CN110570941A - System and device for assessing psychological state based on text semantic vector model - Google Patents
System and device for assessing psychological state based on text semantic vector model Download PDFInfo
- Publication number
- CN110570941A CN110570941A CN201910645841.0A CN201910645841A CN110570941A CN 110570941 A CN110570941 A CN 110570941A CN 201910645841 A CN201910645841 A CN 201910645841A CN 110570941 A CN110570941 A CN 110570941A
- Authority
- CN
- China
- Prior art keywords
- text
- psychological
- test
- data
- module
- 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.)
- Granted
Links
Classifications
-
- 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
- G06F16/353—Clustering; Classification into predefined classes
-
- 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
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- 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
Abstract
the invention provides a system and a device for evaluating a psychological state based on a text semantic vector model, by adopting the technical scheme of the invention, the psychological state is evaluated based on the text semantic vector model, a user does not need to manually do questions or contact with the user face to face, but the psychological state of the user is evaluated by analyzing the mood text or saying words of the user, the mode does not cause pressure on the user, the latest real psychological state of the user can be obtained, and finally, an evaluation result and a corresponding countermeasure suggestion can be obtained by text analysis, so that the user can intuitively know the current psychological state and self-adjust or even seek medical advice according to the suggestion so as to achieve the state of psychological health.
Description
Technical Field
The invention belongs to the technical field of health monitoring and management, and particularly relates to a system and a device for evaluating a psychological state based on a text semantic vector model.
Background
With the increasing pressure of life in modern society, psychological diseases become an increasingly common phenomenon. Common psychological disorders include depression, anxiety, obsessive compulsive disorder, and the like. These psychological diseases not only affect the normal lives of patients, but also even cause suicide attempts in severe cases, thereby raising social concerns and concerns about the psychological diseases. According to the report of the world health organization, the incidence rate of depression is about 11 percent worldwide, the depression becomes the fourth disease which endangers human health, and the depression may become the second disease second to heart disease by 2020. In China, the incidence rate of depression is up to 7%, and the treatment rate is only 20% due to the untimely discovery and the insufficient understanding. Suicidal death events due to depression are frequent.
However, most current mental health services stay in a "passive" mode, and find out the psychologically abnormal individuals mainly through a traditional questionnaire issuing manner or by a user consulting a mental health counseling center or visiting a hospital. However, due to the limitation of manpower and material resources, psychological researchers cannot acquire data covering the whole study object for a long time, and are inconvenient to track and study the change of the individual mental health state, so that timely active intervention on individuals with abnormal psychological behaviors is difficult to perform.
there are many existing psychological state analyzing devices, but the existing technical devices are large and complex, the emotional fluctuation of the devices and the tested objects easily influences the analysis result, and the psychological state of the tested person cannot be expressed intuitively and simply. The mental health test is usually a questionnaire type test, that is, a paper question is curled into the hands of an evaluated person, the evaluated person finishes answering the questionnaire, then the questionnaire is recovered, and the evaluating person makes an evaluation according to the answering condition of each questionnaire. The test mode has the defects that the physical sign information of the evaluated person, such as blood pressure, heart rate and the like, cannot be monitored simultaneously when the evaluated person makes a questionnaire for filling, so that more accurate mental health test analysis cannot be performed on the evaluated person, and on the other hand, when the evaluated person needs to test various indexes in a state close to a sleep state, the existing equipment has defects and does not have a display for displaying.
meanwhile, the traditional internet psychological assessment software is relatively simplified, focuses on single test and report generation result analysis, can cause the contingency of the assessment result and generate the error of the assessment result for a tester, and along with the development of the industry, internet products are gradually added and supplemented with products and technical schemes of statistical analysis, so that the result of a user is more scientific. However, this still does not meet the practical requirements of psychological assessment, and still causes many errors.
The patent "an internet-based mental health assessment system" (CN201610808709.3) proposes an internet-based mental health assessment system. In the system, the cloud database is used for storing the factor scores of the psychological test scale in a known sample; and establishing a mental health assessment model by using an RBF neural network algorithm. And after the RBF neural network model evaluates the mental health state of the new individual, uploading an evaluation result to a cloud. The system is also based on traditional psychological test chart results, and cannot objectively evaluate and track and study the psychological health state.
The patent "a mental health state assessment method" (CN201210576344.8) proposes a method for mental health state assessment using machine learning. The evaluation method comprises the following implementation steps: firstly, establishing and training a mental health state assessment model based on network behavior characteristics based on the network behavior characteristics and the demographic characteristics of individuals in known samples; secondly, acquiring network behavior characteristics and demographic characteristics of the new individual; preferably, the mental health status of the new individual is obtained according to the assessment model established above. The method has the advantages that the influence of subjective factors on the mental health state assessment is eliminated, and the defects that the behavior data source is single, the mining is not thorough, and the accuracy of the mental health state assessment cannot be guaranteed.
CN109524085A discloses a cognitive analysis method and system based on interaction, which can analyze and obtain personal cognitive information of a user, thereby providing more powerful help for mental health services of the user. And outputting interactive output information to interact with the user through at least one preset interactive mode to obtain interactive input information of the user, then carrying out content recognition and analysis on the interactive input information to obtain cognitive analysis data, and then constructing a personal cognitive structure model of the user according to the cognitive analysis data. Therefore, by implementing the embodiment of the invention, the interaction information (including the output interaction information for interacting with the user and the interaction input information input by the user aiming at the output interaction information) between the user and the user can be analyzed by interacting with the user on the basis of cognitive psychology, so as to obtain the personal cognitive information of the user, thereby establishing a personal cognitive structure model of the user, analyzing and solving the psychological problem of the user on the basis of the personal cognitive structure model, and providing more powerful help for the psychological health service of the user; moreover, a man-machine interactive mode based on Natural Language Processing (NLP) technology is adopted, so that communication is more real and Natural.
however, in any of the above solutions, the user is required to actively participate and cooperate, the accuracy of the detection result depends greatly on the degree of cooperation and the accuracy of the user, and if the user chooses a wrong answer at will or deliberately chooses a wrong answer, or inputs interactive information at will, the above solutions cannot process the result, and the accuracy and objectivity of the result cannot be guaranteed.
Disclosure of Invention
In order to solve the technical problems, the invention provides a system and a device for evaluating a psychological state based on a text semantic vector model. The technical scheme of the invention is based on a conclusion obtained by long-term research of semantic texts by the inventor: usually, when conducting psychological tests, people usually do not feel aware of the fact of avoiding concretization of the true psychological state, or even intentional hiding. Most of the time, users express their true emotions through fragmented texts (such as social ways of microblog, saying, circle of friends and the like).
Therefore, the invention provides the method for evaluating the psychological state based on the text semantic vector model, the psychological state of the user is evaluated by analyzing the mood text or the saying of the user without manually making questions or making face-to-face contact with the user, the mode does not cause pressure on the user, the latest real psychological state of the user can be obtained, and finally the evaluation result and the corresponding strategy suggestion can be obtained by text analysis, so that the user can intuitively know the current psychological state of the user and self-adjust or even seek medical advice to achieve the state of psychological health.
the technical scheme of the invention is concretely realized as follows:
A system for evaluating psychological states based on a text semantic vector model comprises a text data acquisition module, a text data analysis module, a text data vectorization module, a psychological test model construction module and a result analysis module.
The text data acquisition module comprises psychological test database data acquisition and/or personal psychological text acquisition;
The data acquisition of the psychological test database mainly comprises the acquisition of professional psychological measurement tables and relevant assessment results, suggestions and the like: professional psychometric data can be collected from professional institutions such as psychotherapeutic institutions or medical institutions, and the like, wherein the data mainly comprises test data time, a psychometric table and scores thereof, evaluation results, strategy suggestions and the like;
This acquisition is optional. As mentioned above, there are many psychological health counseling schemes in the prior art, such as questionnaire survey, on-line survey, etc., which require human interaction, and a large number of professional psychometric tables and their related assessment results can be obtained through the schemes themselves.
However, as the first important innovation point of the present invention, the text data collection module also collects personal psychological texts.
Unlike the prior art which refers to the data of "questionnaire" which requires active participation of the user, the technical scheme of the invention utilizes personal psychological texts for mental health monitoring for the first time. The acquisition mode of the personal psychological text is completely passive and does not need to be actively provided by the user, so that the method is not influenced by factors such as whether the user objectively answers questions or not, whether the user deliberately covers the self state and the like, and the result is objective.
specifically, the method for acquiring the personal psychological text mainly comprises the following steps of acquiring personal information and historical psychological texts thereof: the personal information can be acquired through personal registration information, and the historical psychological text can be acquired according to personal friend circles, microblogs and the like of individuals;
for a user seeking mental health, a large amount of personal psychological texts can be obtained by collecting fragmented texts (such as social ways of microblog, saying, friend circle and the like);
and after data acquisition, entering the text data analysis module.
the text data analysis comprises a text classification step, the data preprocessing is the first step of text classification, and the quality of a preprocessing result directly influences whether the subsequent analysis processing can be smoothly carried out. The purpose of text preprocessing is to extract main content from a text corpus in a normative manner and remove information irrelevant to the emotion classification of the text. For Chinese preprocessing, the main operations include standard coding, illegal character filtering, word segmentation processing, stop word removal and other steps;
The text data after data preprocessing enters a text classification step, and the specific implementation mode is as follows:
text labeling and segmentation: firstly, labeling a data set;
Then dividing the data set into a training set and a test set; training set text: the training set text is used for training a psychological classification model; test set text: the test set text is used to evaluate the predictive, etc., capabilities of the model.
Based on the training set and the test set, a classification model can be trained and a model evaluation test can be performed.
As a second innovation of the present invention, we need to vectorize the text before training the classification model, and the computer cannot recognize Chinese, so we need to convert it. The nature of model training is the various computations of the various values or matrices. Converting the sample into a corresponding feature vector, and feeding data to the model according to batch during training;
as a third innovation point of the invention, the test set is used to test the effect of the classification model, where the classification model can be evaluated by using evaluation methods such as F1-score (F1 score), accuracy (accuracy rate), precision (precision rate), etc.; then, optimizing and adjusting the model according to the evaluation result; the optimization and adjustment methods include adjusting learning _ rate (the learning rate is usually 0.001 at the initial learning rate), dropping (dropping the common value 3 is between 0.5 and 1.0, and in a neural network, it is generally understood that neurons with a certain proportion are randomly disconnected), adjusting an optimization function (Adam optimization algorithm, SGD random gradient descent), and the like; finally, the prediction effect of the model is better, and the generalization capability is stronger;
the classification model finally optimized is the model that we want.
Next, a mental health assessment is performed using the classification model. Firstly, semantic vectorization needs to be performed, the text data is converted into corresponding semantic vectors through the text data vectorization module, and deep learning or machine learning methods can be used for vectorizing the text data, for example: constructing semantic vectors by using a method such as BERT (bidirectional coding representation of an encoder) for converting the semantic vectors, TF-IDF (word frequency-inverse text frequency), LDA (topic model) and the like;
As another important improvement of the invention, the system comprises a psychological test model building module for building a psychological test calculation expression.
The psychological test calculation expression is constructed as follows:
S301 psychological test database: acquiring a psychological test database, and reading the content of the psychological test database;
s302, classifying and labeling the historical psychological texts of the user, and counting the texts of each category according to the labeling resultCounting, and calculating the proportion Sn occupied by each category, wherein the weight of each category is Wn, N is 1, 2. Vectorizing the historical psychological text of each category to obtain a historical psychological text vector sequence Ln；
S303, establishing a psychological test table and the scores thereof: extracting a psychological test table and a score thereof in a psychological test database; and converting the test questions in the psychological test table into corresponding test question semantic vector sequences Ckk is 1, 2,.... M, M is the number of test questions; calculating historical psychological text vector sequence LnAnd test topic semantic vector sequence CkCosine similarity matrix Y between two pairsij，i＝1，2，..，N，j＝1，2，......M；
S304, constructing a psychological test calculation expression: the test standard quantity was calculated using the following formula:
the result analysis module performs result analysis based on the expression result, and includes:
Calculating a test standard quantity according to a psychological test calculation expression;
And analyzing results according to the values calculated by the results, and feeding back standard evaluation results and strategy suggestions in the database to the user.
On the other hand, the invention provides a device for judging the psychological state of a user through text analysis, which comprises a data acquisition module, a psychological test database construction module, a text analysis module, a psychological health assessment module and a result analysis module; specifically, the text analysis is to objectively evaluate a psychological state by establishing a semantic vector model based on the text analysis. The device comprises:
The data acquisition device is used for acquiring data of the psychological test database and data of the individual psychological text;
The psychological test database construction module is used for establishing a psychological test database based on the psychological test database data collected by the data collection module;
the text analysis module is used for preprocessing the personal psychological text data acquired by the data acquisition module, vectorizing and classifying the personal psychological text data, converting the personal psychological text data into corresponding semantic vectors and constructing a text analysis model;
the mental health evaluation module is used for constructing a mental health test calculation expression by utilizing the text analysis model based on mental text data of the user;
and the result analysis module is used for calculating based on the information health test calculation expression constructed by the mental health assessment module and analyzing the calculation result.
in the technical scheme of the invention, an important innovation point is that a psychological test database is constructed by utilizing a professional psychological measurement table contained in a psychological test database data set, and evaluation results, suggestions and the like thereof in combination with personal information and historical psychological texts thereof;
And based on psychological text data newly acquired by an individual, the psychological text data is combined with the psychological test database, is input into the text-to-text analysis module, is subjected to text classification and semantic vectorization, and is subjected to psychological health assessment.
In addition, the psychological test calculation expression provided by the invention is an objective measurement standard obtained based on the user historical psychological text classification result, the psychological test table and the scores thereof, and can correctly correspond to the data set of the psychological test database, thereby objectively and accurately reflecting the psychological health state of the user.
Therefore, by adopting the technical scheme of the invention, the user does not need to manually do questions or make face-to-face contact with the user, but the psychological state of the user is evaluated by analyzing the mood text or saying the mood text of the user, so that no pressure is caused to the user, the latest real psychological state of the user can be obtained, and finally, the evaluation result and the corresponding strategy suggestion can be obtained by text analysis, so that the user can intuitively know the current psychological state of the user and self-adjust or even seek medical advice to achieve the psychological health state.
additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
further advantages and embodiments of the present invention will be further apparent from the accompanying drawings.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
FIG. 1 is a system framework diagram for estimating a psychological state based on a text semantic vector model according to the present embodiment;
FIG. 2 is a flowchart illustrating module execution of the apparatus for determining a psychological state of a user through text analysis according to the embodiment;
FIG. 3 is a flowchart of the classification model used in the psychological test model according to the embodiment;
Fig. 4 is a flowchart for constructing a psychological test calculation expression according to the present embodiment.
DETAILED DESCRIPTION OF EMBODIMENT (S) OF INVENTION
For further explanation of the various embodiments, the drawings which form a part of the disclosure and which are incorporated in and constitute a part of this specification, illustrate embodiments and, together with the description, serve to explain the principles of operation of the embodiments, and to enable others of ordinary skill in the art to understand the various embodiments and advantages of the invention, and, by reference to these figures, reference is made to the accompanying drawings, which are not to scale and wherein like reference numerals generally refer to like elements.
Referring to fig. 1, the system for evaluating a psychological state based on a text semantic vector model according to the present embodiment includes a text data acquisition module, a text data analysis module, a text data vectorization module, a psychological test model construction module, and a result analysis module;
The text data acquisition module comprises psychological test database data acquisition and/or personal psychological text acquisition;
the text data analysis module is used for preprocessing text data and classifying texts, wherein the processing comprises standard coding, illegal character filtering, word segmentation processing and stop word removal; the text classification comprises text labeling and segmentation; establishing a text classification model by using the text data after the text segmentation and carrying out model test;
The text data vectorization module is used for vectorizing the text data processed by the text data analysis module;
And the psychological test model building module is used for building a psychological test calculation expression.
specifically, the specific execution flow of each module is as follows:
s101, a data acquisition module: the data acquisition module comprises two parts:
s102, psychological test database data acquisition: the data acquisition of the psychological test database mainly comprises two parts of data:
S103, acquiring a professional psychometric measuring meter and related evaluation results, suggestions and the like: professional psychometric data can be collected from professional institutions such as psychotherapeutic institutions or medical institutions, and the like, wherein the data mainly comprises test data time, a psychometric table and scores thereof, evaluation results, strategy suggestions and the like;
S104, collecting personal information and historical psychological texts thereof: the personal information can be acquired through personal registration information, and the historical psychological text can be acquired according to personal friend circles, microblogs and the like of individuals;
S105, acquiring psychological texts of new individuals: personal registration information of the new individual;
S106, constructing a psychological test database: the data stored in the psychological test database comprises the following data: the psychometric table and the scores thereof, the source time of test data, personal information, personal historical psychometric text data, evaluation results and strategy suggestions;
S107, a text analysis module: the text analysis module comprises two parts:
and S108, text classification.
By integrating the above processes, a device for judging the psychological state of the user through text analysis according to another embodiment of the present invention is obtained, the device includes a data acquisition module, a psychological test database construction module, a text analysis module, a psychological health assessment module, and a result analysis module, wherein the text analysis is a semantic vector model established based on text analysis; the device comprises:
The data acquisition device is used for acquiring data of the psychological test database and data of the individual psychological text;
the psychological test database construction module is used for establishing a psychological test database based on the psychological test database data collected by the data collection module;
the text analysis module is used for preprocessing the personal psychological text data acquired by the data acquisition module, vectorizing and classifying the personal psychological text data, converting the personal psychological text data into corresponding semantic vectors and constructing a text analysis model;
The mental health evaluation module is used for constructing a mental health test calculation expression by utilizing the text analysis model based on mental text data of the user;
and the result analysis module is used for calculating based on the information health test calculation expression constructed by the mental health assessment module and analyzing the calculation result.
The psychological test database is constructed by utilizing a professional psychological measurement table contained in a psychological test database data set, an evaluation result and a suggestion thereof and combining personal information and historical psychological texts thereof.
And based on the psychological text data newly acquired by the individual, the psychological text data is combined with a psychological test database and input into a text-by-text analysis module, and then the psychological health assessment is carried out after text classification and semantic vectorization processing.
the psychological test calculation expression is an objective measurement standard obtained based on the user historical psychological text classification result, the psychological test table and the scores of the psychological test table.
Fig. 3 is a flowchart of a classification model executed in the psychological test model according to the embodiment, where the classification model includes text classification, data preprocessing, classification results, model evaluation, and other processes.
TABLE 1
s201 text labeling and segmentation: firstly, labeling a data set, specifically labeling a depression test as an example: labeling the psychological text according to options in a depression test psychological measuring table; depression tests it generally includes three types of features: physiological, psychological and behavioral aspects, we can classify the disease into different grades (e.g. severe, moderate, mild and normal), i.e. the classification model of depression has N-12 categories; therefore, the text can be labeled according to the ranking or strength of the options in the corresponding psychometric table, such as table 1.
The data set is then partitioned into a training set and a test set, typically at a partition ratio of (8: 2 or 7: 3);
s202 training set text: the training set text is used for training a psychological classification model;
S203 test set text: test set text for evaluating model prediction and other capabilities
s204, data preprocessing: the method is the first step of text classification, and the quality of a preprocessing result directly influences whether the subsequent analysis processing can be smoothly carried out. The purpose of text preprocessing is to extract main content from a text corpus in a normative manner and remove information irrelevant to the emotion classification of the text. For Chinese preprocessing, the main operations include standard coding, illegal character filtering, word segmentation processing, stop word removal and other steps;
1) and (3) encoding specification: the Chinese text generally relates to the problem of coding, the common Chinese coding comprises GB2312, GBK, UTF-8 and the like, and in order to avoid messy codes of the text, the text is uniformly coded;
2) and (3) filtering illegal characters: usually, only a few normal punctuations (such as:,. etc.) are needed when we process Chinese text, and even no punctuations other than Chinese are needed (such as:, #, @,％、&etc.), so we need to filter illegal characters in order to avoid affecting the accuracy of the subsequent model training;
3) word segmentation processing: the method is an important step in text analysis, the accuracy of the model is even directly influenced by the quality of the word segmentation (for example, "how good she cannot see" is divided into "how good she cannot see" and "how good she can see"), and common word segmentation methods such as Jieba word segmentation, Glove word segmentation, NLTK (Natural language processing toolkit) and the like;
4) Removing stop words: it is common to filter out certain Words or phrases, known as Stop Words, before processing text data. Generally, the stop words are manually input and are not automatically generated, the generated stop words form a stop word list, and here, the stop word list can be constructed according to texts and tasks (such as yes, and the like), and the stop words can not influence the accuracy of the model after being removed;
S205 training a classification model: before training the classification model, we need to vectorize the text, and the computer cannot recognize Chinese, so we need to convert it. The nature of model training is the various computations of the various values or matrices. Converting the samples into corresponding feature vectors, and feeding data to the model according to batch during training, wherein the data comprises the following steps: depression tests it generally includes three types of features: physiological, psychological and behavioral aspects, we can classify the disease into different grades (e.g. severe, moderate, mild and normal), i.e. the classification model of depression has N-12 categories; sequentially carrying out onehot (one-hot) coding on the labels, and training a psychological classification model by using sample data of a training set, thereby finishing the training and evaluation optimization of the psychological classification model;
and S206 model evaluation: testing the effect of the classification model by using the test set, wherein the classification model can be evaluated by using evaluation methods such as F1-score (F1 score), accuracy (accuracy rate), precision (precision rate) and the like; then, optimizing and adjusting the model according to the evaluation result; the optimization and adjustment methods include adjusting learning _ rate (the learning rate is usually 0.001 at the initial learning rate), dropping (dropping the common value 3 is between 0.5 and 1.0, and in a neural network, it is generally understood that neurons with a certain proportion are randomly disconnected), adjusting an optimization function (Adam optimization algorithm, SGD random gradient descent), and the like; finally, the prediction effect of the model is better, and the generalization capability is stronger;
S207, classification result: the classification model which is finally optimized is the model which is wanted by people, and the classification result is the classification result;
Fig. 4 is a flowchart for constructing a psychological test calculation expression according to the present embodiment. Wherein the content of the first and second substances,
s301 psychological test database: acquiring a psychological test database, and reading the content of the psychological test database;
s302, classifying and labeling the historical psychological texts of the user, counting the number of texts in each category according to a labeling result, and calculating the proportion Sn occupied by each category, wherein the weight of each category is Wn, N is 1, 2,. Vectorizing the historical psychological text of each category to obtain a historical psychological text vector sequence Ln；
Here the weight Wn for each category can be determined in a variety of ways, for example, expert determination; a historical data utilization rate allocation method, wherein the higher the category utilization rate is, the higher the weight is; historical data trend method, the more trends a certain category appears, the higher the weight, and so on;
S303, establishing a psychological test table and the scores thereof: extracting a psychological test table and a score thereof in a psychological test database; and converting the test questions in the psychological test table into corresponding test question semantic vector sequences Ck，k＝1，2，......M，m is the number of test questions; calculating historical psychological text vector sequence LnAnd test topic semantic vector sequence CkCosine similarity matrix Y between two pairsij，i＝1，2，..，N，j＝1，2，......M；
S304, constructing a psychological test calculation expression: the test standard quantity was calculated using the following formula:
The result analysis module performs result analysis based on the expression result, and includes:
calculating a test standard quantity according to a psychological test calculation expression;
and analyzing results according to the values calculated by the results, and feeding back standard evaluation results and strategy suggestions in the database to the user.
specifically, the above formula considers the ratio Sn of each class, the weight Wn of each class, and the cosine similarity matrix YijIf the standard quantity B is testedscoreor the closer the absolute value is to 1, the more stable the emotion of the current detected user is, and the psychological health is normal; conversely, the emotional fluctuation is large, and the mental health risk is large. This can be demonstrated by the inventors through extensive case analysis.
the method comprises the following steps of collecting personal psychological texts, including collecting personal information and historical psychological texts thereof: the personal information may be obtained through personal registration information, and the historical psychographic text is obtained from a social network account of the individual.
the data stored in the psychological test database comprises the following data: the system comprises a psychometric table and scores thereof, test data source time, personal information, personal historical psycho-text data, evaluation results and strategy suggestions.
the text classification also includes dividing the data set into a training set and a test set; the training set text is used for training a psychological classification model; the test set text is used to evaluate the performance of the model.
according to the technical scheme, the user does not need to manually do questions or make face-to-face contact with the user, the psychological state of the user is evaluated by analyzing the mood text or words of the user, the mode does not cause pressure on the user, the latest real psychological state of the user can be obtained, and finally an evaluation result and a corresponding countermeasure suggestion can be obtained through text analysis, so that the user can visually know the current psychological state of the user and self-adjust or even seek medical advice to achieve the state of psychological health.
One of the preferred implementations of the invention is a client application, namely, a set of instructions (program code) or other functional descriptive material in a code module that may, for example, be resident in the random access memory of the computer. Until required by the computer, the set of instructions may be stored in another computer memory, for example, in a hard disk drive, or in a removable memory such as an optical disk (for eventual use in a CD ROM) or floppy disk (for eventual use in a floppy disk drive), or downloaded via the Internet or other computer network. Thus, the present invention may be implemented as a computer program product for use in a computer. In addition, although the various methods described are conveniently implemented in a general purpose computer selectively activated or reconfigured by software, one of ordinary skill in the art would also recognize that such methods may be carried out in hardware, in firmware, or in more specialized apparatus constructed to perform the required method steps. Functional descriptive material is information that imparts functionality to a machine. Functional descriptive material includes, but is not limited to, computer programs, instructions, rules, facts, definitions of computable functions, objects, and data structures.
while particular embodiments of the present invention have been shown and described, it will be obvious to those skilled in the art that, based upon the teachings herein, that changes and modifications may be made without departing from this invention and its broader aspects.
the method and system provided by the present invention are described in detail above, and the principle and the implementation of the present invention are explained in the present document by applying specific examples, and the above description of the examples is only used to help understanding the method and the core idea of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.
Claims (8)
1. A system for evaluating psychological state based on a text semantic vector model comprises a text data acquisition module, a text data analysis module, a text data vectorization module, a psychological test model construction module and a result analysis module;
the method is characterized in that:
the text data acquisition module comprises psychological test database data acquisition and/or personal psychological text acquisition;
the text data analysis module is used for preprocessing text data and classifying the text, wherein the preprocessing comprises standard coding, filtering illegal characters, performing word segmentation processing and removing stop words; the text classification comprises text labeling and segmentation; establishing a text classification model by using the text data after the text segmentation and carrying out model test;
The text data vectorization module is used for vectorizing the text data processed by the text data analysis module;
the psychological test model building module is used for building a psychological test calculation expression, and the construction mode of the psychological test calculation expression is as follows:
s301, connecting the psychological test database, and reading the content of the psychological test database;
s302, classifying and labeling the historical psychological texts of the user, counting the number of texts in each category according to a labeling result, and calculating the proportion Sn occupied by each category, wherein the weight of each category is Wn, N is 1, 2,. Vectorizing the historical psychological text of each category to obtain a historical psychological text vector sequence Ln；
S303, establishing a psychological test table and the scores thereof: extracting a psychological test table in a psychological test database; and converting the test questions in the psychological test table into corresponding test question semantic vector sequences Ckk is 1, 2,.... M, M is the number of test questions; calculating historical psychological text vector sequence LnAnd test topic semantic vector sequence CkCosine similarity matrix Y between two pairsij，i＝1，2，..，N，j＝1，2，......M；
s304, constructing a psychological test calculation expression: the test standard quantity was calculated using the following formula:
The result analysis module performs result analysis based on the expression result, and includes:
calculating a test standard quantity according to a psychological test calculation expression;
and analyzing results according to the values calculated by the results, and feeding back standard evaluation results and strategy suggestions in the database to the user.
2. the system of claim 1, wherein collecting the personal psychographic text comprises collecting the personal information and its historical psychographic text: the personal information may be obtained through personal registration information, and the historical psychographic text is obtained from a social network account of the individual.
3. The system of claim 1, wherein the data stored by the psychological test database comprises the following data: the system comprises a psychometric table and scores thereof, test data source time, personal information, personal historical psycho-text data, evaluation results and strategy suggestions.
4. The system of claim 1, wherein text classification further comprises dividing the data set into a training set and a test set; the training set text is used for training a psychological classification model; the test set text is used to evaluate the performance of the model.
5. a device for judging the psychological state of a user through text analysis, which comprises a data acquisition module, a psychological test database construction module, a text analysis module, a psychological health assessment module and a result analysis module, wherein the text analysis is a semantic vector model established by text analysis based on the system of any one of claims 1-4; the device comprises:
the data acquisition device is used for acquiring data of the psychological test database and data of the individual psychological text;
The psychological test database construction module is used for establishing a psychological test database based on the psychological test database data collected by the data collection module;
the text analysis module is used for preprocessing the personal psychological text data acquired by the data acquisition module, vectorizing and classifying the personal psychological text data, converting the personal psychological text data into corresponding semantic vectors and constructing a text analysis model;
The mental health evaluation module is used for constructing a mental health test calculation expression by utilizing the text analysis model based on mental text data of the user;
And the result analysis module is used for calculating based on the information health test calculation expression constructed by the mental health assessment module and analyzing the calculation result.
6. the apparatus of claim 5, wherein the psychological test database is constructed by using professional psychological measurement tables and evaluation results and suggestions thereof contained in the psychological test database data set, and combining the personal information and historical psychological texts thereof.
7. The apparatus according to claim 5, wherein the psychometric health assessment is performed after text classification and semantic vectorization processing are performed after the newly collected psychometric text data is input into the text analysis module together with the psychometric test database based on the individual.
8. The apparatus of claim 5, wherein said psychometric computational expression is an objective measure based on historical psychometric text classification results of the user and psychometric test charts and scores thereof.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910645841.0A CN110570941B (en) | 2019-07-17 | 2019-07-17 | System and device for assessing psychological state based on text semantic vector model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910645841.0A CN110570941B (en) | 2019-07-17 | 2019-07-17 | System and device for assessing psychological state based on text semantic vector model |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110570941A true CN110570941A (en) | 2019-12-13 |
| CN110570941B CN110570941B (en) | 2020-08-14 |
Family
ID=68773154
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910645841.0A Active CN110570941B (en) | 2019-07-17 | 2019-07-17 | System and device for assessing psychological state based on text semantic vector model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110570941B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111312394A (en) * | 2020-01-15 | 2020-06-19 | 东北电力大学 | Psychological health condition evaluation system based on combined emotion and processing method thereof |
| CN111477329A (en) * | 2020-03-31 | 2020-07-31 | 北京智能工场科技有限公司 | Method for evaluating psychological state based on image-text combination |
| CN111881677A (en) * | 2020-07-28 | 2020-11-03 | 武汉大学 | Address matching algorithm based on deep learning model |
| CN112185558A (en) * | 2020-09-22 | 2021-01-05 | 珠海中科先进技术研究院有限公司 | Mental health and rehabilitation evaluation method, device and medium based on deep learning |
| CN113343711A (en) * | 2021-06-29 | 2021-09-03 | 南方电网数字电网研究院有限公司 | Work order generation method, device, equipment and storage medium |
| CN115019954A (en) * | 2022-05-26 | 2022-09-06 | 北京师范大学 | Post-traumatic stress disorder patient prediction system |
| CN115910345A (en) * | 2022-12-22 | 2023-04-04 | 广东数业智能科技有限公司 | Mental health assessment intelligent early warning method and storage medium |
Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6189002B1 (en) * | 1998-12-14 | 2001-02-13 | Dolphin Search | Process and system for retrieval of documents using context-relevant semantic profiles |
| CN104636456A (en) * | 2015-02-03 | 2015-05-20 | 大连理工大学 | Question routing method based on word vectors |
| CN105740224A (en) * | 2014-12-11 | 2016-07-06 | 仲恺农业工程学院 | Text analysis based user psychology early warning method and apparatus |
| CN106202032A (en) * | 2016-06-24 | 2016-12-07 | 广州数说故事信息科技有限公司 | A kind of sentiment analysis method towards microblogging short text and system thereof |
| CN106502989A (en) * | 2016-10-31 | 2017-03-15 | 东软集团股份有限公司 | Sentiment analysis method and device |
| CN106776503A (en) * | 2016-12-22 | 2017-05-31 | 东软集团股份有限公司 | The determination method and device of text semantic similarity |
| CN107145524A (en) * | 2017-04-12 | 2017-09-08 | 清华大学 | Suicide risk checking method and system based on microblogging and Fuzzy Cognitive Map |
| CN108021660A (en) * | 2017-12-04 | 2018-05-11 | 中国人民解放军国防科技大学 | Topic self-adaptive microblog emotion analysis method based on transfer learning |
| CN108171358A (en) * | 2017-11-27 | 2018-06-15 | 科大讯飞股份有限公司 | Result prediction method and device, storage medium, electronic equipment |
| CN108399575A (en) * | 2018-01-24 | 2018-08-14 | 大连理工大学 | A kind of five-factor model personality prediction technique based on social media text |
| CN108511071A (en) * | 2018-04-18 | 2018-09-07 | 广东惠禾科技发展有限公司 | Mental health evaluation method and device |
| CN109299865A (en) * | 2018-09-06 | 2019-02-01 | 西南大学 | Psychological assessment system and method, information data processing terminal based on semantic analysis |
| CN109376251A (en) * | 2018-09-25 | 2019-02-22 | 南京大学 | A kind of microblogging Chinese sentiment dictionary construction method based on term vector learning model |
| CN109543084A (en) * | 2018-11-09 | 2019-03-29 | 西安交通大学 | A method of establishing the detection model of the hidden sensitive text of network-oriented social media |
| CN109671487A (en) * | 2019-02-25 | 2019-04-23 | 上海海事大学 | A kind of social media user psychology crisis alert method |
| CN109906449A (en) * | 2016-10-27 | 2019-06-18 | 华为技术有限公司 | A kind of lookup method and device |
-
2019
- 2019-07-17 CN CN201910645841.0A patent/CN110570941B/en active Active
Patent Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6189002B1 (en) * | 1998-12-14 | 2001-02-13 | Dolphin Search | Process and system for retrieval of documents using context-relevant semantic profiles |
| CN105740224A (en) * | 2014-12-11 | 2016-07-06 | 仲恺农业工程学院 | Text analysis based user psychology early warning method and apparatus |
| CN104636456A (en) * | 2015-02-03 | 2015-05-20 | 大连理工大学 | Question routing method based on word vectors |
| CN106202032A (en) * | 2016-06-24 | 2016-12-07 | 广州数说故事信息科技有限公司 | A kind of sentiment analysis method towards microblogging short text and system thereof |
| CN109906449A (en) * | 2016-10-27 | 2019-06-18 | 华为技术有限公司 | A kind of lookup method and device |
| CN106502989A (en) * | 2016-10-31 | 2017-03-15 | 东软集团股份有限公司 | Sentiment analysis method and device |
| CN106776503A (en) * | 2016-12-22 | 2017-05-31 | 东软集团股份有限公司 | The determination method and device of text semantic similarity |
| CN107145524A (en) * | 2017-04-12 | 2017-09-08 | 清华大学 | Suicide risk checking method and system based on microblogging and Fuzzy Cognitive Map |
| CN108171358A (en) * | 2017-11-27 | 2018-06-15 | 科大讯飞股份有限公司 | Result prediction method and device, storage medium, electronic equipment |
| CN108021660A (en) * | 2017-12-04 | 2018-05-11 | 中国人民解放军国防科技大学 | Topic self-adaptive microblog emotion analysis method based on transfer learning |
| CN108399575A (en) * | 2018-01-24 | 2018-08-14 | 大连理工大学 | A kind of five-factor model personality prediction technique based on social media text |
| CN108511071A (en) * | 2018-04-18 | 2018-09-07 | 广东惠禾科技发展有限公司 | Mental health evaluation method and device |
| CN109299865A (en) * | 2018-09-06 | 2019-02-01 | 西南大学 | Psychological assessment system and method, information data processing terminal based on semantic analysis |
| CN109376251A (en) * | 2018-09-25 | 2019-02-22 | 南京大学 | A kind of microblogging Chinese sentiment dictionary construction method based on term vector learning model |
| CN109543084A (en) * | 2018-11-09 | 2019-03-29 | 西安交通大学 | A method of establishing the detection model of the hidden sensitive text of network-oriented social media |
| CN109671487A (en) * | 2019-02-25 | 2019-04-23 | 上海海事大学 | A kind of social media user psychology crisis alert method |
Non-Patent Citations (4)
| Title |
|---|
| 刘林: "《面向论坛文本的大学生情绪识别研究》", 《中国优秀硕士论文全文数据库 社会科学II辑》 * |
| 徐源音: "《面向社交网络文本的情绪分析方法研究》", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 方振宇: "《基于词向量的微博用户抑郁预测方法研究》", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 杜天宝等: "《基于文本情感特征的心理评估模型》", 《吉林大学学报（理学版）》 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111312394A (en) * | 2020-01-15 | 2020-06-19 | 东北电力大学 | Psychological health condition evaluation system based on combined emotion and processing method thereof |
| CN111312394B (en) * | 2020-01-15 | 2023-09-29 | 东北电力大学 | Psychological health assessment system based on combined emotion and processing method thereof |
| CN111477329A (en) * | 2020-03-31 | 2020-07-31 | 北京智能工场科技有限公司 | Method for evaluating psychological state based on image-text combination |
| CN111477329B (en) * | 2020-03-31 | 2021-04-13 | 北京智能工场科技有限公司 | Method for evaluating psychological state based on image-text combination |
| CN111881677A (en) * | 2020-07-28 | 2020-11-03 | 武汉大学 | Address matching algorithm based on deep learning model |
| CN112185558A (en) * | 2020-09-22 | 2021-01-05 | 珠海中科先进技术研究院有限公司 | Mental health and rehabilitation evaluation method, device and medium based on deep learning |
| CN113343711A (en) * | 2021-06-29 | 2021-09-03 | 南方电网数字电网研究院有限公司 | Work order generation method, device, equipment and storage medium |
| CN115019954A (en) * | 2022-05-26 | 2022-09-06 | 北京师范大学 | Post-traumatic stress disorder patient prediction system |
| CN115910345A (en) * | 2022-12-22 | 2023-04-04 | 广东数业智能科技有限公司 | Mental health assessment intelligent early warning method and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110570941B (en) | 2020-08-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110570941B (en) | System and device for assessing psychological state based on text semantic vector model | |
| Kim et al. | A systematic review of the validity of screening depression through Facebook, Twitter, Instagram, and Snapchat | |
| Victor et al. | Detecting depression using a framework combining deep multimodal neural networks with a purpose-built automated evaluation. | |
| CN110391013B (en) | System and device for predicting mental health by building neural network based on semantic vector | |
| AU2016278357A1 (en) | Method and system for monitoring stress conditions | |
| KR101829606B1 (en) | Apparatus and method for diagnostic of internet overflow | |
| Wang et al. | Classification of proactive personality: Text mining based on weibo text and short-answer questions text | |
| Ranyard et al. | Verbal data and decision process analysis | |
| KR20200076183A (en) | Psychological analysis and psychotherapy system using diary | |
| CN111477329B (en) | Method for evaluating psychological state based on image-text combination | |
| Kono et al. | Predictive power of leisure constraint-negotiation models within the leisure-time physical activity context: A partial least squares structural equation modeling approach | |
| Nasrullah et al. | Detection of types of mental illness through the social network using ensembled deep learning model | |
| US20210312942A1 (en) | System, method, and computer program for cognitive training | |
| Lenzi et al. | The social phenotype: Extracting a patient-centered perspective of diabetes from health-related blogs | |
| CN113658697A (en) | Psychological assessment system based on video fixation difference | |
| Amini et al. | Word associations contribute to machine learning in automatic scoring of degree of emotional tones in dream reports | |
| Flores et al. | Depression screening using deep learning on follow-up questions in clinical interviews | |
| Latif et al. | Understanding depression detection using social media | |
| Yuan et al. | Applying item response theory modeling to identify social (pragmatic) communication disorder | |
| Bremer et al. | Predicting the individual mood level based on diary data | |
| Cowen et al. | Facial movements have over twenty dimensions of perceived meaning that are only partially captured with traditional methods | |
| JP7116515B1 (en) | Decision-making ability evaluation device, system, and program | |
| Su et al. | Depressive emotion recognition based on behavioral data | |
| RU2813438C1 (en) | System and method for identifying and using reference emotional-intellectual profile (ei-profile) by analysis groups | |
| Simari et al. | The Big-2/ROSe Model of Online Personality: Towards a Lightweight Set of Markers for Characterizing the Behavior of Social Platform Denizens |
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 | ||
| CB03 | Change of inventor or designer information | ||
| CB03 | Change of inventor or designer information |
Inventor after: Wang Chongchong Inventor after: Ren Yongliang Inventor after: Yang Fei Inventor after: Zhang Jia Inventor after: Li Jiayi Inventor after: He Tonglu Inventor after: Gong Yousan Inventor before: Wang Chongchong Inventor before: Ren Yongliang Inventor before: Yang Fei Inventor before: Zhang Jia Inventor before: Li Jiayi Inventor before: He Tonglu Inventor before: Gong Yousan |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |