Menstrual cycle prediction device, menstrual cycle prediction method and menstrual cycle prediction program

Abstract

To provide a menstrual cycle prediction device, a menstrual cycle prediction method and a menstrual cycle prediction program that can accurately predict menstrual cycle without being affected by a user's life environment and life style.SOLUTION: A menstrual cycle prediction device comprises: an acquisition unit for acquiring temperature data including a measured value of a body temperature of a user, and pulsation data including a measured value of cardiac beats or pulses of the user; a determination unit for determining a basic cardiac rate of the user on each date on the basis of the pulsation data; a calculation unit for calculating a representative temperature, which is handled as a deep part body temperature of the user for each date, on the basis of the temperature data in a time zone corresponding to the determined basic cardiac rate; and a prediction unit for predicting information related to the menstrual cycle of the user on the basis of transition in the representative temperature.SELECTED DRAWING: Figure 3

Description

[Technical field]

[0001] The present disclosure relates to a menstrual cycle prediction device, a menstrual cycle prediction method, and a menstrual cycle prediction program. [Background technology]

[0002] By predicting the menstrual cycle (menstrual days), women can accurately estimate the day of ovulation, increase the success rate of pregnancy, and properly manage their physical condition each month. For this reason, there is a high demand for accurate prediction and management of menstrual cycles. In order to predict the menstrual cycle, it is desirable to accurately measure basal body temperature during the menstrual period and understand its trends.

[0003] For example, a technique is known that uses a sensor built into a wristwatch to obtain a stable basal body temperature during sleep (see Patent Document 1 below). Also, a technique is known that obtains a basal heart rate to identify a stable state of the human body, such as deep sleep, and calculates health information of a user based on the basal heart rate (see Patent Document 2 below). [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Publication No. 11-84036 [Patent Document 2] Patent No. 6047346 Summary of the Invention [Problem to be solved by the invention]

[0005] If the user's basal body temperature can be measured accurately, the menstrual cycle can be predicted with high accuracy based on the changes in the basal body temperature. However, measuring basal body temperature is generally difficult. For example, even if the temperature during a certain period of time when going to bed (for example, one hour before and after 4:00 a.m.) is used as in the technology described in Patent Document 1, an accurate temperature may not be obtained due to the floating of the sensor or the influence of sweat depending on the sleeping position.

[0006] In addition, some users go to bed later than normal, or work at night, making it difficult to measure basal body temperature accurately because it is unclear what time of day a stable temperature can be measured for that user.

[0007] Therefore, the present disclosure proposes a menstrual cycle prediction device, a menstrual cycle prediction method, and a menstrual cycle prediction program that are capable of accurately predicting a menstrual cycle without being affected by a user's living environment or lifestyle. [Means for solving the problem]

[0008] In order to solve the above problems, the menstrual cycle prediction device of the present disclosure is characterized by comprising an acquisition unit that acquires temperature data including a measurement value of a user's body temperature and pulse data including a measurement value of the user's heart rate or pulse, a determination unit that determines the user's basal heart rate for each date based on the pulse data, a calculation unit that calculates a representative temperature to be treated as the user's deep body temperature for each date based on the temperature data for a time period corresponding to the determined basal heart rate, and a prediction unit that predicts information regarding the user's menstrual cycle based on a trend in the representative temperature. Effect of the Invention

[0009] According to one aspect of the embodiment, it is possible to accurately predict a menstrual cycle without being affected by a user's living environment or lifestyle. [Brief description of the drawings]

[0010] [Figure 1] FIG. 10 is a diagram illustrating a flow of a menstrual cycle prediction process according to the embodiment. [Figure 2A] FIG. 1 is a diagram for explaining the relationship between body temperature and menstrual cycle. [Figure 2B] FIG. 13 is a diagram for explaining the basal heart rate. [Diagram 3] FIG. 11 is a diagram for explaining a body temperature measurement process according to the embodiment. [Figure 4] FIG. 1 is a diagram illustrating an example of a configuration of a prediction device according to an embodiment. [Diagram 5] FIG. 4 is a diagram illustrating an example of a representative temperature data storage unit according to the embodiment. [Figure 6] FIG. 4 is a diagram illustrating an example of a physiological event data storage unit according to the embodiment. [Figure 7] 4 is a flowchart showing a processing procedure according to the embodiment. [Figure 8] FIG. 2 is a hardware configuration diagram illustrating an example of a computer that realizes the functions of the prediction device. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0011] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the drawings. In the following embodiments, the same components are designated by the same reference numerals, and duplicated descriptions will be omitted.

[0012] (1. EMBODIMENT) (1-1. Overview of Menstrual Cycle Prediction Process According to the Embodiment) Fig. 1 is a diagram illustrating a flow of menstrual cycle prediction processing according to an embodiment. The menstrual cycle prediction processing according to the embodiment is executed by a menstrual cycle prediction system 1 illustrated in Fig. 1. The menstrual cycle prediction system 1 includes a prediction device 100 which is an example of a menstrual cycle prediction device according to the present disclosure, a measuring device 10, and a user terminal 200. Each device included in the menstrual cycle prediction system 1 can transmit and receive data to and from each other via wireless communication or the like.

[0013] The measuring device 10 is a device used to measure body temperature. The measuring device 10 is a so-called wearable device that is stored in the user's clothing, such as underwear, and measures biological information of the user 20 continuously or periodically.

[0014] For example, the measuring device 10 measures the body temperature of the user 20 and stores the measured body temperature daily as temperature data. The measuring device 10 also measures the heart rate or pulse rate of the user 20 and stores the measured heart rate or pulse rate as pulsation data. The measuring device 10 may be realized as a plurality of devices depending on the data to be measured. For example, the measuring device 10 may be composed of a device that measures temperature data and another device that measures pulsation data.

[0015] The user terminal 200 is a terminal device used by the user 20, such as a smartphone or a tablet terminal. An application for controlling the measurement device 10 is installed in the user terminal 200. The user 20 can control the measurement device 10 and refer to the body temperature data and pulse data measured by the measurement device 10 by using the application running on the user terminal 200. The user terminal 200 also acquires the body temperature data and pulse data measured by the measurement device 10 and transmits the acquired data to the prediction device 100. The user terminal 200 also receives the result predicted by the prediction device 100 from the prediction device 100. The user 20 can refer to the result predicted by the prediction device 100 via the user terminal 200.

[0016] The prediction device 100 is an information processing device that acquires temperature data and heartbeat data measured by the measuring device 10 and executes a process of predicting menstruation days, ovulation days, menstrual cycles, etc. of the user 20 based on the acquired data. For example, the prediction device 100 is a cloud server or the like.

[0017] 1, it is assumed that there are many users other than the user 20 who use the measuring device 10. The prediction device 100 can acquire temperature data and heartbeat data from these many users at any time and use the acquired data for statistical processing, etc.

[0018] The prediction device 100 predicts the menstrual period of the user 20, that is, the menstrual cycle. The menstrual cycle is cyclical (biphasic) in that it enters a high temperature phase due to the influence of hormones secreted in association with ovulation, and then enters a low temperature phase after the start of menstruation (monthly period). For this reason, the prediction device 100 is able to predict the pattern of the menstrual cycle to some extent by statistically processing temperature data indicating the body temperature of the user 20.

[0019] In the above-mentioned prediction process, basal body temperature is generally used. Basal body temperature is the body temperature when one is at rest and consuming only the minimum amount of energy necessary to maintain life, and generally refers to the body temperature measured with a thermometer while lying down when waking up in the morning.

[0020] However, as mentioned above, there are difficulties in measuring basal body temperature. For example, even if a wearable device such as the measuring device 10 is used, an accurate temperature may not be obtained due to the sensor floating or sweat depending on the sleeping position. In addition, although it is desirable for the basal body temperature to be the deep body temperature in a deep sleep state (the lowest body temperature in a day), since the living environment and lifestyle, such as sleeping habits, differ from person to person, it is difficult to say that it is optimal to uniformly adopt the body temperature at the time when a person's body temperature is usually the lowest (around 4 a.m.) as the basal body temperature.

[0021] In this regard, there is a correlation between pulse data such as pulse rate and body temperature, and the pulse rate is lower and more stable during non-REM sleep, which is the deeper sleep state, compared to REM sleep and non-REM sleep. Taking advantage of this fact, a method has been proposed for predicting the day of ovulation based on data during non-REM sleep. However, during a day's sleep, people alternate between REM sleep and non-REM sleep every 90 minutes, and even if a certain timing is determined to be non-REM sleep, the pulse rate and body temperature at that time are not necessarily the lowest values. For example, even if the pulse value at the time of non-REM sleep immediately after going to bed, when body temperature fluctuates greatly, is used, the data will vary widely and lack reliability.

[0022] Additionally, a method has been proposed that uses a specified calculation to correct discrepancies in temperature data measured on a certain date, but it is difficult to determine how to convert the discrepancies because temperature changes during sleep vary depending on sleep time, stress, alcohol consumption, medication, and low and high temperature periods.

[0023] As described above, in order to obtain a versatile basal body temperature regardless of the living environment or lifestyle of the user 20, the problem is what data to obtain as the basal body temperature and how to obtain it. That is, the measuring device 10 can continuously measure the body temperature (skin temperature) of the user 20, but the problem is to appropriately determine which time period data of the measured body temperature and how the data should be processed to use as the body temperature of the user 20 on that day. This is because the more accurate the data used as the body temperature of the user 20 on that day is, the more accurately the prediction device 100 can predict the menstrual cycle.

[0024] Therefore, the prediction device 100 according to the embodiment has the configuration described below to solve the above problem. For example, the prediction device 100 acquires temperature data including a measurement value of the body temperature of the user 20 and pulsation data including a measurement value of the heart rate or pulse rate of the user 20. Then, the prediction device 100 determines the basal heart rate of the user 20 for each date based on the pulsation data. Furthermore, the prediction device 100 calculates a temperature (hereinafter referred to as a "representative temperature") to be treated as the deep body temperature of the user 20 for each date based on the temperature data of the time period corresponding to the determined basal heart rate, and predicts information about the menstrual cycle of the user 20 based on the transition of the representative temperature.

[0025] In this way, the prediction device 100 determines the basal heart rate of the user 20, performs a predetermined calculation on the deep body temperature during the time period when the basal heart rate is observed, and treats the calculated value as a representative temperature that corresponds to the basal body temperature of the user 20 on that day. In other words, even when measuring multiple users with different living environments such as sleeping times, the prediction device 100 uses the body temperature corresponding to the basal heart rate that is considered to indicate the most stable state of each user in the prediction process, so that accurate predictions can be made for all users.

[0026] Hereinafter, an overview of the processing performed by the menstrual cycle prediction system 1 will be described with reference to FIGS.

[0027] 1, the user 20 wears the measuring device 10 while sleeping, and continuously measures temperature data indicating the body temperature every day. That is, the measuring device 10 continuously measures the body temperature of the user 20 for each date at predetermined time intervals (e.g., every minute) (step S1).

[0028] In addition, the measuring device 10 continuously measures the heartbeat data including the heart rate or pulse rate of the user 20 for each date at predetermined time intervals (e.g., every minute) together with the temperature data. The measuring device 10 transmits the measured temperature data and heartbeat data to the user terminal 200 sequentially or periodically (step S2).

[0029] The user terminal 200 sequentially or periodically transmits the temperature data and heartbeat data measured by the measuring device 10 to the prediction device 100 (step S3).

[0030] The temperature data transmitted from the user terminal 200 to the prediction device 100 can be shown as a waveform by plotting the body temperature value and the date of measurement, for example, as in the graph 30 shown in Fig. 1. Note that when the user 20 recognizes the day of menstruation, the user 20 can include the date of menstruation in the temperature data and pulse data by registering data indicating the date of menstruation.

[0031] Graph 30 shows temperature data for approximately one menstrual cycle of user 20. Note that graph 30 shows data with a biphasic tendency, with the first half indicating a low temperature period and the second half indicating a high temperature period.

[0032] The prediction device 100 accumulates the acquired temperature data and pulse data (measurement data by the measuring device 10) in the database 50. It is assumed that the prediction device 100 also accumulates previously acquired temperature data and information on past menstrual days and menstrual cycles (hereinafter referred to as "menstrual item data") for each user in the database 50. It is noted that the menstrual item data may include various information that is assumed to affect menstruation, such as the date of menstruation, the number of days in the menstrual cycle, the number of days the low temperature period lasted, the number of days the high temperature period lasted, and events registered by the user 20 (drinking alcohol, catching a cold, exercising, etc.).

[0033] Then, the prediction device 100 identifies the basal heart rate of the user 20 on the target date based on the acquired data, and calculates the representative temperature of the user 20 on that date from the temperature data corresponding to the time when the basal heart rate was observed (step S4). The calculation process will be described in detail later.

[0034] Thereafter, when it becomes possible to predict the next menstrual period or ovulation date based on the representative temperatures accumulated over a predetermined period, the prediction device 100 predicts the next menstrual period or ovulation date and transmits the prediction result to the user terminal 200 (step S5).

[0035] Here, an example of temperature data observed when the technology of the present disclosure is not used is shown in Fig. 2A. Fig. 2A is a diagram for explaining the relationship between body temperature and menstrual cycle. Fig. 2A shows a graph 31 in which body temperature data obtained from a user 20, when the technology of the present disclosure is not used, is plotted by date.

[0036] In graph 31, among the body temperatures observed in the low temperature period, data 32 and data 33 are outliers that deviate from the average value for the low temperature period. For example, data 33 is expected to be close to the value shown as data 34 if there is no measurement error, but in reality, the value is significantly different from the average value for the low temperature period. Data 32 and data 33 are expected to be outliers due to, for example, the user 20 turning over in bed, the floating of the measuring device 10, sweat, or a difference in the time period of measurement.

[0037] In order to prevent such outliers, the prediction device 100 identifies the basal heart rate based on the acquired data, and adopts the temperature data corresponding to the time period in which the basal heart rate that is assumed to be the most stable state for the user 20 is observed as the representative temperature. The basal heart rate generally refers to the heart rate when the user is in the deepest sleep and the body is in the most stable state. Figure 2B shows the relationship between the heart rate and the time of day. Figure 2B is a diagram for explaining the basal heart rate.

[0038] Graph 36 shown in Fig. 2B is a plot of values ​​with the horizontal axis representing the time period during the day when the heart rate is expected to be low (from midnight to 7:00 in the example of Fig. 2B) and the vertical axis representing the number of heart rates measured per minute. In the example of Fig. 2B, time period 37 is the time period during the day when the heart rate is the lowest, and can be said to correspond to the basal heart rate.

[0039] Here, an example of the process of identifying the basal heart rate in the present disclosure will be described. First, the prediction device 100 removes, as outliers, values ​​that are obvious measurement errors (for example, values ​​smaller than 20 bpm (beats per minutes) or values ​​exceeding 200 bpm, etc.) from the pulsation data acquired on the target date. Note that the setting of the outliers is not limited to this, and may be any value.

[0040] Furthermore, the prediction device 100 creates a graph of the heart rate (bpm) on the horizontal axis and the frequency (number of times) of the heartbeat data observed on the date on the vertical axis. This graph shows the heart rate frequency distribution (a distribution centered on the most frequent heart rate in a day). The prediction device 100 then treats the upper limit heart rate value in the area that occupies, for example, 1% from the low heart rate in the heart rate frequency distribution as the basal heart rate. Through this process, the prediction device 100 can specify the basal heart rate after removing extremely low heart rates (the lowest heart rate in a day) that were not removed by the outlier removal.

[0041] The above process is an example, and the prediction device 100 may specify the basal heart rate by any method. For example, in the initial outlier removal, when the prediction device 100 creates a heart rate frequency distribution after removing all values ​​other than those assumed to be when the user 20 is asleep, the prediction device 100 may set the upper limit value in the bottom 10% area as the basal heart rate. In addition, the prediction device 100 may set an arbitrary value of the heart rate frequency (for example, a heart rate observed at 10% of the total frequency) as the basal heart rate, or may set the lower limit value of twice the standard deviation (2σ) of the heart rate during sleep as the basal heart rate.

[0042] Next, the prediction device 100 identifies a time period corresponding to the adopted basal heart rate. For example, if the basal heart rate is observed only once on a date (for example, the basal heart rate is observed only once between "4:00" and "4:01"), the prediction device 100 can identify that time period as the time period corresponding to the basal heart rate.

[0043] When there are multiple time periods corresponding to the basal heart rate, the prediction device 100 can specify the time period by several methods. As an example, the prediction device 100 uses the time period that is closest to "4 o'clock" among the multiple time periods. This is because, empirically, 4 o'clock is the time period in which the most stable body temperature and heartbeat data of a human being are observed.

[0044] Alternatively, the prediction device 100 may use all of the multiple time periods in which the basal heart rate was observed to perform subsequent processing. As described below, the representative temperature can be calculated by setting various calculation times, but for example, when the calculation time of the representative temperature is relatively short (such as one minute), the prediction device 100 uses multiple time periods. Alternatively, when the calculation time of the representative temperature is relatively long (such as one hour), the prediction device 100 may use a time closer to dawn among the multiple time periods in which the basal heart rate was observed.

[0045] Next, an example of a method for calculating a representative temperature based on temperature data measured during a time period corresponding to a basal heart rate after the time period corresponding to the basal heart rate is determined will be described. Fig. 3 is a diagram for explaining a body temperature measurement process according to an embodiment. Specifically, Fig. 3 shows a schematic side view of the torso of a user 20 wearing a measuring device 10.

[0046] As described above, the measuring device 10 is placed in contact with the torso of the user 20, and measures the body temperature of the user 20 by a sensor. That is, the measuring device 10 can measure a stable body temperature by measuring the body temperature of the trunk such as the chest, not of the extremities such as the fingers or arms. However, the body temperature measured by the measuring device 10 is the skin temperature of the user 20. In order to grasp the body temperature of the user 20 more accurately, it is desirable to obtain the deep body temperature of the user 20, and therefore the measuring device 10 calculates the deep body temperature of the user 20 based on the skin temperature and the temperature of the outside air. If possible, the measuring device 10 may measure the rectal temperature or digestive temperature to obtain the deep body temperature, but considering that the user 20 measures his / her body temperature every day, it is not realistic to measure the rectal temperature or digestive temperature to grasp the menstrual cycle.

[0047] 3 shows variables used when the measuring device 10 calculates the deep body temperature. The measuring aspect 40 shows the relationship between the heat flow I of the deep body temperature of the user 20, the contact of the measuring device 10 with the skin of the user 20, the position where the measuring device 10 measures the temperature, and the flow of the heat flow from the deep part of the user 20, based on the concept of the heat flow I of the deep body temperature of the user 20. In addition, a schematic diagram 41 shows the flow of the heat flow I shown in the measuring aspect 40.

[0048] The measuring device 10 measures the skin temperature Ts on the skin surface 45 of the user 20 in order to calculate the deep body temperature Tb of the user 20. Furthermore, in order to take into account the influence of the outside air, the measuring device 10 measures the outside air temperature Ta on the side opposite the skin surface 45. For example, the outside air temperature Ta is the temperature inside the clothes of the user 20 in which the measuring device 10 is housed.

[0049] 3, the deep body temperature Tb is subjected to resistance Rs, which is an influence in the human body of the user 20, before being observed by the measuring device 10. The measuring device 10 also calculates the deep body temperature Tb by taking into account resistance Rd, which is an influence inside the measuring device 10. As an example, the measuring device 10 calculates the deep body temperature Tb based on the following formula.

[0050]

number

[0051] As shown in the above formula (1), the core body temperature Tb can be calculated from the constant K obtained by dividing the resistance Rs by the resistance Rd, and the measured values ​​of the skin temperature Ts and the outside air temperature Ta. In this case, the constant K may be, for example, a predetermined value obtained in advance from the measurement results of multiple subjects and set as an initial value, or may be calculated from the measurement results for each subject. For example, in order to calculate the constant K for each subject, the above formula (1) is modified as follows.

[0052]

number

[0053] The above formula (2) indicates that the constant K can be calculated as a slope α when the horizontal axis represents the outside air temperature Ta and the vertical axis represents the skin temperature Ts. That is, the measuring device 10 can calculate the slope α using the outside air temperature Ta and the skin temperature Ts obtained while the user 20 is asleep, for example, and calculate the constant K from the slope α.

[0054] The measuring device 10 may also remove outliers from the calculated deep body temperature. Outliers of the deep body temperature appear, for example, when the user 20 turns over in bed and the measuring device 10 floats off the skin, there is an effect of sweat, the body temperature rises due to turning over in bed, or a heat source (for example, a pet, another person, a heated carpet, etc.) is placed near the user 20. The measuring device 10 can, for example, determine whether the measuring device 10 is floating off the user 20 using a contact sensor provided in the measuring device 10 itself, and remove the measurement value when determining whether the measuring device 10 is floating in advance. Alternatively, the measuring device 10 may remove the measurement value when the amount of change from the previous measurement is greater than a predetermined value, or when the outside air temperature exceeds the skin temperature, or when the difference between the skin temperature and the outside air temperature is extremely small, as an outlier.

[0055] When the deep body temperature is obtained in this manner, the prediction device 100 determines the representative temperature of the user 20 on that date from the time period corresponding to the obtained deep body temperature and basal heart rate.

[0056] As an example, the prediction device 100 adopts the average or median of the deep body temperature in a predetermined time range centered on the time period corresponding to the basal heart rate as the representative temperature. The predetermined time range can be set to, for example, one minute before and after the time period corresponding to the basal heart rate, a range of up to one hour centered on the time period corresponding to the basal heart rate, or any time in between.

[0057] In addition, when the calculation range time of the representative temperature is set short (for example, 1 minute), there is a possibility that a valid temperature will not exist due to the influence of the removal of outliers of the deep body temperature. In this case, the prediction device 100 may adopt the temperature at the time closest to the calculation range time, or may adopt a value obtained by interpolating the deep body temperatures before and after the deep body temperature removed as an outlier using a predetermined function.

[0058] Furthermore, if the calculation range time of the representative temperature is set long (for example, one hour), the basal heart rate may be observed multiple times within that range, and it may be difficult to determine which data should be valid. In such a case, the prediction device 100 may use the body temperature around 4 o'clock, when the body temperature is expected to be the lowest. Furthermore, since the above-mentioned inconveniences are likely to occur if the calculation range time of the representative temperature is set too long, the prediction device 100 may set the calculation range time of the representative temperature to be less than one-third of the bedtime.

[0059] In the above process, the measuring device 10 and the prediction device 100 can determine whether the user 20 is asleep. For example, the measuring device 10 and the prediction device 100 use an acceleration sensor provided in the measuring device 10 and the user terminal 200 to determine that the user 20 has gone to sleep when the change in acceleration becomes small. Alternatively, when the measuring device 10 is attached to the trunk, the measuring device 10 and the prediction device 100 may determine whether the user 20 has gone to sleep by determining that the user 20 has turned sideways from the direction of acceleration. As an example, the prediction device 100 determines that the user 20 has turned sideways when the gravitational acceleration in the body length direction of the user 20 becomes equal to or less than a threshold based on the gravitational acceleration of the three-axis acceleration. In addition, the prediction device 100 may accept the registration of the bedtime reported by the user 20 based on the input operation of the user 20.

[0060] Next, when the representative temperatures are calculated over several days, the prediction device 100 can predict the menstrual period or ovulation date of the user 20.

[0061] For example, if a representative temperature that is 0.2 degrees or more higher than the average representative temperature for the past six days is observed for three consecutive days, the prediction device 100 can predict that the day before those three consecutive days will be the ovulation day (the transition from the low temperature period to the high temperature period) for the user 20.

[0062] The prediction device 100 can predict the menstrual day of the user 20 by adding 14 days, which is a general number of days in the high temperature period, to the predicted ovulation day. Note that, when the prediction device 100 holds information on the past menstrual cycle of the user 20, it may calculate the number of days in the high temperature period of the user 20 from the past menstrual cycle of the user 20 and predict the next menstrual day from the calculated number of days in the high temperature period. Furthermore, the prediction device 100 may perform machine learning on the transition of the representative temperature using AI (Artificial Intelligence) or the like, and predict the ovulation day and the next menstrual day using the learned prediction model.

[0063] Furthermore, the prediction device 100 may transmit the prediction result to the user terminal 200. For example, the prediction device 100 transmits the predicted next menstrual date of the user 20 to the user terminal 200 and displays the prediction result on the user terminal 200, thereby presenting the prediction result to the user 20. Note that, when the deviation between the predicted date based on the daily temperature data and the past menstrual cycle is a predetermined value or more (for example, 7 days or more), the prediction device 100 may display a notification or a warning that there is a change in physical condition. Specifically, the prediction device 100 may display, on the user terminal 200, advice to the user 20 regarding symptoms expected due to a deviation in the menstrual date and matters expected as reasons for the irregular menstrual cycle.

[0064] (1-2. Configuration of Prediction Device According to the Embodiment) Next, a configuration of the prediction device 100 that executes the menstrual cycle prediction process according to the embodiment will be described. Fig. 4 is a diagram showing an example of the configuration of the prediction device 100 according to the embodiment.

[0065] 4, the prediction device 100 includes a communication unit 110, a storage unit 120, and a control unit 130. The prediction device 100 may include an input unit (e.g., a keyboard, a mouse, etc.) that receives various operations from an administrator who manages the prediction device 100, and a display unit (e.g., a liquid crystal display, etc.) that displays various information.

[0066] The communication unit 110 is realized by, for example, a network interface controller. The communication unit 110 is connected to a network N (for example, the Internet) by wire or wirelessly, and transmits and receives information to and from the measuring device 10, the user terminal 200, and the like via the network N. For example, the communication unit 110 may transmit and receive information using a communication standard or communication technology such as Wi-Fi (registered trademark), SIM (Subscriber Identity Module), or LPWA (Low Power Wide Area).

[0067] The storage unit 120 is realized by, for example, a semiconductor memory element such as a random access memory (RAM) or a flash memory, or a storage device such as a hard disk or an optical disk. The storage unit 120 has a measurement data storage unit 121, a representative temperature data storage unit 122, and a physiological event data storage unit 123.

[0068] The measurement data storage unit 121 stores the measurement data acquired from the user 20 wearing the measuring device 10. That is, the measurement data storage unit 121 stores the basal body temperature data acquired from the user 20 in the past and the basal body temperature data acquired from the user 20 continuously on a daily basis.

[0069] Next, the representative temperature data storage unit 122 will be described with reference to Fig. 5. Fig. 5 is a diagram showing an example of the representative temperature data storage unit 122 according to an embodiment. As shown in Fig. 5, the representative temperature data storage unit 122 has items such as "user ID", "measurement date and time", and "representative temperature".

[0070] "User ID" is identification information for identifying the user 20, or the measuring device 10 and user terminal 200 used by the user 20. "Measurement date and time" indicates the date and time when the body temperature and pulse rate of the user 20 were measured. "Representative temperature" indicates representative temperature data calculated on the date corresponding to the measurement date and time.

[0071] That is, the prediction device 100 calculates the representative temperature of the user 20 based on the information stored in the measurement data storage unit 121, and stores the calculated representative temperature in the representative temperature data storage unit 122. The prediction device 100 can predict the date of ovulation, the date of the next menstruation, etc. by plotting the representative temperature for each date.

[0072] Next, the physiological information data storage unit 123 will be described with reference to Fig. 6. Fig. 6 is a diagram showing an example of the physiological information data storage unit 123 according to an embodiment. As shown in Fig. 6, the physiological information data storage unit 123 has items such as "user ID", "cycle data", "average number of days in low temperature period", and "average number of days in high temperature period". Note that Fig. 6 conceptually shows a portion of the data stored in the physiological information data storage unit 123 as "B01", but in reality, various data described later are stored.

[0073] The "user ID" corresponds to the same item shown in FIG. 5. The "cycle data" is data related to the menstrual cycle of the user 20, and is, for example, various data such as the past menstrual dates, menstrual cycles, and representative temperatures of the user 20. The cycle data may be a prediction result by the prediction device 100, or may be data such as menstrual dates and menstrual cycles registered by the user 20. The "average number of days in the low temperature period" indicates the average number of days in the low temperature period of the user in the menstrual cycle. The "average number of days in the high temperature period" indicates the average number of days in the high temperature period of the user in the menstrual cycle. When the date of the change point of the low temperature period or the high temperature period is determined by observing the representative temperature, the prediction device 100 can predict the next menstrual date or ovulation date using the average number of days in the low temperature period or the average number of days in the high temperature period of the user.

[0074] Returning to Fig. 4, the explanation will be continued. The control unit 130 is realized by, for example, a central processing unit (CPU), a micro processing unit (MPU), a graphics processing unit (GPU), or the like executing a program stored inside the prediction device 100 using a RAM or the like as a working area. The control unit 130 is also a controller, and is realized by, for example, an integrated circuit such as an application specific integrated circuit (ASIC) or a field programmable gate array (FPGA).

[0075] As shown in FIG. 4, the control unit 130 includes an acquisition unit 131, a determination unit 132, a calculation unit 133, and a prediction unit 134.

[0076] The acquisition unit 131 acquires various information. For example, the acquisition unit 131 acquires temperature data (body temperature) measured by the measurement device 10, which is a wearable device attached to the torso of the user 20, from the measurement device 10. Specifically, the acquisition unit 131 controls a program (app) installed in the user terminal 200, and acquires temperature data from the user terminal 200 at the timing when the temperature data is acquired by the user terminal 200, at a fixed time every day, etc.

[0077] Furthermore, the acquiring unit 131 acquires beat data including a measurement value of the heartbeat or pulse of the user 20. For example, the acquiring unit 131 may acquire beat data measured by the measuring device 10, or may acquire beat data from a device other than the measuring device 10 (for example, a pulse meter worn on the wrist of the user 20).

[0078] The acquisition unit 131 may acquire not only temperature data, but also any other physical information that is expected to affect the menstrual cycle, such as the age, height, and weight of each user. The acquisition unit 131 acquires such information by accepting input from the user via user registration in an app, for example. In addition, when the measuring device 10 is capable of measuring biological information other than body temperature, the acquisition unit 131 may acquire the biological information together with the temperature data.

[0079] The acquiring unit 131 may acquire body movement data of the user 20 using various sensors included in the measuring device 10 or the user terminal 200. The body movement data is information indicating the body movement of the user 20, such as information indicating that the user 20 is awake or that the user 20 is lying down (asleep). The body movement data may be detected by combining, for example, an acceleration sensor, an inertial sensor, a geomagnetic sensor, and the like.

[0080] Based on the pulsation data, the determination unit 132 determines the basal heart rate of the user 20 for each date. For example, the determination unit 132 determines the basal heart rate of the user 20 using the above-mentioned method based on the pulsation data continuously measured while the user 20 is asleep.

[0081] Specifically, the determination unit 132 identifies the sleeping time zone of the user 20 based on the body movement data and the heartbeat data acquired by the acquisition unit 131. Then, the determination unit 132 determines the basal heart rate and the time zone corresponding to the basal heart rate from the heartbeat data during the sleeping time zone.

[0082] The calculation unit 133 calculates a representative temperature to be treated as the deep body temperature of the user 20 for each date, based on the temperature data for the time period corresponding to the basal heart rate determined by the determination unit 132.

[0083] Specifically, the calculation unit 133 calculates the deep body temperature of the user 20 using the above-mentioned calculation method based on the skin temperature and the outside air temperature measured by the measuring device 10. Then, the calculation unit 133 calculates the deep body temperature in the time period corresponding to the basal heart rate as the representative temperature of the user 20 on that date.

[0084] The prediction unit 134 predicts information about the menstrual cycle of the user 20 based on the transition of the representative temperature. For example, the prediction unit 134 identifies a transition date from a low temperature period to a high temperature period, or from a high temperature period to a low temperature period, based on the transition of the representative temperature calculated over several days. The prediction unit 134 then predicts the next menstrual day or ovulation day of the user 20 by adding the average number of days in the low temperature period or the average number of days in the high temperature period of the user 20, or the average number of days in the low temperature period or the average number of days in the high temperature period of the general public, to the identified date.

[0085] Furthermore, the prediction unit 134 may perform control so that the result of the prediction by the prediction unit 134 is displayed on the user terminal 200. For example, the prediction unit 134 displays the predicted date of the next menstruation on the user terminal 200. Alternatively, the prediction unit 134 displays the predicted date of ovulation on the user terminal 200.

[0086] Furthermore, when a difference between the predicted information on the next menstrual cycle and information on a plurality of past menstrual cycles of the user 20 satisfies a predetermined condition, the prediction unit 134 may perform control so as to display information on the difference to the user 20. For example, when the next menstrual day statistically calculated based on the results of a plurality of past menstrual cycles differs from the predicted next menstrual day by 7 days or more, the prediction unit 134 performs control so as to display a message to that effect on the user terminal 200.

[0087] The user 20 can obtain various information based on the display of the user terminal 200. For example, if the user 20 experiences a large or continuous deviation in her menstrual cycle, she can understand that there is something wrong with her physical condition, and can easily think of the cause of the deviation (caught a cold, was under a lot of stress, or had nothing in particular, etc.) by linking it to changes in her lifestyle and physical condition that occurred during the current menstrual cycle. In this way, the prediction unit 134 allows the user 20 to judge for herself whether she can relax because her physical condition is no different from usual, or whether she should be cautious because something unusual has occurred.

[0088] The prediction unit 134 may provide various information other than the predicted menstrual period to the user 20 via the user terminal 200. When a sign such as an approaching menstrual period is observed in the prediction result, the prediction unit 134 may display (notify) the user 20 with more emphasis than usual. Furthermore, the prediction unit 134 may transmit advice to the user based on the menstrual cycle predicted by the prediction unit 134. For example, the prediction unit 134 may transmit advice regarding the physical condition of the user 20 estimated from the menstrual cycle, the possibility of pregnancy, premenstrual syndrome (PMS), a time when it is easy to lose weight, menopausal symptoms, and the like.

[0089] (1-3. Procedure of menstrual cycle prediction process according to the embodiment) The flow of processing in the above-mentioned menstrual cycle prediction system 1 will be described with reference to Fig. 7. Fig. 7 is a flowchart showing the procedure of processing according to the embodiment.

[0090] The prediction device 100 continuously acquires the body temperature of the user 20 measured by the measuring device 10 at regular intervals (step S101). The measuring device 10 may be provided with a predetermined trigger, such as starting continuous measurement when the skin temperature is observed to be 34°C or higher. This prevents the measuring device 10 from starting continuous measurement at a stage when the user 20 is not yet ready to measure, such as before wearing the measuring device 10. The prediction device 100 may also calculate the deep body temperature of the user 20 from the acquired skin temperature and outside air temperature at this point.

[0091] The prediction device 100 also continuously acquires the heart rate or pulse rate of the user 20 measured by the measuring device 10 at regular intervals (step S102). As an example, the measuring device 10 measures the skin temperature and the outside air temperature every two minutes, and continuously measures pulse data (heart rate or pulse rate) for one minute every 20 seconds. The prediction device 100 appropriately acquires the data measured by the measuring device 10.

[0092] Next, the prediction device 100 determines whether data acquisition for the day has ended (step S103). As an example, when the prediction device 100 determines that the user 20, who was asleep, has woken up and started activity based on the body movement data of the user 20, the prediction device 100 determines that data acquisition for the day has ended. Alternatively, the prediction device 100 may determine that data acquisition for the day has ended when a predetermined time during which the user 20 is usually assumed to be asleep has passed (for example, when the time has passed from 10 p.m. of the previous day to 8 a.m. of the next day). When data acquisition for the day has not ended (step S103; No), the prediction device 100 continues data acquisition for the day.

[0093] When data acquisition for the day is completed (step S103; Yes), the prediction device 100 removes outliers from the acquired data (step S104). As an example, when the outside air temperature is higher than the acquired skin temperature, the prediction device 100 removes the temperature data acquired at that time. Also, when the skin temperature is below 34°C, the prediction device 100 may remove the data as an outlier. Also, the prediction device 100 calculates, for example, an average value for 10 minutes between two measured values ​​as the deep body temperature corresponding to that time. In this way, the prediction device 100 can remove the influence of sudden outliers, such as when the device floats off the skin at a certain time.

[0094] The prediction device 100 also determines the basal heart rate for the date (step S105). At this time, the prediction device 100 may remove, in advance, values ​​lower than 30 bpm or values ​​exceeding 150 bpm as outliers. The prediction device 100 then identifies the time period during which the user 20 is asleep based on the transition of the measured heart rate, input of the time the user 20 went to bed yesterday upon request, and the like.

[0095] Next, the prediction device 100 determines the area that occupies 1% from the lowest heart rate in the heart rate frequency distribution during sleep (i.e., the 1% limit value of the integral value of the heart rate frequency distribution) as the basal heart rate. Furthermore, the prediction device 100 identifies the time corresponding to the determined basal heart rate (step S106).

[0096] Next, the prediction device 100 identifies the deep body temperature corresponding to the time corresponding to the basal heart rate, and calculates the identified temperature as the representative temperature (step S107). Note that, if the deep body temperature calculated at the relevant time does not have a valid value, the prediction device 100 may use the valid temperature at the nearest time.

[0097] Thereafter, the prediction device 100 determines whether the menstrual day or ovulation day is predictable based on the accumulation of representative temperatures for several days (step S108). If the menstrual day or ovulation day is predictable (step S108; Yes), the prediction device 100 predicts the menstrual day or ovulation day (step S109). The prediction device 100 then notifies the user 20 of the prediction result (step S110). If the menstrual day or ovulation day is not predictable (step S108; No), the prediction device 100 does not perform the prediction process and ends the process.

[0098] (2. Modifications of the embodiment) The above embodiment may be modified in various ways. For example, in the above embodiment, the user terminal 200 according to the present disclosure acquires temperature data and heartbeat data measured by the measuring device 10. However, the user terminal 200 does not necessarily acquire temperature data and the like from the measuring device 10. For example, the measuring device 10 may transmit data directly to the prediction device 100 without passing through the user terminal 200.

[0099] In the embodiment, the user terminal 200 transmits data to the prediction device 100, and the prediction device 100 predicts the menstrual period. However, when the user terminal 200 has a processing unit corresponding to the control unit 130, the user terminal 200 may predict the menstrual period of the user based on the temperature data and the pulse data measured by the measuring device 10. That is, the processing performed by the prediction device 100 in the embodiment may be performed by the user terminal 200.

[0100] In the embodiment, the prediction device 100 has the storage unit 120 and stores the measurement data, physiological data, and the like, but these pieces of information may be stored in an external storage device (such as cloud storage) other than the prediction device 100. The measurement device 10 is not limited to the embodiment shown in Fig. 1, and may be a wearable device such as a smart watch. The device that measures the temperature data and the heartbeat data does not necessarily have to be the same device.

[0101] In addition, while FIG. 2A shows body temperature measured on consecutive days in a menstrual cycle, such body temperature data is sufficient if it is data for a predetermined number of days, such as one menstrual cycle, and is not necessarily limited to data acquired from the user every day. For example, even if there is a missing part due to the user forgetting to measure or measuring incorrectly, the prediction device 100 may interpolate the missing part with data before and after, and acquire the interpolated data as data corresponding to the missing date. In addition, the temperature data and pulse data may be subjected to various modifications in information processing, such as converting the measured numerical value into an arbitrary value and performing calculations and statistics.

[0102] (3. Other embodiments) The processing according to the above-described embodiment may be implemented in various different forms other than the above embodiment.

[0103] For example, among the processes described in the above embodiments, all or part of the processes described as being performed automatically can be performed manually, or all or part of the processes described as being performed manually can be performed automatically by a known method. In addition, the information including the processing procedures, specific names, various data and parameters shown in the above documents and drawings can be changed arbitrarily unless otherwise specified. For example, the various information shown in each drawing is not limited to the illustrated information.

[0104] In addition, each component of each device shown in the figure is a functional concept, and does not necessarily have to be physically configured as shown in the figure. In other words, the specific form of distribution and integration of each device is not limited to that shown in the figure, and all or part of them can be functionally or physically distributed and integrated in any unit according to various loads, usage conditions, etc.

[0105] Furthermore, the above-described embodiments and modifications can be appropriately combined as long as the processing contents are not contradictory.

[0106] Furthermore, the effects described in this specification are merely examples and are not limiting, and other effects may also be obtained.

[0107] (4. Effects of the Menstrual Cycle Prediction Device According to the Present Disclosure) As described above, the menstrual cycle prediction device (prediction device 100 in the embodiment) according to the present disclosure includes an acquisition unit (acquisition unit 131 in the embodiment), a determination unit (determination unit 132 in the embodiment), and a prediction unit (prediction unit 134 in the embodiment). The acquisition unit acquires temperature data including a measurement value of the user's body temperature and pulse data including a measurement value of the user's heart rate or pulse. The determination unit determines the basal heart rate of the user for each date based on the pulse data. The calculation unit calculates a representative temperature to be treated as the deep body temperature of the user for each date based on temperature data for a time period corresponding to the determined basal heart rate. The prediction unit predicts information related to the menstrual cycle of the user based on a transition of the representative temperature.

[0108] In this way, the menstrual cycle prediction device according to the present disclosure determines the basal heart rate that is considered to be the most stable state of the user, calculates the deep body temperature during the time period when the basal heart rate was observed, treats the calculated value as a representative temperature, and performs prediction processing based on this representative temperature. In other words, the menstrual cycle prediction device can predict menstruation days, etc., based on the body temperature at which the physical condition of each user is stable, even for users who do not have stable bedtimes or who work at night. This allows the menstrual cycle prediction device to accurately predict the menstrual cycle without being affected by the user's living environment or lifestyle.

[0109] The acquisition unit acquires body movement data of the user. The determination unit identifies a sleeping time period of the user based on the body movement data and the heartbeat data, and determines a basal heart rate and a time period corresponding to the basal heart rate from the heartbeat data of the sleeping time period.

[0110] In this way, the menstrual cycle prediction device determines whether the user is asleep based on data related to the user's movements, and is therefore able to determine the daily basal heart rate and calculate the representative temperature without requiring any user operation, etc. This allows the menstrual cycle prediction device to achieve prediction processing with excellent usability.

[0111] The acquisition unit also acquires at least one of temperature data and heartbeat data from a wearable device (measurement device 10 in this embodiment) attached to the user's torso.

[0112] In this way, the menstrual cycle prediction device acquires temperature data and the like using a device worn on the user's torso, thereby placing no burden on the user and enabling accurate data measurement to be performed over consecutive days.

[0113] (5. Hardware Configuration) The prediction device 100, user terminal 200, measurement device 10, and other information devices according to the above-described embodiments are realized by a computer 1000 having a configuration as shown in FIG. 8, for example. The prediction device 100 according to the embodiment will be described below as an example. FIG. 8 is a hardware configuration diagram showing an example of a computer 1000 that realizes the functions of the prediction device 100. The computer 1000 has a CPU 1100, a RAM 1200, a ROM (Read Only Memory) 1300, a HDD (Hard Disk Drive) 1400, a communication interface 1500, and an input / output interface 1600. The various components of the computer 1000 are connected by a bus 1050.

[0114] The CPU 1100 operates and controls each unit based on a program stored in the ROM 1300 or the HDD 1400. For example, the CPU 1100 loads the program stored in the ROM 1300 or the HDD 1400 into the RAM 1200 and executes processing corresponding to the various programs.

[0115] The ROM 1300 stores boot programs such as a basic input output system (BIOS) executed by the CPU 1100 when the computer 1000 is started, and programs that depend on the hardware of the computer 1000.

[0116] The HDD 1400 is a computer-readable recording medium that non-temporarily records programs executed by the CPU 1100 and data used by the programs, etc. Specifically, the HDD 1400 is a recording medium that records a program for executing a menstrual cycle prediction process according to the present disclosure, which is an example of the program data 1450.

[0117] The communication interface 1500 is an interface for connecting the computer 1000 to an external network 1550 (e.g., the Internet). For example, the CPU 1100 receives data from other devices and transmits data generated by the CPU 1100 to other devices via the communication interface 1500.

[0118] The input / output interface 1600 is an interface for connecting the input / output device 1650 and the computer 1000. For example, the CPU 1100 receives data from an input device such as a keyboard or a mouse via the input / output interface 1600. The CPU 1100 also transmits data to an output device such as a display, a speaker, or a printer via the input / output interface 1600. The input / output interface 1600 may also function as a media interface for reading a program or the like recorded on a predetermined recording medium. The medium may be, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or a PD (Phase change rewritable Disk), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory.

[0119] For example, when the computer 1000 functions as the prediction device 100 according to the embodiment, the CPU 1100 of the computer 1000 executes a menstrual cycle prediction processing program loaded onto the RAM 1200, thereby realizing functions of the control unit 130, etc. Also, the HDD 1400 stores a program for executing the menstrual cycle prediction processing according to the present disclosure and data in the storage unit 120. Note that the CPU 1100 reads and executes the program data 1450 from the HDD 1400, but as another example, these programs may be obtained from other devices via an external network 1550.

[0120] The above describes the embodiments of the present application in detail based on the drawings. However, these are merely examples, and the present invention can be embodied in other forms that include the aspects described in the Disclosure of the Invention section, as well as in other forms that include various modifications and improvements based on the knowledge of those skilled in the art. [Explanation of symbols]

[0121] 1. Menstrual cycle prediction system 10. Measuring Devices 100 Prediction Device 110 Communications Department 120 Storage section 121 Measurement data storage unit 122 Representative temperature data storage section 123 Physiological data storage unit 130 Control section 131 Acquisition Department 132 Judgment section 133 Calculation section 134 Prediction Department 200 User terminals

Claims

1. An acquisition unit that acquires temperature data including a measured value of a user's body temperature and pulse data including a measured value of the user's heart rate or pulse rate; A determination unit that determines a basal heart rate of the user for each date based on the heartbeat data; A calculation unit that calculates a representative temperature to be treated as a deep body temperature of the user for each date based on the temperature data for a time period corresponding to the determined basal heart rate; a prediction unit that predicts information about the menstrual cycle of the user based on a transition of the representative temperature; A menstrual cycle prediction device comprising:

2. The acquisition unit is Acquire body movement data of the user; The determination unit is identifying a sleeping time period of the user based on the body movement data and the heartbeat data, and determining the basal heart rate and a time period corresponding to the basal heart rate from the heartbeat data of the sleeping time period; The menstrual cycle prediction device according to claim 1 .

3. The acquisition unit is At least one of the temperature data and the heartbeat data is acquired from a wearable device attached to a torso of the user. The menstrual cycle prediction device according to claim 1 .

4. The computer Acquire temperature data including a measurement value of a user's body temperature and pulse data including a measurement value of the user's heart rate or pulse rate; determining a basal heart rate for the user for each date based on the heartbeat data; Calculating a representative temperature to be treated as the deep body temperature of the user for each date based on the temperature data for the time period corresponding to the determined basal heart rate; predicting information about the user's menstrual cycle based on the transition of the representative temperature; A method for predicting a menstrual cycle.

5. Computer, An acquisition unit that acquires temperature data including a measured value of a user's body temperature and pulse data including a measured value of the user's heart rate or pulse rate; A determination unit that determines a basal heart rate of the user for each date based on the heartbeat data; A calculation unit that calculates a representative temperature to be treated as a deep body temperature of the user for each date based on the temperature data for a time period corresponding to the determined basal heart rate; a prediction unit that predicts information about the menstrual cycle of the user based on a transition of the representative temperature; A menstrual cycle prediction program characterized by causing the program to function as a menstrual cycle prediction device comprising:

Images