CN116434957A - Psychological health state identification and assessment method - Google Patents

Psychological health state identification and assessment method Download PDF

Info

Publication number
CN116434957A
CN116434957A CN202310340274.4A CN202310340274A CN116434957A CN 116434957 A CN116434957 A CN 116434957A CN 202310340274 A CN202310340274 A CN 202310340274A CN 116434957 A CN116434957 A CN 116434957A
Authority
CN
China
Prior art keywords
data
individual
questionnaire
network
cloud database
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.)
Withdrawn
Application number
CN202310340274.4A
Other languages
Chinese (zh)
Inventor
蔡培培
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Heilongjiang Economic Management Cadre College
Original Assignee
Heilongjiang Economic Management Cadre College
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Heilongjiang Economic Management Cadre College filed Critical Heilongjiang Economic Management Cadre College
Priority to CN202310340274.4A priority Critical patent/CN116434957A/en
Publication of CN116434957A publication Critical patent/CN116434957A/en
Withdrawn legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/22—Matching criteria, e.g. proximity measures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/084—Backpropagation, e.g. using gradient descent
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
    • G16H20/70—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to mental therapies, e.g. psychological therapy or autogenous training
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
    • Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Health & Medical Sciences (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Public Health (AREA)
  • Medical Informatics (AREA)
  • General Health & Medical Sciences (AREA)
  • Evolutionary Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Epidemiology (AREA)
  • Primary Health Care (AREA)
  • Biomedical Technology (AREA)
  • Databases & Information Systems (AREA)
  • Psychology (AREA)
  • Developmental Disabilities (AREA)
  • Child & Adolescent Psychology (AREA)
  • Psychiatry (AREA)
  • Pathology (AREA)
  • Social Psychology (AREA)
  • Hospice & Palliative Care (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)

Abstract

The invention discloses a method for identifying and evaluating mental health states, which particularly relates to the technical field of mental health evaluation.

Description

Psychological health state identification and assessment method
Technical Field
The invention relates to the technical field of mental health assessment, in particular to a method for identifying and assessing mental health.
Background
People can easily induce various psychological diseases under the long-term and fast-paced life, work and study pressure, and the life quality and physical and mental health of people are affected. For example, many urban white collars are trapped by high working pressures, are in a highly stressed state for a long period of time, often cannot be conditioned in time, produce symptoms such as anxiety, mental depression and the like over time, and seriously induce psychological disorders or mental diseases. Typically, the first step in providing mental health services is to evaluate an individual's mental health. The psychological health state assessment is a method for evaluating and measuring psychological characteristics (cognition, emotion, personality, ability, behavior mode and the like), psychological states and levels of people according to psychological principles and methods and determining reasons, properties and degrees of normal or abnormal states of the people, so that basis is provided for clinical psychological diagnosis.
The reasons for psychological health problems mainly comprise interpersonal interaction, employment stress, self-management ability, affective problems, life development, environmental inadaptation, learning pressure and the like, when psychological problems are encountered, most students choose to complain to friends and families, but a considerable part of people choose not to find any person, so that the psychological problems can not be effectively solved for a long time due to the behaviors of being highly contraindicated and extremely disguised, the occurrence of crisis psychology can be caused by the accumulation of negative emotion over time, normal personal life and social order can be seriously influenced, even extreme events occur, and psychological health assessment and identification have important significance to society and individuals, so that research on a psychological health state identification and assessment method has important significance.
Disclosure of Invention
In order to overcome the defects in the prior art, the invention provides a method for identifying and evaluating mental health state, which aims to solve the technical problems that: the problems mentioned above.
In order to achieve the above purpose, the present invention provides the following technical solutions: a method for identifying and assessing mental health, comprising the steps of:
s1, acquiring data, namely acquiring test data of an individual to be evaluated, and storing the acquired data and the data subjected to evaluation into a cloud database;
s2, data preprocessing, namely firstly calling data in a cloud database according to the obtained test data, taking the data in the called cloud database as training and test samples, and adopting a noise reduction algorithm to perform preprocessing on the obtained test data to obtain processed individual test data;
s3, identifying and evaluating, wherein an evaluation model is adopted to obtain an evaluation result of the psychological health state of the individual on the individual test data.
The individual data comprise video data, questionnaire survey data and network data, wherein the video data are videos of individuals in natural life and are used for extracting instrument features, physical features, language action features and interpersonal interaction features of the individuals, the questionnaire survey data are questionnaires or answer questionnaires which are designed for the individuals to be filled in, the network data are individual network behavior data, and the network behavior data comprise network paths used by the individuals, network use time periods, network use time nodes and network browsing page types;
processing an image by adopting an image noise reduction mode when the video data is acquired;
the questionnaire survey adopts an Eisense personality questionnaire, a Kart 16 personality questionnaires, a Back depression self-evaluation questionnaire, a state-feature anxiety questionnaire, a Wisconsin card classification test, a mental cognition ability test, a coping mode questionnaire and a social support rating scale;
the network data is acquired by adopting a web crawler mode.
The Eisense personality questionnaire and the Kart 16 personality questionnaires are used for testing individuality of an individual, the Back depression self-evaluation questionnaire and the state-property anxiety questionnaire are used for testing emotion aspects of the individual, the Wisconsin card classification test and the mental cognition test are used for testing cognition aspects of the individual, and the coping questionnaire and the social support rating scale are used for testing psychological stress aspects of the individual.
The invoking of the data in the cloud database comprises the following steps:
extracting the characteristics of the acquired individual test data;
extracting features of data in the cloud database;
matching the characteristics of the individual test data and the data in the cloud database, wherein the matching degree is more than 75%;
and calling the data which accords with the matching degree in the cloud database.
Training the model by adopting the data extracted from the cloud database, and testing the model by adopting the data extracted from the cloud database after the model is constructed;
the evaluation model employs the following algorithm:
the BP neural network learning algorithm is as follows: along the error function e p Correcting W along with the negative gradient direction of W, iterating repeatedly until convergence,
d p ＝|t p -y p |
Figure BDA0004157885640000031
Figure BDA0004157885640000032
Figure BDA0004157885640000033
wherein t is p Is the sample output, y p Is network output, eta is E (0, 1) is learning rate, w ij ，v ij Respectively input layer to hidden layer, connection weight value between hidden layer and output layer, theta i Is a hidden layer neuron threshold value, and the algorithm is improved by introducing a momentum factor alpha:
Figure BDA0004157885640000034
support vector algorithm:
linear regression function
f(x)＝(ω+x)+b
Fitting training sample sets
D＝{(x i ,y i )},i＝1,2,…,n,x i ∈R d ,y i ∈R
y i f(x i )＝y i (ω T x i +b)≥1,fori＝1，…M
Assuming that all training data is fitted with a linear function without error at the precision epsilon,
Figure BDA0004157885640000041
the optimization targets are as follows:
Figure BDA0004157885640000042
introducing a relaxation variable ζ i And
Figure BDA00041578856400000411
get a description of its dual problem:
Figure BDA0004157885640000043
Figure BDA0004157885640000044
wherein,,
Figure BDA0004157885640000045
c is a penalty term beyond the error samples, +.>
Figure BDA0004157885640000046
The corresponding point is the support vector, and the obtained regression function is
Figure BDA0004157885640000047
The linear regression problem is converted into a linear problem in a high-dimensional space by nonlinear transformation using a kernel function K (x i ·x j ) Instead of the original inner product operation (x i ·x j ) Performing linear regression in a high-dimensional space;
the information fusion is carried out by adopting the particle swarm optimized segmentation Gaussian weight factors, the information fusion is carried out by taking a neural network and a support vector machine as different evidence bodies, and the mathematical model is as follows:
Figure BDA0004157885640000048
Figure BDA0004157885640000049
Figure BDA00041578856400000410
wherein xi 1 ，ξ 2 The gaussian weights of the two training models are respectively used for optimizing the gaussian function variance sigma by a particle swarm optimization algorithm PSO.
Introducing training mean square error mse 1 And measuring point vector similarity gamma, obtaining self-adjusting factor set A γ Further perfecting the fusion model:
Figure BDA0004157885640000051
γ i ＝α·β
Figure BDA0004157885640000052
Figure BDA0004157885640000053
Figure BDA0004157885640000054
wherein Δη i,j ，Δη 0,j And TP i,j Respectively, in the i-th health mode, the estimated value, the true value and the measuring point vector of the parameter change in the j-th, alpha and beta are the norm similarity and the direction similarity of the vector in sequence, M is the number of the health modes, K is the total number of the parameter change conditions in a certain mode,
Figure BDA0004157885640000055
is a curve fitting function with gamma as an argument.
Personality: the close relationship between individuality and health is often ignored in the past, and along with the development of the long-term medical psychology and the transition of medical modes, the role of individuality factors in health and disease transformation is more and more important for people. It has surprisingly been found that persons with similar personality and spleen qi have similar disease. Therefore, in health management, psychological characteristics such as individual characteristics, air quality type, and behavioral style of the service target must be comprehensively grasped. The psychological test and evaluation tools commonly used for personality characteristics at present comprise a Katel 16 personality factor questionnaire, an Eyehuman personality questionnaire, an A-type behavior type questionnaire and the like.
Emotion: among the numerous psychological elements, the relationship between emotion and health is the most compact, and the fluctuation of emotion causes changes in various systems of the body, such as autonomic nervous system, endocrine system, respiratory system, digestive system, etc. Emotional health is thus an important component of physical and mental health, including in particular: possess positive emotional experiences such as happiness, happiness; the emotional response consistent with the environment, namely, the emotional response is unified with the external environmental stimulus; ability to control emotional experience. In health management, negative emotions are improved, positive emotion experiences are cultivated, and the health management method has a promoting effect on physical health and is a necessary means for realizing the highest boundary of health. The current common assessment tools for emotion at home and abroad comprise an overall happiness scale, a life satisfaction degree, a Beck depression self-assessment questionnaire, a state-feature anxiety questionnaire, an anxiety self-assessment scale, a Chinese emotion quotient scale and the like.
Cognition: the cognitive psychological component includes various aspects of perception, memory, thinking, language, attention, etc., which are based on the division of the information processing process. Any process functional or organic deficiency can lead to a decrease in the individual's ability to live and even increase the individual's health risk. For example, the individual has pain defect and is excessively desensitized to pain, at the moment, the individual cannot feel possible lesions and injuries of the individual, and the individual cannot treat the lesions and injuries in time, so that the illness state is finally worsened; for individuals with memory function defects, many health risks exist in life, such as getting lost, forgetting to turn off gas, forgetting to take medicines on time, and the like. Therefore, in the process of health management, it is very important to evaluate the cognitive ability of an individual, which not only can provide a reference for the individual to reduce the health risk, but also can discover the problem of cognitive deficiency and perform intervention in advance, and this information is very important, for example, research shows that the development of relevant treatment intervention before the onset of senile dementia can effectively reduce the possibility of the onset of senile dementia or delay the occurrence age of senile dementia. Currently, psychological assessment tools for cognitive competence are the halstead-Reitan neuropsychological suite test, the Wisconsin card class test, the mental cognitive competence test and the like.
Psychological stress: stress generally refers to tension and stress. When the body is in a stress state, the environmental balance in the body is influenced by a series of changes of nervous system, neurobiochemical, neuroendocrine, immune system and the like, and organic dysfunction occurs, so that structural changes are generated. It has double effects on health. Advantageous aspects are that: can mobilize nonspecific adaptation system of organism, produce resistance to diseases, and strengthen constitution and adaptability. Adverse aspects: the failure of the adaptation mechanism can lead to psychological, behavioral and physical disorders of different degrees, so that the emotions such as anxiety, fear, depression and the like are generated to lead the emotions to be easy to fluctuate, easy to anger, easy to fatigue, further have the advantages of distraction, memory decline, low working efficiency and the like, and are closely related to the occurrence of certain mental diseases, such as neurosis, psychogenic mental disorder, heart body diseases and the like. The pressure management is an important component of the health management, and the evaluation information related to the psychological stress of the health management service object can provide scientific basis for the pressure management, and the current evaluation tools related to the psychological stress at home and abroad comprise life event scales, response mode questionnaires, social support rating scales, professional burnout scales and the like.
The invention has the beneficial effects that:
1. the invention acquires the video data, questionnaire survey data and network data of the individual, realizes the questionnaire survey on the aspects of instrument features, physical features, language action features and interpersonal interaction features of the individual, and the individual's own personality, emotion, cognition and psychological stress, wherein the network data comprises the individual use network path, network use time length and network use time node, and the network browse page type, acquires and analyzes the data of the individual in multiple aspects, more comprehensively and intuitively judges the psychological health state of the individual, greatly improves the comprehensiveness of the data and ensures the accuracy of the subsequent evaluation result;
2. according to the invention, an evaluation model obtained by fusing a neural network algorithm and a support vector algorithm is adopted, the characteristics of the obtained test data of the individual are extracted, the characteristics of the data stored in a cloud database are extracted, the data in the cloud database with the characteristic matching degree with the individual test data of more than 75% is called as a training sample and a test sample, and the finally obtained model is ensured to be more fit with the actual data of the individual.
Detailed Description
The technical solutions in the embodiments of the present invention are clearly and completely described, and it is obvious that the described embodiments are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The invention provides a method for identifying and evaluating psychological health status, which comprises the following steps:
s1, acquiring data, namely acquiring test data of an individual to be evaluated, and storing the acquired data and the data subjected to evaluation into a cloud database;
s2, data preprocessing, namely firstly calling data in a cloud database according to the obtained test data, taking the data in the called cloud database as training and test samples, and adopting a noise reduction algorithm to perform preprocessing on the obtained test data to obtain processed individual test data;
s3, identifying and evaluating, wherein an evaluation model is adopted to obtain an evaluation result of the psychological health state of the individual on the individual test data.
The individual data comprise video data, questionnaire survey data and network data, wherein the video data is video of an individual in natural life, is used for extracting instrument characteristics, physical characteristics, language action characteristics and interpersonal interaction characteristics of the individual, the questionnaire survey data fills out questionnaires or answers questionnaires which are designed for the individual, the network data is individual network behavior data, and the network behavior data comprises individual network paths, network use time periods, network use time nodes and network browsing page types;
processing the image by adopting an image noise reduction mode when the video data is acquired;
the questionnaire survey adopts an Eisense personality questionnaire, a Kart 16 personality questionnaires, a Back depression self-evaluation questionnaire, a state-feature anxiety questionnaire, a Wisconsin card class test, a mental cognition ability test, a coping mode questionnaire and a social support rating scale;
the network data is acquired by adopting a web crawler mode.
The personal questionnaire of the Eisense and the 16 personal questionnaires of the Kart are used for testing the individuality of the individuals, the self-evaluation questionnaire of the Back depression and the state-property anxiety questionnaire are used for testing the emotion aspect of the individuals, the Wisconsin card classification test and the mental cognition test are used for testing the cognition aspect of the individuals, and the coping questionnaire and the social support rating scale are used for testing the psychological stress aspect of the individuals.
The invoking of the data in the cloud database comprises the following steps:
extracting the characteristics of the acquired individual test data;
extracting features of data in the cloud database;
matching the characteristics of the individual test data and the data in the cloud database, wherein the matching degree is more than 75%;
and calling the data which accords with the matching degree in the cloud database.
Training a model by adopting data extracted from a cloud database, and testing the model by adopting the data extracted from the cloud database after the model is constructed;
the evaluation model employs the following algorithm:
the BP neural network learning algorithm is as follows: along the error function e p Correcting W along with the negative gradient direction of W, iterating repeatedly until convergence,
d p ＝|t p -y p |
Figure BDA0004157885640000091
Figure BDA0004157885640000092
Figure BDA0004157885640000093
wherein t is p Is the sample output, y p Is network output, eta is E (0, 1) is learning rate, w ij ，v ij Respectively input layer to hidden layer, connection weight value between hidden layer and output layer, theta i Is a hidden layer neuron threshold value, and the algorithm is improved by introducing a momentum factor alpha:
Figure BDA0004157885640000094
support vector algorithm:
linear regression function
f(x)＝(ω+x)+b
Fitting training sample sets
D＝{(x i ,y i )},i＝1,2,…,n,x i ∈R d ,y i ∈R
y i f(x i )＝y i (ω T x i +b)≥1,fori＝1，…M
Assuming that all training data is fitted with a linear function without error at the precision epsilon,
Figure BDA0004157885640000101
the optimization targets are as follows:
Figure BDA0004157885640000102
introducing a relaxation variable ζ i And
Figure BDA00041578856400001011
get a description of its dual problem:
Figure BDA0004157885640000103
Figure BDA0004157885640000104
wherein,,
Figure BDA0004157885640000105
c is a penalty term beyond the error samples, +.>
Figure BDA0004157885640000106
The corresponding point is the support vector, and the obtained regression function is
Figure BDA0004157885640000107
The linear regression problem is converted into a linear problem in a high-dimensional space by nonlinear transformation using a kernel function K (x i ·x j ) Instead of the original inner product operation (x i ·x j ) Linear regression is performed in a high-dimensional space,
the information fusion is carried out by adopting the particle swarm optimized segmentation Gaussian weight factors, the information fusion is carried out by taking a neural network and a support vector machine as different evidence bodies, and the mathematical model is as follows:
Figure BDA0004157885640000108
Figure BDA0004157885640000109
Figure BDA00041578856400001010
wherein xi 1 ，ξ 2 The gaussian weights of the two training models are respectively used for optimizing the gaussian function variance sigma by a particle swarm optimization algorithm PSO.
Introducing training mean square error mse 1 And measuring point vector similarity gamma, obtaining self-adjusting factor set A γ Further perfecting the fusion model:
Figure BDA0004157885640000111
γ i ＝α·β
Figure BDA0004157885640000112
Figure BDA0004157885640000113
Figure BDA0004157885640000114
wherein Δη i,j ，Δη 0,j And TP i,j Respectively, in the i-th health mode, the estimated value, the true value and the measuring point vector of the parameter change in the j-th, alpha and beta are the norm similarity and the direction similarity of the vector in sequence, M is the number of the health modes, K is the total number of the parameter change conditions in a certain mode,
Figure BDA0004157885640000115
is a curve fitting function with gamma as an argument.
To sum up, in the present invention:
the invention acquires the video data, questionnaire survey data and network data of the individual, realizes the questionnaire survey on the aspects of instrument features, physical features, language action features and interpersonal interaction features of the individual, and the individual's own personality, emotion, cognition and psychological stress, wherein the network data comprises the individual use network path, network use time length and network use time node, and the network browse page type, acquires and analyzes the data of the individual in multiple aspects, more comprehensively and intuitively judges the psychological health state of the individual, greatly improves the comprehensiveness of the data and ensures the accuracy of the subsequent evaluation result.
According to the invention, an evaluation model obtained by fusing a neural network algorithm and a support vector algorithm is adopted, the characteristics of the obtained test data of the individual are extracted, the characteristics of the data stored in a cloud database are extracted, the data in the cloud database with the characteristic matching degree with the individual test data of more than 75% is called as a training sample and a test sample, and the finally obtained model is ensured to be more fit with the actual data of the individual.
Only the structures related to the embodiments of the present disclosure are referred to, other structures may refer to the general design, and the same embodiment and different embodiments of the present disclosure may be combined with each other without conflict;
finally: the foregoing description of the preferred embodiments of the invention is not intended to limit the invention to the precise form disclosed, and any such modifications, equivalents, and alternatives falling within the spirit and principles of the invention are intended to be included within the scope of the invention.

Claims (5)

1. A method for identifying and assessing mental health, comprising the steps of:
s1, acquiring data, namely acquiring test data of an individual to be evaluated, and storing the acquired data and the data subjected to evaluation into a cloud database;
s2, data preprocessing, namely firstly calling data in a cloud database according to the obtained test data, taking the data in the called cloud database as training and test samples, and adopting a noise reduction algorithm to perform preprocessing on the obtained test data to obtain processed individual test data;
s3, identifying and evaluating, wherein an evaluation model is adopted to obtain an evaluation result of the psychological health state of the individual on the individual test data.
2. The method for identifying and assessing the state of mental health of claim 1, wherein: the individual data comprise video data, questionnaire survey data and network data, wherein the video data are videos of individuals in natural life and are used for extracting instrument features, physical features, language action features and interpersonal interaction features of the individuals, the questionnaire survey data are questionnaires or answer questionnaires which are designed for the individuals to be filled in, the network data are individual network behavior data, and the network behavior data comprise network paths used by the individuals, network use time periods, network use time nodes and network browsing page types;
processing an image by adopting an image noise reduction mode when the video data is acquired;
the questionnaire survey adopts an Eisense personality questionnaire, a Kart 16 personality questionnaires, a Back depression self-evaluation questionnaire, a state-feature anxiety questionnaire, a Wisconsin card classification test, a mental cognition ability test, a coping mode questionnaire and a social support rating scale;
the network data is acquired by adopting a web crawler mode.
3. The method for identifying and assessing a mental health of claim 2, wherein: the Eisense personality questionnaire and the Kart 16 personality questionnaires are used for testing individuality of an individual, the Back depression self-evaluation questionnaire and the state-property anxiety questionnaire are used for testing emotion aspects of the individual, the Wisconsin card classification test and the mental cognition test are used for testing cognition aspects of the individual, and the coping questionnaire and the social support rating scale are used for testing psychological stress aspects of the individual.
4. The method for identifying and assessing the state of mental health of claim 1, wherein: the invoking of the data in the cloud database comprises the following steps:
extracting the characteristics of the acquired individual test data;
extracting features of data in the cloud database;
matching the characteristics of the individual test data and the data in the cloud database, wherein the matching degree is more than 75%;
and calling the data which accords with the matching degree in the cloud database.
5. The method for identifying and assessing the state of mental health of claim 1, wherein: training the model by adopting the data extracted from the cloud database, and testing the model by adopting the data extracted from the cloud database after the model is constructed;
the evaluation model employs the following algorithm:
the BP neural network learning algorithm is as follows: along the error function e p Correcting W along with the negative gradient direction of W, iterating repeatedly until convergence,
d p ＝|t p -y p |
Figure FDA0004157885630000021
Figure FDA0004157885630000022
Figure FDA0004157885630000023
wherein t is p Is the sample output, y p Is network output, eta is E (0, 1) is learning rate, w ij ，v ij Respectively input layer to hidden layer, connection weight value between hidden layer and output layer, theta i Is a hidden layer neuron threshold value, and the algorithm is improved by introducing a momentum factor alpha:
Figure FDA0004157885630000024
support vector algorithm:
linear regression function
f(x)＝(ω+x)+b
Fitting training sample sets
D＝{(x i ,y i )},i＝1,2,…,n,x i ∈R d ,y i ∈R
y i f(x i )＝y i (ω T x i +b)≥1,fori＝1，…M
Assuming that all training data is fitted with a linear function without error at the precision epsilon,
Figure FDA0004157885630000031
the optimization targets are as follows:
Figure FDA0004157885630000032
introducing a relaxation variable ζ i And
Figure FDA0004157885630000033
get a description of its dual problem:
Figure FDA0004157885630000034
wherein,,
Figure FDA0004157885630000035
c is a penalty term beyond the error samples, +.>
Figure FDA0004157885630000036
The corresponding point is the support vector, and the obtained regression function is
Figure FDA00041578856300000310
The linear regression problem is converted into a linear problem in a high-dimensional space by nonlinear transformation using a kernel function K (x i ·x j ) Instead of the original inner product operation (x i ·x j ) Linear regression is performed in a high-dimensional space,
the information fusion is carried out by adopting the particle swarm optimized segmentation Gaussian weight factors, the information fusion is carried out by taking a neural network and a support vector machine as different evidence bodies, and the mathematical model is as follows:
Figure FDA0004157885630000037
Figure FDA0004157885630000038
Figure FDA0004157885630000039
wherein xi 1 ，ξ 2 The gaussian weights of the two training models are respectively used for optimizing the gaussian function variance sigma by a particle swarm optimization algorithm PSO.
Introducing training mean square error mse 1 And measuring point vector similarity gamma, obtaining self-adjusting factor set A γ Further perfecting the fusion model:
γ i ＝α·β
Figure FDA0004157885630000042
Figure FDA0004157885630000043
Figure FDA0004157885630000044
wherein Δη i,j ，Δη 0,j And TP i,j Respectively, in the i-th health mode, the estimated value, the true value and the measuring point vector of the parameter change in the j-th, alpha and beta are the norm similarity and the direction similarity of the vector in sequence, M is the number of the health modes, K is the total number of the parameter change conditions in a certain mode,
Figure FDA0004157885630000045
is a curve fitting function with gamma as an argument.
CN202310340274.4A 2023-04-03 2023-04-03 Psychological health state identification and assessment method Withdrawn CN116434957A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310340274.4A CN116434957A (en) 2023-04-03 2023-04-03 Psychological health state identification and assessment method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310340274.4A CN116434957A (en) 2023-04-03 2023-04-03 Psychological health state identification and assessment method

Publications (1)

Publication Number Publication Date
CN116434957A true CN116434957A (en) 2023-07-14

Family

ID=87086653

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310340274.4A Withdrawn CN116434957A (en) 2023-04-03 2023-04-03 Psychological health state identification and assessment method

Country Status (1)

Country Link
CN (1) CN116434957A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117524422B (en) * 2024-01-08 2024-03-26 青岛理工大学 Evaluation system and method for improving stress recovery of human body based on indoor green planting

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117524422B (en) * 2024-01-08 2024-03-26 青岛理工大学 Evaluation system and method for improving stress recovery of human body based on indoor green planting

Similar Documents

Publication Publication Date Title
Miller et al. Using online, crowdsourcing platforms for data collection in personality disorder research: The example of Amazon’s Mechanical Turk.
Haynes et al. Idiographic assessment: Conceptual and psychometric foundations of individualized behavioral assessment
McCreary et al. The drive for muscularity and masculinity: testing the associations among gender-role traits, behaviors, attitudes, and conflict.
Ganong et al. Multiple segment factorial vignette designs
Sherman et al. Situational similarity and personality predict behavioral consistency.
Bègue et al. Two spheres of belief in justice: Extensive support for the bidimensional model of belief in a just world
Matsumoto et al. Psychological skills related to intercultural adjustment
CN112820371B (en) Health recommendation system and method based on medical knowledge map
Sander et al. Predictors of emotional distress in family caregivers of persons with traumatic brain injury: A systematic review
Krause et al. Evaluating the relationships among religion, social virtues, and meaning in life
Love Demographic differences in organizational commitment to the university of college of business administration students: An application of the Allen and Meyer model
Keller-Schneider Job demands appraisals, classroom climate, and team support predict changes in emotional exhaustion among teachers after two years: A sequential mediation model
Seidman et al. Setting the stage: The effect of affirming personal values before psychotherapy intake screenings on perceptions of self-stigma and self-disclosure.
Lyons et al. Benefits of a self-management program for the couple living with Parkinson’s disease: a pilot study
Cramer et al. Can preferences in information processing aid in understanding suicide risk among emerging adults?
CN116434957A (en) Psychological health state identification and assessment method
van Zyl et al. Mental health, work engagement and meaningful work-role fit of industrial psychologists: a latent profile analysis
Marinescu et al. Conceptual approaches in quality of life assessment for the elderly
Haradhvala Meta-emotions in daily life: Associations with emotional awareness and depression
Hosemans Meditation: a process of cultivating enhanced well-being
Sluta et al. The role of psychological factors in imroving health, activity and longevity
Amani et al. The Structural Model of Emotional Divorce based on Neuroticism through the Mediating Role of coping strategies and emotional regulation
Wang et al. Exploring risk factors and their differences on suicidal ideation and suicide attempts among depressed adolescents based on decision tree model
Campbell Cognitive representation of challenging behaviour among staff working with adults with learning disabilities
Alayed et al. An Arabic Intelligent Diagnosis Assistant for Psychologists using Deep Learning

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
WW01 Invention patent application withdrawn after publication
WW01 Invention patent application withdrawn after publication

Application publication date: 20230714