CN111524578A - Psychological assessment device, method and system based on electronic psychological sand table - Google Patents
Psychological assessment device, method and system based on electronic psychological sand table Download PDFInfo
- Publication number
- CN111524578A CN111524578A CN202010564640.0A CN202010564640A CN111524578A CN 111524578 A CN111524578 A CN 111524578A CN 202010564640 A CN202010564640 A CN 202010564640A CN 111524578 A CN111524578 A CN 111524578A
- Authority
- CN
- China
- Prior art keywords
- psychological
- sand table
- data
- prediction model
- feature vector
- 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
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
- 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
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61M—DEVICES FOR INTRODUCING MEDIA INTO, OR ONTO, THE BODY; DEVICES FOR TRANSDUCING BODY MEDIA OR FOR TAKING MEDIA FROM THE BODY; DEVICES FOR PRODUCING OR ENDING SLEEP OR STUPOR
- A61M21/00—Other devices or methods to cause a change in the state of consciousness; Devices for producing or ending sleep by mechanical, optical, or acoustical means, e.g. for hypnosis
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63F—CARD, BOARD, OR ROULETTE GAMES; INDOOR GAMES USING SMALL MOVING PLAYING BODIES; VIDEO GAMES; GAMES NOT OTHERWISE PROVIDED FOR
- A63F9/00—Games not otherwise provided for
- A63F9/001—Games or toys connected to, or combined with, other objects; Objects with a second use as a toy or game
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/237—Lexical tools
- G06F40/242—Dictionaries
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/049—Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61M—DEVICES FOR INTRODUCING MEDIA INTO, OR ONTO, THE BODY; DEVICES FOR TRANSDUCING BODY MEDIA OR FOR TAKING MEDIA FROM THE BODY; DEVICES FOR PRODUCING OR ENDING SLEEP OR STUPOR
- A61M21/00—Other devices or methods to cause a change in the state of consciousness; Devices for producing or ending sleep by mechanical, optical, or acoustical means, e.g. for hypnosis
- A61M2021/0005—Other devices or methods to cause a change in the state of consciousness; Devices for producing or ending sleep by mechanical, optical, or acoustical means, e.g. for hypnosis by the use of a particular sense, or stimulus
- A61M2021/0044—Other devices or methods to cause a change in the state of consciousness; Devices for producing or ending sleep by mechanical, optical, or acoustical means, e.g. for hypnosis by the use of a particular sense, or stimulus by the sight sense
- A61M2021/005—Other devices or methods to cause a change in the state of consciousness; Devices for producing or ending sleep by mechanical, optical, or acoustical means, e.g. for hypnosis by the use of a particular sense, or stimulus by the sight sense images, e.g. video
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63F—CARD, BOARD, OR ROULETTE GAMES; INDOOR GAMES USING SMALL MOVING PLAYING BODIES; VIDEO GAMES; GAMES NOT OTHERWISE PROVIDED FOR
- A63F9/00—Games not otherwise provided for
- A63F9/0001—Games specially adapted for handicapped, blind or bed-ridden persons
- A63F2009/0007—Games with therapeutic effects
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Psychology (AREA)
- Public Health (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Social Psychology (AREA)
- Evolutionary Biology (AREA)
- Hospice & Palliative Care (AREA)
- Psychiatry (AREA)
- Child & Adolescent Psychology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Epidemiology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Primary Health Care (AREA)
- Developmental Disabilities (AREA)
- Multimedia (AREA)
- Acoustics & Sound (AREA)
- Anesthesiology (AREA)
- Heart & Thoracic Surgery (AREA)
- Hematology (AREA)
- Animal Behavior & Ethology (AREA)
- Veterinary Medicine (AREA)
Abstract
The invention relates to a psychological assessment device, a psychological assessment method and a psychological assessment system based on an electronic psychological sand table. Obtaining original data of various electronic psychological sand table works; processing the original data by adopting an artificial intelligence method according to the characteristics of the original data to obtain different psychological word segmentation; taking each original data as input and the corresponding psychological participle as output, and performing model training to obtain a psychological participle prediction model; acquiring various different types of psychological participles and psychological states corresponding to the psychological participles; taking each psychological word as input, taking the corresponding psychological state as output, and training by adopting a logistic regression method to obtain a psychological state prediction model; acquiring an electronic psychological sand table work to be predicted; and predicting the electronic psychological sand table work to be predicted by adopting a psychological word segmentation prediction model and a psychological state prediction model to obtain the psychological state of the tester. The invention can solve the difficult problems of popularization and application of the electronic psychological sand table caused by the shortage of a sand table psychoanalyst.
Description
Technical Field
The invention relates to the field of psychological assessment based on an electronic psychological sand table, in particular to a psychological assessment device, method and system based on the electronic psychological sand table.
Background
The sand table game is also called a boxcourt game and is a popular psychological treatment method in the world. In schools and kindergartens, it is widely used for the psychological education and psychological treatment of children; it is also popular in university and adult psychology clinics. By arousing the mind of children, people find a way of returning to soul, and further the problems of physical and mental disorder, poor social adaptation, personality development disorder and the like are solved in the sand table. The sand table game is a kind of psychological test of throwing nature, the testee can be through the sand in the sand table, sand and water etc. the object is in the sand table work with the subconscious projection of the inner heart, the sand table psychology analyst explores the inner heart world of the author by analyzing the sand table work and listening to the story that takes place in the sand table work.
Although the sand table game is a psychological projection test which is widely concerned, the popularization of the sand table game is limited by a plurality of factors, the sand table is composed of sand boxes and sand tools, the number of the sand tools is hundreds and thousands, and the sand tools with a large number are put on sand tool racks in different categories, which undoubtedly requires a lot of space and time. Secondly, an analyst needs to record and take pictures of sand information during the process of manufacturing a sand table by a traditional sand table game operator, the process of manufacturing sand table works is accompanied by the analyst, the time for manufacturing one sand table work is short, dozens of minutes and more hours, and the sand table psychology analyst is in a state of personnel shortage in China or the world, so that the popularization problem of the traditional sand table game is caused, and the situation is also the reason that the traditional sand table game is in a state like a nominal mode in a plurality of institutions such as schools, prisons and the like.
In recent years, with the development of computer technology and multimedia technology, an electronic psychological sand table of a psychological sand table environment is built by means of 3D technology, and a software device for enabling visitors to outsidely project in the internal world in a rich and flexible sand tool kingdom is provided. The electronic mental sand table really solves the problems that the traditional sand table occupies large space and the operation process is automatically recorded, but the electronic sand table works still need to be analyzed by sand table psychoanalysts one by one, so that the shortage of the analysts becomes the biggest obstacle to the popularization and application of the electronic mental sand table.
Disclosure of Invention
The invention aims to provide a psychology evaluation device, a psychology evaluation method and a psychology evaluation system based on an electronic psychology sand table, which can solve the difficult problems of popularization and application of the electronic psychology sand table caused by shortage of sand table psychoanalysts.
In order to achieve the purpose, the invention provides the following scheme:
an electronic psychological sand table based psychological assessment device comprising: the system comprises an electronic psychological sand table device, an electronic psychological sand table analysis server, a data storage server and a data analysis and display server which are sequentially connected, wherein an operator manufactures electronic psychological sand table works on the electronic psychological sand table device and transmits original data of the electronic psychological sand table works to the electronic psychological sand table analysis server; the electronic psychological sand table equipment is used for transmitting the original data to an electronic psychological sand table analysis server, and the electronic psychological sand table analysis server adopts different data processing and artificial intelligence methods to train an artificial intelligence psychological assessment model for intelligently assessing the psychological state of an author exposed out of each electronic sand table work; the data storage server is used for storing user basic information, psychological state evaluation results of authors at each time and data analysis results; the data analysis and display server is used for acquiring basic information of the users stored in the data storage and psychological state evaluation results of each author, performing data analysis on single and multiple analysis results of a single user, determining abnormal psychological state and abnormal psychological change of the user, and determining adjustment suggestions of the abnormal psychological state of the user according to the abnormal psychological state and the abnormal psychological change.
Optionally, the original data includes topographic image data of the sand table works, information data of sand placement tools in the sand table works, text description data, and voice description data.
A psychology assessment method based on an electronic psychology sand table comprises the following steps:
acquiring original data of electronic psychological sand table works of various different types from electronic psychological sand table equipment, wherein the original data comprises topographic image data of the sand table works, sand placement information data in the sand table works, text description data and voice description data;
processing the original data by adopting different artificial intelligence methods according to the characteristics of the original data to obtain different psychological word segmentation;
taking each original data as input and corresponding psychological participles as output, and performing model training to obtain a psychological participle prediction model;
acquiring various psychological segmentation words of different types and secondary labeling data labeled by a sand table psychoanalyst, wherein the secondary labeling data labeled by the sand table psychoanalyst is a psychological state corresponding to the psychological segmentation words;
taking each psychological participle as input, taking a corresponding psychological state as output, and training by adopting a logistic regression method to obtain a psychological state prediction model;
acquiring an electronic psychological sand table work to be predicted;
and predicting the electronic psychological sand table work to be predicted by adopting the psychological word segmentation prediction model and the psychological state prediction model to obtain the psychological state of the tester.
Optionally, the method includes performing model training by using each original data as input and using corresponding psychological segmentation as output to obtain a psychological segmentation prediction model, and specifically includes:
extracting a characteristic vector in the topographic image data of the sand table work by adopting a convolutional neural network technology, and recording the characteristic vector as a first characteristic vector;
the first feature vector is used as input, image psychology participle marks displayed by a work given by a psychoanalyst through analysis of topographic image data of the sand table work are used as output, and a long-term and short-term memory network algorithm is adopted for training to obtain a first psychology participle prediction model;
acquiring a characteristic vector of sand setting information data in the sand table works, and recording the characteristic vector as a second characteristic vector;
taking the second feature vector as input, taking image psychology participle labels displayed by works, which are given by psychoanalysts through analysis of sand information data, as output, and training by adopting a machine learning method of a support vector machine to obtain a second psychology participle prediction model;
acquiring a feature vector of text description data in the sand table work, and recording the feature vector as a third feature vector;
taking the first feature vector as input, taking image psychology participle labels displayed by works given by a psychologist through analyzing text description data as output, and training by adopting a long-term and short-term memory network algorithm to obtain a third psychology participle prediction model;
acquiring a feature vector of the voice description data in the sand table work, and recording the feature vector as a third feature vector;
and taking the first feature vector as input, taking image psychological word segmentation labels displayed by works given by a psychological analyst through analyzing voice description data as output, and training by adopting a long-term and short-term memory network algorithm to obtain a fourth psychological word segmentation prediction model.
Optionally, the method for predicting the psychological state includes the steps of using each psychological segmentation as an input, using a corresponding psychological state as an output, and training by using a logistic regression method to obtain a psychological state prediction model, where the method specifically includes:
collecting and integrating all the psychological word segmentation to obtain a psychological word segmentation feature vector;
normalizing the psychological word segmentation feature vector to obtain a normalized feature vector;
and taking the normalized feature vector as input and the corresponding psychological state as output, and training by adopting a logistic regression method to obtain a psychological state prediction model.
An electronic psychological sand table based psychological assessment system comprising:
the system comprises an original data acquisition module, a data processing module and a data processing module, wherein the original data acquisition module is used for acquiring original data of electronic psychological sand table works of various different types from electronic psychological sand table equipment, and the original data comprises topographic image data of the sand table works, sand placing tool information data in the sand table works, text description data and voice description data;
the psychological word segmentation determining module is used for processing the characteristics of the original data by adopting different artificial intelligence methods to obtain different psychological words;
the psychological word segmentation prediction model determining module is used for performing model training by taking each original data as input and the corresponding psychological word segmentation as output to obtain a psychological word segmentation prediction model;
the sand table psychology analyst labeling module is used for labeling the sand table psychology analysts with the second-level labeling data, and obtaining a plurality of psychographic segmentation and psychological state obtaining modules;
the psychological state prediction model determining module is used for taking each psychological word as input and taking the corresponding psychological state as output, and training by adopting a logistic regression method to obtain a psychological state prediction model;
the child psychological sand table work to be predicted obtaining module is used for obtaining the electronic psychological sand table work to be predicted;
and the prediction module is used for predicting the electronic psychological sand table work to be predicted by adopting the psychological word segmentation prediction model and the psychological state prediction model to obtain the psychological state of the tester.
Optionally, the module for determining a psychological word segmentation prediction model specifically includes:
the first feature vector determining unit is used for extracting feature vectors in the topographic image data of the sand table works by adopting a convolutional neural network technology and recording the feature vectors as first feature vectors;
a first psychology participle prediction model determining unit, configured to use the first feature vector as input, use image psychology participles displayed by a work given by a psychoanalyst through analysis of topographic image data of the sand table work as output, and perform training by using a long-term and short-term memory network algorithm to obtain a first psychology participle prediction model;
the second characteristic vector determining unit is used for acquiring the characteristic vector of the sand table work for arranging the sand tool information data and recording the characteristic vector as a second characteristic vector;
a second psychology participle prediction model determining unit, configured to use the second feature vector as input, use an image psychology participle label, which is displayed by a work given by a psychologist through analysis of sand information data, as output, and perform training by using a machine learning method of a support vector machine to obtain a second psychology participle prediction model;
the third feature vector determining unit is used for acquiring a feature vector of the text description data in the sand table work and recording the feature vector as a third feature vector;
a third mental word segmentation prediction model determining unit, configured to use the first feature vector as input, use image mental word segmentation labels displayed by a work, which are given by a mental analyst through analysis of text description data, as output, and perform training by using a long-term and short-term memory network algorithm to obtain a third mental word segmentation prediction model;
the fourth feature vector determining unit is used for acquiring the feature vector of the voice description data in the sand table work and recording the feature vector as a third feature vector;
and the fourth psychological word segmentation prediction model determining unit is used for taking the first feature vector as input, taking image psychological word segmentation labels shown by works given by a psychological analyst through analysis of voice description data as output, and training by adopting a long-term and short-term memory network algorithm to obtain a fourth psychological word segmentation prediction model.
Optionally, the mental state prediction model determining module specifically includes:
the collecting and integrating unit is used for collecting and integrating all the psychological word segmentation to obtain a psychological word segmentation feature vector;
the normalization unit is used for normalizing the psychological word segmentation feature vector to obtain a normalized feature vector;
and the psychological state prediction model determining unit is used for taking the normalized feature vector as input and the corresponding psychological state as output, and training by adopting a logistic regression method to obtain a psychological state prediction model.
According to the specific embodiment provided by the invention, the invention discloses the following technical effects:
the invention collects various data output by an electronic psychological sand table, selects different technical methods in the field of artificial intelligence according to the respective characteristics of each data, trains a plurality of prediction models, predicts a psychological word segmentation result, integrates the predicted psychological word segmentation result, normalizes the predicted psychological word segmentation result into a characteristic vector, and inputs the characteristic vector into a prediction model of a psychological state through the final psychological word segmentation to obtain a final psychological state. According to the invention, a large amount of sample data of sand table works are collected, a data processing method using secondary labeling is innovated, the psychological word segmentation labeling of each kind of data is labeled firstly, and then the psychological state labeling is given according to the integral data analysis of the works. Because the invention adopts an artificial intelligence means, the accuracy of the model can be continuously improved along with the prompting of the sample amount and the technology, thereby solving the problem that a large number of data samples cannot be processed and summarized manually.
According to the invention, through the technical means of artificial intelligence, the use cost and the use efficiency of the electronic sand table can be reduced, and the problem that the electronic psychological sand table is difficult to be widely used due to the shortage of a sand table psychoanalyst is 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 block diagram of the psychological assessment device based on the electronic psychological sand table according to the present invention;
FIG. 2 is a flow chart of a psychology evaluation method based on an electronic psychology sand table according to the invention;
FIG. 3 is a data annotation structural diagram of the present invention;
FIG. 4 is a flow chart of the training and detection of topographic images of sand table works according to the present invention;
FIG. 5 is a flowchart of a method for psychological assessment during the testing phase according to the present invention;
fig. 6 is a structural diagram of a psychology evaluation system based on an electrical psychology sand table according to the 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 psychology evaluation device, a psychology evaluation method and a psychology evaluation system based on an electronic psychology sand table, which can solve the difficult problems of popularization and application of the electronic psychology sand table caused by shortage of sand table psychoanalysts.
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.
In order to solve the difficult problems of popularization and application of the electronic psychological sand table caused by shortage of sand table psychoanalysts, the invention provides an artificial intelligence psychological assessment device, method and system based on the electronic psychological sand table, which can intelligently complete analysis work of sand table works by training an algorithm model capable of automatically analyzing sand table works for psychological assessment by utilizing advanced technologies such as computer image understanding technology, natural language understanding technology, voice recognition technology and the like in the field of artificial intelligence. In addition, due to the inherent advantages of big data and artificial intelligence technology, the accuracy of the evaluation system can be continuously improved along with the increase of data volume. In addition, the psychological assessment device, the psychological assessment method and the psychological assessment system can track the results of multiple psychological assessments of the testee, intelligently analyze the mutational and persistent psychological states of the testee, and give a suggestion or early warning prompt, so that a psychological analyst or a user can pay more attention to the psychological states of the testee.
Fig. 1 is a block diagram of the psychological assessment device based on the cyber mental sand table according to the present invention. As shown in fig. 1, a psychology evaluation apparatus based on an electronic psychology sand table includes: the electronic psychological sand table analysis system comprises an electronic psychological sand table device 1, an electronic psychological sand table analysis server 2, a data storage server 3 and a data analysis and display server 4 which are sequentially connected, wherein an operator makes an electronic psychological sand table work on the electronic psychological sand table device 1 and transmits original data of the electronic psychological sand table work to the electronic psychological sand table analysis server 2; the electronic psychological sand table device 1 is used for transmitting the original data to an electronic psychological sand table analysis server 2, and the electronic psychological sand table analysis server 2 trains an artificial intelligence psychological assessment model for intelligently assessing the psychological state of an author exposed out of each electronic sand table work by adopting different data processing and artificial intelligence methods according to the characteristics of different data; the data storage server 3 is used for storing user basic information, psychological state evaluation results of authors and data analysis results; the data analysis and presentation server 4 is configured to obtain basic information of users and psychological state evaluation results of authors each time stored in the data storage, perform data analysis on single and multiple analysis results of a single user, determine abnormal psychological states and abnormal psychological changes of the user, and determine adjustment suggestions for the abnormal psychological states of the user according to the abnormal psychological states and the abnormal psychological changes. The original data comprises topographic image data of the sand table works, sand placing information data, text description data and voice description data in the sand table works.
Fig. 2 is a flow chart of a psychology evaluation method based on an electronic psychology sand table according to the invention. As shown in fig. 2, a psychology evaluation method based on an electronic psychology sand table includes:
step 101: the method comprises the steps of obtaining original data of electronic psychological sand table works of various different types from electronic psychological sand table equipment, wherein the original data comprise topographic image data of the sand table works, sand placement information data in the sand table works, text description data and voice description data.
The invention collects a large amount of sample data of sand table works with the help of related organizations, and fig. 3 is a data labeling structure chart of the invention, and as shown in fig. 3, a two-level data labeling method is adopted, and the first-level labeling is to label each kind of data independently. Firstly, a plurality of professional sand table psychoanalysts summarize psychological participles related to sand table analysis by looking up a large amount of documents and years of experience, and a group of psychological participle labels are respectively given by image data of sand table works, sand tool information data put in the sand table works, text description data and voice description data. And then summarizing the four psychological segmentation labels, and giving out the psychological state label of the author reflected by the sand table work by the psychological analysts according to the summarized psychological segmentation labels to be regarded as a secondary label.
Step 102: and processing the original data by adopting different artificial intelligence methods according to the characteristics of the original data to obtain different psychological word segmentation.
Step 103: and taking each original data as input and the corresponding psychological participle as output, and performing model training to obtain a psychological participle prediction model.
Step 103 mainly comprises four data processing and four psychological word segmentation prediction model training and using. The first type of data is sand table work terrain image data, and the training samples of the model are sand table work terrain image data and the above-mentioned psychological word segmentation labels of the work given by a psychological analyst through analysis of the sand table work terrain image data. The step 103 specifically includes:
step 1031: and extracting the characteristic vector in the topographic image data of the sand table work by adopting a convolutional neural network technology, and recording the characteristic vector as a first characteristic vector.
Step 1032: and taking the first feature vector as input, taking image psychology participle marks displayed by the work given by a psychoanalyst through analyzing topographic image data of the sand table work as output, and training by adopting a long-term and short-term memory network algorithm to obtain a first psychology participle prediction model.
The sand table work terrain image is a gray scale image formed by mapping the height of a sand table terrain height map drawn by an operator on the upper side of a graphic pixel. FIG. 4 is a flow chart of the training and detection of the terrain images of the sand table work of the present invention. As shown in fig. 4, during model training, a Convolutional Neural Network (CNN) technique is used to extract feature vectors of a topographic image of a sand table work, and the feature vectors and image psychology participle labels are trained by using a long short-Term Memory (LSTM) algorithm to train a psychology participle prediction classifier, wherein the training method includes, but is not limited to, an LSTM method. When the method is used in the same way, the sand table work image is input into a trained prediction model to obtain predicted psychological word segmentation.
Step 1033: and acquiring a characteristic vector of the sand setting information data in the sand table works, and recording the characteristic vector as a second characteristic vector.
Step 1034: and taking the second feature vector as input, taking image psychology participle labels displayed by works, which are given by a psychoanalyst through analysis of the sand information data, as output, and training by adopting a machine learning method of a support vector machine to obtain a second psychology participle prediction model.
The sand placing tool information data in the sand table works comprise: the number of sand tools placed in each position of the sand table, the number of sand tools placed in each category, the number of sand tools deleted, the number of sand tools placed in each category of hidden attributes and the number of sand tools placed in each direction are divided by the total number of the sand tools placed in each direction to form a characteristic vector. The sand table psychology analyst can give a group of psychographic word segmentation labels according to the sand tool information data in each sand table work. The feature vectors and the psychology participles generated by the sand placement information data in the generated sand table works are labeled, and a machine learning method of a Support Vector Machine (SVM) is adopted to train a prediction model from the sand placement information data in the sand table works to the psychology participles, but the training method includes but is not limited to an SVM algorithm. When the method is used, the characteristic vectors of the sand tool placement information data in the sand table works are extracted, and then the characteristic vectors are input into a prediction model to obtain a group of psychological word segmentation prediction results.
Step 1035: and acquiring a feature vector of the text description data in the sand table work, and recording the feature vector as a third feature vector.
Step 1036: and taking the first characteristic vector as input, taking image psychology participle labels displayed by the work, which are given by a psychoanalyst through analyzing text description data, as output, and training by adopting a long-term and short-term memory network algorithm to obtain a third psychology participle prediction model.
The textual description data is a textual description of the sand table work that the operator has performed after the sand table work has been made. Firstly, a sand table psychology analyst establishes a common word dictionary of text description according to years of case experience and literature data research, and common words in the dictionary are related to the psychological state of an author to a certain extent. The method comprises the steps of generating Chinese Word segmentation from text description data by using the existing Word segmentation method of Word2Vec, extracting keywords by using a Term Frequency-inverse document Frequency (TF-IDF) method, and generating a feature vector of a common Word dictionary. And (3) utilizing TF-IDF characteristic vectors of a common word dictionary generated by the text description data and psychological word segmentation labels corresponding to the text description data, and training a prediction model from the text description data to the psychological word segmentation by adopting an LSTM algorithm. When the method is used, Chinese Word segmentation is generated from text description data by using a Word2Vec method, then keyword extraction is performed by adopting a TF-IDF algorithm, a feature vector of a common Word dictionary is generated, and then the feature vector is input into a prediction model to obtain predicted psychological Word segmentation. There are many methods for generating Chinese text segmentation vectors, including but not limited to TF-IDF vector extraction method. Methods of text classification also include but are not limited to the LSTM text classification method.
Step 1037: and acquiring a feature vector of the voice description data in the sand table work, and recording the feature vector as a third feature vector.
Step 1038: and taking the first feature vector as input, taking image psychological word segmentation labels displayed by works given by a psychological analyst through analyzing voice description data as output, and training by adopting a long-term and short-term memory network algorithm to obtain a fourth psychological word segmentation prediction model.
The voice description data is actually text description data recorded in a voice form, and is description or psychological state expression of a sand table work recorded in a voice form by a sand table operator after the sand table work is made. Therefore, the processing method of the voice description data is basically the same as the processing method of the text description data, only one step is added, namely, the voice description data is recognized into the text description through a voice recognition mode, and the text adopts the existing voice recognition technology to realize the operation of converting voice into characters. Then processing the voice description data according to the processing method of the text description data to obtain a psychological word segmentation result.
Step 104: and acquiring various psychological segmentation words of different types and secondary labeling data labeled by a sand table psychoanalyst, wherein the secondary labeling data labeled by the sand table psychoanalyst is the psychological state corresponding to the psychological segmentation words.
Step 105: taking each psychological segmentation word as input, taking a corresponding psychological state as output, and training by adopting a logistic regression method to obtain a psychological state prediction model, wherein the method specifically comprises the following steps:
step 1051: and summarizing and integrating all the psychological word segmentation to obtain a psychological word segmentation feature vector.
Step 1052: and normalizing the psychological word segmentation feature vector to obtain a normalized feature vector.
Step 1053: and taking the normalized feature vector as input and the corresponding psychological state as output, and training by adopting a logistic regression method to obtain a psychological state prediction model.
The psychological segmentation result is only an intermediate product of the psychological assessment system, that is, an intermediate result, and to obtain a final psychological assessment result, a machine learning method is used to train a prediction model from the psychological segmentation to the psychological state. And during model training, the primary sample label and the secondary sample label of the sample are used, the primary sample label is four groups of psychological participle labels respectively given by a sand table psychological analyst according to four input data, and the secondary label is evaluation of the psychological state of an operator given by the sand table psychological analyst according to the summarized psychological participle result and the analysis of the integral data of the sand table work. Therefore, when the model is trained, the psychological participles marked at the first level are collected and integrated into the psychological participle feature vector, and then normalization is carried out to form a normalized feature vector. Then, an LR method is adopted to train a prediction model from the psychological participle to the psychological state, namely a psychological state prediction model.
Step 106: acquiring an electronic psychological sand table work to be predicted;
step 107: and predicting the electronic psychological sand table work to be predicted by adopting the psychological word segmentation prediction model and the psychological state prediction model to obtain the psychological state of the tester.
During detection, the obtained psychological word segmentation results predicted by the four data are integrated into a psychological word segmentation characteristic vector, then the characteristic vector is normalized, and the normalized psychological word segmentation characteristic vector is input into a psychological state prediction model to obtain the psychological state of the final tester.
FIG. 5 is a flowchart of the psychological assessment method in the detection stage according to the present invention. The electronic sand table psychological analysis server can collect four kinds of data in each piece of electronic sand table works, namely topographic image data of the sand table works, sand table information data placed in the sand table works, text description data (written form description of an operator on the sand table works) and voice description data (voice form description of the operator on the sand table works), different data processing methods and training methods of prediction models are adopted according to the characteristics of each kind of data, and the detailed description is omitted here. Inputting the four data into the trained four psychological word segmentation prediction models to obtain four psychological word segmentation results, namely psychological word segmentation results 1 to 4 in the graph, then integrating the psychological word segmentation results, namely adding feature vectors, then normalizing the psychological word segmentation results, inputting the psychological word segmentation results into a psychological state prediction model, namely the trained LR model, for prediction to obtain the psychological state of the testee.
The invention can provide professional customized suggestions aiming at the primary psychological word segmentation result and the psychological state (final psychological assessment result), and the suggestions are summarized by an electronic sand table psychoanalyst through years of experience and cases. Meanwhile, the psychological evaluation results of each tester can be tracked for many times, the change of the psychological states of the testers is recorded, and early warning is given to the psychological state problems of mutation and evolution.
The invention collects various data output by an electronic psychological sand table, selects different technical methods in the field of artificial intelligence according to the respective characteristics of each data, trains a plurality of prediction models, predicts a psychological word segmentation result, integrates the predicted psychological word segmentation result, normalizes the predicted psychological word segmentation result into a characteristic vector, inputs the characteristic vector into a prediction model of a psychological state through the final psychological word segmentation, and obtains a final psychological assessment result, namely the psychological state.
The invention collects a large amount of sample data of sand table works, and innovatively adopts a data processing method of secondary labeling. The invention solves the problem that the electronic psychological sand table is difficult to be widely used due to the shortage of the psychological analyst of the sand table by the technical means of artificial intelligence.
Fig. 6 is a structural diagram of a psychology evaluation system based on an electrical psychology sand table according to the invention. As shown in fig. 6, a psychology evaluation system based on an electronic psychology sand table includes:
the original data acquisition module 201 is configured to acquire original data of electronic psychological sand table works of various different types from the electronic psychological sand table device, where the original data includes topographic image data of the sand table works, sand placement information data in the sand table works, text description data, and voice description data.
And the psychological word segmentation determining module 202 is configured to process the original data according to characteristics of the original data by using different artificial intelligence methods to obtain different psychological words.
And the psychological word segmentation prediction model determining module 203 is used for performing model training by taking each original data as input and the corresponding psychological word segmentation as output to obtain a psychological word segmentation prediction model.
The mental segmentation and mental state acquisition module 204 is configured to acquire multiple different types of mental segmentation and secondary labeling data labeled by a sand table mental analyst, where the secondary labeling data labeled by the sand table mental analyst is a mental state corresponding to the mental segmentation.
A psychological state prediction model determining module 205, configured to take each psychological word as an input and take a corresponding psychological state as an output, and train by using a logistic regression method to obtain a psychological state prediction model;
and the to-be-predicted sub-psychological sand table work obtaining module 206 is configured to obtain the to-be-predicted electronic psychological sand table work.
And the prediction module 207 is used for predicting the electronic psychological sand table work to be predicted by adopting the psychological word segmentation prediction model and the psychological state prediction model to obtain the psychological state of the tester.
The psychological word segmentation prediction model determining module 203 specifically includes:
and the first characteristic vector determining unit is used for extracting the characteristic vector in the topographic image data of the sand table work by adopting a convolutional neural network technology and recording the characteristic vector as a first characteristic direction.
And the first mental word segmentation prediction model determining unit is used for taking the first characteristic vector as input, taking image mental word segmentation marks displayed by a work given by a mental analyst through analysis of topographic image data of the sand table work as output, and training by adopting a long-term and short-term memory network algorithm to obtain a first mental word segmentation prediction model.
And the second characteristic vector determining unit is used for acquiring the characteristic vector of the sand table placing information data in the sand table works and recording the characteristic vector as a second characteristic vector.
And the second mental word segmentation prediction model determining unit is used for taking the second characteristic vector as input, taking image mental word segmentation labels displayed by works given by a mental analyst through analysis of the sand information data as output, and training by adopting a machine learning method of a support vector machine to obtain a second mental word segmentation prediction model.
And the third feature vector determining unit is used for acquiring the feature vector of the text description data in the sand table work and recording the feature vector as the third feature vector.
And the third mental word segmentation prediction model determining unit is used for taking the first characteristic vector as input, taking image mental word segmentation labels displayed by the work given by a mental analyst through analysis of the text description data as output, and training by adopting a long-term and short-term memory network algorithm to obtain a third mental word segmentation prediction model.
And the fourth feature vector determining unit is used for acquiring the feature vector of the voice description data in the sand table work and recording the feature vector as the third feature vector.
And the fourth psychological word segmentation prediction model determining unit is used for taking the first feature vector as input, taking image psychological word segmentation labels shown by works given by a psychological analyst through analysis of voice description data as output, and training by adopting a long-term and short-term memory network algorithm to obtain a fourth psychological word segmentation prediction model.
The mental state prediction model determining module 205 specifically includes:
and the collecting and integrating unit is used for collecting and integrating all the psychological word segmentation to obtain the psychological word segmentation feature vector.
And the normalization unit is used for normalizing the psychological word segmentation feature vector to obtain a normalized feature vector.
And the psychological state prediction model determining unit is used for taking the normalized feature vector as input and the corresponding psychological state as output, and training by adopting a logistic regression method to obtain a psychological state prediction model.
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. For the system disclosed by the embodiment, the description is relatively simple because the system corresponds to the method disclosed by the embodiment, and the relevant points can be referred to the method 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 psychological assessment device based on an electronic psychological sand table, comprising: the system comprises an electronic psychological sand table device, an electronic psychological sand table analysis server, a data storage server and a data analysis and display server which are sequentially connected, wherein an operator manufactures electronic psychological sand table works on the electronic psychological sand table device and transmits original data of the electronic psychological sand table works to the electronic psychological sand table analysis server; the electronic psychological sand table equipment is used for transmitting the original data to an electronic psychological sand table analysis server, and the electronic psychological sand table analysis server adopts different data processing and artificial intelligence methods to train an artificial intelligence psychological assessment model for intelligently assessing the psychological state of an author exposed out of each electronic sand table work; the data storage server is used for storing user basic information, psychological state evaluation results of authors at each time and data analysis results; the data analysis and display server is used for acquiring basic information of the users stored in the data storage and psychological state evaluation results of each author, performing data analysis on single and multiple analysis results of a single user, determining abnormal psychological state and abnormal psychological change of the user, and determining adjustment suggestions of the abnormal psychological state of the user according to the abnormal psychological state and the abnormal psychological change.
2. The psychoacoustic sand table-based psychological assessment device according to claim 1, wherein said original data comprises topographic image data of sand table works, information data of sand laying tools in the sand table works, text description data and voice description data.
3. A psychological assessment method based on an electronic psychological sand table is characterized by comprising the following steps:
acquiring original data of electronic psychological sand table works of various different types from electronic psychological sand table equipment, wherein the original data comprises topographic image data of the sand table works, sand placement information data in the sand table works, text description data and voice description data;
processing the original data by adopting different artificial intelligence methods according to the characteristics of the original data to obtain different psychological word segmentation;
taking each original data as input and corresponding psychological participles as output, and performing model training to obtain a psychological participle prediction model;
acquiring various psychological segmentation words of different types and secondary labeling data labeled by a sand table psychoanalyst, wherein the secondary labeling data labeled by the sand table psychoanalyst is a psychological state corresponding to the psychological segmentation words;
taking each psychological participle as input, taking a corresponding psychological state as output, and training by adopting a logistic regression method to obtain a psychological state prediction model;
acquiring an electronic psychological sand table work to be predicted;
and predicting the electronic psychological sand table work to be predicted by adopting the psychological word segmentation prediction model and the psychological state prediction model to obtain the psychological state of the tester.
4. The psychology evaluation method based on an electronic psychology sand table according to claim 3, wherein the model training is performed by taking each original data as an input and a corresponding psychology participle as an output to obtain a psychology participle prediction model, specifically comprising:
extracting a characteristic vector in the topographic image data of the sand table work by adopting a convolutional neural network technology, and recording the characteristic vector as a first characteristic vector;
the first feature vector is used as input, image psychology participle marks displayed by a work given by a psychoanalyst through analysis of topographic image data of the sand table work are used as output, and a long-term and short-term memory network algorithm is adopted for training to obtain a first psychology participle prediction model;
acquiring a characteristic vector of sand setting information data in the sand table works, and recording the characteristic vector as a second characteristic vector;
taking the second feature vector as input, taking image psychology participle labels displayed by works, which are given by psychoanalysts through analysis of sand information data, as output, and training by adopting a machine learning method of a support vector machine to obtain a second psychology participle prediction model;
acquiring a feature vector of text description data in the sand table work, and recording the feature vector as a third feature vector;
taking the first feature vector as input, taking image psychology participle labels displayed by works given by a psychologist through analyzing text description data as output, and training by adopting a long-term and short-term memory network algorithm to obtain a third psychology participle prediction model;
acquiring a feature vector of the voice description data in the sand table work, and recording the feature vector as a third feature vector;
and taking the first feature vector as input, taking image psychological word segmentation labels displayed by works given by a psychological analyst through analyzing voice description data as output, and training by adopting a long-term and short-term memory network algorithm to obtain a fourth psychological word segmentation prediction model.
5. The psychology evaluation method according to claim 4, wherein the psychology segmentation is used as an input, a corresponding psychology is used as an output, and a logistic regression method is used for training to obtain a psychology prediction model, specifically comprising:
collecting and integrating all the psychological word segmentation to obtain a psychological word segmentation feature vector;
normalizing the psychological word segmentation feature vector to obtain a normalized feature vector;
and taking the normalized feature vector as input and the corresponding psychological state as output, and training by adopting a logistic regression method to obtain a psychological state prediction model.
6. A psychology evaluation system based on an electronic psychology sand table, comprising:
the system comprises an original data acquisition module, a data processing module and a data processing module, wherein the original data acquisition module is used for acquiring original data of electronic psychological sand table works of various different types from electronic psychological sand table equipment, and the original data comprises topographic image data of the sand table works, sand placing tool information data in the sand table works, text description data and voice description data;
the psychological word segmentation determining module is used for processing the characteristics of the original data by adopting different artificial intelligence methods to obtain different psychological words;
the psychological word segmentation prediction model determining module is used for performing model training by taking each original data as input and the corresponding psychological word segmentation as output to obtain a psychological word segmentation prediction model;
the sand table psychology analyst labeling module is used for labeling the sand table psychology analysts with the second-level labeling data, and obtaining a plurality of psychographic segmentation and psychological state obtaining modules;
the psychological state prediction model determining module is used for taking each psychological word as input and taking the corresponding psychological state as output, and training by adopting a logistic regression method to obtain a psychological state prediction model;
the child psychological sand table work to be predicted obtaining module is used for obtaining the electronic psychological sand table work to be predicted;
and the prediction module is used for predicting the electronic psychological sand table work to be predicted by adopting the psychological word segmentation prediction model and the psychological state prediction model to obtain the psychological state of the tester.
7. The psychology evaluation system based on cyber mental sand table according to claim 6, wherein the psychology word segmentation prediction model determining module specifically comprises:
the first feature vector determining unit is used for extracting feature vectors in the topographic image data of the sand table works by adopting a convolutional neural network technology and recording the feature vectors as first feature vectors;
a first psychology participle prediction model determining unit, configured to use the first feature vector as input, use image psychology participles displayed by a work given by a psychoanalyst through analysis of topographic image data of the sand table work as output, and perform training by using a long-term and short-term memory network algorithm to obtain a first psychology participle prediction model;
the second characteristic vector determining unit is used for acquiring the characteristic vector of the sand table work for arranging the sand tool information data and recording the characteristic vector as a second characteristic vector;
a second psychology participle prediction model determining unit, configured to use the second feature vector as input, use an image psychology participle label, which is displayed by a work given by a psychologist through analysis of sand information data, as output, and perform training by using a machine learning method of a support vector machine to obtain a second psychology participle prediction model;
the third feature vector determining unit is used for acquiring a feature vector of the text description data in the sand table work and recording the feature vector as a third feature vector;
a third mental word segmentation prediction model determining unit, configured to use the first feature vector as input, use image mental word segmentation labels displayed by a work, which are given by a mental analyst through analysis of text description data, as output, and perform training by using a long-term and short-term memory network algorithm to obtain a third mental word segmentation prediction model;
the fourth feature vector determining unit is used for acquiring the feature vector of the voice description data in the sand table work and recording the feature vector as a third feature vector;
and the fourth psychological word segmentation prediction model determining unit is used for taking the first feature vector as input, taking image psychological word segmentation labels shown by works given by a psychological analyst through analysis of voice description data as output, and training by adopting a long-term and short-term memory network algorithm to obtain a fourth psychological word segmentation prediction model.
8. The psychology evaluation system according to claim 7, wherein the mental state prediction model determining module specifically comprises:
the collecting and integrating unit is used for collecting and integrating all the psychological word segmentation to obtain a psychological word segmentation feature vector;
the normalization unit is used for normalizing the psychological word segmentation feature vector to obtain a normalized feature vector;
and the psychological state prediction model determining unit is used for taking the normalized feature vector as input and the corresponding psychological state as output, and training by adopting a logistic regression method to obtain a psychological state prediction model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010564640.0A CN111524578B (en) | 2020-06-19 | 2020-06-19 | Psychological assessment device, method and system based on electronic psychological sand table |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010564640.0A CN111524578B (en) | 2020-06-19 | 2020-06-19 | Psychological assessment device, method and system based on electronic psychological sand table |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111524578A true CN111524578A (en) | 2020-08-11 |
| CN111524578B CN111524578B (en) | 2023-08-11 |
Family
ID=71909853
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010564640.0A Active CN111524578B (en) | 2020-06-19 | 2020-06-19 | Psychological assessment device, method and system based on electronic psychological sand table |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111524578B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111951922A (en) * | 2020-08-13 | 2020-11-17 | 李守龙心理科学技术(青岛)有限公司 | Report generation method of 3D psychological sand table system based on five-element and psychological image |
| CN112885432A (en) * | 2021-02-06 | 2021-06-01 | 北京色彩情绪健康科技发展有限公司 | Emotion analysis and management system |
| CN113436706A (en) * | 2021-07-01 | 2021-09-24 | 中国科学院自动化研究所 | Psychological state analysis system and method based on electronic psychological sand table and time sequence characteristics |
| CN114068030A (en) * | 2022-01-14 | 2022-02-18 | 中国科学院自动化研究所 | Sand table splitting topic identification system, method and equipment based on visual analysis |
| CN114120047A (en) * | 2022-01-26 | 2022-03-01 | 中国科学院自动化研究所 | Method, system and equipment for judging object connectivity based on visual analysis |
| CN118553381A (en) * | 2024-07-29 | 2024-08-27 | 中国科学院自动化研究所 | Intelligent psychological assessment system based on electronic sand table and operation method thereof |
| CN118553382A (en) * | 2024-07-29 | 2024-08-27 | 中国科学院自动化研究所 | Psychological sand table description method and device based on large language model |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8147251B1 (en) * | 2006-03-23 | 2012-04-03 | Anson Wendy C | Computer-aided psychological diagnosis and treatment system |
| CN107280693A (en) * | 2017-06-20 | 2017-10-24 | 国网技术学院 | Psychoanalysis System and method based on VR interactive electronic sand tables |
| 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 |
| RU2676969C1 (en) * | 2018-05-10 | 2019-01-11 | Федеральное государственное бюджетное образовательное учреждение высшего образования "Южно-Уральский государственный медицинский университет" Министерства здравоохранения Российской Федерации (ФГБОУ ВО ЮУГМУ Минздрава России) | Method of sand art diagnostics for the determination of nervo-mental disorders of child age |
| CN110279425A (en) * | 2019-05-09 | 2019-09-27 | 中国科学院自动化研究所 | Psychological assessment method and system based on intellectual analysis |
| CN110391013A (en) * | 2019-07-17 | 2019-10-29 | 北京智能工场科技有限公司 | A kind of system and device based on semantic vector building neural network prediction mental health |
| CN110916687A (en) * | 2019-11-07 | 2020-03-27 | 苏志强 | Virtual sand table psychological analysis processing method, storage medium and system |
| CN111161846A (en) * | 2019-12-06 | 2020-05-15 | 中国科学院自动化研究所 | Knowledge base construction and analysis method, device and equipment based on electronic psychological sand table |
-
2020
- 2020-06-19 CN CN202010564640.0A patent/CN111524578B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8147251B1 (en) * | 2006-03-23 | 2012-04-03 | Anson Wendy C | Computer-aided psychological diagnosis and treatment system |
| CN107280693A (en) * | 2017-06-20 | 2017-10-24 | 国网技术学院 | Psychoanalysis System and method based on VR interactive electronic sand tables |
| 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 |
| RU2676969C1 (en) * | 2018-05-10 | 2019-01-11 | Федеральное государственное бюджетное образовательное учреждение высшего образования "Южно-Уральский государственный медицинский университет" Министерства здравоохранения Российской Федерации (ФГБОУ ВО ЮУГМУ Минздрава России) | Method of sand art diagnostics for the determination of nervo-mental disorders of child age |
| CN110279425A (en) * | 2019-05-09 | 2019-09-27 | 中国科学院自动化研究所 | Psychological assessment method and system based on intellectual analysis |
| CN110391013A (en) * | 2019-07-17 | 2019-10-29 | 北京智能工场科技有限公司 | A kind of system and device based on semantic vector building neural network prediction mental health |
| CN110916687A (en) * | 2019-11-07 | 2020-03-27 | 苏志强 | Virtual sand table psychological analysis processing method, storage medium and system |
| CN111161846A (en) * | 2019-12-06 | 2020-05-15 | 中国科学院自动化研究所 | Knowledge base construction and analysis method, device and equipment based on electronic psychological sand table |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111951922A (en) * | 2020-08-13 | 2020-11-17 | 李守龙心理科学技术(青岛)有限公司 | Report generation method of 3D psychological sand table system based on five-element and psychological image |
| CN112885432A (en) * | 2021-02-06 | 2021-06-01 | 北京色彩情绪健康科技发展有限公司 | Emotion analysis and management system |
| CN113436706A (en) * | 2021-07-01 | 2021-09-24 | 中国科学院自动化研究所 | Psychological state analysis system and method based on electronic psychological sand table and time sequence characteristics |
| CN114068030A (en) * | 2022-01-14 | 2022-02-18 | 中国科学院自动化研究所 | Sand table splitting topic identification system, method and equipment based on visual analysis |
| CN114068030B (en) * | 2022-01-14 | 2022-04-26 | 中国科学院自动化研究所 | Sand table splitting topic identification system, method and equipment based on visual analysis |
| CN114120047A (en) * | 2022-01-26 | 2022-03-01 | 中国科学院自动化研究所 | Method, system and equipment for judging object connectivity based on visual analysis |
| CN114120047B (en) * | 2022-01-26 | 2022-04-08 | 中国科学院自动化研究所 | Method, system and equipment for judging object connectivity based on visual analysis |
| CN118553381A (en) * | 2024-07-29 | 2024-08-27 | 中国科学院自动化研究所 | Intelligent psychological assessment system based on electronic sand table and operation method thereof |
| CN118553382A (en) * | 2024-07-29 | 2024-08-27 | 中国科学院自动化研究所 | Psychological sand table description method and device based on large language model |
| CN118553382B (en) * | 2024-07-29 | 2024-12-06 | 中国科学院自动化研究所 | Psychological sand table description method and device based on large language model |
| CN118553381B (en) * | 2024-07-29 | 2024-12-06 | 中国科学院自动化研究所 | Intelligent psychological assessment system based on electronic sand table and operation method thereof |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111524578B (en) | 2023-08-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111524578B (en) | Psychological assessment device, method and system based on electronic psychological sand table | |
| CN110427463B (en) | Search statement response method and device, server and storage medium | |
| US10831769B2 (en) | Search method and device for asking type query based on deep question and answer | |
| CN118296132B (en) | Customer service searching method and system based on intelligent large model | |
| CN111145903B (en) | Method and device for acquiring vertigo inquiry text, electronic equipment and inquiry system | |
| CN109710931A (en) | A kind of class teaching content evaluation system and its method based on Intellectual Analysis Technology | |
| CN117407502A (en) | Question-answer pair extraction method and device, electronic equipment and storage medium | |
| CN116976321A (en) | Text processing method, apparatus, computer device, storage medium, and program product | |
| CN110298597A (en) | A kind of assessment method, device and storage medium | |
| Liu et al. | RoseMatcher: Identifying the impact of user reviews on app updates | |
| Boran et al. | Leveraging auxiliary image descriptions for dense video captioning | |
| CN120470179A (en) | An intelligent multidimensional retrieval system for course data based on deep learning | |
| CN114648981A (en) | Multi-dimensional evaluation system based on oral English examination | |
| CN114037571A (en) | Test question expansion method and related device, electronic equipment and storage medium | |
| CN117454217A (en) | A method, device and system for identifying depressive emotions based on deep integrated learning | |
| CN116910216A (en) | Intelligent question-answering system | |
| Depositario et al. | Automated Categorization of Research Papers with MONO Supervised Term Weighting in RECApp | |
| CN117993792B (en) | Classroom teaching mode construction method and system, electronic equipment and storage medium | |
| CN119090155A (en) | Adaptive learning content generation method for smart learning cloud platform | |
| CN119180274A (en) | Structural analysis and scoring method for academic papers | |
| CN114417001B (en) | Chinese writing intelligent analysis method, system and medium based on multimodal model | |
| CN109325096A (en) | A Knowledge Resource Search System Based on Knowledge Resource Classification | |
| CN114969564A (en) | Grading reading evaluation and recommendation method and system for books outside class of primary school | |
| CN119692823B (en) | Intelligent education teaching evaluation method, system and equipment | |
| CN112861536A (en) | Research learning ability portrayal method, device, computing equipment and storage medium |
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 |