Method and system for calibrating a human condition sensor - Patents.com

Abstract

A method and system for calibrating a human condition sensor is provided, the method including: detecting a plurality of output values ​​of the sensor, the output values ​​indicative of a mental and / or physiological state of a user; determining a boundary output value based on the detected plurality of output values, a predetermined portion of the detected output values ​​being higher or lower than the boundary output value; and determining a threshold output value of the sensor based on the boundary output value.

Description

[Technical field]

[0001] The present disclosure relates to human state sensors, such as mental and / or physiological state sensors, and calibration thereof, and in particular to personalizing human state sensors. [Background technology]

[0002] Human mental, physiological or psychological state detection is a rapidly developing area, especially in the automotive domain. Better state detection can, for example, improve the driving safety and comfort of the vehicle user, and can also exploit well-being and health-related applications. Moreover, it can help explore the vehicle as yet another living space, especially with regard to health checks.

[0003] A person's mental, physiological or psychological state is highly personalized. Each person has a different background and is used to managing problems with different efficiency. Environmental conditions affect different people differently. What is stressful for one user may be an easy task for another, and what requires significant cognitive effort for one user may be a routine task for another.

[0004] Thus, improved and / or more reliable sensors or sensing methods that take into account personalized mental, physiological, or psychological state indicators or symptoms are desirable. Summary of the Invention [Means for solving the problem]

[0005] According to one of many embodiments, there is provided a method of calibrating a mental and / or physiological condition sensor, the method including: detecting a plurality of output values ​​of the sensor, the output values ​​indicative of a mental and / or physiological condition of a user; determining a boundary output value based on the detected plurality of output values, a predetermined portion of the detected output values ​​being higher or lower than the boundary output value; and determining a threshold output value of the sensor based on the boundary output value.

[0006] For example, the personalized threshold output value may be determined as a boundary output value, or may be determined as a boundary output value plus a (predetermined and / or dynamic) offset value or offset value range. In other words, a guard band may be provided around the boundary value. Thus, the threshold output value may represent a personalized threshold output value. The threshold output value may be (usable) to determine a threshold (e.g., severe) mental and / or physiological state of the user. In other words, the method may further include determining the mental and / or physiological state of the user based on the determined threshold output value. Thereby, the method is extended to a method of determining a human state of the user via a mental and / or physiological state sensor.

[0007] The present invention is based on the discovery that human states, for example mental states, which may also be referred to as psychological states, and / or physiological states, which may also be referred to as (physical) health states, may surface differently for different people. In addition, each person may react differently to different situations. By taking into account previously detected or historical sensor data of a particular person or user, a human state (mental and / or physiological state) sensor can be specifically calibrated, i.e. personalized for a particular user. In addition, even during the use of the sensor, the defined calibration method can be continuously performed, thereby continuously controlled and improved. In this way, the relevance of the sensor is increased.

[0008] The sensor may be installed in the vehicle, i.e. the user may be the driver of the vehicle.

[0009] According to an embodiment, the method further includes determining a frequency of detection for each of the detected plurality of output values ​​and determining a boundary threshold output value based on the determined frequency of detection.

[0010] The frequency of detection may represent the frequency of a detection function, such as a value density function or a value histogram. By considering a limited or bounded area of ​​historical sensor data via a boundary output value above (or below) a predefined portion or percentage, such as 1% or 5% of all detected sensor output values, as the boundary output value, the calibration method takes into account individual variations in detectable human condition indicators or symptoms. Thus, a simple and robust method of calibrating or personalizing a sensor is provided, thereby further enhancing the validity of the sensor.

[0011] According to an embodiment, the method further includes determining an integral distribution of the detected output values ​​over a range of output values ​​based on the determined frequency of detection, and determining a boundary output value based on the determined integral distribution.

[0012] The output value range may be a detected output value range, an estimated output value range, a predicted output value range, or a predetermined output value range. The integral distribution may be an integral (function) of the frequency of detections for the detected output values. In other words, the integral distribution may be an integral density function or an integral value histogram. The integral distribution function may indicate, for a particular detected output data value, the proportion or fraction of determined output data values ​​that are greater or less than a particular determined output data value. Thereby, an effective, simple, and reliable method of determining boundary outputs is provided.

[0013] According to an embodiment, the integral distribution of the integral distribution function is [ka] where IH(i) is the integral distribution function value for detected output value i, H(j) is the determined frequency of detection for detected output data value j, and N is the total number of detected output values. Alternatively, the integral distribution function can be expressed as: [ka] where IH(i) in both discrete and continuous forms indicates the frequency of detection for output values ​​greater than i. Similarly, discrete and continuous integral distribution function values ​​IH(i) may indicate the frequency of detection for output values ​​less than i, thereby providing an effective, simple, and reliable method of determining the integral distribution.

[0014] According to an embodiment, the output value is an output value range of output values, in particular an output value range of a predetermined width.

[0015] The multiple value ranges may be within and / or extend across the (total) output value range of the sensor. In other words, each output value may be assigned to a corresponding value range. In that way, a subgroup of output values ​​may be considered as one output value or one group of output values. Thereby, the processing power or time required to perform the method is reduced. In other words, the efficiency of the method is increased.

[0016] According to an embodiment, the multiple value ranges have different widths, in particular the multiple value ranges decrease in size for lower or higher output values.

[0017] For example, the multiple value ranges are reduced in size as they become closer to the boundary value or estimated boundary value, thus achieving better resolution within the higher (or lower) output value area, particularly within areas relatively close to, e.g., adjacent to, the boundary output value.

[0018] According to an embodiment, the method further comprises determining the number of value ranges based on a predetermined accuracy requirement of the threshold, in particular based on a predetermined portion of the detected output values ​​that are higher or lower than the boundary output value.

[0019] For example, if the total number of value ranges is 10, then the total range of detected (or detectable) output values ​​is divided by 10, and the value range closest to the extreme (i.e., highest or lowest) includes 4% of the detected value range, but the boundary output value is required to be higher (or lower) than 99% of the detected output values, and the number of value ranges is increased, thereby taking into account accuracy requirements and reducing the processing power or time required to perform the method.

[0020] According to an embodiment, the method further includes determining whether the detected plurality of output values ​​satisfy a first threshold number of output values, in particular whether they are within a total output value range of the sensor and / or whether they are within one or more output value ranges, more particularly whether they are above or below a determined boundary output value, and if the first threshold number is satisfied, determining a threshold output value based on the boundary output values.

[0021] According to an embodiment, the method further includes detecting a plurality of output values ​​of the sensor within a predetermined time interval, and determining a threshold output value based on the boundary output value after the predetermined time interval has expired.

[0022] In that way, it can be ensured that detected historical data provides a meaningful basis for determining personalized threshold output values.

[0023] According to an embodiment, the method further includes determining whether a second threshold number of output values ​​is detected within one or more specific, in particular different, sensor environments, user scenarios, and / or time frames, and if the second threshold number is met, determining a threshold output value based on the boundary output value.

[0024] In this way, it is ensured that the detected historical data is detected with respect to a typical situation and / or user's experience, and the sensor or sensor system then operates. For example, the environment, user scenario, and / or time frame may include one or more of the user's regular commute (e.g., between work and home), typical routes, (e.g., types of routes such as highways and urban areas), typical dates and times, and / or cognitive load scenarios such as the user making phone calls, cognitive distractions or daydreaming while driving (e.g., heavy internal cognition caused by thinking about a problem), etc. Thus, a useful, i.e., realistic, criterion for determining the threshold output value is provided.

[0025] According to an embodiment, the method further includes defining a threshold output value based on a predetermined boundary output value if the first threshold and / or the second threshold are not met and / or the time interval has not expired.

[0026] Thereby, the calibration method allows interpretation of sensor output values ​​even when sufficient historical data has not yet been detected.

[0027] According to another embodiment, there is provided a device including a processor configured to perform the method described above. The device may be arranged in or provided with a vehicle.

[0028] According to another embodiment, there is provided a computer program comprising instructions which, when executed by a computer, cause the computer to carry out the method described above. The computer may be arranged in or provided with a vehicle.

[0029] According to another embodiment, a non-transitory computer readable storage medium is provided that contains instructions that, when executed by a computer, cause the computer to perform the method described above.

[0030] Features, objects, and advantages of the present disclosure will become apparent from the detailed description of non-limiting embodiments set forth below when taken in conjunction with the drawings, in which like reference characters refer to like elements. [Brief description of the drawings]

[0031] [Figure 1] 1 shows a flowchart of a method for calibrating a mental and / or physiological condition sensor. [Diagram 2] 1 shows a flow chart of a method for improving the validity of a calibration method. [Diagram 3] 1 illustrates a data processing device including a sensor, a memory, and a processor. [Figure 4] 4 shows exemplary output values ​​of the sensor. [Diagram 5] 13 illustrates a frequency of detection histogram for example output values. [Figure 6] 13 illustrates a first frequency of detection histogram for all exemplary output values ​​within an exemplary total output value range. [Figure 7] 1 illustrates a first exemplary integral distribution histogram of a first frequency of detection histograms. [Figure 8A] 11 illustrates a second frequency of detection histogram having output value ranges of different widths for all example output values ​​within an example total output value range. [Figure 8B] 13 illustrates a second example integral distribution histogram of a second frequency of detection histograms having output value ranges of different widths. [Figure 9] 13 shows exemplary output values ​​for a sensor having a determined 5% critical output value. [Figure 10] 13 illustrates a third exemplary integral distribution histogram of a second frequency of detection histograms. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0032] 1 shows a flow chart of a method 100 for calibrating mental and / or physiological condition sensors, also referred to as human condition sensors. The described method steps may be performed in different orders in any suitable manner.

[0033] In step 110, a plurality of output values ​​of the sensor are detected. The human condition sensor or detector may have consecutive outputs within a time interval. The output values ​​of the sensor indicate the human condition of the user, i.e., the mental and / or physiological condition of the user. More specifically, the output values ​​indicate the intensity of the detected condition depending on the quantity of the output values ​​or corresponding to the output values. The output values ​​extend over a certain output value range. In a preferred embodiment, the plurality of output values ​​includes more than two different output values. As an example, the user's heart rate or heart rate pattern may be detected.

[0034] In step 120, the number of output value ranges within the total value range of the sensor or the total value range of the detected output values ​​is determined. In other words, the output values ​​detected in step 110 are grouped into subranges. Additionally or alternatively, the detectable output values ​​(i.e., the output value range of the sensor) are divided into subranges. For example, the range [0...1] is divided into three subranges [0...0.33], (0.33...0.66], and (0.66...1]. In yet another way, the detected output value within the subrange is represented by one of the values ​​within the subrange, e.g., the highest output value, the lowest output value, or the average output value within the subrange. The subranges within the output value range may have equal widths or sizes. Alternatively, the subranges may have different sizes, in particular smaller or larger for higher or lower subranges.

[0035] With reference to FIG. 4, exemplary output values ​​of the sensor are presented over time. It is illustrated that detector output values ​​of 0.4 and approximately 0.4 are grouped together into a subrange of output values ​​of 0.4. In other words, values ​​that are close to 0.4 are rounded to 0.4. In this example, all output values ​​detected three times within the time interval shown are rounded to three separate values ​​of 0.4 each. In other words, output values ​​that are close to 0.4 (including output values ​​at 0.4) that are detected one at a time immediately after each other or consecutively are considered as one output value of 0.4.

[0036] 1, in step 130, the frequency of detection of the detected output values ​​is determined. In other words, it is determined how many times each output value is detected within a (predetermined) time interval.

[0037] In figures 4 and 5 the frequency of detection histograms for the output value range 0.4 (figure 5) and for all output value ranges within the total output value range (figure 6) are shown. It is illustrated that within the illustrated time interval the output value or subrange 0.4 was detected three times. As illustrated in figure 6, the frequency of detection is determined for each subrange within the range of detected output values. In the present example, seven equally spaced subranges have been determined for that purpose. As illustrated in figure 8A, the subranges may have different sizes.

[0038] 1, in step 140, an integral distribution function of the detected output values ​​is determined. The integral distribution function may be an integral value histogram.

[0039] Figure 7 shows an example integral distribution histogram determined based on a previously determined frequency of detection of sensor output values ​​as illustrated in Figure 6. Figure 8B shows an example histogram determined based on a previously determined frequency of detection of sensor output values ​​as illustrated in Figure 8A.

[0040] As shown, an integral distribution function can be described as indicating the number, portion, or percentage of other output values ​​below or above a particular output value for a particular output value or subrange of output values. For example, the illustrated histogram shows values ​​distributed from 0 to 1. Considering the leftmost subrange, 100% of the output values ​​are greater than an output value of 0. Considering the rightmost subrange, 0% of the output values ​​are greater than an output value of 1. Stated differently, the integral distribution indicates the total over all frequencies of detection of output values ​​above or below (and including) a particular output value or subrange of output values, preferably divided by the total number of detected output values ​​for a particular output value or subrange of output values. As a formula, such an integral distribution can be expressed as: [ka] where IH(i) is the integral distribution function value for the detected output value or subrange i, H(j) is the determined frequency of detection for the detected output data value or subrange j, N is the total number of detected output values, and M is the highest or lowest output data value.

[0041] Referring again to FIG. 1, in step 150, a boundary output value is determined. The boundary output value may be determined based on the determined integral distribution, where a predetermined portion of the detected output values ​​are higher or lower than the boundary output value. For example, the boundary output value may be determined such that 5% of the detected output values ​​are higher than the boundary output value. More specifically, a particular value of the integral distribution that is associated with a 5% percentage of the detected output values ​​higher or lower than a particular value, or that is less than 5% of the detected output values, may be selected as the boundary output value.

[0042] If none of the subranges of the integral distribution are associated with a predetermined or desired portion or percentage of the detected output value that is higher or lower than the subranges, the method may return to step 120, where a different, and in particular a greater number, of output value ranges are determined. As such, the number of value ranges may be based on the accuracy requirements of the threshold.

[0043] 9 and 10, it is shown that in this embodiment, the boundary output value may be set to 0.86. The integral histogram shown in Fig. 10 shows a sub-range from 0.86 to 1, e.g., [0.86,1) or [0.86,1] or (0.86,1] or (0.86,1), that contains 5% of all detected output values. In other words, 95% of all detected output values ​​are below the boundary output value of 0.86.

[0044] 1, in step 160, a threshold output value for the sensor is determined based on the previously determined boundary output value. The threshold output value may be set to, i.e., equal to, the boundary output value of 0.86. Alternatively, the threshold output value may include an offset to the boundary output value, which may be predetermined and fixed for each boundary output value, or may depend on the (absolute) boundary output value or a quantity thereof.

[0045] Based on the threshold output value, a deterministic output value above the threshold output value can be detected. In that way, a deterministic mental or physiological state of the user can be detected. Thus, normal or inconclusive variations in the sensor output value can be ignored and only outliers in the output value can be determined to be deterministic. In that way, both the user behavior or characteristics and the sensor behavior or characteristics are taken into account when interpreting the sensor output value.

[0046] 2, a further step 200 of the exemplary method 100 of FIG 1 is shown. The further step 200 may also be referred to as a method 200 for improving the validity of the calibration method 100 of FIG 1. The method 200 may be included in the method 100 during any method steps 110-160 of the method 100, particularly after step 110.

[0047] Method 100 begins with method step 210, where it is determined whether the output values ​​detected in step 110 of method 100 satisfy a threshold value. The threshold value may be a first threshold number of output values. The first threshold number of output values ​​may be a total number within a full range of detected or detectable output values, or may be a total number within a subrange of detected or detectable output values, such as a highest or lowest subrange, or a subrange higher or lower than a determined, predicted, or estimated boundary output value. In other words, it is determined in step 210 whether enough output values ​​have been detected to determine a valid or appropriate threshold output value.

[0048] Alternatively or additionally, the threshold value of step 210 may be a second threshold number of output values ​​detected in different sensor environments, different user scenarios, and / or different time frames or intervals during a (24-hour) day. For example, the second threshold number may indicate a minimum number of output values ​​to be detected in a vehicle (i) during rush hour, (ii) during phone calls made by the user, (iii) during weekdays or weekends, (iv) during the user's commute to or from work, (v) on a particular route, and / or (vi) during a particular night or day time. In other words, it is ensured that sufficient output values ​​are detected during different mental and / or physiological states of the user, in particular stress states, to obtain a representative set of historical output values ​​based on which threshold output value is determined.

[0049] Alternatively or additionally, the threshold of step 210 may be a time interval during which multiple output values ​​are detected. In other words, it is determined whether the output values ​​of the sensor have been detected during a particular period of time, and in particular during a period of time that is long enough to allow for detection of a significant number of output values.

[0050] If, in step 210, it is determined that the threshold is met (yes branch), then a threshold output value is determined based on the determined boundary output value as described above with respect to FIG. 1. If, in step 210, it is determined that the threshold is not (yet) met (no branch), then a threshold output value is determined based on a pre-defined boundary output value. Alternatively, the boundary output value may be determined based on pre-defined or pre-calculated reference data. Alternatively, the threshold output value may be set to a pre-defined, predicted or estimated threshold output value.

[0051] 3 illustrates a data processing device 300, e.g., a computer. The data processing device 300 includes a processor 310 and one or more human condition sensors 320 communicatively coupled to the processor 310. The processor 310, the sensor 320, or the data processing device 300 may be arranged on or provided in a vehicle. The processor 310 is configured to use output values ​​of the sensor 320 to perform one or more of the method steps of the methods 100 and 200 described with reference to FIGS. 1 and 2.

[0052] The data processing device 300 further includes a memory 330 communicatively coupled to at least one of the processor 310 and the sensor(s) 320. The memory 330 is, in particular, a non-transitory, computer-readable storage medium. The memory 330 includes, i.e. stores, instructions that, when executed by the data processing device 300, in particular by the processor 310, cause the data processing device 300 to perform one or more of the method steps of the methods 100 and 200 described with reference to Figures 1 and 2. In other words, the memory 330 comprises, i.e. stores, a computer program that includes instructions that, when executed by the data processing device 300, in particular by the processor 310, cause the data processing device 300 to perform one or more of the method steps of the methods 100 and 200 described with reference to Figures 1 and 2. [Explanation of symbols]

[0053] 100 Method for calibrating mental and / or physiological state sensors 100~160 Method 100 Method Steps 200 How to improve the validity of calibration method 100 210~230 Method 100 method steps 300 Data Processing Devices 310 Processor 320 Sensors 330 Memory

Claims

1. 1. A method for calibrating a mental and / or physiological condition sensor, comprising: detecting a plurality of output values ​​of the sensor, the output values ​​being indicative of a mental and / or physiological state of a user; determining a boundary output value based on the detected output values, a predetermined portion of the detected output values ​​being higher or lower than the boundary output value; determining a threshold output value for the sensor based on the boundary output value; The method comprising:

2. determining a frequency of detection for each of the detected plurality of output values; determining the boundary threshold output value based on the determined frequency of detection; The method of claim 1 further comprising:

3. determining an integral distribution of the detected output values ​​over a range of detected output values ​​based on the determined frequency of detection; determining the boundary output value based on the determined integral distribution; and The method of claim 2 further comprising:

4. The integral distribution of the integral distribution function is [0010] or [0025] where IH(i) is the integral distribution function value for detected output value i, H(j) is the determined frequency of detection for detected output data value j, and N is the total number of detected output values. The method according to claim 3.

5. 10. The method according to any of the preceding claims, wherein the output value is an output value range of output values, in particular an output value range of a predetermined width.

6. The method of claim 5 , wherein the ranges of values ​​have different widths, in particular the ranges of values ​​decrease in size for lower or higher output values.

7. 7. The method of claim 5 or 6, further comprising determining a number of value ranges based on a predetermined accuracy requirement of the threshold, in particular based on the predetermined portion of the detected output values ​​that are higher or lower than the boundary output value.

8. determining whether the detected plurality of output values ​​meets a first threshold number of output values, in particular whether it is within a total output value range of the sensor and / or whether it is within one or more output value ranges, more particularly whether it is above or below the determined boundary output value; determining the threshold output value based on the boundary output value if the first threshold number is met; 13. The method of any preceding claim, further comprising:

9. detecting the plurality of output values ​​of the sensor within a predetermined time interval; determining the threshold output value based on the boundary output value after the predetermined time interval has expired; 13. The method of any preceding claim, further comprising:

10. determining whether a second threshold number of output values ​​is detected within one or more particular, particularly distinct, sensor environments, user scenarios, and / or time frames; determining the threshold output value based on the boundary output value if the second threshold number is met; 13. The method of any preceding claim, further comprising:

11. The method according to any one of claims 8 to 10, further comprising: defining the threshold output value based on a predetermined boundary output value if the first threshold and / or the second threshold are not met and / or if the time interval has not expired.

12. A device comprising a processor configured to carry out the method according to any one of claims 1 to 11.

13. A computer program comprising instructions which, when said program is executed by a computer, cause said computer to carry out a method according to any of claims 1 to 11.

14. A non-transitory computer readable storage medium comprising instructions which, when executed by a computer, cause the computer to perform a method according to any of claims 1 to 11.

Images