JP2016153978A - Health prediction system and health prediction method - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a health prediction system and a health prediction method capable of predicting a health status of a woman to be measured on the basis of a menstruation cycle of the woman.SOLUTION: A storage device 31A of a processing device 31 accumulates body temperature data D3 of a plurality of days, a mental index MI, which is an index of emotion, and a physical condition index PCI, which is an index of a body condition. The processing device 31 calculates an average low temperature period day NLm and an average high temperature period day NHm on the basis of the body temperature data D3, etc. accumulated in the storage device 31A. The processing device 31 specifies a stage, among first to eighth stages S1-S8 in the menstruation cycle, corresponding to a stage Sa of a predictive day on the basis of the average low temperature period day NLm and the average high temperature period day NHm. The processing device 31 estimates a health status of a measured person H on the predictive day on the basis of the mental index MI and the physical condition index PCI in the stage Sa on the predictive day and meteorological information for the predictive day.SELECTED DRAWING: Figure 5

Description

  The present invention relates to a health prediction system and a health prediction method for predicting the health state of a measurement subject.

  In order to grasp the hormonal balance situation of a woman, a method of measuring basal body temperature using various measuring devices and recording changes in basal body temperature over several months is known (for example, see Patent Document 1). ). Patent Document 1 discloses a configuration for predicting the next ovulation period or menstrual period based on body temperature data accumulated in advance for a plurality of days.

JP 2014-176737 A

  By the way, in the case of women, the health condition such as physical condition and emotion may vary with the menstrual cycle. There is a great demand for working women to be able to grasp or predict such changes in health status, not just in the ovulation period or menstrual period. On the other hand, the system described in Patent Document 1 predicts the next ovulation period or menstrual period, but does not predict changes in physical condition or emotions, and does not sufficiently respond to the needs of women. In addition, weather information such as season, temperature, and barometric pressure has been said to be related to women's health status, but the relationship between such weather information and women's health status has not been fully studied. There is a problem.

  The present invention has been made in view of the above-described problems, and an object of the present invention is to provide a health prediction system and a health prediction method that can predict the health state of a measurement subject based on a woman's menstrual cycle. It is in.

  In order to solve the above-mentioned problem, the invention of claim 1 is a health prediction in which the processing device predicts the health condition of the subject using a series of body temperature data obtained by measuring the subject's body temperature over a plurality of days. The processing apparatus includes: a predicted date stage identifying unit that identifies a predicted date stage within a menstrual cycle using the body temperature data series; and a predicted date stage identified by the predicted date stage identifying unit And a health condition predicting means for predicting the health condition on the prediction date based on.

  In the invention of claim 2, the predicted date stage specifying means is based on the transition time specifying means for specifying the transition time from the low temperature period to the high temperature period in the menstrual cycle, and the transition time specified by the transition time specifying means. Stage determining means for determining the stage of the prediction date.

  According to a third aspect of the present invention, the processing apparatus further includes storage means for storing the health condition of the measurement subject over a plurality of days, and the health condition prediction means is specified by the prediction date stage specifying means. The health state on the prediction date is predicted based on the prediction date stage and the health state of the same stage as the prediction date stage stored in the storage unit.

  According to a fourth aspect of the present invention, there is further provided an emotion determination unit that determines an emotion based on the voice of the measurement subject, and the storage unit stores information on the emotion determined by the emotion determination unit as the health state. .

  According to a fifth aspect of the present invention, the information processing apparatus further includes an anemia degree determination unit that determines an anemia degree based on an image on the back side of the subject's eyelid, and the storage unit stores information on the anemia degree determined by the anemia degree determination unit. Is stored as the health status.

  In the invention of claim 6, the processing device further includes weather information acquisition means for acquiring weather information of the prediction date, and the health state prediction means is a stage of the prediction date specified by the prediction date stage specifying means. And the health condition on the predicted date is predicted based on the weather information on the predicted date acquired by the weather information acquiring means.

  The invention of claim 7 is a health prediction method for predicting a health condition of the subject by a processing device using a series of body temperature data obtained by measuring the subject's body temperature over a plurality of days, wherein the body temperature data A prediction date stage specifying means for specifying a prediction date stage in the menstrual cycle using a sequence of the above, and a health for predicting a health condition on the prediction date based on the prediction date stage specified by the prediction date stage specifying means State prediction means.

  According to the first and seventh aspects of the invention, the predicted date stage specifying means is based on the body temperature data series, and the measured person is in either the low temperature period or the high temperature period on a prediction date such as today or the near future. And the stage in the menstrual cycle, such as whether or not it is approaching the ovulation period or menstrual period. The health state prediction means can predict the health state of the predicted date such as emotion and physical condition based on the stage of the predicted date specified in this way. As a result, the person to be measured can grasp in advance a health condition such as undulation of emotion or deterioration of physical condition.

  According to the invention of claim 2, the predicted date stage specifying means specifies the transition time from the low temperature period to the high temperature period within the menstrual cycle, and determines the prediction date stage based on the transition time. For this reason, since the stage of the forecast date is specified in consideration of the transition period to the high temperature period, it is not affected by the fluctuation part of the low temperature period compared to the case where the transition period to the high temperature period is not considered, The estimation accuracy of the stage of the prediction date can be increased.

  According to the invention of claim 3, the health condition predicting means is based on the predicted date stage specified by the predicted date stage specifying means and the health condition of the same stage as the predicted date stage stored in the storage means. Predict the health status on the forecast date. Therefore, when predicting the health status based on the relationship between the general menstrual cycle and the health status, the health status is predicted based on the past health status stored for each person to be measured. Compared to the above, it is possible to predict the health state suitable for the measurement subject, and to improve the prediction accuracy of the health state.

  According to the fourth aspect of the present invention, since the apparatus further includes emotion determination means for determining the emotion based on the voice of the measured person, the fluctuation of the emotion can be objectively compared to the case where the measured person inputs the emotion subjectively. I can grasp it.

  According to the fifth aspect of the present invention, since the anemia degree determination means for determining the degree of anemia is further provided based on the image on the back side of the measurement subject's eyelid, the fluctuation of the physical condition can be objectively grasped.

  According to the invention of claim 6, since the weather information acquisition means for acquiring the weather information of the prediction date is further provided, the health condition of the measurement subject is predicted in consideration of the weather information such as season, temperature, and atmospheric pressure. be able to.

It is an external view which shows the state which the to-be-measured person mounted | worn with the wearable sensor apparatus used for embodiment of this invention. It is a front view which shows the wearable sensor apparatus in FIG. It is sectional drawing which looked at the wearable sensor apparatus from the arrow III-III direction in FIG. It is a block diagram which shows the structure of the control unit provided in the wearable sensor apparatus. It is explanatory drawing which shows the health prediction system comprised from the wearable sensor apparatus and the external processing apparatus. It is explanatory drawing which shows a body temperature data series. It is explanatory drawing which shows the menu screen of a portable terminal. It is explanatory drawing which shows an example of the emotion determination screen of a portable terminal. It is explanatory drawing which shows the sound recording state. It is explanatory drawing which shows an example of the emotion determination result screen of a portable terminal. It is explanatory drawing which shows an example of the headache degree input screen of a portable terminal. It is explanatory drawing which shows an example of the anemia degree determination screen of a portable terminal. It is explanatory drawing which shows the measurement state of anemia degree. It is explanatory drawing which shows an example of the anemia index display screen of a portable terminal. It is a flowchart which shows a health forecast process. It is a flowchart which shows the average menstrual cycle days specific process in FIG. It is a flowchart which shows the period average temperature calculation process in FIG. It is a flowchart which shows the determination process of the low temperature period and high temperature period in FIG. It is a flowchart which shows the estimation process of an ovulation period and the menstrual start date in FIG. It is a flowchart which shows the estimation process of the next ovulation period in FIG. It is a flowchart which shows the stage specific process in FIG. It is a flowchart which shows the health condition prediction process in FIG. It is explanatory drawing which shows an example of a menstrual cycle graph. It is explanatory drawing which shows an example of a stage display board. It is explanatory drawing which shows an example of the body temperature data in a menstrual cycle, a heart index, and a body index. It is explanatory drawing which shows an example of the prediction result of the health state when it is favorable. It is explanatory drawing which shows an example of the prediction result of the health condition at the time of malfunction. It is explanatory drawing which shows the measurement state of the anemia degree by a modification.

  Hereinafter, a health prediction system according to an embodiment of the present invention will be described in detail with reference to the accompanying drawings.

  First, a wearable sensor device 1 (hereinafter referred to as a sensor device 1) that constitutes a part of the health prediction system of the present invention will be described.

  As shown in FIGS. 1 to 4, the sensor device 1 is roughly constituted by a casing 2, a body surface temperature detection unit 3, an outside air temperature detection unit 4, a control unit 6, a display unit 11, and the like which will be described later.

  The casing 2 constitutes the main body (main support) of the sensor device 1. As shown in FIGS. 1 to 3, the casing 2 is formed in a substantially elliptical (egg-shaped) box shape using, for example, a resin material, and a circuit board 5 and the like to be described later are accommodated therein.

  The body surface temperature detection unit 3 detects the temperature of the body surface of the person H to be measured. The body surface temperature detection unit 3 is configured by a temperature measuring element such as a thermistor. The body surface temperature detection unit 3 is disposed on the body surface side of the measurement subject H in the casing 2. For this reason, the casing 2 contacts the body surface H0 of the person H to be measured, and the body surface temperature is thermally conducted to the temperature measuring element through the casing 2. Here, the resin material of the part which the body surface temperature detection part 3 of the casing 2 contacts is processed thinly. Thereby, the body surface temperature detection part 3 outputs the signal according to the body surface temperature of the to-be-measured person H by the temperature measuring element.

  The body surface temperature detector 3 is configured to directly detect the body temperature by contacting the body surface H0 of the person H to be measured. However, the present invention is not limited to this, and the body surface temperature detection unit 3 may be configured to indirectly detect the body temperature of the person H to be measured through, for example, underwear, for example, the temperature inside the body of the person H to be measured. It is good also as a structure using the deep part thermometer which detects this.

  The outside air temperature detector 4 detects the outside air temperature. As shown in FIG. 3, the outside air temperature detection unit 4 is located on the opposite side (rear side) of the body 2 of the measurement subject H in the casing 2. A circuit board 5 described later is arranged between the outside air temperature detection unit 4 and the body surface temperature detection unit 3. And since the outside temperature detection part 4 is located in the back side of the casing 2, it detects outside temperature via the casing 2, and outputs the signal according to outside temperature from a temperature measuring element.

  The circuit board 5 is accommodated in the casing 2. As shown in FIG. 4, a circuit board 5 is equipped with a control unit 6 as a reading means composed of a microcomputer or the like. The control unit 6 has an input side connected to the body surface temperature detection unit 3 and the outside air temperature detection unit 4, and an output side connected to a display unit 11 described later. Further, the control unit 6 is provided with a storage unit 7 composed of, for example, a ROM, a RAM or the like as a storage means.

  Here, the storage unit 7 stores in advance a program for operating the control unit 6, a start time ts, an end time te, and a time interval Δt used in the program. The storage unit 7 is configured to store body surface temperature detection data D1, outside air temperature detection data D2, and body temperature data D3, which will be described later, by the operation of the control unit 6.

  At this time, the start time ts and the end time te are set as, for example, 0:00 am (ts = 0: 0 am) and 6:00 am (te = 6: 00 am) as sleeping time, and the time interval Δt is, for example, 10 It is set to a value of about minutes. Note that the start time ts and the end time te are set to the start time and the end time of bedtime if the person H to be measured is a night worker, for example. Also, the time interval Δt is not limited to 10 minutes, and is appropriately set according to the measurement conditions and the like, for example, between about 1 to 30 minutes.

  Further, the control unit 6 has a timer 8 for measuring time, and is connected to a switch unit 9 including, for example, three button switches 9A to 9C. The control unit 6 is driven by a power source 10 such as a coin-type lithium battery mounted on the casing 2, and operates by reading a program from the storage unit 7 by operating the switch unit 9. As a result, when the time by the timer 8 reaches the start time ts, the control unit 6 sets the detected temperature from the body surface temperature detection unit 3 to the detected temperature at regular time intervals Δt from the start time ts to the end time te. The corresponding body surface temperature detection data D1 is read, and the outside air temperature detection data D2 corresponding to the detected temperature is read from the outside air temperature detection unit 4.

  Then, the control unit 6 sequentially stores the body surface temperature detection data D1 and the outside air temperature detection data D2 in the storage unit 7. As a result, the storage unit 7 stores a time-series body surface temperature data group DG1 composed of a plurality of body surface temperature detection data D1 from a start time ts to an end time te, and a time series composed of a plurality of outside air temperature detection data D2. Of the outside air temperature data group DG2.

  The storage unit 7 is a value within a preset allowable temperature range (for example, 32 ° C. to 40 ° C.) of the temperature detection data D 1 and D 2 by the control unit 6 and an allowable temperature change range (for example, ± 1). The data groups DG1 and DG2 are stored with values within (° C./10 minutes) as normal values and values outside the allowable range as abnormal values. Specifically, the temperature detection data D1 and D2 are stored as they are as normal values, and missing data (for example, an error flag that can be distinguished from normal values) is stored as an abnormal value. The allowable temperature range and the allowable temperature change range are not limited to the exemplified values, and may be set as appropriate in consideration of measurement conditions and the like.

  In determining the representative temperature T3, which is an index of basal body temperature fluctuation, the control unit 6 excludes the temperature detection data D1, D2 from the candidates when D1 <D2, and sets the highest value of the temperature detection data D1 on the day. The representative temperature T3 is determined. Since the body surface temperature detection data D1 other than the maximum value is considered to have been affected by the external cooling factor, it is assumed that the casing 2 reflects the deep body temperature under the best conditions when the sensor device 1 is mounted. The highest possible value is determined as the representative temperature T3, and body temperature data D3 corresponding to the representative temperature T3 is stored in the storage unit 7.

  The display unit 11 is provided on the back side of the casing 2 and is configured by a liquid crystal screen or the like. The display unit 11 is connected to the control unit 6 and displays, for example, the driving state of the control unit 6. The display unit 11 constitutes a transfer means for transferring the body surface temperature detection data D1, the outside air temperature detection data D2 and the body temperature data D3 stored in the storage unit 7 to an external processing device 31 described later, and the switch unit 9 By operating, a two-dimensional code such as a QR code (registered trademark) is displayed. Here, the two-dimensional code includes information on the transmission destination address of data such as one day (one night) of data D1 to D3 and URL (Uniform Resource Locator) stored in the storage unit 7. For this reason, the person H to be measured reads information in the two-dimensional code into the portable terminal 21 by using the portable terminal 21 or the like having a two-dimensional code reading function. As shown in FIG. 5, the person H to be measured may access the external processing device 31 from the portable terminal 21 via the communication network NT such as the Internet and transfer data D1 to D3 toward the processing device 31. it can.

  Further, the person H to be measured may input the menstrual start date data by operating the switch unit 9 of the sensor device 1. In this case, the measurement subject H transfers the menstrual start date data to the processing device 31 by performing operations of displaying, reading, and transmitting the two-dimensional code using the sensor device 1 and the portable terminal 21 as described above. be able to.

  The transfer means uses a two-dimensional code display by the display unit 11. However, the present invention is not limited to this, and a connection unit such as a connector for connecting the control unit 6 and the portable terminal 21 described later using, for example, a wired system using a cable connection or a wireless system using infrared or Bluetooth (registered trademark). And the transfer means may be constituted by this connecting portion. Further, for example, the body temperature data D3 and the menstrual start date may be directly accessed by accessing the processing device 31.

  The clip 12 constitutes mounting means for attaching the casing 2 to the subject H. The clip 12 is located on the center side of the casing 2 and covers the surface of the casing 2, and the tip thereof is a free end and is elastically pressed against the casing 2. Further, an opening 12A that penetrates the clip 12 in the thickness direction is provided at a position corresponding to the display unit 11 in the clip 12. Thereby, the display part 11 is visible through the opening part 12A. And clothes etc. can be clamped between the clip 12 and the casing 2. For this reason, as shown in FIG. 1, the clip 12 fixes the sensor device 1 to the abdomen of the person H to be measured by sandwiching underwear such as shorts.

  The sensor device 1 is not limited to the abdomen of the person to be measured H, and may be configured to be fixed to the chest of the person to be measured H, for example. In this case, the clip 12 is attached to an underwear or the like worn at bedtime.

  Next, the portable terminal 21 that constitutes a part of the health prediction system will be described. As shown in FIGS. 5 and 7 to 14, the mobile terminal 21 is configured by, for example, a mobile phone, a smartphone, a tablet terminal, a PDA (Personal Digital Assistant), and the like, and the processing described later is performed through a communication network NT such as the Internet. The device 31 is accessible. The mobile terminal 21 includes a microphone 21A, a camera 21B, and a monitor device 21C, and functions as an emotion determination unit and an anemia degree determination unit by executing a built-in program.

  As illustrated in FIG. 7, when the health prediction system program is executed in the mobile terminal 21, a menu screen 22 on which various operations and processes can be selected is displayed on the monitor device 21 </ b> C. On the menu screen 22, any one of the body temperature data processing unit 23, the emotion data processing unit 24, the physical condition data processing unit 25, and the long-term graph processing unit 26 can be selected.

  When the person H to be measured selects the body temperature data processing unit 23 in the menu screen 22, the body temperature data processing program is activated. Thereby, the portable terminal 21 executes a two-dimensional code reading process and the like to acquire the data D1 to D3 from the sensor device 1 and transfers the data D1 to D3 to the processing device 31.

  When the person H to be measured selects the emotion data processing unit 24 in the menu screen 22, the emotion data processing program is activated. Thereby, the portable terminal 21 functions as an emotion determination means. At this time, as shown in FIG. 8, an emotion determination screen 24 </ b> A for determining the emotion of the person H to be measured is displayed on the monitor device 21 </ b> C of the mobile terminal 21.

  On this emotion determination screen 24A, for example, questions such as “what year, what day, what day of the week is today”, “how is the weather?”, Etc. are displayed. These questions are not limited to the screen output to the monitor device 21 </ b> C, but may be sound output by a speaker (not shown). As shown in FIG. 9, when the person under test H answers this question with voice, the portable terminal 21 records the answer through the microphone 21A. The mobile terminal 21 analyzes the frequency component of the recorded answer voice, for example, by analyzing its frequency component, such as “excitement”, “sadness”, “joy”, “anger”, etc. Is determined in a plurality of stages (for example, 7 stages). Then, the mobile terminal 21 displays the emotion determination result on the emotion determination result screen 24 </ b> B as shown in FIG. 10, and transfers the emotion data thus acquired to the processing device 31. In addition, in the determination of emotion, in addition to the voice of the person to be measured H, the facial expression of the person to be measured H may be considered.

  Based on these emotion data, the processing device 31 calculates a heart index MI that is an index of the quality of emotion. For example, when the emotion component of “joy” is large, it is considered that the emotion is good, so the processing device 31 increases the heart index MI. On the other hand, when the emotion component of “sorrow” or “anger” is large, it is considered that the emotion is disturbed, so the processing device 31 decreases the heart index MI. The heart index MI is displayed as a percentage with the maximum value being 100, for example.

  When the person H to be measured selects the physical condition data processing unit 25 in the menu screen 22, the physical condition data processing program is activated. Thereby, the portable terminal 21 functions as a physical condition determination unit. At this time, the portable terminal 21 acquires the degree of headache (headache index) and the degree of anemia (anemia index) as the physical condition of the person H to be measured.

  More specifically, as shown in FIG. 11, a headache information input screen 25 </ b> A for inputting a headache degree is displayed on the monitor device 21 </ b> C of the mobile terminal 21. At this time, the person H to be measured self-judges the current size of the headache, for example, in six stages from “0” to “5”, and inputs a numerical value corresponding to the size of the headache. Thereby, the portable terminal 21 acquires the input numerical value as a headache degree. In addition, the headache degree is not limited to what is input in 6 steps, but may be input in 2 steps whether or not there is a headache, may be input in 3 to 5 steps, and is input in 7 steps or more. Also good.

  When the input of the headache degree is completed, an anemia determination screen 25B for determining the anemia degree of the person H to be measured is displayed on the monitor device 21C of the portable terminal 21 as shown in FIG. In this anemia determination screen 25B, the screen is switched to a photo shooting screen, and the lower eyelid is pulled downward with the fingertip of the person H to be measured, for example, “Let ’s do it.” Encourage the back side of the lower armpit to be exposed. At this time, for example, a frame-shaped mark 25 </ b> C is displayed on the photo shooting screen in order to arrange the eyeball and the back side portion of the lower eyelid at predetermined positions. As shown in FIGS. 12 and 13, the person H to be measured takes an image around the eyeball with the camera 21 </ b> B built in the portable terminal 21 with the back side portion of the lower eyelid or the like aligned with the mark 25 </ b> C. . The mobile terminal 21 estimates the hemoglobin concentration in the blood, for example, by analyzing the red component or the like of the photographed lower part of the lower eyelid, and determines the degree of anemia (anemia index). The portable terminal 21 totals the acquired data on the degree of anemia over a plurality of days and displays it on an anemia index display screen 25D as shown in FIG. When the acquisition of the headache degree and the anemia degree is completed, the portable terminal 21 transfers these pieces of information to the processing device 31.

  The processing device 31 calculates a body index PCI that serves as an index of physical condition based on the degree of headache and anemia. For example, when the degree of headache or anemia is small, the physical condition is considered good, so the processing device 31 increases the body index PCI. On the other hand, when the degree of headache or anemia is large, it is considered that the physical condition is poor, so the processing device 31 decreases the body index PCI. The body index PCI is displayed as a percentage with the maximum value being 100, for example.

  Further, when the subject H selects the long-term graph processing unit 26 in the menu screen 22, the long-term graph processing program is activated. As a result, the mobile terminal 21 accesses the processing device 31, and multi-day emotion data (heart index MI), physical condition data (body index PCI), ovulation period, menstruation stored in the storage device 31 </ b> A of the processing device 31. Read analysis results such as start date. As shown in FIG. 25, the portable terminal 21 displays the heart index MI and the body index PCI for each measurement date together with the body temperature data D3 for a plurality of days.

  Moreover, the portable terminal 21 displays the menstrual cycle graph 27 which consists of the collection of the bar graph shown in FIG. 23, and the substantially circular stage display board 28 shown in FIG. 24 as an analysis result by the processing apparatus 31.

  Next, the processing apparatus 31 which comprises a part of health prediction system is demonstrated. The processing device 31 uses the body temperature data D3 measured by the sensor device 1 to predict the health state of the measurement subject H on the current or near future prediction date. As illustrated in FIG. 5, the processing device 31 includes, for example, various server computers, and includes a storage device 31 </ b> A (storage means) that includes a ROM, a RAM, and the like. The processing device 31 includes a predicted date stage specifying unit, a health state predicting unit, a transition time specifying unit, a stage determining unit, an ovulation period estimating unit, a weather information acquiring unit, and the like.

  The processing device 31 can access a weather data center 32 such as HP of the Japan Meteorological Agency via the communication network NT. The processing device 31 acquires current and future weather information (weather data) from the weather data center 32. Then, the processing device 31 estimates the health condition of the measurement subject H on the prediction date based on the body temperature data D3 for a plurality of days accumulated in the storage device 31A and the weather information.

  The processing device 31 is not limited to the case where the body temperature data D3 transferred from the sensor device 1 is used. The processing device 31 obtains body temperature data D3 (representative temperature data) based on the body surface temperature data group DG1 and the outside air temperature data group DG2 of the day by performing the same processing as the control unit 6 of the sensor device 1, for example. May be. The storage device 31A of the processing device 31 preferably stores body temperature data D3 for a plurality of cycles. However, in order to specify the stage Sa for the predicted date, for example, body temperature data D3 for one cycle, etc. May be stored.

  The health prediction system according to the present embodiment has the above-described configuration. Next, the health prediction process will be described with reference to FIG.

  Here, when the person H to be measured transfers the daily body temperature data D3 from the sensor device 1 to the processing device 31, the storage device 31A of the processing device 31 stores a plurality of cycles (n in advance) as shown in FIG. It is assumed that the body temperature data D3 of the menstrual cycles MC1 to MCn) is accumulated as a body temperature data series ST0. And the processing apparatus 31 starts the below-mentioned health forecast process by receiving the request command etc. from the to-be-measured person H.

  At this time, the menstrual cycle MC0 indicates the current menstrual cycle, and the menstrual cycle MC1 indicates the menstrual cycle that has just ended. Therefore, the menstrual cycle traced back to the past is shown as it becomes menstrual cycle MC2-MCn.

  First, in step 1, the person H to be measured inputs a menstruation start date and inputs menstrual continuation information such as the presence or absence of bleeding due to menstruation. In addition to this, in Step 1, a prediction date for predicting the health condition is input. The predicted date may be, for example, the current day or a few days later (for example, 2-3 days later). The range of the predicted date may be, for example, a range from the present to the next ovulation period, a range from the present to the next menstruation start date, a range from the present to one cycle after the number of menstrual cycles.

  The menstrual start date and the menstrual continuation information may be input in advance by the sensor device 1 or the like, stored in the storage device 31A, or newly input. The storage device 31A of the processing device 31 stores a plurality of menstrual start dates Ds0 to Dsn and menstrual continuation days DX0 to DXn within a period in which the body temperature data D3 is accumulated. At this time, the menstrual start date Ds0 represents the latest menstrual start date, and the menstrual start date Dsn represents the oldest menstrual start date. Further, the menstrual continuation days DX0 represents the latest menstrual continuation days, and the menstrual continuation days DXn represent the oldest menstrual continuation days.

  In the subsequent step 2, missing data is supplemented from the accumulated body temperature data D3 for n cycles. When missing data occurs due to forgotten measurement, lack of measurement state, etc., for example, linear interpolation is performed using body temperature data D3 on the previous day and the later day to supplement the missing data. Further, the body temperature data D3 deviating from the range of the average value ± 1 ° C. of the corresponding period is considered to be an inappropriate value due to fever or measurement deficiency. For this reason, such body temperature data D3 is also replaced with a value obtained by linear interpolation in the same manner as the missing data. Thereby, the body temperature data series ST0 is converted into a body temperature data series ST1 supplemented with missing data. Note that supplementation of missing data or the like is not limited to linear interpolation, and may be performed using various types of interpolation processing.

  Next, in step 3, as shown in FIG. 16, the average menstrual cycle days specifying process for specifying the average menstrual cycle days Nm is performed. In step 4, as shown in FIG. 17, in the menstrual cycle for determining the low temperature period and the high temperature period (for example, the menstrual cycle MC1 ended immediately before), the body temperature data D3 is averaged to calculate the cycle average temperature Tm. Perform temperature calculation processing.

  In step 5, as shown in FIG. 18, the low temperature period and the high temperature period in the menstrual cycle are determined using the cycle average temperature Tm calculated in step 4. In step 6, as shown in FIG. 19, the estimation process of the ovulation period and the menstrual start date is executed. In step 7, as shown in FIG. 20, the stage Sa of the predicted date within the menstrual cycle (for example, the current menstrual cycle MC0) is specified. In step 8, as shown in FIG. 21, the health state of the prediction date is predicted.

  Finally, in step 9, the health condition prediction result specified in step 8 is output to the mobile terminal 21 and displayed on the monitor device 21 </ b> C of the mobile terminal 21.

  Next, the average menstrual cycle days specifying process in step 3 will be described with reference to FIG.

  In step 11, the self-reporting cycle days N0 is input. The self-report cycle days N0 may be input in advance by the sensor device 1 or the like, stored in the storage device 31A, or newly input.

  In step 12, with the menstrual cycle MC1 that specifies the transition period from the low temperature period to the high temperature period as a reference, the latest three menstrual cycles MC1, the previous menstrual cycle MC2, and the previous menstrual cycle MC3 (menstrual periods). The menstrual cycle days Nmc1 to Nmc3 of the cycles MC1 to MC3) are calculated. Specifically, the menstrual start dates Ds0 to Ds3 for the latest three cycles are read, and the number of days from the day before the menstrual start date Ds0 to the menstrual start date Ds1 is calculated as the first menstrual cycle day number Nmc1. Similarly, the number of days from the day before the menstrual start date Ds1 to the menstrual start date Ds2 is calculated as the second menstrual cycle day Nmc2, and the days from the day before the menstrual start date Ds2 to the menstrual start date Ds3 are calculated as the third menstrual cycle days. Calculate as Nmc3.

  In step 13, it is determined whether or not each menstrual cycle days Nmc1 to Nmc3 are within the normal range based on the self-reported cycle days N0. Specifically, it is normal when the menstrual cycle days Nmc1 to Nmc3 are within the range of 6 days before and after the self-reported cycle days N0 (N0-6 days ≦ Nmc1 to Nmc3 ≦ N0 + 6 days). When it becomes other values, it is determined that it is abnormal.

  Here, the normal range was defined as the range of 6 days before and after the self-reporting cycle number N0. However, the standard of the normal range is not limited to this. For example, it may be in the range of 2 to 8 days before and after the self-reporting cycle days N0, and about 10 to 30% before and after the self-reporting cycle days N0. In other words, it can be set as appropriate in consideration of individual differences of the person to be measured H, measurement conditions, and the like.

  Next, in step 14, it is determined whether or not all the menstrual cycle days Nmc1 to Nmc3 for the latest three cycles are normal. If “YES” is determined in step 14, since the menstrual cycle days Nmc1 to Nmc3 are all within the normal range, the process proceeds to step 15 and the menstrual cycle days Nmc1 to Nmc3 for the latest three cycles are used. The average menstrual cycle days Nm is calculated. Specifically, the average menstrual cycle days Nm is calculated from the average value of normal menstrual cycle days Nmc1 to Nmc3.

  On the other hand, when “NO” is determined in step 14, the process proceeds to step 16 to determine whether or not all the menstrual cycle days Nmc1 to Nmc3 for the latest three cycles are abnormal. If “YES” is determined in step 16, since the menstrual cycle days Nmc1 to Nmc3 are all out of the normal range, the process proceeds to step 17 to calculate the self-reported cycle days N0 as the average menstrual cycle days Nm. To do.

  If "NO" is determined in the step 16, the process proceeds to a step 18 to calculate the average menstrual cycle days Nm using the normal menstrual cycle days Nmc1 to Nmc3 and the self-reported cycle days N0. For example, when two menstrual cycle days Nmc1 and Nmc2 are normal and one menstrual cycle day Nmc3 is not normal, average two menstrual cycle days Nmc1 and Nmc2 and one self-reported cycle day N0. The number of cycle days Nm is calculated. In addition, when one menstrual cycle day Nmc1 is normal and two menstrual cycle days Nmc2 and Nmc3 are not normal, one menstrual cycle day Nmc1 and one self-reported cycle day N0 are averaged to obtain an average menstrual cycle The number of days Nm is calculated.

  Thereby, only the specific menstrual cycle days are not used, and the bias etc. based on the menstrual cycle days can be reduced. When steps 15, 17, and 18 are completed, the process returns.

  When a value after the decimal point is generated in the average menstrual cycle days Nm, the average menstrual cycle days Nm is set to a natural number based on criteria such as rounding up, rounding down, and rounding.

  In addition, the above average menstrual cycle days specifying process is performed on the basis of the latest three menstrual cycles MC1 to MC3 in order to specify the transition period from the low temperature period to the high temperature period for the menstrual cycle MC1 that has just ended. The menstrual cycle days Nm were calculated. However, the present invention is not limited to this. For example, when the transition time is specified for the past mth (m <n) menstrual cycle MCm, the menstrual cycle MCm, the previous menstrual cycle MCm + 1, and the next menstrual cycle. The average menstrual cycle days Nm may be calculated based on the menstrual cycles MCm-1 to MCm + 1 for three cycles before and after MCm-1. Further, the average menstrual cycle days Nm is calculated based on the menstrual cycles MCm-2 to MCm for the immediately following three periods comprising the menstrual cycle MCm, the next menstrual cycle MCm-1 and the subsequent menstrual cycle MCm-2. Also good.

  Next, the periodic average temperature calculation process in step 4 will be described with reference to FIG.

  In step 21, the current menstrual cycle days Nmc1 and the average menstrual cycle days Nm are compared. Specifically, it is determined whether the menstrual cycle days Nmc1 is equal to or less than the average menstrual cycle days Nm.

  If "YES" is determined in the step 21, the process proceeds to a step 22, where the body temperature data D3 of the entire cycle is averaged for the menstrual cycle MC1, the cycle average temperature Tm is calculated, and the process returns.

  On the other hand, if “NO” is determined in step 21, the process proceeds to step 23, where the body temperature data D 3 for the average menstrual cycle days Nm from the last day of the cycle (the day before the menstrual start date Ds 0) is averaged. Then, the cycle average temperature Tm is calculated and the process returns.

  For example, the ovulation of the subject H may be delayed due to stress or the like, and the low temperature period (follicular period) may be prolonged, and the low temperature period may be longer than normal. Thus, it is considered that the menstrual cycle days Nmc1 are longer than the average menstrual cycle days Nm in many cases because the low temperature period is prolonged. In this case, since the average value of the body temperature data D3 for the entire cycle is low, it tends to be an inappropriate reference value for determining the transition from the low temperature period to the high temperature period.

  Therefore, the average menstrual cycle days Nm of the subject H is calculated in advance, and when the menstrual cycle days Nmc1 exceeds the average menstrual cycle days Nm, body temperature data D3 of the average menstrual cycle days Nm from the last cycle date is obtained. A period average temperature Tm is calculated by averaging. As a result, it is possible to prevent the cycle average temperature Tm from excessively decreasing and to omit the body temperature data D3 near the menstrual start date Ns1 that tends to become unstable when calculating the cycle average temperature Tm. As a result, it is possible to prevent a decrease in the cycle average temperature Tm associated with the prolonged low temperature period, and it is possible to calculate a cycle average temperature Tm appropriate as a reference for determining whether or not the high temperature period.

  Next, the low temperature period and high temperature period determination processing in step 5 will be described with reference to FIG.

  In step 31, the body temperature data D3 and the cycle average temperature Tm are compared within a predetermined period. Here, as the predetermined period, for example, as a period in which the transition from the low temperature period to the high temperature period is likely to occur in the menstrual cycle, the menstruation start date that is the 12th day after the menstrual start date Ds1 and is the last day of the cycle Within 16 days from the previous day of Ds0 is set. This is because the Japanese Society of Obstetrics and Gynecology sets the normal range of follicular phase (cold phase) days to 17.9 days ± 6.2 days, and the normal range of luteal phase (high temperature phase) days to 12.7 days ± 1. It is based on what is defined as 6 days. That is, the normal low temperature period exceeds at least 12 days, and the normal high temperature period is considered to be within 16 days.

  Note that the predetermined period for grasping the appropriate transition time is not limited to the above. The predetermined period may be, for example, 10 to 14 days after the menstrual start date Ds1, or may be within 14 to 18 days from the last day of the cycle. That is, the predetermined period can be appropriately set in consideration of individual differences of the person being measured H.

  Next, in step 32, it is determined whether the body temperature data D3 has exceeded the cycle average temperature Tm for two days or more. If "YES" is determined in the step 32, the process proceeds to the steps 33 and 34, the transition period between the high temperature period and the low temperature period is specified, and the high temperature period and the low temperature period are determined. Specifically, it is determined that the body temperature data D3 has shifted from the low temperature period to the high temperature period between the first day and the previous day when the body temperature data D3 exceeds the cycle average temperature Tm for two or more days.

  Therefore, in step 33, the period from the first day to the last day of the cycle when the body temperature data D3 exceeds the cycle average temperature Tm for two or more days is determined as the high temperature period. At this time, the number of days in the high temperature period (number of days in the high temperature period NH) is also calculated. In step 34, the period from the menstrual start date Ds1 to the day before the high temperature period is determined as the low temperature period. At this time, the number of days in the low temperature period (number of days in the low temperature period NL) is also calculated. Then, when step 34 ends, the process returns.

  On the other hand, when “NO” is determined in Step 32, the process proceeds to Step 35, and it is determined that the process has not shifted to the high temperature period. At this time, the low temperature period days NL and the high temperature period days NH are not calculated, and the process returns.

  Next, the ovulation period and menstrual start date estimation processing in step 6 will be described with reference to FIG.

  In step 41, it is determined whether or not the menstrual cycles MC1 to MC3 for the latest three cycles are normal. Specifically, regarding the latest three cycles (menstrual cycles MC1 to MC3), when the transition from the low temperature period to the high temperature period cannot be determined, it is determined to be abnormal. If the transition from the low temperature period to the high temperature period cannot be determined for the latest three cycles (menstrual cycles MC1 to MC3), the low temperature period days NL for the latest three cycles (menstrual cycles MC1 to MC3), It is examined whether the high temperature period days NH and the temperature difference ΔT between the low temperature average temperature TmL and the high temperature average temperature TmH are within the normal range. When these are within the normal range, the menstrual cycles MC1 to MC3 are determined to be normal, and when they are outside the normal range, it is determined to be abnormal. Note that the normal range of the low temperature period days NL, the high temperature period days NH, and the temperature difference ΔT is appropriately set in consideration of individual differences of the person H to be measured.

  In the following step 42, it is determined whether or not the menstrual cycles MC1 to MC3 are all normal. When it is determined that the menstrual cycles MC1 to MC3 are all normal, “YES” is determined in the step 42, and the process proceeds to a step 43.

  In step 43, the average low temperature period days NLm are calculated using the low temperature period days NL1 to NL3 for the latest three cycles. Specifically, the average low temperature period NLm is calculated from the average value of the low temperature period days NL1 to NL3 (NL1 + NL2 + NL3) / 3.

  In the following step 44, the average number of high temperature periods NHm is calculated using the high temperature periods NH1 to NH3 for the latest three cycles. Specifically, the average high temperature period NHH is calculated from the average value of the high temperature periods NH1 to NH3 (NH1 + NH2 + NH3) / 3.

  On the other hand, if “NO” is determined in the step 42, the process proceeds to a step 45 to determine whether or not all the menstrual cycles MC1 to MC3 are abnormal. When it is determined that all the menstrual cycles MC1 to MC3 are not normal, “YES” is determined in the step 45, and the process proceeds to a step 46.

  In step 46, the average number of low-temperature days NLm is set to the average value of each age. Specifically, the average value of the low temperature period days NL in each age is stored in the storage device 31A in advance, and the age of the person H to be measured belongs among the stored average values of the low temperature days NL in each age. Select one and set it to the average low temperature days NLm.

  In the subsequent step 47, the average number of high-temperature days NHM is set to the average value of each age. Specifically, the average value of the high temperature period days NH in each age is stored in the storage device 31A in advance, and the age of the person H to be measured belongs to the stored average value of the high temperature days NH in each age. Select one and set it to the average number of hot days, NHm.

  In addition, the average value of each age may be an average value obtained in an age group at the age of 10 years, for example, teens, 20s, etc., for example, an age group at an age of 5 years, such as in the early 20s and late 20s. The average value obtained in step 1 may be used. Moreover, not only each age but the average value of each age may be sufficient.

  If "NO" is determined in the step 45, the process proceeds to a step 48, and the average low temperature period days NLm is calculated by using the low temperature period days NL1 to NL3 in which the menstrual cycles MC1 to MC3 are determined to be normal. Specifically, when two of the menstrual cycles MC1 to MC3 (for example, menstrual cycles MC1 and MC2) are in the normal range, two values corresponding to these among the low temperature days NL1 to NL3 (for example, the number of low temperature days NL1) , NL2) is calculated from the average value (for example, (NL1 + NL2) / 2) NLm. When only one of the menstrual cycles MC1 to MC3 (for example, menstrual cycle MC1) is determined to be normal, a value corresponding to this (for example, the number of low temperature days NL1) is calculated as the average number of low temperature days NLm.

  Also in the following step 49, the average high temperature is obtained using the processing in which the average low temperature period NLm in step 48 is performed in a similar manner, and the menstrual cycles MC1 to MC3 are determined to be normal among the high temperature periods NH1 to NH3. Calculate the number of days NHm.

  Thereby, only the specific low temperature period days and high temperature period days are not used, and the bias etc. based on the low temperature period days and the high temperature period days can be reduced.

  If the average low temperature days NLm and average high temperature days NHM are generated with a value after the decimal point, the average low temperature days NLm and average high temperature days NHH are calculated based on criteria such as rounding up, rounding down, and rounding. Try to be a natural number.

  In addition, the average low temperature period days NLm are calculated based on the low temperature period days NL1 to NL3 for the latest three cycles. However, the present invention is not limited to this. For example, the average low temperature period NLm may be calculated based on the low temperature period days for the latest one cycle and the latest two cycles, and the average low temperature days for the latest 4 to 6 cycles may be calculated. Based on this, the average low temperature period NLm may be calculated. The same applies to the calculation of the average high temperature days NHM. That is, the average number of high temperature days NHm may be calculated based on the number of high temperature days for the latest one cycle, the latest two cycles, or the latest four to six cycles.

  When Steps 44, 47, and 49 are completed, the process proceeds to Step 50, and the next ovulation period estimation process shown in FIG. 20 is executed. In the following step 51, the next menstrual start date Dsx is estimated based on the current menstrual start date Ds0, the average low temperature period days NLm, and the average high temperature period days NHM. Specifically, the day after the number of days (NLm + NHH) obtained by adding the average low temperature period NLm and the average high temperature period NHH to the current (latest) menstrual start date Ds0 is estimated as the next menstrual start date Dsx.

  Instead of the number of days obtained by adding the average low temperature period NLm and the average high temperature period NHm, the average menstrual cycle days Nm specified by the average menstrual cycle days specifying process in step 3 may be used.

  Next, in step 52, it is determined whether or not there has been a transition to the high temperature period during the current menstrual cycle MC0. Here, in step 52, the presence or absence of the transition to the high temperature period is determined in the middle of the current menstrual cycle MC0. At this time, the body temperature data D3 of the entire menstrual cycle MC0 are not prepared, and the cycle average temperature Tm cannot be obtained. Therefore, the determination method shown in step 32 cannot determine the transition to the high temperature period.

  Therefore, in step 52, it is determined that the transition from the low temperature period to the high temperature period occurs when the body temperature data D3 exceeds the predetermined high temperature period reference temperature, and the transition period from the low temperature period to the high temperature period is specified. At this time, the predetermined high temperature reference temperature is the average value of the body temperature data D3 from the fourth day to the eleventh day of the menstrual cycle MC0 as the low temperature reference temperature as disclosed in, for example, Japanese Patent No. 4933227. In contrast, a value obtained by adding a predetermined temperature difference (for example, 0.3 ° C.) is set.

  The low temperature reference temperature is not limited to the average value of the body temperature data D3 from the fourth day to the eleventh day of the menstrual cycle MC0, but for example, the average of the body temperature data D3 from the first day to the eleventh day of the menstrual cycle MC0 It may be a value or may be specified by other methods. Further, the predetermined temperature difference is not limited to 0.3 ° C., and may be set as appropriate within a range of 0.2 ° C. to 0.4 ° C. in consideration of individual differences of the person H to be measured, for example.

  If “YES” is determined in step 52, the process shifts to step 53 because the shift to the high temperature period has occurred. In step 53, as the next menstrual start date Dsx, the day after the average high temperature period NHH from the transition date Dox to the high temperature period, that is, the day when the average high temperature period NHH has elapsed from the last day of the low temperature period is estimated. As a result, the menstruation start date Dsx estimated in step 51 is updated along with the determination of the transition to the high temperature period, and then the process returns.

  On the other hand, when it is determined as “NO” in step 52, the transition to the high temperature period does not occur, and it is considered that the low temperature period is maintained. Therefore, the menstruation start date Dsx estimated in step 51 is maintained, and the process returns as it is.

  The estimation result of the next ovulation period obtained in step 50 and the next menstrual start date Dsx obtained in steps 51 and 53 may be displayed together with the menstrual cycle graph 27 shown in FIG. 23, for example. You may display separately from the menstrual cycle graph 27 according to the request | requirement and operation of H.

  Next, the process for estimating the next ovulation period in step 50 in FIG. 19 will be described with reference to FIG.

  In step 61, processing similar to that in steps 31 to 33 is executed for the latest three cycles, and the high temperature days NH1 to NH3 for the latest three cycles are calculated. Specifically, it is determined whether or not the body temperature data D3 has exceeded the cycle average temperature Tm for the last 3 cycles (menstrual cycles MC1 to MC3) for 2 days or more, and the body temperature data D3 is the cycle average for 2 days or more. It is determined that the low temperature period has shifted to the high temperature period between the first day when the temperature Tm is exceeded and the previous day. For this reason, the period from the first day when the body temperature data D3 exceeds the cycle average temperature Tm for two or more days to the last day of the cycle is determined as the high temperature period, and the high temperature period days NH1 to NH3 are calculated. When the transition from the low temperature period to the high temperature period cannot be determined, the high temperature period days NH1 to NH3 are not calculated for the menstrual cycles MC1 to MC3. Further, for the menstrual cycles MC1 to MC3 determined to be abnormal in steps 42 and 45 in FIG. 19, the high temperature periods NH1 to NH3 are not calculated.

  In the subsequent step 62, it is determined whether or not all the high temperature periods NH1 to NH3 have been calculated. When it is determined as “YES” in step 62, since the high temperature days NH1 to NH3 are all calculated, the process proceeds to step 63, and the average is calculated using the high temperature days NH1 to NH3 for the latest three cycles. Calculate the number of days of high temperature NHm. Specifically, the average high temperature period NHH is calculated from the average value of the high temperature periods NH1 to NH3 (NH1 + NH2 + NH3) / 3.

  On the other hand, if “NO” is determined in the step 62, the process proceeds to a step 64 to determine whether or not all the high temperature periods NH1 to NH3 for the latest three cycles are not calculated. If “YES” is determined in step 64, it is considered that the transition from the low temperature period to the high temperature period cannot be determined, or the high temperature period days NH1 to NH3 are not calculated due to insufficient data accumulation. For this reason, the process proceeds to step 65, and the average number of high temperature days NHm is set on the 13th, which is generally the number of days with high consistency with the ovulation period, as will be described later.

  If "NO" is determined in the step 64, the process shifts to a step 66, and the average high temperature period NHH is calculated using the calculated one of the high temperature periods NH1 to NH3. Specifically, when only two values (for example, the high temperature period NH1 and the high temperature period NH2) are calculated among the high temperature days NH1 to NH3, the average high temperature is calculated based on the average value (for example, (NH1 + NH2) / 2). Calculate the number of days NHm. Further, when only one value (for example, the number of high temperature days NH1) is calculated among the high temperature days NH1 to NH3, the value (NH1) at this time is calculated as the average high temperature days NHM.

  Thereby, only the specific high temperature period days are not used, but the bias etc. based on the high temperature period days can be reduced.

  When a value after the decimal point is generated in the average high-temperature days NHH, the average high-temperature days NHH is set to a natural number based on criteria such as rounding up, rounding down, and rounding.

  In the above, the average number of high temperature days NHm was calculated based on the number of high temperature days NH1 to NH3 for the latest three cycles. However, the present invention is not limited to this, and the average high temperature days NHm may be calculated based on the number of high temperature days for the latest one cycle and the latest two cycles, and based on the high temperature days for the latest four cycles or more. The average number of high temperature days NHm may be calculated.

  When Steps 63, 65, and 66 are completed, the process goes to Step 67 to specify the next scheduled menstrual start date Ds. Specifically, the date when the average menstrual cycle days Nm specified by the average menstrual cycle days specifying process in step 3 from the current menstrual start date Ds0 is specified as the next scheduled menstrual start date Ds.

  In the following step 68, it is determined whether or not the average number of high temperature days NHm is within a normal range. Specifically, it is determined to be normal if the average number of high-temperature days NHm is within the range of 11 to 16 days, and it is determined to be abnormal when it has a value other than that.

  Here, the range from the 11th to the 16th was defined as the normal range of the average number of high temperature days NHm. However, the standard of the normal range of the average number of high temperature days NHm is not limited to this, and may be, for example, 10 to 17 days, or 12 to 15 days, taking into account individual differences of the subject H, measurement conditions, etc. It can be set appropriately.

  If “YES” is determined in step 68, the process proceeds to step 69, where the ovulation period is within the range of the next two days before and after the next scheduled menstrual start date Ds, centering on the day before the average high temperature period NHm Estimated. For example, if the average number of high-temperature days NHm is 11, the ovulation period is estimated for 5 days from 9 days to 13 days before the menstrual start date Ds. If the average number of high-temperature days NHm is 16, the ovulation period is estimated for 5 days from 14 days to 18 days before the menstrual start date Ds. The same applies when the average high temperature period NHm is 12 to 15 days.

  The predetermined range for estimating the ovulation period is a range of 2 days before and after the average high temperature period NHm before the next scheduled menstrual start date Ds. However, it may be within the range of three days before and after, and can be set as appropriate in consideration of individual differences of the person to be measured H, measurement conditions, and the like.

  On the other hand, when “NO” is determined in step 68, the process proceeds to step 70, and when the average high temperature period number NHm is shorter than 11 days, the average high temperature period number NHm is 11 days that is the minimum number of days in the normal range. Assuming that, the ovulation period is estimated by the same processing as in step 69. That is, when the average number of high-temperature days NHm is shorter than 11 days (NHm <11 days), the ovulation period falls within the range of 2 days before and after the next scheduled menstrual start date Ds. presume.

  In addition, when the average high temperature period number NHm is longer than 16 days, the ovulation period is estimated by the same process as in step 69, assuming that the average high temperature period number NHm is 16 days which is the maximum number of days in the normal range. That is, when the average high temperature period NHm is longer than 16 days (NHm> 16 days), the ovulation period is within the range of 2 days before and after the day 16s before the next scheduled menstrual start date Ds. presume.

  When steps 69 and 70 are completed, the process returns. The estimation result of the ovulation period obtained in steps 69 and 70 may be displayed together with the menstrual cycle graph 27 shown in FIG. 23, for example, and is separated from the menstrual cycle graph 27 according to the request and operation of the person H to be measured. May be displayed.

  Next, the stage specifying process in step 7 will be described with reference to FIG.

  In step 71, the days Ns1 to Ns4 of the first to fourth stages S1 to S4 in the low temperature period are determined. Specifically, the days Ns1 to Ns4 of the first to fourth stages S1 to S4 are set to the number of days (NLm / 4) obtained by dividing the average low temperature period number NLm into four equal parts. When a value after the decimal point is generated in the days Ns1 to Ns4 of each stage S1 to S4, the days Ns1 to Ns4 are set to natural numbers based on criteria such as rounding up, rounding down, and rounding.

  In step 72, days Ns5 to Ns8 of the fifth to eighth stages S5 to S8 in the high temperature period are determined. Specifically, the number of days Ns5 to Ns8 of the fifth to eighth stages S5 to S8 is set to the number of days (NHm / 4) obtained by dividing the average high temperature period number NHm into four equal parts. When a value after the decimal point is generated in the number of days Ns5 to Ns8 of each stage S5 to S8, the number of days Ns5 to Ns8 is made to be a natural number based on criteria such as rounding up, rounding down, and rounding.

  In step 73, it is determined whether or not there is a transition to the high temperature period in the middle of the menstrual cycle including the predicted date (for example, the current menstrual cycle MC0). Specifically, it is determined whether or not there has been a transition to the high temperature period by executing the same determination process as in step 52. At this time, the transition time from the low temperature period to the high temperature period (transition date Dox) is specified as the transition from the low temperature period to the high temperature period when the body temperature data D3 exceeds the predetermined high temperature period reference temperature.

  If "YES" is determined in the step 73, it is considered that the present time is in the high temperature period. Therefore, the process proceeds to step 74, and the number of elapsed days Nx1 from the transition date Dox to the high temperature period to the prediction date is calculated. In the following step 75, the stage Sa of the prediction date is determined based on the transition date Dox and the elapsed days Nx1.

  For example, if the elapsed days Nx1 is 5 days and the days Ns5 to Ns8 of the fifth to eighth stages S5 to S8 in the high temperature period are all 3 days, it is determined that the stage Sa of the forecast date is the sixth stage S6. To do. Further, the number of elapsed days Nx1 is 15, the number of days Ns1 to Ns4 in the first to fourth stages in the low temperature period are all four days, and the number of days Ns5 to Ns8 in the fifth to eighth stages in the high temperature period are all three. If it is a day, it is determined that the stage Sa of the prediction date is the first stage S1. When step 75 ends, the process returns.

  On the other hand, when it is determined as “NO” in step 73, the transition to the high temperature period has not occurred, and it is considered that the low temperature period is maintained at the present time. Therefore, the process proceeds to step 76, and the number of elapsed days Nx2 from the latest menstrual start date Ds0 to the predicted date is calculated. In the subsequent step 77, the stage Sa of the predicted date is determined based on the menstrual start date Ds0 and the number of elapsed days Nx2.

  For example, when the elapsed days Nx2 is 5 days and the days Ns1 to Ns4 of the first to fourth stages S1 to S4 in the low temperature period are all 4 days, it is determined that the stage Sa of the forecast date is the second stage S2. To do. The elapsed days Nx2 is 18 days, the days Ns1 to Ns4 of the first to fourth stages S1 to S4 in the low temperature period are all four days, and the days Ns5 of the fifth to eighth stages S5 to S8 in the high temperature period. When all of Ns8 are 3 days, it is determined that the stage Sa of the prediction date is the fifth stage S5. Then, when step 77 ends, the process returns.

  Next, the health state prediction process in step 8 will be described with reference to FIG.

  In step 81, the processing device 31 accesses the weather data center 32 that can acquire current and future weather information (meteorological data) such as HP of the Japan Meteorological Agency. And the processing apparatus 31 acquires meteorological information, such as atmospheric pressure, temperature, weather, etc. regarding the area previously registered as a living area of the person H to be measured.

  Note that if the predicted date is a predetermined number of days after the current date (for example, one week later), the weather information cannot be acquired, or even if the weather information can be acquired, the accuracy may decrease. In this case, the following processing is continued without considering the weather information.

  In step 82, for example, the average value MIm of the heart index MI at the stage Sa on the prediction date is calculated for the menstrual cycles MC1 to MC3 for the latest three cycles. In the subsequent step 83, for example, the average value PCIm of the body index PCI at the stage Sa on the prediction date is calculated for the menstrual cycles MC1 to MC3 for the latest three cycles.

  The average value MIm of the heart index MI and the average value PCIm of the body index PCI are not limited to the average value for the three most recent cycles, but may be the average value for the two most recent cycles or the average value for the four most recent cycles. . The number of cycles for obtaining the average values MIm and PCIm is appropriately set in consideration of the physical condition change of the person H to be measured, for example.

  In step 84, the correlation between the weather information on the predicted date and the heart index MI and the body index PCI in the stage Sa on the predicted date is determined. Specifically, the correlation coefficient between the weather information such as atmospheric pressure, the heart index MI, and the body index PCI is calculated at the stage Sa of the prediction date. The data for calculating the correlation coefficient (weather information, heart index MI, body index PCI) may be for the latest three cycles, for the last two cycles, or for the last four cycles or more. .

  In step 85, it is determined whether or not there is a correlation between the weather information on the predicted date and the heart index MI and the body index PCI in the stage Sa on the predicted date. For example, when the correlation coefficient is larger than a predetermined value such as 0.7, it is considered that both are correlated. Therefore, “YES” is determined in step 85, and the process proceeds to step 86. In step 86, taking into account the correlation of weather information, the average value MIm of the heart index MI and the average value PCIm of the body index PCI are increased or decreased, and the process proceeds to step 87. Note that the predetermined value for determining the presence or absence of the correlation is not limited to 0.7, and may be, for example, about 0.4, and is set as appropriate within a range of 0.4 or more where moderate correlation is recognized.

  On the other hand, if there is no correlation between the weather information on the predicted date and the heart index MI and the body index PCI at the stage Sa on the predicted date, or if the correlation is weak or there is no weather information, step In 85, it is determined as “NO”, and the process proceeds to step 87.

  In step 87, based on the average value MIm of the heart index MI and the average value PCIm of the body index PCI, the health condition of the measurement subject H on the prediction date is predicted. For example, when the average values MIm and PCIm are smaller than a predetermined decrease determination value Ct1 (for example, Ct1 = about 20 to 40%), emotional disturbance and poor physical condition are predicted. On the other hand, for example, when the average values MIm and PCIm are larger than a predetermined increase determination value Ct2 (for example, Ct2 = about 60 to 80%), it is predicted that the emotion and the physical condition are good. At this time, the processing device 31 outputs advice or the like according to the prediction result together with the prediction result of the health condition. When step 87 ends, the process returns.

  It should be noted that the health condition of the person H to be measured on the prediction date may be determined based on the same criteria as the average values MIm and PCIm of the heart index MI and the body index PCI, or may be determined based on different criteria. . The health condition of the person H to be measured on the prediction date may be predicted based on the average values MIm and PCIm of both the heart index MI and the body index PCI, or may be predicted based on either one. Furthermore, the average value MIm of the heart index MI corresponding to the emotion and the average value PCIm of the body index PCI corresponding to the physical condition may be predicted separately as the health state of the prediction day.

  In the present embodiment, the health prediction process described above is performed, and the prediction result of the health state of the person H to be measured when this process is used next will be described.

  First, the processing device 31 supplements missing data to a body temperature data series ST0 composed of body temperature data D3 for six months accumulated in advance. Next, the average menstrual cycle days Nm in the vicinity of the menstrual cycle MC1 is specified using the body temperature data series ST1 supplemented with the missing data, and the cycle average temperature Tm is calculated based on the average menstrual cycle days Nm. Then, the transition time from the low temperature period to the high temperature period is specified using the periodic average temperature Tm, and the low temperature period days NL and the high temperature period days NH are obtained.

  Further, the average low temperature period NLm and the average high temperature period NHm are calculated based on the latest three menstrual cycles MC1 to MC3, and based on these, the low temperature period first to fourth stages S1 to S4 are calculated. Ns1 to Ns4 and days Ns5 to Ns8 of the fifth to eighth stages S5 to S8 in the high temperature period are obtained.

  Based on the number of days Ns1 to Ns8 of each stage S1 to S8, the transition date Dox from the low temperature period to the high temperature period, and the latest menstrual start date Ds0, the stage Sa of the prediction date is specified. The average values MIm and PCIm of the heart index MI and the body index PCI of the stage Sa on the prediction date are calculated in consideration of the weather information on the prediction date. Based on these average values MIm and PCIm, the health condition of the person H to be measured on the prediction date is estimated. Finally, the prediction result of the health state is displayed on the monitor device 21C of the portable terminal 21 of the person H to be measured or a screen of another computer or the like that can access the processing device 31 by the person H to be measured.

  At this time, the processing device 31 outputs the body temperature data series ST1 as an image based on a set of bar graphs of the body temperature data D3 toward an output device such as the portable terminal 21. Specifically, as shown in FIGS. 23 and 25, the series of body temperature data D3 corresponding to the menstrual cycle MC1 is represented by a bar graph of daily body temperature data D3, and the bar graph is displayed in different colors in the low temperature period and the high temperature period. It is divided and displayed. For example, a bar graph in the low temperature period is displayed in a cool color (for example, blue, green, etc.), and a bar graph in the high temperature period is displayed in a warm color (red, yellow, etc.).

  In addition, in the example of the menstrual cycle graph 27 shown in FIG. 23, auxiliary lines for the cycle average temperature Tm, the low temperature average temperature TmL, and the high temperature average temperature TmH are included so that the measurement subject H can easily grasp the temperature change. it's shown. Further, around the bar graph, there are menstrual cycle days Nmc1, low temperature days NL, high temperature days NH, cycle average temperature Tm, low temperature average temperature TmL, high temperature average temperature TmH, temperature difference ΔT between average temperatures TmL and TmH, The next ovulation period and the next menstrual start date Dsx are also displayed.

  Further, as illustrated in FIG. 24, the processing device 31 outputs the predicted date stage Sa to the portable terminal 21 or the like as an image using the substantially circular stage display board 28. Here, the stage display board 28 is divided into eight equal fan-shaped portions 28A to 28H, and these fan-shaped portions 28A to 28H respectively correspond to the first to eighth stages S1 to S8. The right half sector portions 28A to 28D correspond to the first to fourth stages S1 to S4 in the low temperature period, and the remaining (left half) sector portions 28E to 28H correspond to the fifth to eighth stages S5 to S8 in the high temperature period. It corresponds. The fan-shaped portions 28A to 28H are arranged clockwise in the order of the first to eighth stages S1 to S8, and one turn of the stage display board 28 corresponds to one cycle of basal body temperature. The first day of the first stage S1 is determined based on the menstrual start notification reported by the person H to be measured.

  The stage display panel 28 displays the sector part corresponding to the stage Sa on the prediction date by shifting the position from the other part, for example. Thereby, the stage display board 28 displays which stage of the first to eighth stages S1 to S8 corresponds to the person H to be measured on the predicted date.

  Note that the display method of the stage Sa of the prediction date is not limited to the above-described method, and a symbol indicating the stage Sa may be displayed inside the fan-shaped portion, or may be displayed by blinking or the like. Further, the fan-shaped portions 28A to 28H corresponding to the first to eighth stages S1 to S8 in the stage display board 28 may be displayed in different colors. In this case, the fan-shaped portions 28A to 28D corresponding to the low temperature period are displayed in a cold color (for example, indigo, blue, green, yellowish green, etc.), and the fan-shaped portions 28E to 28H corresponding to the high temperature period are warm colors (pink, red, orange). , Yellow, etc.).

  Furthermore, as shown in FIGS. 26 and 27, the monitor device 21C of the mobile terminal 21 displays the health condition prediction result output from the processing device 31 and the like. Specifically, the average value MIm of the heart index MI and the average value PCIm of the body index PCI are displayed on the monitor device 21C as the health state of the predicted date together with the stage display board 28. At this time, the portable terminal 21 displays the prediction result of emotion and physical condition of the prediction date, advice corresponding to the prediction result, and the like together with the average values MIm and PCIm.

  For example, before and after menstruation, headaches and anemia tend to occur, and the mood tends to decrease. For this reason, in the first stage S1 and the eighth stage S8, a decrease in the heart index MI and the body index PCI is predicted. At this time, for example, as shown in FIG. 26, when it is determined that the predicted date is the first stage S1, the average value MIm of the heart index MI and the average value PCIm of the body index PCI in the first stage S1 are displayed. . Thereby, the to-be-measured person H can grasp | ascertain beforehand that an emotion and a physical condition are in the fall tendency on a prediction day.

  On the other hand, before and after the ovulation period, the physical condition is good and the mood tends to increase. For this reason, in the fourth stage S4 and the fifth stage S5, an increase in the heart index MI and the body index PCI is predicted. At this time, for example, as shown in FIG. 27, when it is determined that the predicted date is the fourth stage S4, the average value MIm of the heart index MI and the average value PCIm of the body index PCI in the fourth stage S4 are displayed. . Thereby, the to-be-measured person H can grasp | ascertain beforehand that feelings and physical condition are favorable on a prediction day.

  Thus, according to the present embodiment, the processing device 31 determines whether the measurement subject H is in the low temperature period or the high temperature period on the prediction date such as today or the near future based on the body temperature data series ST0. Also, it is specified which stage S1 to S8 in the menstrual cycle corresponds to whether it is approaching the ovulation period or menstrual period. The processing device 31 can predict the health state of the prediction date such as emotion and physical condition based on the stage Sa of the prediction date specified in this way. As a result, the person H to be measured can grasp in advance a health condition such as undulation of emotion or deterioration of physical condition.

  Further, when the processing device 31 determines the transition time from the low temperature period to the high temperature period (transition date Dox) within the menstrual cycle MC0, the processing device 31 specifies the stage Sa of the prediction date based on the transition date Dox. For this reason, the stage Sa of the prediction date is specified in consideration of the transition time to the high temperature period, and therefore, it may be affected by the fluctuation part of the low temperature period days NL compared to the case where the transition time to the high temperature period is not considered. In addition, the estimation accuracy of the stage Sa on the prediction date can be increased.

  The processing device 31 predicts the health state on the prediction date based on the prediction date stage Sa and the health state of the same stage as the prediction date stage Sa stored in the storage device 31A. Specifically, the health state of the prediction date is estimated by calculating the average value MIm and PCIm of the heart index MI and the body index PCI of the same stage as the stage Sa of the prediction date stored in the storage device 31A. For this reason, since the health state is predicted based on the past health state stored for each person to be measured, compared with the case of predicting the health state based on the relationship between the general menstrual cycle and the health state, It is possible to predict a health condition suitable for the person H to be measured.

  In addition to this, since the processing device 31 acquires the weather information of the predicted date, it can predict the health condition of the measurement subject in consideration of the weather information of the predicted date. For this reason, for example, even when the physical condition or emotion of the person H to be measured changes according to weather conditions such as season, temperature, atmospheric pressure, etc., the health condition is predicted in consideration of such fluctuations in physical condition, etc. Can improve the prediction accuracy of the health condition.

  Further, the mobile terminal 21 determines the emotion based on the voice of the measurement subject H, and determines the degree of anemia based on the image on the back side of the lower arm of the measurement subject H. For this reason, compared with the case where the to-be-measured person H inputs emotion and physical condition subjectively, emotion and physical condition can be objectively grasped.

  In the above embodiment, the stage specifying process shown in step 7 and FIG. 21 in FIG. 15 shows a specific example of the stage specifying means, and the health state predicting process shown in step 8 and FIG. 22 in FIG. 21 shows a specific example of the predicting means, step 73 in FIG. 21 shows a specific example of the transition timing specifying means, and steps 74 to 77 show a specific example of the stage determining means.

  In the above embodiment, steps 43, 46, and 48 in FIG. 19 show a specific example of the average low temperature period days specifying means, and steps 44, 47, and 49 in FIG. 19 are specific examples of the average high temperature period days specifying means. An example, step 50 in FIG. 19 and the next ovulation period estimation process shown in FIG. 20 show a specific example of the ovulation period estimation means, and steps 51 to 53 in FIG. 19 show a specific example of the menstrual start date estimation means. Show.

  Moreover, in the said embodiment, step 3 in FIG. 15 and the average menstrual cycle days specification process shown in FIG. 16 show the specific example of an average menstrual cycle days specification means, and step 13 in FIG. 16, steps 14 to 18 in FIG. 16 show a specific example of the number of days calculation means, and the periodic average temperature calculation processing shown in steps 4 and 17 in FIG. 15 is a specific example of the periodic average temperature calculation means. Step 81 in FIG. 22 shows a specific example of the weather information acquisition means.

  In the embodiment, the menstrual cycle is divided into eight stages S1 to S8, and the stage Sa of the prediction date is specified. However, the present invention is not limited to this, and each stage S1 to S8 may be divided into the first half and the second half, and the stage Sa on the prediction date may be specified among a total of 16 stages. In addition, the first to fourth stages S1 to S4 are divided into four equal parts in the low temperature period. However, the first to fourth stages S1 to S4 are not necessarily divided into equal days. For example, the first to fourth stages S1 to S4 are divided into different days. May be. Similarly, in the fifth to eighth stages S5 to S8, the high temperature period is divided into four equal parts, but it is not always necessary to divide into the equal days. For example, the fifth to eighth stages S5 to S8 are divided into different days. May be. Further, the health state in the next ovulation period may be predicted separately from the eight stages S1 to S8. In this case, the health condition in the next ovulation period can be predicted by referring to the health condition in the past ovulation period.

  In the embodiment, when measuring the degree of anemia, the lower eyelid is pulled downward with the fingertip of the person H to be measured. However, the present invention is not limited to this, and the lower eyelid may be pulled downward by using an auxiliary instrument 41 whose color is specified in advance as in a modification shown in FIG. 28, for example. As a result, the auxiliary device 41 can be photographed together when taking a picture of the back side of the lower arm, so even when taking a picture in a place where the illumination color is different, such as daylight white, light bulb color, etc. The color of the captured image can be corrected based on the color of the instrument 41. For this reason, the measurement accuracy of the anemia degree can be increased. The auxiliary instrument 41 is not limited to the spatula shape as shown in FIG. 28, and may be one that covers the fingertip, such as a finger sack.

  In the embodiment, the body index PCI is calculated based on the degree of headache and anemia. However, the present invention is not limited to this. In addition to the degree of headache and anemia, the body index PCI is calculated in consideration of, for example, abdominal pain, coldness, swelling of the face, rough skin, hairiness, thirst in the mouth, etc. Also good. Moreover, it is not necessary to calculate as a single body index PCI, and headache, anemia, abdominal pain, coldness, etc. may be separately indexed to predict the magnitude of these degrees on the prediction date. Furthermore, although the degree of anemia is measured by the image on the back side of the lower eyelid, a subjective value by the person to be measured may be input in the same manner as the degree of headache.

  In the above embodiment, the heart index MI is calculated based on the four criteria of “excitement”, “sadness”, “joy”, and “anger”, but in addition to these, for example, “motivation”, “irritability” May be taken into account. In addition, it is not necessary to calculate as a single heart index MI. The four criteria of “excitement”, “sadness”, “joy” and “anger” are separately indexed to predict the magnitude of these numbers on the forecast date. May be. Furthermore, although the heart index MI is calculated based on the voice of the person to be measured, a subjective value by the person to be measured may be input.

  Moreover, in the said embodiment, the processing apparatus 31 estimates the health condition of the to-be-measured person's H prediction day using the health condition of the to-be-measured person's H of several days memorize | stored beforehand in the memory | storage device 31A. However, the present invention is not limited to this. The storage device 31A may store in advance the health state of each stage in each age (for example, the average value of the heart index MI and the body index PCI). In this case, when the stage Sa for the predicted date of the person H to be measured is specified, the processing device 31 refers to the storage device 31A and specifies and specifies the health state of each age according to the stage Sa. The health state may be output as a prediction result.

  In the above embodiment, when none of the high-temperature days NH1 to NH3 for the latest three cycles is calculated, the average high-temperature days NHm is set to 13 days. For example, data for the latest three cycles is accumulated. Before the high temperature period days NH1 and NH2 are calculated, the average high temperature period number NHm may be set to 13th or 14th, or may be set to the average value of each age. .

  In the embodiment, the day after the average menstrual cycle number Nm from the current menstrual start date Ds0 is specified as the next scheduled menstrual cycle date Ds. For example, instead of the average menstrual cycle date Nm, self-reported cycle days N0 May be used to specify the next scheduled menstrual start date Ds, and the date after the number of days after the average low temperature period NLm and average high temperature period NHH are added from the current menstrual start date Ds0. You may specify as Ds.

  Moreover, in the said embodiment, the sensor apparatus 1 presets the measurement start time and end time, and detects the body surface temperature detection data D1 and the outside temperature detection data D2 for every fixed time between these. It was. However, the present invention is not limited to this, and the sensor device 1 reads the temperature detection data D1 and D2 when, for example, the temperature T1 detected by the body surface temperature detection unit 3 rises above a certain temperature (for example, 32 ° C.), The storage may be started and the reading of the temperature detection data D1 and D2 and the like may be terminated when the temperature falls below a certain temperature.

  Further, the sensor device 1 is provided with a micro azimuth switch, and when the person to be measured changes the posture from the sitting position or the standing position to the lying position, the azimuth switch is turned on, and the person to be measured changes the posture from the lying position to the sitting position or standing position. If changed, the azimuth switch may be turned off. As a result, the sensor device 1 can start and end reading of the temperature detection data D1, D2 and the like according to the ON state and OFF state of the direction switch.

  The sensor device 1 may be configured to detect and store only the body surface temperature detection data D1. In each of the above embodiments, the body surface temperature detection data D1 during sleep is detected a plurality of times per day. However, for example, the body surface temperature detection data D1 may be detected only once per day after the body temperature is sufficiently stabilized.

  Furthermore, the body temperature data D3, which is a representative temperature, is obtained based on the body surface temperature detection data D1 while sleeping, but, for example, in a stable state immediately after getting up, the mouth temperature, the ear temperature, etc. It is good also as a structure using the body temperature data which measured the basal body temperature.

  Further, in the determination process of the low temperature period and the high temperature period shown in FIG. 18, when the body temperature data D3 exceeds the cycle average temperature Tm continuously for two days or more in the menstrual cycle, the low temperature period is assumed to have shifted to the high temperature period from the first day. The transition period from the period to the high temperature period was identified. However, the present invention is not limited to this. For example, when the body temperature data D3 exceeds the cycle average temperature Tm within one day within a predetermined period, the transition time from the low temperature period to the high temperature period may be specified. As disclosed in Japanese Patent No. 4933227, the transition time from the low temperature period to the high temperature period may be specified when the body temperature data D3 exceeds a predetermined high temperature period reference temperature.

  In the embodiment, the processing device 31 calculates the cycle average temperature Tm based on the average menstrual cycle days Nm. However, the present invention is not limited to this. For example, when the menstrual cycle for specifying the transition period from the low temperature period to the high temperature period is determined regardless of the average menstrual cycle days Nm, the body temperature data D3 of the entire menstrual cycle is averaged. Then, the cycle average temperature Tm may be calculated.

  Further, in the above embodiment, based on the body temperature data D3 for a plurality of days accumulated in the storage device 31A and the weather information acquired from the weather data center 32, the health condition of the measurement subject H in the present and the future is estimated. To do. However, the present invention is not limited to this. For example, except for weather information, the present state and future health condition of the person H to be measured can be estimated based on the body temperature data D3 for a plurality of days accumulated in the storage device 31A. Good.

1 Wearable sensor device (sensor device)
21 Mobile terminal 31 Processing device

Claims (7)

A health prediction system for predicting the health state of the subject by a processing device using a series of body temperature data obtained by measuring the body temperature of the subject over a plurality of days,
The processor is
A predicted date stage identifying means for identifying a predicted date stage within the menstrual cycle using the series of body temperature data;
A health prediction system comprising health state prediction means for predicting a health state on the prediction date based on a prediction date stage specified by the prediction date stage specifying means. The forecast date stage identifying means includes a transition timing identifying means for identifying a transition timing from the low temperature period to the high temperature period within the menstrual cycle,
The health prediction system according to claim 1, further comprising stage determination means for determining a stage of the prediction date based on the transition time specified by the transition time specifying means. The processing apparatus further includes storage means for storing the health condition of the measurement subject over a plurality of days,
The health state prediction means is based on the prediction date stage specified by the prediction date stage specifying means and the health state of the same stage as the prediction date stage stored in the storage means. The health prediction system according to claim 1 or 2, wherein the state is predicted. Further comprising an emotion determination means for determining an emotion based on the voice of the measurement subject,
The health prediction system according to claim 3, wherein the storage unit stores emotion information determined by the emotion determination unit as the health state. An anemia degree determination means for determining the degree of anemia by the image of the back side of the measurement subject's eyelid,
The health prediction system according to claim 3 or 4, wherein the storage unit stores information on the anemia degree determined by the anemia degree determination unit as the health state. The processing apparatus further includes weather information acquisition means for acquiring weather information on the forecast date,
The health state prediction means predicts a health state on the prediction date based on the prediction date stage specified by the prediction date stage specification means and the weather information of the prediction date acquired by the weather information acquisition means. The health prediction system according to any one of claims 1 to 5. A health prediction method for predicting the health state of the measurement subject by a processing device using a series of body temperature data obtained by measuring the temperature of the measurement subject over a plurality of days,
A predicted date stage identifying means for identifying a predicted date stage within the menstrual cycle using the series of body temperature data;
A health prediction method comprising health state prediction means for predicting a health state on the prediction date based on a prediction date stage specified by the prediction date stage specifying means.

Images