CN112182339A - Psychological assessment method and system - Google Patents
Psychological assessment method and system Download PDFInfo
- Publication number
- CN112182339A CN112182339A CN202011211739.9A CN202011211739A CN112182339A CN 112182339 A CN112182339 A CN 112182339A CN 202011211739 A CN202011211739 A CN 202011211739A CN 112182339 A CN112182339 A CN 112182339A
- Authority
- CN
- China
- Prior art keywords
- data
- psychological assessment
- psychological
- behavior
- network
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/951—Indexing; Web crawling techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
- G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- 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
Abstract
The system can improve the accuracy of sample data and ensure the accuracy of test results by acquiring network behavior data which does not need to be subjectively matched by a person to be evaluated or data which is less influenced by subjective factors of the person to be evaluated as analysis sample data of psychological evaluation, so that the current psychological health state of the person to be evaluated can be objectively and accurately reflected by a psychological evaluation scoring result calculated by a psychological evaluation model, and accurate and objective judgment basis is provided for clinical psychological diagnosis.
Description
Technical Field
The invention belongs to the technical field of computers, and particularly relates to a psychological assessment method and a psychological assessment system.
Background
Under the long-term fast-paced pressure of life, work and learning, people are easy to induce various psychological diseases, and the life quality and physical and psychological health of people are influenced. For example, many urban white collars are under high working stress, are under high tension for a long time, and often cannot be conditioned in time, and can cause anxiety, mental depression and other symptoms over time, and can induce psychological disorders or mental diseases. Generally, the first step in providing mental health services is to perform mental health status assessment on an individual. The mental health state assessment is a method for evaluating and estimating the psychological characteristics (cognition, emotion, personality, capability, behavior mode and the like), the psychological state and level of a human according to the principle and method of psychology, and determining the reason, the nature and the degree of normality or abnormality of the human, thereby providing a basis for clinical psychological diagnosis.
The questionnaire test method is one of the methods widely applied in mental health state assessment test. The psychological data collected by the traditional questionnaire method of individuals has the following problems: on the one hand, the data collected through the questionnaire is greatly influenced by subjective factors of the respondents, for example, the questionnaire is designed in an irregular and scientific manner, or the respondents easily fail to answer, and blindly answer due to the cognitive ability, knowledge level, and other factors, so that the questionnaire result cannot truly reflect the psychological state of the respondents. On the other hand, questionnaire survey is heavy and complicated in workload, processing such as distribution, recovery and arrangement of questionnaires is often required, a large amount of labor, material and time costs are required, collection efficiency is low, and the questionnaire survey is difficult to apply to a large-scale psychological assessment test.
Disclosure of Invention
The embodiment of the invention aims to provide a psychological assessment method and a psychological assessment system, and aims to solve the problems that the existing psychological assessment test method is low in assessment accuracy and needs to consume a large amount of manpower, material resources and time cost.
The embodiment of the invention is realized in such a way that a psychological assessment system comprises a data acquisition unit, a data preprocessing unit and a psychological assessment result calculation unit;
the data acquisition unit is used for obtaining network behavior data of a person to be evaluated in a crawling mode from a network and acquiring expression data, behavior data and physiological characteristic data which are induced when the person to be evaluated watches a virtual reality scene corresponding to the selected psychological scale;
the data preprocessing unit is used for performing data cleaning and vectorization preprocessing on the network behavior data, the expression data, the behavior data and the physiological characteristic data and constructing a vector sequence;
and the psychological assessment result calculating unit is used for inputting the vector sequence into a preset psychological assessment model obtained through convolutional neural network training for calculation to obtain and output a psychological assessment scoring result.
Another objective of an embodiment of the present invention is to provide a psychological assessment method, including the following steps:
the method comprises the steps that network behavior data of a person to be evaluated are obtained through crawling from a network, and expression data, behavior data and physiological feature data which are induced when the person to be evaluated watches a virtual reality scene corresponding to a selected psychological scale are obtained;
performing data cleaning and vectorization preprocessing on the network behavior data, the expression data, the behavior data and the physiological characteristic data, and constructing a vector sequence;
and inputting the vector sequence into a preset psychological assessment model obtained through convolutional neural network training for calculation to obtain and output a psychological assessment scoring result.
According to the psychological assessment system provided by the embodiment of the invention, the network behavior data of the to-be-assessed person are obtained by crawling from the network through the data acquisition unit, the network behavior data can truly and objectively reflect information such as individual preference deviation and use route and the like expressed by the to-be-assessed person when the to-be-assessed person uses a network medium/service tool, and the data are acquired without subjective cooperation of the to-be-assessed person or active participation of the to-be-assessed person, so that data errors caused by subjective factors of the to-be-assessed person can be avoided, the result accuracy of psychological assessment is improved, and reliable bases are better provided for clinical psychological diagnosis; in addition, expression data, behavior data and physiological characteristic data which are induced when the person to be evaluated watches the virtual reality scene corresponding to the selected psychological scale are obtained through the data obtaining unit, the data can objectively reflect real emotional expression of the person to be evaluated under the specific virtual reality scene, and authenticity and accuracy of sample data are guaranteed; in addition, in order to further improve the accuracy of the data, the acquired data is cleaned through the data preprocessing unit, vectorization processing is carried out on the cleaned data to construct a vector sequence, a preset psychological assessment model is input to carry out calculation, and a psychological assessment scoring result is obtained.
Drawings
Fig. 1 is a block diagram of a psychological assessment system according to an embodiment of the present invention;
fig. 2 is a flowchart illustrating an implementation of a psychological assessment method according to an embodiment of the present invention;
FIG. 3 is a flowchart illustrating another implementation of a psychological assessment method according to an embodiment of the present invention;
fig. 4 is a flowchart illustrating a training process of a psychological assessment model according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
It will be understood that, as used herein, the terms "first," "second," and the like may be used herein to describe various elements, but these elements are not limited by these terms unless otherwise specified. These terms are only used to distinguish one element from another. For example, the first convolutional neural network may be referred to as a second convolutional neural network, and similarly, the second convolutional neural network may be referred to as a first convolutional neural network, without departing from the scope of the present application.
According to the psychological assessment system provided by the embodiment of the invention, the network behavior data which does not need to be subjectively matched with the person to be assessed is obtained, or the data which is less influenced by the subjective factors of the person to be assessed, for example, expression data, behavior data and physiological characteristic data which are induced when the person to be assessed watches a virtual reality scene corresponding to the selected psychological scale are used as the analysis sample data of the psychological assessment, so that the accuracy of the sample data can be improved, the accuracy of the test result is ensured, the current psychological health state of the person to be assessed can be objectively and accurately reflected by the psychological assessment scoring result calculated by the psychological assessment model, and an accurate and objective judgment basis is provided for clinical psychological diagnosis.
Referring to fig. 1, an embodiment of the present invention provides a psychological assessment system, which includes a data acquisition unit 100, a data preprocessing unit 200, and a psychological assessment result calculation unit 300.
The data obtaining unit 100 is configured to obtain network behavior data of a person to be evaluated by crawling from a network, and obtain expression data, behavior data, and physiological feature data induced when the person to be evaluated watches a virtual reality scene corresponding to a selected mental scale.
The data preprocessing unit 200 is configured to perform data cleaning and vectorization preprocessing on the network behavior data, the expression data, the behavior data, and the physiological characteristic data, and construct a vector sequence.
And the psychological evaluation result calculating unit 300 is configured to input the vector sequence into a preset psychological evaluation model obtained through convolutional neural network training for calculation, obtain a psychological evaluation scoring result, and output the psychological evaluation scoring result.
The network, as the most efficient way of human interaction and propagation medium so far, has widely and profoundly changed the way of life of people. Plays an indispensable important role in life, work and learning of people. Froude said that "one of the most prominent features exhibited by a psychological group is: regardless of who the individuals comprising the mental group are, and regardless of how similar or dissimilar the lifestyle, occupation, personality, and intelligence of the individuals are, the fact that they have formed a group places them under the mental control of a group whose mind makes them feel, think, and act in a manner that is distinct from when they are solitary individually. That is, human behavior is very different between the time of the individuality and the time of the collective transaction, the internet enables users to connect with the society in a relatively isolated manner, and the cognitive process, the behavioral process, emotional feeling and self-consciousness of network users are affected. Based on this theoretical basis, there is an established basis for assessing mental health using the behavior of the network.
In the embodiment of the invention, the network behavior data is time sequence information and webpage content generated when the to-be-evaluated person uses a network medium/service tool; the webpage content comprises various instant messaging information used by the to-be-evaluated person, browsed webpage types, webpage access content, webpage download content, and time interval and time length of surfing the internet every day.
The network media/service tools include, but are not limited to, QQ, WeChat, mailbox, Ebook, electronic newspaper, electronic magazine, radio, television, newsletter, audiovisual product, exhibition product, etc. The types of web pages include enterprise web sites, large portal web sites, industry web sites, transaction web sites, classification information web sites, forum web sites, government web sites, functional web sites, entertainment web sites, and the like. The web page access content includes an IP address, an access path, etc. of the accessed web page. The web page download content refers to text, pictures, audio, video and the like downloaded from a web page by a user.
In an exemplary embodiment of the invention, the time series information generated by the evaluator when using the network medium/service tool and the corresponding web page content can be obtained by crawling from the log of the network device such as a mobile phone, a computer and the like used by the evaluator.
In an exemplary embodiment of the present invention, the time series information generally refers to time information recorded in a log about the use of a network medium/service tool by a person to be evaluated using a network device such as a mobile phone, a computer, or the like. The time sequence information and the web page content can be recorded and formed into a schedule according to the form that one column of time sequence information corresponds to one column of web page content. For example, the time series information field records in sequence: 20XX year X month X day 8: 23. 9:00, 12: 30; the web page content column correspondingly records the events of the user using the network media/service tool at each time point or time period. For example, 20XX year X month X day 8: 23, logging in Taobao APP; 9:00, quitting the Taobao APP; 12:30 registers in QQ mailbox, receives the mail sent by XX, the title of the mail is XXX, and the attachment is XXX.
In the embodiment of the invention, the psychological scales comprise 78 types of commonly used scales such as emotion evaluation, mental health evaluation, interpersonal communication evaluation, ability evaluation, learning evaluation, personality evaluation, marital family evaluation and the like. Examples include symptom self-rating scale (SCL-90), life satisfaction index A, B (LSIA, LSIB), family Function Assessment (FAD), Olson marital quality questionnaire (ENRICH), BECK Depression questionnaire (BDI-13), Depression self-rating scale (SDS), senile Depression scale (GDS), orphan Classification scale (DLS), social avoidance and distress Scale (SAD), personality type diagnosis scale, Essen mood stability test (ASK), and the like.
In an embodiment of the present invention, the virtual reality scene is a virtual reality scenario generated by a virtual reality technology and corresponding to the selected mental scale and having a specific emotion inducing effect, and is used for inducing a person to be evaluated to generate an expected emotion so as to collect expression data, behavior data and physiological characteristic data generated by the person to be evaluated when dealing with the virtual reality scenario.
The selected psychological scale is taken as a depression self-rating scale for example and is explained in detail below. Virtual reality scenes with specific emotion induction effects respectively corresponding to 20 items designed on the depression self-rating scale are generated through virtual reality technology. For example, the first item on the depression self-rating scale is the question and answer item "i find depressed, depressed". At this time, a virtual reality scene corresponding to the item, which is previously constructed by the virtual reality technology, may be displayed on the screen, for example, a scene in which a child alone sitting in a dark environment is displayed on a black-and-white screen. At this time, the data acquisition unit 100 may acquire a series of expression, behavior, and physiological characteristic data generated when the person to be evaluated views the virtual reality scene through a preset image pickup device, a sensor, and the like.
In the preferred embodiment of the invention, in order to design the virtual reality scene, the content designed by each item on the scale can be met, and the effect of inducing the person to be evaluated to generate expected emotion can be achieved, so that the relevant evaluation data of real and objective emotional expression of the person to be evaluated in response to the scenes can be collected, the scientific reasonableness of evaluation is further improved, and the virtual reality scene corresponding to the content of the item designed on the scale can be designed by combining the clinical experience knowledge of professional medical care personnel, psychologists, micro-expression researchers and the like.
In the embodiment of the invention, expression data, behavior data and physiological characteristic data induced when a user watches a virtual reality scene corresponding to a certain item on the scale can be collected, and then the test score of the user in the item can be determined according to a preset scoring rule.
The preset scoring rule may first find, based on a known sample, a correspondence between expressions, behaviors, and physiological characteristics induced by the user when viewing the virtual reality scene corresponding to each item in the selected mental scale, by using an existing machine learning method, thereby creating a mapping table based on a correspondence between expression, behavior, and physiological characteristic data generated by the user when the user is induced by a specific virtual reality scene and the corresponding item score.
For example, the depression self-rating scale is designed with 20 items (only a part of the items are shown in table 1),
TABLE 1
The collected expression, behavior and physiological characteristic data of the person to be evaluated in each corresponding specific virtual reality scene are compared with the preset standard expression, standard behavior and standard physiological characteristic data generated in the specific virtual reality scene corresponding to the item, whether the collected expression, behavior and physiological characteristic data are within the threshold range of the preset standard expression, standard behavior and standard physiological characteristic data is judged, and the score of the person to be evaluated in the test of the item is determined according to the number of the conforming items of each item of data. For example, when it is collected that expression data, behavior data and physiological characteristic data generated by a person to be evaluated in a specific virtual reality scene corresponding to the first item in table 1 are not within a preset threshold range of standard behavior and standard physiological characteristic data, a vector sequence [0,0,0] is constructed and the score is 1; when two of the acquired expression data, behavior data and physiological characteristic data are not in a preset threshold range, a vector sequence [1,0,0] or [0,1,0] or [0,0,1] is constructed, and the score is 2; when one of the acquired expression data, behavior data and physiological characteristic data is not in a preset threshold range, constructing to obtain a vector sequence [1,1,0] or [0,1,1] or [1,0,1], and scoring for 3 points; when the collected expression data, behavior data and physiological characteristic data are all in a preset threshold range, a vector sequence [1,1,1] is constructed, and the score is 4.
In an embodiment of the present invention, the expression data includes facial expressions that are excited, liked, surprised, painful, feared, humiliated, disgusted, and angry; the behavioral data includes eye movements, head movements, and limb movements. The physiological characteristic data comprises brain wave, pulse, electrocardio, respiration and myoelectric data.
The real expression, behavior and physiological characteristic data of the to-be-evaluated person under the scene can be collected by collecting the expression data, behavior data and physiological characteristic data which are induced when the to-be-evaluated person watches the virtual reality scene corresponding to the selected psychological scale, the authenticity and scientificity of sample data are improved, and the mental health state of the to-be-evaluated person under a certain specific scene at a certain period can be comprehensively judged in multiple aspects by combining the network behavior data of the to-be-evaluated person which is crawled from the network.
In an embodiment of the present invention, the data preprocessing unit 200 is specifically configured to:
and cleaning and removing abnormal data and repeated data in the network behavior data, the expression data, the behavior data and the physiological characteristic data, and constructing a vector sequence based on a preset vectorization rule.
In the embodiment of the present invention, the network behavior data is text data, and the expression data and the behavior data are image data.
The step of cleaning and removing abnormal data and repeated data in the network behavior data, the expression data, the behavior data and the physiological characteristic data specifically comprises the following steps:
and performing word segmentation processing on the network behavior data, and filtering to remove stop words and illegal characters.
Extracting contour characteristic information and pixel characteristic information of a target area of the expression data and the behavior data, comparing the contour characteristic information and the pixel characteristic information with contour characteristic information and pixel characteristic information in a preset standard expression and standard behavior database respectively, determining whether the target area has a corresponding standard expression or standard behavior, and filtering image data of which the corresponding standard expression or standard behavior cannot be found.
In an embodiment of the invention, the network behavior data is participled to remove stop words (e.g., certain manually entered, non-automatically generated words, or words not present in a dictionary, etc.) and illegal characters (e.g., &,.... etc.). The filtered stop words and illegal characters have no influence on the substantial content of the sample data and the accuracy of the subsequent analysis.
In the embodiment of the present invention, the standard expression and standard behavior database collects a picture storing various standard expressions and standard behaviors corresponding to each test item in the psychometric scale for psychological assessment. For example, the first test in the depression self-rating scale is the question and answer "i find depressed, depressed" with four scoring options, one for each standard expression and standard behavior.
By extracting the contour characteristic information and the pixel characteristic information of the target area in each frame of picture in the target area of the expression data and the behavior data and comparing the contour characteristic information and the pixel characteristic information with the contour characteristic information and the pixel characteristic information in a preset standard expression and standard behavior database, whether the corresponding standard expression or standard behavior exists in the target area of the expression data and the behavior data can be determined, so that the image data without the corresponding standard expression or standard behavior is filtered, the image data without the statistical analysis significance is removed, the burden of machine operation is reduced, and the efficiency and the accuracy of analysis and evaluation are improved.
In an exemplary embodiment of the present invention, first, it is determined whether the network behavior data has a similar word or a similar word to a preset word, or whether the expression data and the behavior data (image data) have attribute features of expressions or actions that are similar or similar to a preset standard expression or action, or whether physiological feature indexes in the physiological feature data are within a preset threshold range, and the physiological feature indexes are recorded in the form of boolean values (0 or 1). And recording as 1, wherein preset words which are the same or similar to the preset words exist in the network behavior data, and recording as 0 if the preset words are not the same. The expression data contains the same or similar expressions of the preset standard substances, and the expression data is marked as 1, otherwise, the expression data is marked as 0. The behavior data contains the same or similar actions of the preset standard substance, and is marked as 1, otherwise, the action data is marked as 0. And (3) the physiological characteristic indexes in the physiological characteristic data accord with a preset threshold range and are marked as 1, otherwise, the physiological characteristic indexes are marked as 0, and the attribute characteristics are constructed into a characteristic vector sequence.
Assuming that words which are the same as or similar to preset words (such as gloomy) exist in the network behavior data and are marked as 1; the expression data contains the same or similar expression of a preset standard expression (such as a crying face), and the expression data is marked as 1; the behavior data contains the same or similar actions of preset standard actions (such as umbrellas) and is marked as 1; if the heartbeat frequency in the physiological characteristic data meets a preset threshold range, the heartbeat frequency is marked as 1. The feature vector constructed by these attribute features is [1,1,1,1 ].
In the embodiment of the present invention, the preset words and phrases, the standard expressions, the standard behaviors, and the physiological characteristic index threshold ranges in the network behavior data, the expression data, the behavior data, or the physiological characteristic data may be set in a matching manner according to the evaluated items. For example, the task of psychological assessment is a character type test, such as outward type character, the preset words of the text data of the network behavior can be "like", "enthusiasm", "cheerful", "good at social", etc., and the standard expressions preset in the expression data can be "smiling face picture", "handshaking picture", etc. The standard behaviors in the behavior data can be 'dance pictures' and the like. The preset physiological characteristic indexes in the physiological characteristic data include heart rate, brain waves and the like, and the corresponding threshold ranges of the heart rate and the brain waves can be set according to common medical general knowledge, for example, the threshold range for quickening the heartbeat is 100 heartbeats/minute.
In an embodiment of the present invention, the step of obtaining the psychological assessment model through convolutional neural network training includes:
respectively carrying out data cleaning and vectorization preprocessing on the acquired network behavior data of the user to obtain a network behavior vector sequence;
extracting contour characteristic information and pixel characteristic information from the collected expression data and behavior data of the user respectively;
extracting physiological characteristic information in the physiological characteristic data;
inputting the network behavior vector sequence and the physiological characteristic data vector sequence into a first convolutional neural network for training, and inputting the extracted shape characteristic information, pixel characteristic information and physiological characteristic information into a second convolutional neural network for training;
and fusing the network behaviors, the shape characteristic information, the pixel characteristic information and the physiological characteristic information which are processed by the first convolutional neural network and the second convolutional neural network to obtain a psychological assessment model.
In the embodiment of the invention, the first convolution neural network and the second neural network have the same structure. Inputting a vector sequence to the convolutional neural network for training is a technical means well known to those skilled in the art, and a specific implementation process of the step is not described in detail in the present invention.
In the embodiment of the invention, the outputs of the first convolutional neural network of the network behavior and physiological characteristic data vector sequence, the second convolutional neural network of the shape characteristic information and the pixel characteristic information are input into a softmax layer after characteristic fusion, and the psychological assessment model of the invention is obtained.
Fig. 2 is a flowchart illustrating an implementation of a psychological assessment method according to an embodiment of the present invention, and for convenience of description, only the parts related to the embodiment of the present invention are shown in the present invention.
As shown in fig. 2, an embodiment of the present invention provides a psychological assessment method, including the following steps:
step S202, network behavior data of a person to be evaluated is obtained through crawling from a network, and expression data, behavior data and physiological feature data induced when the person to be evaluated watches a virtual reality scene corresponding to a selected psychological scale are obtained.
Step S204, performing data cleaning and vectorization pretreatment on the network behavior data, the expression data, the behavior data and the physiological characteristic data, and constructing a vector sequence;
and S206, inputting the vector sequence into a preset psychological assessment model obtained through convolutional neural network training for calculation, obtaining and outputting a psychological assessment scoring result.
According to the psychological assessment method provided by the embodiment of the invention, the network behavior data of the person to be assessed can be obtained by crawling the network from the network through the data acquisition unit, the network behavior data can truly and objectively reflect information such as individual preference bias and use route and the like expressed by the person to be assessed when the person to be assessed uses a network medium/service tool, and the data acquisition does not need subjective cooperation of the person to be assessed or active participation of the person to be assessed, so that data errors caused by subjective factors of the person to be assessed can be avoided, the accuracy of the result of the psychological assessment is improved, and reliable basis is better provided for clinical psychological diagnosis; in addition, expression data, behavior data and physiological characteristic data which are induced when the person to be evaluated watches the virtual reality scene corresponding to the selected psychological scale are obtained through the data obtaining unit, the data can objectively reflect real emotional expression of the person to be evaluated under the specific virtual reality scene, and authenticity and accuracy of sample data are guaranteed; in addition, in order to further improve the accuracy of the data, the acquired data is cleaned through the data preprocessing unit, vectorization processing is carried out on the cleaned data to construct a vector sequence, a preset psychological assessment model is input to carry out calculation, and a psychological assessment scoring result is obtained.
Fig. 3 is a flowchart illustrating another implementation of the psychological assessment method according to the embodiment of the present invention, and for convenience of description, only the parts related to the embodiment of the present invention are shown in the diagram, which is described in detail below.
As shown in fig. 3, the embodiment of the present invention is substantially the same as the implementation flow of the psychological assessment method shown in fig. 2, and is different from the implementation flow of the psychological assessment method shown in fig. 2 in that step S204 is replaced with step S302.
Step S302, abnormal data and repeated data in the network behavior data, the expression data, the behavior data and the physiological characteristic data are cleaned and removed, and a vector sequence is constructed based on a preset vectorization rule.
In an embodiment of the present invention, the step S302 specifically includes:
and performing word segmentation processing on the network behavior data, and filtering to remove stop words and illegal characters.
Extracting contour characteristic information and pixel characteristic information of a target area of the expression data and the behavior data, comparing the contour characteristic information and the pixel characteristic information with contour characteristic information and pixel characteristic information in a preset standard expression and standard behavior database respectively, determining whether the target area has a corresponding standard expression or standard behavior, and filtering image data of which the corresponding standard expression or standard behavior cannot be found.
Fig. 4 illustrates a training step of the psychological assessment model in step S206 in the embodiment of the present invention, and for convenience of explanation, only the parts related to the embodiment of the present invention are illustrated in the figure, which is described in detail below.
As shown in fig. 4, in the embodiment of the present invention, the step of obtaining the psychological assessment model through convolutional neural network training in step S206 specifically includes:
step S402, carrying out data cleaning and vectorization preprocessing on the collected network behavior data of the user to obtain a network behavior vector sequence.
And S404, extracting contour characteristic information and pixel characteristic information from the collected expression data and behavior data of the user respectively.
Step S406, extracting physiological characteristic information in the physiological characteristic data.
Step S408, inputting the network behavior vector sequence and the physiological characteristic data vector sequence into a first convolutional neural network for training, and inputting the extracted shape characteristic information, pixel characteristic information and physiological characteristic information into a second convolutional neural network for training.
And step S410, fusing the network behaviors, the shape characteristic information, the pixel characteristic information and the physiological characteristic information processed by the first convolutional neural network and the second convolutional neural network to obtain a psychological assessment model.
It should be noted that the steps S402, S404 and S406 may be executed simultaneously or not, and the execution order of the steps may be exchanged, which is not limited in the present invention.
With regard to the method in the above-described embodiment, the detailed implementation of each step has been described in detail in the embodiment of the relevant execution module, and will not be elaborated here.
It should be understood that, although the steps in the flowcharts of the embodiments of the present invention are shown in sequence as indicated by the arrows, the steps are not necessarily performed in sequence as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a portion of the steps in various embodiments may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performance of the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a non-volatile computer-readable storage medium, and can include the processes of the embodiments of the methods described above when the program is executed. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the embodiments described above may be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the embodiments described above are not described, but should be considered as being within the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A psychological assessment system is characterized by comprising a data acquisition unit, a data preprocessing unit and a psychological assessment result calculation unit;
the data acquisition unit is used for obtaining network behavior data of a person to be evaluated in a crawling mode from a network and acquiring expression data, behavior data and physiological characteristic data which are induced when the person to be evaluated watches a virtual reality scene corresponding to the selected psychological scale;
the data preprocessing unit is used for performing data cleaning and vectorization preprocessing on the network behavior data, the expression data, the behavior data and the physiological characteristic data and constructing a vector sequence;
and the psychological assessment result calculating unit is used for inputting the vector sequence into a preset psychological assessment model obtained through convolutional neural network training for calculation to obtain and output a psychological assessment scoring result.
2. A psychological assessment system according to claim 1, wherein said network behavior data is time series information and web contents generated by said person to be assessed when using network mediation/service tool; the webpage content comprises various instant messaging information used by the to-be-evaluated person, browsed webpage types, webpage access content, webpage download content, and time interval and time length of surfing the internet every day.
3. A psychological assessment system according to claim 1, wherein said virtual reality scenario is a virtual reality scenario with specific emotion inducing effects corresponding to the selected psychological scale generated by virtual reality technology, which is used to induce the examinee to generate the expected emotion, so as to collect the expression data, behavior data and physiological characteristic data generated by the examinee when dealing with the virtual reality scenario.
4. A psychological assessment system according to claim 1, wherein said data pre-processing unit is specifically configured to:
cleaning and removing abnormal data and repeated data in the network behavior data, the expression data, the behavior data and the physiological characteristic data, and constructing a vector sequence based on a preset vectorization rule;
the psychological evaluation result calculating unit is specifically configured to:
and inputting the vector sequence into a preset psychological assessment model obtained through convolutional neural network training for calculation to obtain and output a psychological assessment scoring result.
5. A psychological assessment system according to claim 4, wherein said network behavioural data and physiological characteristic data are text data and said expression data and behavioural data are image data;
the step of cleaning and removing abnormal data and repeated data in the network behavior data, the expression data, the behavior data and the physiological characteristic data specifically comprises the following steps:
performing word segmentation processing on the network behavior data, and filtering to remove stop words and illegal characters;
extracting contour characteristic information and pixel characteristic information of a target area of the expression data and the behavior data, comparing the contour characteristic information and the pixel characteristic information with contour characteristic information and pixel characteristic information in a preset standard expression and standard behavior database respectively, determining whether the target area has a corresponding standard expression or standard behavior, and filtering image data of which the corresponding standard expression or standard behavior cannot be found.
6. A psychological assessment system according to claim 1, wherein said step of deriving a psychological assessment model by convolutional neural network training comprises:
respectively carrying out data cleaning and vectorization preprocessing on the acquired network behavior data of the user to obtain a network behavior vector sequence;
extracting contour characteristic information and pixel characteristic information from the collected expression data and behavior data of the user respectively;
extracting physiological characteristic information in the physiological characteristic data;
inputting the network behavior vector sequence and the physiological characteristic data vector sequence into a first convolutional neural network for training, and inputting the extracted shape characteristic information, pixel characteristic information and physiological characteristic information into a second convolutional neural network for training;
and fusing the network behaviors, the shape characteristic information, the pixel characteristic information and the physiological characteristic information which are processed by the first convolutional neural network and the second convolutional neural network to obtain a psychological assessment model.
7. The psychological assessment system of claim 1, wherein said expression data comprises facial expressions of excitement, likes, surprise, distress, fear, stigmatosis, disgust, and anger;
the behavioral data includes eye movements, head movements, and limb movements.
8. A psychological assessment system according to claim 1, wherein said physiological characteristic data comprises brain wave, pulse, electrocardiogram, respiration, myoelectric data.
9. A psychological assessment method, comprising the steps of:
the method comprises the steps that network behavior data of a person to be evaluated are obtained through crawling from a network, and expression data, behavior data and physiological feature data which are induced when the person to be evaluated watches a virtual reality scene corresponding to a selected psychological scale are obtained;
performing data cleaning and vectorization preprocessing on the network behavior data, the expression data, the behavior data and the physiological characteristic data, and constructing a vector sequence;
and inputting the vector sequence into a preset psychological assessment model obtained through convolutional neural network training for calculation to obtain and output a psychological assessment scoring result.
10. A psychological assessment method according to claim 9, wherein said step of performing data cleaning and vectorization preprocessing on said network behavior data, expression data, behavior data and physiological characteristic data to construct a vector sequence comprises:
cleaning and removing abnormal data and repeated data in the network behavior data, the expression data, the behavior data and the physiological characteristic data, and constructing a vector sequence based on a preset vectorization rule;
the method comprises the following steps of inputting the vector sequence into a preset psychological assessment model obtained through convolutional neural network training for calculation, obtaining a psychological assessment scoring result and outputting the psychological assessment scoring result, wherein the steps comprise:
and inputting the vector sequence into a preset psychological assessment model obtained through convolutional neural network training for calculation to obtain and output a psychological assessment scoring result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011211739.9A CN112182339A (en) | 2020-11-03 | 2020-11-03 | Psychological assessment method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011211739.9A CN112182339A (en) | 2020-11-03 | 2020-11-03 | Psychological assessment method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112182339A true CN112182339A (en) | 2021-01-05 |
Family
ID=73916482
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011211739.9A Pending CN112182339A (en) | 2020-11-03 | 2020-11-03 | Psychological assessment method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112182339A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112716494A (en) * | 2021-01-18 | 2021-04-30 | 上海对外经贸大学 | Mental health condition analysis algorithm based on micro-expression and brain wave analysis algorithm |
| CN113080968A (en) * | 2021-03-29 | 2021-07-09 | 中国人民解放军联勤保障部队第九六〇医院 | Comprehensive psychological state evaluation system based on heart rate variability |
| CN113707294A (en) * | 2021-08-05 | 2021-11-26 | 沃民高新科技（北京）股份有限公司 | Psychological evaluation method based on dynamic video data |
| CN113793687A (en) * | 2021-09-27 | 2021-12-14 | 盐城师范学院 | Mental health dynamic management system and method |
| CN113974631A (en) * | 2021-12-03 | 2022-01-28 | 中国科学院心理研究所 | Autism computer-aided diagnosis system based on physiological signal recognition and analysis |
| 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 |
| CN116453656A (en) * | 2023-04-11 | 2023-07-18 | 中国人民解放军总医院第六医学中心 | Psychological health assessment early warning system and psychological health assessment early warning method |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103905486A (en) * | 2012-12-26 | 2014-07-02 | 中国科学院心理研究所 | Mental health state evaluation method |
| CN106407672A (en) * | 2016-09-08 | 2017-02-15 | 山东腾泰医疗科技有限公司 | Mental health evaluation system based on Internet |
| 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 |
| CN110279425A (en) * | 2019-05-09 | 2019-09-27 | 中国科学院自动化研究所 | Psychological assessment method and system based on intellectual analysis |
-
2020
- 2020-11-03 CN CN202011211739.9A patent/CN112182339A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103905486A (en) * | 2012-12-26 | 2014-07-02 | 中国科学院心理研究所 | Mental health state evaluation method |
| CN106407672A (en) * | 2016-09-08 | 2017-02-15 | 山东腾泰医疗科技有限公司 | Mental health evaluation system based on Internet |
| 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 |
| CN110279425A (en) * | 2019-05-09 | 2019-09-27 | 中国科学院自动化研究所 | Psychological assessment method and system based on intellectual analysis |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112716494A (en) * | 2021-01-18 | 2021-04-30 | 上海对外经贸大学 | Mental health condition analysis algorithm based on micro-expression and brain wave analysis algorithm |
| CN113080968A (en) * | 2021-03-29 | 2021-07-09 | 中国人民解放军联勤保障部队第九六〇医院 | Comprehensive psychological state evaluation system based on heart rate variability |
| CN113707294A (en) * | 2021-08-05 | 2021-11-26 | 沃民高新科技（北京）股份有限公司 | Psychological evaluation method based on dynamic video data |
| CN113707294B (en) * | 2021-08-05 | 2023-12-05 | 沃民高新科技（北京）股份有限公司 | Psychological evaluation method based on dynamic video data |
| CN113793687A (en) * | 2021-09-27 | 2021-12-14 | 盐城师范学院 | Mental health dynamic management system and method |
| CN113974631A (en) * | 2021-12-03 | 2022-01-28 | 中国科学院心理研究所 | Autism computer-aided diagnosis system based on physiological signal recognition and analysis |
| 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 |
| CN116453656A (en) * | 2023-04-11 | 2023-07-18 | 中国人民解放军总医院第六医学中心 | Psychological health assessment early warning system and psychological health assessment early warning method |
| CN116453656B (en) * | 2023-04-11 | 2023-10-03 | 中国人民解放军总医院第六医学中心 | Psychological health assessment early warning system and psychological health assessment early warning method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112182339A (en) | Psychological assessment method and system | |
| Henschel et al. | Social cognition in the age of human–robot interaction | |
| Schütze et al. | Support value of sketching in the design process | |
| Schütte* et al. | Concepts, methods and tools in Kansei engineering | |
| Kopinak | The use of triangulation in a study of refugee well-being | |
| Lauri et al. | Decision‐making models in different fields of nursing | |
| CN108009954B (en) | Teaching plan making method, device and system and electronic equipment | |
| Langevin et al. | The PARK framework for automated analysis of Parkinson's disease characteristics | |
| Khalili et al. | Emotion detection using brain and peripheral signals | |
| CN109903127A (en) | A kind of group recommending method, device, storage medium and server | |
| JP2005124909A (en) | Method for presenting emotional information, emotional information display device, and method for retrieving information content | |
| Papandonatos et al. | Online community use predicts abstinence in combined Internet/phone intervention for smoking cessation. | |
| Andry et al. | Interpreting the effect of embellishment on chart visualizations | |
| Boswell et al. | A review and preview of developments in the measurement of sociability | |
| JP2017120595A (en) | Method for evaluating state of application of cosmetics | |
| Cai et al. | Correlation analyses between personality traits and personal behaviors under specific emotion states using physiological data from wearable devices | |
| Samp et al. | Presenting and monitoring a gender‐defined self on the internet | |
| CN115458099A (en) | Person psychological image obtaining method and system based on questionnaire evaluation and electronic equipment | |
| KR20020082828A (en) | Real-time integrated sensibility assessments method and system thereof | |
| JP5032097B2 (en) | Comfort evaluation system | |
| Deenadayalan et al. | EEG based learner’s learning style and preference prediction for E-learning | |
| Chou et al. | A framework for measuring happiness in online social networks | |
| JP6901139B2 (en) | Lifelog image generator, lifelog image generation method, and program | |
| Elleman et al. | Laying personality BARE: Behavioral frequencies strengthen personality-criterion relationships | |
| JP2022021399A (en) | Evaluation system, evaluation method and program |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 518000 Room 101, 201, 301, 401, 501, building B, junsida Science Park, clock base, mashantou community, Matian street, Guangming District, Shenzhen City, Guangdong Province Applicant after: SHENZHEN ELITE MEDICAL TECHNOLOGY Co.,Ltd. Address before: 6 / F, building D, Huawan Industrial Park, Bao'an Avenue, Bao'an District, Shenzhen City, Guangdong Province Applicant before: SHENZHEN ELITE MEDICAL TECHNOLOGY Co.,Ltd. |