CN112185558A - Mental health and rehabilitation evaluation method, device and medium based on deep learning - Google Patents
Mental health and rehabilitation evaluation method, device and medium based on deep learning Download PDFInfo
- Publication number
- CN112185558A CN112185558A CN202011004525.4A CN202011004525A CN112185558A CN 112185558 A CN112185558 A CN 112185558A CN 202011004525 A CN202011004525 A CN 202011004525A CN 112185558 A CN112185558 A CN 112185558A
- Authority
- CN
- China
- Prior art keywords
- data
- mental health
- rehabilitation
- deep learning
- assessment
- 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
- 230000004630 mental health Effects 0.000 title claims abstract description 100
- 238000013135 deep learning Methods 0.000 title claims abstract description 51
- 238000011156 evaluation Methods 0.000 title claims abstract description 30
- 238000000034 method Methods 0.000 claims abstract description 41
- 238000012549 training Methods 0.000 claims abstract description 19
- 208000019901 Anxiety disease Diseases 0.000 claims description 19
- 230000036506 anxiety Effects 0.000 claims description 19
- 208000007848 Alcoholism Diseases 0.000 claims description 13
- 208000025746 alcohol use disease Diseases 0.000 claims description 13
- 230000006399 behavior Effects 0.000 claims description 10
- 238000012795 verification Methods 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 8
- 230000003340 mental effect Effects 0.000 claims description 8
- LFQSCWFLJHTTHZ-UHFFFAOYSA-N Ethanol Chemical compound CCO LFQSCWFLJHTTHZ-UHFFFAOYSA-N 0.000 claims description 6
- 238000004422 calculation algorithm Methods 0.000 claims description 6
- 238000013095 identification testing Methods 0.000 claims description 6
- 230000015654 memory Effects 0.000 claims description 6
- 238000011160 research Methods 0.000 claims description 6
- 230000006403 short-term memory Effects 0.000 claims description 6
- 238000013145 classification model Methods 0.000 claims description 5
- 230000007613 environmental effect Effects 0.000 claims description 5
- 230000007787 long-term memory Effects 0.000 claims description 5
- 238000003058 natural language processing Methods 0.000 claims description 4
- 230000008451 emotion Effects 0.000 claims description 3
- 238000013139 quantization Methods 0.000 claims description 3
- 238000011084 recovery Methods 0.000 claims 2
- 238000004458 analytical method Methods 0.000 abstract description 4
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 238000013210 evaluation model Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 14
- 238000003745 diagnosis Methods 0.000 description 6
- 201000010099 disease Diseases 0.000 description 6
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 4
- 208000020016 psychiatric disease Diseases 0.000 description 4
- 238000013473 artificial intelligence Methods 0.000 description 3
- 230000002452 interceptive effect Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000009323 psychological health Effects 0.000 description 2
- 230000035945 sensitivity Effects 0.000 description 2
- 238000010200 validation analysis Methods 0.000 description 2
- 208000017667 Chronic Disease Diseases 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 230000002996 emotional effect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000009533 lab test Methods 0.000 description 1
- 238000011545 laboratory measurement Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000003997 social interaction Effects 0.000 description 1
- 230000001502 supplementing effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
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
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/16—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state
- A61B5/165—Evaluating the state of mind, e.g. depression, anxiety
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
Abstract
The invention relates to a mental health and rehabilitation assessment method, a device and a medium based on deep learning, which comprises the following steps: constructing a big data environment; collecting multidimensional data for mental health and rehabilitation evaluation based on deep learning through a big data environment, and storing the multidimensional data through a database; calculating psychological rehabilitation evaluation indexes and influence factors according to the dimension data; quantifying the dimension data and constructing panel data; constructing a plurality of models for evaluating mental health and rehabilitation evaluation based on deep learning according to the panel data; the dimensional data of the corresponding user is predicted according to a model for assessing deep learning-based mental health and rehabilitation assessment, and a descriptive report is generated. The invention has the beneficial effects that: establishing a mental health and rehabilitation evaluation model training data set based on deep learning, and ensuring high accuracy of the data set; the model analysis and prediction result can generate a descriptive readable report, and readable data support is provided for mental health care personnel.
Description
Technical Field
The invention relates to the field of computers, in particular to a mental health and rehabilitation assessment method, a device and a medium based on deep learning.
Background
In recent years, the introduction of artificial intelligence technology brings a brand new innovation for psychological rehabilitation and mental disease treatment. Research reports in many areas, from computer vision to healthcare, indicate that deep learning algorithms have performance due to other methods. Unlike diagnosis of other chronic diseases that rely on laboratory tests and measurements, diagnosis of mental disorders is often diagnosed through self-reporting of specific problems designed to detect specific emotional or social interactions. The artificial intelligence technology based on deep learning can effectively help psychology and mental health medical practitioners including psychiatrists and psychologists to make rehabilitation plan decisions by mining and processing relevant historical data such as patient medical records, behavior data, social media and the like. Moreover, a plurality of researches show that deep learning is one of the latest progresses of artificial intelligence and machine learning, data related to personal mental health conditions are converted through the multilayer nonlinear computing processing units, a new paradigm is provided, useful information can be effectively obtained from complex data, and the technology can effectively improve understanding of patients and medical care personnel on the mental health conditions and help the mental health medical care personnel to make better rehabilitation decisions.
Disclosure of Invention
The invention aims to solve at least one of the technical problems in the prior art, and provides a mental health and rehabilitation assessment method, a device and a medium based on deep learning.
The technical scheme of the invention comprises a mental health and rehabilitation assessment method based on deep learning, which is characterized by comprising the following steps: s100, constructing a big data environment; s200, collecting multidimensional data for mental health and rehabilitation evaluation through the big data environment, and storing the multidimensional data through a database; s300, calculating psychological rehabilitation evaluation indexes and influence factors according to the dimension data; s400, quantifying the dimension data and constructing panel data; s500, constructing a plurality of models for assessing mental health and rehabilitation according to the panel data; s600, predicting the dimension data of the corresponding user according to the model for evaluating the deep learning-based mental health and rehabilitation evaluation, and generating a descriptive report.
According to the mental health and rehabilitation assessment method based on deep learning, the method further comprises the following steps: s700, optimizing the model for assessing the mental health and rehabilitation based on deep learning, and adjusting the model for assessing the mental health and rehabilitation according to the descriptive report.
According to the mental health and rehabilitation assessment method based on deep learning, S100 includes: the method comprises the steps that multi-dimensional data of a designated crowd are collected through a plurality of computer devices, the computer devices comprise collecting devices and storage devices, the collecting devices are based on the combination of distributed frameworks of Hadoop, Spark and Pysspark, and the storage devices are Hive distributed storage devices.
According to the mental health and rehabilitation assessment method based on deep learning, S200 includes: the multidimensional data stored in the database comprises training data and verification data, wherein the training data and the verification data are randomly distributed in the database according to a set proportion, and the set proportion of the training data and the verification data is randomly and dynamically changed.
According to the mental health and rehabilitation assessment method based on deep learning, the calculation of the mental rehabilitation assessment index and the influence factors comprises calculation of one or more of mental health assessment data, environmental influence factor data, mental rehabilitation condition data and mental rehabilitation theory research data.
According to the mental health and rehabilitation assessment method based on deep learning, S400 includes: the quantization comprises dividing the dimension data into a range of [0,1], wherein 0 represents that there is no classified dimension behavior, and the degree of the dimension behavior of the sample classification is low and high when the dimension behavior is more than 0 and less than or equal to 1; and constructing panel data, wherein the panel takes time as an X axis, the quantized dimension data is a Y axis, and the evaluation index number is constructed three-dimensional panel data of a Z axis, wherein the quantized dimension data is set as social media data, the evaluation index number is mental health assessment data and self-assessment table data of the social media data and self-assessment table data of other people to the target person, and the indexes comprise anxiety, depression, alcohol use disorder and mental health degree.
According to the mental health and rehabilitation assessment method based on deep learning, S500 includes: performing index evaluation on the mental health evaluation data and the self-rating scale data of the social media data and the self-rating scale data of the target personnel by other people; establishing a mental health related model through a model combining text classification and structural formula classification and a network classification model of a long-term and short-term memory of an encoder-decoder; the input node of the mental health related model is Y-axis data of the panel data, and the output node is Z-axis data of the panel data.
According to the mental health and rehabilitation assessment method based on deep learning, S500 includes: the mental health assessment data of the social media data comprises a method for removing stop words, reducing dimension, extracting key words, identifying words, classifying and analyzing emotion of the social media text data by adopting a natural language processing related algorithm based on a Beck anxiety scale, a Beck depression scale, an alcohol use obstacle identification test and a Wallace Edinburgh mental health scale, marking the text data aiming at anxiety, depression, alcohol use obstacle and mental health degree, and assessing the anxiety, depression, alcohol use obstacle and mental health degree; the self-rating scale data and the self-rating scale data of other people to the target people comprise: the anxiety, depression, alcohol use disorder and mental health degree of the target person are evaluated by adopting the scales of a Beck anxiety scale, a Beck depression scale, an alcohol use disorder identification test and a Warrick-Edinburgh mental health scale.
According to the mental health and rehabilitation assessment method based on deep learning, the method further comprises the following steps: the method comprises the steps of collecting multidimensional data of a user related to mental health and rehabilitation through a remote medical terminal, and evaluating and interacting through a model for evaluating the mental health and rehabilitation.
The technical solution of the present invention also includes a mental health and rehabilitation assessment apparatus based on deep learning, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements any of the method steps when executing the computer program.
The present invention also includes a computer-readable storage medium, in which a computer program is stored, wherein the computer program, when executed by a processor, implements any of the method steps.
The invention has the beneficial effects that: by adopting a distributed acquisition and storage technology based on a social media network, the method is convenient for periodic self-optimization of deep learning, reduces the time for reading and storing results of the model, and is convenient for developers and users to remotely read data; based on a deep learning model based on a large amount of data, a natural language processing related algorithm is adopted to establish a mental health and rehabilitation evaluation model training data set based on deep learning, and the accuracy rate of the data set is ensured to be high; the model analysis and prediction result can generate a descriptive readable report, has high clinical value and provides readable data support for mental health medical staff.
Drawings
The invention is further described below with reference to the accompanying drawings and examples;
FIG. 1 illustrates an overall flow diagram according to an embodiment of the invention;
FIG. 2 is a diagram illustrating a psychological rehabilitation rating database according to an embodiment of the present invention;
FIG. 3 is a diagram illustrating a configuration of personal psychological rehabilitation data according to an embodiment of the present invention;
FIG. 4 is a diagram illustrating a classification model of an encoder-decoder long and short term memory network according to an embodiment of the present invention;
FIG. 5 is a flowchart illustrating mental health and rehabilitation assessment based on deep learning according to an embodiment of the present invention;
FIG. 6 shows a diagram of an apparatus and media according to an embodiment of the invention.
FIG. 7 is a diagram illustrating a database according to an embodiment of the present invention.
FIG. 8 is a chart illustrating an interface of assessment results according to an embodiment of the present invention.
FIG. 9 is a graph illustrating initial sample training indicators, according to an embodiment of the present invention.
Fig. 10 is a diagram illustrating an encoder-decoder prediction performance index according to an embodiment of the present invention.
Detailed Description
Reference will now be made in detail to the present preferred embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like reference numerals refer to like elements throughout.
In the description of the present invention, the meaning of a plurality of means is one or more, the meaning of a plurality of means is two or more, and larger, smaller, larger, etc. are understood as excluding the number, and larger, smaller, inner, etc. are understood as including the number.
In the description of the present invention, the consecutive reference numbers of the method steps are for convenience of examination and understanding, and the implementation order between the steps is adjusted without affecting the technical effect achieved by the technical solution of the present invention by combining the whole technical solution of the present invention and the logical relationship between the steps.
In the description of the present invention, unless otherwise explicitly defined, terms such as set, etc. should be broadly construed, and those skilled in the art can reasonably determine the specific meanings of the above terms in the present invention in combination with the detailed contents of the technical solutions.
Interpretation of terms:
CNN, convolutional neural network;
LSTM, long short term memory network.
Fig. 1 shows a general flow diagram according to an embodiment of the invention, the flow comprising: s100, constructing a big data environment; s200, collecting multidimensional data for mental health and rehabilitation evaluation based on deep learning through a big data environment, and storing the multidimensional data through a database; s300, calculating psychological rehabilitation evaluation indexes and influence factors according to the dimension data; s400, quantifying the dimension data and constructing panel data, wherein the quantifying comprises dividing the dimension data into a range of [0,1], wherein 0 represents that no classified dimension behavior exists, and the degree of the dimension behavior of sample classification is low when the dimension behavior is more than 0 and less than or equal to 1; the panel takes time as an X axis, dimension data after quantization is a Y axis, and evaluation index number is Z axis to construct three-dimensional panel data; s500, constructing a plurality of models for evaluating mental health and rehabilitation based on deep learning according to panel data; s600, predicting the dimension data of the corresponding user according to a model for evaluating the psychological health and rehabilitation evaluation based on deep learning, and generating a descriptive report; s700, optimizing the model for evaluating the mental health and rehabilitation based on deep learning, and adjusting the model for evaluating the mental health and rehabilitation based on deep learning according to the descriptive report. The panel data are referenced in table 1 below.
The data stored by the database includes a training data set and a validation data set:
the training data and the verification data set are randomly distributed in the database according to a certain proportion, and when the system is automatically upgraded, the training data and the verification data set are randomly distributed again
The training database and the verification database (panel data) include the following data:
TABLE 1 training and validation databases (Panel data)
Fig. 2 is a schematic diagram illustrating a psychological rehabilitation assessment database according to an embodiment of the present invention, and the creation of the psychological health and rehabilitation assessment database based on deep learning mainly includes: and the equipment based on high computational power adopts distributed acquisition equipment and Hive distributed storage equipment combined by distributed frames based on Hadoop, Spark and Pysspark to realize the construction of a big data environment. The database collection data types are as follows: the rehabilitation assessment database collects data that is divided into four categories (see fig. 2).
Fig. 3 is a schematic diagram illustrating a configuration of personal psychological rehabilitation data according to an embodiment of the invention, including:
mental health assessment data: mainly comprises personal basic information data, school basic information data, epidemic stations, post social media data, self-rating table data and self-rating table data of relative friends to the people (as shown in figure 2).
Environmental impact factor data: mainly comprises natural environment data (such as indoor and outdoor temperature of the region where the mental rehabilitation service object is located); home environment data (e.g., how well the family supports the physical rehabilitation service subject); community environmental data (e.g., number of people visiting a community of mental illness); social environment data (such as local mental disease subsidy amount), and related environmental influence factors;
psychological rehabilitation condition data: personal psychological rehabilitation condition data; mental rehabilitation facility condition data (e.g., the number of rehabilitation facility team members where the mental rehabilitation service object is located); if the psychological rehabilitation service object has a doctor, medical condition data (such as the grade of a doctor institution where the psychological rehabilitation service object is located) and related rehabilitation condition factors are added;
research data of psychological rehabilitation theory: theoretical disease conditions of psychological diseases; theoretical percentage of cure for psychological disease (e.g., percentage of cure for psychological disease in a province); theoretical time for curing psychological diseases (for example, theoretical time for curing psychological diseases in a certain province); and other psychological rehabilitation theory research data.
Fig. 4 is a diagram illustrating a classification model of an encoder-decoder long and short term memory network according to an embodiment of the present invention, which mainly includes: the mental health assessment method of the social media data comprises the following steps: based on a Beck anxiety scale (BAI), a Beck depression scale (BDI), an alcohol use disorder recognition test (AUDIT) and a Wollike Edinburgh mental health scale (WEMWBS), social media text data are subjected to methods such as word removal, dimension reduction, keyword extraction, word recognition, classification, emotion analysis and the like by adopting a natural language processing related algorithm, so that the text data are marked aiming at anxiety, depression, alcohol use disorder and mental health degree, and the values of the anxiety, depression, alcohol use disorder, mental health degree and the like are 3 and the like, namely mild, severe and severe.
The self-rating scale data are represented by Beck anxiety scale (BAI), Beck Depression scale (BDI), Alcohol Use Disorder Identification Test (AUDIT) and Warrick Edinburgh mental health scale (WEMWBS), and the values of anxiety, depression, alcohol use disorder, mental health degree and the like are 3 and the like, namely mild, severe and severe.
The self-rating scale data of the relative friend to the target person adopts the scales of a Beck anxiety scale (BAI), a Beck depression scale (BDI), an Alcohol Use Disorder Identification Test (AUDIT) and a Wollike Edingbao mental health scale (WEMWBS), and the values of anxiety, depression, alcohol use disorder, mental health degree and the like are 3 and the like, namely mild, severe and severe.
The deep learning algorithm adopts a model combining text classification and structural formula (digital) classification, is based on but not limited to a long-term and short-term memory network classification model of a coder-decoder, and adopts a mean value supplementing method if the selected model does not allow the input node to have a missing value, wherein the input node is Y-axis data of panel data; the output nodes are panel data Z-axis data, and the number of the nodes is more than or equal to 4. (as shown in fig. 5).
Fig. 5 is a flowchart illustrating mental health and rehabilitation assessment based on deep learning according to an embodiment of the present invention. Based on the flow chart, the technical scheme of the invention comprises the following steps:
the invention adopts a springboot + freemark + jpa + mybatis + mysql development mode to realize front-end development, and builds a medical care and intelligent interactive diagnosis and treatment system platform to realize the following functions:
(1) terminal is diagnose to intelligence: self-uploading of self-evaluation results of the mental health questionnaire is supported; the self-evaluation result data analysis and remote transmission are supported to obtain the support of mental health experts; support for receiving expert treatment plans and recommendations pushed by the system.
(2) Remote expert support service system: the remote data reading is supported, and the on-line expert pushing suggestion, treatment scheme and evaluation are supported.
(3) Mental health and rehabilitation evaluation AI system based on deep learning: and generating a descriptive report through deep learning and data mining based on the built database and the analysis and prediction model.
(4) Remote training education system: and remote video training education is supported.
FIG. 6 shows a diagram of an apparatus and media according to an embodiment of the invention. Fig. 6 shows a schematic view of an apparatus according to an embodiment of the invention. The apparatus comprises a memory 100 and a processor 200, wherein the processor 200 stores a computer program for performing: constructing a big data environment; collecting multidimensional data for mental health and rehabilitation evaluation based on deep learning through a big data environment, and storing the multidimensional data through a database; calculating psychological rehabilitation evaluation indexes and influence factors according to the dimension data; quantifying the dimension data and constructing panel data; constructing a plurality of models for evaluating mental health and rehabilitation evaluation based on deep learning according to the panel data; the dimensional data of the corresponding user is predicted according to a model for assessing deep learning-based mental health and rehabilitation assessment, and a descriptive report is generated. Wherein the memory 100 is used for storing data.
FIG. 7 is a diagram illustrating a database according to an embodiment of the present invention. The mental health assessment database is shown in fig. 7, and is a plurality of sql files, and after the project is started, the project is distributed and stored in a server in a hive form. As shown in fig. 7, the mental health assessment database contains 288 indexes, 7 ten thousand data.
FIG. 8 is a chart illustrating an interface of assessment results according to an embodiment of the present invention. The medical care and student intelligent interactive diagnosis and treatment system is characterized in that a UI interface and a diagnosis report of the medical care and student intelligent interactive diagnosis and treatment system are preliminarily completed.
FIG. 9 is a graph illustrating initial sample training indicators, according to an embodiment of the present invention. The project has preliminarily completed the establishment of a CNN-LSTM Encoder-Decoder model and is trained by applying a mental health initial sample, and the indexes of the training prediction Loss value and effect are shown in FIG. 9.
Fig. 10 is a diagram illustrating an encoder-decoder prediction performance index according to an embodiment of the present invention. The lower graph predicts the performance of the training of the initial sample data of the mental health through the CNN-LSTM Encoder-Decoder, and the performance comprises index values such as accuracy, specificity, sensitivity and the like. Wherein accuracy and val _ accuracy represent accuracy, spec _ avgs represents specificity, sens _ avgs and sens _ spec _ avgs represent sensitivity.
The embodiments of the present invention have been described in detail with reference to the accompanying drawings, but the present invention is not limited to the above embodiments, and various changes can be made within the knowledge of those skilled in the art without departing from the gist of the present invention.
Claims (11)
1. A mental health and rehabilitation assessment method based on deep learning is characterized by comprising the following steps:
s100, constructing a big data environment;
s200, collecting multidimensional data for mental health and rehabilitation evaluation through the big data environment, and storing the multidimensional data through a database;
s300, calculating psychological rehabilitation evaluation indexes and influence factors according to the dimension data;
s400, quantifying the dimension data and constructing panel data;
s500, constructing a plurality of models for assessing mental health and rehabilitation according to the panel data;
s600, predicting the dimension data of the corresponding user according to the model for evaluating the deep learning-based mental health and rehabilitation evaluation, and generating a descriptive report.
2. The deep learning based mental health and rehabilitation assessment method according to claim 1, characterized in that the method further comprises:
s700, optimizing the model for assessing the mental health and rehabilitation based on deep learning, and adjusting the model for assessing the mental health and rehabilitation according to the descriptive report.
3. The deep learning based mental health and rehabilitation assessment method according to claim 1, wherein the S100 comprises:
the method comprises the steps that multi-dimensional data of a designated crowd are collected through a plurality of computer devices, the computer devices comprise collecting devices and storage devices, the collecting devices are based on the combination of distributed frameworks of Hadoop, Spark and Pysspark, and the storage devices are Hive distributed storage devices.
4. The deep learning based mental health and rehabilitation assessment method according to claim 1, wherein the S200 comprises:
the multidimensional data stored in the database comprises training data and verification data, wherein the training data and the verification data are randomly distributed in the database according to a set proportion, and the set proportion of the training data and the verification data is randomly and dynamically changed.
5. The deep learning based mental health and rehabilitation assessment method according to claim 1, wherein the calculating of the mental health assessment indicators and the influencing factors comprises calculating one or more of mental health assessment data, environmental influencing factor data, mental recovery condition data and mental recovery theory research data.
6. The deep learning based mental health and rehabilitation assessment method according to claim 5, wherein the S400 comprises:
the quantization comprises dividing the dimension data into a range of [0,1], wherein 0 represents that there is no classified dimension behavior, and the degree of the dimension behavior of the sample classification is low and high when the dimension behavior is more than 0 and less than or equal to 1;
and constructing panel data, wherein the panel takes time as an X axis, the quantized dimension data is a Y axis, and the evaluation index number is constructed three-dimensional panel data of a Z axis, wherein the quantized dimension data is set as social media data, the evaluation index number is mental health assessment data and self-assessment table data of the social media data and self-assessment table data of other people to the target person, and the indexes comprise anxiety, depression, alcohol use disorder and mental health degree.
7. The deep learning based mental health and rehabilitation assessment method according to claim 1, wherein the S500 comprises:
performing index evaluation on the mental health evaluation data and the self-rating scale data of the social media data and the self-rating scale data of the target personnel by other people;
establishing a mental health related model through a model combining text classification and structural formula classification and a network classification model of a long-term and short-term memory of an encoder-decoder;
the input node of the mental health related model is Y-axis data of the panel data, and the output node is Z-axis data of the panel data.
8. The deep learning based mental health and rehabilitation assessment method according to claim 1, wherein the S500 comprises:
the mental health assessment data of the social media data comprises a method for removing stop words, reducing dimension, extracting key words, identifying words, classifying and analyzing emotion of the social media text data by adopting a natural language processing related algorithm based on a Beck anxiety scale, a Beck depression scale, an alcohol use obstacle identification test and a Wallace Edinburgh mental health scale, marking the text data aiming at anxiety, depression, alcohol use obstacle and mental health degree, and assessing the anxiety, depression, alcohol use obstacle and mental health degree;
the self-rating scale data and the self-rating scale data of other people to the target people comprise: the anxiety, depression, alcohol use disorder and mental health degree of the target person are evaluated by adopting the scales of a Beck anxiety scale, a Beck depression scale, an alcohol use disorder identification test and a Warrick-Edinburgh mental health scale.
9. The mental health and rehabilitation assessment method according to claim 1, characterized in that the method further comprises:
the method comprises the steps of collecting multidimensional data of a user related to mental health and rehabilitation through a remote medical terminal, and evaluating and interacting through a model for evaluating the mental health and rehabilitation.
10. A mental health and rehabilitation assessment device based on deep learning, comprising a memory, a processor and a computer program stored in said memory and executable on said processor, characterized in that said processor implements the method steps of any of claims 1-9 when executing said computer program.
11. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the method steps of any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011004525.4A CN112185558A (en) | 2020-09-22 | 2020-09-22 | Mental health and rehabilitation evaluation method, device and medium based on deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011004525.4A CN112185558A (en) | 2020-09-22 | 2020-09-22 | Mental health and rehabilitation evaluation method, device and medium based on deep learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112185558A true CN112185558A (en) | 2021-01-05 |
Family
ID=73956775
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011004525.4A Pending CN112185558A (en) | 2020-09-22 | 2020-09-22 | Mental health and rehabilitation evaluation method, device and medium based on deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112185558A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112967804A (en) * | 2021-01-29 | 2021-06-15 | 西安新能技术有限公司 | Computer self-adaptive mental health screening system for physical examination and screening method thereof |
| CN113032418A (en) * | 2021-02-08 | 2021-06-25 | 浙江大学 | Method for converting complex natural language query into SQL (structured query language) based on tree model |
| CN115359914A (en) * | 2022-08-26 | 2022-11-18 | 山东心法科技有限公司 | Method, apparatus, and medium for discriminating psychological states based on quantization description vector |
| TWI817077B (en) * | 2021-01-12 | 2023-10-01 | 中華電信股份有限公司 | Maternity protection evaluation apparatus, system and method thereof |
Citations (25)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104127186A (en) * | 2014-07-31 | 2014-11-05 | 李风华 | Attention deficit hyperactivity disorder objective evaluation system |
| CN106407673A (en) * | 2016-09-08 | 2017-02-15 | 山东腾泰医疗科技有限公司 | Mental health evaluation method based on Internet cloud database |
| KR101834003B1 (en) * | 2017-09-21 | 2018-03-02 | 주식회사 엠쓰리솔루션 | Cognitive learning and estimation system |
| CN107799165A (en) * | 2017-09-18 | 2018-03-13 | 华南理工大学 | A kind of psychological assessment method based on virtual reality technology |
| CN107958213A (en) * | 2017-11-20 | 2018-04-24 | 北京工业大学 | A kind of cospace pattern based on the medical treatment of brain-computer interface recovering aid and deep learning method |
| KR101911516B1 (en) * | 2017-12-26 | 2018-10-24 | (주)에프앤아이 | Method for obtaining psychological state data, assessing psychological state of user and providing feedback, and server using the same |
| CN109036561A (en) * | 2018-07-10 | 2018-12-18 | 同济大学 | A kind of graduates ' mental status appraisal procedure of Behavior-based control information |
| CN109119130A (en) * | 2018-07-11 | 2019-01-01 | 上海夏先机电科技发展有限公司 | A kind of big data based on cloud computing is health management system arranged and method |
| CN109431521A (en) * | 2018-10-12 | 2019-03-08 | 西北工业大学 | A kind of multi-modal bipolar depression automatic testing method based on audio/video information |
| KR20190060108A (en) * | 2017-11-24 | 2019-06-03 | 울산과학기술원 | Method for screening makers for predicting depressive disorder or suicide risk using machine learning, markers for predicting depressive disorder or suicide risk, method for predicting depressive disorder or suicide risk |
| CN109875565A (en) * | 2019-01-25 | 2019-06-14 | 电子科技大学 | A kind of cerebral apoplexy upper extremity exercise function method for automatically evaluating based on deep learning |
| CN109902558A (en) * | 2019-01-15 | 2019-06-18 | 安徽理工大学 | A kind of human health deep learning prediction technique based on CNN-LSTM |
| CN110289101A (en) * | 2019-07-02 | 2019-09-27 | 京东方科技集团股份有限公司 | A kind of computer equipment, system and readable storage medium storing program for executing |
| CN110347837A (en) * | 2019-07-17 | 2019-10-18 | 电子科技大学 | A kind of unplanned Risk Forecast Method of being hospitalized again of cardiovascular disease |
| CN110383389A (en) * | 2017-03-01 | 2019-10-25 | 怡素数字健康有限公司 | Psychotherapy classification method |
| US20190341152A1 (en) * | 2018-05-01 | 2019-11-07 | Blackthorn Therapeutics, Inc. | Machine learning-based diagnostic classifier |
| CN110507335A (en) * | 2019-08-23 | 2019-11-29 | 山东大学 | Inmate's psychological health states appraisal procedure and system based on multi-modal information |
| CN110570941A (en) * | 2019-07-17 | 2019-12-13 | 北京智能工场科技有限公司 | System and device for assessing psychological state based on text semantic vector model |
| KR20200001777A (en) * | 2018-06-28 | 2020-01-07 | 연세대학교 산학협력단 | Method for predicting of depression and device for predicting of depression risk using the same |
| US20200075040A1 (en) * | 2018-08-31 | 2020-03-05 | The Regents Of The University Of Michigan | Automatic speech-based longitudinal emotion and mood recognition for mental health treatment |
| US20200090812A1 (en) * | 2018-07-16 | 2020-03-19 | Smart Score Technologies, LLC | Machine learning for measuring and analyzing therapeutics |
| CN110993102A (en) * | 2019-11-18 | 2020-04-10 | 温州医科大学 | Campus big data-based student behavior and psychological detection result accurate analysis method and system |
| KR20200043800A (en) * | 2018-10-18 | 2020-04-28 | 주식회사 셀바스에이아이 | Method for predicting state of mental health and device for predicting state of mental health using the same |
| CN111225612A (en) * | 2017-10-17 | 2020-06-02 | 萨蒂什·拉奥 | Neural obstacle identification and monitoring system based on machine learning |
| CN111402095A (en) * | 2020-03-23 | 2020-07-10 | 温州医科大学 | Method for detecting student behaviors and psychology based on homomorphic encrypted federated learning |
-
2020
- 2020-09-22 CN CN202011004525.4A patent/CN112185558A/en active Pending
Patent Citations (25)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104127186A (en) * | 2014-07-31 | 2014-11-05 | 李风华 | Attention deficit hyperactivity disorder objective evaluation system |
| CN106407673A (en) * | 2016-09-08 | 2017-02-15 | 山东腾泰医疗科技有限公司 | Mental health evaluation method based on Internet cloud database |
| CN110383389A (en) * | 2017-03-01 | 2019-10-25 | 怡素数字健康有限公司 | Psychotherapy classification method |
| CN107799165A (en) * | 2017-09-18 | 2018-03-13 | 华南理工大学 | A kind of psychological assessment method based on virtual reality technology |
| KR101834003B1 (en) * | 2017-09-21 | 2018-03-02 | 주식회사 엠쓰리솔루션 | Cognitive learning and estimation system |
| CN111225612A (en) * | 2017-10-17 | 2020-06-02 | 萨蒂什·拉奥 | Neural obstacle identification and monitoring system based on machine learning |
| CN107958213A (en) * | 2017-11-20 | 2018-04-24 | 北京工业大学 | A kind of cospace pattern based on the medical treatment of brain-computer interface recovering aid and deep learning method |
| KR20190060108A (en) * | 2017-11-24 | 2019-06-03 | 울산과학기술원 | Method for screening makers for predicting depressive disorder or suicide risk using machine learning, markers for predicting depressive disorder or suicide risk, method for predicting depressive disorder or suicide risk |
| KR101911516B1 (en) * | 2017-12-26 | 2018-10-24 | (주)에프앤아이 | Method for obtaining psychological state data, assessing psychological state of user and providing feedback, and server using the same |
| US20190341152A1 (en) * | 2018-05-01 | 2019-11-07 | Blackthorn Therapeutics, Inc. | Machine learning-based diagnostic classifier |
| KR20200001777A (en) * | 2018-06-28 | 2020-01-07 | 연세대학교 산학협력단 | Method for predicting of depression and device for predicting of depression risk using the same |
| CN109036561A (en) * | 2018-07-10 | 2018-12-18 | 同济大学 | A kind of graduates ' mental status appraisal procedure of Behavior-based control information |
| CN109119130A (en) * | 2018-07-11 | 2019-01-01 | 上海夏先机电科技发展有限公司 | A kind of big data based on cloud computing is health management system arranged and method |
| US20200090812A1 (en) * | 2018-07-16 | 2020-03-19 | Smart Score Technologies, LLC | Machine learning for measuring and analyzing therapeutics |
| US20200075040A1 (en) * | 2018-08-31 | 2020-03-05 | The Regents Of The University Of Michigan | Automatic speech-based longitudinal emotion and mood recognition for mental health treatment |
| CN109431521A (en) * | 2018-10-12 | 2019-03-08 | 西北工业大学 | A kind of multi-modal bipolar depression automatic testing method based on audio/video information |
| KR20200043800A (en) * | 2018-10-18 | 2020-04-28 | 주식회사 셀바스에이아이 | Method for predicting state of mental health and device for predicting state of mental health using the same |
| CN109902558A (en) * | 2019-01-15 | 2019-06-18 | 安徽理工大学 | A kind of human health deep learning prediction technique based on CNN-LSTM |
| CN109875565A (en) * | 2019-01-25 | 2019-06-14 | 电子科技大学 | A kind of cerebral apoplexy upper extremity exercise function method for automatically evaluating based on deep learning |
| CN110289101A (en) * | 2019-07-02 | 2019-09-27 | 京东方科技集团股份有限公司 | A kind of computer equipment, system and readable storage medium storing program for executing |
| CN110570941A (en) * | 2019-07-17 | 2019-12-13 | 北京智能工场科技有限公司 | System and device for assessing psychological state based on text semantic vector model |
| CN110347837A (en) * | 2019-07-17 | 2019-10-18 | 电子科技大学 | A kind of unplanned Risk Forecast Method of being hospitalized again of cardiovascular disease |
| CN110507335A (en) * | 2019-08-23 | 2019-11-29 | 山东大学 | Inmate's psychological health states appraisal procedure and system based on multi-modal information |
| CN110993102A (en) * | 2019-11-18 | 2020-04-10 | 温州医科大学 | Campus big data-based student behavior and psychological detection result accurate analysis method and system |
| CN111402095A (en) * | 2020-03-23 | 2020-07-10 | 温州医科大学 | Method for detecting student behaviors and psychology based on homomorphic encrypted federated learning |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI817077B (en) * | 2021-01-12 | 2023-10-01 | 中華電信股份有限公司 | Maternity protection evaluation apparatus, system and method thereof |
| CN112967804A (en) * | 2021-01-29 | 2021-06-15 | 西安新能技术有限公司 | Computer self-adaptive mental health screening system for physical examination and screening method thereof |
| CN113032418A (en) * | 2021-02-08 | 2021-06-25 | 浙江大学 | Method for converting complex natural language query into SQL (structured query language) based on tree model |
| CN115359914A (en) * | 2022-08-26 | 2022-11-18 | 山东心法科技有限公司 | Method, apparatus, and medium for discriminating psychological states based on quantization description vector |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20210343384A1 (en) | Systems and methods for managing autoimmune conditions, disorders and diseases | |
| CN112185558A (en) | Mental health and rehabilitation evaluation method, device and medium based on deep learning | |
| Milovic et al. | Prediction and decision making in health care using data mining | |
| Thomas | Rewards of bridging the divide between measurement and clinical theory: demonstration of a bifactor model for the Brief Symptom Inventory. | |
| EP3783619A1 (en) | Human body health assessment method and system based on sleep big data | |
| KR20200005987A (en) | System and method for diagnosing cognitive impairment using touch input | |
| CN110570941B (en) | System and device for assessing psychological state based on text semantic vector model | |
| CN111666477A (en) | Data processing method and device, intelligent equipment and medium | |
| CN112069329B (en) | Text corpus processing method, device, equipment and storage medium | |
| CN113707252B (en) | Intelligent case quality control method and system | |
| CN112331349B (en) | Cerebral apoplexy relapse monitoring system | |
| Li et al. | An artificial intelligence based model for evaluation of college students’ ability and characteristics through teaching evaluation | |
| CN115714022B (en) | Neonatal jaundice health management system based on artificial intelligence | |
| Tong et al. | Testing the generalizability of an automated method for explaining machine learning predictions on asthma patients’ asthma hospital visits to an academic healthcare system | |
| CN114388103A (en) | Algorithm for teenager psychological early warning analysis | |
| CN109360658A (en) | A kind of the disease pattern method for digging and device of word-based vector model | |
| Kindel et al. | Improving metadata infrastructure for complex surveys: Insights from the Fragile Families Challenge | |
| CN105893748A (en) | Happiness index evaluation method and system based on rough set theory | |
| CN111696673A (en) | Mental health management model system and method | |
| CN114141379A (en) | Sleep disorder attribution analysis method, device and system based on knowledge graph | |
| CN113223734A (en) | Disease diagnosis and big health management platform based on algorithm, medical image and big data | |
| CN112259232A (en) | VTE risk automatic evaluation system based on deep learning | |
| CN113842113A (en) | Developing reading disorder intelligent identification method, system, equipment and storage medium | |
| Bieliński et al. | Comparison of Selected Machine Learning Algorithms in the Analysis of Mental Health Indicators | |
| Strobel et al. | Healthcare in the Era of Digital twins: towards a Domain-Specific Taxonomy. |
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 |