[0011] Furthermore, core body temperature changes due to the combined effects of various factors. The technologies described in Patent Documents 1, 3, and 4 predict core body temperature based on tympanic membrane temperature, heart rate, respiratory rate, bathing time, bathwater temperature, submerged body surface area, non-submerged body surface area, and bathroom temperature. However, the types of data required for accurate prediction are limited, resulting in low accuracy. The technology described in Patent Document 2 predicts core body temperature by taking into account the heat balance from the skin to the core. However, the prediction results of the technology described in Patent Document 2 are easily affected by the bather's body temperature before bathing. Specifically, if a bather bathes multiple times between entering and exiting the bathroom, the previous bathing experience will affect the bather's body temperature. For example, if the initial core body temperature at the start of the first bathing session is 37°C, the initial core body temperature at the start of the second bathing session will be higher than 37°C. In order to accurately predict the rise in core body temperature, the technology in Patent Document 2 uses a complex prediction model to predict the core body temperature itself at regular intervals from the start of bathing each time the bather bathes, and then determines whether the core body temperature has risen to the temperature rise threshold from the start of bathing, which places an excessive computational load on the device and requires high computational processing power. Therefore, there is room for improvement in the technology that predicts changes in the bather's core body temperature and provides information to the bather. [Means for solving the problem]

[0012] The bathing navigation program devised to solve the above problem is (1) a bathing navigation program that can be executed by a bathing navigation device and provides information to a bather soaking in a bathtub, the bathing navigation device being configured to perform a biological information acquisition process to acquire biological information of the bather, a bathing environment information acquisition process to acquire bathing environment information that is information about the bathing environment of the bather, a bather physical information acquisition process to acquire bather physical information that is information about the body of the bather, and a bathing environment information acquisition process to acquire the biological information acquired in the biological information acquisition process and the bathing environment information acquired in the bathing environment information acquisition process. The system is configured to execute a prediction probability calculation process that extracts feature data significant to a rise in core body temperature based on the bather's physical information acquired in the bather's physical information acquisition process, substitutes the extracted feature data into a prediction model for calculating a predicted probability, which is the probability that the bather's core body temperature will rise by a target amount or more, and calculates the predicted probability, and a first recommendation process that advises the bather to leave the bath if the predicted probability calculated in the prediction probability calculation process is equal to or greater than a threshold, and does not advise the bather to leave the bath if the predicted probability calculated in the prediction probability calculation process is equal to or greater than the threshold.

[0013] The bathing navigation program with the above configuration extracts feature data by taking into account not only biometric information and bathing environment information but also the bather's physical information, and then substitutes the extracted feature data into a prediction model to calculate a predicted probability. Therefore, the bathing navigation program achieves higher prediction accuracy compared to predictions based on biometric information and bathing environment information that do not consider the bather's physical information. For example, even with the same bathing environment information, differences in the calculated predicted probability may occur depending on age and gender. In other words, it is possible to calculate a predicted probability that takes into account elderly people, who are at high risk of bathing accidents. The bathing navigation program compares the calculated predicted probability with a threshold and recommends that the bather exit the bath before deviating from a physiologically safe timing, regardless of whether the bather is elderly, young, male, or female. Furthermore, the bathing navigation program with the above configuration uses a prediction model to calculate a predicted probability, which is the probability that the bather's core body temperature will exceed a target temperature rise, rather than the core body temperature itself, so the prediction result is less affected by the bather's body temperature before entering the bath. Therefore, the prediction model that calculates the prediction probability is simpler than a prediction model that takes into account the heat balance from the skin to the core, and it is possible to predict the rise in core body temperature with high accuracy without placing an excessive computational load on the device or installing high computing power. Therefore, the bathing navigation program with the above configuration can accurately predict changes in core body temperature using a simple prediction model and can advise the bather to exit the bath before they deviate from a physiologically safe timing.

[0014] (2) In the bathing navigation program described in (1), it is preferable that the threshold value is set to a value at which the recall rate and the accuracy rate are equal.

[0015] According to the bathing navigation program configured as above, it is expected that the timing of the bather's recommendation to get out of the water will coincide with the timing when the bather becomes aware of sweating or feels the thermal effect, so that the bather who is recommended to get out of the water can get out of the water after experiencing the thermal effect of the water.

[0016] (3) In the bathing navigation program described in (1) or (2), the bathing navigation device is preferably configured to execute a detection process for detecting the bather's release of hot water, and a first warning process for warning the bather to release hot water if it is determined that the warning condition is met after advising the bather to release hot water in the first recommendation process, and not warning the bather to release hot water if it is determined that the warning condition is not met, and the warning condition is preferably a predetermined time that has elapsed since the execution of the first recommendation process without detecting the release of hot water in the detection process.

[0017] According to the bathing navigation program configured as above, after the bather is advised to exit the bath upon prediction that the deep body temperature has exceeded the target increase amount, a warning to exit the bath is given to the bather after a predetermined time has elapsed, thereby preventing a bather whose deep body temperature has exceeded the target increase amount from continuing to bathe at a timing significantly outside of physiologically safe times.

[0018] (4) In the bathing navigation program described in (3), it is preferable that the warning condition is such that the specified time varies depending on the temperature of the water into which the bather bathes, as detected by a water temperature sensor of the bathing navigation device.

[0019] The higher the water temperature, the more likely the body's core body temperature rises during bathing. The bathing navigation program configured as described above warns the bather to turn off the water at different times depending on the water temperature, so if the bather's core body temperature rises above the target amount, the warning to turn off the water can be issued at an appropriate time based on the change in the body's core body temperature.

[0020] (5) In the bathing navigation program described in any one of (1) to (4), it is preferable that the bathing navigation device executes a second warning process that warns the bather when the predicted probability calculated in the predicted probability calculation process is not equal to or greater than the threshold value and the bather's bathing time exceeds the water discharge warning time set before the timing deviates from the physiologically safe timing.

[0021] For example, if the bather is elderly and their core body temperature does not rise easily, the predicted probability may not reach the threshold, and the bather may not be advised to exit the bath. Even in such cases, the bathing navigation program configured as described above will issue a warning to exit the bath if the bathing time exceeds the exit warning time. Therefore, the bathing navigation program configured as described above can prompt the bather to exit the bath before significantly deviating from a physiologically safe timing while adapting to the bather's physical functions.

[0022] (6) In the bathing navigation program described in (5), it is preferable that the bathing navigation device executes a second recommendation process that recommends the bather to remove the water when the bathing time exceeds the water removal recommendation time set before the water removal warning time.

[0023] The bathing navigation program configured as described above, even when it predicts that the deep body temperature will not reach the target increase amount or more, can make the bather aware that the bathing time is getting longer and encourage the bather to safely get out of the water by advising the bather to get out of the water before the bathing time exceeds the water-out warning time.

[0024] (7) In the bathing navigation program described in any one of (1) to (6), it is preferable to have the bathing navigation device execute a storage process for storing bathing-related information regarding bathing in the memory of the bathing navigation device, and an update process for updating the predictive model using the bathing-related information stored in the memory.

[0025] The bathing navigation program configured as described above stores bathing-related information in memory, and updates the prediction model using the stored bathing-related information, thereby refining the prediction model and improving prediction accuracy.

[0026] The system, method, and device capable of realizing the functions of the bathing navigation program having the above configuration, as well as the storage medium for storing the bathing navigation program, are also novel and useful. [Effects of the Invention]

[0027] The above technology predicts changes in the bather's deep body temperature and provides information to the bather.It uses a simple prediction model to accurately predict when the deep body temperature has exceeded a target increase, and can advise the bather to exit the bath before it deviates from a physiologically safe timing. [Brief explanation of the drawings]

[0028] [Figure 1] 1A and 1B are diagrams illustrating an example of how to use the bathing navigation device. [Figure 2] 1 is a diagram illustrating a schematic configuration of a bathing navigation device. [Figure 3] FIG. 2 is a diagram illustrating an example of feature amount data. [Figure 4] An example of a judgment cross-tabulation table is shown below. [Figure 5] 10 shows an example of a scatter plot of data for constructing a prediction model. [Figure 6] 10 is a flowchart illustrating an example of a procedure for hot water outlet navigation processing. [Figure 7] 10 is a flowchart illustrating an example of a procedure for a predicted probability calculation process. [Figure 8] FIG. 10 is a diagram illustrating an example of a notification. [Figure 9] 10 is a flowchart illustrating an example of a procedure for a re-warning process. [Figure 10] FIG. 10 is a sequence diagram illustrating an example of an update process. DETAILED DESCRIPTION OF THE INVENTION

[0029] The following describes the bathing navigation program, bathing navigation system, bathing navigation method, and bathing navigation device according to the present embodiment, with reference to the drawings. The present embodiment discloses a navigation system including a bathing navigation device capable of executing a bathing navigation program that provides information to bathers.

[0030] <Bathroom navigation system> For example, as shown in FIG. 1, a bathing navigation system 1 includes a bathing navigation device 2 that is communicatively connected to a wearable device 5, a smartphone 6, and a hot water supply and heating system 8. The bathing navigation device 2 is installed in a bathroom 7, for example, in a detached house or an apartment building. A bathtub 71 is installed in the bathroom 7, and hot water 72 supplied from the hot water supply and heating system 8 is stored in the bathtub 71. The bathing navigation device 2 can provide information about bathing to a bather M who is soaking in the hot water 72 in the bathtub 71.

[0031] In this specification, as shown in Figure 1, the state in which bather M is immersed in hot water 72 in bathtub 71 is referred to as "bathing." The state in which bather M gets out of hot water 72 in bathtub 71 is referred to as "exiting." The time that bather M is immersed in hot water 72 is referred to as "bathing time." The general actions that bather M performs in bathroom 7 are referred to as "bathing."

[0032] The bathing navigation device 2 is configured such that a main unit 21 and a sensor unit 23 are connected via a cable 22. The main unit 21 is attached to a wall surface 73 of the bathroom 7. The sensor unit 23 is attached to the inner wall of the bathtub 71 at a position where it will be submerged in hot water 72.

[0033] <Outline of bathing navigation device> The general configuration of the bathing navigation device 2 will be described with reference to Figure 2. The main device 21 of the bathing navigation device 2 has a controller 10 including a CPU 11 and a memory 12. The main device 21 has a user interface (hereinafter referred to as "user IF") 13, a communication interface (hereinafter referred to as "communication IF") 14, an audio output unit 15, a bathroom temperature sensor 16, and a timing unit 17, which are electrically connected to the controller 10. The CPU 11 is an example of a "controller." The memory 12 is an example of a "memory accessible by the bathing navigation device."

[0034] Sensor device 23 includes a water temperature sensor 28 that measures water temperature and a water pressure sensor 29 that measures water pressure. Sensor device 23 transmits water temperature data including the value of the water temperature measured by water temperature sensor 28 and water pressure data including the value of the water pressure measured by water pressure sensor 29 to main device 21 via cable 22.

[0035] The CPU 11 executes various processes according to the programs read from the memory 12 and based on the user's operations. Note that the controller 10 in Fig. 2 is a collective term for the hardware and software used to control the bathing navigation device 2, and does not necessarily represent a single piece of hardware actually present in the main device 21.

[0036] The memory 12 stores various programs including the bathing navigation program 30 and various data including a bathing file 41. The memory 12 is also used as a temporary storage area.

[0037] The bathing navigation program 30 is a program that controls the operation of the bathing navigation device 2. The bathing navigation program 30 stores a prediction model previously constructed through machine learning. The prediction model is a prediction formula for calculating the predicted probability, which is the probability that the bather M's core body temperature will increase by a target amount from the start of bathing (0 minutes after bathing). In this embodiment, the target increase is 0.4°C. The prediction model uses feature data that can be extracted as significant data for the increase in core body temperature based on bathing environment information 31, which is information about the bathing environment; biological information 32, which is information indicating the bather M's condition; and bather physical information 33, which is information about the bather M's body. If the predicted probability calculated by the prediction model is equal to or greater than a threshold, the bathing navigation program 30 advises the bather M to exit the bath. If the calculated predicted probability is less than the threshold, the bather M is not advised to exit the bath. This bathing navigation process will be described later. The bathing navigation program 30 also performs an update process to update the prediction model. This update process will be described later.

[0038] A bathing file 41 is created for each bathing session. For example, if bather M bathes twice between entering and leaving the bathroom 7, a bathing file 41 is created for each of the first and second bathing sessions. For example, if bather M and another bather both bathe, a bathing file 41 is created for each of bather M's bathing session and the other bather's bathing session.

[0039] The bathing file 41 stores bathing-related information related to bathing. In other words, the bathing navigation device 2 keeps a bathing log in the bathing file 41. The bathing file 41 stores, for example, bathing environment information 31, biometric information 32, bather physical information 33, intermediate variables 34, and processing content 35. The intermediate variables 34 store feature data extracted from the bathing environment information 31, biometric information 32, and bather physical information 33. The processing content 35 stores the processing content of the bathing navigation process. The processing content 35 stores, for example, the prediction probability calculated by the prediction model and the content of recommendations made to bather M. The bathing file 41 is used, for example, to build and update prediction files. The bathing file 41 will be described later.

[0040] The user IF 13 includes hardware for displaying a screen to notify the user of information and hardware for accepting user operations. In this embodiment, the user IF 13 is a combination of a display 13a capable of displaying information, an indicator lamp 13b indicating the operating status of the bathing navigation device 2, and a stop button 13c for stopping the operation of the bathing navigation device 2. The user IF 13 may also be a touch panel equipped with a display function and an input receiving function.

[0041] The communication IF 14 includes hardware for communicating with external devices such as the wearable terminal 5, the smartphone 6, and the hot water supply and heating equipment 8. The communication method of the communication IF 14 may be wireless LAN communication such as Wi-Fi (registered trademark) or short-range wireless communication such as Bluetooth (registered trademark). The communication IF 14 includes hardware for communicating with the sensor device 23.

[0042] Audio output unit 15 includes hardware for outputting sounds such as a buzzer sound and audio guidance. Bathroom temperature sensor 16 is a sensor that measures the temperature (bathroom temperature) of bathroom 7. Timekeeping unit 17 measures time.

[0043] <Wearable devices> The wearable device 5 in this embodiment is a wristwatch-type communication terminal device. The wearable device 5 may be a pendant-type, ring-type, or eyeglass-type communication terminal device, or may be a communication terminal device worn on the chest. The wearable device 5 may be worn on the upper arm, ankle, or the like. The wearable device 5 can transmit the heart rate of the bather M measured by the heart rate sensor 51 to the bathing navigation device 2 using the communication unit 52.

[0044] <Smartphone> The smartphone 6 has a touch panel 61 and a communication unit 62. The smartphone 6 stores a bathing management application program (hereinafter referred to as the "bathing management app") 63. The bathing management app 63 has a function of displaying a screen provided by the bathing navigation program 30 on the touch panel 61 when communication between the smartphone 6 and the bathing navigation device 2 is established. For example, the bathing management app 63 receives a screen for inputting bather physical information 33 from the bathing navigation program 30 and displays it on the touch panel 61. The bathing navigation program 30 can acquire the bather physical information 33 by accepting the bather physical information 33 via the touch panel 61 and storing it in the memory 12. The bathing management app 63 may, for example, access the bathing file 41 and display the bather M's bathing log on the touch panel 61. The smartphone 6 may be a tablet device.

[0045] <Building a predictive model> This section explains how to build a predictive model. For the predictive model, a machine learning model that handles binary values, such as binary logistic regression analysis or decision trees, is used. The data used to build the predictive model can be data obtained from laboratory experiments or data obtained from field surveys.

[0046] The training data is a binary value of target increase in core body temperature change not reached / reached (for example, a change in core body temperature of 0.5°C not reached / reached), or a binary value of subjective sweating sensation of "not sweating" / "sweating (more than sweaty)."

[0047] The feature data used is data from the time when the prediction model is executed, prior to the time when the prediction is executed. For example, if a prediction is executed using the prediction model five minutes after the start of bathing, data from one minute after the time when the prediction is executed (five minutes), i.e., four minutes after the start of bathing, is used. This is because changes in core body temperature are the result of being influenced by the bathing environment in the past. Using past data makes it possible to predict changes in core body temperature or subjective sweating sensation in real time.

[0048] The feature data includes data based on bathing environment information 31, data based on biological information 32, and data based on bather's physical information 33.

[0049] The data based on the bathing environment information 31 includes indicators that can be easily measured over time using sensors or the like, indicators that can be easily obtained through questionnaires or the like, and data generated from these indicators. Examples of the data based on the bathing environment information 31 include water temperature, bathroom temperature, bathing time, water level at the time of bathing (or the proportion of body surface area submerged in water), posture (sitting bent over, sitting with legs apart, sitting cross-legged, etc.), amount of water filled into the bath, number of baths (how many times the bather has taken a bath), which number of baths the bather has taken (whether other people live with them, etc.), bathroom size, bathtub size, bathroom construction method, presence or absence of a bathroom window, floor on which the bathroom is installed, home insulation rating, home construction method, home structure, home type, floor on which the home is located (in the case of an apartment building or condominium), presence or absence of a window, season, calendar information (year / month / day / day of the week / time), exhaled CO2 concentration, whether the bathroom heater is operating, humidity, airflow, and environmental assessment index (discomfort index, WBGT). Furthermore, for example, the water temperature or bathroom temperature one minute before the prediction execution time also falls under the category of data based on bathing environment information 31.

[0050] The data based on the biological information 32 includes indicators that can be easily measured over time using a wearable sensor or the like to measure the condition of the bather M, and data generated from these indicators. Examples of the measured data include ear temperature, sublingual temperature, axillary temperature, heart rate, skin blood flow, local sweat rate, SpO2, pressure related to body movement, acceleration, and gyroscope. The data based on the biological information 32 includes the amount of change from a certain starting point, the rate of change from a certain starting point, difference sequence, statistics per unit time (e.g., one-minute average, standard deviation, standard error, maximum, minimum, median, coefficient of variation, etc.), and heart rate variability indicators generated from these time-series data.

[0051] The data based on bather physical information 33 uses indicators that affect the thermal effect of bathing as well as data generated from those indicators as the physical condition of bather M. Data based on bather physical information 33 includes, for example, age, sex, height, weight, body mass index BMI (calculated from height and weight using a known formula), body surface area (calculated from height and weight using a known formula), body fat percentage, skeletal muscle mass, bone mass, body fat mass, body age (e.g., measured values using a body composition scale, etc.), and exercise frequency (questionnaire).

[0052] <Update of forecast model> Generally, when building a predictive model, the more data there is, the wider the scope of application and the better the model can be built. However, the human body's thermal physiological response during bathing is essentially unchanged unless the human body structure changes, although it is affected by changes in lifestyle. Therefore, data acquired for past research and development can be used to build a predictive model. Furthermore, if new data can be acquired through laboratory experiments or field surveys, the scope of application of feature data can be expanded, and the prediction accuracy of the predictive model can be refined. Therefore, in this embodiment, bathing logs are accumulated, and a predictive model is built and updated based on the accumulated bathing logs.

[0053] As the amount of data used to build a predictive model increases, the feature data that contributes to the prediction may change. Therefore, updating a predictive model also involves replacing the feature data.

[0054] <Example of prediction model> The inventors constructed a prediction model shown in Formula 1 by machine learning using binomial logistic regression analysis with training data. In Formula 1, p represents a predicted probability, a represents a coefficient, x represents feature data, b represents a constant, and e represents the base of the natural logarithm (Napier's constant).

[0055]

number

[0056] The data used to build the prediction model was bathing data obtained from a subject experiment that included various physical information and bathing environment information. Time series data of eardrum temperature and heart rate were obtained as biological information 32.

[0057] The training data used was time-series data in which the amount of change in tympanic membrane temperature, starting from the time bathing began, was calculated from the time-series data of tympanic membrane temperature acquired as biological information 32, and categorized into two values: (1) if the temperature reached 0.4°C or higher, and (0) if the temperature did not reach 0.4°C. The reason for using 0.4°C here is to ensure that the water is prepared to be dispensed before the temperature reaches 0.5°C, and that the water is dispensed reliably when it reaches 0.5°C. The reason for using the amount of change in tympanic membrane temperature as training data is that tympanic membrane temperature is said to reflect brain temperature, which controls the body's thermoregulation function.

[0058] For feature data x, the data shown in Figure 3 was used based on previous findings from hot spring research. In Figure 3, "importance" indicates the degree of influence on the amount of change in tympanic membrane temperature reaching 0.4°C or higher. In this form, "importance" is shown by odds ratio. The "*" next to the odds ratio indicates the statistical significance of the odds ratio. "*" indicates significance with a probability of less than 5%. "**" indicates significance with a probability of less than 1%. "***" indicates significance with a probability of less than 0.1%. As shown in Figure 3, for feature data x, data that is significant with a probability of less than 5% for tympanic membrane temperature to reach 0.4°C or higher is used.

[0059] For example, as shown in Figure 3, "age" is an indicator of bather M's physical decline. Specifically, young people "under 20" have a flexible cardiovascular system, which allows their body temperature to rise quickly when bathing and quickly return to normal after bathing. Elderly people "over 60" have an increased stiffness of the cardiovascular system, making it difficult for their body temperature to rise and return to normal. Middle-aged people "in their 30s to 50s" are in the middle generation between young and old. Considering that physical decline affects core body temperature during bathing, "age" can be categorized into "under 20s," "30s to 50s," and "over 60s." In binomial logistic regression analysis, more than three data points cannot be used as explanatory variables. Therefore, two dummy variables for "age" are generated and used as feature data x. Specifically, the feature data x uses the "first generation" categorized into two values: "under 20s" (0) and "30s to 50s" (1), and the "second generation" categorized into two values: "under 20s" (0) and "over 60s" (1).

[0060] "Gender" is an indicator of heat balance from the skin to the core. Men and women generally have distinctive physical differences, such as differences in body fat percentage and muscle mass. For example, women have more body fat than men, which makes it harder for heat to be transferred from the skin to the core, making it harder for their core body temperature to rise. Considering that "gender differences" affect the rise in core body temperature in this way, "gender" is classified into two values, "male (0)" and "female (1)," and used as feature data x.

[0061] "Height" is an index of the body surface area to which heat is transferred from the water. Specifically, the taller a person is, the higher their sitting height is, and therefore the ratio of the area of contact with the water to the total surface area while bathing is smaller. If the ratio of the body surface area immersed in the water is small, the core body temperature does not rise easily. Therefore, "height" itself is used as feature data x.

[0062] It should be noted that "age," "gender," and "height" are examples of data based on bather physical information 33, and are data that can be easily acquired by bather M's input.

[0063] "Heart rate one minute ago" is an index showing the heart rate one minute before the prediction execution time. The baseline heart rate varies depending on the bather, depending on lifestyle habits, sports habits, genetic factors, etc. The maximum heart rate can generally be calculated as 220 bpm - age (years), and as this formula shows, there is an upper limit to the number of times the human heart can beat. Therefore, "heart rate one minute ago" itself is used as feature data x.

[0064] "Heart rate change one minute before" is an index showing the change in heart rate from the start of bathing to one minute before the prediction execution. Heart rate tends to increase from the time elapsed time is measured, and "heart rate change one minute before" indicates responsiveness to the thermal effect of the water from the start of bathing. Therefore, "heart rate change one minute before" itself is used as feature data x.

[0065] The "heart rate difference one minute before" is an index that represents the difference between the value at the time of prediction execution and the value one minute before. For example, when the bath temperature is high, the amount of change in heart rate per unit time tends to be large. In this way, the "heart rate difference one minute before" can indicate the responsiveness to the thermal effect of bathing. Therefore, the "heart rate difference one minute before" itself is used as feature data x.

[0066] "Percentage change in heart rate from 3 minutes before 1 minute" is an index showing the amount of change in heart rate from 3 minutes after starting to bathe to 1 minute before the prediction execution. The effects of body movements and changes in posture before and after starting to bathe statistically settle down approximately 3 minutes after starting to bathe. Therefore, the rate of change in heart rate from the time when the effects of body movements and changes in posture cease to exist can be used to determine responsiveness to the thermal effects of the water. Therefore, "Percentage change in heart rate from 3 minutes before 1 minute" itself is used as feature data x.

[0067] Note that "heart rate one minute ago," "heart rate change one minute ago," "heart rate difference one minute ago," and "rate of change from three minutes ago in heart rate" are examples of data based on biometric information 32, and can be easily calculated from the time series data of heart rate measured by wearable device 5.

[0068] Since the thermal effect of hot water increases as the time spent in the bath increases, "elapsed time" is used as feature data x. "Elapsed time (minutes)" is the time elapsed measured from the start of bathing (0 minutes into the bath).

[0069] The thermal effect of hot water is influenced by the bathing environment immediately before, and is greater the higher the bathroom temperature. Therefore, the "bathroom temperature one minute ago" itself is used as feature data x. Also, since the thermal effect of hot water is greater the higher the water temperature, the "bathroom temperature one minute ago" itself is used as feature data x. In this embodiment, the bathroom temperature data and water temperature data one minute ago are used as feature data x, but since bathing environment data is generally relatively stable compared to biological information data, it does not have to be from one minute ago.

[0070] Because peripheral vascular reactivity differs depending on whether bather M's physical condition is in the cold acclimation transition period or cold acclimation period, or the heat acclimation transition period or heat acclimation period, "season" is classified into two values, spring / summer (0) and autumn / winter (1), and is used as feature data x.

[0071] "Elapsed time," "bathroom temperature 1 minute ago," "bathroom temperature 1 minute ago," and "season" are examples of data based on bathing environment information 31. "Elapsed time" can be easily measured by timing unit 17. "bathroom temperature 1 minute ago" and "bathroom temperature 1 minute ago" can be easily measured by bathroom temperature sensor 16 and water temperature sensor 28. "Season" can be obtained from the date of bathing or the day of bathing.

[0072] As shown in Figure 3, the odds ratio for "feature data x" indicates the magnitude of influence of the comparison on the eardrum temperature change when the comparison's influence on the eardrum temperature change is set to "1," for qualitative data such as "age," "gender," and "season" (i.e., "under 20s (0)," "male (0)," and "spring / summer (0)"). For quantitative data such as "height," "heart rate 1 minute ago," "heart rate change 1 minute ago," "heart rate difference 1 minute ago," "rate of change in heart rate from 3 minutes ago 1 minute ago," "elapsed time," "bathroom temperature 1 minute ago," and "bathroom temperature 1 minute ago" increases by "1." Because the odds ratio indicates the magnitude of influence when a change of "1" occurs, features can be compared side by side. "Bathroom temperature 1 minute ago" has the greatest influence on eardrum temperature change and is the largest factor in increasing eardrum temperature change. "Coefficient a" is the value used in Equation 1, as described above. The "coefficient a" is based on the influence (odds ratio in this embodiment) that the feature amount data x has on the amount of change in eardrum temperature due to hot water.

[0073] Of the feature data x, when the influence of "age group" "age 60s or older" on the amount of change in tympanic membrane temperature is set to "1," the odds ratio of "age group 60s or older" is smaller than "1," and it contributes to suppressing the increase in the amount of change in tympanic membrane temperature. When the influence of "age group 20s or younger" on the amount of change in tympanic membrane temperature is set to "1," the odds ratio of "season" "autumn / winter" is smaller than "1," and it contributes to suppressing the increase in the amount of change in tympanic membrane temperature. The odds ratio of "heart rate change one minute ago" and "heart rate difference one minute ago" are also smaller than "1," and they contribute to suppressing the increase in the amount of change in tympanic membrane temperature. These data are set to negative values for "coefficient a," and act to lower the prediction probability p.

[0074] On the other hand, among the feature data x, when the influence of "30s to 50s" on the change in tympanic membrane temperature for "under 20s" is set to "1," the influence of "female" on the change in tympanic membrane temperature for "male" is set to "1," and the influence of "autumn / winter" on the change in tympanic membrane temperature for "spring / summer" is set to "1," the odds ratio is smaller than "1," contributing to suppressing the increase in the change in tympanic membrane temperature. The odds ratios of "height," "heart rate one minute ago," "rate of change in heart rate one minute ago from three minutes ago," "elapsed time," "bathroom temperature one minute ago," "water temperature one minute ago," and "season" are larger than "1," contributing to an increase in the change in tympanic membrane temperature. These data are assigned positive values to "coefficient a," which acts to increase the prediction probability p.

[0075] The constant b is set to -101.301.

[0076] <Prediction accuracy of prediction models> Figure 4 shows a cross-tabulation table of judgments. The estimated group of tympanic membrane changes in Figure 4 is the value when the cutoff value of the prediction probability p was set to 22.6%. Area a shows the frequency of "the actually measured tympanic membrane temperature change is 0.4°C or more, and the tympanic membrane temperature change predicted by the prediction model is 0.4°C or more." Area b shows the frequency of "the actually measured tympanic membrane temperature change is 0.4°C or more, and the tympanic membrane temperature change predicted by the prediction model is less than 0.4°C." Area c shows the frequency of "the actually measured tympanic membrane temperature change is less than 0.4°C, and the tympanic membrane temperature change predicted by the prediction model is 0.4°C or more." Area d shows the frequency of "the actually measured tympanic membrane temperature change is less than 0.4°C, and the tympanic membrane temperature change predicted by the prediction model is less than 0.4°C."

[0077] In this embodiment, of the 2,846 bathing data obtained to construct the predictive model of the embodiment, 516 data belonged to region a, 59 data belonged to region b, 231 data belonged to region c, and 2,040 data belonged to region d.

[0078] A prediction model can be evaluated by its recall, precision, and accuracy. Recall is the percentage of cases where the tympanic membrane temperature (core body temperature) actually reached 0.4°C or higher and the predicted tympanic membrane temperature was also determined to be 0.4°C or higher. In other words, recall can be calculated by dividing the number of data points in area a by the number of data points in area a + the number of data points in area b. The recall of this embodiment is 0.899.

[0079] The precision is the percentage of data in which the actual eardrum temperature rise was less than 0.4°C among the data in which the eardrum temperature was predicted to be 0.4°C or higher. In other words, the precision can be calculated by dividing the number of data in area a by the number of data in area a + the number of data in area c. The precision in this embodiment is 0.691.

[0080] The accuracy rate is the percentage of the total data where the actual value matches the predicted value. The accuracy rate can be calculated by (number of data in area a + number of data in area d) / (number of data in area a + number of data in area b + number of data in area c + number of data in area d). The accuracy rate in this embodiment is 0.899.

[0081] The prediction model of this embodiment has a high accuracy rate of 0.899, and it can be seen that the prediction probability p can be calculated with high accuracy.

[0082] Figure 5 is a scatter plot of data used to build a prediction model. The vertical axis of Figure 5 shows the actual value (°C) of the amount of change in tympanic membrane temperature. The horizontal axis shows the prediction probability (%) calculated using the prediction model. sv is the target increase in core body temperature. The target increase in core body temperature sv is a value set as the amount of change in core body temperature at which the bather feels "sweating." cv indicates a cutoff value. The cutoff value cv is a value that distinguishes between cases where it is determined that the core body temperature has reached or exceeded the target increase sv, based on the prediction probability p, and cases where it is determined that the core body temperature has not reached or exceeded the target increase sv. In this embodiment, the target increase in core body temperature sv is set to 0.4°C. The cutoff value cv is set to 22.6%. The cutoff value cv is an example of a "threshold value."

[0083] The bathing navigation program 30's prediction model calculates the predicted probability p rather than the core body temperature itself. Therefore, the bathing navigation program 30 needs a cutoff value cv to determine whether to advise the bather M to exit the bath based on the predicted probability p.

[0084] The prediction model is a prediction aimed at achieving the goal of ensuring a safe bath. Therefore, as a prediction accuracy index, the prediction probability p at which the recall rate is highest should be adopted as the cutoff value cv. However, if we focus only on the recall rate, the precision rate will drop significantly, and the bather M will be prompted to turn on the water before they can feel the thermal effect of the water. This may lead to increased complaints due to a discrepancy with the bather M's sense of the water, and reduce convenience. Therefore, in this embodiment, the prediction probability p at which the recall rate and accuracy rate are equal is adopted as the cutoff value cv.

[0085] <Hot water discharge navigation processing> Next, the aforementioned bathing navigation process will be explained with reference to Figure 6. When the bathing navigation device 2 is powered on, the CPU 11 starts and executes the bathing navigation program 30. When the CPU 11 detects that bather M has entered the bath, it executes the bathing navigation process shown in Figure 6. In this embodiment, the CPU 11 detects bather M's entry into the bath from an increase in water pressure measured by the water pressure sensor 29. Note that the CPU 11 may also detect bather M's entry into the bath from measurement data of a water level sensor that detects the water level of the hot water 72 in the bathtub 71, for example. Alternatively, for example, the CPU 11 may detect whether bather M is entering the bath using a human presence sensor.

[0086] The CPU 11 first notifies the user IF 13 of start information (S10). For example, the CPU 11 switches the indicator lamp 13b from an off state to a green lit state. This allows the bather M to know that his or her bathing behavior is being monitored by the bathing navigation device 2.

[0087] CPU 11 starts acquiring the heart rate and bathing environment information (S12). For example, wearable device 5 measures the heart rate of bather M at predetermined time intervals (for example, every 1 second) using heart rate sensor 51. CPU 11 acquires the heart rate measured by heart rate sensor 51 from wearable device 5. For example, CPU 11 acquires the water temperature measured by water temperature sensor 28 of sensor device 23 and the bathroom temperature measured by bathroom temperature sensor 16 of main device 21. S12 is an example of a "biometric information acquisition process," a "bathing environment information acquisition process," a "biometric information acquisition step," and a "bathing environment information acquisition step."

[0088] The bathing navigation program 30 acquires bather physical information before executing the bath outlet navigation process. For example, the bathing navigation program 30 acquires bather physical information 33, such as age and height, entered into the smartphone 6 before bather M enters the bathroom 7. This process is an example of a "bather physical information acquisition process" or a "bather physical information acquisition step."

[0089] The CPU 11 determines whether the standby time has elapsed (S13). The CPU 11 waits until the standby time has elapsed (S13: NO). In this embodiment, the standby time is set to three minutes. That is, the CPU 11 does not make a determination based on the predicted probability p until the fluctuation in the heart rate due to body movement has stabilized.

[0090] When the waiting time has elapsed (S13: YES), the CPU 11 executes a predicted probability calculation process to calculate the predicted probability p (S21). S21 is an example of a "predicted probability calculation process" or a "predicted probability calculation step".

[0091] The predicted probability calculation process will be described with reference to Fig. 7. The CPU 11 extracts feature amount data x based on the bathing environment information 31, the biological information 32, and the bather's physical information 33 (S111).

[0092] For example, the CPU 11 extracts the "elapsed time (minutes)," the "bath water temperature (°C) one minute ago," the "bathroom temperature (°C) one minute ago," and the "season" as feature data x based on the bathing time, water temperature data, bathroom temperature data, and bathing start date included in the bathing environment information 31. Furthermore, for example, the CPU 11 extracts the "heart rate one minute ago (bpm)," the "heart rate change one minute ago," the "heart rate difference one minute ago," and the "rate of change in heart rate one minute ago from three minutes ago" as feature data x based on the bather M's bather physical information 33.

[0093] The CPU 11 substitutes the feature data x acquired in S111 into the prediction model shown in Equation 1 to calculate the prediction probability p (S112). The prediction model includes not only feature data x based on the bathing environment information 31 and biometric information 32, but also feature data x based on the bather's physical information 33. The feature data x used in the prediction model is weighted by a coefficient a. The coefficient a for "60s" is set to "-0.978," and the coefficient a for "30s to 50s" is set to "1.245." Therefore, even if bathers "60s or older" and bathers "30s to 50s" bathe in the same bathing environment, there will be a difference in the prediction probability p. Therefore, when determining whether the core body temperature has reached 0.4°C or higher based on the prediction probability p, the influence of age will be taken into account.

[0094] After calculating the predicted probability p, the CPU 11 returns to Fig. 6 and determines whether the calculated predicted probability p is equal to or greater than the cutoff value cv (S22). The cutoff value cv is set to a value at which the recall rate and accuracy rate are equal. Therefore, if it is determined that the deep body temperature is 0.4°C or higher based on the predicted probability p, there is a high probability that the actual deep body temperature is also 0.4°C or higher, and it is expected that the determination will be satisfactory to the bather M.

[0095] When the CPU 11 determines that the predicted probability p is equal to or greater than the cutoff value cv (S22: YES), that is, when it predicts that the core body temperature will be 0.4°C or higher, it executes a first recommendation process (S41). The first recommendation process is a process for recommending to the bather M to drain the hot water when it predicts that the core body temperature will be 0.4°C or higher.

[0096] For example, as shown in Figure 8(a), the CPU 11 may display a message on the display 13a such as "Your body is warming up. It is now time to get out of the hot water. Get ready to get out of the hot water," or may cause the audio output unit 15 to issue an audio notification. Furthermore, for example, the CPU 11 may switch the indicator lamp 13b from green to yellow, advising the bather M to get out of the bath. This allows the bather M to objectively recognize that his or her body has warmed up to the core, and to get out of the bath after enjoying the thermal effect of the hot water.

[0097] Generally, when the bather's core body temperature rises by about 0.5°C after bathing, the bather M begins to feel sweating or a thermal effect. Therefore, it is desirable to advise the bather to exit the bath when the core body temperature reaches 0.5°C or higher. However, in actual bathing, the body's metabolism is accelerated by actions such as washing the body and pouring water over the bathtub 71, which may cause the core body temperature to rise more quickly than when simply bathing. Therefore, in this embodiment, the bather is advised to exit the bath when the core body temperature reaches 0.4°C or higher. For example, elderly people have a duller sense of temperature than younger people, and even after being advised to exit the bath, they may not feel sweating or a thermal effect, and may continue bathing, significantly deviating from a physiologically safe timing.

[0098] Therefore, the CPU 11 executes the first recommendation process and then determines whether or not the warning condition is met (S42), as shown in Figure 6. The warning condition is a condition for determining whether or not to issue a warning to the bather M whose core body temperature is predicted to be 0.4°C or higher to have the hot water discharged.

[0099] The higher the water temperature, the easier it is for the core body temperature to rise, and the shorter the time it takes to deviate from a physiologically safe timing. Therefore, in this embodiment, the content of the warning condition differs depending on the water temperature. For example, if the water temperature is below 41°C, the warning condition is that a first predetermined time (e.g., 2 minutes) has passed since the first recommendation process was executed. On the other hand, if the water temperature is 41°C or higher, the warning condition is that a second predetermined time (e.g., 1 minute) has passed since the first recommendation process was executed. The second predetermined time is set to be shorter than the first predetermined time.

[0100] If the CPU 11 determines that the warning conditions are not met (S42: NO), it determines whether hot water has been detected (S43). S43 is an example of a "detection process." For example, if the water pressure value measured by the water pressure sensor 29 does not fluctuate, the CPU 11 determines that hot water has not been detected (S43: NO). In this case, the CPU 11 returns to S42 and continues monitoring the bather M.

[0101] After executing the first recommendation process (S41), if the CPU 11 detects hot water outlet (S43: YES) without satisfying the warning condition (S42: NO), the CPU 11 proceeds to S62. For example, if the water pressure value measured by the water pressure sensor 29 decreases, the CPU 11 detects hot water outlet.

[0102] On the other hand, after executing the first recommendation process (S41), if the CPU 11 determines that the warning condition is met (S42: YES), it proceeds to S51 and issues a warning about the hot water being dispensed. S42 and S51 are an example of a "first warning process."

[0103] For example, as shown in FIG. 8(b), the CPU 11 may display a message on the display 13a such as "Your body is getting warmer. Would you like to get out of the water?" or may cause the audio output unit 15 to issue an audio notification. Alternatively, the CPU 11 may switch the indicator lamp 13b from yellow to red to warn the bather M to drain the water. Furthermore, the CPU 11 may use the audio output unit 15 to output a warning sound, such as audio guidance or a buzzer sound. This allows the bathing navigation device 2 to warn the bather M to drain the water before their continued bathing, even after their core body temperature has been determined to be 0.4°C or higher, significantly deviates from a physiologically safe range. Furthermore, by using a different warning method from the recommendation method, the bather M can more easily determine whether or not they need to drain the water.

[0104] Returning to Figure 6, if the CPU 11 determines that the predicted probability p is not greater than the cutoff value cv (S22: NO), that is, if it predicts that the deep body temperature is not greater than 0.4°C, it does not advise the bather M to turn off the water.

[0105] Even if the core body temperature is not above 0.4°C, prolonged bathing may cause large fluctuations in blood pressure or induce drowsiness when the water is released, making bathing unsafe. Therefore, if the CPU 11 determines that the predicted probability p is not equal to or greater than the cutoff value cv (S22: NO), it determines whether the elapsed time has exceeded the water release warning time (S31). The water release warning time is a time set as the amount of time that bathing can be sustained within a physiologically safe range. In this embodiment, the water release warning time is set to 20 minutes.

[0106] If the CPU 11 determines that the elapsed time has not exceeded the hot water discharge warning time (S31: NO), it determines whether the elapsed time has exceeded the hot water discharge recommendation time (S32). The hot water discharge recommendation time is a time set to recommend that the bather M discharge hot water before the hot water discharge warning time has elapsed. In this embodiment, the hot water discharge recommendation time is set to 17 minutes.

[0107] If the CPU 11 determines that the elapsed time has not exceeded the hot water discharge recommendation time (S32: NO), it determines whether hot water discharge has been detected (S34). If the CPU 11 does not detect hot water discharge (S34: NO), it determines whether to make the next determination (S35). The determination of whether to prompt hot water discharge is made periodically. In this embodiment, the determination is made at one-minute intervals. The CPU 11 determines that the next determination will not be made until one minute has passed since the time of prediction execution, i.e., from the time the prediction probability calculation process (S21) was executed (S35: NO). In this case, the CPU 11 returns to S34 and waits while monitoring the bather M until the next determination is made.

[0108] If the CPU 11 determines that one minute or more has passed since the prediction execution time when no hot water is detected (S34: NO), it decides to execute the next determination (S35: YES), returns to S21, and calculates the next prediction probability p.

[0109] Therefore, if the bathing navigation device 2 predicts that the deep body temperature is not above 0.4°C, and there is a high possibility that the bather M is safely bathing until the hot water discharge advice time has elapsed, the bathing navigation device 2 will not issue a notification regarding hot water discharge.

[0110] On the other hand, if the CPU 11 determines that the predicted probability p is not equal to or greater than the cutoff value cv, that is, even if it predicts that the core body temperature is not equal to or greater than 0.4°C (S22: NO), if the elapsed time exceeds the hot water drain recommendation time (S31: NO, S32: YES), it executes the second recommendation process (S33). The second recommendation process is a process for recommending that the bather M drain the hot water when it is not predicted that the core body temperature will be equal to or greater than 0.4°C.

[0111] For example, as shown in Figure 8(c), CPU 11 may display a message on display 13a such as "Ten minutes have passed since you began soaking in the hot water. It's time to get ready to get out," or may cause audio output unit 15 to issue a voice notification. Furthermore, for example, CPU 11 may switch indicator lamp 13b from green to yellow, advising bather M to drain the water. This allows bather M to recognize that the bath time has been prolonged and that it is time to drain the water, even if he or she is not aware of sweating or feeling the thermal effect.

[0112] Returning to FIG. 6, if the CPU 11 that has executed the second recommendation process does not detect hot water being dispensed (S34: NO), it waits while monitoring the hot water being dispensed until the next determination is made (S35: NO), as described above.

[0113] On the other hand, if the CPU 11 detects hot water being dispensed after the second recommendation process is executed (S22: NO, S31: NO, S32: NO, S34: YES), the process proceeds to S62. The process from S62 onwards will be described later.

[0114] Even if the CPU 11 determines that the predicted probability p is not equal to or greater than the cutoff value cv (S22: NO), if it determines that the elapsed time has exceeded the hot water discharge warning time (20 minutes) (S31: YES), it executes a warning process (S51) and warns the bather M to discharge the hot water. S31 and S51 are an example of a "second warning process." Therefore, the bathing navigation device 2 can be expected to make bathers M, who are unaware of sweating or do not feel the effects of the heat, aware that a long bath may make it unsafe to discharge the hot water, and to encourage them to discharge the hot water. Note that the warning process of S51 has been described above, so a detailed explanation will be omitted.

[0115] After executing the warning process, the CPU 11 executes a re-warning process to prompt the user to dispense hot water again (S53).

[0116] An example of the procedure for the re-warning process will be described with reference to the flowchart in Figure 9. CPU 11 resets the number of re-warnings n (n is a natural number) by substituting 0 (S211). CPU 11 determines whether a stop instruction, which is an instruction to stop the warning prompting hot water to be dispensed, has been received (S212).

[0117] For example, when the stop button 13c is operated and a stop instruction is received (S212: YES), the CPU 11 stops the warning (S221). For example, the CPU 11 erases the message that was being displayed on the display 13a. For example, the CPU 11 switches the indicator lamp 13b from a red light state to a green light state. For example, the CPU 11 stops the warning sound output from the audio output unit 15. This allows the bather M to intentionally avoid the discomfort caused by the warning.

[0118] The CPU 11 determines whether or not hot water has been detected (S222). If hot water has been detected (S222: YES), the CPU 11 ends the re-warning process and proceeds to S62 in FIG.

[0119] For example, if the CPU 11 does not detect a change in the water pressure value measured by the water pressure sensor 29, it will not detect hot water being dispensed (S222: NO). In this case, the CPU 11 determines whether 10 minutes have passed since the first warning (S223). Note that the time that has passed since the first warning does not have to be 10 minutes, as long as it is a timing that can prompt the user to safely dispense hot water.

[0120] If the CPU 11 determines that 10 minutes have not yet elapsed since the first warning (S223: NO), the CPU 11 returns to S222 and waits while monitoring the bathing status of the bather M and the time elapsed since the first warning.

[0121] If the CPU 11 does not detect hot water discharge (S222: NO) and determines that 10 minutes have passed since the first warning (S223: YES), it executes emergency warning processing (S231). In the emergency warning processing, a stronger warning is issued than the previous warning because there is a possibility that the bather M may be asleep or unconscious in the bathtub 71. For example, the CPU 11 outputs a loud warning sound or warning message from the audio output unit 15. In addition, the CPU 11 may, for example, cause a hot water supply remote control (not shown) of the hot water supply and heating equipment 8 installed in the kitchen or living room to issue a warning to notify the bather M's family of the abnormality.

[0122] On the other hand, if the stop button 13c is not operated after the first warning, for example, the CPU 11 determines that a stop instruction has not been received (S212: NO). In this case, the CPU 11 determines whether one minute has passed since the previous warning without detecting hot water being dispensed (S213). Note that one minute is a time that takes into account the time it takes to stop the warning and dispense hot water, and a time other than one minute may be used as the standard.

[0123] For example, after issuing a warning to prompt hot water to be dispensed in S51 of FIG. 6, the CPU 11 waits until one minute has elapsed while monitoring the operation of the stop button 13c and the hot water dispense state (S213: NO).

[0124] On the other hand, if the CPU 11 determines that one minute has passed without detecting hot water being dispensed after issuing a warning to prompt the user to dispense hot water in S51 of FIG. 6 (S213: YES), it determines whether the number of re-warnings n is three or less (S214). If the number of re-warnings n is three or less (S214: YES), the CPU 11 executes re-warning processing (S215). For example, as shown in FIG. 8(d), the CPU 11 may display a message on the display 13a saying, "Your body is sufficiently warm. Please get out of the hot water." or cause the audio output unit 15 to issue an audio notification. After issuing the re-warning, the CPU 11 keeps the indicator lamp 13b lit in red. The CPU 11 re-outputs the warning sound using the audio output unit 15.

[0125] After executing the re-warning process, the CPU 11 adds 1 to the number of re-warnings n (S216) and returns to S212. If the CPU 11 receives a stop instruction after the re-warning (S212: YES), it stops the re-warning (S221).

[0126] After the re-warning, if the CPU 11 does not accept a stop instruction (S212: NO) and one minute has passed since the previous re-warning process was executed without detecting hot water being dispensed (S213: YES), the CPU 11 executes the re-warning process in the same manner as above (S214: YES, S215, S216) and returns to S212. The CPU 11 repeats the processes of S213 to S216 without accepting a stop instruction until it has issued a re-warning a maximum of three times.

[0127] If the number of re-warnings n exceeds three (S214: NO), that is, if the warning has been issued four times, the CPU 11 executes emergency warning processing (S231). The emergency warning processing has been described above, so a description thereof will be omitted.

[0128] After executing the emergency warning process, the CPU 11 determines whether a stop command has been received (S232). If the CPU 11 determines that a stop command has been received in response to the operation of the stop button 13c (S232: YES), it stops the emergency warning (S233) and determines whether hot water has been detected (S241). The process of stopping the emergency warning is the same as stopping the warning in S221, so a detailed explanation will be omitted. On the other hand, if the CPU 11 does not receive a stop command (S232: NO), it keeps the emergency warning active and determines whether hot water has been detected (S241).

[0129] If the CPU 11 does not detect hot water dispensing (S241: NO), it returns to S232 and waits while monitoring the operation of the stop button 13c and the bathing status of the bather M. If the CPU 11 detects hot water dispensing (S241: YES), it ends the re-warning process and proceeds to S62 in FIG.

[0130] Returning to FIG. 6, the CPU 11 proceeds to S62 and ends the acquisition of the heart rate and bathing environment information that began in S12 (S62).

[0131] The CPU 11 creates a bathing file 41 and stores information about the bathing that is the subject of the bathing navigation process in the bathing file 41 (S63). The bathing file 41 is stored in a non-volatile area of the memory 12. S63 is an example of a "storage process."

[0132] For example, the CPU 11 creates bathing files 41 with file names including the bathing start date and time so that each file can be distinguished. The CPU 11 stores measurement data showing the water temperature measured by the water temperature sensor 28, the water pressure measured by the water pressure sensor 29, and the bathroom temperature measured by the bathroom temperature sensor 16 in chronological order in the bathing environment information 31. The CPU 11 also determines the season based on the bathing start date and time and stores the determined season in the bathing environment information 31. The CPU 11 also stores the bathtub size that the bather M entered into the bathing navigation device 2 via the smartphone 6 in the bathing environment information 31. The CPU 11 also stores heart rate time series data showing the heart rate measured by the wearable device 5 in chronological order in the biometric information 32. The CPU 11 also stores the gender, age, and height that the bather M entered into the bathing navigation device 2 via the smartphone 6 in the bather's physical information 33. For example, CPU 11 stores the feature data x extracted in S111 of Figure 7 in intermediate variable 34. CPU 11 stores the predicted probability p calculated in S21 of Figure 6 in processing content 35. CPU 11 stores the recommendation content of S41 of Figure 6, the recommendation content of S33, the warning content of S51, the re-warning content of S215 of Figure 9, and the emergency warning content of S233 in processing content 35. Note that if bather M dispenses water before the predicted probability p becomes equal to or exceeds cutoff value cv and before the bathing time has elapsed the water dispense recommendation time, CPU 11 stores "no notification" in processing content 35.

[0133] Thereafter, the CPU 11 notifies the user that the hot water dispense navigation process has ended by turning off the indicator lamp 13b (S64), and ends the hot water dispense navigation process.

[0134] <Update process> As shown in Figure 2, the bathing navigation system 1 automatically updates the prediction model of the bathing navigation program 30 using an update program 81 stored in the hot water supply and heating equipment 8. The hot water supply and heating equipment 8 is an example of an "external device."

[0135] For example, as shown in Figure 10, when the bathing navigation program 30 of the bathing navigation device 2 detects the timing for an update (A1), it sends an update request to the hot water supply and heating equipment 8 using the communication unit 14 (A2). The update request is accompanied by a hot water file 41. The update timing may be, for example, periodically, such as at the end of the month or once a year, or may be when a predetermined number of hot water files 41 have accumulated in the memory 12. A2 is an example of a "sending process."

[0136] When the hot water supply and heating equipment 8 receives the hot water file 41 using the communication unit 83 (A2), it accumulates and stores the received hot water file 41 in the bathing log database (hereinafter referred to as the "bathing log DB") 82 (A3). This allows past bathing-related information to be collected in the bathing log DB 82. AS2 is an example of a "receiving process." A3 is an example of a "bathing history storage process."

[0137] The hot water supply and heating equipment 8 constructs a new prediction model based on the bathing file 41 stored in the bathing log DB 82 (B1). B1 is an example of a "construction process." The hot water supply and heating equipment 8 sends update information to the bathing navigation device 2 using the communication unit 83 (C1). The update information includes information such as the newly constructed new prediction model and the construction date and time. C1 is an example of a "prediction model transmission process."

[0138] When the bathing navigation program 30 receives update information using the communication unit 14, it updates the existing prediction model based on the update information (C2). In other words, the existing prediction model is updated to a new prediction model. C2 is an example of an "update process." The bathing navigation program 30 reduces memory load by deleting the hot water file 41 that was sent to the hot water supply and heating equipment 8 and backed up from memory 12 (C3).

[0139] As described above in detail, the bathing navigation program 30 of this embodiment extracts feature data x by taking into account not only the biometric information 32 and bathing environment information 31 but also the bather's physical information 33, and then substitutes the extracted feature data x into a prediction model to calculate the predicted probability p. Therefore, the bathing navigation program 30 achieves higher prediction accuracy compared to predictions based on the biometric information 32 and bathing environment information 31 without taking the bather's physical information 33 into account. For example, even with the same bathing environment information 31, the calculated predicted probability p varies depending on age and gender. In other words, it is possible to calculate a predicted probability that takes into account elderly people, who are at high risk of bathing accidents. The bathing navigation program 30 compares this predicted probability p with the cutoff value cv to recommend that bather M exit the bath. Therefore, regardless of whether bather M is elderly or young, male or female, it can recommend that bather M exit the bath before a physiologically safe timing is exceeded. Furthermore, the bathing navigation program 30 of this embodiment uses a prediction model to calculate a predicted probability p, which is the probability that the core body temperature will be 0.4°C or higher, rather than the core body temperature itself. This means that the prediction results are less affected by the bather M's body temperature before entering the bath. Therefore, the prediction model that calculates the predicted probability is simpler than a prediction model that takes into account the heat balance from the skin to the core, making it possible to accurately predict the rise in core body temperature without placing an excessive computational load on the device or requiring high computing power. Therefore, the bathing navigation program 30 of this embodiment uses a simple prediction model to accurately predict changes in core body temperature and can recommend that the bather M exit the bath before the timing deviates from a physiologically safe range.

[0140] Note that this embodiment is merely an example and does not limit the present invention in any way. Therefore, the present invention can naturally be improved and modified in various ways without departing from the spirit and scope of the present invention. For example, the biosensor that measures biometric information 32 may be incorporated into a device other than wearable device 5, such as a bathroom remote control for hot water supply and heating equipment 8, or may be a standalone device attached to wall 73 or bathtub 71 of bathroom 7.

[0141] For example, the bathing navigation device 2 may be configured using a hot water supply and heating system 8. For example, if the bathroom remote control of the hot water supply and heating system 8 has a communication function for communicating with external devices such as a wearable device 5 or a smartphone 6, the bathing navigation program 30 may be stored in the control device of the hot water supply and heating system 8. In this case, the bathing navigation program 30 may use the water level sensor, water temperature sensor, and bathroom temperature sensor provided in the hot water supply and heating system 8 instead of the water pressure sensor 29, water temperature sensor 28, and bathroom temperature sensor 16. The bathing navigation program 30 may also use the display, indicator lamps, operation buttons, speaker, and clock of the bathroom remote control instead of the display 13a, indicator lamps 13b, stop button 13c, audio output unit 15, and timer unit 17. The control device of the hot water supply and heating system 8 may also be provided with an update program 81 and a bathing log database 82.

[0142] For example, in the above embodiment, the bathing navigation program 30 displays a management screen on the smartphone 6 to accept settings or changes to the bather's physical information 33. However, the bathing navigation program 30 may also accept settings or changes to the bather's physical information 33 using the user IF 13 of the bathing navigation device 2 or the bathroom remote control of the hot water supply and heating equipment 8. Since this bathing navigation program 30 can acquire the bather's physical information 33 without using the smartphone 6, the bather's physical information 33 can be easily set or changed when a new bather M changes or before bathing. The bathing navigation program 30 may also acquire the bather's physical information after bather M enters the bathroom 7. For example, the bathing navigation program 30 may access a device that stores the bather's physical information 33 and acquire the bather's physical information 33 before calculating the prediction probability p using the prediction model.

[0143] For example, the cutoff value cv does not have to be a value at which the recall rate and the accuracy rate are equal. However, by setting the cutoff value cv to a value at which the recall rate and the accuracy rate are equal, the timing at which the bather M is advised to turn off the water will coincide with the timing at which the bather M begins to sweat or feels the thermal effect, allowing the bather who is advised to turn off the water to enjoy the thermal effect of the water and turn it off.

[0144] For example, steps S42, S51, and S53 in Figure 6 may be omitted. However, the bathing navigation program 30 warns the bather M to turn off the water after a predetermined time has elapsed since predicting that the deep body temperature has reached the target increase amount. This prevents the bather M, whose deep body temperature has reached the target increase amount, from continuing to bathe at a time significantly outside of physiologically safe times.

[0145] For example, the predetermined time set in the warning condition in S42 of Figure 6 may be constant regardless of the water temperature. However, if the bathing navigation program 30 sets the predetermined time set in the warning condition to vary depending on the water temperature, the timing of warning bather M to drain the water will vary depending on the water temperature, and the warning to drain water for bather M whose core body temperature has exceeded the target increase amount can be issued at an appropriate time in accordance with the change in core body temperature.

[0146] For example, steps S31, S51, and S53 in Figure 6 may be omitted. However, if bather M is an elderly person whose core body temperature does not easily rise, and if the bathing time exceeds the water-discharge warning time before the predicted probability p reaches or exceeds the cutoff value cv, the bathing navigation program 30 can prompt bather M to drain the water before it deviates from a physiologically safe timing while taking into account bather M's physical functions.

[0147] For example, steps S32 and S33 in Figure 6 may be omitted. However, the bathing navigation program 30 can make the bather M aware that the bathing time is getting longer by advising the bather M to drain the water before the bathing time exceeds the water drain warning time, thereby urging the bather M to drain the water safely.

[0148] For example, the bathing navigation program 30 does not need to update the prediction model. However, the bathing navigation program 30 stores a bathing file 41 that stores bathing-related information in the memory 12, and updates the prediction model using the stored bathing file 41, thereby refining the prediction model and improving prediction accuracy.

[0149] For example, the bathing navigation program 30 may send an update request in response to a user operation to update the prediction model.The bathing navigation program 30 may also automatically upload the bathing file 41 to an external server to reduce the memory load on the memory 12.

[0150] For example, if the memory 12 of the bathing navigation device 2 has sufficient memory capacity, the update program 81 may be stored in the memory 12, or the bathing file 41 may be accumulated and saved in the memory 12. This allows the bathing navigation device 2 to automatically update the prediction model without relying on an external device.

[0151] For example, the update program 81 and bathing log DB 82 may be stored on an external server on the cloud. In this case, the bathing navigation device 2 may be connected to the server directly, or may be connected to the server via a relay device such as a hot water supply and heating system 8 or a smartphone 6. Multiple bathing navigation devices 2 are connected to the server. This allows the server to collect an unspecified number of bathing files 41 and build a predictive model based on them, thereby enabling the construction of a more precise predictive model than in the above embodiment. The bathing navigation program 30 may update the predictive model in response to a request from the server, or the bathing navigation program 30 may request the server to send the predictive model and download and update the predictive model.

[0152] For example, the bathing navigation program 30 may store the bathing file 41 in an external memory such as an SD card connected to the bathing navigation device 2. External memory and a server are examples of "memory accessible by the bathing navigation device." In this case, the user may export the bathing file 41 stored in the external memory to an information processing device such as a personal computer or mobile terminal, and accumulate and store the file in the information processing device. The information processing device may store the update program 81 in its own device, or may be connected to a server that has the update program 81. The information processing device passes the bathing file 41 to the update program 81 to construct a prediction model, and stores the constructed prediction model in the external memory. When an external memory storing the prediction model is connected to the bathing navigation device 2, the bathing navigation program 30 may obtain the prediction model from the external memory and update the prediction model.

[0153] For example, a user may use an information processing device to download a new predictive model from a server and store it in external memory, and the bathing navigation program 30 may automatically update the existing predictive model using the new predictive model when the external memory is connected to the bathing navigation device 2.

[0154] For example, when an external memory storing an update program 81 is communicatively connected to the bathing navigation device 2, the bathing navigation program 30 may cause the CPU 11 to execute the update program 81, construct a predictive model using the bathing file 41 stored in the memory 12, and update the predictive model.

[0155] Furthermore, in any flowchart disclosed in the embodiments, the execution order of multiple processes in any multiple steps can be changed or they can be executed in parallel as long as no contradiction occurs in the processing content.

[0156] The processes disclosed in the embodiments may be executed by hardware such as a single CPU, multiple CPUs, or ASIC, or a combination thereof. The processes disclosed in the embodiments may be realized in various ways, such as a recording medium on which a program for executing the processes is recorded, or a method. [Explanation of symbols]

[0157] 1. Bathing navigation system 2. Bathing navigation device 5. Wearable devices 11 CPU 12 Memory 13 User Interface 14 Communications Department 28 Water temperature sensor 30 Bathing Navigation Program

Claims

1. A bathing navigation program that can be executed by a bathing navigation device and provides information to a bather soaking in a bathtub, The bathing navigation device includes: a biological information acquisition process for acquiring biological information of the bather; A bathing environment information acquisition process for acquiring bathing environment information, which is information about the bather's bathing environment; a bather's physical information acquisition process for acquiring bather's physical information, which is information about the bather's body; a prediction probability calculation process for extracting feature data significant to a rise in core body temperature based on the biometric information acquired in the biometric information acquisition process, the bathing environment information acquired in the bathing environment information acquisition process, and the bather's physical information acquired in the bather's physical information acquisition process, substituting the extracted feature data into a prediction model for calculating a prediction probability, which is the probability that the bather's deep body temperature will be equal to or greater than a target increase, and calculating the prediction probability; a first recommendation process that advises the bather to remove the hot water if the predicted probability calculated by the predicted probability calculation process is equal to or greater than a threshold, and does not advise the bather to remove the hot water if the predicted probability calculated by the predicted probability calculation process is not equal to or greater than the threshold; Execute A bathing navigation program that is designed to:

2. 2. The bathing navigation program according to claim 1, The threshold is set to a value at which the recall rate and the accuracy rate are equal. A bathing navigation program that is designed to:

3. 2. The bathing navigation program according to claim 1, The bathing navigation device includes: A detection process for detecting the bather's water exit; a first warning process in which, after advising the bather to dispense hot water in the first warning process, if it is determined that the warning conditions are met, the bather is warned to dispense hot water, and if it is determined that the warning conditions are not met, the bather is not warned to dispense hot water; Execute The warning condition is that a predetermined time has elapsed after the first recommendation process has been executed in a state where the hot water discharge has not been detected in the detection process. A bathing navigation program that is designed to:

4. 4. The bathing navigation program according to claim 3, The predetermined time period for the warning condition varies depending on the temperature of the water into which the bather bathes, which is detected by a water temperature sensor of the bathing navigation device. A bathing navigation program that is designed to:

5. 2. The bathing navigation program according to claim 1, The bathing navigation device includes: If the predicted probability calculated in the predicted probability calculation process is not equal to or greater than the threshold value and the bather's bathing time exceeds a water discharge warning time set before a time that deviates from a physiologically safe timing, a second warning process is executed to issue a warning to the bather. A bathing navigation program that is designed to:

6. 6. The bathing navigation program according to claim 5, The bathing navigation device includes: When the bathing time exceeds a hot water outlet recommendation time set before the hot water outlet warning time, a second recommendation process is executed to recommend that the bather take hot water out. A bathing navigation program that is designed to:

7. 2. The bathing navigation program according to claim 1, The bathing navigation device includes: a storage process for storing bathing-related information about bathing in a memory of the bathing navigation device; an update process for updating the prediction model using the bathing-related information stored in the memory; Execute A bathing navigation program that is designed to:

8. A bathing navigation system is a system in which a bathing navigation device capable of executing a bathing navigation program that provides information to a bather soaking in a bathtub is communicably connected to a wearable terminal that measures biological information of the bather, The wearable terminal includes: a transmission process for transmitting the biological information of the bather to the bathing navigation device; Run The bathing navigation device includes: a biometric information acquisition process for receiving the biometric information from the wearable device and storing the biometric information in a memory accessible by the bathing navigation device; A bathing environment information acquisition process for acquiring bathing environment information, which is information about the bather's bathing environment; a bather's physical information acquisition process for acquiring bather's physical information, which is information about the bather's body; a prediction probability calculation process for extracting feature data significant to a rise in core body temperature based on the biometric information acquired in the biometric information acquisition process, the bathing environment information acquired in the bathing environment information acquisition process, and the bather's physical information acquired in the bather's physical information acquisition process, substituting the extracted feature data into a prediction model for calculating a prediction probability, which is the probability that the bather's deep body temperature will be equal to or greater than a target increase, and calculating the prediction probability; a recommendation process for advising the bather to remove the hot water if the predicted probability calculated by the predicted probability calculation process is equal to or greater than a threshold, and not advising the bather to remove the hot water if the predicted probability is not equal to or greater than the threshold; To execute A bathing navigation system that is configured as follows.

9. 9. The bathing navigation system according to claim 8, an external device to which the bathing navigation device is connected; The bathing navigation device includes: A storage process for storing bathing-related information about the bather's bathing for each bathing session; a transmission process of transmitting the bathing-related information to the external device; an update process for updating the existing prediction model with a new prediction model constructed by the external device; Run The bathing-related information includes at least the biological information, the bathing environment information, the bather's physical information, feature data used to calculate the predicted probability, the predicted probability calculated by the predicted probability calculation process, and the content of a notification sent to the bather based on the predicted probability; The external device is a receiving process for receiving the bathing-related information transmitted from the bathing navigation device; a bathing history storage process for accumulating and storing the bathing-related information received in the receiving process; A construction process for constructing the new prediction model based on the bathing-related information stored in the bathing history storage process; a prediction model transmission process for transmitting the new prediction model constructed in the construction process to the bathing navigation device; To execute A bathing navigation system that is configured as follows.

10. A bathing navigation method for providing information to a bather soaking in a bathtub, comprising: a biological information acquisition step of acquiring biological information of the bather; a bathing environment information acquisition step of acquiring bathing environment information, which is information about the bathing environment of the bather; a bather's physical information acquisition step of acquiring bather's physical information, which is information about the bather's body; a prediction probability calculation step in which the computer extracts feature data significant to the rise in core body temperature based on the biometric information acquired in the biometric information acquisition step, the bathing environment information acquired in the bathing environment information acquisition step, and the bather's physical information acquired in the bather's physical information acquisition step, and substitutes the extracted feature data into a prediction model for calculating a prediction probability, which is the probability that the bather's core body temperature will be equal to or greater than a target rise, to calculate the prediction probability; a recommendation step of advising the bather to remove the hot water if the predicted probability calculated in the predicted probability calculation step is equal to or greater than a threshold, and not advising the bather to remove the hot water if the predicted probability is not equal to or greater than the threshold; To do A bathing navigation method configured as follows.

11. A bathing navigation device capable of executing a bathing navigation program that provides information to a bather soaking in a bathtub, A controller; The Communications Department and A user interface; and The controller: a biological information acquisition process for acquiring biological information of the bather; A bathing environment information acquisition process for acquiring bathing environment information, which is information about the bather's bathing environment; a bather's physical information acquisition process for acquiring bather's physical information, which is information about the bather's body; a prediction probability calculation process for extracting feature data significant to a rise in core body temperature based on the biometric information acquired in the biometric information acquisition process, the bathing environment information acquired in the bathing environment information acquisition process, and the bather's physical information acquired in the bather's physical information acquisition process, substituting the extracted feature data into a prediction model for calculating a prediction probability, which is the probability that the bather's deep body temperature will be equal to or greater than a target increase, and calculating the prediction probability; a recommendation process for advising the bather to remove the hot water if the predicted probability calculated by the predicted probability calculation process is equal to or greater than a threshold, and not advising the bather to remove the hot water if the predicted probability is not equal to or greater than the threshold; To execute A bathing navigation device configured as follows:

Images