CN110060762A - A kind of mental development level appraisal procedure and system based on multiple-factor scale data - Google Patents
A kind of mental development level appraisal procedure and system based on multiple-factor scale data Download PDFInfo
- Publication number
- CN110060762A CN110060762A CN201910321101.1A CN201910321101A CN110060762A CN 110060762 A CN110060762 A CN 110060762A CN 201910321101 A CN201910321101 A CN 201910321101A CN 110060762 A CN110060762 A CN 110060762A
- Authority
- CN
- China
- Prior art keywords
- scale
- factor
- topic
- user
- mental development
- 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
- 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
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/20—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for electronic clinical trials or questionnaires
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
- G16H20/70—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to mental therapies, e.g. psychological therapy or autogenous training
Abstract
The invention discloses a kind of mental development level appraisal procedure and system based on multiple-factor scale data.The method and system establish assessment models according to all user's initial data stored in database module, can be realized large-scale mental development level assessment；Assessment models carry out data cleansing to user's initial data first before establishing, and filter out scale topic answer that user conscientiously answers as sample point, therefore the assessment models evaluating result accuracy based on the foundation of this sample point is higher；And the test information that the present invention is presented to user includes single-factor topic and multiple-factor topic, the hope property of society caused by single-factor scale can be effectively prevented to answer this phenomenon, the authenticity for improving evaluating result solves the problems, such as that scale evaluating result accuracy that existing scale assessment method obtains and authenticity are low.
Description
Technical field
The present invention relates to mental development level assessment technology field, more particularly to a kind of based on multiple-factor scale data
Mental development level appraisal procedure and system.
Background technique
Mental development refers to the psychology variation for the series of active that individual is occurred in entire life course.Mental development
It is a uninterrupted process, each mental process and characteristics of personality gradually, constantly develop.Mental development
Has directionality, for the people of various years, different geographical, the direction of mental development is also not quite similar.Mental development
Level can be used for measuring the different directions of mental development.Thus it is possible to which no accurately evaluate an individual psychology development level, it will
Play the role of on its occupational planning and life style vital.In recent years, scale assessing method is because it is in tool volume
Structural and objectivity possessed by system, testing operation, result explanation etc. obtains relatively wider use.However,
Its own still has some shortcomings, has much room for improvement.
Norm description point-score is the division mode that scale generallys use, for this kind of division mode, norm data it is accurate
Whether will directly influence scale assessment accuracy.But in traditional psychological field, due to the limit of some social conditions
System, experiment is difficult that the individual of quantity abundance is convened to fill in scale every time, usually, sample used in norm description point-score
Amount is generally at 1500~2000 person-times, which is not sufficient to represent the distribution situation of all assessment crowds, in data scale
On will generate limitation.Secondly, the less service life for leading to norm of revision number of norm is very long, most of scale institute is right
As long as answering the service life of norm to reach many decades, the norm service life so grown will will be greatly reduced the timeliness of scale
Property, this is the limitation of scale in the time domain.Simultaneously as most of scale is formulated by foreign countries' exploitation, norm is established
When the data that are collected into also both from foreign countries.China for the part scale use or directly apply it is external normal
Mould or external norm is slightly changed, even if different provinces at home are still used with a norm data, so norm exists
Geographically also bring along certain limitation.It can be seen that traditional norm description point-score is in data scale, time, geographically
There is limitation, the accuracy that numerous limitations of norm can directly result in scale assessment substantially reduces.
There is also another problems in traditional Research advancement on measuring scale, and the scale factor is excessively single and topic is with very strong
Specific aim.Such topic can make subject easily guess assessment intention, for a part of subject,
Will the true psychological condition of active concealment oneself, namely society hope property answer.Once the phenomenon occurs, scale evaluating result
Authenticity will decrease.
Summary of the invention
The object of the present invention is to provide a kind of mental development level appraisal procedure and system based on multiple-factor scale data,
To solve the problems, such as that scale evaluating result accuracy that existing scale assessment method obtains and authenticity are low.
To achieve the above object, the present invention provides following schemes:
A kind of mental development level appraisal procedure based on multiple-factor scale data, which comprises
Obtain all user's initial data stored in database module；It include multiple users in user's initial data
The scale topic answer answered and corresponding Reaction time；
Data cleansing is carried out to user's initial data, filters out scale topic answer that user conscientiously answers as sample
This point；
Single-factor assessment models are established according to the sample point and determine the corresponding mental development of each described sample point
It is horizontal；
Multiple-factor topic group is determined according to the mental development level；
Multiple-factor assessment models are established according to the corresponding topic answer of the multiple-factor topic group；
Obtain the current question answer for the current scale that active user answers；
It is determined according to the type of the current scale and uses the single-factor assessment models or the multiple-factor assessment models
As evaluation model；
According to the mental development level of active user described in the current question answer and the evaluation model evaluation.
Optionally, described that data cleansing is carried out to user's initial data, filter out the scale topic that user conscientiously answers
Mesh answer is specifically included as sample point:
Judge whether contain missing values in i-th of user answers in user's initial data scale topic answer, obtains
Obtain the first judging result；
If containing missing values in the scale topic answer that first judging result is answered for i-th of user, described in rejecting
The scale topic answer that i-th of user answers；
If there is no missing values in the scale topic answer that first judging result is answered for i-th of user, described in reservation
The scale topic answer that i-th of user answers, the data set after forming prescreening；
The corresponding Reaction time of scale topic answer that i-th of user answers in data set after judging the prescreening is
It is no to preset within the scope of Reaction time, obtain the second judging result；
If second judging result is that the corresponding Reaction time of scale topic answer that i-th of user answers is not being preset
Within the scope of Reaction time, the scale topic answer that i-th of user answers is rejected；
If second judging result is that the corresponding Reaction time of scale topic answer that i-th of user answers is answered default
It inscribes in time range, the scale topic answer that the scale topic answer that i-th of user answers conscientiously is answered as user；
The scale topic answer that i-th of user is conscientiously answered forms a column vector as i-th of sample point.
Optionally, described that single-factor assessment models are established according to the sample point and determine that each described sample point is corresponding
Mental development level, specifically include:
It obtains the corresponding sample point of single scale topic answer that user in the sample point conscientiously answers and is used as single scale sample
This point；
Single scale initial cluster center of multiple single scale sample points is determined using minimax distance algorithm；
According to single scale initial cluster center, using the multiple single scales of K-means clustering algorithm iterative calculation
Single scale cluster centre of sample point, and multiple single scale sample points are clustered as multiple single scale clusters；
Using single scale cluster centre as the single-factor assessment models；Each single corresponding heart of scale cluster
Manage development level；The corresponding mental development level of list scale cluster where the list scale sample point is single scale sample point
Corresponding mental development level.
Optionally, described that multiple-factor topic group is determined according to the mental development level, it specifically includes:
Obtain all topics in the multiple-factor scale that user answers；
Using the topic as independent variable, using the mental development level of the user as dependent variable, by orderly multinomial
Logic Regression Models obtain the coefficient between each described independent variable and the dependent variable；
Each described coefficient is made into T inspection by significance of preset value, is obtained significant related to the dependent variable
The independent variable；It is significant relevant with the mental development level to the significant relevant independent variable of the dependent variable
Multiple-factor topic group.
Optionally, described that multiple-factor assessment models are established according to the corresponding topic answer of the multiple-factor topic group, specifically
Include:
The topic answer for the multiple-factor topic group that each user is answered forms a column vector as multiple-factor scale sample
This point；
The multiple-factor scale initial clustering of multiple multiple-factor scale sample points is determined using minimax distance algorithm
Center；
According to the multiple-factor scale initial cluster center, iterated to calculate using K-means clustering algorithm multiple described more
The multiple-factor scale cluster centre of factor scale sample point, and by multiple multiple-factor scale sample points cluster for it is multiple mostly because
Sub- scale cluster；
Using the multiple-factor scale cluster centre as the multiple-factor assessment models；Each multiple-factor scale cluster pair
Answer a mental development level.
Optionally, the heart of the active user according to the current question answer and the evaluation model evaluation
Development level is managed, is specifically included:
The current question answer is formed into current question column vector；
Calculate the distance between each cluster centre of the current question column vector Yu the evaluation model；
Determine the heart of the nearest corresponding mental development level of the cluster centre of the distance as the active user
Manage development level.
A kind of mental development level assessment system based on multiple-factor scale data, the system comprises: human-computer interaction mould
Block, database module, assessment models building module and mental development level evaluation module；The assessment models construct module
Data cleansing submodule, single-factor topic level calibration submodule, multiple-factor topic choose submodule and multiple-factor topic is horizontal
Demarcate submodule；
The data cleansing submodule, for obtaining all user's initial data stored in the database module, institute
State the scale topic answer answered in user's initial data including multiple users and corresponding Reaction time；And to described in acquisition
User's initial data carries out data cleansing, filters out scale topic answer that user conscientiously answers as sample point；
The single-factor topic level calibration submodule, for establishing single-factor assessment models and true according to the sample point
The corresponding mental development level of fixed each described sample point；
The multiple-factor topic chooses submodule, for determining multiple-factor topic group according to the mental development level；
The multiple-factor topic level calibration submodule, for being built according to the corresponding topic answer of the multiple-factor topic group
Vertical multiple-factor assessment models；
The mental development level evaluation module, the current question for obtaining the current scale that active user answers are answered
Case, and determined according to the type of the current scale and use the single-factor assessment models or the multiple-factor assessment models conduct
Evaluation model；It is subsequent, according to the heart of acquired current question answer and the evaluation model evaluation active user
Manage development level；
The human-computer interaction module, the survey for showing assessment topic for the active user, receiving the active user
It comments information and shows the mental development level of the active user.
The database module updates model request to the assessment models for storing the assessment information of user and sending
Construct module.
Optionally, the single-factor topic level calibration submodule specifically includes:
Single scale sample point acquiring unit, the single scale topic answer conscientiously answered for obtaining user in the sample point
Corresponding sample point is as single scale sample point；
Single scale initial cluster center determination unit, for determining multiple single scales using minimax distance algorithm
Single scale initial cluster center of sample point；
Single scale data clusters unit is used for according to single scale initial cluster center, using K-means clustering algorithm
Single scale cluster centre of multiple single scale sample points is iterated to calculate, and is more by multiple single scale sample point clusters
A list scale cluster；
Single-factor assessment models establish unit, for assessing mould using single scale cluster centre as the single-factor
Type；Each single corresponding mental development level of scale cluster；The corresponding heart of list scale cluster where the list scale sample point
Reason development level is the corresponding mental development level of single scale sample point.
Optionally, the multiple-factor topic is chosen submodule and is specifically included:
Regression coefficient determination unit, for obtaining all topics in the multiple-factor scale that user answers, the institute that will acquire
Topic is stated as independent variable and passes through orderly multinomial Logic Regression Models using the mental development level of the user as dependent variable
Obtain the coefficient between each described independent variable and the dependent variable；
Coefficient test unit obtains and institute for each described coefficient to be made T inspection by significance of preset value
State the significant relevant independent variable of dependent variable；It is to be sent out with the psychology to the significant relevant independent variable of the dependent variable
The horizontal significant relevant multiple-factor topic group of exhibition.
Optionally, the mental development level evaluation module specifically includes:
Metrics calculation unit calculates the current topic for the current question answer to be formed current question column vector
The distance between each cluster centre of mesh column vector and the evaluation model；
Mental development level determination unit, for determining the nearest corresponding mental development of the cluster centre of the distance
The horizontal mental development level as the active user.
The specific embodiment provided according to the present invention, the invention discloses following technical effects:
The present invention provides a kind of mental development level appraisal procedure and system based on multiple-factor scale data, according to data
All user's initial data stored in library module establish assessment models, can be realized large-scale mental development level assessment；
Assessment models carry out data cleansing to user's initial data first before establishing, and filter out the scale topic answer that user conscientiously answers
As sample point, thus it is higher based on the assessment models evaluating result accuracy that this sample point is established；And the present invention is presented to
The test information of user includes single-factor topic and multiple-factor topic, can be effectively prevented from society caused by single-factor scale
Hope property is answered this phenomenon, and the authenticity of evaluating result is improved, and solves the scale assessment that existing scale assessment method obtains
Result precision and the low problem of authenticity.
Detailed description of the invention
It in order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, below will be to institute in embodiment
Attached drawing to be used is needed to be briefly described, it should be apparent that, the accompanying drawings in the following description is only some implementations of the invention
Example, for those of ordinary skill in the art, without any creative labor, can also be according to these attached drawings
Obtain other attached drawings.
Fig. 1 is the general frame of the mental development level assessment system provided by the invention based on multiple-factor scale data
Figure；
Fig. 2 is the inner frame figure that assessment models provided by the invention construct module；
Fig. 3 is the method flow of the mental development level appraisal procedure provided by the invention based on multiple-factor scale data
Figure.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
The object of the present invention is to provide a kind of mental development level appraisal procedure and system based on multiple-factor scale data,
To solve the problems, such as that scale evaluating result accuracy that existing scale assessment method obtains and authenticity are low.
In order to make the foregoing objectives, features and advantages of the present invention clearer and more comprehensible, with reference to the accompanying drawing and specific real
Applying mode, the present invention is described in further detail.
Fig. 1 is the general frame of the mental development level assessment system provided by the invention based on multiple-factor scale data
Figure.Referring to Fig. 1, a kind of mental development level assessment system based on multiple-factor scale data provided by the invention, including it is following
Several modules: human-computer interaction module 101, database module 102, assessment models building module 103 and mental development level are commented
Estimate module 104.
(1) human-computer interaction module
The human-computer interaction module 101 is mainly used for showing assessment topic for user, receives the assessment information of user and anti-
It feeds user's evaluating result.
The human-computer interaction module 101 shows several directions to be measured (such as personality type, occupational planning type, pressure first for user
Power type etc.), after user chooses a certain direction to be measured, the human-computer interaction module 101 can be chosen from database module 102 should
All scales (such as: Eisenke Personality Questionnaire, adolescent psychology toughness scale, school's atmosphere questionnaire) test question of direction subordinate
Mesh is simultaneously successively presented to the user.
After user completes to test and assess, the human-computer interaction module 101 will record down all topics that the user is completed and make
The process data (answer time and sequence of answering) of answer and answer, and this two parts answer data is submitted to system
Database module 102 and mental development level evaluation module 104, meanwhile, human-computer interaction module 101 can automatic identification user institute
The scale quantity of completion, if being only completed a scale, the human-computer interaction module 101 can be to mental development proficiency assessment module
104 submit parameter " 1 ", if completing multiple scales, the human-computer interaction module 101 can be to mental development proficiency assessment module
104 submit parameter " 2 ", and different parameters selects different models to be assessed for mental development level evaluation module 104.
The mental development level of the user is assessed when mental development proficiency assessment module 104 completes, and assessment is tied
Fruit returns to human-computer interaction module 101, and human-computer interaction module 101 can turn mental development level assessment result in conjunction with direction to be measured
It changes descriptive sentence into and presents on a user interface.
Such as, direction to be measured is personality type, and mental development level result is returned as 1, then presenting on a user interface:
You are introverted, is fond of tranquility, and is imbued with introspection, does not like stimulation, likes Methodistic life style, and mood is more stable.
(2) database module
The database module 102 mainly includes two functions: first is that information storage function, second is that data volume monitors function
Energy.
Informational function is wherein stored, mainly by dividing table to realize in database.It include three in the database module 102
A table stores the information of three parts: the personal information of user, such as user's test No. respectively, demography variable (gender,
Grade, area etc.)；Measurement direction belonging to Research advancement on measuring scale information, the topic information of each scale and the scale (such as:
Eisenke Personality Questionnaire is under the jurisdiction of personality type measurement direction)；User answers information, user's performance table title purpose topic answer with
And process data (Reaction time, answer sequence of user etc.).
Database module 102 is also required to real time monitoring amount of new data (received data after last model modification) simultaneously
The ratio for accounting for total amount of data in database, after ratio is more than preset ratio threshold value (threshold value is set as 10%), the data
Library module 102 will construct the request that module 103 sends a update module to assessment models.
(3) assessment models construct module
Assessment models, which construct 103 major function of module, to be made after receiving the update model request of database module 102
New assessment models are constructed with all data in database module, and new assessment models are output to mental development level
Evaluation module 104.The assessment models building module 103 is the nucleus module of this system, and its normal operation needs database
The support of module 102 and human-computer interaction module 101.The internal structure of assessment models building module 103 as shown in Fig. 2,
The assessment models building module 103 contains data cleansing submodule, single-factor topic level calibration submodule, multiple-factor topic
Mesh chooses submodule and multiple-factor topic level calibration submodule, the major function of each submodule are as follows:
1) data cleansing submodule:
The major function of data cleansing submodule is original to the user from human-computer interaction module and database module
Data are screened.The standard of screening has: judging the process data whether answered containing missing values and user in initial data.
It will be by if containing initial data of the Reaction time of missing values or user not between 2s~2min in the initial data
Automatic rejection.It is data that user conscientiously answers after guaranteeing cleaning with this.
2) single-factor topic level calibration submodule:
The answer of the single scale (such as: Eisenke Personality Questionnaire in personality type measurement direction) directly related with mental development
Record will be obtained as data source in single-factor topic level calibration submodule using by each of described single scale
All topic answers of user form a column vector as a sample point, and the answer of each topic is one of the sample point
Characteristic value, unsupervised learning method of all sample points by K-means cluster are classified, and it is corresponding to obtain each user
Mental development level is simultaneously output to mental level evaluation module 104 for cluster centre as single-factor assessment models.
But due to K-means cluster initial cluster center selection be it is random, cluster result also include it is very big with
Machine.So fixing initial cluster center using minimax distance algorithm in single-factor topic level calibration submodule.
In minimax distance algorithm, initial cluster center xlThe following formula of selection shown in:
Wherein dikFor i-th of sample point to the Euclidean distance of k-th of initial cluster center.
Initial cluster center by the number of the cluster of cluster sets 4 after determining, and starts K-means and clusters iteration, repeatedly
In generation, is divided into two processes, first sorts out each sample point to nearest cluster centre:
ti=min (dij)
Wherein tiFor the classification of i-th of sample point, dijFor i-th of sample point to the Euclidean distance of j-th of cluster centre.
Next cluster centre is recalculated, new cluster centre is the central point of all sample points under the category.
When the cluster centre recalculated does not change or after reaching maximum number of iterations (100 times), cluster knot
Beam.Each cluster that K-means is clustered represents each mental development level (obtaining using the assessment of single-factor topic),
User corresponding to each sample point is in the corresponding mental development level of the cluster under one cluster.The mental development water
Flat can be intuitively found out from cluster as a result, can measure the height of mental development level with 1,2,3,4.
The input of the single-factor level calibration submodule be the single scale directly related with mental development (such as: personality type
Eisenke Personality Questionnaire in measurement direction) answer record；Output is that the mental development level of each user (uses single-factor
Topic assessment).The single-factor topic level calibration submodule not only can assess mould for 4 final cluster centres as single-factor
Type is output to mental development level evaluation module, while also the mental development level of each sample point can be output to multiple-factor
Topic is chosen in submodule.
3) multiple-factor topic chooses submodule:
It chooses in submodule, is inputted as the Research advancement on measuring scale with mental development level indirect correlation (such as: green in multiple-factor topic
Juvenile mentality toughness scale, school's atmosphere questionnaire etc.) in obtain in all topics and single-factor topic level calibration submodule
The corresponding mental development level of each user, obtained between each topic and mental development level by logistic regression
Coefficient then carries out significance test to coefficient, to select one and psychology in all topics in multiple-factor scale
The relevant multiple-factor topic group of development level.
The multiple-factor topic selection submodule application is ordered into multinomial Logic Regression Models, and independent variable is each use
All topic answers of multiple-factor scale in family answer data, dependent variable are the users in mental development level calibration submodule
The mental development level of calibration.By the Logic Regression Models it can be concluded that being between each independent variable and dependent variable
Number:
Y=g (θ0+θ1x1+θ2x2+θ3x3+...+θnxn)
Wherein y is dependent variable, xnIt is n-th of independent variable, θnIt is the coefficient of n-th of independent variable, g is nonlinear function.
Next, each coefficient θ1,θ2,...,θnMake T inspection with 0.005 for significance, obtains aobvious with dependent variable
Relevant independent variable, relate to the practical significance of independent variable and dependent variable, the independent variable selected be and mental development level
Significant relevant multiple-factor topic group, the multiple-factor topic group will be output to multiple-factor topic level calibration submodule.
4) multiple-factor topic level calibration submodule:
Algorithm used in multiple-factor topic level calibration submodule is still used with single-factor topic level calibration submodule
K-means clustering algorithm.The difference is that: the input of the multiple-factor topic level calibration submodule is the choosing of multiple-factor topic
Take the multiple-factor topic group exported in submodule.The output of multiple-factor topic level calibration submodule is in 4 final clusters
The heart, the multiple-factor assessment models as mental development level evaluation module.
By all topic answers of each user in the multiple-factor topic group that multiple-factor topic chooses submodule output
It is packaged into a column vector, the sample point (multiple-factor scale sample point) as cluster.Still minimax distance is used
Algorithm determines initial cluster center, and the number of clustering cluster is set as 4, after end of clustering, 4 final cluster centres as mostly because
Sub- assessment models are output to mental development level evaluation module.
(4) mental development level evaluation module
Mental development level evaluation module 104 is main to construct the assessment models exported in module 103 (packet by assessment models
Include single-factor assessment models and multiple-factor assessment models) user data in human-computer interaction module 101 is carried out in real time
Assessment.The input of mental development level evaluation module is the assessment data for the active user that human-computer interaction module 101 transmits, together
When, mental development level evaluation module can be selected according to the parameter " 1 " of human-computer interaction module transmitting or " 2 " using from list
The single-factor assessment models of factor topic level calibration submodule output are defeated using multiple-factor topic level calibration submodule
Multiple-factor assessment models out.
Current-user data (topic answer) can be packaged into a column vector by mental development level evaluation module, be asked respectively
The distance for taking 4 cluster centres in the column vector and evaluation model, the psychology corresponding to the nearest cluster centre
Development level is to correspond to the mental development level of active user.The mental development level of active user is as mental development level
The output of evaluation module returns to human-computer interaction module 101.Human-computer interaction module 101 is website portal, is user and system
Interactive unique channel, after mental development level assessment, the human-computer interaction module 101 can be commented from mental development level
Estimate and get assessment result in module 104, and user will be fed back to after assessment result synthesis.
A kind of mental development level assessment system based on multiple-factor scale data provided by the invention, the system are applied
, in this way will be more convenient to the acquisition of big data in the network platform, and using the mode of data-driven, it is calculated using machine learning
Method automatically sets up assessment models in real time, assesses the mental development level of user.
Compared with prior art, innovative point of the invention is: firstly, data markers used in training pattern pass through no prison
It superintends and directs machine learning algorithm to obtain, such data markers can be changed in time with the variation of user crowd, have very strong
Flexibility efficiently solves limitation brought by traditional norm method；Meanwhile the present invention can more easily collect psychological hair
Data needed for opening up proficiency assessment, help to carry out large-scale individual data items acquisition in wide range, realize extensive
Mental development level assessment；Secondly, the test information that system is presented to user is multiple-factor topic, to replace single-factor amount
Table efficiently avoids the hope property of society caused by single-factor scale and answers this phenomenon；Finally, present system is not only
Have the function of the online evaluation of mental development level, and can be assessed according to the size real-time update of data volume in database
Model guarantees the timeliness of assessment system with this.
Based on mental development level assessment system provided by the invention, the present invention also provides one kind to be based on multiple-factor scale number
According to mental development level appraisal procedure.As shown in figure 3, the mental development level appraisal procedure specifically includes:
Step 301: obtaining all user's initial data stored in database module.Include in user's initial data
The answer of scale topic and corresponding Reaction time that multiple users answer.
Step 302: data cleansing being carried out to user's initial data, the scale topic that user conscientiously answers is filtered out and answers
Case is as sample point.It specifically includes:
Judge whether contain missing values in i-th of user answers in user's initial data scale topic answer, obtains
Obtain the first judging result；
If containing missing values in the scale topic answer that first judging result is answered for i-th of user, described in rejecting
The scale topic answer that i-th of user answers；
If there is no missing values in the scale topic answer that first judging result is answered for i-th of user, described in reservation
The scale topic answer that i-th of user answers, the data set after forming prescreening；
The corresponding Reaction time of scale topic answer that i-th of user answers in data set after judging the prescreening is
It is no to preset within the scope of Reaction time, obtain the second judging result；
If second judging result is that the corresponding Reaction time of scale topic answer that i-th of user answers is not being preset
Within the scope of Reaction time, the scale topic answer that i-th of user answers is rejected；
If second judging result is that the corresponding Reaction time of scale topic answer that i-th of user answers is answered default
It inscribes in time range, the scale topic answer that the scale topic answer that i-th of user answers conscientiously is answered as user；
The scale topic answer that i-th of user is conscientiously answered forms a column vector as i-th of sample point.
Step 303: single-factor assessment models being established according to the sample point and determine that each described sample point is corresponding
Mental development level.It specifically includes:
It obtains the corresponding sample point of single scale topic answer that user in the sample point conscientiously answers and is used as single scale sample
This point；
Single scale initial cluster center of multiple single scale sample points is determined using minimax distance algorithm；
According to single scale initial cluster center, using the multiple single scales of K-means clustering algorithm iterative calculation
Single scale cluster centre of sample point, and multiple single scale sample points are clustered as multiple single scale clusters；
Using single scale cluster centre as the single-factor assessment models；Each single corresponding heart of scale cluster
Manage development level；The corresponding mental development level of list scale cluster where the list scale sample point is single scale sample point
Corresponding mental development level.
Step 304: multiple-factor topic group is determined according to the mental development level.It specifically includes:
Obtain all topics in the multiple-factor scale that user answers；
Using the topic as independent variable, using the mental development level of the user as dependent variable, by orderly multinomial
Logic Regression Models obtain the coefficient between each described independent variable and the dependent variable；
Each described coefficient is made into T inspection by significance of preset value, is obtained significant related to the dependent variable
The independent variable；It is significant relevant with the mental development level to the significant relevant independent variable of the dependent variable
Multiple-factor topic group.
Step 305: multiple-factor assessment models are established according to the corresponding topic answer of the multiple-factor topic group.Specific packet
It includes:
The topic answer for the multiple-factor topic group that each user is answered forms a column vector as multiple-factor scale sample
This point；
The multiple-factor scale initial clustering of multiple multiple-factor scale sample points is determined using minimax distance algorithm
Center；
According to the multiple-factor scale initial cluster center, iterated to calculate using K-means clustering algorithm multiple described more
The multiple-factor scale cluster centre of factor scale sample point, and by multiple multiple-factor scale sample points cluster for it is multiple mostly because
Sub- scale cluster；
Using the multiple-factor scale cluster centre as the multiple-factor assessment models；Each multiple-factor scale cluster pair
Answer a mental development level.
Step 306: obtaining the current question answer for the current scale that active user answers.
Step 307: being determined according to the type of the current scale and use the single-factor assessment models or the multiple-factor
Assessment models are as evaluation model.
Step 308: according to the psychology of active user described in the current question answer and the evaluation model evaluation
Development level.It specifically includes:
The current question answer is formed into current question column vector；
Calculate the distance between each cluster centre of the current question column vector Yu the evaluation model；
Determine the heart of the nearest corresponding mental development level of the cluster centre of the distance as the active user
Manage development level.
Mental development level appraisal procedure provided by the invention based on multiple-factor scale data, according in database module
All user's initial data of storage establish assessment models, can be realized large-scale mental development level assessment；Assessment models
Data cleansing is carried out to user's initial data first before establishing, filters out scale topic answer that user conscientiously answers as sample
Point, thus it is higher based on the assessment models evaluating result accuracy that this sample point is established；And the present invention is presented to the survey of user
Examination information includes single-factor topic and multiple-factor topic, can be effectively prevented from the hope property of society caused by single-factor scale and make
This phenomenon is answered, the authenticity of evaluating result is improved, it is accurate to solve the scale evaluating result that existing scale assessment method obtains
Spend the problem low with authenticity.
Each embodiment in this specification is described in a progressive manner, the highlights of each of the examples are with other
The difference of embodiment, the same or similar parts in each embodiment may refer to each other.For method disclosed in embodiment
For, since it is corresponding with system disclosed in embodiment, so being described relatively simple, related place is defended oneself referring to Account Dept
It is bright.
Used herein a specific example illustrates the principle and implementation of the invention, and above embodiments are said
It is bright to be merely used to help understand method and its core concept of the invention；At the same time, for those skilled in the art, foundation
Thought of the invention, there will be changes in the specific implementation manner and application range.In conclusion the content of the present specification is not
It is interpreted as limitation of the present invention.
Claims (10)
1. a kind of mental development level appraisal procedure based on multiple-factor scale data, which is characterized in that the described method includes:
Obtain all user's initial data stored in database module；It include that multiple users answer in user's initial data
The answer of scale topic and corresponding Reaction time；
Data cleansing is carried out to user's initial data, filters out scale topic answer that user conscientiously answers as sample
Point；
Single-factor assessment models are established according to the sample point and determine the corresponding mental development level of each described sample point；
Multiple-factor topic group is determined according to the mental development level；
Multiple-factor assessment models are established according to the corresponding topic answer of the multiple-factor topic group；
Obtain the current question answer for the current scale that active user answers；
It is determined according to the type of the current scale and uses the single-factor assessment models or the multiple-factor assessment models conduct
Evaluation model；
According to the mental development level of active user described in the current question answer and the evaluation model evaluation.
2. mental development level appraisal procedure according to claim 1, which is characterized in that described to user's original number
According to data cleansing is carried out, scale topic answer that user conscientiously answers is filtered out as sample point, is specifically included:
Judge whether contain missing values in i-th of user answers in user's initial data scale topic answer, obtains the
One judging result；
If containing missing values in the scale topic answer that first judging result is answered for i-th of user, reject described i-th
The scale topic answer that user answers；
If there is no missing values in the scale topic answer that first judging result is answered for i-th of user, retain described i-th
The scale topic answer that user answers, the data set after forming prescreening；
The corresponding Reaction time of scale topic answer that i-th of user answers in data set after judging the prescreening whether
Within the scope of default Reaction time, the second judging result is obtained；
If second judging result is the corresponding Reaction time of scale topic answer answered of i-th of user not in default answer
In time range, the scale topic answer that i-th of user answers is rejected；
If second judging result is the corresponding Reaction time of scale topic answer answered of i-th of user in default answer
Between in range, scale topic answer that the scale topic answer that i-th of user answers conscientiously is answered as user；
The scale topic answer that i-th of user is conscientiously answered forms a column vector as i-th of sample point.
3. mental development level appraisal procedure according to claim 1, which is characterized in that described to be built according to the sample point
Vertical single-factor assessment models simultaneously determine the corresponding mental development level of each described sample point, specifically include:
It obtains the corresponding sample point of single scale topic answer that user in the sample point conscientiously answers and is used as single scale sample point；
Single scale initial cluster center of multiple single scale sample points is determined using minimax distance algorithm；
According to single scale initial cluster center, using the multiple single scale samples of K-means clustering algorithm iterative calculation
Single scale cluster centre of point, and multiple single scale sample points are clustered as multiple single scale clusters；
Using single scale cluster centre as the single-factor assessment models；Each single corresponding psychology hair of scale cluster
Exhibition is horizontal；The corresponding mental development level of list scale cluster where the list scale sample point is that single scale sample point is corresponding
Mental development level.
4. mental development level appraisal procedure according to claim 3, which is characterized in that described according to the mental development
Level determines multiple-factor topic group, specifically includes:
Obtain all topics in the multiple-factor scale that user answers；
Pass through orderly multinomial logic using the mental development level of the user as dependent variable using the topic as independent variable
Regression model obtains the coefficient between each described independent variable and the dependent variable；
Each described coefficient is made into T inspection by significance of preset value, is obtained and the significant relevant institute of the dependent variable
State independent variable；To the significant relevant independent variable of the dependent variable be with the mental development level it is significant it is relevant mostly because
Crosshead mesh group.
5. mental development level appraisal procedure according to claim 4, which is characterized in that described to be inscribed according to the multiple-factor
Multiple-factor assessment models are established in the corresponding topic answer of mesh group, are specifically included:
The topic answer for the multiple-factor topic group that each user is answered forms a column vector as multiple-factor scale sample point；
The multiple-factor scale initial cluster center of multiple multiple-factor scale sample points is determined using minimax distance algorithm；
According to the multiple-factor scale initial cluster center, multiple multiple-factors are iterated to calculate using K-means clustering algorithm
The multiple-factor scale cluster centre of scale sample point, and multiple multiple-factor scale sample points are clustered as multiple multiple-factor amounts
Table cluster；
Using the multiple-factor scale cluster centre as the multiple-factor assessment models；Each multiple-factor scale cluster corresponding one
A mental development level.
6. mental development level appraisal procedure according to claim 1, which is characterized in that described according to the current question
The mental development level of active user described in answer and the evaluation model evaluation, specifically includes:
The current question answer is formed into current question column vector；
Calculate the distance between each cluster centre of the current question column vector Yu the evaluation model；
Determine psychology hair of the nearest corresponding mental development level of the cluster centre of the distance as the active user
Exhibition is horizontal.
7. a kind of mental development level assessment system based on multiple-factor scale data, which is characterized in that the system comprises: people
Machine interactive module, database module, assessment models building module and mental development level evaluation module；The assessment models building
Module includes data cleansing submodule, single-factor topic level calibration submodule, multiple-factor topic selection submodule and multiple-factor
Topic level calibration submodule；
The data cleansing submodule, for obtaining all user's initial data stored in the database module, the use
It include the answer of scale topic and corresponding Reaction time that multiple users answer in the initial data of family；And to the user of acquisition
Initial data carries out data cleansing, filters out scale topic answer that user conscientiously answers as sample point；
The single-factor topic level calibration submodule, for establishing single-factor assessment models according to the sample point and determining every
The corresponding mental development level of one sample point；
The multiple-factor topic chooses submodule, for determining multiple-factor topic group according to the mental development level；
The multiple-factor topic level calibration submodule is more for being established according to the corresponding topic answer of the multiple-factor topic group
Factor assessment models；
The mental development level evaluation module, for obtaining the current question answer for the current scale that active user answers, and
It is determined using the single-factor assessment models or the multiple-factor assessment models according to the type of the current scale as current
Assessment models；It is subsequent, it is sent out according to the psychology of acquired current question answer and the evaluation model evaluation active user
Exhibition is horizontal；
The human-computer interaction module, the assessment letter for showing assessment topic for the active user, receiving the active user
It ceases and shows the mental development level of the active user；
The database module is constructed for storing the assessment information of user and sending update model request to the assessment models
Module.
8. mental development level assessment system according to claim 7, which is characterized in that the single-factor topic level mark
Stator modules specifically include:
Single scale sample point acquiring unit, it is corresponding for obtaining single scale topic answer that user in the sample point conscientiously answers
Sample point as single scale sample point；
Single scale initial cluster center determination unit, for determining multiple single scale samples using minimax distance algorithm
Single scale initial cluster center of point；
Single scale data clusters unit is used for according to single scale initial cluster center, using K-means clustering algorithm iteration
Single scale cluster centre of multiple single scale sample points is calculated, and multiple single scale sample points are clustered as multiple lists
Scale cluster；
Single-factor assessment models establish unit, for using single scale cluster centre as the single-factor assessment models；Often
A single corresponding mental development level of scale cluster；The corresponding mental development of list scale cluster where the list scale sample point
Level is the corresponding mental development level of single scale sample point.
9. mental development level assessment system according to claim 8, which is characterized in that the multiple-factor topic chooses son
Module specifically includes:
Regression coefficient determination unit, for obtaining all topics in the multiple-factor scale that user answers, the topic that will acquire
Mesh is obtained using the mental development level of the user as dependent variable by orderly multinomial Logic Regression Models as independent variable
Coefficient between each described independent variable and the dependent variable；
Coefficient test unit, for each described coefficient to be made T inspection by significance of preset value, obtain with it is described because
The significant relevant independent variable of variable；It is and the mental development water to the significant relevant independent variable of the dependent variable
Head up display relevant multiple-factor topic group.
10. mental development level assessment system according to claim 7, which is characterized in that the mental development level is commented
Estimate module to specifically include:
Metrics calculation unit calculates the current question column for the current question answer to be formed current question column vector
The distance between each cluster centre of vector and the evaluation model；
Mental development level determination unit, for determining the nearest corresponding mental development level of the cluster centre of the distance
Mental development level as the active user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910321101.1A CN110060762B (en) | 2019-04-22 | 2019-04-22 | Psychological development level assessment method and system based on multi-factor scale data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910321101.1A CN110060762B (en) | 2019-04-22 | 2019-04-22 | Psychological development level assessment method and system based on multi-factor scale data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110060762A true CN110060762A (en) | 2019-07-26 |
| CN110060762B CN110060762B (en) | 2021-06-25 |
Family
ID=67319932
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910321101.1A Active CN110060762B (en) | 2019-04-22 | 2019-04-22 | Psychological development level assessment method and system based on multi-factor scale data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110060762B (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111062626A (en) * | 2019-12-19 | 2020-04-24 | 北京儒博科技有限公司 | Capability level evaluation method, device, equipment and storage medium |
| CN111210896A (en) * | 2019-12-30 | 2020-05-29 | 西安慧云医疗科技股份有限公司 | Scale generation system based on cloud psychological diagnosis |
| CN111292833A (en) * | 2020-01-22 | 2020-06-16 | 浙江连信科技有限公司 | Physiological and psychological state prediction method and device based on intelligent robot |
| CN111292832A (en) * | 2020-01-22 | 2020-06-16 | 浙江连信科技有限公司 | Intelligent terminal based psychological crisis personnel active prediction method and device |
| CN111831681A (en) * | 2020-01-22 | 2020-10-27 | 浙江连信科技有限公司 | Intelligent terminal-based personnel discrimination method and device |
| CN111899823A (en) * | 2020-06-11 | 2020-11-06 | 上海梅斯医药科技有限公司 | Method and system for processing gauge information, terminal equipment and storage medium |
| CN113299358A (en) * | 2021-05-20 | 2021-08-24 | 北京大学深圳医院 | Negative emotion screening method, device and equipment based on assessment scale |
| CN113536072A (en) * | 2020-11-16 | 2021-10-22 | 厦门市和家健脑智能科技有限公司 | Method and device for model voting combination of cognitive screening data processing modeling |
| CN113593674A (en) * | 2020-04-30 | 2021-11-02 | 北京心数矩阵科技有限公司 | Character impact factor analysis method based on structured neural network |
| CN113662547A (en) * | 2021-09-28 | 2021-11-19 | 南京融媒数智信息科技有限公司 | Psychological online dynamic monitoring auxiliary psychological assessment method and equipment |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130030266A1 (en) * | 2011-07-29 | 2013-01-31 | Jiann-Shing Shieh | Psychological stress index measuring system and analysis method |
| CN103905486A (en) * | 2012-12-26 | 2014-07-02 | 中国科学院心理研究所 | Mental health state evaluation method |
| CN104715129A (en) * | 2013-12-13 | 2015-06-17 | 中国科学院心理研究所 | Mental health state assessment system and method based on mobile equipment using behavior |
| CN106407673A (en) * | 2016-09-08 | 2017-02-15 | 山东腾泰医疗科技有限公司 | Mental health evaluation method based on Internet cloud database |
| CN107330237A (en) * | 2017-05-12 | 2017-11-07 | 广州市润心教育咨询有限公司 | A kind of psychological condition appraisal procedure and system |
| CN107799165A (en) * | 2017-09-18 | 2018-03-13 | 华南理工大学 | A kind of psychological assessment method based on virtual reality technology |
| CN108231139A (en) * | 2018-01-17 | 2018-06-29 | 姜涵予 | Comprehensive social adaptation's appraisal procedure and device |
-
2019
- 2019-04-22 CN CN201910321101.1A patent/CN110060762B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130030266A1 (en) * | 2011-07-29 | 2013-01-31 | Jiann-Shing Shieh | Psychological stress index measuring system and analysis method |
| CN103905486A (en) * | 2012-12-26 | 2014-07-02 | 中国科学院心理研究所 | Mental health state evaluation method |
| CN104715129A (en) * | 2013-12-13 | 2015-06-17 | 中国科学院心理研究所 | Mental health state assessment system and method based on mobile equipment using behavior |
| CN106407673A (en) * | 2016-09-08 | 2017-02-15 | 山东腾泰医疗科技有限公司 | Mental health evaluation method based on Internet cloud database |
| CN107330237A (en) * | 2017-05-12 | 2017-11-07 | 广州市润心教育咨询有限公司 | A kind of psychological condition appraisal procedure and system |
| CN107799165A (en) * | 2017-09-18 | 2018-03-13 | 华南理工大学 | A kind of psychological assessment method based on virtual reality technology |
| CN108231139A (en) * | 2018-01-17 | 2018-06-29 | 姜涵予 | Comprehensive social adaptation's appraisal procedure and device |
Non-Patent Citations (1)
| Title |
|---|
| 周涓等: "基于最大最小距离法的多中心聚类算法", 《计算机应用》 * |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111062626A (en) * | 2019-12-19 | 2020-04-24 | 北京儒博科技有限公司 | Capability level evaluation method, device, equipment and storage medium |
| CN111210896A (en) * | 2019-12-30 | 2020-05-29 | 西安慧云医疗科技股份有限公司 | Scale generation system based on cloud psychological diagnosis |
| CN111292833A (en) * | 2020-01-22 | 2020-06-16 | 浙江连信科技有限公司 | Physiological and psychological state prediction method and device based on intelligent robot |
| CN111292832A (en) * | 2020-01-22 | 2020-06-16 | 浙江连信科技有限公司 | Intelligent terminal based psychological crisis personnel active prediction method and device |
| CN111831681A (en) * | 2020-01-22 | 2020-10-27 | 浙江连信科技有限公司 | Intelligent terminal-based personnel discrimination method and device |
| CN111292832B (en) * | 2020-01-22 | 2021-09-14 | 浙江连信科技有限公司 | Intelligent terminal based psychological crisis personnel active prediction method and device |
| CN111831681B (en) * | 2020-01-22 | 2022-03-25 | 浙江连信科技有限公司 | Intelligent terminal-based personnel discrimination method and device |
| CN113593674A (en) * | 2020-04-30 | 2021-11-02 | 北京心数矩阵科技有限公司 | Character impact factor analysis method based on structured neural network |
| CN111899823A (en) * | 2020-06-11 | 2020-11-06 | 上海梅斯医药科技有限公司 | Method and system for processing gauge information, terminal equipment and storage medium |
| CN113536072A (en) * | 2020-11-16 | 2021-10-22 | 厦门市和家健脑智能科技有限公司 | Method and device for model voting combination of cognitive screening data processing modeling |
| CN113299358A (en) * | 2021-05-20 | 2021-08-24 | 北京大学深圳医院 | Negative emotion screening method, device and equipment based on assessment scale |
| CN113662547A (en) * | 2021-09-28 | 2021-11-19 | 南京融媒数智信息科技有限公司 | Psychological online dynamic monitoring auxiliary psychological assessment method and equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110060762B (en) | 2021-06-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110060762A (en) | A kind of mental development level appraisal procedure and system based on multiple-factor scale data | |
| Temple | Growth effects of education and social capital in the OECD countries | |
| Talukder et al. | Using multi‐criteria decision analysis for assessing sustainability of agricultural systems | |
| Alegre | Decentralization and the composition of public expenditure in Spain | |
| CN104835087A (en) | Data processing method and apparatus for education test system | |
| Ewusi | Disparities in levels of regional development in Ghana | |
| CN109964265A (en) | Language learning is measured using standardized fraction scale and self-adaptive estimation engine | |
| Laureti et al. | Measuring the efficiency of teaching activities in Italian universities: An information theoretic approach | |
| CN107885726A (en) | Customer service quality evaluating method and device | |
| CN109783601A (en) | Computer intelligence group volume method and its system based on knowledge on testing point | |
| Giménez et al. | Human capital measurement in OECD countries and its relation to GDP growth and innovation | |
| CN110648259A (en) | College entrance examination volunteer evaluation system based on big data | |
| Jinhua et al. | E-government evaluation based on citizen satisfaction and its implementation | |
| Erdogan et al. | Comparison of urban housing satisfaction in modern and traditional neighborhoods in Edirne, Turkey | |
| Widiputera et al. | The attractiveness of programmes in higher education: An empirical approach | |
| CN107291616A (en) | A kind of online generating platform of project report | |
| CN108924369B (en) | NPS (network platform System) evaluation operation method, system and management platform based on telephone survey | |
| CN109816260A (en) | Based on psychologic vocational ability evaluation system | |
| CN112598184A (en) | Method and device for predicting relapse risk of drug-dropping person | |
| CN112883271A (en) | Course education system based on analytic hierarchy process evaluation and course recommendation method | |
| Sun et al. | Study on third-party logistics service provider selection evaluation indices system based on analytic network process with BOCR | |
| CN112598944B (en) | Intelligent English teaching system | |
| KR101223325B1 (en) | Method for supllying of vocation list and system for the same | |
| CN106970994A (en) | A kind of online practical demonstration extracting method of automation | |
| e Costa et al. | Locating centres of information and recruitment of volunteers for the Portuguese armed forces: A decision-analysis case-study |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |