Intelligent training and control system for heart rate and respiration

Abstract

The invention provides an intelligent training and control system for heart rate and respiration, and belongs to the technical field of intelligent control. The intelligent training and control system comprises the steps that an existing detection module detects an original heart rate electrocardio curve and an original respiration curve of a patient; the simulation operation module analyzes the original curve to determine the number of initial simulation times, and captures a simulation curve under each simulation operation; the analysis module analyzes the original curve and the plurality of simulation curves; a predictability determination module for determining training predictability of the patient based on the analysis result; if the training predictability is greater than the preset predictability, determining a scanning time period, otherwise, issuing a re-simulation instruction; and the motion control module is used for locking the non-autonomous respiration moment based on the simulation curves under the last two times of simulation, and controlling the resistance belt to pull the patient to move based on artificial intelligence if the non-autonomous respiration moment is reached until the training is qualified. Therefore, the following effective capturing of the image under the condition that the heart rate and respiration of the patient are relatively stable is ensured, and the image acquisition accuracy is improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent control technology, and in particular to an intelligent training and control system for heart rate and breathing. Background Art

[0002] During coronary CTA angiography, the patient is required to hold his breath completely and maintain a steady heart rate. The contrast agent is injected and scanned within 3-5 seconds. However, many patients, especially elderly patients, find it difficult to hold their breath completely and maintain a steady heart rate. Their heart rate often fluctuates and they cannot control their breathing in the most critical few seconds, resulting in blurred images, inability to accurately judge the condition, and even complete failure of the examination.

[0003] Currently, the most common method is to manually train breathing before the examination, which takes nurses ten minutes to half an hour. However, the results are inconsistent, and some patients struggle to see results and cannot control their breathing. Unstable heart rates are primarily caused by nervousness during the examination in the machine, and the feeling of warmth during the contrast agent injection can exacerbate this nervousness. There is currently no solution.

[0004] Conventional CT and MRI scans require the patient to remain still to avoid motion artifacts. However, some patients experience involuntary movements and uncontrolled breathing. Sometimes, family members are needed to help control the body, but this is not always effective.

[0005] Therefore, the present invention proposes an intelligent training and control system for heart rate and breathing. Summary of the Invention

[0006] The present invention provides an intelligent training and control system for heart rate and respiration, which is used to perform intelligent heart rate and respiration training on patients in advance to ensure the subsequent effective capture of images when the patient's heart rate and respiration are relatively stable, thereby improving the accuracy of image acquisition.

[0007] The present invention provides an intelligent training and control system for heart rate and breathing, comprising:

[0008] An existing detection module, used for detecting the patient's original heart rate electrocardiogram curve and original respiratory curve based on existing equipment;

[0009] a simulation operation module, configured to analyze the original heart rate and electrocardiogram curve and the original respiration curve, determine an initial number of simulations, perform simulation operations on the patient for the initial number of simulations, and capture the simulated heart rate and electrocardiogram curve and the simulated respiration curve under each simulation operation, wherein the simulation operation is implemented based on an intelligent simulator;

[0010] an analysis module, configured to perform a first analysis on the original heart rate and electrocardiogram curves and the plurality of simulated heart rate and electrocardiogram curves, and simultaneously perform a second analysis on the original respiration curve and the plurality of simulated respiration curves;

[0011] a predictability determination module, configured to determine the training predictability of the patient based on the first analysis result and the second analysis result;

[0012] If the training predictability is greater than the preset predictability, determining the scanning time period; otherwise, issuing a re-simulation instruction to the patient;

[0013] The motion control module is used to lock the patient's involuntary breathing moment based on the simulated heart rate and electrocardiogram curves and simulated breathing curves under the last two simulations, and when the patient is re-simulated, if the involuntary breathing moment is reached, the resistance band is controlled based on artificial intelligence to pull the patient to exercise until the training is qualified.

[0014] Preferably, the simulation operation module includes:

[0015] The curve segment locking unit is used to lock the high-frequency curve segments in each original curve respectively, determine the curve division interval points according to the standard setting frequency of the corresponding curve type, obtain the first variance of the corresponding high-frequency curve segment, the second variance of all high-frequency curve segments, and at the same time, lock the highest point and the second highest point of the corresponding high-frequency curve segment;

[0016] Reference point determination unit, used if The highest point is regarded as the first reference point of the corresponding high-frequency curve segment, where H z Indicates the curve value corresponding to the highest point; H c Indicates the curve value corresponding to the second highest point; σ1 2 represents the first variance; σ2 2 represents the second variance;

[0017] Otherwise, the second highest point is regarded as the second reference point of the corresponding high-frequency curve segment;

[0018] a times determination unit, for determining an amplitude variable corresponding to the original curve based on a difference between a first sum of all first reference points and a second sum of all second reference points in the same original curve, and obtaining an initial simulation times in combination with a reference variable corresponding to the curve type;

[0019]

[0020] Where Nc represents the corresponding initial simulation number; max represents the maximum value symbol; n1 represents the number of the first reference points in the corresponding original curve; n2 represents the number of the second reference points in the corresponding original curve; σ3 2 Represents the variance of the curve values corresponding to all first reference points in the original curve; σ4 2Indicates the variance of the curve values corresponding to all second reference points in the original curve; sum1 represents the first sum; sum2 represents the second sum; Cb represents the reference variable of the corresponding curve type; [] represents the rounding symbol.

[0021] Preferably, the intelligent simulator includes: a temperature heating device and a bioelectric stimulation device.

[0022] Preferably, the analysis module includes:

[0023] An alignment and interception unit is used to align and intercept the first peak of the original curve with the simulated curves in the order of the initial simulation times, and obtain the peak set and valley set of each aligned curve to calculate the first average peak value, the first average valley value and the first average value of the corresponding aligned curve;

[0024] a zero point number acquisition unit, configured to acquire a first zero point number of the original curve based on the intercepted alignment curve, and a second zero point number of each simulation curve based on the intercepted alignment curve;

[0025] inserting an analysis unit for maintaining the alignment curve intercepted by the corresponding simulation curve unchanged if the first number of zero points is less than or equal to the second number of zero points;

[0026] Otherwise, performing curve expansion on the aligned curve intercepted by the corresponding simulation curve according to the absolute value of the difference between the first number of zero points and the second number of zero points to obtain a first curve, and calculating a second average peak value, a second average valley value, and a second average value of the first curve;

[0027] a first calculation unit, configured to calculate a corresponding first convergence coefficient according to the first average peak value, the first average valley value, and the first average value when no curve expansion occurs in the alignment curve intercepted by the corresponding simulation curve;

[0028] a second calculation unit, configured to calculate a corresponding second convergence coefficient based on the first average peak value, the first average valley value, the first average value, the second average peak value, the second average valley value, and the second average value when the alignment curve intercepted by the corresponding simulation curve has curve expansion;

[0029] A curve drawing unit is used to determine the convergence coefficient of each alignment curve respectively, and draw all the convergence coefficients in the order of the alignment curve before the simulation and the alignment curve after the simulation to obtain a coefficient curve;

[0030] The result acquisition unit is used to input the coefficient curve into the curve analysis model to obtain the curve trend and linear coefficient.

[0031] Preferably, the predictability determination module includes:

[0032] A first comparison unit is used to match the curve trend ZS1 and the linear coefficient x1 related to the heart rate electrocardiogram curve with the first comparison table to obtain a first prediction coefficient YJ1;

[0033] A second comparison unit is used to match the curve trend ZS2 and the linear coefficient x2 related to the respiratory curve with the second comparison table to obtain a second prediction coefficient YJ2;

[0034] The predictability determination unit is used to obtain the training predictability YX1 according to the first predictability coefficient and the second predictability coefficient.

[0035] Preferably, the predictability determination module further includes:

[0036] The enumeration matrix construction unit is used to lock the effective time points of the curves under each simulation operation according to the scanning presentation standard, and sequentially input the effective time points under each simulation operation into the corresponding positions of the blank matrix to obtain the enumeration matrix;

[0037] A quantity counting unit is used to count the first number of non-empty elements in each column vector in the enumerated matrix and sort all the first numbers. valid time points corresponding to the first number, and perform continuous time analysis on the screened valid time points to obtain a continuous time period, where N0 represents the number of column vectors;

[0038] A time adjustment unit, configured to adjust the continuous time period according to the training predictability to determine an initial time point and an end time point;

[0039]

[0040]

[0041] Wherein, Tc0 represents the initial time point; Tc1 represents the end time point; T0 represents the first time point of the continuous time period; T1 represents the end time point of the continuous time period; YX0 represents the preset foresight; Indicates the number of all valid time points in a continuous time period LT and The time difference variable of the valid time points;

[0042] The initial time point and the end time point are used as the scanning time period.

[0043] Preferably, the motion control module includes:

[0044] A point locking unit is used to lock the turning points of the simulated heart rate and electrocardiogram curves and the simulated respiratory curves under the last two simulations according to the corresponding simulation standards, and perform an overlapping analysis on the turning points under the same type of curves to obtain a first overlapping point;

[0045] The overlap analysis unit is used to perform a secondary overlap analysis on the first overlap point under each type of curve to obtain a second overlap point, and regard the appearance time of the second overlap point as the involuntary breathing time.

[0046] Preferably, the motion control module further includes:

[0047] a range determination unit, configured to obtain, from the last simulation curve, a heart rate and electrocardiogram range and a respiration range of a recent qualified period corresponding to the moment of involuntary breathing, and, at the same time, obtain a heart rate and electrocardiogram value and a respiration value corresponding to the moment of involuntary breathing from the last simulation curve;

[0048] a deviation determining unit, configured to obtain a first deviation between the heart rate and electrocardiogram value and the heart rate and electrocardiogram range, and simultaneously obtain a second deviation between the respiration value and the respiration range, and obtain an initial tension from a dual deviation-resistance comparison table;

[0049] The tension adjustment unit is used to adjust the initial tension according to the historical usage of the resistance band to obtain the current tension, and control the resistance band to pull the patient to exercise according to the current tension.

[0050] Compared with the prior art, the present invention has the following advantages:

[0051] It is used to conduct intelligent training on the patient's heart rate and breathing in advance to ensure the subsequent effective capture of images when the patient's heart rate and breathing are relatively stable, thereby improving the accuracy of image acquisition.

[0052] Other features and advantages of the present invention will be described in the following description, and in part will become apparent from the description, or will be understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description and the accompanying drawings.

[0053] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0055] Figure 1 This is a structural diagram of a heart rate and breathing intelligent control system in an embodiment of the present invention. DETAILED DESCRIPTION

[0056] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0057] The present invention provides an intelligent training and control system for heart rate and breathing, such as Figure 1 Shown, including:

[0058] An existing detection module, used for detecting the patient's original heart rate electrocardiogram curve and original respiratory curve based on existing equipment;

[0059] a simulation operation module, configured to analyze the original heart rate and electrocardiogram curve and the original respiration curve, determine an initial number of simulations, perform simulation operations on the patient for the initial number of simulations, and capture the simulated heart rate and electrocardiogram curve and the simulated respiration curve under each simulation operation, wherein the simulation operation is implemented based on an intelligent simulator;

[0060] an analysis module, configured to perform a first analysis on the original heart rate and electrocardiogram curves and the plurality of simulated heart rate and electrocardiogram curves, and simultaneously perform a second analysis on the original respiration curve and the plurality of simulated respiration curves;

[0061] a predictability determination module, configured to determine the training predictability of the patient based on the first analysis result and the second analysis result;

[0062] If the training predictability is greater than the preset predictability, determining the scanning time period; otherwise, issuing a re-simulation instruction to the patient;

[0063] The motion control module is used to lock the patient's involuntary breathing moment based on the simulated heart rate and electrocardiogram curves and simulated breathing curves under the last two simulations, and when the patient is re-simulated, if the involuntary breathing moment is reached, the resistance band is controlled based on artificial intelligence to pull the patient to exercise until the training is qualified.

[0064] In this embodiment, the intelligent simulator includes a temperature heating device and a bioelectric stimulation device, and is an existing simulator.

[0065] In this embodiment, the existing device may be a heart rate dynamic monitoring sensor to collect the heart rate and electrocardiogram curve, and a piezoelectric device to collect the respiration curve, thereby directly obtaining the original heart rate and electrocardiogram curve and the original respiration curve.

[0066] In this embodiment, the initial simulation times refer to the subsequent training times preliminarily set for the patient, so as to ensure that the patient maintains correct movements during the subsequent actual measurement process to achieve effective image acquisition.

[0067] In this embodiment, the simulation operation refers to the operation of each training, that is, the training is achieved by performing temperature heating and bioelectric stimulation through an intelligent simulator, so that the patient can be as familiar as possible with the subsequent actual measurement environment to ensure effective image acquisition.

[0068] In this embodiment, a corresponding simulated heart rate and electrocardiogram curve and a simulated respiration curve are obtained in each simulation operation.

[0069] In this embodiment, the first analysis and the second analysis are to determine whether there is a training effect on heart rate, electrocardiogram and respiration. Under normal circumstances, if the patient continues to train, he or she will adapt to the subsequent actual measurement environment. Then, the subsequent simulation results will meet the set standards more and more, which is comprehensively reflected in the simulation trend and linear coefficient.

[0070] In this embodiment, the training predictability is achieved based on the combination of the first analysis result and the second analysis result, and the preset predictability value is generally 0.6.

[0071] In this embodiment, the scanning time period refers to the time period in which the doctor scans the patient to obtain images, and this time period is based on the results comprehensively extracted after the previous simulation operation. It is mainly to determine the time so that the image can be directly and efficiently obtained, and the images obtained in this time period will be clearer.

[0072] In this embodiment, the re-simulation instruction is for continuing to train the patient's breathing.

[0073] In this embodiment, the involuntary breathing moment refers to the moment when the standard is not met. Then, during the re-simulation process, adjustments are made with the help of external force to further ensure the clarity of subsequent image acquisition.

[0074] In this embodiment, the resistance band is provided to adjust the patient's breathing and heart rate with the help of external force to ensure that they are within the corresponding qualified range as much as possible.

[0075] The beneficial effect of the above technical solution is: it is used to conduct intelligent training of the patient's heart rate and breathing in advance to ensure the subsequent effective capture of images when the patient's heart rate and breathing are relatively stable, thereby improving the accuracy of image acquisition.

[0076] The present invention provides an intelligent training and control system for heart rate and breathing, wherein the simulation operation module comprises:

[0077] The curve segment locking unit is used to lock the high-frequency curve segments in each original curve respectively, determine the curve division interval points according to the standard setting frequency of the corresponding curve type, obtain the first variance of the corresponding high-frequency curve segment, the second variance of all high-frequency curve segments, and at the same time, lock the highest point and the second highest point of the corresponding high-frequency curve segment;

[0078] Reference point determination unit, used if The highest point is regarded as the first reference point of the corresponding high-frequency curve segment, where H z Indicates the curve value corresponding to the highest point; H c Indicates the curve value corresponding to the second highest point; σ1 2 represents the first variance; σ2 2 represents the second variance;

[0079] Otherwise, the second highest point is regarded as the second reference point of the corresponding high-frequency curve segment;

[0080] a times determination unit, for determining an amplitude variable corresponding to the original curve based on a difference between a first sum of all first reference points and a second sum of all second reference points in the same original curve, and obtaining an initial simulation times in combination with a reference variable corresponding to the curve type;

[0081]

[0082] Where Nc represents the corresponding initial simulation number; max represents the maximum value symbol; n1 represents the number of the first reference points in the corresponding original curve; n2 represents the number of the second reference points in the corresponding original curve; σ3 2 Represents the variance of the curve values corresponding to all first reference points in the original curve; σ4 2 Indicates the variance of the curve values corresponding to all second reference points in the original curve; sum1 represents the first sum; sum2 represents the second sum; Cb represents the reference variable of the corresponding curve type; [] represents the rounding symbol.

[0083] In this embodiment, a high-frequency curve segment refers to a peak point in the curve whose value is greater than a set value, and the peak points greater than the set value are continuously drawn to obtain several high-frequency curve segments, and the set value is pre-set, and the set value for respiration and heart rate is different.

[0084] In this embodiment, the standard setting frequency for heart rate is 1 / t1, and the standard setting frequency for breathing is 1 / t2, where t1 and t2 are interval times, and the value of t1 is 2 seconds, and the value of t2 is 3 seconds. Then, the high-frequency curve segment is divided according to t1 and t2, and each division point and the value corresponding to the division point are used as the basic data for the subsequent calculation of the variance.

[0085] In this embodiment, the first variance is calculated based on the values of the division points involved in the corresponding high-frequency curve segments, and the second variance is calculated based on the values of each division point involved in all high-frequency curve segments, and the first variance and the second variance are calculated based on the variance formula.

[0086] In this embodiment, the highest point and the second highest point are obtained based on the curve segment.

[0087] In this embodiment, the result obtained by accumulating and calculating the values of all first reference points in the same original curve is the first sum, and so on, the result obtained by accumulating and calculating the values of all second reference points is the second sum.

[0088] In this embodiment, |sum1-sum2| is the amplitude variable.

[0089] In this embodiment, the reference variable is pre-set, and different curve types correspond to different reference variables. The reference variable is generally the average of the absolute values of the differences between any two adjacent time points under a normal heart rate ECG curve or a normal breathing curve.

[0090] The beneficial effects of the above technical solution are: by determining the high-frequency curve segment and the standard setting frequency, the variance of the curve segment is calculated, and then the reference points of the highest point and the second highest point are set, providing a basis for the subsequent calculation of the initial simulation times, and by calculating the difference between the first reference point and the second reference point and combining the reference variables, the simulation times are obtained to the greatest extent, the rationality of the training is ensured as much as possible, to ensure that the patient adapts to the test environment, and to provide a basis for obtaining clear images.

[0091] The present invention provides an intelligent training and control system for heart rate and breathing, wherein the analysis module comprises:

[0092] An alignment and interception unit is used to align and intercept the first peak of the original curve with the simulated curves in the order of the initial simulation times, and obtain the peak set and valley set of each aligned curve to calculate the first average peak value, the first average valley value and the first average value of the corresponding aligned curve;

[0093] a zero point number acquisition unit, configured to acquire a first zero point number of the original curve based on the intercepted alignment curve, and a second zero point number of each simulation curve based on the intercepted alignment curve;

[0094] inserting an analysis unit for maintaining the alignment curve intercepted by the corresponding simulation curve unchanged if the first number of zero points is less than or equal to the second number of zero points;

[0095] Otherwise, performing curve expansion on the aligned curve intercepted by the corresponding simulation curve according to the absolute value of the difference between the first number of zero points and the second number of zero points to obtain a first curve, and calculating a second average peak value, a second average valley value, and a second average value of the first curve;

[0096] a first calculation unit, configured to calculate a corresponding first convergence coefficient according to the first average peak value, the first average valley value, and the first average value when no curve expansion occurs in the alignment curve intercepted by the corresponding simulation curve;

[0097] a second calculation unit, configured to calculate a corresponding second convergence coefficient based on the first average peak value, the first average valley value, the first average value, the second average peak value, the second average valley value, and the second average value when the alignment curve intercepted by the corresponding simulation curve has curve expansion;

[0098] A curve drawing unit is used to determine the convergence coefficient of each alignment curve respectively, and draw all the convergence coefficients in the order of the alignment curve before the simulation and the alignment curve after the simulation to obtain a coefficient curve;

[0099] The result acquisition unit is used to input the coefficient curve into the curve analysis model to obtain the curve trend and linear coefficient.

[0100] In this embodiment, the first peak refers to the position where a peak first appears in the corresponding curve.

[0101] In this embodiment, alignment and interception refers to preliminary alignment based on the first peak, and then interception at the same time, that is, the time period of the intercepted curves is the same, and thus are called aligned curves.

[0102] In this embodiment, the peak set is composed of all peak points in the alignment curve, the valley set is composed of all valley points in the alignment curve, the first average peak value is the average value of all values in the peak set, the first average valley value is the average value of all values in the valley set, and the first average value is the average value of all values in the peak set and the valley set.

[0103] In this embodiment, the number of zero points refers to the number of points that cross the horizontal setting line, and the horizontal setting line is pre-set and serves as an analysis basis.

[0104] In this embodiment, the curve extension refers to extending the curve after the alignment curve intercepted by the simulation curve, and the extension length is based on: Among them, LC is the extension length of the curve, D10 is the number of the first zero point; D20 is the number of the second zero point; L0 min L0 is the minimum length of the curve lengths between all adjacent zero points under the first zero point number; max is the maximum length of the curve between all adjacent zero points under the first zero point number; ln represents the sign of the logarithmic function.

[0105] In this embodiment, the curve after expansion and the aligned curve are used as the first curve, and the calculation method of the second average peak value, the second average valley value, and the second average value is the same as the calculation method of the first average peak value, the first average valley value, and the first average value, which will not be repeated here.

[0106] In this embodiment, the first convergence coefficient and the second convergence coefficient are calculated as follows:

[0107]

[0108] Wherein, f1 is the first average peak value; g1 is the first average valley value; ave1 is the first average value; and Ds1 is the first convergence coefficient.

[0109]

[0110] Wherein, f2 is the second average peak value; g2 is the second average valley value; ave2 is the second average value; and Ds2 is the second convergence coefficient.

[0111] In this embodiment, the coefficient curve is obtained by connecting all coefficients in sequence.

[0112] In this embodiment, the curve analysis model is obtained by training a neural network model based on different curves and expert analysis of the curve trends and linear coefficients. Therefore, the curve trends and linear coefficients can be directly obtained.

[0113] The beneficial effects of the above technical solution are: by aligning the curves, it is convenient to conduct subsequent comparative analysis, and by analyzing the number of zero points to determine whether the curve is a curve, it effectively guarantees the basis of curve analysis, and then provides a reliable data basis for calculating the convergence coefficient, and subsequently by drawing the curve of the convergence coefficient to obtain the trend and coefficient, it provides convenience for subsequent foresight.

[0114] The present invention provides an intelligent training and control system for heart rate and breathing, wherein the predictability determination module includes:

[0115] A first comparison unit is used to match the curve trend ZS1 and the linear coefficient x1 related to the heart rate electrocardiogram curve with the first comparison table to obtain a first prediction coefficient YJ1;

[0116] A second comparison unit is used to match the curve trend ZS2 and the linear coefficient x2 related to the respiratory curve with the second comparison table to obtain a second prediction coefficient YJ2;

[0117] The predictability determination unit is used to obtain the training predictability YX1 according to the first predictability coefficient and the second predictability coefficient.

[0118] In this embodiment, the first comparison table includes the curve trend of heart rate and electrocardiogram, the linear coefficient combination and the prediction coefficient set by the expert to match it. The first prediction coefficient can be directly obtained through the table.

[0119] In this embodiment, the second comparison table includes the curve trend of breathing, the linear coefficient combination and the prediction coefficient set by the expert to match it. The second prediction coefficient can be directly obtained through the table.

[0120] Training predictability=heart rate and ECG weight×first predictive coefficient+respiration weight×second predictive coefficient, where heart rate and ECG weight+respiration weight=1.

[0121] The beneficial effect of the above technical solution is: by obtaining the relevant prediction coefficient from the corresponding comparison table, and then combining it with the weight, the training predictability is effectively obtained, providing a basis for judging whether to continue training in the future.

[0122] The present invention provides an intelligent training and control system for heart rate and breathing, wherein the predictability determination module further includes:

[0123] The enumeration matrix construction unit is used to lock the effective time points of the curves under each simulation operation according to the scanning presentation standard, and sequentially input the effective time points under each simulation operation into the corresponding positions of the blank matrix to obtain the enumeration matrix;

[0124] A quantity counting unit is used to count the first number of non-empty elements in each column vector in the enumerated matrix and sort all the first numbers. valid time points corresponding to the first number, and perform continuous time analysis on the screened valid time points to obtain a continuous time period, where N0 represents the number of column vectors;

[0125] A time adjustment unit, configured to adjust the continuous time period according to the training predictability to determine an initial time point and an end time point;

[0126]

[0127] Wherein, Tc0 represents the initial time point; Tc1 represents the end time point; T0 represents the first time point of the continuous time period; T1 represents the end time point of the continuous time period; YX0 represents the preset foresight; Indicates the number of all valid time points in a continuous time period LT and The time difference variable of the valid time points;

[0128] The initial time point and the end time point are used as the scanning time period.

[0129] In this embodiment, the scanning presentation standard refers to the most reasonable time for scanning and acquiring images when the heart rate reaches a certain numerical range and the respiration reaches a certain numerical range. At this time, the effective time point is locked according to this standard, and the basis for locking the effective time point is to rely on the relevant numerical range. Only by locking the numerical value can the effective time point be locked.

[0130] In this embodiment, the blank matrix is a blank list including time points. For example, if the curve acquisition is based on 1 minute, then there are 60 time points in the blank matrix. Then, the valid time points in each curve are obtained in turn to adjust the blank matrix accordingly, that is, element 1 is filled in the blank position of the corresponding valid time point.

[0131] In this embodiment, the first number counted is the number of elements that are 1, that is, non-empty elements.

[0132] In this embodiment, the value of N0 is 60.

[0133] In this embodiment, the continuous time period refers to a time period without interruption. For example, the valid time points are: t1, t2, t3, t4, t6, t7, and t11. At this time, t1 to t7 can be regarded as a continuous time period.

[0134] In this embodiment, t1 corresponds to T0, and t7 corresponds to T1.

[0135] In this embodiment, the scanning time period is (Tc0, Tc1).

[0136] The beneficial effects of the above technical solution are: effective time points are locked according to the scanning presentation standards, and input into the blank matrix to obtain a list matrix, and by sorting the quantity and screening the time points, it is convenient to obtain the time period to provide a basis for the subsequent determination of the scanning time period, and the time period is adjusted through training foresight, further ensuring the accuracy and reliability of the scanning time period acquisition, and indirectly improving the clarity of image acquisition.

[0137] The present invention provides an intelligent training and control system for heart rate and breathing, wherein the motion control module comprises:

[0138] A point locking unit is used to lock the turning points of the simulated heart rate and electrocardiogram curves and the simulated respiratory curves under the last two simulations according to the corresponding simulation standards, and perform an overlapping analysis on the turning points under the same type of curves to obtain a first overlapping point;

[0139] The overlap analysis unit is used to perform a secondary overlap analysis on the first overlap point under each type of curve to obtain a second overlap point, and regard the appearance time of the second overlap point as the involuntary breathing time.

[0140] In this embodiment, the simulation standard is pre-set, and the turning point refers to the prominent point where the curve exceeds the simulation standard. Since two curves under the same type of curve are obtained, the turning points of these two curves are overlapped and analyzed to obtain the first overlapping point. For example, the turning points of curve 1 are: point 1, point 2, point 4, and the turning points of curve 2 are: point 1, point 4, point 5. At this time, the overlapping points are: point 1 and point 4.

[0141] In this embodiment, the overlapping points under type 1 are point 1 and point 4, and the overlapping points under type 2 are point 1 and point 6. At this time, the second overlapping point is point 1, and the moment of occurrence of point 1 is regarded as the moment of involuntary breathing.

[0142] The beneficial effect of the above technical solution is that through the primary overlapping analysis of the same type of curves and the secondary overlapping analysis of different types of curves, the moment of involuntary breathing can be effectively determined, providing a basis for subsequent training with the help of external force.

[0143] The present invention provides an intelligent training and control system for heart rate and breathing, wherein the motion control module further comprises:

[0144] a range determination unit, configured to obtain, from the last simulation curve, a heart rate and electrocardiogram range and a respiration range of a recent qualified period corresponding to the moment of involuntary breathing, and, at the same time, obtain a heart rate and electrocardiogram value and a respiration value corresponding to the moment of involuntary breathing from the last simulation curve;

[0145] a deviation determining unit, configured to obtain a first deviation between the heart rate and electrocardiogram value and the heart rate and electrocardiogram range, and simultaneously obtain a second deviation between the respiration value and the respiration range, and obtain an initial tension from a dual deviation-resistance comparison table;

[0146] The tension adjustment unit is used to adjust the initial tension according to the historical usage of the resistance band to obtain the current tension, and control the resistance band to pull the patient to exercise according to the current tension.

[0147] In this embodiment, for example, if the patient's heart rate and ECG cycle is 20 seconds, the heart rate and ECG range and the respiration range are obtained by capturing the patient's heart rate and ECG cycle in 20 seconds.

[0148] In this embodiment, if the heart rate and ECG value is greater than the maximum value of the heart rate and ECG range, the first deviation is: the heart rate and ECG value - the maximum value of the heart rate and ECG range;

[0149] If the heart rate and ECG value is less than the minimum value of the heart rate and ECG range, the first deviation is: the heart rate and ECG value - the minimum value of the heart rate and ECG range.

[0150] In this embodiment, if the respiration value is greater than the maximum value of the respiration range, the second deviation is: respiration value - maximum value of the respiration range;

[0151] If the respiration value is less than the maximum value of the respiration range, the second deviation is: respiration value minus the minimum value of the respiration range.

[0152] In this embodiment, the dual deviation-resistance comparison table includes heart rate ECG deviation, breathing deviation, and the initial tension that matches these two deviations, which facilitates subsequent training with the help of external force.

[0153] In this embodiment, the current pulling force = the initial pulling force + the deviation pulling force that causes the resistance band to loosen under historical usage conditions.

[0154] The beneficial effects of the above technical solution are: obtaining the initial tension from the two aspects of heart rate and ECG deviation and respiratory deviation, and adjusting the tension based on the historical use of the resistance band, effectively ensuring auxiliary training for patients, and indirectly improving the effectiveness of training and the clarity of image acquisition.

[0155] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. An intelligent training and control system for heart rate and breathing, characterized in that: include: An existing detection module, used for detecting the patient's original heart rate electrocardiogram curve and original respiratory curve based on existing equipment; a simulation operation module, configured to analyze the original heart rate and electrocardiogram curve and the original respiration curve, determine an initial number of simulations, perform simulation operations on the patient for the initial number of simulations, and capture the simulated heart rate and electrocardiogram curve and the simulated respiration curve under each simulation operation, wherein the simulation operation is implemented based on an intelligent simulator; an analysis module, configured to perform a first analysis on the original heart rate and electrocardiogram curves and the plurality of simulated heart rate and electrocardiogram curves, and simultaneously perform a second analysis on the original respiration curve and the plurality of simulated respiration curves; a predictability determination module, configured to determine the training predictability of the patient based on the first analysis result and the second analysis result; If the training predictability is greater than the preset predictability, determining the scanning time period; otherwise, issuing a re-simulation instruction to the patient; The motion control module is used to lock the patient's involuntary breathing moment based on the simulated heart rate and electrocardiogram curves and simulated breathing curves under the last two simulations, and when the patient is re-simulated, if the involuntary breathing moment is reached, the resistance band is controlled based on artificial intelligence to pull the patient to exercise until the training is qualified.

2. The intelligent training and control system for heart rate and breathing according to claim 1, characterized in that: The simulation operation module includes: The curve segment locking unit is used to lock the high-frequency curve segments in each original curve respectively, determine the curve division interval points according to the standard setting frequency of the corresponding curve type, obtain the first variance of the corresponding high-frequency curve segment, the second variance of all high-frequency curve segments, and at the same time, lock the highest point and the second highest point of the corresponding high-frequency curve segment; Reference point determination unit, used if The highest point is regarded as the first reference point of the corresponding high-frequency curve segment, where H z Indicates the curve value corresponding to the highest point; H c Indicates the curve value corresponding to the second highest point; σ1 2 represents the first variance; σ2 2 represents the second variance; Otherwise, the second highest point is regarded as the second reference point of the corresponding high-frequency curve segment; a times determination unit, for determining an amplitude variable corresponding to the original curve based on a difference between a first sum of all first reference points and a second sum of all second reference points in the same original curve, and obtaining an initial simulation times in combination with a reference variable corresponding to the curve type; Where Nc represents the corresponding initial simulation number; max represents the maximum value symbol; n1 represents the number of the first reference points in the corresponding original curve; n2 represents the number of the second reference points in the corresponding original curve; σ3 2 Represents the variance of the curve values corresponding to all first reference points in the original curve; σ4 2 Indicates the variance of the curve values corresponding to all second reference points in the original curve; sum1 represents the first sum; sum2 represents the second sum; Cb represents the reference variable of the corresponding curve type; [] represents the rounding symbol.

3. The intelligent training and control system for heart rate and breathing according to claim 1, characterized in that: The intelligent simulator includes a temperature heating device and a bioelectric stimulation device.

4. The intelligent training and control system for heart rate and breathing according to claim 1, characterized in that: The analysis module includes: An alignment and interception unit is used to align and intercept the first peak of the original curve with the simulated curves in the order of the initial simulation times, and obtain the peak set and valley set of each aligned curve to calculate the first average peak value, the first average valley value and the first average value of the corresponding aligned curve; a zero point number acquisition unit, configured to acquire a first zero point number of the original curve based on the intercepted alignment curve, and a second zero point number of each simulation curve based on the intercepted alignment curve; inserting an analysis unit for maintaining the alignment curve intercepted by the corresponding simulation curve unchanged if the first number of zero points is less than or equal to the second number of zero points; Otherwise, performing curve expansion on the aligned curve intercepted by the corresponding simulation curve according to the absolute value of the difference between the first number of zero points and the second number of zero points to obtain a first curve, and calculating a second average peak value, a second average valley value, and a second average value of the first curve; a first calculation unit, configured to calculate a corresponding first convergence coefficient according to the first average peak value, the first average valley value, and the first average value when no curve expansion occurs in the alignment curve intercepted by the corresponding simulation curve; a second calculation unit, configured to calculate a corresponding second convergence coefficient based on the first average peak value, the first average valley value, the first average value, the second average peak value, the second average valley value, and the second average value when the alignment curve intercepted by the corresponding simulation curve has curve expansion; A curve drawing unit is used to determine the convergence coefficient of each alignment curve respectively, and draw all the convergence coefficients in the order of the alignment curve before the simulation and the alignment curve after the simulation to obtain a coefficient curve; The result acquisition unit is used to input the coefficient curve into the curve analysis model to obtain the curve trend and linear coefficient.

5. The intelligent training and control system for heart rate and breathing according to claim 4, characterized in that: The predictability determination module includes: A first comparison unit is used to match the curve trend ZS1 and the linear coefficient x1 related to the heart rate electrocardiogram curve with the first comparison table to obtain a first prediction coefficient YJ1; A second comparison unit is used to match the curve trend ZS2 and the linear coefficient x2 related to the respiratory curve with the second comparison table to obtain a second prediction coefficient YJ2; The predictability determination unit is used to obtain the training predictability YX1 according to the first predictability coefficient and the second predictability coefficient.

6. The intelligent training and control system for heart rate and breathing according to claim 5, characterized in that: The predictability determination module further includes: The enumeration matrix construction unit is used to lock the effective time points of the curves under each simulation operation according to the scanning presentation standard, and sequentially input the effective time points under each simulation operation into the corresponding positions of the blank matrix to obtain the enumeration matrix; A quantity counting unit is used to count the first number of non-empty elements in each column vector in the enumeration matrix and sort all the first numbers. valid time points corresponding to the first number, and perform continuous time analysis on the screened valid time points to obtain a continuous time period, where N0 represents the number of column vectors; A time adjustment unit, configured to adjust the continuous time period according to the training predictability to determine an initial time point and an end time point; Wherein, Tc0 represents the initial time point; Tc1 represents the end time point; T0 represents the first time point of the continuous time period; T1 represents the end time point of the continuous time period; YX0 represents the preset foresight; Indicates the number of all valid time points in a continuous time period LT and The time difference variable of the valid time points; The initial time point and the end time point are used as the scanning time period.

7. The intelligent training and control system for heart rate and breathing according to claim 1, characterized in that: The motion control module includes: A point locking unit is used to lock the turning points of the simulated heart rate and electrocardiogram curves and the simulated respiratory curves under the last two simulations according to the corresponding simulation standards, and perform an overlapping analysis on the turning points under the same type of curves to obtain a first overlapping point; The overlap analysis unit is used to perform a secondary overlap analysis on the first overlap point under each type of curve to obtain a second overlap point, and regard the appearance time of the second overlap point as the involuntary breathing time.

8. The intelligent training and control system for heart rate and breathing according to claim 7, characterized in that: The motion control module further includes: a range determination unit, configured to obtain, from the last simulation curve, a heart rate and electrocardiogram range and a respiration range of a recent qualified period corresponding to the moment of involuntary breathing, and, at the same time, obtain a heart rate and electrocardiogram value and a respiration value corresponding to the moment of involuntary breathing from the last simulation curve; a deviation determining unit, configured to obtain a first deviation between the heart rate and electrocardiogram value and the heart rate and electrocardiogram range, and simultaneously obtain a second deviation between the respiration value and the respiration range, and obtain an initial tension from a dual deviation-resistance comparison table; The tension adjustment unit is used to adjust the initial tension according to the historical usage of the resistance band to obtain the current tension, and control the resistance band to pull the patient to exercise according to the current tension.

Images