• 专利附录
  • 专利说明
  • 权利要求
  • 类似技术
  • 同族专利
  • 引用文献
  • 法律状态
  • 优先权
    • 专利摘要:
    STRESS MEASUREMENT DEVICE FOR DETERMINING A USER'S STRESS LEVEL, WEARABLE DEVICE USED BY A USER, STRESS MEASUREMENT SYSTEM, STRESS MEASUREMENT METHOD FOR DETERMINING A USER'S STRESS LEVEL, PROGRAM OF COMPUTER, BLOOD PRESSURE MEASURING DEVICE AND BLOOD PRESSURE MEASUREMENT METHOD The present invention relates to a stress measurement device and method (10) for determining a user's stress level (15) ( 1), in particular long-term stress. The stress measuring device (10) comprises an input interface (12) for receiving a skin conductivity signal (11) which indicates the user's skin conductivity (1), and the skin conductivity signal ( 11) forms the skin conductivity tracking data over time (13). The stress measuring device (10) further comprises a processing unit (14) for processing the skin conductivity tracking data (13), and the processing unit (14) is adapted to determine, at least. minus a portion of the skin conductivity screening data (13), the values of a rise time (tr) between at least (...).
    公开号:BR112013026063B1
    申请号:R112013026063-7
    申请日:2012-04-02
    公开日:2021-08-31
    发明作者:Jan Johannes Gerarrdus De Vries；Martin Ouwerkerk
    申请人:Koninklijke Philips N.V；
    IPC主号:
    专利说明:

    FIELD OF THE INVENTION
    The present invention relates to a stress measurement device and method for determining a user's stress level, in particular long-term stress. The present invention also relates to a wearable device and a stress measuring system, and each comprises said stress measuring device. Furthermore, the present invention relates to a computer program that implements said stress measurement method. HISTORY OF THE INVENTION
    Skin conductivity is known as a measure for effective short-term reactions, such as emotions. In this sense, skin conductivity is typically analyzed using the phasic component of the skin conductivity signal, with rises and falls lasting on the order of seconds.
    For example, the article “Effect of movements on the electrodermal response after a startle event” by J. Schumm, M. Bachlin, C. Setz, B. Arnrich, D. Roggen and G. Troster, Second International Conference on Computer Technologies Diffused for Health, 2008, pages 315-318, reveals an Electrodermal Activity (EDA) sensor that measures EDA on fingers through finger strips, performs EDA signal processing and simultaneously measures finger acceleration. The effect of continuous stationary motions on EDA is presented. Controlled walking speeds as movements and startle events as a trigger are executed. EDA is investigated by measuring skin conductivity. The signal consists of a tonic component and a fast-changing phasic component superimposed on the tonic component. The startle event leads to peak shaped responses in the phasic portion of the signal. A simple peak detection algorithm with a threshold is applied to the phasic signal. A similar device is also described in the article "Discriminating Stress From Cognitive Load Using a Wearable EDA Device" by C. Setz, B. Arnich, J. Schumm, R. La Marca, G. Troster, U. Ehlert, IEEE Transactions on Information Technology in Biomedicine, Vol. 14, No. 2, March 2010, pages 410-417.
    In US 2009270170 A1 a method for obtaining biofeedback for a gaming device is disclosed.
    In WO 2010/107788 A2 a stress monitoring system and method are presented.
    EP 1407713 A1 discloses an apparatus and a method for healthcare-based mobile biomedical signals.
    In WO 2008/099320 A1 a computer program product, a device and a method for measuring the excitation of a user are presented.
    In "Decomposing skin conductance into tonic and phasic components" by Lim CL, Rennie C, Barry RJ, Bahramali H, Lazzaro I, Manor B and Gordon E., Int. Journal of Psychophysiology, February 1997, 25(2), pages 97-109 a method for decomposing skin conductivity into tonic and phasic components is reported.
    When considering determining the stress level of a physiological signal, it is important to discriminate between short-term stress and long-term stress. Short-term stress is usually conceptualized in terms of startle responses or events, that is, the user faces an altered context and the user's body acts quickly to adapt to the new context situation, which results in a change of a physiological sign. Long-term stress occurs when short-term stress occurs too often, without sufficient possibility of recovery. Constructed effects, which cause more bodily processes to change or be disturbed, possibly result in illnesses due to a weaker immune system, burnout syndrome, and the like.
    For example, in "Central effects of stress hormones in health and disease: Understanding the protective and damaging effects of stress and mediators", B. McEwen, European Journal on Pharmacology 583, 2008, pages 174-185, it is revealed that by a On the one hand, acute (short-term) stress responses promote adaptation and survival through the responses of the neurological, cardiovascular, autonomic, immune and metabolic systems and, on the other hand, chronic (long-term) stress can promote and exacerbate the pathophysiology through the same systems that are deregulated. The chronic (long-term) stress load and the changes in personal behavior that accompany it are called allostatic overload.
    The general problem with physiological signs is a good interpretation of these signs. Generally, the context situation in which the physiological signal was measured must be known. SUMMARY OF THE INVENTION
    It is an object of the present invention to provide a (long-term) stress measurement device and method for determining a user's stress level, in particular long-term stress, which provides independent detection of the situation of stress level context. It is also an object of the present invention to provide said stress measuring device and method which is less intrusive and/or cheaper. Furthermore, it is an object of the present invention to provide a wearable device comprising said stress measuring device, a stress measuring system comprising said stress measuring device and a computer program implementing said method of stress measurement. Another aspect of the invention provides a blood measuring device and method. The invention is defined by the independent claims.
    In a first aspect of the present invention, a stress measurement device is presented for determining a user's stress level, in particular long-term stress, which device comprises an input interface for receiving a signal from skin conductivity which indicates the user's skin conductivity, and the skin conductivity signal forms the skin conductivity tracking data over time. The device further comprises a processing unit for processing the skin conductivity tracking data, with the processing unit adapted, during at least a portion of the skin conductivity tracking data, for determining the values of a time of elevation between at least two different points (time) of the skin conductivity tracking data, of a frequency distribution of the elevation time values, and for the determination of the user's stress level, in particular long-term stress, based on the determined frequency distribution.
    In another aspect of the present invention, a wearable device is provided, which wearable device comprises the stress measuring device and a skin conductivity sensor for detecting the wearer's skin conductivity.
    In yet another aspect of the present invention, a stress measurement system is presented in which the stress measurement system comprises the stress measurement device, a skin conductivity sensor for detecting the conductivity of the user's skin, and a output device to output the user's stress level.
    In another aspect of the present invention, a stress measurement method is presented for determining a user's stress level, in particular long-term stress, which method comprises receiving a skin conductivity signal that indicates the the user's skin conductivity, and the skin conductivity signal over time forms the skin conductivity tracking data and processes the skin conductivity tracking data, the processing of which comprises determining, over at least a portion of the data conductivity tracking data, the values of a rise time between at least two different points of the skin conductivity tracking data, the determination of a frequency distribution of the rise time values, and the determination of the stress level the user, in particular the long-term stress, based on the determined frequency distribution.
    In yet another aspect of the present invention, a computer program is provided in which the computer program comprises program code means for causing a computer to perform the steps of the stress measurement method when said computer program is executed on the computer.
    The basic idea of the invention is to take into account the way in which the skin conductivity is screened by means of the rise time values (rise time between at least two different points, in particular two exact points) and use the distribution of these time values of elevation for determining the stress level, in particular the long-term stress level. Rise time is basically a measure of shape. Thus, the variety of forms, or the variety of rise time values in the skin conductivity screening data, in particular the skin conductivity responses, is used in determining a user's long-term stress level. It was found that the type of frequency distribution, in particular the shape of its histogram representation, is an indicator of the user's (chronically increased) blood pressure (which is related to hypertension) and therefore is also an indicator of the level of long-term user stress. The level of long-term (or chronic) stress, or the quantification of long-term stress, depends on conditions that change over a longer period of time, for example, a period of one or more weeks. According to this invention, a quantification of the cumulative effect of subsequent stressors is given, for example, over a time period of several hours. With the use of this invention, the long-term stress level (or allostatic load) can be assessed, and even a prediction of an altered stress response in the near future can be given after the occurrence of severe stressors. Furthermore, the present invention provides a less intrusive device, especially as it can be integrated with a wearable device such as a bracelet. In addition, the necessary hardware is inexpensive and can be easily miniaturized. Thus, a cheaper device can also be provided. Additionally, the present invention allows for context-independent stress measurement. Therefore, there is no need for additional context information, for example for user input and thus a simple stress measurement device and system can be provided that can measure stress over a busy day 10 with the activities of daily living.
    Preferred embodiments of the invention are defined in the dependent claims. It should be understood that the claimed stress measurement method, computer program, wearable device, and stress measurement system 15 have preferred embodiments similar and/or identical to those of the claimed stress measurement device as defined in dependent claims.
    In one embodiment, the stress measuring device is adapted to extract the tonic component of the skin conductivity signal 20 or the skin conductivity tracking data, and to process the tonic component (such as the skin conductivity tracking data ). This can be done, for example, by the processing unit. The tonic component indicates gradual and lasting changes in the conductivity of the skin. Rise time values can be determined in the tonic component and thus rise over a longer period of time. These values, more particularly their frequency distribution, can then be used in determining the long-term stress level.
    In an alternative or cumulative embodiment, the stress measuring device is adapted to extract the phasic component of the skin conductivity signal or skin conductivity tracking data, and to process the phasic component (such as the conductivity tracking data of the skin) . The phasic component indicates short-term changes in skin conductivity. Rise time values can be determined in the phasic component and thus rise over a shorter period of time. These values, more particularly their frequency distribution, can then be used in determining the long-term stress level.
    In one embodiment, the processing unit is adapted for detecting peaks in the skin conductivity tracking data. In this way, rise time values are determined only for the peaks (which are of interest), and not for all skin conductivity tracking data. For example, a rise time value can be determined for each (detected) peak. This reduces calculation time. This embodiment can be used, for example, in combination with previous embodiments of separation and processing of the tonic and/or phasic component.
    In a variant of this embodiment, peaks are detected using the slope of the skin conductivity tracking data. This provides more effective peak detection compared to simple peak detection using amplitude alone.
    In another variant of this embodiment, the processing unit is adapted for detecting skin conductivity responses as peaks in the skin conductivity data. This variant can be combined, for example, with the previous variant of detecting the slope of the skin conductivity tracking data. Furthermore, this variant can be used, for example, in combination with performing separation and processing of the phasic component of the skin conductivity signal. In a variant of this variant, the processing unit is adapted for determining a rise time value for each (detected) skin conductivity response. For example, an onset time point (time point at which the skin conductivity response starts) and a peak time point (time point at which the skin conductivity response is at its maximum) are determined for each conductivity response of the skin, and the rise time value is between the start time point and its corresponding maximum time point. Thus, rise time values are determined only for the conductivity responses of the skin, which reduces calculation time and effort.
    In yet another embodiment, the frequency distribution of rise time values is determined using a histogram representation. This provides an easy implementation.
    In another embodiment, the frequency distribution is a cumulative frequency distribution.
    In another embodiment, the stress level is determined based on the uniformity or flatness of the determined frequency distribution. In a variant of this embodiment, the stress level is greater when the determined frequency distribution is less uniform (or with more peaks) and/or the stress level is lower when the determined frequency distribution is more uniform (or with fewer peaks ) . This provides a reliable way to determine the long-term stress level. The uniformity/flatness of the frequency distribution, or its histogram representation, is an indicator/estimator of blood pressure and thus also of the long-term stress level.
    In yet another embodiment, the stress level is determined using at least one statistical measure selected from the group comprising the standard deviation, mean, variance, skewness and kurtosis of the determined frequency distribution. This allows the description of the type/shape of the frequency distribution (or its histogram representation) in a reliable way.
    In a variant of this embodiment, especially in combination with the standard deviation as the statistical measure, the processing unit is adapted for determining an estimated (user) blood pressure (systolic) value based on the statistical measure in particular the standard deviation. In particular, the standard deviation is a good statistical measure for describing the type/shape of the frequency distribution (or its histogram representation), and for determining an indicator/estimator of the user's blood pressure and thus the level. of long-term stress. The user's (long-term) stress level can then be determined according to the estimated blood pressure value. Thus, from the estimated blood pressure value (systolic), or the estimated blood pressure values over time, the long-term stress level of the user/patient can be determined.
    In another variant, when the statistical measure is the standard deviation of the given frequency distribution, the stress level is greater when the standard deviation is smaller and/or the stress level is smaller when the standard deviation is larger. In particular, when determining an estimated blood pressure value, the estimated blood pressure value is larger when the standard deviation is smaller, and/or the estimated blood pressure value is smaller when the standard deviation is larger. Thus, there is a negative correlation between the estimated value of blood pressure (systolic), or long-term stress level, and the statistical measure of the determined frequency distribution, in particular, the standard deviation. For a user/patient with hypertension and thus with a chronic increase in blood pressure, their blood pressure level (systolic) will be at an elevated value for a longer period of time, in particular for a few hours, or days, or weeks.
    In yet another embodiment, in particular in combination with, or as an alternative to the above embodiment, the stress level is determined by comparing the determined frequency distribution and the at least one reference frequency distribution. For example, a functional distance is used for the comparison between the determined frequency distribution and at least one reference frequency distribution. For example, the functional distance can be a measure of divergence (such as the Kullback-Leibler divergence). All of these measurements are good predictors of blood pressure, which is known to relate to long-term stress. In addition, the stress level can also be determined using other suitable means, such as using appropriately chosen quantiles or quantile ranges from the given frequency distribution (or cumulative frequency distribution).
    In another embodiment, the stress measuring device is adapted to form the skin conductivity tracking data over more than one hour, in particular more than 6 hours, more than 12 hours (noon), more than 24 hours (one day), or even several days or weeks. This allows for the determination of long-term stress that occurs over a longer period of time.
    In a variant of this embodiment, the processing unit is adapted to process the skin conductivity screening data over more than one hour, in particular more than 6 hours, more than 12 hours (midday), more than 24 hours (one day), or even several days or weeks. Thus, a large part or all of the formed skin conductivity screening data (not just a small part) is processed in order to determine the long term stress level. BRIEF DESCRIPTION OF THE DRAWINGS
    These and other aspects of the invention will become apparent from and elucidate with reference to the embodiments described below. In the following drawings,
    Fig. 1 shows a schematic diagram of a stress measuring device according to an embodiment;
    Fig. 2 shows an illustration of a stress measurement system according to one embodiment;
    Fig. 3 shows a perspective view of a wearable device according to an embodiment;
    Fig. 4 shows a diagram of exemplary skin conductivity screening data;
    Fig. 5 shows an enlarged portion of the exemplary skin conductivity screening data of Fig. 4;
    Figs. 6a and 6b show different exemplary histogram representations of frequency distributions; and
    Fig. 7 shows a diagram of an exemplary linear regressor. DETAILED DESCRIPTION OF THE INVENTION
    Fig. 1 shows a schematic diagram of a stress measuring device 10 according to an embodiment, in particular a long-term stress measuring device. The stress measuring device 10 comprises an input interface 12 for receiving a skin conductivity signal 11 that indicates the conductivity of the user's skin 1. For example, a skin conductivity sensor 20 can detect the conductivity of the skin. of a user 1 and providing the corresponding skin conductivity signal 11 to the input interface 12. The skin conductivity signal 11 forms, over time, the skin conductivity tracking data 13. For example, the device The stress measurement device 10 may comprise a memory (not shown in Fig. 1) in which the received skin conductivity signal is stored over time to produce the skin conductivity tracking data 13.
    The stress measuring device is used in particular in determining a long-term stress level 15 (hereinafter simply referred to as stress level 15). Thus, the stress measuring device 10 can be adapted to form the skin conductivity tracking data 13 over more than one hour, more than 6 hours, more than 12 hours (midday), more than 24 hours ( a day), or even several days or weeks. Thus, the memory described above must have sufficient capacity to store the skin conductivity signal during that period of time.
    The stress measuring device 10 further comprises a processing unit 14 for processing the skin conductivity screening data 13. The processing unit 14 is adapted to determine, in at least a portion of the skin conductivity screening data. 13, the values of a rise time tr between at least two different points of the skin conductivity tracking data 13. This can be carried out, for example, by the first determining means 14a. Furthermore, the processing unit 14 is adapted for determining the frequency distribution of the rise time values tr. This can be carried out, for example, by the second determining means 14b. Finally, the processing unit 14 is adapted for determining the stress level 15 of the user 1 based on the determined frequency distribution. This can be carried out, for example, by the third determining means 14c. It should be understood that the described processing of the skin conductivity screening data can be performed using any suitable hardware and/or software. For example, the first, second and third determining means 14a, 14b, 14c can be implemented in software.
    The stress measuring device 10 of the embodiment of Fig. 1 further comprises an output interface 16 for outputting the output data 17 indicating the level of stress 15. For example, the output data 17 may be provided to a device output 40 to user 1 stress level 15 output 1.
    A corresponding stress measurement method for determining a stress level 15 of a user 1, in particular long-term stress, comprises receiving a skin conductivity signal 11 which indicates the skin conductivity of user 1, and the skin conductivity signal 11 forms over time the skin conductivity tracking data 13 and processes the skin conductivity tracking data 13. Processing comprises determining, for at least a portion of the skin conductivity tracking data. skin conductivity 13, the values of a rise time between at least two different points of the skin conductivity 13 tracking data, the determination of a frequency distribution of the rise time values, and the determination of the stress level 15 user, based on the determined frequency distribution. A computer program comprising program code means can be used to cause a computer to perform the steps of said stress measurement method when said computer program is executed on the computer. The computer can be a personal computer or any other suitable computer medium. For example, an embedded processor can be used. The computer can be built-in or an integral part of the stress measurement device.
    Fig. 2 shows an illustration of a stress measurement system 100 according to one embodiment. The stress measurement system 100 comprises a skin conductivity sensor 20 for detecting the conductivity of the user's skin 1. In Fig. 2, the skin conductivity sensor 20 is integrated with a wearable device worn by the user 1, in particularly a bracelet. However, the skin conductivity sensor 20 can also detect the skin conductivity in other suitable body parts, such as the finger(s) and/or the palm or volar side of the hand. The stress measurement system 100 further comprises an output device 40 for outputting the stress level 15 for the user 1. The output device 40 may be portable, for example, being attached to a belt of the user 1, such as indicated in Fig. 2. The output device 40 shown in Fig. 2 comprises the display means 41 for displaying the stress level 15. Alternatively or additionally, the stress level 15 can also be sent to the user 1 with use of sound, light, and/or vibration.
    In general, the output device 40 can be a separate device (as shown in Fig. 2), or it can be integrated, for example, with the skin conductivity sensor 20 or with a wearable device comprising the sensor. Output can be through a variety of modalities such as audio (eg sound), visual (eg light), and/or tactile (eg vibrations) feedback.
    The stress measuring system 100 further comprises the stress measuring device 10 described above. The stress measuring device 10 can be a separate part, or it can be integrated with the wearable device or the output device 40. In addition, the stress measuring device 10 can be adapted to output a warning signal when the stress level 15 exceeds a predefined threshold. The output device 40 can be adapted to output a warning to the user when he receives the warning signal. In this way, the device and the system can be used in an application to prevent people at high risk, for example, of brain damage such as stroke patients, from becoming very tense and thus having an increase in blood pressure, being led to potential brain damage. The stress measurement system 100 can further comprise additional devices, such as an electrocardiogram (ECG) sensor, such as the ECG chest belt 20a shown in Fig. 2. The ECG sensor can detect the user's electrocardiogram 1. A From the electrocardiogram, heart rate variability (HRV) can be determined, which is also known to relate to stress. In this way, the determination of the stress level 15, as explained above, can be further enriched. In general, long-term stress measurement can be combined with other stress measurements (potentially short-term stress) to obtain richer information about the user's stress level or state. This additional (short-term) stress measurement can be obtained, for example, by means of physiological measurements such as the ECG mentioned above. However, other suitable measurements such as BVP, respiration, skin temperature, electroencephalography (EEG)/brain activity, activity measurement (eg via an accelerometer) and/or questionnaires may also be used for additional measurements.
    Fig. 3 shows a perspective view of an embodiment of a wearable device 30 worn by a user. In the embodiment of Fig. 3, the wearable device 30 is in the form of a bracelet comprising a part of bracelet material 33 and a casing 34. It should be understood that the wearable device 30 could also be worn around any other part. of the appropriate body, such as the ankle, foot or hand. In Fig. 3, two skin conductivity electrodes 31, 32 are integrated into the wrist strap material 33. Skin conductivity electrodes 31, 32 are used for detecting the wearer's skin conductivity. Thus, the wearable device 30 comprises the skin conductivity sensor 20. In particular, the skin conductivity electrodes 31, 32 may be arranged to contact the volar side of the wrist, where normally there is not a large amount. of hair. Thus, a better measurement of the conductivity of the skin can be provided.
    Furthermore, the wearable device 30 comprises the stress measuring device 10, for example the stress measuring device 10 described with reference to Fig. 1. The stress measuring device 10 may be integrated with the casing 34 of the wearable device 30. The wearable device 30 may further comprise a transmitter for wireless data transmission over a wireless communication link, such as the data output 17.
    Fig. 4 shows a diagram of exemplary skin conductivity screening data 13, for example, measured with the wearable device 30 as shown in Fig. 3. The x-axis indicates time t over a period of several hours, here from about 5 1/2 hours, from 3 pm (3 pm) to 8 pm (20:30 pm). Thus, the conductivity data for the skin 13 is formed over several hours. The processing unit 14 can then in particular be adapted to process the skin conductivity tracking data 13 over several hours.
    In Fig. 4, the y-axis indicates the conductivity of the skin, also called the galvanic skin response (GPR), measured in microSiemens µS. Each point of the skin conductivity tracking data 13 indicates the skin conductivity detected by the skin conductivity sensor 20 at that specific point at time t. Emotional events appear as peaks with a steep upward slope and a milder downward slope. In Fig. 4, each peak corresponds to the response of the sympathetic nervous system to an emotion release event (communicated via the vagus nerve to the skin's sweat glands).
    In particular, the skin conductivity screening data 13 comprises or is the tonic component. The tonic component indicates long-lasting gradual changes in skin conductivity, despite being represented by the general or basic form of the skin conductivity screening shown in Fig. 4. The stress measuring device 10 as shown, for example, in Fig. 1, can be adapted to extract the tonic component of the skin conductivity signal 11 (before the skin conductivity scan data 13 is formed), and thus the skin conductivity scan data 13 comprise only (or are) the tonic component (and not the phasic component), and then the tonic component is processed by the processing unit 14. Alternatively, the stress measuring device 10 can be adapted to extract the tonic component of the conductivity tracking signal from the skin 13 (after the skin conductivity tracking data 13 is formed), and then the tonic component of the skin conductivity tracking data is processed by the processing unit 14. For example, from the skin conductivity screening data 13 shown in Fig. 4, the tonic component can be extracted and processed. Rise time tr values can be determined in the tonic component and thus rise over a longer period of time. The tonic component can be extracted, for example, with the use of a frequency filter, such as a low-pass filter, for example, for frequencies up to 0.05 Hz.
    Alternatively or cumulatively, the skin conductivity screening data 13 may comprise or be the phasic component. The phasic component indicates short-term changes in skin conductivity, thus, it would be represented by small changes superimposed on the general/basic (tonic) form of skin conductivity tracking, for example, the thickness of the line (or oscillation) shown in Fig. 4. The stress measuring device 10 as shown, for example, in Fig. 1 can be adapted to extract the phasic component of the skin conductivity signal 11 (before the skin conductivity tracking data 13 is formed), and thus the skin conductivity tracking data 13 comprise only (or are) the phasic component (and not the tonic component), and then the phasic component is processed by the processing unit 14. Alternatively, the measuring device of stress 10 can be adapted to extract the phasic component of the skin conductivity tracking signal 13 (after the skin conductivity tracking data 13 is formed), and then compose it. The phasic component of the skin conductivity tracking data is processed by the processing unit 14. For example, from the skin conductivity tracking data 13 shown in Fig. 4, the phasic component can be extracted and processed. Rise time tr values can be determined in the phasic component and thus rise over a shorter period of time. The phasic component can be extracted, for example, using a frequency filter, such as a high-pass filter, for example, for frequencies above 0.05 Hz. Skin conductivity may also be used (as, for example, a method known as SCRGAUGE, see Kolish P., 1992, "SCRGAUGE-A Computer Program for the Detection and Quantification of SCRs", Electrodermal Activity, Boucsein, W. ed. , New York: Plenum: 432-442, which is incorporated herein by reference), as will be explained below.
    Fig. 5 shows an enlarged portion of the exemplary skin conductivity tracking data 13 of Fig. 4, for example, a few minutes (e.g., about 3 minutes) of the skin conductivity tracking data 13 shown in Fig. 4. The processing unit 12 is adapted for detecting peaks in the skin conductivity tracking data 13 of Fig. 5. In particular, the processing unit 12 is adapted for detecting the SCR 1 skin conductivity responses, SCR2, SCR3 (see Fig. 5) as peaks in the skin conductivity tracking data 13. For example, the skin conductivity responses SCR 1, SCR2, SCR3 are detected using the slope of the conductivity tracking data 13. SCR skin conductivity responses are detected by evaluating the slope, or slope gradient, at subsequent points of the skin conductivity tracking data 13. If the slope exceeds a given value, it is determined that an SCR skin conductivity response is present. Then, a start time point for toi, to2, to3 (time point at which the SCR starts) and a maximum time point tmi, tm2, tm3 (time point at which the SCR is at its maximum) are determined for each skin conductivity response SCR1, SCR2, SCR3. Detection of the onset time point for an SCR skin conductivity response is performed by moving backward on the curve to the point of maximum curvature. Detection of the maximum time point tm of an SCR skin conductivity response is performed by moving forward until the slope becomes negative. Then, the rise time value tr2, tr2, tr3 is determined between (each) start time point to2, to2, to3 and its corresponding maximum time point tm2, tm2, tm3. Thus, with reference to Fig. 5, a rise time value tr is determined for each detected skin conductivity response SCR1, SCR2, SCR3. For each skin conductivity response SCR1, SCR2, SCR3, the rise time value tr3, tr2, tr3 is between (exactly) two different points to2, to2, to3 (start time point) and tm2, tm2, tm3 (maximum time point), respectively.
    In addition, other values for each skin conductivity response can also be determined. In one example, the amplitude (range of amplitude) ampl, amp2, amp3 can be further determined. In particular, the amplitude ampl, amp2, amp3 corresponding to the respective rise time tr2, tr2, tr3 can be determined, for example, between (each) start time point to3, to2, to3 and its maximum time point tm2, tm2, tm3 corresponding. In another example, also the trec/2 half-recovery time can be further determined, at a point at which the skin conductivity tracking data falls to less than 1/2 the amplitude of the skin conductivity response SCR1, SCR2 , SCR3. In case the skin conductivity tracking data does not fall to this value in a reasonable period of time, the half-recovery time trec/2 can be estimated by extrapolating the negative slope skin conductivity tracking that occurs right after the local maximum.
    Then, the frequency distribution of these determined values of the rise time tr is determined, in particular, using a histogram representation. Fig. 6a and Fig. 6b show two different exemplary histogram representations of said frequency distributions. The x-axis indicates rise time tr, and the y-axis indicates frequency. Alternatively, the y-axis can also indicate cumulative frequency, in which case the frequency distribution would be a cumulative frequency distribution. For example, more than 100, in particular more than 400 or more than 800 peaks or skin conductivity responses can be used for frequency distribution or histogram representation. The histogram representation can be, for example, normalized.
    Then, a user 1's stress level 15 is determined based on the determined frequency distribution or its histogram representation. In particular, the stress level 15 can be determined based on the uniformity or flatness of the determined frequency distribution or histogram representation. For example, stress level 15 is determined to be greater when the given frequency distribution or histogram representation is less uniform (or has more peaks). Likewise, it is determined that the stress level 15 is lower when the determined frequency distribution or histogram representation is more uniform (or has fewer peaks). As can be seen in Fig. 6a, the frequency distribution or histogram representation is less uniform. Thus, in this case, it is determined that the stress level 15 is higher. As can be seen in Fig. 6b, the frequency distribution or histogram representation is more uniform. Thus, it is determined that stress level 15 is lower. Consequently, the uniformity or shape of the frequency distribution or the histogram representation can be used to determine the long-term stress level 15.
    The stress level 15 can be determined using at least one statistical measure selected from the group comprising the standard deviation, mean, variance, skewness and kurtosis of the determined frequency distribution or its histogram representation. In particular, the stress level 15 can be determined using the std standard deviation of the determined frequency distribution or its histogram representation. Having n the values xiz i = 1, 2, ... n, the standard deviation std is
    In a computational representation, the standard deviation is std = SQRT(1/(n-1)SUM( (xm)2) )=SQRT(1/(n-1) (n*m2+SUM(x2) - 2* m*SUM(x)). This only requires managing the number of n values, the sum of the SUM(x) values and the squared sum of 9. zzz . zv . SUM(x) values. little computational power to administer this statistical measure over a longer period of time.
    These statistical measures, in particular the standard deviation of the frequency distribution or the histogram representation, were found to be a good indicator of blood pressure, which is known to be related to long-term stress. In particular, when the statistical measure is the standard deviation of the given frequency distribution, the stress level is larger when the standard deviation is smaller and/or the stress level is smaller when the standard deviation is larger.
    The processing unit 14 can be adapted for determining an estimated blood pressure (in particular systolic) value on the basis of the statistical measure, in particular the standard deviation. The user's (long term) stress level can then be determined according to the estimated blood pressure value. Thus, from the estimated value of blood pressure (systolic), or the estimated values of blood pressure over time, the long-term stress level of the user/patient can be determined.
    The estimated blood pressure value is larger when the standard deviation is smaller, and/or the estimated blood pressure value is smaller when the standard deviation is larger.
    Thus, there is a negative correlation between the estimated value of blood pressure (systolic), or long-term stress level, and the statistical measure of the determined frequency distribution, in particular, the standard deviation. This will be explained below.
    Fig. 7 shows a diagram of an exemplary linear regressor. The x-axis indicates the std standard deviation of the frequency distribution of rise time tr values. The y axis indicates systolic blood pressure BP. The solid line represents the linear regressor of BP estimated blood pressures for a given measure of std(tr): BP = a+std *b. The correlation of the example shown in Fig. 7 is -0.75, which is considered very high in the context of physiological measurements. Thus, the std(tr) standard deviation can be considered as a good indicator for systolic blood pressure. The linear regressor of the estimated BP blood pressure decreases with increasing std(tr), which indicates that the higher measured std values correspond to the lower blood pressure values (as also indicated by the negative correlation).
    To specify the accuracy of the linear regressor, the positive signs in Fig. 7 indicate measurement values based on skin conductivity measurements and simultaneous systolic blood pressure measurements for different patients. The dashed lines in Fig. 7 indicate a confidence link around the linear regressor line (solid line), which here indicates a 95% confidence interval around the linear regressor, and thus the area in which a occurrence of 95% of the estimated blood pressure values (for each possible value of std(tr)). It should be noted that the confidence interval is highly dependent on the number of measurements. Thus, in general, the estimated blood pressure (in particular, systolic) is determined with a certain confidence range, for example, with a probability of more than 80%, in particular more than 90%, in particular more than 95 %.
    In the example shown in Fig. 7, the estimated blood pressure values are calculated over a time period of about three hours, for example, using the skin conductivity tracking data of Fig. 4 and/or the histogram representations of Fig. 6a and Fig. 6b. It is important to note that, with the use of said time period in which a wide variety of tasks can be performed by the user, the skin conductivity tracking data 13 or the determined skin conductivity responses or peaks include a wide variety of contextual effects that well reflect everyday life. Thus, it is shown that the statistical measure of the standard deviation of the rise time values is reasonably context-independent. Therefore, this statistical measure is well suited to the case where people wear a stress measuring device for a long period of time in everyday life, where many different context situations influence their skin conductivity.
    Alternatively or cumulatively, the stress level 15 can be determined by comparing the determined frequency distribution and at least one reference frequency distribution, in particular a reference frequency distribution set. For example, a functional distance can be used for the comparison between the determined frequency distribution and at least one reference frequency distribution. In one example, the functional distance is a measure of divergence (such as the Kullback-Leibler divergence). For example, a reference frequency distribution or histogram can be used for each stress level class (or blood pressure level). Once a new measurement has been made, the similarity between the new frequency distribution or histogram representation and each of the reference frequency distributions can be calculated using the divergence measure. Then, the closest reference frequency distribution is determined, and its corresponding estimated stress level/blood pressure value is determined. This method requires the formulation of at least one, in particular a set of reference frequency distributions, which is a single action and can be predefined, for example coded to the device. The formulation of reference frequency distributions can be automated through machine learning that incorporates the same similarity measure (eg, a divergence measure). For example, reference frequency distributions can be learned through "learning vector quantization".
    Thus, the comparison between the determined frequency distribution and at least one reference frequency distribution may comprise one or more of the following steps: - creation (at once, before the comparison is started) of at least one frequency distribution (in particular, at least two reference frequency distributions), for example a reference frequency distribution by blood pressure class (for example BP classes: {0-70, 71-100, 101-130, 131-Inf}), - for each determination of the stress level (long term) or estimated blood pressure value, compare the determined frequency distribution (or its histogram representation) with each of the reference distributions, in particular by means of calculating and using the functional distance between them (for example, provided by divergence measure) - for each determination of (long-term) stress level or blood pressure estimate, choosing her the closest reference frequency distribution by choosing the reference frequency distribution with the smallest divergence measurement value.
    In addition, the corresponding (long term) stress level or the estimated blood pressure value (blood pressure (BP) value) can be the output (eg 71-100).
    Although the invention has been illustrated and described in detail in the drawings and description above, said illustration and description are to be considered as illustrative or exemplary and not restrictive; the invention is not limited to the described embodiments. Other variations of the described embodiments may be understood and made by those skilled in the art in the practice of the claimed invention, from a study of the drawings, the disclosure and the appended claims.
    In the claims, the word "comprises" does not exclude other elements or steps, and the indefinite article "a" or "an" does not exclude a plurality. A single element or other unit can perform the functions of several items recited in the claims. The mere fact that certain measures are recited in mutually different dependent claims does not indicate that a combination of these measures cannot be used to advantage.
    A computer program may be stored/distributed on a suitable non-transient medium, such as an optical storage medium, or a solid-state medium provided together with or as part of other hardware, but it may also be distributed in other ways, such as via the internet or other wired or wireless telecommunications systems.
    Any reference signs in the claims are not to be construed as limiting the scope.
    权利要求:
    Claims (16)
    [0001]
    1. STRESS MEASUREMENT DEVICE (10) FOR DETERMINING A USER (1) STRESS LEVEL (15), wherein the device (10) comprises: - an input interface (12) for receiving a skin conductivity signal (11) which indicates a user's skin conductivity (1), and the skin conductivity signal (11) forms over time the skin conductivity tracking data (13), and - a processing unit (14) for processing the skin conductivity tracking data (13), and the processing unit (14) is adapted for determining, in at least a portion of the skin conductivity tracking data (13) , of the values of a rise time (tr) between at least two different points of the skin conductivity tracking data (13), characterized in that the processing unit (14) is further adapted for determining a frequency distribution of the values of rise time (tr), and for the determination of the level l (15) user stress (1) based on the determined frequency distribution.
    [0002]
    2. STRESS MEASUREMENT DEVICE (10) according to claim 1, characterized in that it is adapted to extract the tonic component of the skin conductivity signal (11) or the skin conductivity tracking data (13) and to processing the tonic component, and/or adapted to extract the phasic component of the skin conductivity signal (11) or the skin conductivity tracking data (13) and to process the phasic component.
    [0003]
    3. STRESS MEASUREMENT DEVICE (10) according to claim 1, characterized in that the processing unit is adapted for detecting peaks in the skin conductivity tracking data (13), in particular with the use of the slope of the skin conductivity screening data (13).
    [0004]
    4. STRESS MEASUREMENT DEVICE (10) according to claim 3, characterized in that the processing unit (12) is adapted for detecting the skin conductivity responses (CPR) as peaks in the skin conductivity data (13 ), in particular wherein the processing unit (12) is adapted for determining a rise time value for each skin conductivity response (CPR).
    [0005]
    5. STRESS MEASUREMENT DEVICE (10), according to claim 1, characterized in that the frequency distribution of the rise time values is determined using a histogram representation.
    [0006]
    6. STRESS MEASUREMENT DEVICE (10), according to claim 1, characterized in that the stress level (15) is determined based on the uniformity or flatness of the frequency distribution determined.
    [0007]
    7. STRESS MEASUREMENT DEVICE (10), according to claim 6, characterized in that the stress level (15) is greater when the determined frequency distribution is less uniform and/or where the stress level (15) is smaller when the determined frequency distribution is more uniform.
    [0008]
    8. STRESS MEASUREMENT DEVICE (10), according to claim 1, characterized in that the stress level (15) is determined using at least one statistical measure selected from the group comprising the standard deviation (std), the variance, asymmetry and kurtosis of the determined frequency distribution.
    [0009]
    9. STRESS MEASUREMENT DEVICE (10), according to claim 8, characterized in that the processing unit is adapted for determining an estimated blood pressure value based on the statistical measure, in particular the standard deviation.
    [0010]
    10. STRESS MEASUREMENT DEVICE (10), according to claim 1, characterized in that the stress level (15) is determined by comparing the determined frequency distribution and at least one reference frequency distribution.
    [0011]
    11. STRESS MEASUREMENT DEVICE (10) according to claim 1, characterized in that it is adapted to form the skin conductivity screening data (13) over more than one hour, in particular more than 6 hours, more than 12 hours, or more than 24 hours.
    [0012]
    12. WEARABLE DEVICE (30) USED BY A USER, the wearable device (30) being characterized by comprising the stress measuring device (10), as defined in claim 1, and a skin conductivity sensor (20) for the detection of the user's skin conductivity (1).
    [0013]
    13. STRESS MEASUREMENT SYSTEM (100), characterized in that it comprises: - the stress measurement device (10), as defined in claim 1, - a skin conductivity sensor (20) for detecting the conductivity of the skin of the user (1), and - an output device (40) to output the stress level (15) to the user (1).
    [0014]
    14. STRESS MEASUREMENT METHOD FOR DETERMINING A USER (1) STRESS LEVEL (15), wherein the method comprises: - receiving a skin conductivity signal (11) that indicates a skin conductivity of the user (1), and the skin conductivity signal (11) forms over time the skin conductivity tracking data (13), and - the processing of the skin conductivity tracking data (13), and o comprises determining, in at least a portion of the skin conductivity tracking data (13), the values of a rise time (tr) between at least two different points of the skin conductivity tracking data (13), characterized by processing further comprising determining a frequency distribution of rise time values (tr), and determining the user's stress level (15) based on the determined frequency distribution.
    [0015]
    15. BLOOD PRESSURE MEASURING DEVICE (10), comprising: an input interface (12) for receiving a skin conductivity signal (11) which indicates a user's skin conductivity (1), and the signal of skin conductivity (11) forms over time the skin conductivity tracking data (13), and a processing unit (14) for processing the skin conductivity tracking data (13), and the processing (14) is adapted to determine, in at least a portion of the skin conductivity tracking data (13), the values of a rise time (tr) between at least two different points of the skin conductivity tracking data (13), characterized in that the processing unit (14) is further adapted for determining a frequency distribution of the rise time values (tr), for determining at least one statistical measure of the determined frequency distribution, and for determined it an estimated blood pressure value based on the statistical measure.
    [0016]
    16. METHOD OF MEASUREMENT OF BLOOD PRESSURE, comprising: receiving a skin conductivity signal (11) that indicates a user's skin conductivity (1), and the skin conductivity signal (11) forms along the time the skin conductivity screening data (13), and processing the skin conductivity screening data (13), and comprising determining, in at least a portion of the skin conductivity screening data (13), ), of the values of a rise time (tr) between at least two different points of the skin conductivity tracking data (13), characterized in that the processing further comprises determining a frequency distribution of the rise time values ( tr), determining at least one statistical measure of the determined frequency distribution, and determining an estimated blood pressure value based on the statistical measure.
    类似技术:
    公开号 | 公开日 | 专利标题
    BR112013026063B1|2021-08-31|Stress measuring device for determining a wearer's stress level, wearable device worn by a wearer, stress measuring system, stress measuring method for determining a wearer's stress level, measuring device blood pressure and blood pressure measurement method
    Charlton et al.2017|Breathing rate estimation from the electrocardiogram and photoplethysmogram: A review
    US10531808B2|2020-01-14|Method of detecting the wearing limb of a wearable electronic device
    JPWO2017179696A1|2019-02-21|Biological information analyzer, system, and program
    KR101656611B1|2016-09-09|Method for obtaining oxygen desaturation index using unconstrained measurement of bio-signals
    Melillo et al.2015|Wearable technology and ECG processing for fall risk assessment, prevention and detection
    KR20170109554A|2017-09-29|A method and apparatus for deriving a mental state of a subject
    van Velzen et al.2017|Increasing accuracy of pulse transit time measurements by automated elimination of distorted photoplethysmography waves
    Zhang et al.2014|Adaptive motion artefact reduction in respiration and ECG signals for wearable healthcare monitoring systems
    Kurz et al.2010|Levodopa influences the regularity of the ankle joint kinematics in individuals with Parkinson’s disease
    JP2019512311A|2019-05-16|Method and apparatus for determining a criterion of one or more physiological characteristics of a subject
    Marques et al.2011|A real time, wearable ECG and blood pressure monitoring system
    Cho2019|Current status and prospects of health-related sensing technology in wearable devices
    Nagura et al.2018|A practical BCG measuring system with bed sensors and algorithm for heartbeat detection
    CN108430310B|2022-03-01|Method for evaluating the reliability of blood pressure measurements and device for carrying out the method
    US20210169406A1|2021-06-10|Apparatus for determining a stress and/or pain level
    WO2014153665A1|2014-10-02|System and method for monitoring a subject
    Charlton2018|Capitalising on Smart Wearables to Improve Health Monitoring
    US20200315516A1|2020-10-08|Traumatic brain injury diagnostics system and method
    Seok et al.2018|Photoplethysmographic pulse quality assessment methods based on similarity analysis
    CN112272534A|2021-01-26|Method and apparatus for estimating blood pressure surrogate trends
    Ahmed et al.2018|QUANTITATIVE APPROACH TO ASSESSING STRESS IN AUTISM INDIVIDUALS
    Vehkaoja2015|Unobtrusive Monitoring of Heart Rate and Respiration Rate during Sleep
    同族专利:
    公开号 | 公开日
    PL2696754T3|2015-03-31|
    ES2513666T3|2014-10-27|
    RU2013150592A|2015-05-20|
    US20140031704A1|2014-01-30|
    BR112013026063A2|2016-12-27|
    WO2012140537A1|2012-10-18|
    DK2696754T3|2014-12-15|
    CN103596493B|2018-08-07|
    RU2602797C2|2016-11-20|
    CN103596493A|2014-02-19|
    JP2014514080A|2014-06-19|
    JP6053755B2|2016-12-27|
    EP2696754A1|2014-02-19|
    EP2696754B1|2014-09-03|
    US9962104B2|2018-05-08|
    引用文献:
    公开号 | 申请日 | 公开日 | 申请人 | 专利标题
    JPS6220816B2|1981-11-02|1987-05-08|Asahi Medical Co|
    US5064410A|1984-12-12|1991-11-12|Frenkel Richard E|Stress control system and method|
    JPH0471537A|1990-07-11|1992-03-06|Omron Corp|Health level measuring device|
    DE4134960A1|1991-10-23|1993-04-29|Popp Fritz Albert Dr|METHOD FOR A HOLISTIC ANALYSIS OF THE HEALTH CONDITION|
    RU2073484C1|1993-05-17|1997-02-20|Юматов Евгений Антонович|Method and device for psychologic stress estimation|
    AUPN236595A0|1995-04-11|1995-05-11|Rescare Limited|Monitoring of apneic arousals|
    JPH0919420A|1995-07-07|1997-01-21|Omron Corp|Physiological state judging method and physiological state judging device|
    JPH09135826A|1995-11-15|1997-05-27|Omron Corp|Judgement method for concentration degree, eye fatigue judgement method and control method for difficulty|
    NO313534B1|1999-06-01|2002-10-21|Hanne Storm|Apparatus and method of monitoring and method of controlling a warning signal|
    KR100418434B1|2000-01-21|2004-02-11|김현|Peripheral device of computer for automatically recognizing stress and system for determining stress using the same|
    JP2002034933A|2000-07-26|2002-02-05|Nippon Colin Co Ltd|Postoperative recovery state evaluating device|
    KR100580618B1|2002-01-23|2006-05-16|삼성전자주식회사|Apparatus and method for recognizing user emotional status using short-time monitoring of physiological signals|
    US6887239B2|2002-04-17|2005-05-03|Sontra Medical Inc.|Preparation for transmission and reception of electrical signals|
    JP4071537B2|2002-05-08|2008-04-02|富士通株式会社|Critical area calculation method|
    KR20040032451A|2002-10-09|2004-04-17|삼성전자주식회사|Mobile device having health care function and method of health care using the same|
    US20050154264A1|2004-01-08|2005-07-14|International Business Machines Corporation|Personal stress level monitor and systems and methods for using same|
    WO2005067522A2|2004-01-13|2005-07-28|University Of Toledo|Noninvasive birefringence compensated sensing polarimeter|
    KR100646868B1|2004-12-29|2006-11-23|삼성전자주식회사|Home control system and method using information of galvanic skin response and heart rate|
    NO322696B1|2005-02-04|2006-11-27|Hanne Storm|Method and apparatus for monitoring a sedentary patient|
    CN101032395A|2006-03-08|2007-09-12|香港中文大学|Blood pressure measuring method based on characteristic parameter of photoelectricity plethysmography of signal cycle|
    US20100004977A1|2006-09-05|2010-01-07|Innerscope Research Llc|Method and System For Measuring User Experience For Interactive Activities|
    RU2009118381A|2006-10-03|2010-11-10|Андрей Евгеньевич Наздратенко |METHOD FOR DETERMINING A STRESS STATUS OF A HUMAN VOICE AND A DEVICE FOR ITS IMPLEMENTATION|
    WO2008099320A1|2007-02-13|2008-08-21|Koninklijke Philips Electronics N.V.|Computer program product, device and method for measuring the arousal of a user|
    JP4971041B2|2007-06-11|2012-07-11|株式会社デンソー|Blood pressure measuring device, program, and recording medium|
    WO2009036326A1|2007-09-14|2009-03-19|Corventis, Inc.|Adherent athletic monitor|
    US8308562B2|2008-04-29|2012-11-13|Bally Gaming, Inc.|Biofeedback for a gaming device, such as an electronic gaming machine |
    EP2408358A4|2009-03-18|2014-08-20|A M P S Llc|Stress monitor system and method|EP2747638A1|2011-11-22|2014-07-02|Koninklijke Philips N.V.|Mental balance or imbalance estimation system and method|
    US10448874B2|2013-03-12|2019-10-22|Koninklijke Philips N.V.|Visit duration control system and method|
    US10506944B2|2013-03-16|2019-12-17|Empatica Srl|Apparatus for electrodermal activity measurement with current compensation|
    WO2015082231A2|2013-12-05|2015-06-11|Koninklijke Philips N.V.|Processor for processing skin conductance data and device for detecting at least one stage of burnout and/or chronic fatigue syndrome of a living being|
    CN104939824B|2014-03-31|2018-06-19|深圳市宏电技术股份有限公司|A kind of wearable device, detection circuit and method for wearable device|
    EP3154426A1|2014-06-12|2017-04-19|Koninklijke Philips N.V.|Circadian phase detection system|
    US9830781B2|2014-06-13|2017-11-28|Verily Life Sciences Llc|Multipurpose contacts for delivering electro-haptic feedback to a wearer|
    CN104042204B|2014-06-23|2016-09-21|深圳市宏电技术股份有限公司|A kind of resistance to compression based on Wearable, reduced pressure capabilities detection method and device|
    CN107257654B|2015-02-24|2020-08-25|皇家飞利浦有限公司|Device for detecting heart rate and heart rate variability|
    US10368810B2|2015-07-14|2019-08-06|Welch Allyn, Inc.|Method and apparatus for monitoring a functional capacity of an individual|
    US11116397B2|2015-07-14|2021-09-14|Welch Allyn, Inc.|Method and apparatus for managing sensors|
    EP3324836A1|2015-07-17|2018-05-30|Koninklijke Philips N.V.|Devices, systems, and methods for assessing a vessel|
    US10092203B2|2015-08-21|2018-10-09|Verily Life Sciences Llc|Using skin resistance measurements to determine timing of bio-telemetry measurements|
    US10617350B2|2015-09-14|2020-04-14|Welch Allyn, Inc.|Method and apparatus for managing a biological condition|
    US10964421B2|2015-10-22|2021-03-30|Welch Allyn, Inc.|Method and apparatus for delivering a substance to an individual|
    US10918340B2|2015-10-22|2021-02-16|Welch Allyn, Inc.|Method and apparatus for detecting a biological condition|
    JP6707886B2|2016-02-10|2020-06-10|ソニー株式会社|Measuring device and electronic equipment|
    EP3435853B1|2016-04-01|2021-09-01|Nitto Denko Corporation|A method of deriving systolic blood pressure and/or diastolic blood pressure of a subject|
    CN106063709B|2016-05-24|2019-07-05|京东方科技集团股份有限公司|A kind of fatigue detection method and device|
    WO2017202626A1|2016-05-25|2017-11-30|Koninklijke Philips N.V.|Measurement of skin conductance|
    CN106073806B|2016-06-01|2019-01-01|深圳市宏电技术股份有限公司|A kind of fatigue detection method, device and wearable device for wearable device|
    CA3029998A1|2016-07-08|2018-01-11|Ontolead, Inc.|Relationship analysis utilizing biofeedback information|
    US10973416B2|2016-08-02|2021-04-13|Welch Allyn, Inc.|Method and apparatus for monitoring biological conditions|
    US10791994B2|2016-08-04|2020-10-06|Welch Allyn, Inc.|Method and apparatus for mitigating behavior adverse to a biological condition|
    FR3057152B1|2016-10-07|2018-12-07|Commissariat A L'energie Atomique Et Aux Energies Alternatives|METHOD AND SYSTEM FOR MONITORING STRESS OF A USER|
    US20180249939A1|2017-03-06|2018-09-06|Intel Corporation|Stress detection and management system|
    CN107292244A|2017-06-01|2017-10-24|深圳欧德蒙科技有限公司|A kind of stress recognition methods, smart machine and computer-readable recording medium|
    DE102018000883A1|2018-02-03|2019-08-08|Louis Samuel Seidel|Biofeedback system, its use and methods for the prevention, diagnosis and therapy of stress and cognitive decline due to entertainment, communication and data processing electronic VDUs|
    US10898119B2|2018-05-24|2021-01-26|International Business Machines Corporation|Coordinating activities responsive to physiologic signals|
    EP3594963A1|2018-07-11|2020-01-15|Koninklijke Philips N.V.|Device, system and method for determining a stress level of a user|
    RU2699929C1|2018-12-18|2019-09-11|Дмитрий Игоревич Ростковский|Method of measuring stress level|
    RU2736397C1|2020-02-19|2020-11-16|Общество с ограниченной ответственностью «Лаборатория знаний»|System and method for determining state of stress based on biometric eeg signal and electrodermal activity|
    法律状态:
    2018-12-18| B06F| Objections, documents and/or translations needed after an examination request according [chapter 6.6 patent gazette]|
    2019-12-24| B06U| Preliminary requirement: requests with searches performed by other patent offices: procedure suspended [chapter 6.21 patent gazette]|
    2021-06-15| B09A| Decision: intention to grant [chapter 9.1 patent gazette]|
    2021-08-31| B16A| Patent or certificate of addition of invention granted [chapter 16.1 patent gazette]|Free format text: PRAZO DE VALIDADE: 20 (VINTE) ANOS CONTADOS A PARTIR DE 02/04/2012, OBSERVADAS AS CONDICOES LEGAIS. |
    优先权:
    申请号 | 申请日 | 专利标题
    EP11162418.5|2011-04-14|
    EP11162418|2011-04-14|
    PCT/IB2012/051592|WO2012140537A1|2011-04-14|2012-04-02|Stress-measuring device and method|
    [返回顶部]