Method for detecting whether there is a person on the sensor based on cardiac shock signal

Abstract

The present invention discloses a method for detecting whether there is a person on a sensor based on a cardiac impact signal, and the method comprises the steps of: collecting an original cardiac impact signal; obtaining a high-frequency signal according to the original signal; calculating the amplitude ratio between the original signal and the high-frequency signal; if all amplitude ratios within a specified time are greater than a threshold value of a person's amplitude, it is determined that there is a person on the sensor, and if all amplitude ratios within a specified time are less than the threshold value of a person's amplitude, it is determined that there is no person on the sensor; wherein, if the amplitude ratios are all less than a first specified value, and the first coefficient of variation is less than a second specified value, the threshold value of a person's amplitude is refreshed. By collecting the original time-series signal of the cardiac impact signal and dynamically refreshing the judgment threshold, the robustness of the algorithm is increased, the sensor is effectively suppressed from being easily interfered with by high-frequency interference from other devices, the problem of the signal amplitude and the signal standard deviation being affected by it is solved, and the accuracy is improved.

Description

Technical Field

[0001] The present invention relates to the field of sensor detection technology, and in particular to a method and system for detecting whether there is a person on a sensor based on a cardiac shock signal. Background Art

[0002] As a physiological signal that reflects the mechanical activities of the heart, breathing, and body movement, the cardiac signal has a signal frequency of 0.05 to 20 Hz. The cardiac signal can be detected by a variety of different sensors, including piezoelectric sensors, fiber optic sensors, and radar sensors. During the acquisition process of the cardiac signal, it contains a lot of information, including breathing signals, heartbeat signals, body movement signals, and high-frequency interference generated by electronic devices.

[0003] In the actual use of piezoelectric sensors, fiber optic sensors, and radar sensors to detect human body signals, how to determine whether there is someone on the sensor is the prerequisite for detecting human body signals. The common methods currently used are to set the threshold by signal amplitude and signal standard deviation. However, since common usage scenarios such as homes and hospitals usually have high-frequency interference from other devices, when high-frequency interference is serious, the signal amplitude and signal standard deviation will be affected, causing the algorithm to make mistakes. At the same time, even if there is no influence of high-frequency interference, different sleeping positions, sitting positions, and different sensor placement positions will have different signal amplitudes and signal standard deviations, and the possibility of fixed threshold errors is also relatively high. Summary of the invention

[0004] In the existing technology of using sensors to determine whether there is someone on the bed, the sensors are easily affected by high-frequency interference from other devices, causing the signal amplitude and signal standard deviation to be affected, thereby causing the method to make errors in judgment.

[0005] To solve the above problems, a method for detecting whether there is a person on the sensor based on the cardiac shock signal is proposed. By collecting the original time / frequency domain signals of the cardiac shock signal and dynamically refreshing the judgment threshold, the robustness of the algorithm is increased, and the sensor is effectively suppressed from being easily affected by high-frequency interference from other devices. The problem that the signal amplitude and signal standard deviation will be affected by it is solved, and the accuracy is improved.

[0006] In a first aspect, a method for detecting whether a person is on a sensor based on a heartbeat signal comprises:

[0007] Step 100, collecting original heartbeat signals;

[0008] Step 200: obtaining a high-frequency signal according to the original signal;

[0009] Step 300, calculating the amplitude ratio between the original signal and the high frequency signal;

[0010] Step 400: If all the amplitude ratios within the specified time are greater than the human amplitude threshold, it is determined that there is a person on the sensor; if all the amplitude ratios within the specified time are less than the human amplitude threshold, it is determined that there is no person on the sensor;

[0011] Wherein, the step 400 includes:

[0012] Step 410: If the amplitude ratios are all smaller than the first specified value, and the first coefficient of variation is smaller than the second specified value, the human amplitude threshold is refreshed.

[0013] In combination with the method described in the first aspect, in a first possible implementation manner, step 200 includes:

[0014] Step 210, filtering the original signal of the cardiac impulse signal within a specified time by using finite impulse response filtering, zero-phase shift infinite impulse response filtering, or wavelet filter filtering;

[0015] Step 220: retain the original signal with a frequency value above a specified value within a specified time to obtain a high-frequency signal.

[0016] In combination with the first or second possible implementation manner of the first aspect, in a third possible implementation manner, step 410 includes:

[0017] Step 411, obtaining a first average value of all amplitude ratios that are less than a first specified value;

[0018] Step 412: Multiply the first average value by the first adjustment coefficient to obtain a refreshed human amplitude threshold value;

[0019] Step 413: Determine whether there is a person on the sensor according to the refreshed human amplitude threshold:

[0020] If the sensor is determined to be in an unmanned state, the first adjustment coefficient is used to continuously refresh the human amplitude threshold.

[0021] In combination with the third possible implementation of the first aspect, in a fourth possible implementation, the adjustable range of the human amplitude is 1.5-4.5.

[0022] In a second aspect, a method for detecting whether there is a person on a sensor based on a heartbeat signal comprises:

[0023] Step 500, collecting original heartbeat signals;

[0024] Step 600, obtaining the slope value of the discrete power spectrum fitting straight line within a unit time according to the original signal;

[0025] Step 700: Determine whether there is a person on the sensor according to the discrete power spectrum slope value and the person slope threshold:

[0026] If all the discrete power spectrum slope values ​​within the specified time are greater than the slope threshold for someone, it is determined that there is someone on the sensor; if all the discrete power spectrum slope values ​​within the specified time are less than the slope threshold for someone, it is determined that there is no one on the sensor;

[0027] Wherein, the step 700 includes:

[0028] Step 710: If the discrete power spectrum slope values ​​are all smaller than the third specified value, and the second coefficient of variation is smaller than the fourth specified value, the presence slope threshold is refreshed.

[0029] In combination with the method described in the second aspect, in a first possible implementation manner, step 600 includes:

[0030] Step 610: Calculate the power spectrum of the original signal per unit time;

[0031] Step 620: retain the original signal power spectrum that is less than the second frequency value.

[0032] In combination with the first possible implementation of the second aspect, in a second possible implementation, step 600 further includes:

[0033] Step 630, fitting the original signal power spectrum with a straight line;

[0034] Step 640: Calculate the slope value of the straight line fitted by all discrete power spectra within a specified time.

[0035] In combination with the first or second possible implementation manner of the second aspect, in a third possible implementation manner, step 710 includes:

[0036] Step 711, obtaining a second average value of all discrete power spectrum slope values ​​greater than a third specified value;

[0037] Step 712: Multiply the second average value by the second adjustment coefficient to obtain a refreshed occupancy slope threshold;

[0038] Step 713: Determine whether there is someone on the sensor according to the refreshed occupancy slope threshold:

[0039] If the sensor is determined to be in an unmanned state, the second adjustment coefficient is used to continuously refresh the manned slope threshold.

[0040] In combination with the method described in the second aspect, in a fourth possible implementation manner, the occupant slope threshold may be adjusted in the range of -0.75 to -3.

[0041] The method for detecting whether there is a person on the sensor based on the cardiac shock signal described in the present invention is implemented, by collecting the time series / frequency domain original signal of the cardiac shock signal and dynamically refreshing the judgment threshold, the robustness of the algorithm is increased, and the sensor is effectively suppressed from being susceptible to high-frequency interference from other devices, solving the problem that the signal amplitude and signal standard deviation will be affected by it, and improving the accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0043] Figure 1 This is a first schematic diagram of a method for detecting whether there is a person on a sensor based on a heart ballistic signal in the present invention;

[0044] Figure 2 It is a second schematic diagram of a method for detecting whether there is a person on a sensor based on a heart ballistic signal in the present invention;

[0045] Figure 3 This is a third schematic diagram of a method for detecting whether there is a person on a sensor based on a heart ballistic signal in the present invention;

[0046] Figure 4 This is a fourth schematic diagram of a method for detecting whether there is a person on a sensor based on a heartbeat signal in the present invention;

[0047] Figure 5 This is a fifth schematic diagram of a method for detecting whether there is a person on a sensor based on a heart ballistic signal in the present invention;

[0048] Figure 6 This is a sixth schematic diagram of a method for detecting whether there is a person on a sensor based on a heart ballistic signal in the present invention;

[0049] Figure 7 This is a seventh schematic diagram of a method for detecting whether there is a person on a sensor based on a heartbeat signal in the present invention;

[0050] Figure 8 This is an eighth schematic diagram of a method for detecting whether there is a person on a sensor based on a heart ballistic signal in the present invention; DETAILED DESCRIPTION

[0051] The following will be combined with the accompanying drawings in the invention to clearly and completely describe the technical solutions in the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in the present invention, other embodiments obtained by ordinary technicians in this field without creative work are all within the scope of protection of the present invention.

[0052] In the existing technology of using sensors to determine whether there is someone on the bed, the sensors are easily affected by high-frequency interference from other devices, causing the signal amplitude and signal standard deviation to be affected, thereby causing the method to make errors in judgment.

[0053] In view of the above problems, a method and system for detecting whether there is a person on a sensor based on a heartbeat signal is proposed.

[0054] The first method

[0055] Example 1

[0056] A method for detecting whether there is a person on the sensor based on the heartbeat signal, such as Figure 1 , Figure 1 This is a first schematic diagram of a method for detecting whether there is a person on a sensor based on a heartbeat signal in the present invention, comprising:

[0057] Step 100, collecting the original cardiac impact signal; Step 200, obtaining the high-frequency signal according to the original signal; Step 300, calculating the amplitude ratio between the original signal and the high-frequency signal; Step 400, if all amplitude ratios within the specified time are greater than the amplitude threshold of someone, it is determined that there is someone on the sensor, and if all amplitude ratios within the specified time are less than the amplitude threshold of someone, it is determined that there is no one on the sensor; wherein, step 400 includes: Step 410, if the amplitude ratios are all less than the first specified value, and the first coefficient of variation is less than the second specified value, the amplitude threshold of someone is refreshed. By collecting the original time series signal of the cardiac impact signal and dynamically refreshing the judgment threshold, the robustness of the algorithm is increased, the sensor is effectively suppressed from being easily interfered with by high-frequency interference of other devices, the problem of causing the signal amplitude and signal standard deviation to be affected by it is solved, and the accuracy is improved.

[0058] In this embodiment, a signal acquisition unit may be used to acquire a cardiac ballistic signal to obtain an original cardiac ballistic signal data sequence, that is, an original signal.

[0059] The high-frequency signal can be filtered by a signal filtering unit on the collected cardiac ballistometry signal. Preferably, the original signal above 15 Hz is retained, that is, the original signal is high-pass filtered.

[0060] Preferably, if Figure 2 , Figure 2This is the second schematic diagram of a method for detecting whether there is a person on a sensor based on a cardiac shock signal in the present invention; step 200 includes: step 210, using finite impulse response filtering or zero-phase shift infinite impulse response filtering or wavelet filter filtering to filter the original signal of the cardiac shock signal within a specified time; step 220, retaining the original signal above a specified frequency value within the specified time to obtain a high-frequency signal.

[0061] Finite impulse response filtering can be used for high-pass filtering to obtain high-frequency signals.

[0062] In this embodiment, preferably, 10 seconds of original signal is collected, and 10 seconds of high-frequency signal is also acquired, and the original signal and the high-frequency signal are time-aligned and equal.

[0063] When performing amplitude calculation, preferably, 10 discrete amplitudes of the original signal of 10 seconds and 10 discrete amplitudes of the high-frequency signal can be selected, and the amplitude ratio between the original signal and the high-frequency signal can be compared with the human amplitude threshold to determine whether there is a person on the sensor.

[0064] It is worth noting that the amplitude of 10 every second can be calculated, and the discrete amplitude in other time periods can also be calculated. For example, 1 second is calculated in units of 100 milliseconds, which is not limited here.

[0065] The human amplitude threshold is the human threshold for the signal amplitude. When making a judgment, if all amplitude ratios of 10 seconds are greater than the human amplitude threshold, it is determined that there is a person on the sensor. If all amplitude ratios of 10 seconds are less than the human amplitude threshold, it is determined that there is no person on the sensor.

[0066] However, during the sensor detection process, it is easy to be interfered by high-frequency interference from other devices in the environment, which often leads to misjudgment. In order to solve this problem, the human amplitude threshold needs to be continuously updated.

[0067] Preferably, if Figure 4 , Figure 4 This is the fourth schematic diagram of a method for detecting whether there is a person on a sensor based on a cardiac shock signal in the present invention; step 410 includes: step 411, obtaining a first average value of all amplitude ratios less than a first specified value; step 412, multiplying the first average value by the first adjustment coefficient to obtain a refreshed amplitude threshold for someone on the sensor; step 413, judging whether there is a person on the sensor based on the refreshed amplitude threshold for someone on the sensor: if the sensor is determined to be in an unmanned state, the amplitude threshold for someone on the sensor is continuously refreshed using the first adjustment coefficient.

[0068] When updating the human amplitude, specifically, it can be assumed that the human amplitude threshold is 2. If there are 10 discrete amplitude ratios [2, 2.5], and the coefficient of variation of these 10 amplitude ratios is less than the second specified value, the second specified value is preferably 0.2, then the human amplitude threshold needs to be adjusted using the first adjustment coefficient. Preferably, the first adjustment coefficient is 1.5.

[0069] When making adjustments, first calculate the first average value of all amplitude ratios in the interval [2,2.5], multiply the first average value by the first adjustment coefficient, and use the result as the refreshed occupancy amplitude threshold; determine whether there is someone on the sensor based on the refreshed occupancy amplitude threshold. If the sensor is determined to be in an unmanned state, continuously refresh the occupancy amplitude threshold using the first adjustment coefficient. Preferably, the occupancy amplitude can be adjusted in the range of 1.5-4.5.

[0070] Example 2

[0071] Different from Example 1, in this embodiment, Figure 3 , Figure 3 This is the third schematic diagram of a method for detecting whether there is a person on a sensor based on a cardiac shock signal in the present invention; step 200 includes: step 230, using a zero-phase-shift infinite impulse response to filter the original signal of the cardiac shock signal within a specified time; step 240, retaining the original signal above the specified frequency value within the time period to obtain a high-frequency signal.

[0072] In this embodiment, a zero-phase-shift infinite impulse response may be used to perform high-pass filtering to obtain a high-frequency signal.

[0073] Second method implementation

[0074] Example 1

[0075] A method for detecting whether there is a person on the sensor based on the heartbeat signal, such as Figure 5 , Figure 5The fifth schematic diagram of a method for detecting whether there is a person on a sensor based on a cardiac impact signal in the present invention comprises: step 500, collecting the cardiac impact original signal; step 600, obtaining the slope value of the discrete power spectrum after fitting the straight line within a unit time according to the original signal; step 700, judging whether there is a person on the sensor according to the discrete power spectrum slope value and the slope threshold of the person: if all the discrete power spectrum slope values ​​within the specified time are greater than the slope threshold of the person, it is judged that there is a person on the sensor, and if all the discrete power spectrum slope values ​​within the specified time are less than the slope threshold of the person, it is judged that there is no person on the sensor; wherein step 700 comprises: step 710, if the discrete power spectrum slope values ​​are all greater than the third specified value, and the second coefficient of variation is less than the fourth specified value, the slope threshold of the person is refreshed. By collecting the frequency domain original signal of the cardiac impact signal and dynamically refreshing the judgment threshold, the robustness of the algorithm is increased, the sensor is effectively suppressed from being easily interfered with by high frequency of other devices, the problem that the signal amplitude and signal standard deviation are affected by it is solved, and the accuracy is improved.

[0076] In this embodiment, a method for detecting whether there is a person on the sensor based on the heart ball signal is provided in the frequency domain, and the discrete power spectrum slope value can be: the original heart ball signal data sequence is also collected, the power spectrum within 1 second can be calculated, and the part less than 40HZ is retained. The power spectrum of the original signal is fitted with a straight line, and the slope value of the straight line is calculated. In this way, 10 slope values ​​are collected in units of 1 second within 10 seconds.

[0077] In this embodiment, the occupant slope threshold is the occupant threshold for the signal slope. When making a judgment, if all slope ratios within 10 seconds are greater than the occupant slope threshold, it is determined that there is a person on the sensor. If all amplitude ratios within 10 seconds are less than the occupant slope threshold, it is determined that there is no person on the sensor.

[0078] Preferably, if Figure 6 , Figure 6 This is the sixth schematic diagram of a method for detecting whether there is a person on a sensor based on a cardiac shock signal in the present invention; step 600 includes: step 610, calculating the original signal power spectrum per unit time; step 620, retaining the original signal power spectrum that is less than the second frequency value.

[0079] Step 600 also includes: step 630, fitting the power spectrum of the original signal with a straight line; step 640, calculating the slope value of the straight line fitted by all discrete power spectra within a specified time.

[0080] In this embodiment, the default value of the occupancy slope threshold is -0.5. However, during the sensor detection process, it is susceptible to high-frequency interference from other devices in the environment, which often leads to misjudgment. In order to solve this problem, the occupancy slope threshold needs to be continuously updated.

[0081] Specifically, obtain the second average value of all discrete power spectrum slope values ​​greater than the third specified value; multiply the second average value by the second adjustment coefficient to obtain the refreshed occupant slope threshold; multiply the second average value by the second adjustment coefficient to obtain the refreshed occupant slope threshold; determine whether there is someone on the sensor based on the refreshed occupant slope threshold: if the sensor is determined to be in an unmanned state, use the second adjustment coefficient to continuously refresh the occupant slope threshold.

[0082] Preferably, if Figure 7 , Figure 7 This is the seventh schematic diagram of a method for detecting whether there is a person on a sensor based on a cardiac shock signal in the present invention; the step 600 also includes: step 630, fitting the power spectrum of the original signal with a straight line; step 640, calculating the discrete power spectrum slope values ​​of all straight lines within a specified time period.

[0083] Preferably, if Figure 8 , Figure 8 This is the eighth schematic diagram of a method for detecting whether there is someone on a sensor based on a cardiac shock signal in the present invention; the step 710 includes: step 711, obtaining a second average value of all discrete power spectrum slope values ​​greater than a third specified value; step 712, multiplying the second average value by a second adjustment coefficient to obtain a refreshed slope threshold for someone on the sensor; step 713, judging whether there is someone on the sensor based on the refreshed slope threshold for someone on the sensor: if the sensor is determined to be in an unmanned state, the second adjustment coefficient is used to continuously refresh the slope threshold for someone on the sensor.

[0084] When updating the occupied slope, specifically, it can be assumed that the occupied slope threshold is -0.5. If 10 discrete slope values ​​are greater than -0.5, and the coefficient of variation of these 10 slope values ​​is less than the third specified value, the third specified value is preferably 0.2, then the occupied slope threshold needs to be adjusted using the second adjustment coefficient. Preferably, the second adjustment coefficient is 1.5.

[0085] When making adjustments, first calculate the second average value of all slope values ​​greater than -0.5, multiply the second average value by the second adjustment coefficient, and use the result as the refreshed occupancy slope threshold; determine whether there is someone on the sensor based on the refreshed occupancy slope threshold. If the sensor is determined to be in an unmanned state, continuously refresh the occupancy slope threshold using the second adjustment coefficient. Preferably, the occupancy slope threshold can be adjusted in the range of -0.75 to -3.

[0086] The method of detecting whether there is a person on the sensor based on the cardiac shock signal of the present invention increases the robustness of the algorithm by collecting the original time / frequency domain signal of the cardiac shock signal and dynamically refreshing the judgment threshold, effectively suppressing the sensor from being easily affected by high-frequency interference from other devices, solving the problem that the signal amplitude and signal standard deviation will be affected by it, and improving the accuracy.

[0087] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for detecting whether there is a person on a sensor based on a heartbeat signal, characterized in that: include: Step 100, collecting original heartbeat signals; Step 200: obtaining a high-frequency signal according to the original signal; Step 300, calculating the amplitude ratio between the original signal and the high frequency signal; Step 400: If all the amplitude ratios within the specified time are greater than the human amplitude threshold, it is determined that there is a person on the sensor; if all the amplitude ratios within the specified time are less than the human amplitude threshold, it is determined that there is no person on the sensor; Wherein, the step 400 includes: Step 410: If the amplitude ratios are all smaller than the first specified value, and the first coefficient of variation of the amplitude ratios is smaller than the second specified value, the human amplitude threshold is refreshed.

2. The method for detecting whether there is a person on the sensor according to claim 1, characterized in that: The step 200 comprises: Step 210, filtering the original signal of the cardiac impulse signal within a specified time by using finite impulse response filtering, zero-phase shift infinite impulse response filtering, or wavelet filter filtering; Step 220: retain the original signal with a frequency value above a specified value within a specified time to obtain a high-frequency signal.

3. The method for detecting whether there is a person on the sensor according to claim 2, characterized in that: The step 410 includes: Step 411, obtaining a first average value of all amplitude ratios that are less than a first specified value; Step 412: Multiply the first average value by the first adjustment coefficient to obtain a refreshed human amplitude threshold value; Step 413: Determine whether there is a person on the sensor according to the refreshed human amplitude threshold: If the sensor is determined to be in an unmanned state, the first adjustment coefficient is used to continuously refresh the human amplitude threshold.

4. The method for detecting whether there is a person on a sensor according to any one of claims 1 to 3, characterized in that: The adjustable range of the human amplitude threshold is 1.5-4.5.

Images