CN110060762B - Psychological development level assessment method and system based on multi-factor scale data - Google Patents
Psychological development level assessment method and system based on multi-factor scale data Download PDFInfo
- Publication number
- CN110060762B CN110060762B CN201910321101.1A CN201910321101A CN110060762B CN 110060762 B CN110060762 B CN 110060762B CN 201910321101 A CN201910321101 A CN 201910321101A CN 110060762 B CN110060762 B CN 110060762B
- Authority
- CN
- China
- Prior art keywords
- factor
- user
- scale
- development level
- question
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- 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 psychological development level assessment method and system based on multi-factor scale data. The method and the system establish an evaluation model according to all the user original data stored in the database module, and can realize large-scale psychological development level evaluation; before the evaluation model is established, data cleaning is firstly carried out on original data of a user, and quantity table question answers which the user answers seriously are screened out to be used as sample points, so that the evaluation result accuracy of the evaluation model established based on the sample points is higher; the test information presented to the user by the invention comprises the single-factor questions and the multi-factor questions, so that the phenomenon of social prospective response caused by the single-factor scale can be effectively avoided, the authenticity of the evaluation result is improved, and the problems of low accuracy and authenticity of the scale evaluation result obtained by the conventional scale evaluation method are solved.
Description
Technical Field
The invention relates to the technical field of psychological development level assessment, in particular to a psychological development level assessment method and system based on multi-factor scale data.
Background
Mental development refers to a series of positive psychological changes that occur throughout the life of an individual. Psychological development is a continuous and uninterrupted process, and each psychological process and personality trait gradually and continuously develop. The psychological development is directional, and the psychological development direction is different for people of different ages and different regions. The mental development level can be used to measure different directions of mental development. Therefore, whether a human mental development level can be accurately evaluated or not can play a crucial role in the career planning and the life style of the human. In recent years, the scale evaluation method has been used relatively widely because of its structural and objective properties in the fields of tool preparation, measurement operation, result interpretation, and the like. However, it has its own deficiencies and needs to be improved.
The normal mode demarcation method is a commonly adopted dividing mode of the measuring meter, and for the dividing mode, whether the normal mode data is accurate or not directly influences the accuracy of the measuring meter evaluation. However, in the traditional psychological field, due to the limitation of some social conditions, it is difficult to call a sufficient number of individual filling scales for each experiment, generally speaking, the sample size used by the normal demarcation method is generally 1500-2000 people, the sample size is not enough to represent the distribution of all people to be evaluated, and the limitation is generated on the data scale. Secondly, the modification times of the normal mode are less, so that the using period of the normal mode is long, the using period of the normal mode corresponding to most scales reaches decades, and the long using period of the normal mode greatly reduces the timeliness of the scales, which is the limitation of the scales on time domain. Meanwhile, most part of the spreadsheets are developed and established abroad, and the data collected when the normals are established are from abroad. The use of the partial scale in China is realized by directly applying the foreign common model or slightly changing the foreign common model, and the common model still uses the same common model data even in different provinces in China, so the common model also has certain limitation in regions. Therefore, the traditional normal mode demarcation method has limitations in data scale, time and region, and the accuracy of scale evaluation is directly reduced due to the multiple limitations of the normal mode.
Another problem with conventional assessment scales is that they are too single in scale factor and highly subject specific. Such subjects can easily guess the evaluation intention, and some subjects intentionally conceal their true psychological states, i.e., social response. Once this occurs, the authenticity of the scale assessment results will decrease.
Disclosure of Invention
The invention aims to provide a psychological development level assessment method and system based on multi-factor scale data, and aims to solve the problems that the accuracy and the authenticity of a scale assessment result obtained by the existing scale assessment method are low.
In order to achieve the purpose, the invention provides the following scheme:
a method for assessing the level of mental development based on multi-factor scale data, the method comprising:
acquiring all user original data stored in a database module; the original user data comprises the answers of the scale questions answered by a plurality of users and corresponding answer time;
carrying out data cleaning on the original data of the user, and screening out the answers of the scale questions answered seriously by the user as sample points;
establishing a single-factor evaluation model according to the sample points and determining the psychological development level corresponding to each sample point;
determining a multi-factor topic group according to the psychological development level;
establishing a multi-factor evaluation model according to the question answers corresponding to the multi-factor question group;
obtaining the current question answer of the current scale answered by the current user;
determining to adopt the single-factor evaluation model or the multi-factor evaluation model as a current evaluation model according to the type of the current scale;
and evaluating the psychological development level of the current user according to the current question answer and the current evaluation model.
Optionally, the data cleaning is performed on the user original data, and a scale topic answer that the user answers seriously is screened out as a sample point, specifically including:
judging whether the answer of the scale question answered by the ith user in the original user data contains a missing value or not to obtain a first judgment result;
if the first judgment result is that the scale topic answer answered by the ith user contains a missing value, rejecting the scale topic answer answered by the ith user;
if the first judgment result is that the quantity table question answer answered by the ith user has no missing value, retaining the quantity table question answer answered by the ith user to form a pre-screened data set;
judging whether answer time corresponding to the answer of the test table question answered by the ith user in the pre-screened data set is within a preset answer time range or not, and obtaining a second judgment result;
if the second judgment result is that the answer time corresponding to the scale question answer answered by the ith user is not within the preset answer time range, rejecting the scale question answer answered by the ith user;
if the second judgment result is that the answer time corresponding to the quantity table question answer answered by the ith user is within a preset answer time range, taking the quantity table question answer answered by the ith user as the quantity table question answer answered by the user;
and forming a column vector by the quantity table topic answers answered by the ith user carefully as the ith sample point.
Optionally, the establishing a single-factor evaluation model according to the sample points and determining the psychological development level corresponding to each sample point specifically include:
obtaining sample points corresponding to answers of the single quantity table questions carefully answered by the user in the sample points as single quantity table sample points;
determining single-meter initial clustering centers of the single-meter sample points by adopting a maximum-minimum distance algorithm;
according to the initial clustering center of the single quantity table, adopting a K-means clustering algorithm to iteratively calculate the single quantity table clustering center of the multiple single quantity table sample points, and clustering the multiple single quantity table sample points into multiple single quantity table clusters;
taking the single-quantity table clustering center as the single-factor evaluation model; each single scale cluster corresponds to a psychological development level; and the psychological development level corresponding to the single scale cluster where the single scale sample point is located is the psychological development level corresponding to the single scale sample point.
Optionally, the determining a multi-factor topic group according to the mental development level specifically includes:
acquiring all questions in a multi-factor scale answered by a user;
taking the questions as independent variables, taking the psychological development level of the user as dependent variables, and obtaining a coefficient between each independent variable and the dependent variable through an ordered multinomial logistic regression model;
performing T test on each coefficient by taking a preset value as a significance level to obtain the independent variable which is significantly related to the dependent variable; the independent variable which is obviously related to the dependent variable is the multi-factor topic group which is obviously related to the psychological development level.
Optionally, the establishing of the multi-factor evaluation model according to the question answers corresponding to the multi-factor question group specifically includes:
forming a column vector by the question answers of the multi-factor question group answered by each user as a multi-factor scale sample point;
determining the initial clustering centers of the multi-factor scale of the sample points of the multi-factor scale by adopting a maximum and minimum distance algorithm;
according to the initial clustering center of the multi-factor scale, iteratively calculating the multi-factor scale clustering center of a plurality of multi-factor scale sample points by adopting a K-means clustering algorithm, and clustering the plurality of multi-factor scale sample points into a plurality of multi-factor scale clusters;
using the multi-factor scale clustering center as the multi-factor evaluation model; each multifactor scale cluster corresponds to a mental development level.
Optionally, the evaluating the psychological development level of the current user according to the current question answer and the current evaluation model specifically includes:
forming the current question answer into a current question column vector;
calculating the distance between the current topic column vector and each clustering center of the current evaluation model;
and determining the psychological development level corresponding to the clustering center closest to the current user as the psychological development level of the current user.
A system for assessing mental development levels based on multi-factor scale data, the system comprising: the system comprises a human-computer interaction module, a database module, an evaluation model building module and a psychological development level evaluation module; the evaluation model building module comprises a data cleaning sub-module, a single-factor question level calibration sub-module, a multi-factor question selection sub-module and a multi-factor question level calibration sub-module;
the data cleaning submodule is used for acquiring all user original data stored in the database module, and the user original data comprises the quantity table question answers answered by a plurality of users and the corresponding answer time; performing data cleaning on the acquired user original data, and screening out the quantity table question answers which are answered seriously by the user as sample points;
the single-factor theme level calibration submodule is used for establishing a single-factor evaluation model according to the sample points and determining the psychological development level corresponding to each sample point;
the multi-factor topic selection submodule is used for determining a multi-factor topic group according to the psychological development level;
the multi-factor question level calibration submodule is used for establishing a multi-factor evaluation model according to the question answers corresponding to the multi-factor question group;
the psychological development level evaluation module is used for obtaining the answer of the current question of the current scale answered by the current user and determining to adopt the single-factor evaluation model or the multi-factor evaluation model as the current evaluation model according to the type of the current scale; subsequently, assessing the psychological development level of the current user according to the obtained current question answer and the current assessment model;
and the human-computer interaction module is used for displaying the evaluation questions for the current user, receiving the evaluation information of the current user and displaying the psychological development level of the current user.
And the database module is used for storing the evaluation information of the user and sending an update model request to the evaluation model construction module.
Optionally, the single-factor topic level calibration sub-module specifically includes:
the single-quantity table sample point acquisition unit is used for acquiring a sample point corresponding to a single-quantity table question answer which is seriously answered by a user in the sample point as a single-quantity table sample point;
the single-meter initial clustering center determining unit is used for determining single-meter initial clustering centers of the single-meter sample points by adopting a maximum-minimum distance algorithm;
the single-quantity table data clustering unit is used for iteratively calculating single-quantity table clustering centers of a plurality of single-quantity table sample points by adopting a K-means clustering algorithm according to the single-quantity table initial clustering centers and clustering the single-quantity table sample points into a plurality of single-quantity table clusters;
the single-factor evaluation model establishing unit is used for taking the single-quantity table clustering center as the single-factor evaluation model; each single scale cluster corresponds to a psychological development level; and the psychological development level corresponding to the single scale cluster where the single scale sample point is located is the psychological development level corresponding to the single scale sample point.
Optionally, the multi-factor topic selection sub-module specifically includes:
the regression coefficient determining unit is used for acquiring all questions in a multi-factor scale answered by a user, taking the acquired questions as independent variables, taking the psychological development level of the user as dependent variables, and obtaining a coefficient between each independent variable and each dependent variable through an ordered multi-term logistic regression model;
the coefficient checking unit is used for performing T check on each coefficient by taking a preset value as a significance level to obtain the independent variable which is significantly related to the dependent variable; the independent variable which is obviously related to the dependent variable is the multi-factor topic group which is obviously related to the psychological development level.
Optionally, the mental development level assessment module specifically includes:
the distance calculation unit is used for forming the current question answers into a current question column vector and calculating the distance between the current question column vector and each clustering center of the current evaluation model;
and a psychological development level determining unit, configured to determine a psychological development level corresponding to the closest cluster center as the psychological development level of the current user.
According to the specific embodiment provided by the invention, the invention discloses the following technical effects:
the invention provides a psychological development level assessment method and system based on multi-factor scale data, wherein an assessment model is established according to all user original data stored in a database module, so that large-scale psychological development level assessment can be realized; before the evaluation model is established, data cleaning is firstly carried out on original data of a user, and quantity table question answers which the user answers seriously are screened out to be used as sample points, so that the evaluation result accuracy of the evaluation model established based on the sample points is higher; the test information presented to the user by the invention comprises the single-factor questions and the multi-factor questions, so that the phenomenon of social prospective response caused by the single-factor scale can be effectively avoided, the authenticity of the evaluation result is improved, and the problems of low accuracy and authenticity of the scale evaluation result obtained by the conventional scale evaluation method are solved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without inventive exercise.
FIG. 1 is a general block diagram of a mental development level assessment system based on multi-factor scale data according to the present invention;
FIG. 2 is a diagram of the internal framework of an assessment model building module provided by the present invention;
fig. 3 is a flowchart of a method for assessing a mental development level based on data from a multifactorial scale according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention aims to provide a psychological development level assessment method and system based on multi-factor scale data, and aims to solve the problems that the accuracy and the authenticity of a scale assessment result obtained by the existing scale assessment method are low.
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.
Fig. 1 is an overall framework diagram of the psychological development level assessment system based on multi-factor scale data according to the present invention. Referring to fig. 1, the system for assessing the mental development level based on the data of the multi-factor scale provided by the invention comprises the following modules: a human-computer interaction module 101, a database module 102, an assessment model construction module 103 and a psychological development level assessment module 104.
(1) Man-machine interaction module
The human-computer interaction module 101 is mainly used for displaying the evaluation questions for the user, receiving the evaluation information of the user and feeding back the evaluation information to the user.
The human-computer interaction module 101 firstly displays a plurality of directions to be tested (such as sex form, occupation planning form, pressure form and the like) for a user, and after the user selects a certain direction to be tested, the human-computer interaction module 101 selects all scales (such as an Essen personality questionnaire, a teenager psychology toughness scale, a school atmosphere questionnaire and the like) subordinate to the direction from the database module 102 and sequentially displays the test questions to the user.
After the user finishes evaluation, the human-computer interaction module 101 records all questions answered answers and answer process data (answering time and answering sequence) of the questions answered by the user, and submits the two parts of answer data to the database module 102 and the psychological development level evaluation module 104 of the system, meanwhile, the human-computer interaction module 101 can automatically identify the number of scales finished by the user, if only one scale is finished, the human-computer interaction module 101 submits a parameter '1' to the psychological development level evaluation module 104, if a plurality of scales are finished, the human-computer interaction module 101 submits a parameter '2' to the psychological development level evaluation module 104, and different parameters are used for the psychological development level evaluation module 104 to select different models for evaluation.
When the mental development level assessment module 104 completes the assessment of the mental development level of the user and returns the assessment result to the human-computer interaction module 101, the human-computer interaction module 101 converts the mental development level assessment result into a descriptive sentence in combination with the direction to be measured and displays the descriptive sentence on the user interface.
If the direction to be measured is a personality pattern and the mental development level result returns to 1, then what appears on the user interface is: you are sexually inward, calm, rich in internal provinces, dislike stimulation, like an orderly life style, and have stable emotion.
(2) Database module
The database module 102 mainly includes two functions: the data volume monitoring function is realized by the information storage function and the data volume monitoring function.
The function of storing information is realized mainly by sub-tables in a database. The database module 102 includes three tables for storing three pieces of information: personal information of the user, such as the user's test number, its demographic variables (gender, grade, region, etc.); the information of the evaluation scale, the subject information of each scale and the test direction of the scale (such as the Essec personality questionnaire belongs to the test direction of the character pattern); user answering information, the question answers of the user completion table questions and process data (user answering time, answering sequence and the like).
Meanwhile, the database module 102 also needs to monitor the ratio of the new data volume (the data received after the last model update) to the total data volume in the database in real time, and when the ratio exceeds a preset ratio threshold (the threshold is set to be 10%), the database module 102 sends a request for updating the module to the evaluation model building module 103.
(3) Evaluation model construction module
The assessment model construction module 103 mainly functions to construct a new assessment model using all data in the database module after receiving a request for updating the model from the database module 102, and to output the new assessment model to the mental development level assessment module 104. The evaluation model building module 103 is a core module of the system, and the normal operation of the evaluation model building module needs the support of the database module 102 and the human-computer interaction module 101. The internal structure of the evaluation model building module 103 is shown in fig. 2, the evaluation model building module 103 includes a data cleaning sub-module, a single-factor topic level calibration sub-module, a multi-factor topic selection sub-module, and a multi-factor topic level calibration sub-module, and the main functions of each sub-module are as follows:
1) a data cleaning submodule:
the data cleaning sub-module has the main function of screening user original data from the man-machine interaction module and the database module. The criteria for the screening were: and judging whether the original data contains missing values and process data answered by the user. If the original data contains missing values or the answer time of the user is not between 2s and 2min, the original data can be automatically removed. Therefore, the data which are seriously answered by the user are ensured after cleaning.
2) A single-factor topic level calibration submodule:
answer records of a single-scale table (such as an Essenke personality questionnaire in a personality testing direction) directly related to psychological development are used as a data source in a single-factor question level calibration sub-module, all question answers of each user in the single-scale table form a column vector to serve as a sample point, the answer of each question is a characteristic value of the sample point, all sample points are classified through a K-means clustering unsupervised learning method, the psychological development level corresponding to each user is obtained, and a clustering center serves as a single-factor evaluation model and is output to the psychological level evaluation module 104.
However, since the initial cluster center selection of the K-means cluster is random, the clustering result also contains great randomness. Therefore, in the single-factor topic level calibration submodule, the initial clustering center is fixed by adopting a maximum-minimum distance algorithm. In the maximum-minimum distance algorithm, the initial cluster center xlThe following formula is selected:
wherein d isikIs the euclidean distance of the ith sample point to the kth initial cluster center.
After the initial clustering center is determined, the number of clustered clusters is set to be 4, K-means clustering iteration is started, the iteration is divided into two processes, and each sample point is firstly classified to the nearest clustering center:
ti＝min(dij)
wherein t isiIs the category of the ith sample point, dijIs the euclidean distance from the ith sample point to the jth cluster center.
And then recalculating the clustering center, wherein the new clustering center is the center point of all the sample points under the category.
When the recalculated cluster center does not change or after the maximum number of iterations (100) is reached, clustering ends. Each cluster obtained by K-means clustering represents each psychological development level (obtained by single-factor topic evaluation), and the user corresponding to each sample point under one cluster is on the psychological development level corresponding to the cluster. The psychological development level is a result which can be visually seen from the clustering, and the psychological development level can be measured by 1, 2, 3 and 4.
The input of the single-factor horizontal calibration submodule is the answer record of a single scale (such as an Essecker personality questionnaire in the character form testing direction) directly related to the psychological development; the output is the mental development level (assessed using a single factor topic) for each user. The single-factor theme level calibration sub-module not only can output 4 final clustering centers serving as single-factor evaluation models to the psychological development level evaluation module, but also can output the psychological development level of each sample point to the multi-factor theme selection sub-module.
3) A multi-factor topic selection submodule:
in the multi-factor topic selection submodule, all topics in a measurement and evaluation scale (such as a teenager psychology scale, a school atmosphere questionnaire and the like) indirectly related to the psychological development level and the psychological development level corresponding to each user obtained in a single-factor topic level calibration submodule are input, a coefficient between each topic and the psychological development level is obtained through logistic regression, and then significance test is carried out on the coefficient, so that a multi-factor topic group related to the psychological development level is selected from all the topics in the multi-factor scale.
The multi-factor question selection submodule applies an ordered multi-item logistic regression model, the independent variable is all the question answers of the multi-factor table in the answer data of each user, and the dependent variable is the psychological development level calibrated in the psychological development level calibration submodule by the user. The coefficient between each independent variable and dependent variable can be obtained through the logistic regression model:
y＝g(θ0+θ1x1+θ2x2+θ3x3+...+θnxn)
wherein y is a dependent variable, xnIs the nth argument, θnIs the coefficient of the nth argument and g is a non-linear function.
Next, each coefficient θ1,θ2,...,θnAnd performing T test by taking 0.005 as a significance level to obtain independent variables which are significantly related to the dependent variables, and connecting the independent variables with the actual meanings of the dependent variables, wherein the selected independent variables are the multi-factor topic group which is significantly related to the psychological development level, and the multi-factor topic group is output to a multi-factor topic level calibration sub-module.
4) A multi-factor topic level calibration sub-module:
the algorithm used in the multi-factor topic level calibration submodule is the same as that of the single-factor topic level calibration submodule, and the K-means clustering algorithm is still used. The difference lies in that: the input of the multi-factor topic horizontal calibration sub-module is a multi-factor topic group output in the multi-factor topic selection sub-module. The output of the multi-factor topic level calibration sub-module is the final 4 clustering centers which are used as a multi-factor evaluation model of the psychological development level evaluation module.
And packaging all the topic answers in the multi-factor topic group output by each user in the multi-factor topic selection sub-module into a column vector to serve as a sample point (multi-factor scale sample point) of the cluster. And still determining initial clustering centers by using a maximum-minimum distance algorithm, setting the number of the clustering centers to be 4, and outputting the final 4 clustering centers serving as a multi-factor evaluation model to a psychological development level evaluation module after the clustering is finished.
(4) Psychological development level evaluation module
The mental development level evaluation module 104 mainly evaluates the user data from the human-computer interaction module 101 in real time through the evaluation model (including the single-factor evaluation model and the multi-factor evaluation model) output in the evaluation model construction module 103. The input of the mental development level assessment module is the evaluation data of the current user transmitted by the human-computer interaction module 101, and meanwhile, the mental development level assessment module selects to use the single-factor assessment model output by the single-factor topic level calibration sub-module or the multi-factor assessment model output by the multi-factor topic level calibration sub-module according to the parameter "1" or "2" transmitted by the human-computer interaction module.
The mental development level evaluation module encapsulates the current user data (answers to questions) into a column vector, the distance between the column vector and 4 clustering centers in the current evaluation model is respectively obtained, and the mental development level corresponding to the clustering center closest to the column vector corresponds to the mental development level of the current user. The current mental development level of the user is returned to the human-computer interaction module 101 as an output of the mental development level evaluation module. The human-computer interaction module 101 is a web portal, and is the only way for the user to interact with the system, and after the mental development level evaluation is finished, the human-computer interaction module 101 acquires the evaluation result from the mental development level evaluation module 104, synthesizes the evaluation result and feeds back the evaluation result to the user.
The psychological development level assessment system based on the multi-factor scale data is applied to a network platform, so that big data can be acquired more conveniently, and an assessment model is automatically established in real time by using a machine learning algorithm in a data-driven mode to assess the psychological development level of a user.
Compared with the prior art, the invention has the innovation points that: firstly, the data markers used by the training model are obtained through an unsupervised machine learning algorithm, and the data markers can be changed in time along with the change of user groups, so that the method has strong flexibility and effectively solves the limitation caused by the traditional normal model method; meanwhile, the invention can collect the data needed by the psychological development level evaluation more conveniently, is beneficial to large-scale individual data acquisition in a wider range and realizes large-scale psychological development level evaluation; secondly, the test information presented to the user by the system is a multi-factor question which is used for replacing a single-factor scale, so that the phenomenon of social prospective response caused by the single-factor scale is effectively avoided; finally, the system not only has the function of online evaluation of the psychological development level, but also can update the evaluation model in real time according to the data size in the database, thereby ensuring the timeliness of the evaluation system.
Based on the psychological development level assessment system provided by the invention, the invention also provides a psychological development level assessment method based on the multi-factor scale data. As shown in fig. 3, the mental development level assessment method specifically includes:
step 301: and acquiring all user original data stored in the database module. The original data of the users comprise the answers of the table questions answered by a plurality of users and the corresponding answering time.
Step 302: and carrying out data cleaning on the original data of the user, and screening out the answers of the scale questions answered seriously by the user as sample points. The method specifically comprises the following steps:
judging whether the answer of the scale question answered by the ith user in the original user data contains a missing value or not to obtain a first judgment result;
if the first judgment result is that the scale topic answer answered by the ith user contains a missing value, rejecting the scale topic answer answered by the ith user;
if the first judgment result is that the quantity table question answer answered by the ith user has no missing value, retaining the quantity table question answer answered by the ith user to form a pre-screened data set;
judging whether answer time corresponding to the answer of the test table question answered by the ith user in the pre-screened data set is within a preset answer time range or not, and obtaining a second judgment result;
if the second judgment result is that the answer time corresponding to the scale question answer answered by the ith user is not within the preset answer time range, rejecting the scale question answer answered by the ith user;
if the second judgment result is that the answer time corresponding to the quantity table question answer answered by the ith user is within a preset answer time range, taking the quantity table question answer answered by the ith user as the quantity table question answer answered by the user;
and forming a column vector by the quantity table topic answers answered by the ith user carefully as the ith sample point.
Step 303: and establishing a single-factor evaluation model according to the sample points and determining the psychological development level corresponding to each sample point. The method specifically comprises the following steps:
obtaining sample points corresponding to answers of the single quantity table questions carefully answered by the user in the sample points as single quantity table sample points;
determining single-meter initial clustering centers of the single-meter sample points by adopting a maximum-minimum distance algorithm;
according to the initial clustering center of the single quantity table, adopting a K-means clustering algorithm to iteratively calculate the single quantity table clustering center of the multiple single quantity table sample points, and clustering the multiple single quantity table sample points into multiple single quantity table clusters;
taking the single-quantity table clustering center as the single-factor evaluation model; each single scale cluster corresponds to a psychological development level; and the psychological development level corresponding to the single scale cluster where the single scale sample point is located is the psychological development level corresponding to the single scale sample point.
Step 304: and determining a multi-factor topic group according to the psychological development level. The method specifically comprises the following steps:
acquiring all questions in a multi-factor scale answered by a user;
taking the questions as independent variables, taking the psychological development level of the user as dependent variables, and obtaining a coefficient between each independent variable and the dependent variable through an ordered multinomial logistic regression model;
performing T test on each coefficient by taking a preset value as a significance level to obtain the independent variable which is significantly related to the dependent variable; the independent variable which is obviously related to the dependent variable is the multi-factor topic group which is obviously related to the psychological development level.
Step 305: and establishing a multi-factor evaluation model according to the topic answers corresponding to the multi-factor topic group. The method specifically comprises the following steps:
forming a column vector by the question answers of the multi-factor question group answered by each user as a multi-factor scale sample point;
determining the initial clustering centers of the multi-factor scale of the sample points of the multi-factor scale by adopting a maximum and minimum distance algorithm;
according to the initial clustering center of the multi-factor scale, iteratively calculating the multi-factor scale clustering center of a plurality of multi-factor scale sample points by adopting a K-means clustering algorithm, and clustering the plurality of multi-factor scale sample points into a plurality of multi-factor scale clusters;
using the multi-factor scale clustering center as the multi-factor evaluation model; each multifactor scale cluster corresponds to a mental development level.
Step 306: and acquiring the current question answer of the current scale answered by the current user.
Step 307: and determining to adopt the single-factor evaluation model or the multi-factor evaluation model as the current evaluation model according to the type of the current scale.
Step 308: and evaluating the psychological development level of the current user according to the current question answer and the current evaluation model. The method specifically comprises the following steps:
forming the current question answer into a current question column vector;
calculating the distance between the current topic column vector and each clustering center of the current evaluation model;
and determining the psychological development level corresponding to the clustering center closest to the current user as the psychological development level of the current user.
According to the psychological development level assessment method based on the multi-factor scale data, provided by the invention, the assessment model is established according to all the user original data stored in the database module, so that large-scale psychological development level assessment can be realized; before the evaluation model is established, data cleaning is firstly carried out on original data of a user, and quantity table question answers which the user answers seriously are screened out to be used as sample points, so that the evaluation result accuracy of the evaluation model established based on the sample points is higher; the test information presented to the user by the invention comprises the single-factor questions and the multi-factor questions, so that the phenomenon of social prospective response caused by the single-factor scale can be effectively avoided, the authenticity of the evaluation result is improved, and the problems of low accuracy and authenticity of the scale evaluation result obtained by the conventional scale evaluation method are solved.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. The method disclosed by the embodiment corresponds to the system disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the system part for description.
The principles and embodiments of the present invention have been described herein using specific examples, which are provided only to help understand the method and the core concept of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, the specific embodiments and the application range may be changed. In view of the above, the present disclosure should not be construed as limiting the invention.
Claims (8)
1. A method for assessing the level of mental development based on multi-factor scale data, the method comprising:
acquiring all user original data stored in a database module; the original user data comprises the answers of the scale questions answered by a plurality of users and corresponding answer time;
carrying out data cleaning on the original data of the user, and screening out the answers of the scale questions answered seriously by the user as sample points;
establishing a single-factor evaluation model according to the sample points and determining the psychological development level corresponding to each sample point;
the establishing of the single-factor evaluation model according to the sample points and the determination of the psychological development level corresponding to each sample point specifically include:
obtaining sample points corresponding to answers of the single quantity table questions carefully answered by the user in the sample points as single quantity table sample points;
determining single-meter initial clustering centers of the single-meter sample points by adopting a maximum-minimum distance algorithm;
according to the initial clustering center of the single quantity table, adopting a K-means clustering algorithm to iteratively calculate the single quantity table clustering center of the multiple single quantity table sample points, and clustering the multiple single quantity table sample points into multiple single quantity table clusters;
taking the single-quantity table clustering center as the single-factor evaluation model; each single scale cluster corresponds to a psychological development level; the psychological development level corresponding to the single scale cluster where the single scale sample point is located is the psychological development level corresponding to the single scale sample point;
determining a multi-factor topic group according to the psychological development level;
establishing a multi-factor evaluation model according to the question answers corresponding to the multi-factor question group;
obtaining the current question answer of the current scale answered by the current user;
determining to adopt the single-factor evaluation model or the multi-factor evaluation model as a current evaluation model according to the type of the current scale;
and evaluating the psychological development level of the current user according to the current question answer and the current evaluation model.
2. The mental development level assessment method according to claim 1, wherein the data cleaning of the user raw data and the screening of the answers to the scale questions that the user answers seriously as sample points specifically comprises:
judging whether the answer of the scale question answered by the ith user in the original user data contains a missing value or not to obtain a first judgment result;
if the first judgment result is that the scale topic answer answered by the ith user contains a missing value, rejecting the scale topic answer answered by the ith user;
if the first judgment result is that the quantity table question answer answered by the ith user has no missing value, retaining the quantity table question answer answered by the ith user to form a pre-screened data set;
judging whether answer time corresponding to the answer of the test table question answered by the ith user in the pre-screened data set is within a preset answer time range or not, and obtaining a second judgment result;
if the second judgment result is that the answer time corresponding to the scale question answer answered by the ith user is not within the preset answer time range, rejecting the scale question answer answered by the ith user;
if the second judgment result is that the answer time corresponding to the quantity table question answer answered by the ith user is within a preset answer time range, taking the quantity table question answer answered by the ith user as the quantity table question answer answered by the user;
and forming a column vector by the quantity table topic answers answered by the ith user carefully as the ith sample point.
3. The mental development level assessment method according to claim 1, wherein said determining a multi-factor topic group according to said mental development level specifically comprises:
acquiring all questions in a multi-factor scale answered by a user;
taking the questions as independent variables, taking the psychological development level of the user as dependent variables, and obtaining a coefficient between each independent variable and the dependent variable through an ordered multinomial logistic regression model;
performing T test on each coefficient by taking a preset value as a significance level to obtain the independent variable which is significantly related to the dependent variable; the independent variable which is obviously related to the dependent variable is the multi-factor topic group which is obviously related to the psychological development level.
4. The mental development level assessment method according to claim 3, wherein the establishing of the multi-factor assessment model according to the topic answers corresponding to the multi-factor topic group specifically comprises:
forming a column vector by the question answers of the multi-factor question group answered by each user as a multi-factor scale sample point;
determining the initial clustering centers of the multi-factor scale of the sample points of the multi-factor scale by adopting a maximum and minimum distance algorithm;
according to the initial clustering center of the multi-factor scale, iteratively calculating the multi-factor scale clustering center of a plurality of multi-factor scale sample points by adopting a K-means clustering algorithm, and clustering the plurality of multi-factor scale sample points into a plurality of multi-factor scale clusters;
using the multi-factor scale clustering center as the multi-factor evaluation model; each multifactor scale cluster corresponds to a mental development level.
5. The mental development level assessment method according to claim 1, wherein said assessing the mental development level of the current user according to the current topic answer and the current assessment model specifically comprises:
forming the current question answer into a current question column vector;
calculating the distance between the current topic column vector and each clustering center of the current evaluation model;
and determining the psychological development level corresponding to the clustering center closest to the current user as the psychological development level of the current user.
6. A system for assessing the level of mental development based on multi-factor scale data, the system comprising: the system comprises a human-computer interaction module, a database module, an evaluation model building module and a psychological development level evaluation module; the evaluation model building module comprises a data cleaning sub-module, a single-factor question level calibration sub-module, a multi-factor question selection sub-module and a multi-factor question level calibration sub-module;
the data cleaning submodule is used for acquiring all user original data stored in the database module, and the user original data comprises the quantity table question answers answered by a plurality of users and the corresponding answer time; performing data cleaning on the acquired user original data, and screening out the quantity table question answers which are answered seriously by the user as sample points;
the single-factor theme level calibration submodule is used for establishing a single-factor evaluation model according to the sample points and determining the psychological development level corresponding to each sample point;
the single-factor topic level calibration submodule specifically comprises:
the single-quantity table sample point acquisition unit is used for acquiring a sample point corresponding to a single-quantity table question answer which is seriously answered by a user in the sample point as a single-quantity table sample point;
the single-meter initial clustering center determining unit is used for determining single-meter initial clustering centers of the single-meter sample points by adopting a maximum-minimum distance algorithm;
the single-quantity table data clustering unit is used for iteratively calculating single-quantity table clustering centers of a plurality of single-quantity table sample points by adopting a K-means clustering algorithm according to the single-quantity table initial clustering centers and clustering the single-quantity table sample points into a plurality of single-quantity table clusters;
the single-factor evaluation model establishing unit is used for taking the single-quantity table clustering center as the single-factor evaluation model; each single scale cluster corresponds to a psychological development level; the psychological development level corresponding to the single scale cluster where the single scale sample point is located is the psychological development level corresponding to the single scale sample point;
the multi-factor topic selection submodule is used for determining a multi-factor topic group according to the psychological development level;
the multi-factor question level calibration submodule is used for establishing a multi-factor evaluation model according to the question answers corresponding to the multi-factor question group;
the psychological development level evaluation module is used for obtaining the answer of the current question of the current scale answered by the current user and determining to adopt the single-factor evaluation model or the multi-factor evaluation model as the current evaluation model according to the type of the current scale; subsequently, assessing the psychological development level of the current user according to the obtained current question answer and the current assessment model;
the human-computer interaction module is used for displaying the evaluation questions for the current user, receiving the evaluation information of the current user and displaying the psychological development level of the current user;
and the database module is used for storing the evaluation information of the user and sending an update model request to the evaluation model construction module.
7. The mental development level assessment system according to claim 6, wherein the multi-factor topic selection sub-module specifically comprises:
the regression coefficient determining unit is used for acquiring all questions in a multi-factor scale answered by a user, taking the acquired questions as independent variables, taking the psychological development level of the user as dependent variables, and obtaining a coefficient between each independent variable and each dependent variable through an ordered multi-term logistic regression model;
the coefficient checking unit is used for performing T check on each coefficient by taking a preset value as a significance level to obtain the independent variable which is significantly related to the dependent variable; the independent variable which is obviously related to the dependent variable is the multi-factor topic group which is obviously related to the psychological development level.
8. The mental development level assessment system according to claim 6, wherein the mental development level assessment module specifically comprises:
the distance calculation unit is used for forming the current question answers into a current question column vector and calculating the distance between the current question column vector and each clustering center of the current evaluation model;
and a psychological development level determining unit, configured to determine a psychological development level corresponding to the closest cluster center as the psychological development level of the current 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 CN110060762A (en) | 2019-07-26 |
| CN110060762B true 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) |
Families Citing this family (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 |
| 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 |
| 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 |
| 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 |
| 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 |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
Family Cites Families (5)
| 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 |
| CN103905486B (en) * | 2012-12-26 | 2018-05-15 | 中国科学院心理研究所 | A kind of psychological health states appraisal procedure |
| 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 (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110060762A (en) | 2019-07-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110060762B (en) | Psychological development level assessment method and system based on multi-factor scale data | |
| CN101793887B (en) | Construction method of fuzzy neural network expert system for water quality assessment in turbot culture | |
| CN109523194A (en) | Chinese reading capability comparison method, apparatus and readable storage medium storing program for executing | |
| Peng | Research on model of student engagement in online learning | |
| CN108053117A (en) | A kind of student's subject grasps the personalized appraisal procedure of ability | |
| CN107885726A (en) | Customer service quality evaluating method and device | |
| KR101804150B1 (en) | Diagnostic method of reliable student core competencies | |
| CN107273704A (en) | A kind of method for building up and device of cerebral apoplexy recurrence prediction model | |
| CN107610009B (en) | Trinity enrollment probability prediction method based on neural network | |
| CN110222940A (en) | A kind of crowdsourcing test platform tester's proposed algorithm | |
| CN101923667A (en) | Method for comprehensively testing recommending position | |
| Burks et al. | Statistical hazards in nature-nurture investigations | |
| CN112836137A (en) | Person network support degree calculation system and method, terminal, device, and storage medium | |
| CN113011835A (en) | Campus health data management method and system | |
| CN112598184A (en) | Method and device for predicting relapse risk of drug-dropping person | |
| CN106960400A (en) | Enroll the appraisal procedure of probability, recommend the method and device of college entrance examination universities and colleges | |
| Alsulami et al. | The Impact of Campus Culture on the Satisfaction Level of Engineering Students: A Metaheuristics Approach | |
| CN114529142A (en) | Visual analysis system based on subject assessment report | |
| CN112381287A (en) | Chinese developmental reading disorder prediction system and prediction method thereof | |
| CN113077872A (en) | Multi-index group psychological state prediction system and device based on scale test data | |
| CN112581070A (en) | Juvenile learning career and career positioning evaluation device and method | |
| Yan | Research on the relationship between employee mental health and enterprise work performance | |
| CN117352114B (en) | Recommendation method and system of psychological assessment scale based on clustering algorithm | |
| CN101408538A (en) | Method for evaluating leather hand feeling quality based on neural network | |
| CN110634090A (en) | College entrance examination score conversion system and method |
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 |