Calculation method, calculation device, and storage medium

Abstract

A stress value calculation device 100 according to the present invention comprises: a minimum feature amount calculation unit 121 that acquires biometric data measured from a person along a timeline and that calculates, as a minimum feature amount, a feature amount of the acquired biometric data for each preset minimum time unit; a first feature amount calculation unit 122 that calculates, as a first feature amount, a feature amount of the biometric data measured within a first time unit using the minimum feature amount corresponding to the biometric data within the first time unit after the first time unit has elapsed, the first time unit being longer than the minimum time unit; and a calculation unit 123 that calculates a value representing a physical condition of the person using information based on the first feature amount.

Description

[Technical Field]

[0001] The present invention relates to a calculation method, a calculation device, and a program for calculating a value representing a person's physical condition. [Background technology]

[0002] A known method for calculating a person's stress level is to use biometric data such as the person's heart rate. In particular, in recent years, an increasing number of people are wearing wearable devices such as smartwatches, making it easy to obtain biometric data from people on a regular basis over the medium to long term. Such biometric data is then used to calculate a chronic stress level. For example, biometric data over the medium to long term, such as over several hours, several days, or even a month, may be obtained to calculate a chronic stress level. Patent Document 1, for example, describes a method for estimating chronic stress by obtaining biometric data from a wearable device worn by a person. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2010-184041 Summary of the Invention [Problem to be solved by the invention]

[0004] However, when calculating a stress value using mid- to long-term biological data as described above, it is necessary to process a large amount of mid- to long-term biological data all at once. This causes a problem that the stress value calculation process takes time, making it difficult to calculate the stress value quickly. Furthermore, it is difficult to quickly calculate values ​​that represent not only stress but also a person's physical and mental fatigue, internal condition, and other physical conditions.

[0005] Therefore, the object of the present invention is to provide a calculation method that can solve the above-mentioned problem that the calculation process of values ​​representing physical condition takes time and it is difficult to quickly calculate values ​​representing physical condition. [Means for solving the problem]

[0006] A calculation method according to one aspect of the present invention includes: Acquire biometric data measured in time series from a person, and calculate feature amounts for each predetermined minimum time unit of the acquired biometric data as minimum feature amounts; after a first time unit, which is a time unit longer than the minimum time unit, has elapsed, calculating, as a first feature amount, a feature amount of the biometric data measured within the first time unit, using the minimum feature amount corresponding to the biometric data within the first time unit; calculating a value representing the physical condition of the person using information based on the first feature amount; The structure is as follows.

[0007] Furthermore, a calculation device according to one aspect of the present invention includes: a minimum feature amount calculation unit that acquires biometric data measured from a person in time series and calculates a feature amount of the acquired biometric data for each predetermined minimum time unit as a minimum feature amount; a first feature amount calculation unit that, after a first time unit that is a time unit longer than the minimum time unit has elapsed, calculates, as a first feature amount, a feature amount of the biometric data measured within the first time unit by using the minimum feature amount corresponding to the biometric data within the first time unit; a calculation unit that calculates a value representing a physical condition of a person using information based on the first feature amount; Equipped with The structure is as follows.

[0008] Furthermore, a program according to one aspect of the present invention includes: In the information processing device, Acquire biometric data measured in time series from a person, and calculate feature amounts for each predetermined minimum time unit of the acquired biometric data as minimum feature amounts; after a first time unit, which is a time unit longer than the minimum time unit, has elapsed, calculating, as a first feature amount, a feature amount of the biometric data measured within the first time unit, using the minimum feature amount corresponding to the biometric data within the first time unit; calculating a value representing the physical condition of the person using information based on the first feature amount; Execute the process, The structure is as follows. [Effects of the Invention]

[0009] With the above-described configuration, the present invention can quickly calculate values ​​that represent physical condition. [Brief explanation of the drawings]

[0010] [Figure 1] 1 is a block diagram showing the configuration of a stress value calculation device according to a first embodiment of the present invention. [Figure 2] FIG. 2 is a diagram showing how data is processed by the stress value calculation device disclosed in FIG. [Figure 3] FIG. 2 is a diagram showing how data is processed by the stress value calculation device disclosed in FIG. [Figure 4] FIG. 2 is a diagram showing how data is processed by the stress value calculation device disclosed in FIG. [Figure 5] 2 is a flowchart showing the operation of the stress value calculation device disclosed in FIG. [Figure 6] 2 is a flowchart showing the operation of the stress value calculation device disclosed in FIG. [Figure 7] 2 is a flowchart showing the operation of the stress value calculation device disclosed in FIG. [Figure 8] FIG. 10 is a block diagram showing the hardware configuration of a calculation device according to a second embodiment of the present invention. [Figure 9] FIG. 10 is a block diagram showing the configuration of a calculation device according to a second embodiment of the present invention. [Figure 10] 10 is a flowchart showing the operation of a calculation device according to a second embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0011] <Embodiment 1> A first embodiment of the present invention will be described with reference to Figures 1 to 7. Figures 1 to 4 are diagrams for explaining the configuration of a stress value calculation device, and Figures 5 to 7 are diagrams for explaining the processing operation of the stress value calculation device.

[0012] [composition] The stress value calculation device 10 (calculation device) of the present invention is used to calculate a stress value that represents a person's stress state. For example, the stress value calculation device 10 is used to calculate a chronic stress value that occurs chronically in a person. However, the stress value calculation device 10 of the present invention may calculate any stress value of a person. Furthermore, the present invention is not limited to calculating stress values, but can also be applied to calculating values ​​that represent a person's physical condition, such as physical and mental fatigue and internal condition. In other words, the stress value cited in this embodiment is an example of a value of the physical condition of the person to be estimated, and other examples of the physical condition value may be any value, such as a fatigue level that represents the degree of fatigue or some index value that represents the condition.

[0013] The stress value calculation device 10 is composed of one or more information processing devices each including a calculation device and a storage device. As shown in FIG. 1, the stress value calculation device 10 includes a data acquisition unit 11, a short-term feature calculation unit 12, a feature calculation unit 13, a stress value calculation unit 14, and an output unit 15. The functions of the data acquisition unit 11, the short-term feature calculation unit 12, the feature calculation unit 13, the stress value calculation unit 14, and the output unit 15 can be realized by the calculation device executing a program for realizing each function stored in the storage device. The stress value calculation device 10 also includes an acquired data storage unit 16 and a feature storage unit 17. The acquired data storage unit 16 and the feature storage unit 17 are each composed of a storage device. Each component will be described in detail below.

[0014] The data acquisition unit 11 acquires data used to calculate a person's stress value. Specifically, the data acquisition unit 11 acquires biometric data of the person U while the person U is living his or her daily life or performing work at the workplace. For example, the biometric data is various information emitted from the person's body, such as heart rate, acceleration, and sweat rate, for example. As shown in FIG. 1 , such biometric data is constantly measured in chronological order by a measurement device such as a wearable terminal W worn by the person U, and is uploaded from the measurement device to the stress value calculation device 10 via a user terminal 20 such as a smartphone operated by the user.

[0015] Here, the timing at which biometric data is uploaded from the wearable terminal W and the user terminal 20 to the stress value calculation device 10 may be irregular depending on the processing status and communication status of each terminal or device. Furthermore, the time duration of the biometric data uploaded by the wearable terminal W and the user terminal 20 to the stress value calculation device 10 may also not be constant depending on the processing status and communication status. For this reason, the data acquisition unit 11 will acquire an irregular amount of biometric data from the wearable terminal W and the user terminal 20 at irregular intervals, and the acquisition may often be delayed from the time of measurement of the biometric data. As an example, the data acquisition unit 11 may acquire two hours' worth of biometric data measured from a person one hour later than the final measurement time.

[0016] Then, the data acquisition unit 11 associates the acquired biometric data with the person and the measurement time, and temporarily stores the data in the acquired data storage unit 16. However, the data acquisition unit 11 may acquire biometric data measured using any measuring device. Note that the acquired data storage unit 16 does not necessarily have to be provided, and the data acquisition unit 11 may pass the acquired biometric data to the short-term feature calculation unit 12 without storing it.

[0017] As described above, when the data acquisition unit 11 acquires biometric data, the short-time feature calculation unit 12 (minimum feature calculation unit) calculates the feature of the biometric data. Specifically, the short-time feature calculation unit 12 divides the biometric data of a predetermined time width into preset minimum time units along a time series, calculates a feature from each of the biometric data for each divided minimum time unit, and stores these feature amounts as short-time features (minimum features) in the feature storage unit 17 in association with the time at which the original biometric data was measured.

[0018] Here, the processing by the short-time feature calculation unit 12 will be explained with reference to Fig. 2. In Fig. 2, the horizontal axis indicates the time when the biometric data is measured, and the vertical axis indicates the actual time. In Fig. 2, it is assumed that the measurement of the biometric data starts from the measurement time "0:00".

[0019] First, a case will be described in which the data acquisition unit 11 acquires two hours of biometric data d, measured from 0:00 to 2:00, at real time 3:00 in FIG. 2. In this case, the short-term feature calculation unit 12 divides the acquired biometric data d into 1-minute intervals, which is set as the smallest time unit, calculates features for each 1-minute interval of biometric data, and stores the short-term feature d1 in association with each 1-minute interval from 0:00. At this time, the calculated feature may be, for example, the mean value, variance / standard deviation, maximum value, minimum value, or quartile of the biometric data. For simplicity of explanation, in this embodiment, the mean value of the biometric data is calculated as the feature.

[0020] The calculation of the short-term feature d1 by the short-term feature calculation unit 12 is executed immediately after the biometric data d is acquired by the data acquisition unit 11. Therefore, when the biometric data d for two hours, measuring time "2:00-4:00," is acquired at real time "5:00" shown in FIG. 2, the short-term feature calculation unit 12 immediately calculates and stores the short-term feature for each minimum time unit. Note that in the example of FIG. 2, a diagram illustrating the calculation of the short-term feature d1 for the biometric data d acquired at real time "5:00" is omitted, but the short-term feature is calculated in the same manner as described above. Similarly, at other times in FIG. 2 and in FIGS. 3 and 4, a diagram illustrating the calculation of the short-term feature d1 from the biometric data d is omitted, but the short-term feature is calculated in the same manner as described above.

[0021] The feature calculation unit 13 (first feature calculation unit) has a function of first calculating a four-hour feature (first feature) as a feature of the biometric data for "four hours" set as the first time unit, using the short-time feature calculated from the biometric data as described above. Here, in this embodiment, it is assumed that "four hours" is set as the first time unit, which is longer than "one minute," which is an example of the minimum time unit described above. However, the first time unit may be set to any time as long as it is longer than the minimum time unit.

[0022] When "four hours," which is the first time unit that constitutes the target period, have elapsed since the acquisition of biometric data, the feature calculation unit 13 calculates four-hour features using short-time features corresponding to the biometric data measured within those four hours and stores the four-hour features in the feature storage unit 17. At this time, when the four hours that constitute the target period have elapsed, the feature calculation unit 13 first calculates four-hour features using only short-time features corresponding to the biometric data that have already been acquired, even if not all of the biometric data within those four hours have been acquired, and stores the four-hour features in the feature storage unit 17. Thereafter, the feature calculation unit 13 checks whether new biometric data has been acquired within the four hours that constitute the target period. If new biometric data has been acquired, the feature calculation unit 13 calculates new four-hour features using short-time features corresponding to the new biometric data and the four-hour features that have already been calculated and stored, and stores the new four-hour features as updates. Note that if not all of the biometric data within the four hours have been acquired, the feature calculation unit 13 checks every hour, which is a time interval shorter than the first time unit, whether new biometric data has been acquired within the four hours that constitute the target period. However, the time interval for checking whether or not new biometric data has been acquired within the four-hour target period is not limited to one hour, and may be any time interval.

[0023] Then, feature calculation unit 13 acquires all biometric data within the four-hour target period, calculates and stores four-hour features using short-term features corresponding to the biometric data, and then changes the target period to the subsequent four hours. After another four hours have passed, the same process as described above is performed to calculate the subsequent four-hour features using short-term features corresponding to the biometric data measured within the subsequent four hours and store the results in feature storage unit 17.

[0024] Note that the data feature amount calculation unit 13 may treat all biometric data within the four-hour target period as having been acquired even if not all biometric data has actually been acquired. This is because there may be a time period in which biometric data cannot be acquired for some reason. For this reason, for example, if biometric data from the four-hour target period is acquired after that time has elapsed, or if a predetermined time has elapsed after the four-hour target period has elapsed, the data feature amount calculation unit 13 will treat all biometric data within the four-hour target period as having been acquired, even if there is a period in the target period in which biometric data has not been acquired. Then, the four-hour feature amount is calculated using the short-term feature amount of only the acquired biometric data, and the target period is changed to the subsequent four-hour period.

[0025] Here, the process of calculating the 4-hour feature by the feature calculation unit 13 will be described with reference to FIG. 2. First, assuming that the target period is four hours from the measurement time "0:00-4:00," the feature calculation unit 13 calculates the 4-hour feature at the actual time "4:00." At this time, in the example of FIG. 2, only biometric data d for two hours from the measurement time "0:00-2:00" has been acquired prior to this, so the 4-hour feature D1 for the measurement time "0:00-4:00" is calculated and stored only from the short-time feature d1 corresponding to the biometric data d for that time "0:00-2:00." Thereafter, the feature calculation unit 13 checks every hour whether new biometric data has been acquired within the four-hour target period. Then, in the example of FIG. 2, one hour has passed at the actual time "5:00," so the feature calculation unit 13 checks whether new biometric data has been acquired within the four-hour target period. Then, at real time "5:00", biometric data d for two hours, measured from "2:00 to 4:00", is acquired, and short-time features (not shown) are calculated and stored. Therefore, the feature calculation unit 13 updates the four-hour feature D1 using the short-time feature corresponding to the biometric data d measured from "2:00 to 4:00" acquired at real time "5:00" and the four-hour feature D1 corresponding to the biometric data d from "0:00 to 2:00" that has already been calculated and stored. As a result, at real time "5:00", the four-hour feature D1 based on all biometric data for the target period measured from "0:00 to 4:00" is calculated and stored. However, the feature calculation unit 13 may calculate the 4-hour feature D1 using all the acquired short-term features, in this case, the short-term features corresponding to the biometric data d measured at the time "0:00-2:00" and the short-term features corresponding to the biometric data d measured at the time "2:00-4:00".

[0026] As described above, when the short-term feature is an average value of the biometric data, the 4-hour feature can be calculated by simply calculating the average value of the short-term feature, or when there is already a calculated 4-hour feature, the average value can be calculated by taking into account the time between the 4-hour feature and the new short-term feature. Therefore, the feature calculation unit 13 can calculate the 4-hour feature faster than calculating it from the biometric data itself.

[0027] Thereafter, the feature calculation unit 13 changes the target period to the measurement time of the next four hours, "4:00-8:00." Therefore, when the real time reaches "8:00" after the next four hours have passed, the feature calculation unit 13 performs the calculation process of the four-hour feature in the same manner as described above.

[0028] Furthermore, the feature calculation unit 13 (second feature calculation unit) has a function of calculating a 12-hour feature (second feature) as a feature of biometric data for "12 hours" set as the second time unit, using the 4-hour feature (first feature) calculated as described above. Here, in this embodiment, it is assumed that "12 hours" is set as the second time unit, which is longer than "4 hours," which is an example of the first time unit described above. However, the second time unit may be set to any length of time as long as it is longer than the first time unit.

[0029] When "12 hours," which is the second time unit that constitutes the target period, has elapsed since the biometric data was acquired, the feature calculation unit 13 calculates a 12-hour feature using the 4-hour feature corresponding to the biometric data measured within the 12 hours, and stores the 12-hour feature in the feature storage unit 17. At this time, when the 12 hours that constitutes the target period have elapsed, even if not all of the biometric data within the 12 hours has been acquired, the feature calculation unit 13 first calculates a 12-hour feature using only the 4-hour feature corresponding to the biometric data that has already been acquired, and stores the 12-hour feature in the feature storage unit 17. Thereafter, every time the 12 hours that constitutes the target period elapses, the feature calculation unit 13 calculates a new 12-hour feature using the newly calculated and stored 4-hour feature and the already calculated and stored 12-hour feature, and stores the new 12-hour feature as an update.

[0030] Here, the process of calculating 12-hour features by the feature calculation unit 13 will be described with reference to Fig. 3 and Fig. 4. Note that Fig. 3 omits the illustration of some of the data processing shown in Fig. 2 and adds subsequent real-time processing, and Fig. 4 omits the illustration of some of the data processing shown in Fig. 3 and adds subsequent real-time processing.

[0031] First, if the target period is 12 hours from the measurement time "0:00-12:00", the feature calculation unit 13 calculates the 12-hour feature at the real time "12:00". At this time, in the example of Fig. 3, since only the 4-hour feature D1 corresponding to the biometric data d for 10 hours from the measurement time "0:00-10:00" has been generated before, the 12-hour feature D2 for the measurement time "0:00-12:00" is calculated and stored only from the 4-hour feature D1 corresponding to the biometric data d for that time "0:00-10:00".

[0032] Thereafter, the feature calculation unit 13 waits until the subsequent 12 hours have passed before calculating the 12-hour feature D2, and when the real time reaches "0:00" after the next 12 hours have passed, calculates the 12-hour feature D2. At this time, the feature calculation unit 13 calculates the 12-hour feature D2 corresponding to the 12 hours of measurement time "0:00-12:00" because the 12-hour feature D2 corresponding to this 12-hour measurement time "0:00-12:00" does not include all of the biometric data d, and further calculates the 12-hour feature D2 corresponding to the next 12 hours of measurement time "12:00-0:00". 4, since the 4-hour feature D1 corresponding to the biometric data d for all 12 hours of measurement time "0:00-12:00" has been calculated, the 12-hour feature D2 for measurement time "0:00-12:00" is newly calculated and updated using the newly calculated 4-hour feature D1 corresponding to the biometric data d for measurement time "8:00-12:00" and the already calculated 12-hour feature D2 for measurement time "0:00-10:00". In this case, when newly calculating the 12-hour feature D2 for measurement time "0:00-12:00", the data for measurement time "8:00-10:00" overlaps, so the calculation must take this overlap into account. Furthermore, for the next 12 hours of measurement time "12:00-0:00", the 12-hour feature D2 is calculated and stored only from the 4-hour feature D1 corresponding to the calculated biometric data d of the time "12:00-20:00". However, the feature calculation unit 13 may calculate the 12-hour feature D2 using all the 4-hour feature D1 within the target period, in this case, the 4-hour feature D1 corresponding to the biometric data d of measurement time "0:00-4:00", the 4-hour feature D1 corresponding to the biometric data d of measurement time "4:00-8:00", and the 4-hour feature D1 corresponding to the biometric data d of measurement time "8:00-12:00".

[0033] As described above, when the 4-hour feature is the average value of the biometric data, the 12-hour feature can be calculated by simply averaging the 4-hour feature, and when there is already a calculated 12-hour feature, the average value can be calculated by taking into account the time between the 12-hour feature and the new 4-hour feature. Therefore, the feature calculation unit 13 can calculate the 12-hour feature faster than calculating it from the 12-hour biometric data itself.

[0034] However, the feature calculation unit 13 is not limited to calculating the 12-hour feature D2 every 12 hours, and may calculate the 12-hour feature D2 every time a preset time shorter than 12 hours has elapsed. For example, the feature calculation unit 13 may check every hour whether a new 4-hour feature has been calculated, and may calculate a new 12-hour feature D2 every time a new 4-hour feature is calculated.

[0035] As described above, once the feature calculation unit 13 has calculated the 12-hour feature amounts D2 corresponding to all of the biometric data for the target period, the stress value calculation unit 14 (calculation unit) calculates the person's stress value using the 12-hour feature amounts D2. Therefore, in the example of Fig. 4, the 12-hour feature amounts D2 for the 12 hours from the measurement time of the previous day, "0:00-12:00," are calculated at real time "0:00," and the stress value is calculated using the 12-hour feature amounts D2. Note that the stress value calculation unit 14 may calculate the stress value from the 12-hour feature amounts D2 using any method, or may calculate the stress value using other information.

[0036] Note that the stress value calculation unit 14 is not necessarily limited to calculating the stress value from the 12-hour feature D2 calculated as described above. For example, the stress value calculation unit 14 may calculate the stress value using the 12-hour feature D2 for a period during which biometric data has not been acquired. Furthermore, the stress value calculation unit 14 may calculate the stress value at a preset time from the 12-hour feature D2 at that time. In this case, the feature calculation unit 13 may calculate the 12-hour feature D2 for the most recent 12 hours from the previously calculated 4-hour feature D1. As an example, consider a case in which stress values ​​are set to be calculated three times a day, every 8 hours, i.e., at 4:00, 12:00, and 20:00, as shown in FIG. 4 . Then, at 12:00, the 12-hour feature D2 corresponding to biometric data from 0:00 to 10:00 (biometric data not acquired from 10:00 to 12:00) is calculated, and the stress value is calculated from the 12-hour feature D2. Then, at 20:00, the 12-hour feature D2 corresponding to the biometric data for "8:00-20:00" is calculated using the 4-hour feature D1 for each of "8:00-12:00," "12:00-16:00," and "16:00-20:00," and the stress value is calculated from this 12-hour feature D2.

[0037] The output unit 15 outputs information based on the stress value calculated by the stress value calculation unit 14 as described above. For example, each time a stress value is calculated, if the stress value exceeds a predetermined reference value for determining high stress, the output unit 15 outputs an alert to that effect on the display device 30 of an information processing device operated by a workplace manager, family member, or the like of person U. Alternatively, each time a stress value is calculated, the output unit 15 may always output the stress value itself, i.e., the time-series change in person U's stress value, or may output any data based on the stress value. Furthermore, the output unit 15 may output data based on the stress value to any person, such as to person U.

[0038] [Operation] Next, the operation of the stress value calculation device 10 described above will be explained mainly with reference to the flowcharts in Figures 5 to 7. Figure 5 shows the operation of the data acquisition unit 11 and short-term feature calculation unit 12 of the stress value calculation device 10. Figure 6 shows the operation of calculating a 4-hour feature by the feature calculation unit 13 of the stress value calculation device 10, and Figure 7 shows the operation of calculating a 12-hour feature by the feature calculation unit 13. Note that the following explanation will be given in real time, taking as an example the situation in which biometric data is acquired as shown in Figures 2 to 4. Note that in this example, it is assumed that measurement of biometric data begins at measurement time "0:00".

[0039] First, as shown in Fig. 2, after the start of biometric data measurement, at real time "3:00", the data acquisition unit 11 acquires two hours of biometric data d from the measurement time "0:00-2:00" (step S1 in Fig. 5). Then, the short-term feature calculation unit 12 divides the acquired biometric data d into "1 minute" intervals, which are set as the smallest time unit, and calculates features for each "1 minute" of biometric data (step S2 in Fig. 5). Then, the short-term feature calculation unit 12 stores the calculated features as short-term features d1 in association with each minute from "0:00" to "2:00" (step S3 in Fig. 5).

[0040] 2, the target period for calculating the 4-hour feature by the feature calculation unit 13, i.e., the 4 hours from the measurement time "0:00-4:00", has elapsed (Yes in step S11 in FIG. 6). Then, the feature calculation unit 13 calculates and stores the 4-hour feature D1 from the short-time feature d1 corresponding to the biometric data d included in the 4 hours from the measurement time "0:00-4:00" (steps S12 and S13 in FIG. 6). At this time, in the example of FIG. 2, since only the biometric data d for the 2 hours from the measurement time "0:00-2:00" has been acquired, the 4-hour feature D1 for the measurement time "0:00-4:00" is calculated and stored only from the short-time feature d1 corresponding to the biometric data d for that time "0:00-2:00".

[0041] At this point, all biometric data for the four hours of measurement time "0:00-4:00" has not been acquired (No in step S14 of FIG. 6), so it is checked every hour from now whether new biometric data for the four hours of the target period has been acquired (Yes in steps S15 and S16 of FIG. 6). If new biometric data has been acquired (Yes in step S16 of FIG. 6), the feature calculation unit 13 calculates a new four-hour feature using the short-time feature d1 corresponding to the new biometric data and the four-hour feature D1 that has already been calculated and stored, and updates and stores the new four-hour feature (step S17 of FIG. 6). If biometric data for a time beyond the four hours of the target period has been acquired, even if there is a time period for which biometric data has not been acquired, it is considered that all biometric data for the four hours has been acquired, and the four-hour feature D1 is calculated.

[0042] 2, the data acquisition unit 11 acquires biometric data d for two hours from the measurement time of 2:00 to 4:00 (step S1 in FIG. 5). Then, the short-term feature calculation unit 12 calculates and stores short-term features d1 for each minute from the acquired biometric data d, as described above (steps S2 and S3 in FIG. 5). Furthermore, since one hour has passed since the previous calculation of the four-hour feature D1 at the real time of 5:00 in FIG. 2 (Yes in step S15 in FIG. 6), it is checked whether new biometric data d has been acquired within the four-hour target period (step S16 in FIG. 6). At this time, since the data acquisition unit 11 has acquired new biometric data d for two hours from the measurement time "2:00 to 4:00" (Yes in step S16 of FIG. 6), the feature calculation unit 13 calculates and updates the new four-hour feature D1 using the short-time feature d1 corresponding to the new biometric data d and the four-hour feature D1 that has already been calculated and stored (step S17 of FIG. 6). As a result, all biometric data within the four hours from the measurement time "0:00 to 4:00" has been acquired (Yes in step S14 of FIG. 6), and the calculation of the four-hour feature D1 corresponding to the measurement time "0:00 to 4:00" is completed.

[0043] Thereafter, as described above, each time biometric data d is acquired, short-term feature d1 is calculated and 4-hour feature D1 for the measurement time "4:00-8:00" is calculated. Specifically, as shown in Fig. 2, data acquisition unit 11 acquires biometric data d at real time "7:00" and "8:00", and short-term feature calculation unit 12 calculates short-term feature d1 for the acquired biometric data d. Then, at real time "8:00", four hours from the measurement time "4:00-8:00" have passed, so feature calculation unit 13 calculates and stores 4-hour feature D1 from short-term feature d1 corresponding to biometric data d included in the four hours from the measurement time "4:00-8:00". 2, since only two hours' worth of biometric data d from the measurement time "4:00-6:00" have been acquired, the feature calculation unit 13 calculates and stores a four-hour feature D1 from only the short-time feature d1 corresponding to the two hours' worth of biometric data d. Thereafter, the feature calculation unit 13 checks every hour whether new biometric data d has been acquired, and when the real time reaches "10:00," biometric data d from the measurement time "6:00-10:00" is acquired, so that all four hours' worth of biometric data d from the measurement time "4:00-8:00" have been acquired. Therefore, the feature calculation unit 13 calculates and updates a new four-hour feature D1 from the measurement time "4:00-8:00" using the short-time feature d1 corresponding to the new two hours' worth of biometric data d from the measurement time "6:00-8:00" and the four-hour feature D1 that has already been calculated and stored.

[0044] 3, four hours have passed since the next measurement time of "8:00-12:00", and so the four-hour feature D1 is calculated in the same manner as above. At this time, because there is only two hours of biometric data d from the measurement time of "8:00-10:00", the feature calculation unit 13 calculates and stores the four-hour feature D1 for the measurement time of "8:00-12:00" from only the short-time feature d1 corresponding to the two hours of biometric data d.

[0045] At the same time, when the real time shown in Fig. 3 reaches "12:00," 12 hours of measurement time "0:00-12:00" have passed (step S21 in Fig. 7), and therefore the feature calculation unit 13 calculates a 12-hour feature. Then, the feature calculation unit 13 calculates and stores a 12-hour feature D2 using a 4-hour feature D1 of measurement time "0:00-4:00," a 4-hour feature D1 of measurement time "4:00-8:00," and a 4-hour feature D1 of measurement time "8:00-12:00" (steps S22 and S23 in Fig. 7). At this time, in the example of Fig. 3, only biometric data d for 10 hours of measurement time "0:00-10:00" has been acquired (No in step S24 in Fig. 7), and therefore the calculation of the 12-hour feature D2 is postponed until the next 12 hours have passed (step S25 in Fig. 7). As shown in FIG. 3, even after the real time "12:00", new biometric data d is acquired, and short-term feature amounts and four-hour feature amounts are calculated.

[0046] 4, when the real time reaches "0:00" after the next 12 hours have passed (Yes in step S25 in FIG. 7), the feature calculation unit 13 calculates a 12-hour feature (step S26 in FIG. 7). At this time, for the 12 hours of measurement time "0:00-12:00", biometric data d for all hours has been acquired and 4-hour feature D1 for each hour has been calculated. Therefore, using the newly calculated 4-hour feature D1 corresponding to the biometric data d for measurement time "8:00-12:00" and the already calculated 12-hour feature D2 for measurement time "0:00-10:00", a new 12-hour feature D2 for measurement time "0:00-12:00" is calculated and updated and stored. For the 12 hours of the measurement time "12:00-0:00", a 12-hour feature amount D2 is calculated and stored only from the 4-hour feature amount D1 corresponding to the calculated biometric data d of the measurement time "12:00-20:00".

[0047] Then, as described above, the stress value calculation device 10 calculates the 12-hour feature values ​​D2 corresponding to all of the biological data within the 12-hour measurement time period "0:00-12:00," and then calculates the person's stress value using the 12-hour feature values ​​D2 (step S27 in FIG. 7).The stress value calculation device 10 then outputs information based on the calculated stress value (step S28 in FIG. 7).

[0048] As described above, in this embodiment, short-term features are calculated every time biometric data is acquired, and these short-term features are used to calculate 4-hour features, which are then used to calculate 12-hour features. This allows the 12-hour features to be calculated much faster than if they were calculated from 12 hours of biometric data itself, and by calculating the stress value from these features, the stress value can be calculated quickly.

[0049] <Embodiment 2> Next, a second embodiment of the present invention will be described with reference to Figures 8 to 10. Figures 8 to 9 are block diagrams showing the configuration of a calculation device in embodiment 2, and Figure 10 is a flowchart showing the operation of the calculation device. Note that this embodiment shows an outline of the configuration of the stress value calculation device and stress value calculation method described in the above embodiments.

[0050] First, the hardware configuration of the calculation device 100 in this embodiment will be described with reference to Fig. 8. The calculation device 100 is configured as a general information processing device, and is equipped with the following hardware configuration, as an example. ·CPU(Central Processing Unit)101(Arithmetic unit) ROM (Read Only Memory) 102 (storage device) RAM (Random Access Memory) 103 (storage device) Programs 104 loaded into RAM 103 A storage device 105 for storing a group of programs 104 A drive device 106 that reads and writes from a storage medium 110 external to the information processing device A communication interface 107 that connects to a communication network 111 outside the information processing device Input / output interface 108 for inputting and outputting data Bus 109 connecting each component

[0051] The CPU 101 acquires and executes the program group 104, thereby configuring and equipping the calculation device 100 with the minimum feature amount calculation unit 121, the first feature amount calculation unit 122, and the calculation unit 123 shown in FIG. The program group 104 is stored in advance in, for example, the storage device 105 or the ROM 102, and is loaded into the RAM 103 and executed by the CPU 101 as needed. The program group 104 may be supplied to the CPU 101 via the communication network 111, or may be stored in advance in the storage medium 110, and the drive device 106 may read out and supply the programs to the CPU 101. The minimum feature amount calculation unit 121, the first feature amount calculation unit 122, and the calculation unit 123 may be configured using dedicated electronic circuits for realizing such means.

[0052] 8 shows an example of the hardware configuration of the information processing device that is the computing device 100, and the hardware configuration of the information processing device is not limited to the above-described case. For example, the information processing device may be configured with only a part of the above-described configuration, such as not including the drive device 106.

[0053] The calculation device 100 then executes the calculation method shown in the flowchart of FIG. 10 using the functions of the minimum feature amount calculation unit 121, the first feature amount calculation unit 122, and the calculation unit 123, which are constructed by the program as described above.

[0054] As shown in FIG. 10, the calculation device 100 Biometric data measured in time series from a person is acquired, and feature quantities for each predetermined minimum time unit of the acquired biometric data are calculated as minimum feature quantities (step S101); After a first time unit, which is a time unit longer than the minimum time unit, has elapsed, a feature amount of the biometric data measured within the first time unit is calculated as a first feature amount using the minimum feature amount corresponding to the biometric data within the first time unit (step S102); A value representing the physical condition of the person is calculated using information based on the first feature amount (step S103). The following process is executed.

[0055] With the above-described configuration, the present invention calculates a minimum feature amount each time biometric data is acquired, calculates a first feature amount using the minimum feature amount, and calculates a value representing the person's physical condition based on the first feature amount. Therefore, the feature amount can be calculated much faster than calculating the feature amount from the biometric data itself at all times, and the value representing the physical condition can be calculated quickly.

[0056] The above-mentioned program can be stored in various types of non-transitory computer readable media and supplied to a computer. Non-transitory computer-readable media include various types of tangible storage media. Examples of non-transitory computer-readable media include magnetic recording media, media (e.g., flexible disks, magnetic tapes, hard disk drives), magneto-optical recording media (e.g., magneto-optical disks), CD-ROMs (Read Only Memory), CD-Rs, CD-R / Ws, and semiconductor memories (e.g., mask ROMs, PROMs (Programmable ROMs), EPROMs (Erasable PROMs), flash ROMs, and RAMs (Random Access Memory)). The program may also be provided to the computer by various types of transitory computer readable media. Examples of the computer-readable medium include an electric signal, an optical signal, and an electromagnetic wave. The temporary computer-readable medium can provide the program to the computer via a wired communication path such as an electric wire or an optical fiber, or via a wireless communication path.

[0057] Although the present invention has been described above with reference to the above-described embodiments, the present invention is not limited to the above-described embodiments. Various modifications that are understandable to those skilled in the art can be made to the configuration and details of the present invention within the scope of the present invention. Furthermore, at least one or more of the functions of the minimum feature amount calculation unit 121, the first feature amount calculation unit 122, and the calculation unit 123 described above may be executed by an information processing device installed and connected anywhere on a network, that is, may be executed by so-called cloud computing.

[0058] <Additional Notes> A part or all of the above-described embodiments can be described as follows: The following provides an overview of the configurations of the calculation method, calculation device, and program of the present invention. However, the present invention is not limited to the following configurations. (Appendix 1) Acquire biometric data measured in time series from a person, and calculate feature amounts for each predetermined minimum time unit of the acquired biometric data as minimum feature amounts; after a first time unit, which is a time unit longer than the minimum time unit, has elapsed, calculating, as a first feature amount, a feature amount of the biometric data measured within the first time unit, using the minimum feature amount corresponding to the biometric data within the first time unit; calculating a value representing the physical condition of the person using information based on the first feature amount; Calculation method. (Appendix 2) 1. The calculation method according to claim 1, every time biometric data is acquired, a feature amount of the acquired biometric data for each of the minimum time units is calculated as the minimum feature amount; Calculation method. (Appendix 3) The calculation method according to Supplementary Note 1 or 2, After calculating the first feature amount, a new first feature amount is calculated using a new minimum feature amount corresponding to the newly acquired biometric data within the first time unit and the first feature amount that has already been calculated. Calculation method. (Appendix 4) 3. The calculation method according to claim 3, if the first feature amount has not been calculated using the minimum feature amount corresponding to the biometric data for all times within the first time unit, checking whether or not new biometric data within the first time unit has been acquired, and if new biometric data has been acquired, calculating a new first feature amount using a new minimum feature amount corresponding to the newly acquired biometric data and the first feature amount that has already been calculated; Stress value calculation method. (Appendix 5) 5. The calculation method according to claim 4, if the first feature amount has not been calculated using the minimum feature amount corresponding to the biometric data for all times within the first time unit, checking whether or not new biometric data within the first time unit has been acquired at a time interval shorter than the first time unit, and if new biometric data has been acquired, calculating a new first feature amount using a new minimum feature amount corresponding to the newly acquired biometric data and the first feature amount that has already been calculated; Calculation method. (Appendix 6) 6. The calculation method according to any one of Supplementary Notes 1 to 5, After a second time unit, which is a time unit longer than the first time unit, has elapsed, a feature amount of the biometric data measured within the second time unit is calculated as a second feature amount using the first feature amount corresponding to the biometric data included in the second time unit; calculating a value representing the physical condition based on the second feature amount; Calculation method. (Appendix 7) 6. The calculation method according to claim 5, After calculating the second feature amount, a new second feature amount is calculated using the new first feature amount corresponding to the newly acquired biometric data within the second time unit and the second feature amount that has already been calculated. Calculation method. (Appendix 8) 7. The calculation method according to claim 7, When the second feature amount has not been calculated using the first feature amount corresponding to the biometric data for all times within the second time unit, a new second feature amount is calculated using a new first feature amount corresponding to newly acquired biometric data and the second feature amount that has already been calculated, every time the subsequent second time unit elapses or every time a preset time shorter than the second time unit elapses. Calculation method. (Appendix 9) a minimum feature amount calculation unit that acquires biometric data measured from a person in time series and calculates, from the acquired biometric data, feature amounts for each predetermined minimum time unit as minimum feature amounts; a first feature amount calculation unit that, after a first time unit that is a time unit longer than the minimum time unit has elapsed, calculates, as a first feature amount, a feature amount of the biometric data measured within the first time unit by using the minimum feature amount corresponding to the biometric data within the first time unit; a calculation unit that calculates a value representing a physical condition of a person using information based on the first feature amount; A computing device comprising: (Appendix 10) 10. The computing device of claim 9, the minimum feature amount calculation unit calculates, each time biometric data is acquired, a feature amount of the acquired biometric data for each of the minimum time units as the minimum feature amount; Calculation device. (Appendix 11) 11. The calculation device according to claim 9 or 10, after calculating the first feature amount, the first feature amount calculation unit calculates and stores a new first feature amount by using a new minimum feature amount corresponding to the newly acquired biometric data within the first time unit and the first feature amount that has already been calculated. Calculation device. (Appendix 12) 12. The computing device of claim 11, when the first feature amount has not been calculated using the minimum feature amount corresponding to the biometric data of all times within the first time unit, the first feature amount calculation unit checks whether or not new biometric data within the first time unit has been acquired, and when new biometric data has been acquired, calculates a new first feature amount using a new minimum feature amount corresponding to the newly acquired biometric data and the first feature amount that has already been calculated; Calculation device. (Appendix 13) 13. The computing device of claim 12, When the first feature amount has not been calculated using the minimum feature amount corresponding to the biometric data for all times within the first time unit, the first feature amount calculation unit checks whether or not new biometric data within the first time unit has been acquired at a time interval shorter than the first time unit, and when new biometric data has been acquired, calculates a new first feature amount using a new minimum feature amount corresponding to the newly acquired biometric data and the first feature amount that has already been calculated. Calculation device. (Appendix 14) 14. The calculation device according to any one of Supplementary Notes 9 to 13, a second feature amount calculation unit that, after a second time unit that is a time unit longer than the first time unit has elapsed, calculates, as a second feature amount, a feature amount of the biometric data measured within the second time unit using the first feature amount corresponding to the biometric data included in the second time unit; the calculation unit calculates a value representing the physical condition based on the second feature amount. Calculation device. (Appendix 15) 15. The computing device of claim 14, after calculating the second feature amount, the second feature amount calculation unit calculates a new second feature amount by using the new first feature amount corresponding to the newly acquired biometric data within the second time unit and the second feature amount that has already been calculated. Calculation device. (Appendix 16) 16. The computing device of claim 15, When the second feature amount has not been calculated using the first feature amount corresponding to the biometric data for all times within the second time unit, the second feature amount calculation unit calculates a new second feature amount using a new first feature amount corresponding to newly acquired biometric data and the second feature amount that has already been calculated, every time the subsequent second time unit elapses or every time a preset time shorter than the second time unit elapses. Calculation device. (Appendix 17) In the information processing device, Acquire biometric data measured in time series from a person, and calculate feature amounts for each predetermined minimum time unit of the acquired biometric data as minimum feature amounts; after a first time unit, which is a time unit longer than the minimum time unit, has elapsed, calculating, as a first feature amount, a feature amount of the biometric data measured within the first time unit, using the minimum feature amount corresponding to the biometric data within the first time unit; calculating a value representing the physical condition of the person using information based on the first feature amount; A computer-readable storage medium that stores a program for executing a process. [Explanation of symbols]

[0059] 10. Stress value calculation device 11 Data Acquisition Section 12 Short-term feature calculation unit 13 Feature calculation unit 14 Stress value calculation section 15 Output section 16 Acquired data storage unit 17 Feature memory unit 20 User terminal 30 Display device U person W Wearable Device 100 Calculation Device 101 CPU 102 ROM 103 RAM 104 Programs 105 Storage device 106 Drive device 107 Communication Interface 108 Input / Output Interface 109 Bus 110 Storage medium 111 Communication Network 121 Minimum feature calculation unit 122 First feature calculation unit 123 Calculation Unit

Claims

1. The information processing device Acquire biometric data measured in time series from a person, and calculate feature amounts for each predetermined minimum time unit of the acquired biometric data as minimum feature amounts; after a first time unit, which is a time unit longer than the minimum time unit, has elapsed, calculating, as a first feature amount, a feature amount of the biometric data measured within the first time unit, using the minimum feature amount corresponding to the biometric data within the first time unit; when the first feature amount is not calculated using the minimum feature amount corresponding to the biometric data for all times within the first time unit, after calculating the first feature amount, checking whether or not new biometric data within the first time unit has been acquired, and if new biometric data has been acquired, calculating a new first feature amount using a new minimum feature amount corresponding to the newly acquired biometric data within the first time unit and the first feature amount that has already been calculated; calculating a value representing the physical condition of the person using information based on the first feature amount; Calculation method.

2. 2. The calculation method according to claim 1, The information processing device, when the first feature amount is not calculated using the minimum feature amount corresponding to the biometric data for all times within the first time unit, after calculating the first feature amount, checking whether or not new biometric data within the first time unit has been acquired at a time interval shorter than the first time unit, and if new biometric data has been acquired, calculating new first feature amount using new minimum feature amount corresponding to the newly acquired biometric data and the first feature amount that has already been calculated; Calculation method.

3. 3. The calculation method according to claim 1 or 2, The information processing device, After a second time unit, which is a time unit longer than the first time unit, has elapsed, a feature amount of the biometric data measured within the second time unit is calculated as a second feature amount using the first feature amount corresponding to the biometric data included in the second time unit; calculating a value representing the physical condition based on the second feature amount; Calculation method.

4. 4. The calculation method according to claim 3, The information processing device, When the second feature amount is not calculated using the first feature amount corresponding to the biometric data for all times within the second time unit, After calculating the second feature amount, a new second feature amount is calculated using the new first feature amount corresponding to the newly acquired biometric data within the second time unit and the second feature amount that has already been calculated. Calculation method.

5. 5. The calculation method according to claim 4, The information processing device, When the second feature amount has not been calculated using the first feature amount corresponding to the biometric data for all times within the second time unit, a new second feature amount is calculated using a new first feature amount corresponding to newly acquired biometric data and the second feature amount that has already been calculated, every time the subsequent second time unit elapses or every time a preset time shorter than the second time unit elapses. Calculation method.

6. a minimum feature amount calculation unit that acquires biometric data measured from a person in time series and calculates, from the acquired biometric data, feature amounts for each predetermined minimum time unit as minimum feature amounts; after a first time unit, which is a time unit longer than the minimum time unit, has elapsed, calculating, as a first feature amount, a feature amount of the biometric data measured within the first time unit, using the minimum feature amount corresponding to the biometric data within the first time unit; when the first feature amount is not calculated using the minimum feature amount corresponding to the biometric data for all times within the first time unit, a first feature amount calculation unit that, after calculating the first feature amount, checks whether or not new biometric data within the first time unit has been acquired, and, if new biometric data has been acquired, calculates the new first feature amount using the new minimum feature amount corresponding to the newly acquired biometric data within the first time unit and the first feature amount that has already been calculated; a calculation unit that calculates a value representing a physical condition of a person using information based on the first feature amount; A computing device comprising:

7. In the information processing device, Acquire biometric data measured in time series from a person, and calculate feature amounts for each predetermined minimum time unit of the acquired biometric data as minimum feature amounts; after a first time unit, which is a time unit longer than the minimum time unit, has elapsed, calculating, as a first feature amount, a feature amount of the biometric data measured within the first time unit, using the minimum feature amount corresponding to the biometric data within the first time unit; when the first feature amount is not calculated using the minimum feature amount corresponding to the biometric data for all times within the first time unit, after calculating the first feature amount, checking whether or not new biometric data within the first time unit has been acquired, and if new biometric data has been acquired, calculating a new first feature amount using a new minimum feature amount corresponding to the newly acquired biometric data within the first time unit and the first feature amount that has already been calculated; calculating a value representing the physical condition of the person using information based on the first feature amount; A program for executing a process.

Images