Heart rate detection method, heart rate detection system and equipment applied to dental chair

Abstract

The invention relates to the technical field of dental treatment, in particular to a heart rate detection method, a heart rate detection system and equipment applied to a dental chair. Comprising the steps that frequency band waveform analysis is conducted on ECG waveforms collected by an ECG device in real time, normal heart rate frequency bands are collected, Fourier transform is adopted, signals of a data set of the normal heart rate frequency bands are converted into frequency domain signals from time domain signals, and the frequency domain signals serve as a reference frequency domain data set; determining an abnormal heart rate waveform frequency band; the collected normal heart rate frequency bands and abnormal heart rate waveform frequency bands are recognized and analyzed based on a pattern recognition algorithm, heart rate recognizable frequency bands and heart rate unrecognizable frequency bands are judged, and the heart rate unrecognizable frequency bands are screened to serve as abnormal heart rate analysis frequency bands; and analyzing the abnormal heart rate analysis frequency band based on a heart rate abnormity processing method to obtain an abnormal heart rate value of the abnormal heart rate analysis frequency band. According to the device, the heart rate can be effectively detected even if the detection module is interfered.

Description

Technical Field

[0001] The present invention relates to the technical field of dental treatment, and in particular to a heart rate detection method, a heart rate detection system and a device applied to a dental chair. Background Art

[0002] Heart rate is a professional term to describe the cardiac cycle, which refers to the number of heart beats per minute, based on the first sound. Heart rate measurement is one of the commonly used medical examination items. Real-time and accurate heart rate measurement is of great significance and wide application in clinical medicine, monitoring of vital signs of the elderly and competitive sports. Heart rate module is a device used to measure human heart rate, commonly found in products such as smart watches and heart rate monitors. Its principle is to sense the heartbeat through sensors, and then convert it into electrical signals for processing, and finally obtain the user's heart rate value. Dental chairs are medical equipment specially designed for oral surgery and disease examinations. Its main functions include body position adjustment, lighting control and blood pressure adjustment. Dental chairs are designed with electric type. The motor is started by controlling the switch to drive the transmission mechanism to move the corresponding parts of the dental chair, thereby completing various body position adjustments such as rising, falling, and pitching.

[0003] When the patient is using a dental chair for diagnosis, the medical staff's handling movements or the patient's shaking of varying degrees due to pain or tension, especially the tremor of the human body's muscles under tension, will generate corresponding interference signals to the sensor module, resulting in inaccurate signal detection by the sensor.

[0004] Based on the above problems, there is an urgent need for a method that can eliminate the influence of external interference on heart rate signal detection when the patient is using a dental chair. Summary of the invention

[0005] In view of the fact that the heart rate detection equipment currently used in dental chairs is easily affected by the behavior of medical staff during the diagnosis process or the tremors of patients caused by pain and tension, the final detection is affected. This application provides a heart rate detection method, heart rate detection system and equipment applied to dental chairs to solve the above problem.

[0006] To achieve the above object, the present invention is implemented through the following technical solutions: The present application embodiment discloses a heart rate detection method applied to a dental chair, comprising: S1: Perform frequency band waveform analysis on the ECG waveform collected by the ECG electrode device in real time, collect the normal heart rate frequency band, use Fourier transform to convert the signal of the data set of the normal heart rate frequency band from time domain signal to frequency domain signal, and use the frequency domain signal as the reference frequency domain data set; S2: Perform Fourier transform on all collected ECG waveforms to obtain a frequency domain data set to be analyzed, and use a waveform matching algorithm to perform waveform analysis on the reference frequency domain data set and the frequency domain data set to be analyzed to determine the frequency band of the abnormal heart rate waveform; S3: Based on the pattern recognition algorithm, the collected normal heart rate frequency bands and abnormal heart rate waveform frequency bands are identified and analyzed, and the heart rate recognizable frequency bands and the heart rate unrecognizable frequency bands are determined, and the heart rate unrecognizable frequency bands are selected as abnormal heart rate analysis frequency bands; S4: Analyze the abnormal heart rate analysis frequency band based on the abnormal heart rate processing method to obtain an abnormal heart rate value of the abnormal heart rate analysis frequency band.

[0007] The above-mentioned technical scheme is adopted: the above-mentioned scheme provides a heart rate detection method, which can analyze the heart rate waveform collected by the heart rate collection device, determine the frequency band of the abnormal heart rate waveform, and perform corresponding analysis and calculation on the frequency band where the abnormal heart rate waveform is located to obtain the abnormal heart rate value in the frequency band where the abnormal heart rate waveform is located. Even when the collected signal is interfered with by the actions of medical staff or patients, the heart rate value of the interfered heart rate frequency band can be effectively judged.

[0008] Preferably, the abnormal heart rate processing method includes: Taking 0.2S as the division interval, the abnormal heart rate analysis frequency band is divided into multiple judgment intervals, and the optimal frequency band is extracted and the abnormal signal is judged for different judgment intervals; The extraction of the preferred frequency band and the determination of abnormal signals include: S41: collecting effective decision points of the waveform mutation area and the wave peak area within the decision interval; S42: reading the collected peaks of different normal heart rate frequency bands and comparing them with the effective determination points, and determining the peak abnormality of the effective determination points; S43: calculating and determining the difference rate of the peak height, the time point of the peak in the waveform, and the curvature of the waveform on both sides of the peak, filtering out abnormal determination points, and leaving the first normal determination point; S44: Collecting all first normal determination points in all abnormal heart rate analysis frequency bands as the number of heart beats in the heart rate unrecognizable frequency band.

[0009] The above technical solution is adopted: the above provides a method for analyzing the frequency band within the determination interval, which can realize the corresponding numerical determination of the peak within the effective determination point and confirm the heartbeat number.

[0010] Further preferably, the peak abnormality judgment includes: intercepting the waveform mutation area and peak area within the collected judgment interval, setting the time point where the peak point of the normal heart rate frequency band is located to coincide with the point where the peak point of the waveform image area and the peak area within the judgment interval is located, dividing the waveform on both sides of the peak point of the normal heart rate frequency band and the waveform on both sides of the peak point of the waveform image area and the peak area within the judgment interval into multiple collection points, and calculating the curvature of the collection points one by one, loading the curvature data, peak point data and peak height data into the difference rate algorithm to calculate the difference rate, and determining whether the difference rate exceeds the requirement for abnormal judgment.

[0011] The above technical solution is adopted: the above solution provides a method for determining peak abnormalities, processes the corresponding coefficients of the peaks, including the curvature, peak position and peak height, etc., performs numerical analysis on the above coefficients, calculates the difference rate, and can determine the collection points within the determination area for analysis to confirm whether it is a heartbeat waveform.

[0012] Further preferably, the dissimilarity algorithm formula is: , in, is the first dissimilarity rate, For the heart rate bands, is the number of normal heart rate frequency bands, For the The curvature difference between the heart rate frequency band and the judgment interval, is the curvature difference determination coefficient, To determine the height of the peak point of the heart rate frequency band in the interval, For the The height of the peak point of the normal heart rate frequency band, is the determination coefficient of the peak height, To determine the time point of the heart rate frequency band in the interval, No. The time point of the normal heart rate frequency band, is the time point determination coefficient, The first frequency band in the heart rate range is determined The curvature of the sampling points, Normal heart rate band The curvature of each sampling point; The first dissimilarity of each decision point calculated by the dissimilarity algorithm formula is compared with the set dissimilarity threshold, and the decision points exceeding the dissimilarity threshold are taken as abnormal decision points and filtered out, and the decision points below the dissimilarity threshold are taken as the first normal decision points and collected.

[0013] Adopt the above technical scheme: The above scheme provides a difference rate algorithm, which can realize numerical calculation according to the curvature of the peak position, the peak point and the height of the peak, obtain the corresponding calculation results, and perform numerical analysis according to the calculation results to determine whether the peak point is a collectable numerical point.

[0014] Further preferably, it also includes: performing frequency band waveform analysis on the BCG waveform collected by the ECG electrode device in real time, taking the normal heart rate frequency band as a reference frequency domain data set, and determining the abnormal heart rate waveform frequency band, calculating the second difference rate of the BCG waveform by a difference rate algorithm formula, and collecting the judgment point below the difference rate threshold as the second normal judgment point.

[0015] By adopting the above technical solution: in addition to collecting ECG waveform data through the corresponding acquisition module, the corresponding BCG waveform data can also be collected. The two acquisition modules collect data at the same time. When abnormal signals appear, comparative judgment can also be made to improve the fault tolerance rate.

[0016] Further preferably, it also includes: judging whether the number of the first normal judgment point and the second normal judgment point is the same; when the number of the first normal judgment point and the second normal judgment point is the same, taking the first normal judgment point and the second normal judgment point together as the number of heartbeats in the unrecognizable frequency band; when the number of the first normal judgment point and the second normal judgment point is different, performing correction analysis of the abnormal points.

[0017] The above technical solution is adopted: the above solution analyzes the normal judgment points collected by the two collection devices. When the numbers are different, it proves that there may be abnormalities in some of the collected normal judgment points. The abnormal points are determined by comparative analysis, and the abnormal points are analyzed again. The heart rate value can be further analyzed to ensure the accuracy of heart rate collection.

[0018] Further preferably, the time points of the first normal decision point determination interval and the second normal decision point determination interval are compared and analyzed one by one, and different decision points are collected respectively, the different decision points are decision points that do not appear at the same time point in the first normal decision point interval and the second normal decision point interval, and the different decision points are divided by the first dissimilarity rate of the first normal decision point or the second dissimilarity rate of the second normal decision point to obtain a calculation result, and the calculation result is judged. When the final calculation result is abnormal, the different decision point rate is divided; when the calculation result is normal, the different decision point continues to be counted as a normal decision point in the number of heartbeats, and the calculation result is judged in a manner of comparing the result of the division operation of the different decision point with the first normal decision point or the second normal decision point with the results of the previous division operation of multiple first normal decision points or second normal decision points with each other, to determine whether the result of the division operation of the different decision point with the first normal decision point or the second normal decision point is abnormal.

[0019] Adopting the above technical solution: the above solution can realize the corresponding analysis of the different decision points in the first normal decision point and the second normal decision point, and judge whether the different decision points can be included in the numerical calculation of the heart rate.

[0020] A heart rate detection system for a dental chair, applied to a heart rate detection method for a dental chair as described in any one of the above, characterized in that it comprises: Heart rate analysis unit: used to perform frequency band waveform analysis on the ECG waveform collected by the ECG electrode device in real time, collect the normal heart rate frequency band, use Fourier transform to convert the signal of the data set of the normal heart rate frequency band from time domain signal to frequency domain signal, and use the frequency domain signal as the reference frequency domain data set; Abnormal heart rate waveform judgment unit: used to perform Fourier transform on all collected ECG waveforms to obtain the frequency domain data set to be analyzed, use waveform matching algorithm to perform waveform analysis on the reference frequency domain data set and the frequency domain data set to be analyzed, and determine the frequency band of abnormal heart rate waveform; Abnormal heart rate analysis frequency band judgment unit: used to identify and analyze the collected normal heart rate frequency bands and abnormal heart rate waveform frequency bands based on the pattern recognition algorithm, judge the heart rate identifiable frequency bands and the heart rate unidentifiable frequency bands, and select the heart rate unidentifiable frequency bands as abnormal heart rate analysis frequency bands; Abnormal heart rate value calculation unit: used to analyze the abnormal heart rate analysis frequency band based on the abnormal heart rate processing method to obtain the abnormal heart rate value of the abnormal heart rate analysis frequency band.

[0021] Further preferably, it also includes: Amplifier unit: including instrument amplifier and heart rate amplifier, used to amplify the weak electrical signal after acquisition and conversion to a suitable processable state; Low-pass filter: used to filter out high-frequency noise in the collected signal; Analog-to-digital converter: used to convert analog signals into digital signals.

[0022] A device comprises a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the method according to any one of claims 1 to 7. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0024] Figure 1 This is a flow chart of the heart rate detection method for this application; Figure 2 This is a flow chart of the abnormal heart rate processing method for this application; Figure 3 This is the heart rate detection system block diagram for this application; Figure 4 This is a block diagram of the signal processing device of this application.

[0025] In the figure: 1. Heart rate analysis unit; 2. Abnormal heart rate waveform judgment unit; 3. Abnormal heart rate analysis frequency band judgment unit; 4. Abnormal heart rate value calculation unit; 5. Amplifier unit; 6. Low-pass filter; 7. Analog-to-digital converter. DETAILED DESCRIPTION

[0026] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0027] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0028] See also Figure 1-Figure 4 For example, the heart rate detection device originally used in dental chairs may be affected by the treatment of medical staff or the trembling of the patient due to tension or pain, which may affect the heart rate detection device's collection of the heart rate, resulting in inaccurate signals collected by the heart rate detection module. Based on the above problems, the embodiment of the present application discloses a heart rate detection method used in dental chairs, including: S1: Perform frequency waveform analysis on the ECG waveform collected by the ECG electrode device in real time, collect the normal heart rate frequency band, and use Fourier transform to convert the signal of the normal heart rate frequency band data set from time domain signal to frequency domain signal, and use the frequency domain signal as the reference frequency domain data set; in this design, the normal heart rate frequency band is the frequency band that can be collected by the acquisition module, and the normal heart rate frequency band in this acquisition process is used as the reference frequency domain data set, which can perform corresponding analysis according to the heartbeat frequency band conditions of different patient reagents, so as to achieve a more accurate final analysis result.

[0029] S2: Perform Fourier transform on all collected ECG waveforms to obtain the frequency domain data set to be analyzed, and use waveform matching algorithm to perform waveform analysis on the reference frequency domain data set and the frequency domain data set to be analyzed to determine the frequency band of the abnormal heart rate waveform; the above Fourier transform can realize the conversion of the signal from the time domain signal to the frequency domain signal. By observing and analyzing the frequency domain signal, the frequency band of the abnormal heart rate waveform can be better confirmed.

[0030] S3: Based on the graphic recognition algorithm, the collected normal heart rate frequency bands and abnormal heart rate waveform frequency bands are identified and analyzed to determine the heart rate identifiable frequency bands and the heart rate unidentifiable frequency bands, and the unidentifiable heart rate frequency bands are screened as abnormal heart rate analysis frequency bands; among the above-mentioned red heart rate identifiable frequency bands, even if the heart rate waveform frequency band is abnormal, the heart rate can be effectively collected, while the unidentifiable heart rate frequency bands are frequency bands that cannot be effectively collected and need to be processed accordingly to achieve further data collection.

[0031] S4: Analyze the abnormal heart rate analysis frequency band based on the abnormal heart rate processing method to obtain an abnormal heart rate value of the abnormal heart rate analysis frequency band.

[0032] The above scheme provides a heart rate detection method, which can analyze the heart rate waveform collected by the heart rate collection device, determine the frequency band of the abnormal heart rate waveform, and perform corresponding analysis and calculation on the frequency band where the abnormal heart rate waveform is located to obtain the abnormal heart rate value in the frequency band where the abnormal heart rate waveform is located. Even when the collected signal is interfered with by the actions of medical staff or patients, the heart rate value of the interfered heart rate frequency band can be effectively judged.

[0033] The abnormal heart rate processing method comprises: Taking 0.2S as the division interval, the abnormal heart rate analysis frequency band is divided into multiple judgment intervals, and the optimal frequency band is extracted and the abnormal signal is judged for different judgment intervals; The extraction of the preferred frequency band and the determination of abnormal signals include: S41: collecting effective decision points of the waveform mutation area and the wave peak area within the decision interval; S42: reading the collected peaks of different normal heart rate frequency bands and comparing them with the effective determination points, and determining the peak abnormality of the effective determination points; S43: calculating and determining the difference rate of the peak height, the time point of the peak in the waveform, and the curvature of the waveform on both sides of the peak, filtering out abnormal determination points, and leaving the first normal determination point; S44: Collecting all first normal determination points in all abnormal heart rate analysis frequency bands as the number of heart beats in the heart rate unrecognizable frequency band.

[0034] The above provides a method for analyzing the frequency band within the determination interval, which can realize the corresponding numerical determination of the peak within the effective determination point and confirm the heartbeat frequency.

[0035] The peak abnormality judgment includes: intercepting the waveform mutation area and the peak area within the collected judgment interval, arranging the time point where the peak point of the normal heart rate frequency band is located to coincide with the point where the peak point of the waveform image area and the peak area within the judgment interval is located, dividing the waveform on both sides of the peak point of the normal heart rate frequency band and the waveform on both sides of the peak point of the waveform image area and the peak area within the judgment interval into multiple collection points, and calculating the curvature of the collection points one by one, loading the curvature data, the peak point data and the peak height data into the difference rate algorithm to calculate the difference rate, and judging whether the difference rate exceeds the requirement of abnormal judgment.

[0036] The above scheme provides a method for determining peak abnormalities, processes the corresponding coefficients of the peaks, including curvature, peak position and peak height, performs numerical analysis on the above coefficients, calculates the difference rate, and can determine the collection points within the determination area for analysis to confirm whether it is a heartbeat waveform.

[0037] The dissimilarity algorithm formula is: , in, is the first dissimilarity rate, For the heart rate bands, is the number of normal heart rate frequency bands, For the The curvature difference between the heart rate frequency band and the judgment interval, is the curvature difference determination coefficient, To determine the height of the peak point of the heart rate frequency band in the interval, For the The height of the peak point of the normal heart rate frequency band, is the determination coefficient of the peak height, To determine the time point of the heart rate frequency band in the interval, No. The time point of the normal heart rate frequency band, is the time point determination coefficient, The first frequency band in the heart rate range is determined The curvature of the sampling points, Normal heart rate band The curvature of each sampling point; In the above scheme, the curvature of each collection point near the peak is calculated, and the curvature difference between each normal heart rate frequency band and the judgment interval, the difference with the peak height of the normal heart rate frequency band, and the difference with the time point of the normal heart rate frequency band are summarized and calculated, and the corresponding coefficient calculation is performed to obtain the difference rate of the collection points in the judgment interval, and the difference rate is compared with the set difference rate threshold to confirm the heartbeat number.

[0038] The first dissimilarity of each decision point calculated by the dissimilarity algorithm formula is compared with the set dissimilarity threshold, and the decision points exceeding the dissimilarity threshold are taken as abnormal decision points and filtered out, and the decision points below the dissimilarity threshold are taken as the first normal decision points and collected.

[0039] The above scheme provides a dissimilarity algorithm, which can realize numerical calculation according to the curvature of the peak location, the peak point and the peak height, obtain the corresponding operation results, perform numerical analysis based on the operation results, and judge whether the peak point is a collectable numerical point.

[0040] It also includes: performing frequency band waveform analysis on the BCG waveform collected by the ECG electrode device in real time, taking the normal heart rate frequency band as a reference frequency domain data set, and determining the abnormal heart rate waveform frequency band, calculating the second difference rate of the BCG waveform through a difference rate algorithm formula, and taking the judgment point below the difference rate threshold as the second normal judgment point and collecting it.

[0041] In addition to collecting ECG waveform data through the corresponding acquisition module, the corresponding BCG waveform data can also be collected. The two acquisition modules collect data at the same time. When abnormal signals appear, comparative judgment can be made to improve the fault tolerance rate.

[0042] It also includes: judging whether the number of the first normal judgment point and the second normal judgment point is the same; when the number of the first normal judgment point and the second normal judgment point is the same, taking the first normal judgment point and the second normal judgment point together as the number of heartbeats in the unrecognizable frequency band; when the number of the first normal judgment point and the second normal judgment point is different, performing correction analysis of the abnormal points.

[0043] The above scheme analyzes the normal judgment points collected by the two collection devices. When the numbers are different, it proves that some of the collected normal judgment points may have abnormal conditions. The abnormal points are determined by comparative analysis and analyzed again. The heart rate values ​​can be further analyzed to ensure the accuracy of heart rate collection.

[0044] The time points of the first normal decision point decision interval and the second normal decision point decision interval are compared and analyzed one by one, and different decision points are collected respectively, wherein the different decision points are decision points that do not appear at the same time point in the first normal decision point interval and the second normal decision point interval, and the different decision points are divided by the first difference rate of the first normal decision point or the second difference rate of the second normal decision point to obtain a calculation result, and the calculation result is judged. When the final calculation result is abnormal, the different decision point rate is divided, and when the calculation result is normal, the different decision point continues to be counted as a normal decision point in the number of heartbeats, and the calculation result is judged in a manner of comparing the result of the division operation of the different decision point with the first normal decision point or the second normal decision point with the results of the previous division operation of multiple first normal decision points or second normal decision points with each other, to judge whether the result of the division operation of the different decision point with the first normal decision point or the second normal decision point is abnormal.

[0045] The above scheme can realize corresponding analysis of different decision points among the first normal decision point and the second normal decision point, and judge whether the different decision points can be included in the numerical calculation of the heart rate.

[0046] A heart rate detection system for a dental chair, applied to a heart rate detection method for a dental chair as described in any one of the above, comprising: Heart rate analysis unit 1: used to perform frequency band waveform analysis on the ECG waveform collected by the ECG electrode device in real time, collect the normal heart rate frequency band, and use Fourier transform to convert the signal of the data set of the normal heart rate frequency band from time domain signal to frequency domain signal, and use the frequency domain signal as the reference frequency domain data set; Abnormal heart rate waveform judgment unit 2: used to perform Fourier transform on all collected ECG waveforms to obtain a frequency domain data set to be analyzed, and use a waveform matching algorithm to perform waveform analysis on the reference frequency domain data set and the frequency domain data set to be analyzed to determine the frequency band of the abnormal heart rate waveform; Abnormal heart rate analysis frequency band judgment unit 3: used to identify and analyze the collected normal heart rate frequency bands and abnormal heart rate waveform frequency bands based on the pattern recognition algorithm, judge the heart rate identifiable frequency bands and the heart rate unidentifiable frequency bands, and select the heart rate unidentifiable frequency bands as abnormal heart rate analysis frequency bands; The abnormal heart rate value calculation unit 4 is used to analyze the abnormal heart rate analysis frequency band based on the abnormal heart rate processing method to obtain the abnormal heart rate value of the abnormal heart rate analysis frequency band.

[0047] Also includes: Amplifier unit 5: including instrument amplifier and heart rate amplifier, used to amplify the weak electrical signal after collection and conversion to a suitable processable state; Low-pass filter 6: used to filter out high-frequency noise in the collected signal; Analog-to-digital converter 7: used to convert analog signals into digital signals.

[0048] The above-mentioned device can process the collected signals and process the signals into signals that can be processed in the embodiments of this patent.

[0049] A device comprises a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the method according to any one of claims 1 to 7.

[0050] Unless otherwise specified, the device components involved in the above embodiments are all conventional device components, and the connection methods and control methods involved are all conventional connection methods and control methods unless otherwise specified.

[0051] The present invention has been described in detail above in conjunction with the embodiments. However, those skilled in the art will appreciate that, without departing from the spirit of the present invention, the specific parameters in the above embodiments may be changed to form a plurality of specific embodiments, which are all within the common variation range of the present invention and will not be described in detail herein.

Claims

1. A heart rate detection method applied to a dental chair, characterized in that: include: S1: Perform frequency band waveform analysis on the ECG waveform collected by the ECG electrode device in real time, collect the normal heart rate frequency band, use Fourier transform to convert the signal of the data set of the normal heart rate frequency band from time domain signal to frequency domain signal, and use the frequency domain signal as the reference frequency domain data set; S2: Perform Fourier transform on all collected ECG waveforms to obtain a frequency domain data set to be analyzed, and use a waveform matching algorithm to perform waveform analysis on the reference frequency domain data set and the frequency domain data set to be analyzed to determine the frequency band of the abnormal heart rate waveform; S3: Based on the pattern recognition algorithm, the collected normal heart rate frequency bands and abnormal heart rate waveform frequency bands are identified and analyzed, and the heart rate recognizable frequency bands and the heart rate unrecognizable frequency bands are determined, and the heart rate unrecognizable frequency bands are selected as abnormal heart rate analysis frequency bands; S4: Analyze the abnormal heart rate analysis frequency band based on the abnormal heart rate processing method to obtain an abnormal heart rate value of the abnormal heart rate analysis frequency band.

2. The heart rate detection method applied to a dental chair according to claim 1, characterized in that: The abnormal heart rate processing method comprises: Taking 0.2S as the division interval, the abnormal heart rate analysis frequency band is divided into multiple judgment intervals, and the optimal frequency band is extracted and the abnormal signal is judged for different judgment intervals; The extraction of the preferred frequency band and the determination of abnormal signals include: S41: collecting effective decision points of the waveform mutation area and the wave peak area within the decision interval; S42: reading the collected peaks of different normal heart rate frequency bands and comparing them with the effective determination points, and determining the peak abnormality of the effective determination points; S43: calculating and determining the difference rate of the peak height, the time point of the peak in the waveform, and the curvature of the waveform on both sides of the peak, filtering out abnormal determination points, and leaving the first normal determination point; S44: Collecting all first normal determination points in all abnormal heart rate analysis frequency bands as the number of heart beats in the heart rate unrecognizable frequency band.

3. The heart rate detection method applied to a dental chair according to claim 2, characterized in that: The peak abnormality judgment includes: intercepting the waveform mutation area and the peak area within the collected judgment interval, arranging the time point where the peak point of the normal heart rate frequency band is located to coincide with the point where the peak point of the waveform image area and the peak area within the judgment interval is located, dividing the waveform on both sides of the peak point of the normal heart rate frequency band and the waveform on both sides of the peak point of the waveform image area and the peak area within the judgment interval into multiple collection points, and calculating the curvature of the collection points one by one, loading the curvature data, the peak point data and the peak height data into the difference rate algorithm to calculate the difference rate, and judging whether the difference rate exceeds the requirement of abnormal judgment.

4. The heart rate detection method applied to a dental chair according to claim 3, characterized in that: The dissimilarity algorithm formula is: ， in, is the first dissimilarity rate, For the heart rate bands, is the number of normal heart rate frequency bands, For the The curvature difference between the heart rate frequency band and the judgment interval, is the curvature difference determination coefficient, To determine the height of the peak point of the heart rate frequency band in the interval, For the The height of the peak point of the normal heart rate frequency band, is the determination coefficient of the peak height, To determine the time point of the heart rate frequency band in the interval, No. The time point of the normal heart rate frequency band, is the time point determination coefficient, The first frequency band in the heart rate range is determined The curvature of the sampling points, Normal heart rate band The curvature of each sampling point; The first dissimilarity of each decision point calculated by the dissimilarity algorithm formula is compared with the set dissimilarity threshold, and the decision points exceeding the dissimilarity threshold are taken as abnormal decision points and filtered out, and the decision points below the dissimilarity threshold are taken as the first normal decision points and collected.

5. The heart rate detection method applied to a dental chair according to claim 4, characterized in that: Also includes: The BCG waveform collected by the ECG electrode device is subjected to frequency band waveform analysis in real time. The normal heart rate frequency band is used as the reference frequency domain data set, and the abnormal heart rate waveform frequency band is determined. The second difference rate of the BCG waveform is calculated by the difference rate algorithm formula, and the judgment point below the difference rate threshold is taken as the second normal judgment point and collected.

6. The heart rate detection method applied to a dental chair according to claim 5, characterized in that: It also includes: judging whether the number of the first normal judgment point and the second normal judgment point is the same; when the number of the first normal judgment point and the second normal judgment point is the same, taking the first normal judgment point and the second normal judgment point together as the number of heartbeats in the unrecognizable frequency band; when the number of the first normal judgment point and the second normal judgment point is different, performing correction analysis of the abnormal points.

7. The heart rate detection method applied to a dental chair according to claim 6, characterized in that: The time points of the first normal decision point decision interval and the second normal decision point decision interval are compared and analyzed one by one, and different decision points are collected respectively, wherein the different decision points are decision points that do not appear at the same time point in the first normal decision point interval and the second normal decision point interval, and the different decision points are divided by the first difference rate of the first normal decision point or the second difference rate of the second normal decision point to obtain a calculation result, and the calculation result is judged. When the final calculation result is abnormal, the different decision point rate is divided, and when the calculation result is normal, the different decision point continues to be counted as a normal decision point in the number of heartbeats, and the calculation result is judged in a manner of comparing the result of the division operation of the different decision point with the first normal decision point or the second normal decision point with the results of the previous division operation of multiple first normal decision points or second normal decision points with each other, to judge whether the result of the division operation of the different decision point with the first normal decision point or the second normal decision point is abnormal.

8. A heart rate detection system for a dental chair, applied to a heart rate detection method for a dental chair as claimed in any one of claims 1 to 7, characterized in that: include: Heart rate analysis unit: used to perform frequency band waveform analysis on the ECG waveform collected by the ECG electrode device in real time, collect the normal heart rate frequency band, use Fourier transform to convert the signal of the data set of the normal heart rate frequency band from time domain signal to frequency domain signal, and use the frequency domain signal as the reference frequency domain data set; Abnormal heart rate waveform judgment unit: used to perform Fourier transform on all collected ECG waveforms to obtain the frequency domain data set to be analyzed, use waveform matching algorithm to perform waveform analysis on the reference frequency domain data set and the frequency domain data set to be analyzed, and determine the frequency band of abnormal heart rate waveform; Abnormal heart rate analysis frequency band judgment unit: used to identify and analyze the collected normal heart rate frequency bands and abnormal heart rate waveform frequency bands based on the pattern recognition algorithm, judge the heart rate identifiable frequency bands and the heart rate unidentifiable frequency bands, and select the heart rate unidentifiable frequency bands as abnormal heart rate analysis frequency bands; Abnormal heart rate value calculation unit: used to analyze the abnormal heart rate analysis frequency band based on the abnormal heart rate processing method to obtain the abnormal heart rate value of the abnormal heart rate analysis frequency band.

9. The heart rate detection system for dental chair according to claim 8, characterized in that: Also includes: Amplifier unit: including instrument amplifier and heart rate amplifier, used to amplify the weak electrical signal after acquisition and conversion to a suitable processable state; Low-pass filter: used to filter out high-frequency noise in the collected signal; Analog-to-digital converter: used to convert analog signals into digital signals.

10. A device, characterized in that: The method comprises a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the method according to any one of claims 1 to 7.

Images