Psychological health assessment method and device based on galvanic skin bracelet and brain-computer interface

Abstract

The invention discloses a psychological health assessment method and device based on a galvanic skin bracelet and a brain-computer interface. The method comprises the steps that a galvanic skin signal sequence set and an electroencephalogram signal set of a user are acquired; the skin electric signal sequence set comprises skin electric signal sequences; the electroencephalogram signal set comprises an alpha wave signal sequence, a beta wave signal sequence, a theta wave signal sequence and a delta wave signal sequence; preprocessing the skin electric signal sequence set and the electroencephalogram signal set to obtain a to-be-evaluated signal set; and performing psychological health assessment processing on the to-be-assessed signal set to obtain a psychological health assessment value of the user.

Description

Technical Field

[0001] The present invention relates to the fields of industrial data processing and equipment system evaluation, and specifically to a method and device for psychological health evaluation based on an electrodermal wristband and a brain-computer interface. Background Art

[0002] With the development of wearable device technology and bioelectric signal processing, psychological health assessment methods based on physiological signals have gradually become a research hotspot. Electrodermal signals, as physiological signals reflecting the activity of the human autonomic nervous system, can reflect an individual's emotional arousal level in real time. For example, when an individual is in an emotional state such as tension or anxiety, electrodermal signals will show significant changes. Electroencephalogram (EEG) signals contain rich information about brain neural activity. EEG waves of different frequencies, such as alpha, beta, theta, and delta waves, are closely related to an individual's cognition, emotions, and psychological state. However, existing psychological health assessment technologies based on electrodermal and EEG signals still face numerous challenges. Firstly, during the signal acquisition process, due to factors such as human movement and environmental interference, the collected electrodermal and EEG signals often contain noise, missing data, or errors, which affects the accuracy of subsequent assessments. Secondly, in terms of signal processing and assessment model construction, most existing methods fail to fully explore the potential correlations between electrodermal and EEG signals and fail to fully utilize the signals in a comprehensive and accurate manner, resulting in assessment results that fail to fully and accurately reflect an individual's psychological health status. Therefore, it is of great practical significance to develop a mental health assessment method based on an electrodermal bracelet and a brain-computer interface that can effectively overcome the above problems. Summary of the Invention

[0003] The present invention mainly solves the problems of inaccurate data processing and incomplete assessment conclusions in existing psychological health assessment methods based on electrodermal and electroencephalographic (EEG) technology. The present invention discloses a psychological health assessment method and device based on an EEG bracelet and a brain-computer interface.

[0004] In a first aspect, an embodiment of the present invention discloses a method for psychological health assessment based on an electrodermal wristband and a brain-computer interface, comprising:

[0005] S1, collecting and obtaining a user's electrodermal signal sequence set and an electroencephalogram signal set; the electrodermal signal sequence set includes an electrodermal signal sequence; the electroencephalogram signal set includes an α wave signal sequence, a β wave signal sequence, a θ wave signal sequence, and a δ wave signal sequence;

[0006] S2, preprocessing the electrodermal signal sequence set and the electroencephalogram signal set to obtain a signal set to be evaluated;

[0007] S3, performing psychological health assessment processing on the set of signals to be assessed to obtain a psychological health assessment value of the user.

[0008] The preprocessing of the electrodermal signal sequence set and the electroencephalogram signal set to obtain a signal set to be evaluated includes:

[0009] S21, performing data cleaning processing on the electrodermal signal sequence set and the electroencephalogram signal set to obtain a first signal set;

[0010] S22, performing time alignment processing on the first signal set to obtain a second signal set;

[0011] S23: Perform model cross detection processing on the second signal set to obtain a signal set to be evaluated.

[0012] The performing model cross detection processing on the second signal set to obtain a signal set to be evaluated includes:

[0013] S2301, performing autoregressive-sliding average modeling on the data of the electrodermal signal sequence set of the second signal set, using the data collection time of all data as an independent variable and the data value of all data as a dependent variable to obtain a regression model;

[0014] S2302: for each data item in each type of signal sequence of the electroencephalogram signal set of the second signal set, using the data collection time of the data item as an independent variable, calculate the independent variable using the regression model to obtain a regression value corresponding to the data item;

[0015] S2303, determining whether the difference between the data and the corresponding regression value is less than a preset first discrimination threshold, and obtaining a first discrimination result;

[0016] S2304, deleting data with the first discrimination result of not less than from the EEG signal set of the second signal set to obtain a preprocessed EEG signal set;

[0017] S2305, constructing a signal matrix using each type of signal sequence of the electroencephalogram signal set of the second signal set as a row vector;

[0018] S2306, performing singular value calculation processing on the signal matrix to obtain a singular value sequence;

[0019] S2307, taking the element values ​​of the singular value sequence as known dependent variables and the element numbers of the singular value sequence as known independent variables, constructing a curve to be approximated using the known independent variables and the known dependent variables; performing polynomial fitting on the curve to be approximated to obtain an approximation model;

[0020] S2308: For each data in the electrodermal signal set of the second signal set, using the data collection time of the data as an independent variable, calculate the independent variable using the approximation model to obtain a regression value corresponding to the data;

[0021] S2309, determining whether the difference between the data and the corresponding regression value is less than a preset second discrimination threshold, and obtaining a second discrimination result;

[0022] S2310, deleting data with the second discrimination result of not less than from the electrical skin signal sequence set of the second signal set to obtain a preprocessed electrical skin signal sequence set;

[0023] S2311 , constructing a signal set to be evaluated using the preprocessed electrodermal signal sequence set and the preprocessed electroencephalogram signal set.

[0024] The performing mental health assessment processing on the set of signals to be assessed to obtain a mental health assessment value of the user includes:

[0025] S31, performing skin electrical state monitoring processing on the skin electrical signal sequence set in the signal set to be evaluated to obtain a skin electrical state monitoring value;

[0026] S32, performing fusion evaluation processing on the EEG signal set in the signal set to be evaluated to obtain an EEG evaluation value;

[0027] S33, using a preset psychological state fusion assessment model, calculating and processing the electrodermal state monitoring value and the EEG assessment value to obtain the user's psychological health assessment value.

[0028] The performing skin electrical state monitoring processing on the skin electrical signal sequence set in the signal set to be evaluated to obtain the skin electrical state monitoring value includes:

[0029] S311, obtaining a standard sequence of electrodermal signals;

[0030] S312, subtracting the set of electrical skin signal sequences from the standard sequence of electrical skin signals to obtain a set of electrical skin difference signals; the set of electrical skin difference signals includes an electrical skin difference sequence; the electrical skin difference sequence is an electrical skin signal sequence in the set of electrical skin signal sequences, obtained by subtracting the standard sequence of electrical skin signals from the standard sequence of electrical skin signals;

[0031] S313, performing statistical analysis on the set of electrodermal difference signals to obtain a set of statistical values;

[0032] S314: Perform pattern fusion calculation on the statistical value set to obtain a skin electrical state monitoring value.

[0033] The expression for the statistical analysis process is:

[0034]

[0035] Where Tj is the statistical value of the jth skin electrical difference sequence in the skin electrical difference signal set, the statistical analysis value, p ji is the probability of occurrence of the data value of the jth skin electrical difference sequence in the skin electrical difference signal set within the i-th value interval, p jmax and p jave are the maximum and average values ​​of all occurrence probabilities of the jth skin electrical difference sequence in the skin electrical difference signal set, N1 is the number of value intervals of the skin electrical difference signal set, and the statistical value set includes the statistical values ​​of all skin electrical difference sequences in the skin electrical difference signal set;

[0036] The expression of the mode fusion calculation is:

[0037]

[0038] Wherein, spd is the skin electrical status monitoring value, μ and η are the mean and variance of all statistical values ​​of the statistical value set respectively.

[0039] The performing fusion evaluation processing on the EEG signal set in the signal set to be evaluated to obtain an EEG evaluation value includes:

[0040] Performing MEMD transformation and MVMD transformation on the α wave signal sequence and the β wave signal sequence in the EEG signal set in the signal set to be evaluated, respectively, to obtain an α wave transformation sequence and a β wave transformation sequence;

[0041] performing feature extraction processing on the α wave transformation sequence and the β wave transformation sequence to obtain a first EEG evaluation component;

[0042] Obtaining a θ wave standard signal and a δ wave standard signal;

[0043] Subtracting the θ wave signal sequence and the δ wave signal sequence in the EEG signal set in the signal set to be evaluated from the θ wave standard signal and the δ wave standard signal, respectively, to obtain corresponding θ wave difference signals and δ wave difference signals;

[0044] Performing a mutual mode transformation calculation on the θ wave difference signal and the δ wave difference signal to obtain a second EEG evaluation component;

[0045] A weighted sum is performed on the first EEG evaluation component and the second EEG evaluation component to obtain an EEG evaluation value.

[0046] In a second aspect of an embodiment of the present invention, a mental health assessment device based on an electrodermal wristband and a brain-computer interface is disclosed, the device comprising:

[0047] a memory storing executable program code;

[0048] a processor coupled to the memory;

[0049] The processor calls the executable program code stored in the memory to execute the mental health assessment method based on the electrodermal bracelet and brain-computer interface.

[0050] In a third aspect of an embodiment of the present invention, a computer-storable medium is disclosed, which stores computer instructions. When the computer instructions are called by a computer, they are used to execute the mental health assessment method based on an electrodermal bracelet and a brain-computer interface.

[0051] In a fourth aspect of an embodiment of the present invention, an information data processing terminal is disclosed, which is used to implement the mental health assessment method based on an electrodermal bracelet and a brain-computer interface.

[0052] The beneficial effects of the present invention are:

[0053] The present invention performs comprehensive and detailed preprocessing on the collected skin electrodermal signal sequence set and brain electrodermal signal set. In the data cleaning process, it can effectively remove interference factors such as noise, outliers and missing values ​​in the signal to ensure the quality of subsequent analysis data. Time alignment processing synchronizes the skin electrodermal signal and the brain electrodermal signal in the time dimension, providing a basis for comprehensive analysis of the relationship between the two. In particular, the model cross-detection processing uses methods such as autoregressive-sliding average modeling and polynomial fitting to further screen out data that may have deviations, significantly improving the accuracy of the signal set to be evaluated, thereby providing reliable data support for subsequent mental health assessments, so that the assessment results can more truly reflect the user's psychological state.

[0054] During the psychological health assessment and processing stage, the present invention conducts in-depth analysis of the electrodermal signals and EEG signals respectively. The electrodermal state monitoring process can accurately capture the changing characteristics of the electrodermal signals and reflect the user's emotional arousal level by comparing them with the standard sequence of electrodermal signals and performing statistical analysis and pattern fusion calculation on the difference signals. In the EEG signal fusion evaluation process, a variety of advanced transformation and calculation methods are used for brain waves of different frequencies, such as MEMD transformation and MVMD transformation to extract features of α waves and β waves, and comparison of θ waves and δ waves with standard signals and mutual mode transformation calculation, which fully explores the rich psychological information contained in the EEG signals. Finally, the preset psychological state fusion evaluation model is used to integrate the electrodermal state monitoring value and the EEG evaluation value to comprehensively and accurately derive the user's psychological health evaluation value, greatly improving the accuracy of the evaluation. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 4 is an implementation flow chart of the method of the present invention. DETAILED DESCRIPTION

[0056] In order to better understand the content of the present invention, an embodiment is given here.

[0057] Figure 1 4 is an implementation flow chart of the method of the present invention.

[0058] In a first aspect, an embodiment of the present invention discloses a method for psychological health assessment based on an electrodermal wristband and a brain-computer interface, comprising:

[0059] S1, collecting and obtaining a user's electrodermal signal sequence set and an electroencephalogram signal set; the electrodermal signal sequence set includes an electrodermal signal sequence; the electroencephalogram signal set includes an α wave signal sequence, a β wave signal sequence, a θ wave signal sequence, and a δ wave signal sequence;

[0060] S2, preprocessing the electrodermal signal sequence set and the electroencephalogram signal set to obtain a signal set to be evaluated;

[0061] S3, performing psychological health assessment processing on the set of signals to be assessed to obtain a psychological health assessment value of the user.

[0062] The preprocessing of the electrodermal signal sequence set and the electroencephalogram signal set to obtain a signal set to be evaluated includes:

[0063] S21, performing data cleaning processing on the electrodermal signal sequence set and the electroencephalogram signal set to obtain a first signal set;

[0064] S22, performing time alignment processing on the first signal set to obtain a second signal set;

[0065] S23: Perform model cross detection processing on the second signal set to obtain a signal set to be evaluated.

[0066] The performing model cross detection processing on the second signal set to obtain a signal set to be evaluated includes:

[0067] S2301, performing autoregressive-sliding average modeling on the data of the electrodermal signal sequence set of the second signal set, using the data collection time of all data as an independent variable and the data value of all data as a dependent variable to obtain a regression model;

[0068] S2302: for each data item in each type of signal sequence of the electroencephalogram signal set of the second signal set, using the data collection time of the data item as an independent variable, calculate the independent variable using the regression model to obtain a regression value corresponding to the data item;

[0069] S2303, determining whether the difference between the data and the corresponding regression value is less than a preset first discrimination threshold, and obtaining a first discrimination result;

[0070] S2304, deleting data with the first discrimination result of not less than from the EEG signal set of the second signal set to obtain a preprocessed EEG signal set;

[0071] S2305, constructing a signal matrix using each type of signal sequence of the electroencephalogram signal set of the second signal set as a row vector;

[0072] S2306, performing singular value calculation processing on the signal matrix to obtain a singular value sequence;

[0073] S2307, taking the element values ​​of the singular value sequence as known dependent variables and the element numbers of the singular value sequence as known independent variables, constructing a curve to be approximated using the known independent variables and the known dependent variables; performing polynomial fitting on the curve to be approximated to obtain an approximation model;

[0074] S2308: For each data in the electrodermal signal set of the second signal set, using the data collection time of the data as an independent variable, calculate the independent variable using the approximation model to obtain a regression value corresponding to the data;

[0075] S2309, determining whether the difference between the data and the corresponding regression value is less than a preset second discrimination threshold, and obtaining a second discrimination result;

[0076] S2310, deleting data with the second discrimination result of not less than from the electrical skin signal sequence set of the second signal set to obtain a preprocessed electrical skin signal sequence set;

[0077] S2311 , constructing a signal set to be evaluated using the preprocessed electrodermal signal sequence set and the preprocessed electroencephalogram signal set.

[0078] The autoregressive-moving average modeling may adopt an ARMA algorithm.

[0079] The performing mental health assessment processing on the set of signals to be assessed to obtain a mental health assessment value of the user includes:

[0080] S31, performing skin electrical state monitoring processing on the skin electrical signal sequence set in the signal set to be evaluated to obtain a skin electrical state monitoring value;

[0081] S32, performing fusion evaluation processing on the EEG signal set in the signal set to be evaluated to obtain an EEG evaluation value;

[0082] S33, using a preset psychological state fusion assessment model, calculating and processing the electrodermal state monitoring value and the EEG assessment value to obtain the user's psychological health assessment value.

[0083] The performing skin electrical state monitoring processing on the skin electrical signal sequence set in the signal set to be evaluated to obtain the skin electrical state monitoring value includes:

[0084] S311, obtaining a standard sequence of electrodermal signals;

[0085] S312, subtracting the set of electrical skin signal sequences from the standard sequence of electrical skin signals to obtain a set of electrical skin difference signals; the set of electrical skin difference signals includes an electrical skin difference sequence; the electrical skin difference sequence is an electrical skin signal sequence in the set of electrical skin signal sequences, obtained by subtracting the standard sequence of electrical skin signals from the standard sequence of electrical skin signals;

[0086] S313, performing statistical analysis on the set of electrodermal difference signals to obtain a set of statistical values;

[0087] S314: Perform pattern fusion calculation on the statistical value set to obtain a skin electrical state monitoring value.

[0088] The expression for the statistical analysis process is:

[0089]

[0090] Where Tj is the statistical value of the jth skin electrical difference sequence in the skin electrical difference signal set, the statistical analysis value, p ji is the probability of occurrence of the data value of the jth skin electrical difference sequence in the skin electrical difference signal set within the i-th value interval, p jmax and p jave are the maximum and average values ​​of all occurrence probabilities of the jth skin electrical difference sequence in the skin electrical difference signal set, N1 is the number of value intervals of the skin electrical difference signal set, and the statistical value set includes the statistical values ​​of all skin electrical difference sequences in the skin electrical difference signal set;

[0091] The expression of the mode fusion calculation is:

[0092]

[0093] Wherein, spd is the skin electrical status monitoring value, μ and η are the mean and variance of all statistical values ​​of the statistical value set respectively. ji It is obtained by evenly dividing the value range of all data of the j-th skin electrical difference sequence in the skin electrical difference signal set into N1 value intervals, counting the number of data values ​​in each value interval, and dividing the number by the total number of data in the skin electrical difference sequence.

[0094] The performing fusion evaluation processing on the EEG signal set in the signal set to be evaluated to obtain an EEG evaluation value includes:

[0095] Performing MEMD transformation and MVMD transformation on the α wave signal sequence and the β wave signal sequence in the EEG signal set in the signal set to be evaluated, respectively, to obtain an α wave transformation sequence and a β wave transformation sequence;

[0096] performing feature extraction processing on the α wave transformation sequence and the β wave transformation sequence to obtain a first EEG evaluation component;

[0097] Obtaining a θ wave standard signal and a δ wave standard signal;

[0098] Subtracting the θ wave signal sequence and the δ wave signal sequence in the EEG signal set in the signal set to be evaluated from the θ wave standard signal and the δ wave standard signal, respectively, to obtain corresponding θ wave difference signals and δ wave difference signals;

[0099] Performing a mutual mode transformation calculation on the θ wave difference signal and the δ wave difference signal to obtain a second EEG evaluation component;

[0100] A weighted sum is performed on the first EEG evaluation component and the second EEG evaluation component to obtain an EEG evaluation value SBr.

[0101] The weight values ​​for weighted summing of the first EEG evaluation component and the second EEG evaluation component may be 0.4 and 0.5 respectively.

[0102] The expression of the feature extraction process is:

[0103]

[0104] Where SBr1 is the first EEG evaluation component, α() is the α wave transformation sequence, β() is the β wave transformation sequence, i represents the element number of the transformation sequence, k is the time shift number, the integration range is -∞~∞, and θ is the frequency number variable corresponding to i;

[0105] The expression for the mutual mode transformation calculation is:

[0106]

[0107] Among them, SBr2 is the second evaluation component of EEG, B() represents the B function, a i and b i They represent the i-th item of the θ wave difference signal and the δ wave difference signal, θ1 and θ2 represent the mean and variance of the θ wave difference signal, δ1 represents the mean of the δ wave difference signal, and M1 is the length of the θ wave difference signal.

[0108] The preset psychological state fusion assessment model is used to calculate and process the skin electrode state monitoring value and the brain electrical evaluation value to obtain the user's psychological health assessment value, including:

[0109] The expression of the preset mental state fusion evaluation model is:

[0110]

[0111] Among them, ef and af are preset calculation factors, whose values ​​can be 1.2 and 0.8 respectively, and rhp is the user's mental health assessment value.

[0112] The MEMD transformation and MVMD transformation refer to multivariate empirical mode decomposition transformation and multivariate variational mode decomposition transformation respectively.

[0113] The entire assessment process of this invention is based on objectively collected physiological signals, reducing the subjective influence of the assessee in traditional psychological questionnaire assessments. Electrodermal and electroencephalographic signals are objective reflections of the human body's physiological state and are not influenced by the assessee's subjective wishes. By scientifically processing and analyzing these objective signals, more objective and reliable psychological health assessment results can be obtained.

[0114] This invention uses an EGG wristband and a brain-computer interface device to collect real-time EGG and EEG signals, enabling real-time monitoring of a user's mental health. This convenient and quick way for users to collect signals and conduct mental health assessments anytime, anywhere eliminates the need to visit a medical facility or schedule assessments. This helps identify changes in mental status and facilitates early intervention.

[0115] Compared to traditional face-to-face assessments with professional doctors, this method eliminates the need for a large number of specialized doctors, reducing labor costs. Furthermore, the relatively low-cost and reusable electrodermal wristbands and brain-computer interface devices enable large-scale mental health screening and long-term individual mental health monitoring at a low cost, with significant economic and social benefits.

[0116] In a second aspect of an embodiment of the present invention, a mental health assessment device based on an electrodermal wristband and a brain-computer interface is disclosed, the device comprising:

[0117] a memory storing executable program code;

[0118] a processor coupled to the memory;

[0119] The processor calls the executable program code stored in the memory to execute the mental health assessment method based on the electrodermal bracelet and brain-computer interface.

[0120] In a third aspect of an embodiment of the present invention, a computer-storable medium is disclosed, which stores computer instructions. When the computer instructions are called by a computer, they are used to execute the mental health assessment method based on an electrodermal bracelet and a brain-computer interface.

[0121] In a fourth aspect of an embodiment of the present invention, an information data processing terminal is disclosed, which is used to implement the mental health assessment method based on an electrodermal bracelet and a brain-computer interface.

[0122] The foregoing is merely an embodiment of the present invention and is not intended to limit the present invention. It will be apparent to those skilled in the art that various modifications and variations of the present invention are possible. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention are intended to be included within the scope of the claims of the present invention.

Claims

1. A mental health assessment method based on an electrodermal wristband and a brain-computer interface, characterized in that: include: S1, collecting and obtaining a user's electrodermal signal sequence set and an electroencephalogram signal set; the electrodermal signal sequence set includes an electrodermal signal sequence; the electroencephalogram signal set includes an α wave signal sequence, a β wave signal sequence, a θ wave signal sequence, and a δ wave signal sequence; S2, preprocessing the electrodermal signal sequence set and the electroencephalogram signal set to obtain a signal set to be evaluated; S3, performing psychological health assessment processing on the set of signals to be assessed to obtain a psychological health assessment value of the user.

2. The mental health assessment method based on an electrodermal wristband and a brain-computer interface according to claim 1, characterized in that: The preprocessing of the electrodermal signal sequence set and the electroencephalogram signal set to obtain a signal set to be evaluated includes: S21, performing data cleaning processing on the electrodermal signal sequence set and the electroencephalogram signal set to obtain a first signal set; S22, performing time alignment processing on the first signal set to obtain a second signal set; S23: Perform model cross detection processing on the second signal set to obtain a signal set to be evaluated.

3. The mental health assessment method based on an electrodermal wristband and a brain-computer interface as claimed in claim 2, characterized in that: The performing model cross detection processing on the second signal set to obtain a signal set to be evaluated includes: S2301, performing autoregressive-sliding average modeling on the data of the electrodermal signal sequence set of the second signal set, using the data collection time of all data as an independent variable and the data value of all data as a dependent variable to obtain a regression model; S2302: for each data item in each type of signal sequence of the electroencephalogram signal set of the second signal set, using the data collection time of the data item as an independent variable, calculate the independent variable using the regression model to obtain a regression value corresponding to the data item; S2303, determining whether the difference between the data and the corresponding regression value is less than a preset first discrimination threshold, and obtaining a first discrimination result; S2304, deleting data with the first discrimination result of not less than from the EEG signal set of the second signal set to obtain a preprocessed EEG signal set; S2305, constructing a signal matrix using each type of signal sequence of the electroencephalogram signal set of the second signal set as a row vector; S2306, performing singular value calculation processing on the signal matrix to obtain a singular value sequence; S2307, taking the element values ​​of the singular value sequence as known dependent variables and the element numbers of the singular value sequence as known independent variables, constructing a curve to be approximated using the known independent variables and the known dependent variables; performing polynomial fitting on the curve to be approximated to obtain an approximation model; S2308: For each data in the electrodermal signal set of the second signal set, using the data collection time of the data as an independent variable, calculate the independent variable using the approximation model to obtain a regression value corresponding to the data; S2309, determining whether the difference between the data and the corresponding regression value is less than a preset second discrimination threshold, and obtaining a second discrimination result; S2310, deleting data with the second discrimination result of not less than from the electrical skin signal sequence set of the second signal set to obtain a preprocessed electrical skin signal sequence set; S2311 , constructing a signal set to be evaluated using the preprocessed electrodermal signal sequence set and the preprocessed electroencephalogram signal set.

4. The mental health assessment method based on an electrodermal wristband and a brain-computer interface according to claim 1, characterized in that: The performing mental health assessment processing on the set of signals to be assessed to obtain a mental health assessment value of the user includes: S31, performing skin electrical state monitoring processing on the skin electrical signal sequence set in the signal set to be evaluated to obtain a skin electrical state monitoring value; S32, performing fusion evaluation processing on the EEG signal set in the signal set to be evaluated to obtain an EEG evaluation value; S33, using a preset psychological state fusion assessment model, calculating and processing the electrodermal state monitoring value and the EEG assessment value to obtain the user's psychological health assessment value.

5. The mental health assessment method based on an electrodermal wristband and a brain-computer interface as claimed in claim 4, characterized in that: The performing skin electrical state monitoring processing on the skin electrical signal sequence set in the signal set to be evaluated to obtain the skin electrical state monitoring value includes: S311, obtaining a standard sequence of electrodermal signals; S312, subtracting the set of electrical skin signal sequences from the standard sequence of electrical skin signals to obtain a set of electrical skin difference signals; the set of electrical skin difference signals includes an electrical skin difference sequence; the electrical skin difference sequence is an electrical skin signal sequence in the set of electrical skin signal sequences, obtained by subtracting the standard sequence of electrical skin signals from the standard sequence of electrical skin signals; S313, performing statistical analysis on the set of electrodermal difference signals to obtain a set of statistical values; S314: Perform pattern fusion calculation on the statistical value set to obtain a skin electrical state monitoring value.

6. The mental health assessment method based on an electrodermal wristband and a brain-computer interface according to claim 5, characterized in that: The expression for the statistical analysis process is: Where Tj is the statistical value of the jth skin electrical difference sequence in the skin electrical difference signal set, the statistical analysis value, p ji is the probability of occurrence of the data value of the jth skin electrical difference sequence in the skin electrical difference signal set within the i-th value interval, p jmax and p jave are the maximum and average values ​​of all occurrence probabilities of the jth skin electrical difference sequence in the skin electrical difference signal set, N1 is the number of value intervals of the skin electrical difference signal set, and the statistical value set includes the statistical values ​​of all skin electrical difference sequences in the skin electrical difference signal set; The expression of the mode fusion calculation is: Wherein, spd is the skin electrical status monitoring value, μ and η are the mean and variance of all statistical values ​​of the statistical value set respectively.

7. The mental health assessment method based on an electrodermal wristband and a brain-computer interface as claimed in claim 5, characterized in that: The performing fusion evaluation processing on the EEG signal set in the signal set to be evaluated to obtain an EEG evaluation value includes: Performing MEMD transformation and MVMD transformation on the α wave signal sequence and the β wave signal sequence in the EEG signal set in the signal set to be evaluated, respectively, to obtain an α wave transformation sequence and a β wave transformation sequence; performing feature extraction processing on the α wave transformation sequence and the β wave transformation sequence to obtain a first EEG evaluation component; Obtaining a θ wave standard signal and a δ wave standard signal; Subtracting the θ wave signal sequence and the δ wave signal sequence in the EEG signal set in the signal set to be evaluated from the θ wave standard signal and the δ wave standard signal, respectively, to obtain corresponding θ wave difference signals and δ wave difference signals; Performing a mutual mode transformation calculation on the θ wave difference signal and the δ wave difference signal to obtain a second EEG evaluation component; A weighted sum is performed on the first EEG evaluation component and the second EEG evaluation component to obtain an EEG evaluation value.

8. A mental health assessment device based on an electrodermal wristband and a brain-computer interface, characterized in that: The device comprises: a memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the mental health assessment method based on an electrodermal bracelet and a brain-computer interface as described in any one of claims 1 to 7.

9. A computer storable medium, characterized in that The computer storable medium stores computer instructions, which, when called by a computer, are used to execute the mental health assessment method based on an electrodermal bracelet and a brain-computer interface as described in any one of claims 1 to 7.

10. An information data processing terminal, characterized in that: The information data processing terminal is used to implement the mental health assessment method based on an electrodermal bracelet and a brain-computer interface as described in any one of claims 1 to 7.

Images