Information processing apparatus, information processing method, and program
阅读说明:本技术 信息处理装置、信息处理方法和程序 (Information processing apparatus, information processing method, and program ) 是由 伊神徹 于 2018-04-04 设计创作,主要内容包括:[问题]提供了能够在测量自由移动的用户的心率或脉搏中的波动中形成测量的最佳状态的信息处理装置、信息处理方法和程序。[解决方案]提供了一种信息处理装置,包括:可靠性计算单元,用于计算指示从由用户穿戴的脉搏波传感器获取的感测数据获取的脉搏中的波动的身体指数的可靠性,或者从脉搏中的波动计算用户的物理状态;以及控制单元,基于计算出的可靠性控制各种处理。([ problem ] to provide an information processing device, an information processing method, and a program capable of forming an optimal state of measurement in measuring the fluctuation in the heart rate or pulse of a freely moving user. [ solution ] Provided is an information processing apparatus including: a reliability calculation unit for calculating reliability of a body index indicating fluctuation in a pulse wave acquired from sensing data acquired by a pulse wave sensor worn by a user, or calculating a physical state of the user from the fluctuation in the pulse wave; and a control unit that controls various processes based on the calculated reliability.)
1. An information processing apparatus comprising:
a reliability calculation section that calculates reliability of pulsation change data obtained from sensing data obtained from a pulse wave sensor worn by a user or a body index that is calculated from the pulsation change data and indicates a physical state of the user; and
a control unit that controls various processes based on the calculated reliability.
2. The information processing apparatus according to claim 1, wherein the reliability is calculated based on at least one of: the state of the user, the wearing state of the pulse wave sensor and the obtained pulse change data.
3. The information processing apparatus according to claim 2, wherein the reliability is calculated based on a state of the user, the state being acquired by a motion sensor worn by the user.
4. The information processing apparatus according to claim 2, wherein the reliability is calculated based on a wearing state of the pulse wave sensor, the wearing state being acquired by a sensor worn by the user and the pulse wave sensor.
5. The information processing apparatus according to claim 1, further comprising a detection section that detects an abnormal value from the pulsation change data.
6. The information processing apparatus according to claim 5, wherein the reliability is calculated based on the detected abnormal value.
7. The information processing apparatus according to claim 5, wherein the control unit controls the detection section based on the calculated reliability.
8. The information processing apparatus according to claim 5, wherein the detection section detects the abnormal value by extracting pulsation variation data within a section of a predetermined length from the pulsation variation data, and compares the extracted pulsation variation data within the section of the predetermined length with a predetermined pattern.
9. The information processing apparatus according to claim 5, wherein the detection section changes a parameter for detecting the abnormal value in accordance with a physical characteristic of the user.
10. The information processing apparatus according to claim 5, further comprising a correction section that corrects the pulsation variation data based on the detected abnormal value.
11. The information processing apparatus according to claim 10, wherein the control unit controls the correction portion based on the calculated reliability.
12. The information processing apparatus according to claim 10, wherein the correcting section changes the correction process in accordance with a type of the body index to be calculated.
13. The information processing apparatus according to claim 10, wherein the correction section extracts the pulsation variation data within a section of a predetermined length from the pulsation variation data, identifies a pattern of the extracted pulsation variation data within the section of the predetermined length, and changes the correction process according to the identified type of the pattern.
14. The information processing apparatus according to claim 10, further comprising an index calculation section that calculates the body index based on the corrected pulsation variation data.
15. The information processing apparatus according to claim 14, wherein the control unit controls the index calculation section based on the calculated reliability.
16. The information processing apparatus according to claim 14, wherein the index calculation section weights the pulsation change data or the body index for each section based on the reliability.
17. The information processing apparatus according to claim 1, wherein the control unit controls the pulse wave sensor based on the calculated reliability.
18. The information processing apparatus according to claim 1, wherein the control unit controls at least one of: a detection process of detecting an abnormal value from the pulsation change data, a correction process of correcting the pulsation change data, and a calculation process of calculating the body index from the pulsation change data, the detection process, the correction process, and the calculation process being executed in the information processing apparatus.
19. An information processing method comprising:
calculating reliability of pulsation variation data obtained from sensing data obtained by a pulse wave sensor worn by a user or a body index calculated from the pulsation variation data and indicating a physical state of the user; and is
Various processes are controlled based on the calculated reliability.
20. A program for causing a computer to implement:
a function of calculating reliability of pulsation change data obtained from sensing data obtained by a pulse wave sensor worn by a user or a body index calculated from the pulsation change data and indicating a physical state of the user; and is
The functions of the various processes are controlled based on the calculated reliability.
Technical Field
The present disclosure relates to an information processing apparatus, an information processing method, and a program.
Background
It is known to use HRV (heart rate variability) indices based on heart rate variability when assessing the degree of psychological stress and assessing autonomic nerve function. For example, the HRV index may be obtained from a heart rate interval (also referred to as R-R interval (RRI)) calculated by using an Electrocardiogram (ECG) obtained by attaching electrodes or the like to a body part of the user for measurement. The HRV index may also be obtained from a pulse rate interval (PPI) calculated from pulse rate changes highly correlated with heart rate changes. Apparatuses for acquiring such RRIs and the like are disclosed in the following
Reference list
Patent document
Patent document 1: japanese unexamined patent application publication No. H7-284482
Patent document 2: japanese unexamined patent application publication No. 2010-162282
Patent document 3: japanese unexamined patent application publication No. 2009-261419
Disclosure of Invention
Problems to be solved by the invention
In recent years, sensors and the like that detect heart rate variation and pulse rate variation have been miniaturized, which allows a user to wear the sensors and continuously measure the heart rate variation and the pulse rate variation. Therefore, measurement is performed even in the case of free activity of the user such as taking daytime action (moving freely), and sometimes the user does not have to be in a stationary state or keep the same posture when measuring heart rate variation or pulse rate variation. In other words, the measurement of heart rate variation and pulse rate variation is not necessarily in a preferred state. The heart rate variation and the pulse rate variation measured in this state may include, for example, noise caused by the user's motion. This sometimes makes the reliability of the measured heart rate variation and pulse rate variation, the reliability of the HRV index calculated based on the measured heart rate variation and pulse rate variation, and the like lower. However, the HRV index and the like for a user who can freely move about need to be an index having high reliability.
Accordingly, the present disclosure proposes a new and improved information processing apparatus, information processing method, and program that can make measurement of a heart rate variation or a pulse rate variation of a user who is walking freely possible to achieve a preferred state.
Means for solving the problems
According to the present disclosure, there is provided an information processing apparatus including: a reliability calculation unit for calculating the reliability of the pulsation change data or the body index; and a control unit that controls various types of processing based on the calculated reliability. Pulsatile change data is obtained from sensed data obtained by a pulse wave sensor worn by a user. From the pulsatile change data, a body index is calculated, which is indicative of the physical state of the user.
Further, according to the present disclosure, there is provided an information processing method including: calculating the reliability of the pulsation variation data or the body index; and controls various types of processing based on the calculated reliability. Pulsatile change data is obtained from sensed data obtained by a pulse wave sensor worn by a user. From the pulsatile change data, a body index is calculated, which is indicative of the physical state of the user.
Further, according to the present disclosure, there is provided a program for causing a computer to realize: a function of calculating reliability of pulsation change data or body index; and controls the functions of various types of processing based on the calculated reliability. Pulsatile change data is obtained from sensed data obtained by a pulse wave sensor worn by a user. A body index is calculated from the pulsatile change data and is indicative of the physical state of the user.
Effects of the invention
As described above, according to the present disclosure, it is possible to provide an information processing apparatus, an information processing method, and a program that make it possible to realize a preferred state for measurement of a heart rate variation or a pulse rate variation of a user who freely walks.
It should be noted that the above effects are not necessarily restrictive. Any effects indicated in the description or other effects that can be understood from the description may be achieved in addition to or instead of the above-described effects.
Drawings
Fig. 1 is an explanatory diagram describing a configuration example of the
Fig. 2 is a block diagram showing a configuration of the
Fig. 3 is an explanatory diagram describing the
Fig. 4 is an explanatory diagram showing an example of a pulse wave signal acquired by the
Fig. 5 is an explanatory diagram showing an example of time-series data of PPIs acquired by the
Fig. 6 is an explanatory diagram showing an example of wearing the
Fig. 7 is a block diagram showing a configuration of the
Fig. 8 is a block diagram showing a configuration of the
Fig. 9 is an explanatory diagram showing a data flow according to an embodiment.
Fig. 10 is an explanatory diagram (part 1) showing an example of a classification expression pattern of an abnormal value according to the embodiment.
Fig. 11 is an explanatory diagram (part 2) showing an example of a classification expression pattern of an abnormal value according to the embodiment.
Fig. 12 is an explanatory diagram describing correction of an abnormal value according to the first method of the embodiment.
Fig. 13 is an explanatory diagram (part 1) describing correction of an abnormal value according to the second method of the embodiment.
Fig. 14 is an explanatory diagram (part 2) describing correction of an abnormal value according to the second method of the embodiment.
Fig. 15 is an explanatory diagram (part 3) describing correction of an abnormal value according to the second method of the embodiment.
Fig. 16 is an explanatory diagram (part 4) describing correction of an abnormal value according to the second method of the embodiment.
Fig. 17 is an explanatory diagram (part 5) describing correction of an abnormal value according to the second method of the embodiment.
Fig. 18 is an explanatory diagram (part 6) describing correction of an abnormal value according to the second method of the embodiment.
Fig. 19 is an explanatory diagram (part 7) describing correction of an abnormal value according to the second method of the embodiment.
Fig. 20 is an explanatory diagram (part 8) describing correction of an abnormal value according to the second method of the embodiment.
Fig. 21 is an explanatory diagram describing calculation of reliability of the second method according to the embodiment.
Fig. 22 is an explanatory diagram describing calculation of reliability of the third method according to the embodiment.
Fig. 23 is an explanatory diagram describing calculation of reliability of the fourth method according to the embodiment.
Fig. 24 is an explanatory diagram (part 1) describing an output of reliability of the first method according to the embodiment.
Fig. 25 is an explanatory diagram (part 2) describing an output of reliability of the first method according to the embodiment.
Fig. 26 is an explanatory diagram describing an example of the hardware configuration of the information processing apparatus 900 according to the embodiment.
Detailed Description
Preferred embodiments of the present disclosure are described in detail below with reference to the accompanying drawings. It should be noted that in this description and the drawings, components having substantially the same functional configuration are denoted by the same reference symbols, and redundant description thereof is therefore omitted.
Further, in the description and drawings, a plurality of components having substantially the same or similar functional configurations are sometimes distinguished from each other by attaching different numerals to the same reference numerals. However, when it is not necessary to particularly distinguish a plurality of components having substantially the same or similar functional configurations, only the same reference symbols are attached. Moreover, similar components of different embodiments are sometimes distinguished by different letters appended to the same reference label. However, when it is not necessary to particularly distinguish similar components from each other, only the same reference symbols are attached.
Note that the description is made in the following order.
1. Overview of
1.1 overview of an
1.2 configuration of
1.3 configuration of the
2. Generating a background according to embodiments of the present disclosure
3. Detailed configuration of the
4. Information processing method according to the present embodiment
4.1 detection of outliers
4.2 related parameters
4.3 correction of outliers
4.4 calculation of reliability
4.5 output of reliability
5. Conclusion
6. Relating to hardware arrangements
7. Supplement
<1. overview of
<1.1 overview of
Next, a configuration according to an embodiment of the present disclosure is described. First, a configuration according to an embodiment of the present disclosure is described with reference to fig. 1. Fig. 1 is an explanatory diagram describing a configuration example of an
As shown in fig. 1, an
(wearable device 10)
The
Note that, it is assumed below that the
(Server 30)
For example, the
(user terminal 50)
The
It should be noted that fig. 1 shows that the
<1.2 configuration of
Next, the configuration of the
As shown in fig. 2, the
(input unit 100)
The
(output unit 110)
The
(sensor unit 120)
The
PPG sensor part 122-
The
Specifically, the
It should be noted that the present embodiment is not limited to acquiring a pulse wave signal using the PPG method described above, but may acquire a pulse wave signal in another method. For example, in the present embodiment, the pulse wave signal may be acquired by a laser doppler method. The laser doppler method is a method of using a frequency shift due to light scattered by a scattering substance (mainly red blood cells) moving in a
Then, the
The
Further, the
Further, the
Further, the
(control unit 130)
The
(communication unit 140)
The
(storage unit 150)
The
As described above, various wearable devices such as a glasses type, an ear device type, a bracelet type, and an HMD type can be used as the
Next, a configuration of the
(input unit 300)
The input unit 300 receives data or commands input to the
(output unit 310)
For example, the output unit 310 includes a display, a speaker, a video output terminal, an audio output terminal, and the like, and outputs various types of information as images, sounds, and the like.
(control unit 330)
The
(communication unit 340)
The communication unit 340 is provided in the
(memory cell 350)
The storage unit 350 is provided in the
The above describes an overview of the
As described above, the HRV index used in assessing the degree of psychological stress and assessing autonomic nerve function can be obtained from RRIs calculated, for example, based on heart rate changes (electrocardiograms). Further, the HRV index may be obtained from PPIs calculated from pulse rate changes highly correlated with heart rate changes. Such heart rate and pulse rate variations are affected not only by changes in the autonomic nervous system of the user, but also by changes in the physical state of the user. Therefore, it is desirable that the user is in a stationary state and maintains the same posture at the time of measurement.
Incidentally, in recent years, sensors and the like that detect heart rate variation and pulse rate variation have been miniaturized, which allow a user to wear the sensors and continuously measure heart rate variation and pulse rate variation. Therefore, the measurement is performed even in the case of free activities of the user such as taking daytime action (freely walking), and the user does not have to be in a stationary state or keep the same posture when measuring a heart rate change or a pulse rate change. For example. The heart rate variation and the pulse rate variation measured in this state may include noise caused by the user's motion. This sometimes makes the reliability of the measured heart rate variation and pulse rate variation, the reliability of the HRV index calculated based on the measured heart rate variation and pulse rate variation, and the like low.
Thus, in view of the above, the present inventors conceived to calculate the reliability of measuring heart rate variation and pulse rate variation, present the calculated reliability to the user together with the HRV index, and guide the state of the user to the ideal state of measurement. For example, in the case where a low reliability is presented to the user from the
In other words, in the present disclosure described below, an information processing apparatus, an information processing method, and a program are proposed that make it possible to enable measurement of a heart rate variation or a pulse rate variation of a user who is walking freely to be a preferred state.
In addition, data (pulse wave signals) of heart rate variation and pulse rate variation sometimes include abnormal values (noise) due to, for example, "physical movement of the user", "physical characteristics", "measurement device noise", "measurement algorithm error", and the like. Calculating the HRV index by using data including heart rate variation and pulse rate variation data of such abnormal values sometimes causes the HRV index to deviate from the correct normal HRV index that should be calculated. Therefore, when calculating the HRV index, the above-mentioned outlier must be solved to prevent the HRV index from deviating from the correct normal HRV index that should be calculated.
Therefore, in view of the above-described circumstances, the present inventors conceived to accurately detect an abnormal value (noise) from data of a heart rate variation and a pulse rate variation, and correct the data of the heart rate variation and the pulse rate variation based on the detected abnormal value. By doing so, it is possible to prevent the HRV index to be calculated from deviating from the correct normal HRV index that should be calculated. In other words, the present disclosure described below proposes an information processing apparatus, an information processing method, and a program that enable an increase in the accuracy of an HRV index calculated based on data obtained by measuring a heart rate variation or a pulse rate variation. Such embodiments of the present disclosure are described in detail later below.
<3. detailed configuration of
The configuration of the
(detection section 332)
The
(detection/correction control unit 334)
The detection
(correcting part 336)
Correction section 336 performs correction processing, such as insertion or removal of an outlier, on the PPI time-series data assigned an outlier flag. The time-series data of the PPI is acquired from the
(reliability calculating unit 338)
The
(HRV index calculation unit 342)
The HRV
For example, RMSSD is the square root of the mean of the squares of the differences between PPI values adjacent to each other in a time series. RMSSD is considered as an index indicating the state of tone of sympathetic nerves as one of cranial nerves.
For example, SDNN is the standard deviation of a data set of PPI values over a predetermined period (e.g., 12 seconds). SDNN is considered to be an index indicating the state of activity of the autonomic nervous system, including both sympathetic and parasympathetic nerves.
For example, LF/HF is the ratio of the power spectrum of the low frequency component (e.g., 0.004 to 0.15Hz) to the power spectrum of the high frequency component (0.15 to 0.4Hz) of the time series data of PPIs. LF/HF is considered to be an index indicating the balance between sympathetic and parasympathetic nerves. A high LF/HF is considered to indicate a state in which sympathetic nerves are dominant, and a low LF/HF is considered to indicate a state in which parasympathetic nerves are dominant.
<4. information processing method according to the present embodiment >
The detailed configuration of the
As shown in fig. 9, the pulse wave signal provided to the
<4.1 detection of abnormal value >
In the detection of an abnormal value according to the present embodiment described below, consecutive PPI values in a predetermined length period are extracted from the acquired time-series data of PPIs, and an abnormal value is detected by comparing the extracted time-series data of PPIs with the expression pattern of the classified abnormal value. In other words, according to the present embodiment, it is not determined whether each PPI value included in the time-series data of PPIs is an abnormal value, but a plurality of PPI values are determined at a time. This enables reduction of processing and processing time for detecting an abnormal value.
With reference to fig. 10 and 11, an example of detection of an abnormal value according to the present embodiment is described below. Each of fig. 10 and 11 is an explanatory diagram showing an example of a classification expression pattern of an abnormal value according to the present embodiment. Fig. 10 and 11 show eight expression patterns of the abnormal value. By performing experiments and observations in advance, a cycle of a predetermined length of time-series data of PPIs determined to include abnormal values is extracted based on the observation results, and behaviors are classified in the extracted cycle to obtain eight expression patterns. Specifically, each expression pattern of the abnormal values having a period of a predetermined length includes five consecutive PPI values (indicated by black dots in the diagram), and the PPI values determined as the abnormal values are further surrounded by circles in the diagram. In the embodiment described below, an abnormal value is detected by determining whether newly acquired time-series data of PPIs is applied to such an expression pattern of the abnormal value based on the magnitude relation between numerical values.
First, time-series data of PPIs in a cycle of a predetermined length, including five PPI values from the head of the acquired time-series data of PPIs, is extracted. The following references five individual PPI values included in the time-series data of the extracted PPI, p in chronological order n、p n+1、p n+2、p n+3And p n+4。
Next, in the detection of an abnormal value according to the present embodiment, the following expressions (1) to (5) are used to calculate the respective parameters roc, th for detecting an abnormal value roc1、th roc2、th eto1And th eto2. It should be noted thatTh is calculated from the mean value mu and the standard deviation sigma obtained by statistically processing time-series data of a plurality of pieces of PPI obtained by measuring pulse wave signals of respective users a plurality of times in advance, and the mean value mu 'and the standard deviation sigma' obtained by statistically processing time-series data of differences of PPI values adjacent to each other roc1、th roc2、th eto1And th eto2. In addition, th roc1、th roc2、th eto1And th eto2Defined as a predetermined fixed value.
[ expression 1]
roc=(p n+2-p n)/p n… … expression (1)
th roc1Expression (2) ((μ ' - α × σ ')/μ ' … …)
th roc2Expression (3) ((μ ' + α × σ ')/μ ' … …)
th eto1Expression (4) of (μ - α σ)/μ … …
th eto2Expression (5) of (μ + α σ)/μ … …
Note that α included in expressions (2) to (5) is a value determined in advance based on experiments, observations, or the like, for example, 1.0 may be set to α.
(case 1)
P included in time-series data of extracted PPI
nAnd p
n+1In the case where the following expressions (6) and (7) are satisfied, it is determined that the time-series data of the extracted PPI corresponds to
[ expression 2]
th eto2<p n+1/p n… … expression (6)
roc<th roc1… … expression (6)
(case 2)
P included in time-series data of extracted PPI
nAnd p
n+1In the case where the following expressions (8) and (9) are satisfied, it is determined that the time-series data of the extracted PPI corresponds to
[ expression 3]
th eto2<p n+1/p n… … expression (8)
th roc1<roc<th roc2… … expression (9)
(case 3)
P included in time-series data of extracted PPI nAnd p n+1In the case where the following expressions (10) and (11) are satisfied, it is determined that the time-series data of the extracted PPI corresponds to case 3 of fig. 10. In this case, p n+1And p n+2Detected as an outlier.
[ expression 4]
th eto2<p n+1/p n… … expression (10)
th roc2< roc … … expression (11)
(case 5)
P included in time-series data of extracted PPI
nAnd p
n+1In the case where the following expressions (12) and (13) are satisfied, it is determined that the time-series data of the extracted PPI corresponds to
[ expression 5]
th eto1>p n+1/p n… … expression (12)
th roc2< roc … … expression (13)
(case 6)
P included in time-series data of extracted PPI nAnd p n+1In the case where the following expressions (14) and (15) are satisfied, it is determined that the time-series data of the extracted PPI corresponds to case 6 of fig. 11. In this case, p n+1Detected as an outlier.
[ expression 6]
th eto1>p n+1/p n… … expression (14)
th roc1<roc<th roc2… … expression (15)
(case 7)
P included in time-series data of extracted PPI nAnd p n+1In the case where the following expressions (16) and (17) are satisfied, it is determined that the time-series data of the extracted PPI corresponds to case 7 of fig. 11. In this case, p n+1And p n+2Detected as an outlier.
[ expression 7]
th eto1>p n+1/p n… … expression (16)
roc<th roc1… … expression (17)
(case 4)
Next, the time-series data of the extracted PPI does not correspond to
[ expression 8]
th eto2<p n+4/p n+3… … expression (18)
th eto1<p n/p n+3… … expression (19)
p n>p n+1>p n+2>p n+3… … expression (20)
(case 8)
P included in time-series data of extracted PPI n、p n+1、p n+2、p n+3And p n+4In the case where the following expressions (21) to (23) are satisfied, it is determined that the time-series data of the extracted PPI corresponds to case 8 of fig. 11. In this case, p n、p n+1、p n+2And p n+3Detected as an outlier.
[ expression 9]
th eto2>p n+4/p n+3……Expression (21)
th eto1>p n/p n+3… … expression (22)
p n<p n+1<p n+2<p n+3… … expression (23)
As described above, a flag indicating an abnormal value is assigned to the detected abnormal value. Further, time-series data of PPIs in a predetermined length of cycle including the following five PPI values are extracted from the acquired time-series data of PPIs, and detection of an abnormal value as described above is performed. The detection of the abnormal value is then repeatedly performed until the processing of the PPI value at the end of the acquired PPI time-series data is completed.
It should be noted that in the detection of the abnormal value described above, it is determined which of the eight expression patterns of the abnormal value shown in fig. 10 and 11 corresponds to the extracted time-series data of the PPI in a period of a predetermined length, but the present embodiment is not limited to this method. For example, in the present embodiment, the abnormal value may be detected by determining whether the time-series data of the extracted PPI in a period of a predetermined length corresponds to not eight expression patterns but four abnormal values.
<4.2 relevant parameters >
In the above-described detection of the abnormal value, the respective parameters th for detecting the abnormal value have been described roc1、th roc2、th eto1And th eto2Is defined as a predetermined fixed value. However, in the present embodiment, each parameter th roc1、th roc2、th eto1And th eto2Not limited to a fixed value but may be a dynamically changing value.
Specifically, the tendency of the pulse wave signal of the user differs according to the physical characteristics of the user, and further changes according to the measurement time, the age of the user, and the physical state of the user. Therefore, in order to accurately detect an abnormal value, it is preferable to use a parameter th reflecting the influence of physical characteristics and the like of the user
roc1、th
roc2、th
eto1And th
eto2. Therefore, in the present embodiment, when the user is re-measuredFor example, the mean values μ and μ 'and the standard deviations σ and σ' are calculated by using time-series data of the PPI (for example, time-series data of the PPI stored in the
Further, when calculating the mean values μ and μ 'and the standard deviations σ and σ', time series data of PPIs in a section having higher reliability described below may be used. Further, when the mean values μ and μ 'and the standard deviations σ and σ' are calculated, the time-series data of the PPI used for the calculation may be weighted to more contribute to the mean values μ and μ 'and the standard deviations σ and σ' of the time-series data of the latest PPI. In addition, when calculating the parameter th
roc1、th
roc2、th
eto1And th
eto2In the meantime, α included in expressions (2) to (5) may be changed based on sensing data acquired from various biosensors (not shown) provided to the
<4.3 correction of abnormal value >
In correction of an abnormal value according to the present embodiment described below, an abnormal value is detected from the acquired time-series data of the PPI, and the time-series data of the PPI is corrected based on the detection result. According to the present embodiment, the abnormal value is corrected. This enables further increasing the accuracy of various HRV indices obtained from time-series data of corrected PPIs. As correction of an abnormal value, two examples are mainly described below: a method of performing correction according to the type of HRV index; and a method of performing correction according to the expression pattern of the abnormal value.
(first method)
First, with reference to fig. 12, a first method of performing correction according to the type of HRV index is described as an example of correcting an abnormal value. Fig. 12 is an explanatory diagram describing correction of an abnormal value according to the first method of the present embodiment. Specifically, the upper part of fig. 12 shows a correction example of the case a of the portion where the abnormal value is linearly supplementarily detected. The middle part of fig. 12 shows a correction example of the case B in which the abnormal value is removed. The lower part of fig. 12 shows a correction example of the case C where no correction is performed. According to a first method, the correction is performed according to the type of HRV index. This enables calculation of the HRV index by using the time-series data of the PPI corrected with the preferred correction method, and further increases the accuracy of the calculated HRV index.
Specifically, in this method, in the case where the RMSSD is calculated as the HRV index, case a shown in the upper part of fig. 12 is selected, and a portion where the abnormal value is detected is linearly supplemented. Further, in this method, in the case where the SDNN is calculated as the HRV index, the case B shown in the middle of fig. 12 is selected, and the abnormal value is removed. Further, in this method, in the case where LF/HF is calculated as the HRV index, the case C shown in the lower part of fig. 12 is selected, and no correction is performed. In this case, when calculating the LF/HF, the LF/HF is calculated by using the time-series data of PPIs in the longest section having no consecutive outliers.
(second method)
Next, with reference to fig. 13 to 20, a second method of performing correction according to the expression pattern of the abnormal value is described as an example of correcting the abnormal value. Each of fig. 13 to 20 is an explanatory diagram describing a correction abnormal value according to the second method of the present embodiment. In this method, the correction method is selected by taking into account the occurrence cause of the expression pattern of the abnormal value (
Situation 1-
First, with reference to fig. 13, correction of 1 in the case of the expression pattern of an abnormal value is described.
[ expression 10]
Δβ=p n+1–αp n… … expression (24)
Note that α included in expression (24) is a value determined in advance based on experiments, observations, and the like, for example, 1.0 may be set to αIn addition, α included in expression (22) may be calculation th roc1、th roc2α for isochronous use.
Situation 2-
Referring to fig. 14, correction in
[ expression 11]
p′ n+1=α*p n+1… … expression (25)
p″ n+1=p n+1-α*p n+1… … expression (26)
Note that α included in expressions (25) and (26) is a value determined in advance based on experiments, observations, or the like, for example, 0.5 may be set to α.
-situation 3-
Referring to fig. 15, correction in case 3 of the expression pattern of the abnormal value is described. Case 3 is a case where time-series data of PPI as shown in the middle of fig. 15 should be acquired because three peaks should be normally detected in the acquired pulse wave signal as shown in the upper part of fig. 15, but one large peak E results in failure to detect two peaks T. In particular toIn this case, as shown in the upper part of fig. 15, an erroneous peak E caused by impact noise or the like is detected, and it is impossible to detect two correct peaks T which are located close to the erroneous peak E and should be normally detected. As shown in the middle of fig. 15, an abnormal value p having a large value is detected n+1And p n+2. In this case, it is inferred that if the correct peak value T is detected, the abnormal value p is n+1And p n+2Is divided into three. Therefore, in case 3, as shown in the lower part of fig. 15, the abnormal value p n+1Decrease Δ β 1Abnormal value p n+2Decrease Δ β 2And p' n+1Insertion of outlier p n+1And p n+2In the middle of (a). P 'may be calculated according to the following expression (27)' n+1Note that Δ β may be determined from a predefined value or expression based on experimentation, observation, or the like 1And Δ β 2. In this way, an abnormal value caused by impact noise or the like can be corrected.
[ expression 12]
p′ n+1=Δβ 1+Δβ 2… … expression (27)
Situation 4-
Referring to fig. 16, correction in case 4 of the expression pattern of the abnormal value is described. In case 4, as shown in the upper part of FIG. 10, the PPI value (p) in the PPI time-series data is gradually decreased
n、p
n+1、p
n+2And p
n+3) And returns to a normal value (p) that should be detected at a certain point of time
n+4). Such an abnormal value p is generated by detecting peaks at intervals smaller than those of normal pulse waves
n、p
n+1、p
n+2And p
n+3This is because an erroneous peak due to the addition of high-frequency noise caused by the heartbeat to the pulse wave signal is detected. For example, in the
[ expression 13]
m=(p n+p n+1+p n+2+p n+3) Expression/3 … … (28)
Situation 5-
Referring to fig. 17, correction in
[ expression 14]
Δβ=p n+1–αp n… … expression (29)
Note that α included in expression (29) is a value determined in advance based on experiments, observations, or the like, for example, 1.0 may be set to α.
Situation 6-
Referring to fig. 18, correction in case 6 of the expression pattern of the abnormal value is described. Case 6 is a case where one peak should be normally detected in the acquired pulse wave signal as shown in the upper part of fig. 18, but since an erroneous peak E due to impact noise or the like caused by an external influence is also detected, time-series data of PPI as shown in the middle part of fig. 18 is acquired. In this case, if a correct peak is detected, it is estimated that one peak is detected. Thus, in case 6, as shown in the lower part of FIG. 18, p n+1Is added to p according to the following expression (30) n+2To calculate new p' n+2. Then, in case 6, p n+2Is corrected to calculated p' n+2And deleting p n+1. In this way, an abnormal value caused by impact noise or the like can be corrected.
[ expression 15]
p′ n+2=p n+1+p n+2… … expression (30)
Situation 7-
Referring to fig. 19, correction in case 7 of the expression pattern of the abnormal value is described. Case 7 is a case where one peak should be normally detected in the acquired pulse wave signal as shown in the upper part of fig. 19, but since an erroneous peak E due to impact noise or the like caused by external influence is detected, time-series data of PPI as shown in the middle part of fig. 19 is acquired. In this case, if the correct peak value T is detected, it is estimated that one peak value is detected. Thus, in case 7, p is as shown in the lower part of FIG. 19 n+1Is added to p according to the following expression (31) n+2To calculate new p' n+1. Then, in case 7, p n+1Is corrected to calculated p' n+1And deleting p n+2. In this way, an abnormal value caused by impact noise or the like can be corrected.
[ expression 16]
p′ n+1=p n+1+p n+2… … expression (31)
Situation 8-
Referring to fig. 20, correction in case 8 of the expression pattern of the abnormal value is described. In case 8, as shown in the upper part of fig. 20, the PPI value in the PPI time-series data becomes gradually higher (p) n、p n+1、p n+2And p n+3) And returns to a normal value (p) to be detected at a certain point of time n+4). So that such an abnormal value p is generated n、p n+1、p n+2And p n+3This is because high-frequency noise caused by the heartbeat is added to the pulse wave signal, and the peak value to be detected cannot be normally detected. In this case, if a correct peak value T is detected, the peak value that should be detected should be larger than the four peak values detected as abnormal values. Therefore, in case 8, as shown in the lower part of fig. 20, correction is performed to replace the abnormal value p n、p n+1、p n+2Replacement of p by m n+3And is in p n+3Followed by addition of p 'similarly having an m value' n+3. M can be calculated according to the following expression (32). In this way, an abnormal value caused by high-frequency noise or the like can be corrected.
[ expression 17]
m=(p n+p n+1+p n+2+p n+3) /5 … … expression (32)
Note that, in the present embodiment, correction of an abnormal value is not limited to the above-described method, or is not particularly limited. In the present embodiment, for example, an abnormal value may be corrected in accordance with the reliability described below. Specifically, in this case, an abnormal value detected in a section of the time-series data of the PPI having a higher degree of reliability due to some variation of the autonomic nervous system of the user is estimated, and the abnormal value is selected not to be actively corrected. In contrast, it is estimated that an abnormal value detected in a section of time-series data of PPIs having a lower degree of reliability is generated due to an external influence such as an impact, and the abnormal value is selected to be actively corrected. Further, in the present embodiment, regarding the detection of the abnormal value and the correction of the abnormal value, the tendency of the past time-series data of PPIs of the user can be learned by machine learning, and the abnormal value can be detected and corrected according to the tendency of each user based on the learning result.
<4.4 calculation of reliability >
In the calculation of the reliability according to the present embodiment described below, the reliability of time-series data of PPIs acquired from pulse wave signals or the HRV index acquired from time-series data of PPIs is calculated from the viewpoint of whether the state of the user at the time of measurement is suitable for measuring pulse wave signals. As described above, in the case of calculating the HRV index for the purpose of evaluating the degree of psychological stress and evaluating autonomic nerve function, it is desirable that the user be in a stationary state and maintain the same posture when measuring the pulse wave signal. The pulse wave signal is used as basic data of the HRV index. Further, the reliability may be calculated from whether or not the wearing state of the
(first method)
First, as the reliability r
iThe calculation of the reliability r by using the sensing data acquired by the
Specifically, in this method, when measuring the pulse wave signal of the user, acceleration data caused by the motion of the user is acquired from the
Next, in the method, the values of a plurality of vectors Ai are used to calculate an average value μ iAnd standard deviation σ i. Further, in the method, the calculated average value μ iAnd standard deviation σ iFor calculating a "still score" Sr indicating the degree of stillness of the user and a "posture score" Sp indicating the degree of change in posture of the user, that is, a motion state according to the following expressions (33) and (34). It should be noted that it is estimated that Sr has a smaller value if the user is in a stationary state, and that Sp has a smaller value if the user's posture is not changed.
[ expression 18]
Sr=μ i/(2*3σ μ) … … expression (33)
Sp=σ i/(2*3σ σ) … … expression (34)
Note that σ in the above expressions (33) and (34) μAnd σ σIs a set of average values mu calculated in advance from a plurality of vectors Ai obtained from acceleration data in daily life of each user iAnd a set of standard deviations σ iThe respective standard deviation of.
Note that it is preferable to perform peak elimination processing on the stationary score Sr and the pose score Sp so that the values thereof fall within a range of 0 or more and 1 or less. Then, in this method, the reliability r is calculated from the following expression (35) by using the calculated rest score Sr and posture score Sp i。
[ expression 19]
r iα Sr + (1- α) Sp … … expression (35)
It should be noted that α included in expression (33) is a value determined in advance based on experiments, observations, or the like, for example, a value greater than or equal to 0 and less than or equal to 1 may be set to α.
For example, the reliability r obtained in this manner is shifted iIs presented to the user. In this case, it is preferable that the air conditioner,degree of reliability r iMay be presented to the user along with the calculated resting score Sr and gesture score Sp.
Further, in this method, it is sufficient that the stillness score Sr indicating the degree of stillness of the user and the posture score Sp indicating the degree of change in the posture of the user can be calculated, and that the average value μ as described above is excluded
iAnd standard deviation σ
iOther statistics may be used for the calculation. Further, in this method, for example, the stationary score Sr and the posture score Sp may be calculated by using acceleration data in the respective axial directions of X, Y and Z acquired from a three-axis acceleration sensor (not shown) mounted in the
Further, in this method, the posture and state of the user may be estimated from the sensed data acquired by the
(second method)
Next, as the reliability r
iThe calculation of the reliability r by using the pulse wave signal acquired by the
Specifically, the change in the direct current component (DC component) included in the pulse wave signal is quantized within a predetermined period, so that the stillness score Sr indicating the degree of stillness of the user can be calculated. Therefore, in this method, a change in the direct current component of the pulse wave signal is detected, the above-described stationary fraction Sr is calculated based on the detection result, and the reliability r is calculated in a method similar to the first method by using the calculated stationary fraction Sr
i. More specifically, the pulse wave signal includes a pulsating component (AC component) corresponding to a change in blood flow caused by pulsation of the heart of the user, and a direct current component (DC component) corresponding to reflected light and scattered light from a blood layer other than the pulsation and a tissue other than the blood. In the case where the user is in a non-stationary state such as moving, for example, a change in the DC component of the pulse wave signal is caused because the
(third method)
Next, as the reliability r
iThe calculation of the reliability r by using the variation of the pulse wave based on the pulse wave signal acquired by the
The pulse wave signal acquired by the
(fourth method)
As described above, the reliability r can also be calculated from the angle of view whether or not the wearing state of the
In order to properly acquire the pulse wave signal, the
Further, in this method, the wearing state of the
(fifth method)
Further, the reliability r may also be calculated by detection using the above-described abnormal value
i. Then, calculation of the reliability r by detection using an abnormal value is described
iAs the reliability r
iExample of the calculation method of (1). In the case where an abnormal value is detected, it is estimated that the user is not in a state suitable for measuring the pulse wave signal or that the wearing state of the
The reliability r in a certain measurement period can be expressed by the following expression (36) iE.g. wherein T MRepresents a measurement time of time-series data of the PPI in a measurement period, and T NRepresents the total time to obtain a PPI value for which no outliers are detected during the measurement period.
[ expression 20]
r i=T N/T M… … expression (36)
Further, the reliability r in a certain measurement period can be expressed by the following expression (37) iFor example, where M denotes the total number of data pieces included in the time-series data of the PPI in the measurement period, and N denotes the total number of data pieces of the PPI value having no abnormal value detected in the measurement period.
[ expression 21]
r iExpression N/M … … (37)
Further, in the method, the reliability r may be calculated based on an expression pattern of an abnormal value in the obtained time-series data of the PPI i. For example, the reliability r in a certain measurement period can be expressed by the following expression (38) iWherein M represents the number of time series included in the PPI in the measurement periodTotal number of data segments in accordance with, and N iThe number of abnormal values in each case (i is a natural number from 1 to 8) within each of the eight expression patterns falling within the above-described abnormal values is represented and determined as an abnormal value in the measurement cycle.
[ expression 22]
r i=(α 1*N 1+α 2*N 2+α 3*N 3+α 4*N 4+α 5*N 5+α 6*N 6+α 7*N 7+α 8*
N 8) /M … … expression (38)
Note that, in the above expression (38), α i (i is a natural number from 1 to 8) represents a weight factor determined for each case of an expression pattern of an abnormal value note that, for example, the weight factor α i may be experimentally determined based on time-series data of PPIs measured in advance and environmental information at the time of measurement such as the presence or absence of an external impact, an action pattern of a user, and a wearing state of the
It should be noted that the above-mentioned reliability r
iThe calculation method of (d) is an example, and the reliability r according to the present embodiment
iThe calculation method of (2) is not limited to the above-described method. In addition, the above-mentioned reliability r may be combined with each other
iThe method of (3). In the present embodiment, for example, the reliability r obtained in the fifth method described above
iThe reliability r that can be calculated from the acceleration data acquired by the
<4.5 output of reliability >
For example, the reliability r calculated as described above
iIs presented to the user, allowing the user to identify the reliability of the HRV indices presented togetherAnd (4) sex. In addition, for example, the calculated reliability r may also be used
iControl the
(first method)
First, description will be made of the reliability r with reference to fig. 24 and 25 iThe first method presented to the user as reliability r iAn example of the output method of (1). Each of fig. 24 and 25 is a diagram for describing the reliability r of the first method according to the present embodiment iIllustrative diagram of the output of (a). According to the method, for example, a low degree of reliability r is determined iPresenting a user with an action that guides the user to rest and to maintain the same posture to improve the reliability r i. Further, in this method, the reliability r is calculated iIf the reliability of the HRV index or the like presented to the user is low, the method may improve the reliability r for the reason or request the user iIs presented to the user.
More specifically, in this method, as shown in fig. 14, when the stress degree calculated based on the HRV index is displayed to the user, it is determined according to the degree of reliability r
iThe manner of display of the degree of pressure is changed. For example, as shown in the left part of FIG. 24, at the reliability r
iIn the high case, the stress level is displayed by increasing the contrast. Meanwhile, as shown in the right part of fig. 24, at the reliability r
iIn the low case, the degree of stress is displayed by reducing the contrast. Performing display by changing the contrast in this way facilitates the user to recognize the reliability of the degree of stress of the display. Further, for example, as shown in fig. 25, when time-series data of HRV indices are graphically displayed to a user, the gray-out
As a degree of reliability r iThe method of presentation to the user may be based on the reliability r for the display iVarying the degree of reliability r iIs displayed byColor, luminance, etc. The number may be specifically used to display the reliability r i. In the method, the reliability r is determined iThe method of presentation to the user is not particularly limited. In the method, the reliability r is determined iPresenting the user with an action in this way that guides the user to rest and to maintain the same posture improves the reliability r i. Further, user identification is facilitated along with a degree of reliability r iReliability of presented HRV index.
Furthermore, in this method, when the reliability r is present
iThe reason for the reliability of the measurement of the pulse wave signal is reduced and the reliability r is improved
iMay be presented to the user. In this case, the reference is used to calculate the reliability r
iThe estimated reliability r such as the values of the stationary score Sr and the pose score Sp
iCause of the reduction, and the reliability r is determined based on the estimation result
iReasons for the reduction and improvement of the reliability r
iThe method of (2) is presented to the user. More specifically, the sudden motion of the user is estimated as a degree of reliability r
iIn the case of the reason for reduction, the estimated reason is presented to the user like "sudden motion reduction reliability". Furthermore, in this method, in this case, the reliability r will be improved
iSuch as "please rest" or "please make a stable gesture". In addition, the reliability r is estimated
iThe reason for the reduction is that in the case where the wearing state of the
It should be noted that in this method, the reliability r
iReason for the reduction and exhibit improved reliability r
iThe method of (2) is not limited to displaying characters such as the words described above. For example, wearable devicesThe
(second method)
Next, the reliability r will be described
iThe second method of feedback to the
Further, in this method, the reliability r may be set
iThe data is fed back to the
Furthermore, in this method, the reliability r
iMay be fed back to the HRV
Further, in the method, in the case of calculating the predetermined index by combining HRV indexes in a plurality of cycles, it is possible to calculate the reliability r based on the reliability in each cycle
iThe above combination value is calculated after performing weighting processing on each HRV index. More specifically, the user's degree of stress per day is sometimes defined as a weighted average of a plurality of SDNNs (types of HRV indices) calculated during the day. In this method, in this case, weighting processing is performed to provide a large weight to a high degree of reliability r
iIs the value of SDNN in the high part, and provides a small weight to the low reliability r
iIs SDNN in the low section. This weighting makes it possible to suppress the impossibility of properly measuring the pulse wave signal and the degree of reliability r
iIs the effect of SDNN in the low portion on the above-mentioned pressure level,and the degree of pressure is acquired with high reliability. In other words, according to this method, the reliability r is determined
iThe calculation processing fed back to the
<5. conclusion >
As described above, according to the present embodiment, calculating the reliability of the measurement of the pulse wave signal and presenting the above reliability to the user together with the HRV index and the like enables guiding the state of the user to an ideal state for measurement. Further, the control of feeding back the calculated reliability to the
Further, according to the present embodiment, accurately detecting an abnormal value from the time-series data of the PPI and correcting the time-series data of the PPI based on the detected abnormal value makes it possible to prevent the HRV index or the like to be calculated from deviating from the correct normal HRV index or the like that should be calculated. In other words, according to the present embodiment, the accuracy of the HRV index or the like calculated based on the time-series data of the PPI can be increased.
<6. related hardware configuration >)
Fig. 26 is an explanatory diagram describing an example of the hardware configuration of the information processing apparatus 900 according to the present embodiment. In fig. 26, an information processing apparatus 900 is taken as an example of the hardware configuration of the
For example, the information processing apparatus 900 includes a CPU 950, a ROM 952, a RAM954, a recording medium 956, an input/output interface 958, and an operation input device 960. Further, information-processing apparatus 900 includes a display device 962, a communication interface 968, and a sensor 980. Further, for example, the information processing apparatus 900 uses the bus 970 as a transmission path for data to be coupled with each component mutually.
(CPU 950)
For example, the CPU 950 includes one or two or more processors, each of which includes an arithmetic circuit such as a CPU, various processing circuits, and the like, and functions as a control unit (e.g., the above-described control unit 130) that controls the entire information processing apparatus 900. Specifically, the CPU 950 realizes the functions of the above-described
(ROM 952 and RAM 954)
The ROM 952 stores data and the like for control such as programs and operating parameters used by the CPU 950. For example, the RAM954 temporarily stores programs and the like executed by the CPU 950.
(recording Medium 956)
The recording medium 956 functions as the above-described storage unit 350, and stores, for example, data used for the information processing method according to the present embodiment and various types of data such as various applications. Here, examples of the recording medium 956 include a magnetic recording medium such as a hard disk and a nonvolatile memory such as a flash memory. The recording medium 956 may be detachably attached to the information processing apparatus 900.
(input/output interface 958, operation input device 960, and display device 962)
For example, the input/output interface 958 is coupled to an operation input device 960, a display device 962, and the like. Examples of the input/output interface 958 include a USB (universal serial bus) terminal, a DVI (digital visual interface) terminal, an HDMI (high-definition multimedia interface) (registered trademark) terminal, various processing circuits, and the like.
For example, the operation input device 960 is used as the input device 300 described above, and the operation input device 960 is coupled to the input/output interface 958 inside the information processing apparatus 900.
For example, a display device 962 serves as the above-described output unit 310, and the display device 962 is provided on the information processing apparatus 900 and is coupled to the input/output interface 958 inside the information processing apparatus 900. Examples of the display device 962 include a liquid crystal display, an organic electroluminescence display, and the like.
Note that the input/output interface 958 can also be coupled to an external device such as an external operation input device (e.g., a keyboard, a mouse, or the like) of the information processing apparatus 900, and an external display device. Further, the input/output interface 958 may be coupled to a driver (not shown). The drive is a reader/writer for a removable recording medium such as a magnetic disk, an optical disk, or a semiconductor memory and is installed in the information processing apparatus 900 or externally attached to the information processing apparatus 900. The drive reads out information recorded on the mounted removable recording medium and outputs the information to the RAM 954. Further, the drive is also capable of writing a record to a mounted removable recording medium.
(communication interface 968)
The communication interface 968 serves as the communication unit 340 for performing wireless or wired communication with an external apparatus such as the
(sensor 980)
The sensor 980 serves as the
The above has exemplified an example of the hardware configuration of the information processing apparatus 900. It should be noted that the hardware configuration of the information processing apparatus 900 is not limited to the configuration shown in fig. 26. Specifically, each of the above-described components may be configured using a general-purpose member, or may be configured by using hardware dedicated to the function of each component. This configuration may be changed as appropriate according to the technical level at the time of executing the present disclosure.
For example, in the case where the information processing apparatus 900 communicates with an external device or the like via a coupled external communication device or in the case where the information processing apparatus 900 is configured to perform processing in an independent manner, the information processing apparatus 900 does not necessarily include the communication interface 968. Further, communication interface 968 may have components that can communicate with one or two or more external devices in multiple communication schemes. Further, the information processing apparatus 900 may also be configured without providing the recording medium 956, the operation input device 960, the display device 962, and the like.
Further, the information processing apparatus 900 according to the present embodiment may be applied to a system including a plurality of apparatuses, which is considered to be coupled to a network (or communicate with each other), such as cloud computing, for example. In other words, for example, the information processing apparatus 900 according to the present embodiment described above can also be realized as an information processing system that performs processing by using a plurality of apparatuses according to the information processing method of the present embodiment.
<7. supplement >
Note that the embodiments of the present disclosure described above may include, for example, a program for causing a computer to function as the information processing apparatus according to the present embodiment, and a nonvolatile tangible medium having the program recorded thereon. Further, the program may be distributed via a communication line (including wireless communication) such as the internet.
Further, the processing steps according to each of the above embodiments are not necessarily performed in the described order. For example, the order in which the steps are performed may be changed as appropriate. Further, the various steps may be performed partially simultaneously or separately instead of in a chronological order. Further, the processing method of each step does not have to be processed according to the described method, but may be processed in another method by another functional unit, for example.
The preferred embodiments of the present disclosure have been described in detail above with reference to the accompanying drawings, but the technical scope of the present disclosure is not limited to such embodiments. Obviously, various changes and modifications within the technical concept described in the appended claims may be conceived by those of ordinary skill in the art of the present disclosure, and it is to be understood that such changes and modifications naturally fall within the technical scope of the present disclosure.
Further, the effects described herein are merely illustrative and exemplary, and not restrictive. In other words, other effects that would be apparent to one skilled in the art from the description herein may be achieved in accordance with the techniques of this disclosure in addition to or in lieu of the effects described above.
Note that the following configuration also falls within the technical scope of the present disclosure.
(1) An information processing apparatus comprising:
a reliability calculation section that calculates reliability of pulsation change data obtained from sensing data obtained by a pulse wave sensor worn by a user or a body index that is calculated from the pulsation change data and indicates a physical state of the user; and
a control unit that controls various processes based on the calculated reliability.
(2) The information processing apparatus according to (1), wherein the reliability is calculated based on a state of the user, a wearing state of the pulse wave sensor, or the acquired pulsation variation data.
(3) The information processing apparatus according to (2), wherein the reliability is calculated based on a state of the user, the state being acquired by a motion sensor worn by the user.
(4) The information processing apparatus according to (2), wherein the reliability is calculated based on a wearing state of the pulse wave sensor, the wearing state being acquired by a sensor worn by the user and the pulse wave sensor.
(5) The information processing apparatus according to (1), further comprising a detection section that detects an abnormal value from the pulsation variation data.
(6) The information processing apparatus according to (5), wherein the reliability is calculated based on the detected abnormal value.
(7) The information processing apparatus according to (5) or (6), wherein the control unit controls the detection section based on the calculated reliability.
(8) The information processing apparatus according to any one of (5) to (7), wherein the detection section detects the abnormal value by extracting the pulsation change data within a section of a predetermined length from the pulsation change data, and compares the extracted section of the pulsation change data of the predetermined length with a predetermined pattern.
(9) The information processing apparatus according to any one of (5) to (8), wherein the detection section changes a parameter for detecting the abnormal value according to a physical characteristic of the user.
(10) The information processing apparatus according to (5), further comprising a correcting section that corrects the pulsation variation data based on the detected abnormal value.
(11) The information processing apparatus according to (10), wherein the control unit controls the correction section based on the calculated reliability.
(12) The information processing apparatus according to (10) or (11), wherein the correction section changes the correction process according to a type of the body index to be calculated.
(13) The information processing apparatus according to (10) or (11), wherein the correction section extracts the pulsation variation data within a section of a predetermined length from the pulsation variation data, identifies a pattern of the extracted section of the pulsation variation data of the predetermined length, and changes the correction process according to a type of the identified pattern.
(14) The information processing apparatus according to (10), further comprising an index calculation section that calculates a body index based on the corrected pulsation variation data.
(15) The information processing apparatus according to (14), wherein the control unit controls the index calculation section based on the calculated reliability.
(16) The information processing apparatus according to (14), wherein the index calculation section weights the pulsation variation data or the body index in each segment based on the reliability.
(17) The information processing apparatus according to (1), wherein the control unit controls the pulse wave sensor based on the calculated reliability.
(18) The information processing apparatus according to (1), wherein the control unit controls at least one of a detection process of detecting an abnormal value from the pulsation change data, a correction process of correcting the pulsation change data, or a calculation process of calculating the body index from the pulsation change data, the detection process, the correction process, and the calculation process being executed in the information processing apparatus.
(19) An information processing method comprising:
calculating a reliability of the pulsation variation data or the body index, the pulsation variation data being obtained from sensing data obtained by a pulse wave sensor worn by the user, the body index being calculated from the pulsation variation data and being indicative of a physical state of the user; and is
Various types of processing are controlled based on the calculated reliability.
(20) A program for causing a computer to realize the steps of:
a function of calculating reliability of pulsation change data or a body index, the pulsation change data being acquired from sensing data acquired by a pulse wave sensor worn by a user, the body index being calculated from the pulsation change data and indicating a physical state of the user; and is
The functions of the various types of processing are controlled based on the calculated reliability.
REFERENCE SIGNS LIST
1: information processing system
10. 10 a: wearable device
12: watchband part
14: pressure sensor unit
30: server
50: user terminal
70: network
100. 300, and (2) 300: input unit
110. 310: output unit
120: sensor unit
122: PPG sensor unit
124: motion sensor unit
130. 330: control unit
140. 340, and (3): communication unit
150. 350: memory cell
200: measurement site
202: blood vessel
332: detection part
334: detection correction control unit
336: correcting part
338: reliability calculation unit
342: HRV index calculation unit
350: memory cell
352:DB
500: gray-view display
900: information processing apparatus
950:CPU
952:ROM
954:RAM
956: recording medium
958: input/output interface
960: operation input device
962: display device
968: communication interface
970: bus line
980: a sensor.
- 上一篇:一种医用注射器针头装配设备
- 下一篇:在便携式传感器设备中捕获ECG测量