A method and system for predicting D-type personality based on millimeter wave radar

Abstract

The present application relates to a kind of D type personality prediction method and system based on millimeter wave radar, method includes: when target patient is diagnosed with coronary heart disease, the human heart rate variability HRV data of target patient is collected using millimeter wave radar, short-term frequency domain analysis is carried out to HRV data, and the frequency domain index parameter of target patient is obtained;Whether target patient is D type personality according to preset D type personality prediction algorithm and frequency domain index parameter is predicted;If target patient is D type personality, then target patient is carried out according to D type personality coronary heart disease prognosis.The non-contact HRV data acquisition of coronary heart disease patient is realized using millimeter wave radar, and after short-term frequency domain analysis is carried out to HRV data, the frequency domain index parameter for D type personality prediction is obtained, so as to realize the prediction of D type personality.Compared with the existing scale, the accuracy is higher, and the disease prognosis of D type personality coronary heart disease patient can be effectively improved.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of medical treatment, and particularly relates to a D-type personality prediction method and system based on a millimeter wave radar. BACKGROUND

[0002] The millimeter wave radar is a device utilizing electromagnetic waves in the millimeter wave band, which can emit electromagnetic waves to a target and receive electromagnetic waves reflected by the target. In the field of medical health monitoring, the millimeter wave radar has been widely concerned due to its non-contact detection mode. The D-type personality (Distressed Personality Type) is a psychological trait, and its core features include persistent negative emotions and social inhibition. The D-type personality has important significance in the medical field, especially in the research and treatment of coronary heart disease. Disease prognosis refers to the prediction of the future development and outcome of a disease, such as recovery, recurrence, deterioration, disability, complications and death. Studies have shown that individuals with D-type personality traits are more likely to suffer from coronary heart disease, and their mortality rate is significantly higher than that of other types of personality. Early identification and intervention of the D-type personality are crucial for improving the prognosis of patients with coronary heart disease and improving the overall treatment effect.

[0003] In the prior art, clinicians pay more and more attention to the assessment of the D-type personality of patients with coronary heart disease in order to identify high-risk patients as soon as possible and reduce the mortality rate and the incidence of complications. However, in the existing medical and psychological field, the D-type personality is usually assessed by using the DS16 scale (Distress Scale 16), which relies on the manual operation of patients with coronary heart disease and doctors. That is, the D-type personality prediction in the prior art has the technical problems of high labor cost and time cost and insufficient prediction accuracy. SUMMARY

[0004] In order to make up for the defects of the prior art, the application provides a D-type personality prediction method and system based on a millimeter wave radar. Compared with the prior art, the application can greatly improve the accuracy of D-type personality prediction and save labor and time cost by applying technical means such as a millimeter wave radar.

[0005] In order to solve the above technical problems, the technical scheme adopted by the application is as follows:

[0006] In a first aspect, a D-type personality prediction method based on a millimeter wave radar is provided, comprising:

[0007] When the target patient is diagnosed with coronary heart disease, the millimeter wave radar is used to collect the heart rate variability (HRV) data of the target patient, and the HRV data is subjected to short-term frequency domain analysis to obtain the frequency domain index parameters of the target patient.

[0008] Predict whether the target patient has a Type D personality based on a pre-set Type D personality prediction algorithm and frequency domain index parameters;

[0009] If the target patient is a Type D personality, then the prognosis of coronary heart disease for the target patient will be determined according to the Type D personality.

[0010] Furthermore, millimeter-wave radar is used to collect human heart rate variability (HRV) data from the target patient. Short-time frequency domain analysis is performed on the HRV data to obtain the frequency domain index parameters of the target patient, including the following steps:

[0011] The target patient was brought into a resting state, and millimeter-wave radar was used to detect and record the HRV data of the target patient in the resting state. x1 , x1 Indicates a resting state;

[0012] Using regression or fast Fourier transform, HRV was analyzed. x1 Short-time frequency domain analysis was performed to obtain the frequency domain parameters of the target patient in the resting state. The frequency domain parameters include the total power (TP) in the resting state. x1 Very low frequency band power VLF x1 Low-frequency power LF x1 High-frequency band power HF x1 Low frequency / high frequency ratio Normalized low-frequency power (LFnorm) x1 and normalized high-frequency band power HFnorm x1 Normalized low-frequency power Normalized high-frequency band power

[0013] Furthermore, based on a pre-set Type D personality prediction algorithm and frequency domain index parameters, it is predicted whether the target patient has Type D personality, including:

[0014] The calculation formula for the preset Type D personality prediction algorithm in a resting state is as follows:

[0015] Type D personality predictor S x1 =(TP) x1 -TP1)+(VLF x1 -VLF1)+(LF x1 -LF1);

[0016] TP1 represents the average total power of a large number of non-Type D personality patients under resting conditions;

[0017] VLF1 represents the average extremely low frequency power of a large number of non-Type D personality patients under resting conditions;

[0018] LF1 represents the average low-frequency power of a large number of non-Type D personality patients under resting conditions;

[0019] When S x1 ≥ 0, it is determined that the target patient in the resting state is a non-D type personality;

[0020] When S x1 < 0 and (TP x1 - TP1) < 0, (VLF x1 - VLF1) < 0, and (LF x1 - LF1) < 0, it is determined that the target patient in the resting state is a D type personality.

[0021] Further, after determining that the target patient in the resting state is a non-D type personality, the method further comprises the steps of:

[0022] Adjusting the target patient to enter an abdominal breathing state, and using the millimeter wave radar to detect and record the HRV data HRV x2 of the target patient in the abdominal breathing state, x2 indicating the abdominal breathing state;

[0023] Using a regression method or a fast Fourier transform method to perform a short-term frequency domain analysis on the HRV x2 , to obtain frequency domain index parameters of the target patient in the abdominal breathing state, the frequency domain index parameters including total power TP x2 , very low frequency band power VLF x2 , low frequency band power LF x2 , high frequency band power HF x2 , low frequency / high frequency ratio , normalized low frequency band power LFnorm x2 , and normalized high frequency band power HFnorm x2 , the normalized low frequency band power the normalized high frequency band power

[0024] The calculation formula of the preset D type personality prediction algorithm in the abdominal breathing state is:

[0025] D type personality prediction value S x2 = (TP x2 - TP2) + (HF x2 - HF2);

[0026] TP2 represents the average total power of a large number of non-D type personality patients in the abdominal breathing state, and HF2 represents the average high frequency band power of a large number of non-D type personality patients in the abdominal breathing state;

[0027] When S x2 ≥ 0, it is determined that the target patient in the abdominal breathing state is a non-D type personality;

[0028] When Sx2 <0 and (TP x2 <0 and (HF x2 <0, the target patient in abdominal breathing state is determined as type D personality.

[0029] Further, after determining that the target patient in resting state is non-type D personality, the method further comprises the steps of:

[0030] adjusting the target patient to enter a resting post-stress state, detecting and recording HRV data of the target patient in the resting post-stress state using the millimeter wave radar, x3 x3 indicating the resting post-stress state;

[0031] using regression method or fast Fourier transform method to perform short-term frequency domain analysis on the HRV x3 , to obtain frequency domain index parameters of the target patient in the resting post-stress state, the frequency domain index parameters including total power TP x3 , very low frequency band power VLF x3 , low frequency band power LF x3 , high frequency band power HF x3 , low frequency / high frequency ratio , normalized low frequency band power LFnorm x3 , and normalized high frequency band power HFnorm x3 , the normalized low frequency band power the normalized high frequency band power

[0032] the calculation formula of the preset type D personality prediction algorithm in the resting post-stress state is obtained as:

[0033]

[0034] S x3_2 =(HFnorm3-HFnorm x3 );

[0035] indicating the average low frequency / high frequency ratio of a large number of non-type D personality patients in the resting post-stress state; LFnorm3 indicates the average normalized low frequency band power of a large number of non-type D personality patients in the resting post-stress state; HFnorm3 indicates the average normalized high frequency band power of a large number of non-type D personality patients in the resting post-stress state;

[0036] when S x3_1 <0, and (LFnorm3-LFnorm x3 ) <0, and S x3_2 ​When S > 0, it is determined that the target patient in the passive stress state after rest is a D-type personality;

[0037] When S x3_1 ≥ 0 or S x3_2 ≤ 0, it is determined that the target patient in the passive stress state after rest is a non-D-type personality.

[0038] Further, after determining that the target patient in the abdominal breathing state is a non-D-type personality, the method further comprises the steps of:

[0039] Adjusting the target patient to enter the passive stress state after abdominal breathing, using the millimeter wave radar to detect and record the front HRV data HRV 前 before entering the passive stress state after abdominal breathing, and the rear HRV data HRV 后 after entering the passive stress state after abdominal breathing;

[0040] The change calculation formula of the HRV data before and after is:

[0041] ΔHRV = HRV 后 -HRV 前 ;

[0042] When |ΔHRV| > H, it is determined that the target patient is a D-type personality, and H is a preset threshold;

[0043] When |ΔHRV| ≤ H, it is determined that the target patient is a non-D-type personality.

[0044] Further, the method further comprises:

[0045] When it is determined that the target patient is a D-type personality, obtaining D-type personality test scale information of the target patient;

[0046] If it is inferred from the D-type personality test scale information that the target patient is a D-type personality, the prediction result is accurate;

[0047] If it is inferred from the D-type personality test scale information that the target patient is a non-D-type personality, the prediction result is inaccurate.

[0048] In a second aspect, a D-type personality prediction system based on a millimeter wave radar is provided, comprising

[0049] A data acquisition module is configured to, when the target patient is diagnosed with coronary heart disease, collect human heart rate variability HRV data of the target patient by using a millimeter wave radar, perform short-term frequency domain analysis on the HRV data, and obtain frequency domain index parameters of the target patient;

[0050] A D-type personality prediction module is configured to predict whether the target patient is a D-type personality according to a preset D-type personality prediction algorithm and the frequency domain index parameters;

[0051] A coronary heart disease prognosis module is configured to perform coronary heart disease prognosis on a target patient according to D-type personality if the target patient is of D-type personality.

[0052] Further,

[0053] A data acquisition module is configured to adjust the target patient into a resting state, detect and record HRV data HRV of the target patient in the resting state using a millimeter wave radar. x1 , x1 The resting state is indicated; a regression method or a fast Fourier transform method is used to perform short-term frequency domain analysis on the HRV x1 to obtain frequency domain index parameters of the target patient in the resting state, including total power TP x1 , very low frequency band power VLF x1 , low frequency band power LF x1 , high frequency band power HF x1 , low frequency / high frequency ratio , normalized low frequency band power LFnorm x1 , and normalized high frequency band power HFnorm x1 The normalized low frequency band power The normalized high frequency band power

[0054] A D-type personality prediction module is configured to obtain a preset calculation formula of the D-type personality prediction algorithm in the resting state, as follows:

[0055] The D-type personality prediction value S x1 = (TP x1 - TP1) + (VLF x1 - VLF1) + (LF x1 - LF1);

[0056] TP1 represents the average total power of a large number of non-D-type personality patients in the resting state.

[0057] VLF1 represents the average very low frequency band power of a large number of non-D-type personality patients in the resting state.

[0058] LF1 represents the average low frequency band power of a large number of non-D-type personality patients in the resting state.

[0059] When S x1 ≥ 0, it is determined that the target patient in the resting state is of non-D-type personality.

[0060] When S x1 < 0 and (TP x1 - TP1) < 0, (VLF x1 - VLF1) < 0, and (LF x1When -LF1) < 0, the target patient in the resting state is determined to be a Type D personality.

[0061] Furthermore,

[0062] After determining that the target patient, in a resting state, is not a Type D personality...

[0063] The data acquisition module is also used to adjust the target patient into a diaphragmatic breathing state, and to use millimeter-wave radar to detect and record the target patient's HRV data under diaphragmatic breathing conditions. x2 , x2 Indicates diaphragmatic breathing state; uses regression or fast Fourier transform method to analyze HRV. x2 Short-term frequency domain analysis was performed to obtain the frequency domain parameters of the target patient under abdominal breathing conditions. The frequency domain parameters include the total power (TP) under abdominal breathing conditions. x2 Very low frequency band power VLF x2 Low-frequency power LF x2 High frequency band power HF x2 Low frequency / high frequency ratio Normalized low-frequency power LFnorm x2 and normalized high-frequency band power HFnorm x2 Normalized low-frequency power Normalized high-frequency band power

[0064] The Type D personality prediction module also uses the calculation formula of the preset Type D personality prediction algorithm under diaphragmatic breathing state as follows:

[0065] Type D personality predictor S x2 =(TP) x2 -TP2)+(HF x2 -HF2);

[0066] TP2 represents the average total power of a large number of non-Type D personality patients under diaphragmatic breathing conditions, and HF2 represents the average high-frequency band power of a large number of non-Type D personality patients under diaphragmatic breathing conditions.

[0067] When S x2 When ≥0, the target patient is determined to be a non-Type D personality under abdominal breathing conditions;

[0068] When S x2 <0 and (TP) x2 -TP2)<0 and (HF x2 When -HF2) < 0, the target patient is determined to be a Type D personality under abdominal breathing state;

[0069] After determining that the target patient, in a resting state, is not a Type D personality...

[0070] The data acquisition module is also used to adjust the target patient into a passive stress state after resting, and to use millimeter-wave radar to detect and record the target patient's HRV data under the passive stress state after resting. x3 , x3 This indicates the passive stress state after rest; regression or fast Fourier transform methods are used to analyze HRV. x3 Short-term frequency domain analysis was performed to obtain the frequency domain parameters of the target patient under passive stress after rest. The frequency domain parameters include the total power (TP) under passive stress after rest. x3 Very low frequency band power VLF x3 Low-frequency power LF x3 High-frequency band power HF x3 Low frequency / high frequency ratio Normalized low-frequency power (LFnorm) x3 and normalized high-frequency band power HFnorm x3 Normalized low-frequency power Normalized high-frequency band power

[0071] The Type D personality prediction module also uses the preset calculation formula of the Type D personality prediction algorithm to obtain the results under passive stress after rest:

[0072]

[0073] S x3_2 =(HFnorm3-HFnorm) x3 );

[0074] LFnorm3 represents the average low-frequency / high-frequency ratio of a large number of non-Type D personality patients under passive stress after rest; LFnorm3 represents the average normalized low-frequency power of a large number of non-Type D personality patients under passive stress after rest; HFnorm3 represents the average normalized high-frequency power of a large number of non-Type D personality patients under passive stress after rest.

[0075] When S x31 <0、 and (LFnorm3-LFnorm) x3 ) < 0, and S x3_2 When the value is >0, the target patient under passive stress after rest is determined to be a Type D personality;

[0076] When S x3_1 ≥0 or S x3_2 When the value is ≤0, the target patient under passive stress after rest is determined to be a non-Type D personality.

[0077] The beneficial effects achieved by this invention are as follows:

[0078] When a target patient is diagnosed with coronary heart disease, millimeter-wave radar is used to collect the patient's heart rate variability (HRV) data. Short-term frequency domain analysis is performed on the HRV data to obtain the target patient's frequency domain index parameters. Based on a pre-set Type D personality prediction algorithm and the frequency domain index parameters, it is predicted whether the target patient has a Type D personality. If the target patient has a Type D personality, the prognosis for coronary heart disease is assessed according to this personality type. Millimeter-wave radar enables non-contact HRV data collection from coronary heart disease patients, and short-term frequency domain analysis yields frequency domain index parameters for Type D personality prediction, thus achieving Type D personality prediction. Compared to existing scale assessments, this method has higher accuracy and overcomes the high labor and time costs associated with existing technologies for Type D personality prediction. Compared to existing technologies, the application of millimeter-wave radar and other technologies can significantly improve the accuracy of Type D personality prediction while saving labor and time costs. Attached Figure Description

[0079] Figure 1 This is a flowchart of the D-type personality prediction method based on millimeter-wave radar of the present invention;

[0080] Figure 2 The procedure for detecting HRV data during rest;

[0081] Figure 3 The procedure for detecting HRV data during diaphragmatic breathing;

[0082] Figure 4 The procedure for detecting HRV data under passive stress after rest;

[0083] Figure 5 The procedure for detecting HRV data under passive stress after abdominal breathing;

[0084] Figure 6 This is a structural diagram of the D-type personality prediction system based on millimeter-wave radar of the present invention. Detailed Implementation

[0085] The present invention will be further described below with reference to the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present invention, and should not be used to limit the scope of protection of the present invention.

[0086] like Figure 1 As shown, this embodiment of the invention provides a method for predicting Type D personality based on millimeter-wave radar, including:

[0087] 101. When a target patient is diagnosed with coronary heart disease, millimeter-wave radar is used to collect the target patient's HRV data, and short-time frequency domain analysis is performed on the HRV data to obtain the target patient's frequency domain index parameters.

[0088] Millimeter-wave radar is a device that utilizes electromagnetic wave frequencies in the millimeter-wave band. It can transmit electromagnetic waves towards a target and receive the electromagnetic waves reflected back from the target. When electromagnetic waves encounter a moving object, their frequency changes due to the Doppler effect. By precisely analyzing this frequency change, i.e., the Doppler shift, millimeter-wave radar can detect and measure the speed and direction of movement of the target object. Similarly, the human heartbeat is accompanied by subtle movements of the chest cavity. Radar utilizes the time-varying Doppler effect of frequency-modulated continuous waves under these subtle chest movements to extract and analyze the frequency domain signal of the human heart rate variability.

[0089] When performing HRV data testing, there are usually four situations: the first is in the resting state, the second is in the diaphragmatic breathing state, the third is in the passive stress state after rest, and the fourth is in the passive stress state after diaphragmatic breathing.

[0090] like Figure 2 The following is the testing procedure under rest conditions: The target patient is asked to lean back in a high-backed chair with armrests and rest with their eyes closed for ten minutes. Then, millimeter-wave radar is used to detect and record HRV data. After resting for five minutes, the HRV data is recorded a second time.

[0091] like Figure 3 The following is the detection procedure under diaphragmatic breathing: Ask the target patient to lean back in a high-backed chair with armrests and rest with their eyes closed for ten minutes. Instruct the target patient to practice diaphragmatic breathing at a rate of seven times per minute. After practicing for one minute, ask the target patient to perform deep diaphragmatic breathing for five minutes. Use millimeter-wave radar to detect and record HRV data. After resting for five minutes, repeat the above steps to record the HRV data for the second time.

[0092] like Figure 4 The following is the detection procedure under passive stress after rest: The target patient is asked to lean back in a high-backed chair with armrests and rest with their eyes closed for ten minutes. The target patient is asked to watch a video material that induces sadness for five minutes. The HRV data is detected and recorded using millimeter-wave radar. After resting for five minutes, the above steps are repeated, the sad emotion-inducing video material is changed, and the HRV data is recorded a second time.

[0093] like Figure 5 The following is the detection procedure under passive stress after abdominal breathing: The target patient is asked to lean back in a high-backed chair with armrests and rest with their eyes closed for ten minutes. The target patient is instructed to practice abdominal breathing at seven times per minute. After practicing for one minute, the target patient is asked to perform deep abdominal breathing for five minutes. The target patient is asked to watch a video material that induces sadness for five minutes. The HRV data is detected and recorded using millimeter-wave radar. After resting for five minutes, the above steps are repeated, the sad emotion-inducing video material is changed, and the HRV data is recorded a second time.

[0094] Based on the aboveFigures 2-5 The step-by-step changes of the four states can be known that the abdominal breathing state is further deepening of the resting state, the passive stress state after rest is further deepening of the resting state, and the passive stress state after abdominal breathing is further deepening of the abdominal breathing state. Therefore, when predicting the D-type personality, the step-by-step changes of the four states can be used for step-by-step deepening.

[0095] By using the characteristics of the above millimeter wave radar, the target patient is adjusted to enter the resting state, and the millimeter wave radar is used to detect and record the HRV data HRV of the target patient in the resting state. x1 , x1 indicates the resting state;

[0096] The regression method or fast Fourier transform method is used to perform short-term frequency domain analysis on the HRV data, that is, the HRV data is divided into multiple frequency bands; high frequency band (HF): 0.15-0.4 Hz, reflecting the tension of the parasympathetic nerve; low frequency band (LF): 0.04-0.15 Hz, reflecting the common action of the sympathetic and parasympathetic nerves, mainly sympathetic; very low frequency band (VLF): 0.0033-0.04 Hz; total power (TP): ≤0.4 Hz.

[0097] The power spectrum with frequency as the abscissa and power spectral density PSD as the ordinate, the ordinate unit is ms 2 / Hz;

[0098] The normal value range of the power spectrum recorded for 5 minutes in the supine position is:

[0099] TP: 3466±1018 ms 2 / Hz;

[0100] LF: 1170±416 ms 2 / Hz;

[0101] LFnorm: 54±4 nu;

[0102] HF: 975±203 ms 2 / Hz;

[0103] HFnorm: 29±3 nu;

[0104] LF / HF: 1.5-2.0.

[0105] The frequency domain index parameters of the target patient in the resting state include the total power TP x1 , very low frequency band power VLF x1 , low frequency band power LF x1 , high frequency band power HF x1 , low frequency / high frequency ratio ,

[0106] normalized low frequency band power LFnorm x1 and normalized high frequency band power HFnorm x1 , normalized low frequency band power normalized high frequency band power

[0107] 102, according to the preset D-type personality prediction algorithm and the frequency domain index parameter, whether the target patient is a D-type personality is predicted;

[0108] (I) the calculation formula of the preset D-type personality prediction algorithm in the resting state is obtained as follows:

[0109] D-type personality prediction value S x1 = (TP x1 - TP1) + (VLF x1 - VLF1) + (LF x1 - LF1);

[0110] TP1 represents the average total power of a large number of non-D-type personality patients in the resting state;

[0111] VLF1 represents the average very low frequency band power of a large number of non-D-type personality patients in the resting state;

[0112] LF1 represents the average low frequency band power of a large number of non-D-type personality patients in the resting state;

[0113] Since the D-type personality is lower than the non-D-type personality in terms of TP, VLF and LF according to the existing known test parameters, the sympathetic nervous excitability of the D-type personality is lower than that of the non-D-type personality in the resting state, and the HRV is also lower;

[0114] When S x1 ≥ 0, it indicates that one or more of TP x1 , VLF x1 , and LF x1 of the target patient is higher than that of the non-D-type personality, so that the target patient can be determined as a non-D-type personality in the resting state;

[0115] When S x1 < 0 and (TP x1 - TP1) < 0, (VLF x1 - VLF1) < 0, and (LF x1 - LF1) < 0, the target patient is a D-type personality in the resting state.

[0116] (II) after it is determined in (I) above that the target patient is a non-D-type personality in the resting state, it may be that TP x1 , VLF x1, LF x1 There is data loss, confusion, resulting in D personality prediction is not accurate, so you need to further add the diaphragmatic breathing state to predict:

[0117] Adjust the target patient into the diaphragmatic breathing state, use millimeter wave radar to detect and record the HRV data of the target patient in the diaphragmatic breathing state HRV x2 , x2 Indicates the diaphragmatic breathing state;

[0118] Using regression method or fast Fourier transform method, short-term frequency domain analysis is carried out on HRV x2 , the frequency domain index parameters of the target patient in the diaphragmatic breathing state are obtained, the frequency domain index parameters include total power TP x2 , very low frequency band power VLF x2 , low frequency band power LF x2 , high frequency band power HF x2 , low frequency / high frequency ratio , normalized low frequency band power LFnorm x2 and normalized high frequency band power HFnorm x2 , normalized low frequency band power , normalized high frequency band power

[0119] The calculation formula of the preset D personality prediction algorithm in the diaphragmatic breathing state is:

[0120] D personality prediction value S x2 =(TP x2 -TP2)+(HF x2 -HF2);

[0121] TP2 represents the average total power of a large number of non-D personality patients in the diaphragmatic breathing state, and HF2 represents the average high frequency band power of a large number of non-D personality patients in the diaphragmatic breathing state.

[0122] According to the existing known test parameters, in the diaphragmatic breathing state, the D personality is lower than the non-D personality in terms of TP and HF.

[0123] When S x2 ≥0, it indicates that one or both of TP x2 and HF x2 of the target patient are higher than the non-D personality, so the target patient is determined as a non-D personality in the diaphragmatic breathing state.

[0124] When S x2 <0 and (TP x2 -TP2)<0 and (HF x2When HF2) < 0, the target patient in the abdominal breathing state is characterized by D-type personality, and it is determined that the target patient is D-type personality.

[0125] (Three) After determining that the target patient in the abdominal breathing state is non-D-type personality in the above (two), it is possible that TP x2 , VLF x2 , and LF 前 exist data loss or disorder, resulting in inaccurate prediction of D-type personality, so it is necessary to further add passive stress state after abdominal breathing for prediction.

[0126] Adjust the target patient to enter the passive stress state after abdominal breathing, use millimeter wave radar to detect and record the HRV data HRV 后 before entering the passive stress state after abdominal breathing, and the HRV data HRV 后 after entering the passive stress state after abdominal breathing.

[0127] The change calculation formula of HRV data before and after is:

[0128] ΔHRV = HRV 前 - HRV x1 ;

[0129] According to the existing known test parameters, the subjects of D-type personality have a larger heart rate change before and after watching the video in the passive stress state under the abdominal breathing state; then the pre-set threshold H of the change before and after is set in advance.

[0130] When |ΔHRV| > H, the target patient is determined to be D-type personality.

[0131] When |ΔHRV| ≤ H, the target patient is determined to be non-D-type personality.

[0132] (Four) After determining that the target patient in the resting state is non-D-type personality in the above (one), it is possible that TP x1 , VLF x1 , and LF x3 exist data loss or disorder, resulting in inaccurate prediction of D-type personality, so it is necessary to further add passive stress state for prediction.

[0133] Adjust the target patient to enter the passive stress state after resting, use millimeter wave radar to detect and record the HRV data HRV x3 of the target patient in the passive stress state after resting.

[0134] Use regression method or fast Fourier transform method to process HRV x3A short-term frequency domain analysis is performed to obtain the frequency domain index parameters of the target patient in the resting passive stress state, and the frequency domain index parameters include total power TP in the resting passive stress state x3 , very low frequency band power VLF x3 , low frequency band power LF x3 , high frequency band power HF x3 , low frequency / high frequency ratio , normalized low frequency band power LFnorm x3 , and normalized high frequency band power HFnorm x3 , normalized low frequency band power , and normalized high frequency band power

[0135] The calculation formula of the preset D-type personality prediction algorithm in the resting passive stress state is obtained as follows:

[0136]

[0137] S x3_2 =(HFnorm3-HFnorm x3 )

[0138] LFnorm3 represents the average normalized low frequency band power of a large number of non-D-type personality patients in the resting passive stress state; and HFnorm3 represents the average normalized high frequency band power of a large number of non-D-type personality patients in the resting passive stress state.

[0139] According to the existing known test parameters, the LF / HF and LFnorm of the D-type personality tester are higher than those of the non-D-type personality tester, and the HFnorm of the D-type personality tester is lower than that of the non-D-type personality tester when watching a sad emotion-inducing video in the resting state and performing passive stress state testing.

[0140] When S x3_1 < 0, and (LFnorm3-LFnorm x3 ) < 0, and S x3_2 > 0, it is determined that the target patient in the resting passive stress state is a D-type personality.

[0141] When S x3_1 ≥ 0 or S x3_2 ≤ 0, it is determined that the target patient in the resting passive stress state is a non-D-type personality.

[0142] 103. The target patient is diagnosed with coronary heart disease according to the D-type personality.

[0143] When the target patient is determined to be a D-type personality, D-type personality test scale information of the target patient is acquired;

[0144] If it is inferred from the D-type personality test scale information that the target patient is not a D-type personality, the prediction result is inaccurate;

[0145] If it is inferred from the D-type personality test scale information that the target patient is a D-type personality, the prediction result is accurate;

[0146] After determining that the target patient is a D-type personality, coronary heart disease prognosis is performed according to the D-type personality.

[0147] The implementation principle of the embodiment of the present application is:

[0148] When the target patient is diagnosed with coronary heart disease, the human heart rate variability HRV data of the target patient is collected by using a millimeter wave radar, the HRV data is subjected to short-term frequency domain analysis, and the frequency domain index parameter of the target patient is obtained; whether the target patient is a D-type personality is predicted according to a preset D-type personality prediction algorithm and the frequency domain index parameter; if the target patient is a D-type personality, the coronary heart disease prognosis of the target patient is performed according to the D-type personality. The HRV data of the coronary heart disease patient is collected in a non-contact manner by using the millimeter wave radar, and the frequency domain index parameter used for D-type personality prediction is obtained after the short-term frequency domain analysis of the HRV data, so that the prediction of the D-type personality is realized. Compared with the existing scale evaluation, the accuracy is higher, and the coronary heart disease prognosis of the D-type personality patient can be effectively improved.

[0149] In combination with the D-type personality prediction method based on the millimeter wave radar described in the above embodiments, the D-type personality prediction system based on the millimeter wave radar is described below through embodiments.

[0150] As shown in Figure 6 The embodiment of the present application provides a D-type personality prediction system based on a millimeter wave radar, which comprises:

[0151] The data acquisition module 601 is configured to, when the target patient is diagnosed with coronary heart disease, collect the human heart rate variability HRV data of the target patient by using a millimeter wave radar, perform short-term frequency domain analysis on the HRV data, and obtain the frequency domain index parameter of the target patient.

[0152] The D-type personality prediction module 602 is configured to predict whether the target patient is a D-type personality according to a preset D-type personality prediction algorithm and the frequency domain index parameter.

[0153] The coronary heart disease prognosis module 603 is configured to, if the target patient is a D-type personality, perform coronary heart disease prognosis of the target patient according to the D-type personality.

[0154] In combination with Figure 6In the illustrated embodiment, some preferred embodiments of the present application,

[0155] The data acquisition module 601 is specifically configured to adjust the target patient into a resting state, detect and record the HRV data HRV of the target patient in the resting state using the millimeter wave radar x1 , x1 indicates the resting state; the regression method or the fast Fourier transform method is adopted to perform short-term frequency domain analysis on the HRV x1 to obtain frequency domain index parameters of the target patient in the resting state, the frequency domain index parameters including total power TP x1 , very low frequency band power VLF x1 , low frequency band power LF x1 , high frequency band power HF x1 , low frequency / high frequency ratio , normalized low frequency band power LFnorm x1 , and normalized high frequency band power HFnorm x1 , normalized low frequency band power , and normalized high frequency band power

[0156] The D-type personality prediction module 602 is specifically configured to obtain a preset calculation formula of the D-type personality prediction algorithm in the resting state, as follows:

[0157] The D-type personality prediction value S x1 = (TP x1 - TP1) + (VLF x1 - VLF1) + (LF x1 - LF1);

[0158] TP1 represents the average total power of a large number of non-D-type personality patients in the resting state;

[0159] VLF1 represents the average very low frequency band power of a large number of non-D-type personality patients in the resting state;

[0160] LF1 represents the average low frequency band power of a large number of non-D-type personality patients in the resting state;

[0161] When S x1 ≥ 0, it is determined that the target patient in the resting state is a non-D-type personality;

[0162] When S x1 < 0 and (TP x1 - TP1) < 0, (VLF x1 - VLF1) < 0, and (LF x1 - LF1) < 0, it is determined that the target patient in the resting state is a D-type personality.

[0163] In combinationFigure 6 In the embodiments shown, and in some preferred embodiments of the present invention, after determining that the target patient in the resting state is not a Type D personality,

[0164] The data acquisition module 601 is also used to adjust the target patient into a diaphragmatic breathing state, and to use millimeter-wave radar to detect and record the target patient's HRV data under the diaphragmatic breathing state. x2 , x2 Indicates diaphragmatic breathing state; uses regression or fast Fourier transform method to analyze HRV. x2 Short-term frequency domain analysis was performed to obtain the frequency domain parameters of the target patient under abdominal breathing conditions. The frequency domain parameters include the total power (TP) under abdominal breathing conditions. x2 Very low frequency band power VLF x2 Low-frequency power LF x2 High-frequency band power HF x2 Low frequency / high frequency ratio Normalized low-frequency power (LFnorm) x2 and normalized high-frequency band power HFnorm x2 Normalized low-frequency power Normalized high-frequency band power

[0165] The Type D personality prediction module 602 is also used to obtain the calculation formula of the preset Type D personality prediction algorithm under diaphragmatic breathing state:

[0166] Type D personality predictor S x2 =(TP) x2 -TP2)+(HF x2 -HF2);

[0167] TP2 represents the average total power of a large number of non-Type D personality patients under diaphragmatic breathing conditions, and HF2 represents the average high-frequency band power of a large number of non-Type D personality patients under diaphragmatic breathing conditions.

[0168] When S x2 When ≥0, the target patient is determined to be a non-Type D personality under abdominal breathing conditions;

[0169] When S x2 <0 and (TP) x2 -TP2)<0 and (HF) x2 When -HF2) < 0, the target patient is determined to be a Type D personality under abdominal breathing state;

[0170] Combination Figure 6 In the embodiments shown, and in some preferred embodiments of the present invention, after determining that the target patient in the resting state is not a Type D personality,

[0171] The data acquisition module 601 is further configured to adjust the target patient to enter a resting post-stress state, detect and record the HRV data of the target patient in the resting post-stress state using the millimeter wave radar x3 , x3 represents the resting post-stress state; the regression method or the fast Fourier transform method is used to perform short-term frequency domain analysis on the HRV x3 , to obtain the frequency domain index parameters of the target patient in the resting post-stress state, the frequency domain index parameters including total power TP x3 , very low frequency band power VLF x3 , low frequency band power LF x3 , high frequency band power HF x3 , low frequency / high frequency ratio , normalized low frequency band power LFnorm x3 , and normalized high frequency band power HFnorm x3 , the normalized low frequency band power , and the normalized high frequency band power

[0172] The D-type personality prediction module 602 is further configured to obtain a preset calculation formula of the D-type personality prediction algorithm in the resting post-stress state, as follows:

[0173]

[0174] S x3_2 =(HFnorm3-HFnorm x3 );

[0175] represents the average low frequency / high frequency ratio of a large number of non-D-type personality patients in the resting post-stress state; LFnorm3 represents the average normalized low frequency band power of a large number of non-D-type personality patients in the resting post-stress state; and HFnorm3 represents the average normalized high frequency band power of a large number of non-D-type personality patients in the resting post-stress state.

[0176] When S x3_1 < 0, and (LFnorm3-LFnorm x3 ) < 0, and S x3_2 > 0, it is determined that the target patient in the resting post-stress state is a D-type personality.

[0177] When S x3_1 ≥ 0 or S x3_2 ≤ 0, it is determined that the target patient in the resting post-stress state is a non-D-type personality.

[0178] Those skilled in the art will appreciate that embodiments of the present application can be readily used as a method, a system or a computer program product. Accordingly, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application can take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage devices, etc.) embodying computer readable program code.

[0179] The present application is described in reference to the flowchart and / or block diagrams of the method, apparatus (system) and computer program product according to embodiments of the application. It will be understood that each block of the flowchart and / or block diagrams, and combinations of blocks in the flowchart and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, embedded processing system or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart and / or block diagram block or blocks. Figure 1 one or more functions specified in the flowchart and / or block diagram block or blocks. Figure 1 one or more functions specified in the flowchart and / or block diagram block or blocks.

[0180] These computer program instructions can also be stored in a computer- readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the flowchart and / or block diagram block or blocks. Figure 1 one or more functions specified in the flowchart and / or block diagram block or blocks. Figure 1 one or more functions specified in the flowchart and / or block diagram block or blocks.

[0181] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the flowchart and / or block diagram block or blocks. Figure 1 one or more functions specified in the flowchart and / or block diagram block or blocks. Figure 1 one or more functions specified in the flowchart and / or block diagram block or blocks.

[0182] The foregoing is merely illustrative of the principles of the application and various modifications can be made by persons skilled in the art without departing from the scope and nature of the application as disclosed in the specification and the appended claims.

Claims

1. A method of predicting D-type personality based on millimeter wave radar, characterized by, The method comprises the following steps: Adjusting a target patient into a resting state, using millimeter wave radar to detect and record HRV data of the target patient in the resting state , the indicates a resting state; the target patient is a patient with confirmed coronary heart disease; Using regression or fast Fourier transform, the above methods are applied to the... Short-time frequency domain analysis was performed to obtain the frequency domain index parameters of the target patient in the resting state. These frequency domain index parameters included the total power in the resting state. Extremely low frequency power Low-frequency power High-frequency power Low frequency / high frequency ratio Normalized low-frequency power and normalized high-frequency band power The normalized low-frequency power The normalized high-frequency band power ; If the target patient is a D-type personality, the target patient is subjected to coronary heart disease prognosis according to the D-type personality; The method further comprises the following steps: The calculation formula of the preset D-type personality prediction algorithm in the resting state is: After determining that the target patient is a non-D-type personality in the resting state, the method further comprises the following steps: D-type personality prediction value ; The represents the average total power of a statistically large number of non-Type D personality patients at rest; The represents the average very low frequency band power of a large number of non-type D personality patients in a resting state; The represents the average low frequency band power of a large number of non-type D personality patients in a resting state; when the target patient is determined to be in the resting state, and a D-type personality; and when the target patient is determined to be in the resting state, and a D-type personality. when the target patient is in the resting state and the target patient is in the resting state , the target patient is in the resting state and the target patient is in the resting state , the target patient is in the resting state 2.The D-type personality prediction method based on millimeter wave radar according to claim 1, characterized in that, The calculation formula of the preset D-type personality prediction algorithm in the abdominal breathing state is: adjusting the target patient to enter a diaphragmatic breathing state, detecting and recording HRV data of the target patient in the diaphragmatic breathing state using millimeter wave radar , the indicates a diaphragmatic breathing state; Using regression or fast Fourier transform, the above methods are applied to the... Short-term frequency domain analysis was performed to obtain the frequency domain index parameters of the target patient under abdominal breathing conditions. These frequency domain index parameters include the total power under abdominal breathing conditions. Extremely low frequency power Low-frequency power High-frequency power Low frequency / high frequency ratio Normalized low-frequency power and normalized high-frequency band power The normalized low-frequency power The normalized high-frequency band power ; After determining that the target patient is a non-D-type personality in the resting state, the method further comprises the following steps: D-type personality prediction value ; The represents the average total power of a statistically large number of non- Type D personality patients in a diaphragmatic breathing state, and the represents the average high-frequency band power of a statistically large number of non- Type D personality patients in a diaphragmatic breathing state. when the target patient is determined to be a D-type personality in the diaphragmatic breathing state, outputting a result of the determination; and when the target patient is determined to be a D-type personality in the diaphragmatic breathing state, outputting a result of the determination when the target patient is in the diaphragmatic breathing state and the target patient is in the diaphragmatic breathing state and the target patient is in the diaphragmatic breathing state and the target patient is in the diaphragmatic breathing state 3.The D-type personality prediction method based on millimeter wave radar according to claim 1, characterized in that, After determining that the target patient is a non-D-type personality in the abdominal breathing state, the method further comprises the following steps: adjusting the target patient into a post-rest passive stress state, detecting and recording HRV data of the target patient in the post-rest passive stress state using millimeter wave radar , the post-rest passive stress state Using regression or fast Fourier transform, the above methods are applied to the... Short-term frequency domain analysis was performed to obtain the frequency domain index parameters of the target patient under passive stress after rest. These frequency domain index parameters include the total power under passive stress after rest. Extremely low frequency power Low-frequency power High-frequency power Low frequency / high frequency ratio Normalized low-frequency power and normalized high-frequency band power The normalized low-frequency power The normalized high-frequency band power ; The preset D-type personality prediction algorithm calculation formula under the passive stress state after rest is obtained as: ; ； said represents the average low / high frequency ratio of a statistically large number of non- Type D personality patients in the passive stress state after rest; said represents the average normalized low frequency band power of a statistically large number of non- Type D personality patients in the passive stress state after rest; said represents the average normalized high frequency band power of a statistically large number of non- Type D personality patients in the passive stress state after rest; when said , said , and said , and said , it is determined that said target patient is a Type D personality in a passive stress state after rest. when said or said determining that the target patient is non-type D personality in a passive stress state after the rest. 4.The D-type personality prediction method based on millimeter wave radar according to claim 2, characterized in that, The HRV data before and after change calculation formula is: adjusting the target patient into a passive stress state after diaphragmatic breathing, detecting and recording the pre-HRV data before entering the passive stress state after diaphragmatic breathing using millimeter wave radar , and the post-HRV data after entering the passive stress state after diaphragmatic breathing ; The method further comprises the following steps: ； When the At that time, the target patient was determined to be a Type D personality. H The preset threshold; When the personality type. 5.The D-type personality prediction method based on millimeter wave radar according to any one of claims 1-4, characterized in that, After determining that the target patient is a D-type personality, the D-type personality test scale information of the target patient is obtained; If it is inferred from the D-type personality test scale information that the target patient is a D-type personality, the prediction result is accurate; If it is inferred from the D-type personality test scale information that the target patient is a non-D-type personality, the prediction result is inaccurate. The method comprises the following steps: 6.A D-type personality prediction system based on millimeter wave radar, characterized by The D-type personality prediction module is configured to predict whether the target patient is a D-type personality according to a preset D-type personality prediction algorithm and the frequency domain index parameter; A data acquisition module is configured to adjust a target patient into a resting state, detect and record HRV data of the target patient in the resting state using a millimeter wave radar , wherein the target patient is a patient diagnosed with coronary heart disease , and the resting state is represented by a resting symbol The HRV data is subjected to short-term frequency domain analysis using a regression method or a fast Fourier transform method to obtain frequency domain index parameters of the target patient in the resting state, including total power , very low frequency band power , low frequency band power , high frequency band power , low frequency / high frequency ratio , normalized low frequency band power , and normalized high frequency band power , wherein the normalized low frequency band power , and the normalized high frequency band power ​ The coronary heart disease prognosis module is configured to subject the target patient to coronary heart disease prognosis according to the D-type personality if the target patient is a D-type personality; The D-type personality prediction module is specifically configured to obtain a calculation formula of the preset D-type personality prediction algorithm in the resting state as follows: After determining that the target patient is a non-D-type personality in the resting state, D-type personality prediction value ; The represents the average total power of a statistical large number of non-type D personality patients in a resting state; The represents the average very low frequency band power of a statistically large number of non-Type D personality patients in a resting state; The represents the average low frequency band power of a large number of non-type D personality patients in a resting state; when the target patient is determined to be in the resting state, and a D-type personality; and when the target patient is determined to be in the resting state, and a D-type personality. When the And the The above and the aforementioned At that time, the target patient in the resting state was determined to be a Type D personality.

7. The millimeter-wave radar-based Type D personality prediction system of claim 6, wherein, The D-type personality prediction module is further configured to obtain a calculation formula of the preset D-type personality prediction algorithm in the abdominal breathing state as follows: The data acquisition module is further configured to adjust the target patient to enter an abdominal breathing state, detect and record HRV data of the target patient in the abdominal breathing state using a millimeter wave radar , the indicates the abdominal breathing state; short-term frequency domain analysis is performed on the by using a regression method or a fast Fourier transform method to obtain frequency domain index parameters of the target patient in the abdominal breathing state, the frequency domain index parameters including total power , very low frequency band power , low frequency band power , high frequency band power , low frequency / high frequency ratio , normalized low frequency band power , and normalized high frequency band power , the normalized low frequency band power , and the normalized high frequency band power ; After determining that the target patient is a non-D-type personality in the resting state, D-type personality prediction value ; The represents the average total power of a statistically large number of non- Type D personality patients in a diaphragmatic breathing state, and represents the average high frequency band power of a statistically large number of non- Type D personality patients in a diaphragmatic breathing state. when the determining that the target patient is not a type D personality when in a diaphragmatic breathing state; when the target patient is in the diaphragmatic breathing state and the target patient is in the diaphragmatic breathing state and the target patient is in the diaphragmatic breathing state determining that the target patient is a type D personality in the diaphragmatic breathing state ​ The data acquisition module is also used to adjust the target patient into a passive stress state after resting, and to use millimeter-wave radar to detect and record the target patient's HRV data in the passive stress state after resting. The This indicates a passive stress state after rest; regression or fast Fourier transform methods are used to analyze the... Short-term frequency domain analysis was performed to obtain the frequency domain index parameters of the target patient under passive stress after rest. These frequency domain index parameters include the total power under passive stress after rest. Extremely low frequency power Low-frequency power High-frequency power Low frequency / high frequency ratio Normalized low-frequency power and normalized high-frequency band power The normalized low-frequency power The normalized high-frequency band power ; The D-type personality prediction module is further configured to obtain a preset calculation formula of the D-type personality prediction algorithm in a passive stress state after rest, and the calculation formula is as follows: ; ； The represents the average low / high frequency ratio of a statistically large number of non- Type D personality patients in a passive stress state after rest; the represents the average normalized low frequency band power of a statistically large number of non- Type D personality patients in a passive stress state after rest; The represents the average normalized high frequency band power of a statistically large number of non-type D personality patients under passive stress after rest; when said , said , and said , and said , it is determined that the target patient is a Type D personality in a passive stress state after rest; when said or said determining that the target patient is not a Type D personality in a passive stress state after the rest.

Images