CN113842124A - Mental state prediction method, system and equipment based on physiological health indexes - Google Patents
Mental state prediction method, system and equipment based on physiological health indexes Download PDFInfo
- Publication number
- CN113842124A CN113842124A CN202111159498.2A CN202111159498A CN113842124A CN 113842124 A CN113842124 A CN 113842124A CN 202111159498 A CN202111159498 A CN 202111159498A CN 113842124 A CN113842124 A CN 113842124A
- Authority
- CN
- China
- Prior art keywords
- user
- pulse
- mental state
- data
- respiration
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000006996 mental state Effects 0.000 title claims abstract description 47
- 230000036541 health Effects 0.000 title claims abstract description 32
- 238000000034 method Methods 0.000 title claims abstract description 27
- 238000012549 training Methods 0.000 claims abstract description 43
- 238000004458 analytical method Methods 0.000 claims abstract description 20
- 230000029058 respiratory gaseous exchange Effects 0.000 claims description 43
- 238000003062 neural network model Methods 0.000 claims description 29
- 238000012545 processing Methods 0.000 claims description 9
- 238000011156 evaluation Methods 0.000 claims description 8
- 238000013528 artificial neural network Methods 0.000 claims description 6
- 230000000241 respiratory effect Effects 0.000 claims description 6
- 230000036391 respiratory frequency Effects 0.000 claims description 6
- 238000012800 visualization Methods 0.000 claims description 3
- 230000008451 emotion Effects 0.000 abstract description 3
- 239000006185 dispersion Substances 0.000 abstract description 2
- 238000000605 extraction Methods 0.000 abstract 1
- 239000013598 vector Substances 0.000 description 9
- 238000010586 diagram Methods 0.000 description 7
- 238000007405 data analysis Methods 0.000 description 3
- 230000003340 mental effect Effects 0.000 description 3
- 238000007781 pre-processing Methods 0.000 description 3
- 238000001228 spectrum Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 239000002131 composite material Substances 0.000 description 2
- 230000035790 physiological processes and functions Effects 0.000 description 2
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 description 1
- 210000003403 autonomic nervous system Anatomy 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000035565 breathing frequency Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 230000002996 emotional effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000004630 mental health Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000002040 relaxant effect Effects 0.000 description 1
- 230000036387 respiratory rate Effects 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 238000010183 spectrum analysis Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000001515 vagal effect Effects 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
- A61B5/0205—Simultaneously evaluating both cardiovascular conditions and different types of body conditions, e.g. heart and respiratory condition
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7253—Details of waveform analysis characterised by using transforms
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Physiology (AREA)
- Physics & Mathematics (AREA)
- Molecular Biology (AREA)
- Public Health (AREA)
- Pathology (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Veterinary Medicine (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Psychiatry (AREA)
- Signal Processing (AREA)
- Cardiology (AREA)
- Pulmonology (AREA)
- Evolutionary Computation (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention relates to the technical field of mental state prediction, in particular to a mental state prediction method, a system and equipment based on physiological health indexes, wherein the method comprises the steps of collecting the physiological health indexes of a user to be detected; and respectively analyzing the physiological health indexes by utilizing an AI algorithm to obtain characteristic parameters, obtaining a comprehensive relaxation index of the user to be detected based on the characteristic parameters, evaluating the mental state of the user to be detected based on the comprehensive relaxation index, and if the comprehensive relaxation index is higher, the mental state of the user to be detected is better. According to the invention, the acquisition requirements of the physiological data of the user are met, meanwhile, the feature extraction and analysis are carried out on the physiological signals, the data features are classified and identified by utilizing an AI algorithm, a more optimized algorithm model is constructed, the rapid and accurate assessment of the mental state of the user can be realized, the mental state of the user can be assessed, meanwhile, the relaxation training can be carried out, the targeted relaxation training is utilized to carry out emotion dispersion, the individual stress is relieved, and the attention-deficit is improved.
Description
Technical Field
The invention relates to the technical field of mental state prediction, in particular to a mental state prediction method, a mental state prediction system and mental state prediction equipment based on physiological health indexes.
Background
With the improvement of living standard, more and more people pay attention to the physical health and mental health condition of an individual, and meanwhile, daily work and life face various stresses, so that effective evaluation and intervention on the physiological state and the mental stress are very important, but the existing health index evaluation system is difficult to comprehensively and accurately evaluate the physiological state, the mental state and the emotional state of the tested individual comprehensively.
Therefore, it is an urgent need to solve the above-mentioned problems for those skilled in the art to devise a method for collecting related physiological signals and evaluating mental status in a more convenient and faster manner.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides a mental state prediction method based on physiological health indexes, which comprises the following steps:
s1, collecting physiological health indexes of a user to be detected, wherein the physiological health indexes comprise pulse data and respiratory data, and executing the step S2;
s2, analyzing the pulse data and the respiration data respectively by using an AI algorithm to obtain pulse characteristics and respiration characteristics respectively, and executing the step S3;
s3, inputting the pulse characteristics into a trained first LSTM neural network model to obtain an H relaxation index, inputting the respiration characteristics into a trained second LSTM neural network model to obtain a B relaxation index, obtaining a comprehensive relaxation index of the user to be tested based on the H relaxation index and the B relaxation index, and executing the step S4;
s4: and evaluating the mental state of the user to be tested based on the comprehensive relaxation index, wherein the mental state of the user to be tested is better if the comprehensive relaxation index is higher.
Preferably, the method for analyzing the pulse data by using the AI algorithm to obtain the pulse characteristic data comprises the following steps: and calculating RR intervals according to the pulse data, and performing time domain analysis, frequency domain analysis and nonlinear analysis on the RR intervals in a normal range respectively to obtain the pulse characteristics including time domain characteristics, frequency domain characteristics and nonlinear characteristics.
Preferably, the time domain features include MEAN _ NNI, SDNN, RMSSD, PNNI _50, the frequency domain features include LF, HF, LFnorm, HFnorm, and the non-linear features include VLI, VAI.
Preferably, the method for analyzing the respiration data based on the AI algorithm to obtain the respiration characteristics comprises: and constructing a respiration curve graph based on the respiration data, acquiring peak values and valley values of respiration based on the respiration curve graph, and obtaining respiration characteristics including an inspiratory-expiratory ratio and a respiratory frequency based on the peak values and the valley values.
Preferably, the first LSTM neural network model and the second LSTM neural network model are trained in the same way, wherein the first LSTM neural network model is trained in the following way:
s51, acquiring a large amount of pulse data of the user;
s52, analyzing a large amount of user pulse data by using AI to obtain a large amount of user pulse characteristics, marking the user pulse characteristics to obtain labels corresponding to the user pulse characteristics, wherein the labels corresponding to the user pulse characteristics are short-time standard values of the pulse characteristics;
and S53, training a neural network by adopting the user pulse characteristics and the labels corresponding to the user pulse characteristics to obtain a trained first LSTM neural network model.
Preferably, the pulse data of the user, the age of which is similar to that of the user to be tested, is adopted as the pulse data of the user initially used for training the first LSTM neural network model; when the acquired pulse data of the user reaches a set value, the pulse data can be used for training the first LSTM neural network model.
In another aspect, a mental state prediction system based on physiological health indicators includes:
the acquisition module is used for acquiring the physiological health index of the user to be detected;
the first processing module is used for analyzing the pulse data and the respiration data respectively by utilizing an AI algorithm to obtain pulse characteristics and respiration characteristics;
the second processing module is used for respectively inputting the pulse characteristics and the respiration characteristics into the trained first LSTM neural network model and the trained second LSTM neural network model to obtain a comprehensive relaxation index;
and the evaluation module is used for evaluating the mental state of the user to be tested according to the comprehensive relaxation index.
Preferably, the method further comprises the following steps: and the visualization module is used for matching proper relaxation training according to the mental state of the user to be tested and visualizing the mental state of the user and a corresponding relaxation training strategy.
Preferably, the method further comprises the following steps: and the training module is used for performing relaxation training according to the relaxation training strategy, wherein the training module comprises a scene training module and a theme training module.
The invention has the beneficial effects that: on one hand, while meeting the acquisition requirement of the physiological data of the user, the AI algorithm (LSTM neural network) can be used for carrying out big data analysis, carrying out heart rate variability, monitoring the physiological indexes of the human body from multiple aspects, and generating more reliable evaluation basis of the mental state of the user.
Drawings
In order to more clearly illustrate the detailed description of the invention or the technical solutions in the prior art, the drawings that are needed in the detailed description of the invention or the prior art will be briefly described below. Throughout the drawings, like elements or portions are generally identified by like reference numerals. In the drawings, elements or portions are not necessarily drawn to scale.
FIG. 1 is a flow chart of a mental state prediction method based on physiological health indicators according to the present invention;
FIG. 2 is a flow chart of pulse data analysis using the AI algorithm;
FIG. 3 is a flow chart of analysis of respiration data using an AI algorithm;
FIG. 4 is a schematic diagram of a mental state prediction system based on physiological health indicators according to the present invention;
fig. 5 is a schematic structural diagram of an electronic device according to the present invention.
Detailed Description
Embodiments of the present invention will be described in detail below with reference to the accompanying drawings. The following examples are only for illustrating the technical solutions of the present invention more clearly, and therefore are only examples, and the protection scope of the present invention is not limited thereby.
It is to be noted that, unless otherwise specified, technical or scientific terms used herein shall have the ordinary meaning as understood by those skilled in the art to which the invention pertains.
Example 1
A mental state prediction method based on physiological health indexes comprises the following steps:
s1, collecting physiological health indexes of a user to be detected, wherein the physiological health indexes comprise pulse data and respiratory data, and executing the step S2;
s2, analyzing the pulse data and the respiration data respectively by using an AI algorithm to obtain pulse characteristics and respiration characteristics, and executing the step S3;
s3, inputting the pulse characteristics into a trained first LSTM neural network model to obtain an H relaxation index, inputting the respiration characteristics into a trained second LSTM neural network model to obtain a B relaxation index, obtaining a comprehensive relaxation index of the user to be tested based on the H relaxation index and the B relaxation index, and executing the step S4;
of course, not only the composite index but also the maximum and minimum values of the composite index and the real-time value can be obtained based on the H relaxation index and the B relaxation index.
S4: evaluating the mental state of the user to be tested based on the comprehensive relaxation index, wherein the mental state of the user to be tested is better if the comprehensive relaxation index is higher, and the formula for calculating the comprehensive relaxation index is as follows:
L＝λH+(1-λ)B
in the formula, L is the comprehensive relaxation index, H is the H relaxation index, B is the B relaxation index, and lambda is the influence factor, and the user can set up the numerical value of influence factor by oneself according to the self condition, can satisfy different users' demand.
According to the embodiment of the invention, while the acquisition requirement of the physiological data of the user is met, the AI algorithm (LSTM neural network) can be used for carrying out big data analysis, the heart rate variability is carried out, the physiological indexes of the human body are monitored from multiple aspects, a more reliable evaluation basis of the mental state of the user is generated, and the quick and accurate evaluation of the mental state of the user can be realized.
It should be noted that the method for analyzing the pulse data by using the AI algorithm to obtain the pulse feature data includes: and calculating RR intervals according to the pulse data, and performing time domain analysis, frequency domain analysis and nonlinear analysis on the RR intervals in a normal range respectively to obtain the pulse characteristics including time domain characteristics, frequency domain characteristics and nonlinear characteristics.
The normal range of the RR interval is 600- & lt1200 & gt, and RR interval data outside the range of 600- & lt1200 & gt is not accurate in pulse data acquisition due to external reasons, but is not caused by the respiratory rate of the human body. Therefore, the range of the filtered outliers is selected between 600 and 1200, and the analysis of the pulse data can be continued after the filtered outliers.
It is worth mentioning that the time domain features include MEAN _ NNI, SDNN, RMSSD, PNNI _50, the frequency domain features include LF, HF, LFnorm, HFnorm, and the non-linear features include VLI, VAI.
Specifically, the AI algorithm is used for analyzing the collected pulse wave data, and the time domain and frequency domain indexes of the heart rate and the heart rate variability are obtained on the basis of RR interval data, so that firstly, signal processing is carried out according to the pulse wave data, an RR interval is calculated, and then, time domain, frequency domain and nonlinear analysis are carried out on the heart rate variability HRV by using the RR interval data. As shown, fig. 2 is a flow chart of analyzing the acquired pulse data by using an AI algorithm.
(1) Time domain feature analysis
Directly performing statistical or geometric analysis on the acquired RR interval time sequence signals and RR interval values arranged in time sequence or heart beat sequence to obtain time domain characteristics, wherein the time domain characteristics include but are not limited to MEAN _ NNI, SDNN, RMSSD and PNNI _50, and the following table 1 shows:
table 1: time domain characterization
SDNN refers to the average of all normal sinus intervals (NN) in ms, calculated as follows:
RMSSD is the root mean square of the difference between the adjacent NN intervals throughout, in ms, and is calculated as follows:
SDSD is the standard deviation of the difference between the lengths of the adjacent NN intervals in the whole process, and the unit is ms, and the calculation formula is as follows:
PNNI — 50 refers to the ratio of the number of adjacent NN intervals that differ by more than 50ms in the recording of all NN intervals to the total NN interval, expressed as a percentage. Its SDNN reflects the overall assessment of heart rate regulation by the autonomic nervous system, while RMSSD and PNNI — 50 reflect vagal tone.
(2) Frequency domain analysis
The frequency domain analysis method is to perform Fast Fourier Transform (FFT) or autoregressive parameter model (AR) operation on a section of relatively stable RR interval or instantaneous heart rate variation signal (generally more than 256 heart points) to obtain a power spectrogram with frequency (Hz) as a horizontal coordinate and power spectral density as a vertical coordinate for analysis. The heart rate spectrum curve is between 0-0.4Hz, 0.003-0.04Hz is the very low frequency band (VLF), 0.04-0.15Hz is the low frequency band (LF), 0.15-0.4Hz is the high frequency band (HF), 0-0.40Hz is the total power spectrum (TP) under the normal human basal state.
The recording time of the short-range recording is recommended to be 5 minutes. The spectrum of the short-range record is divided into three frequency bands, and the division of each frequency band and the index calculated by each frequency band are defined as shown in table 2 below. Where VLF, LF, and HF are integrated values of PSD components falling in different frequency bands in the PSD curve, that is, areas of the components whose center frequencies fall in different frequency bands.
The normalized low band power is defined as: LF norm is 100 XLF/(Total Power-VLF)
The normalized high band power is defined as: HF norm 100 XHF/(Total Power-VLF)
Table 2: division of short-range recorded spectral analysis frequency bands
(3) Non-linear analysis
The interval scattergram is also called Lorenz scattergram (Lorenz Plot) or pet plus scattergram (Poincare Plot) and reflects the change of adjacent intervals.
The shape of the scatter diagram directly reflects the characteristics of the instantaneous heart rate change curve, and the scatter diagram is mostly concentrated near a straight line with an angle of 45 degrees in the diagram by taking a normal comet-shaped scatter diagram as an example.
Vector Length Index (VLI) and Vector Angle Index (VAI) were used as quantitative indicators to measure the shape of the Lorenz scatterplot.
Vector Length Index (VLI) in ms. Any point in the Lorenz scatter diagram is connected with the coordinate origin i, and the length of the straight line is liThe unit is ms, which is called the vector length of the ith point. The included angle between the straight line and the abscissa is thetaiThe unit is degree, and is called the vector angle of the ith point.
The Vector Length Index (VLI) is defined as:
in the formula IiIs the vector length of the ith point; n is the number of adjacent RR intervals; l is the average of the lengths of the vectors, VLI represents the length along the 45 DEG angle line, and VLI magnitude represents the magnitudes of the HRV very low frequency and low frequency components.
The Vector Angle Index (VAI) is defined as:
in the formula [ theta ]iThe included angle between the connecting line of the ith point and the origin of coordinates and the transverse axis; n is the number of adjacent RR intervals; VAI represents the angle at which the Lorenz scatter plot fans out; the size of the VAI represents the size of the high frequency components in the HRV.
It is worth to be noted that the method for analyzing the respiration data based on the AI algorithm to obtain the respiration characteristics is as follows: and constructing a respiration curve graph based on the respiration data, acquiring peak values and valley values of respiration based on the respiration curve graph, and obtaining respiration characteristics including an inspiratory-expiratory ratio and a respiratory frequency based on the peak values and the valley values.
Specifically, the breathing characteristics include, but are not limited to, breathing frequency, and breathing ratio, and further include effective parameters such as expiration time, inspiration time, and breathing ratio. The respiratory frequency represents the respiratory frequency within one minute, the unit is times/minute, and the respiratory frequency range of a normal human body is 15-25 times/minute. The inhalation-exhalation ratio is the ratio of inhalation time to exhalation time, and the range is about 1: 2-2. Fig. 3 is a flow chart illustrating the analysis of the acquired respiratory data using the AI algorithm, as shown in fig. 3.
It should be noted that the first LSTM neural network model and the second LSTM neural network model are trained in the same way, wherein the first LSTM neural network model is trained in the following way:
s51, acquiring a large amount of pulse data of the user;
s52, analyzing a large amount of user pulse data by using AI to obtain a large amount of user pulse characteristics, marking the user pulse characteristics to obtain labels corresponding to the user pulse characteristics, wherein the labels corresponding to the user pulse characteristics are short-time standard values of the pulse characteristics;
and S53, training a neural network by adopting the user pulse characteristics and the labels corresponding to the user pulse characteristics to obtain a trained first LSTM neural network model.
During actual training, a large amount of user pulse data are used as training samples, the first 80% of the training samples are selected as a training set, and the last 20% of the training samples are selected as a test set. The optimizer was selected as Adam, the loss function was category cross, the batch size was selected as 500, and the number of iterations was 300.
It is worth to be noted that the pulse data of the user, which is initially used for training the first LSTM neural network model, is the pulse data of the user whose age is similar to that of the user to be tested; when the acquired pulse data of the user reaches a set value, the pulse data can be used for training the first LSTM neural network model.
Example 2
As shown in fig. 4, a mental state prediction system based on physiological health indicators includes:
the acquisition module is used for acquiring the physiological health index of the user to be detected;
the system also comprises a database, wherein the database can store the physiological health data and static state data of the user, and form emotion management big data, so that accurate assessment and intervention are provided for stress management and physical and mental relaxation training of personnel, and effective data support is provided for the healthy development of the personnel.
The first processing module is used for analyzing the pulse data and the respiration data respectively by utilizing an AI algorithm to obtain pulse characteristics and respiration characteristics;
the first processing module is used for preprocessing the physiological health indexes, and comprises a first preprocessing module and a second preprocessing module which are respectively used for analyzing and processing the pulse data and the respiratory data to obtain a large amount of pulse characteristics and respiratory characteristics which are used as basic parameters for analyzing and evaluating the mental state of the user.
The second processing module is used for respectively inputting the pulse characteristics and the respiration characteristics into the trained first LSTM neural network model and the trained second LSTM neural network model to obtain a comprehensive relaxation index;
and the evaluation module is used for evaluating the mental state of the user to be tested according to the comprehensive relaxation index.
It is worth mentioning that the method also comprises the following steps: and the visualization module is used for matching proper relaxation training according to the mental state of the user to be tested and visualizing the mental state of the user and a corresponding relaxation training strategy.
It is worth mentioning that the method also comprises the following steps: and the training module is used for performing relaxation training according to the relaxation training strategy, wherein the training module comprises a scene training module and a theme training module.
According to the embodiment of the invention, while the mental state of the user is evaluated, different forms of relaxation training can be developed according to different scenes and requirements, wherein the different scenes comprise: seaside, field, desert, forest etc. different themes have: the subject music comprises various types of music, and the targeted relaxation training is utilized to conduct emotion dispersion, relieve individual stress and improve concentration.
Example 3
As shown in fig. 5, an electronic device according to an embodiment of the present invention includes a processor and a memory, and when the processor executes computer instructions/codes stored in the memory, the electronic device implements the method according to any of the above embodiments.
The electronic equipment of the embodiment includes but is not limited to wearing equipment, so the electronic equipment of the invention also includes other electronic equipment capable of acquiring physiological health indexes, can be used for treating fatigue states of users, achieves the purpose of improving mental states of users, and has practical significance for relaxing mental states of individuals and clinical medicine.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; such modifications and substitutions do not depart from the spirit and scope of the present invention, and they should be construed as being included in the following claims and description.
Claims (10)
1. A mental state prediction method based on physiological health indexes is characterized by comprising the following steps:
s1, collecting physiological health indexes of a user to be detected, wherein the physiological health indexes comprise pulse data and respiratory data, and executing the step S2;
s2, analyzing the pulse data and the respiration data respectively by using an AI algorithm to obtain pulse characteristics and respiration characteristics respectively, and executing the step S3;
s3, inputting the pulse characteristics into a trained first LSTM neural network model to obtain an H relaxation index, inputting the respiration characteristics into a trained second LSTM neural network model to obtain a B relaxation index, obtaining a comprehensive relaxation index of the user to be tested based on the H relaxation index and the B relaxation index, and executing the step S4;
s4: and evaluating the mental state of the user to be tested based on the comprehensive relaxation index, wherein the mental state of the user to be tested is better if the comprehensive relaxation index is higher.
2. The method as claimed in claim 1, wherein the step S2 of analyzing the pulse data by AI algorithm to obtain the pulse characteristic data comprises: and calculating RR intervals according to the pulse data, and performing time domain analysis, frequency domain analysis and nonlinear analysis on the RR intervals in a normal range respectively to obtain the pulse characteristics including time domain characteristics, frequency domain characteristics and nonlinear characteristics.
3. A method as claimed in claim 2, wherein the time domain features include MEAN _ NNI, SDNN, RMSSD, PNNI _50, the frequency domain features include LF, HF, LFnorm, HFnorm, and the non-linear features include VLI, VAI.
4. The mental state prediction method based on physiological health indexes as claimed in claim 2, wherein the method for analyzing the respiration data based on the AI algorithm to obtain the respiration characteristics comprises: and constructing a respiration curve graph based on the respiration data, acquiring peak values and valley values of respiration based on the respiration curve graph, and obtaining respiration characteristics including an inspiratory-expiratory ratio and a respiratory frequency based on the peak values and the valley values.
5. The mental state prediction method based on physiological health indexes of claim 1, wherein the first LSTM neural network model and the second LSTM neural network are trained in the same way, and wherein the first LSTM neural network model is trained by:
s51, acquiring a large amount of pulse data of the user;
s52, analyzing a large amount of user pulse data by using AI to obtain a large amount of user pulse characteristics, marking the user pulse characteristics to obtain labels corresponding to the user pulse characteristics, wherein the labels corresponding to the user pulse characteristics are short-time standard values of the pulse characteristics;
and S53, training a neural network by adopting the user pulse characteristics and the labels corresponding to the user pulse characteristics to obtain a trained first LSTM neural network model.
6. The method as claimed in claim 5, wherein the pulse data of the user used for training the first LSTM neural network model is derived from pulse data of the user whose age is similar to that of the user to be tested; when the acquired pulse data of the user reaches a set value, the pulse data can be used for training the first LSTM neural network model.
7. A mental state prediction system based on physiological health indicators, comprising:
the acquisition module is used for acquiring the physiological health index of the user to be detected;
the first processing module is used for analyzing the pulse data and the respiration data respectively by utilizing an AI algorithm to obtain pulse characteristics and respiration characteristics;
the second processing module is used for respectively inputting the pulse characteristics and the respiration characteristics into the trained first LSTM neural network model and the trained second LSTM neural network model to obtain a comprehensive relaxation index;
and the evaluation module is used for evaluating the mental state of the user to be tested according to the comprehensive relaxation index.
8. A physiological health indicator-based mental state prediction system as claimed in claim 7, further comprising:
and the visualization module is used for matching proper relaxation training according to the mental state of the user to be tested and visualizing the mental state of the user and a corresponding relaxation training strategy.
9. A physiological health indicator-based mental state prediction system as claimed in claim 8, further comprising:
and the training module is used for performing relaxation training according to the relaxation training strategy, wherein the training module comprises a scene training module and a theme training module.
10. An electronic device comprising a processor and a memory, the processor implementing the method of any one of claims 1-6 when executing code stored in the memory.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111159498.2A CN113842124A (en) | 2021-09-30 | 2021-09-30 | Mental state prediction method, system and equipment based on physiological health indexes |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111159498.2A CN113842124A (en) | 2021-09-30 | 2021-09-30 | Mental state prediction method, system and equipment based on physiological health indexes |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113842124A true CN113842124A (en) | 2021-12-28 |
Family
ID=78977292
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111159498.2A Pending CN113842124A (en) | 2021-09-30 | 2021-09-30 | Mental state prediction method, system and equipment based on physiological health indexes |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113842124A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115177843A (en) * | 2022-09-08 | 2022-10-14 | 柏斯速眠科技(深圳)有限公司 | Method and system for evaluating relaxation state of body and method and system for adjusting relaxation state of body |
| CN115607111A (en) * | 2022-11-10 | 2023-01-17 | 北京工业大学 | Mental state prediction method based on ECG signal |
| CN117064350A (en) * | 2023-08-18 | 2023-11-17 | 暨南大学附属第一医院（广州华侨医院） | Safety detection and intelligent evaluation system |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104127193A (en) * | 2014-07-14 | 2014-11-05 | 华南理工大学 | Evaluating system and evaluating method of depressive disorder degree quantization |
| CN105193431A (en) * | 2015-09-02 | 2015-12-30 | 杨静 | Device for analyzing mental stress state of human body |
| CN106137226A (en) * | 2016-07-29 | 2016-11-23 | 华南理工大学 | A kind of stress appraisal procedure based on heart source property breath signal |
| WO2017020500A1 (en) * | 2015-07-31 | 2017-02-09 | 深圳市易特科信息技术有限公司 | Psychological monitoring and relieving system and method based on digital helmet |
| CN107126203A (en) * | 2016-02-28 | 2017-09-05 | 南京全时陪伴健康科技有限公司 | Human health information measures display system in real time |
| CN108888281A (en) * | 2018-08-16 | 2018-11-27 | 华南理工大学 | State of mind appraisal procedure, equipment and system |
| CN110200640A (en) * | 2019-05-14 | 2019-09-06 | 南京理工大学 | Contactless Emotion identification method based on dual-modality sensor |
| CN112568876A (en) * | 2020-12-07 | 2021-03-30 | 深圳镭洱晟科创有限公司 | System and method for predicting health of old people based on LSTM multiple physiological parameters |
-
2021
- 2021-09-30 CN CN202111159498.2A patent/CN113842124A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104127193A (en) * | 2014-07-14 | 2014-11-05 | 华南理工大学 | Evaluating system and evaluating method of depressive disorder degree quantization |
| WO2017020500A1 (en) * | 2015-07-31 | 2017-02-09 | 深圳市易特科信息技术有限公司 | Psychological monitoring and relieving system and method based on digital helmet |
| CN105193431A (en) * | 2015-09-02 | 2015-12-30 | 杨静 | Device for analyzing mental stress state of human body |
| CN107126203A (en) * | 2016-02-28 | 2017-09-05 | 南京全时陪伴健康科技有限公司 | Human health information measures display system in real time |
| CN106137226A (en) * | 2016-07-29 | 2016-11-23 | 华南理工大学 | A kind of stress appraisal procedure based on heart source property breath signal |
| CN108888281A (en) * | 2018-08-16 | 2018-11-27 | 华南理工大学 | State of mind appraisal procedure, equipment and system |
| CN110200640A (en) * | 2019-05-14 | 2019-09-06 | 南京理工大学 | Contactless Emotion identification method based on dual-modality sensor |
| CN112568876A (en) * | 2020-12-07 | 2021-03-30 | 深圳镭洱晟科创有限公司 | System and method for predicting health of old people based on LSTM multiple physiological parameters |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115177843A (en) * | 2022-09-08 | 2022-10-14 | 柏斯速眠科技(深圳)有限公司 | Method and system for evaluating relaxation state of body and method and system for adjusting relaxation state of body |
| CN115607111A (en) * | 2022-11-10 | 2023-01-17 | 北京工业大学 | Mental state prediction method based on ECG signal |
| CN117064350A (en) * | 2023-08-18 | 2023-11-17 | 暨南大学附属第一医院（广州华侨医院） | Safety detection and intelligent evaluation system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113842124A (en) | Mental state prediction method, system and equipment based on physiological health indexes | |
| Acharya et al. | Comprehensive analysis of cardiac health using heart rate signals | |
| WO2020006845A1 (en) | Health reserve evaluation method, and device and application thereof | |
| Germán-Salló et al. | Non-linear methods in HRV analysis | |
| JP6122884B2 (en) | Work alertness estimation device, method and program | |
| Nardelli et al. | Reliability of lagged poincaré plot parameters in ultrashort heart rate variability series: Application on affective sounds | |
| WO2005009226A2 (en) | Apparatus and method for identifying sleep disordered breathing | |
| Hayet et al. | Sleep-wake stages classification based on heart rate variability | |
| Tiwari et al. | A comparative study of stress and anxiety estimation in ecological settings using a smart-shirt and a smart-bracelet | |
| WO2011117784A2 (en) | Assessment of cardiac health based on heart rate variability | |
| CN115251852A (en) | Detection quantification method and system for body temperature regulation function | |
| US20200345251A1 (en) | Method and system for determining heart rate variability | |
| CN114366060A (en) | Health early warning method and device based on heart rate variability and electronic equipment | |
| CN110956406B (en) | Evaluation method of team cooperation ability based on heart rate variability | |
| Wang et al. | Automatic multi-class sleep staging method based on novel hybrid features | |
| Londhe et al. | Heart rate variability: A methodological survey | |
| CN113171061B (en) | Noninvasive vascular function assessment method, noninvasive vascular function assessment device, noninvasive vascular function assessment equipment and noninvasive vascular function assessment medium | |
| Kelwade et al. | Comparative study of neural networks for prediction of cardiac arrhythmias | |
| Lee et al. | Ontological fuzzy agent for electrocardiogram application | |
| RU2246251C1 (en) | Method for evaluating psychophysiological state according to human cardiac rhythm | |
| Ni et al. | RecogHypertension: early recognition of hypertension based on heart rate variability | |
| US10512412B2 (en) | Method of ECG evaluation based on universal scoring system | |
| Zhang et al. | Evaluation of single-lead ECG signal quality with different states of motion | |
| CN115105042B (en) | Evaluation method, evaluation system and evaluation device for stability of autonomic nervous system | |
| Bozhokin et al. | Special techniques in applying continuous wavelet transform to non-stationary signals of heart rate variability |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20211228 |
|
| RJ01 | Rejection of invention patent application after publication |