CN115239527B - Teaching behavior analysis system based on knowledge base teaching feature fusion and modeling - Google Patents
Teaching behavior analysis system based on knowledge base teaching feature fusion and modeling Download PDFInfo
- Publication number
- CN115239527B CN115239527B CN202210829198.9A CN202210829198A CN115239527B CN 115239527 B CN115239527 B CN 115239527B CN 202210829198 A CN202210829198 A CN 202210829198A CN 115239527 B CN115239527 B CN 115239527B
- Authority
- CN
- China
- Prior art keywords
- teaching
- classroom
- module
- student
- analysis
- 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
- 238000004458 analytical method Methods 0.000 title claims abstract description 293
- 230000004927 fusion Effects 0.000 title claims abstract description 42
- 230000006399 behavior Effects 0.000 claims abstract description 82
- 238000000034 method Methods 0.000 claims abstract description 59
- 230000008569 process Effects 0.000 claims abstract description 54
- 238000000605 extraction Methods 0.000 claims abstract description 53
- 238000009411 base construction Methods 0.000 claims abstract description 10
- 238000013507 mapping Methods 0.000 claims abstract description 5
- 238000011156 evaluation Methods 0.000 claims description 77
- 230000008451 emotion Effects 0.000 claims description 43
- 230000014509 gene expression Effects 0.000 claims description 33
- 238000004422 calculation algorithm Methods 0.000 claims description 22
- 238000012512 characterization method Methods 0.000 claims description 17
- 230000003993 interaction Effects 0.000 claims description 14
- 238000010276 construction Methods 0.000 claims description 12
- 238000001514 detection method Methods 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 9
- 238000005070 sampling Methods 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 7
- 238000013441 quality evaluation Methods 0.000 claims description 6
- 230000008921 facial expression Effects 0.000 claims description 5
- 230000011218 segmentation Effects 0.000 claims description 5
- 230000004044 response Effects 0.000 claims description 4
- 238000007405 data analysis Methods 0.000 abstract description 2
- 230000036544 posture Effects 0.000 description 19
- 230000009286 beneficial effect Effects 0.000 description 11
- 230000000694 effects Effects 0.000 description 5
- 238000013210 evaluation model Methods 0.000 description 4
- 238000005065 mining Methods 0.000 description 4
- 241001282135 Poromitra oscitans Species 0.000 description 3
- 206010048232 Yawning Diseases 0.000 description 3
- 238000012098 association analyses Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 210000003414 extremity Anatomy 0.000 description 3
- 230000006872 improvement Effects 0.000 description 3
- 230000007935 neutral effect Effects 0.000 description 3
- 238000007621 cluster analysis Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000036651 mood Effects 0.000 description 2
- 238000007635 classification algorithm Methods 0.000 description 1
- 230000019771 cognition Effects 0.000 description 1
- 230000003930 cognitive ability Effects 0.000 description 1
- 238000013075 data extraction Methods 0.000 description 1
- 230000002996 emotional effect Effects 0.000 description 1
- 230000001815 facial effect Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000007786 learning performance Effects 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007670 refining Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000012916 structural analysis Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 210000001364 upper extremity Anatomy 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
- G06Q50/205—Education administration or guidance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06395—Quality analysis or management
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Educational Administration (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Educational Technology (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Operations Research (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Game Theory and Decision Science (AREA)
- General Health & Medical Sciences (AREA)
- Quality & Reliability (AREA)
- Artificial Intelligence (AREA)
- Primary Health Care (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Electrically Operated Instructional Devices (AREA)
Abstract
The invention relates to the technical field of intelligent teaching data analysis, in particular to a teaching behavior analysis system based on knowledge base teaching feature fusion and modeling, which comprises the following components: the data acquisition module is used for acquiring classroom teaching data and teaching resource data; the knowledge base construction module is used for constructing a multi-mode knowledge base according to classroom teaching data and teaching resource data; the feature extraction module is used for carrying out feature extraction on classroom teaching data according to the multi-mode knowledge base to generate a feature extraction result; the feature fusion module is used for carrying out feature mapping and fusion analysis on the feature extraction result to form a feature fusion result; and the modeling analysis module is used for modeling and analyzing the classroom behaviors according to the feature fusion result and the classroom behavior analysis model to form an analysis result. The teaching process can be comprehensively analyzed according to the classroom teaching data and the teaching resource data, and the classroom behaviors are analyzed, so that the teaching quality is improved.
Description
Technical Field
The invention relates to the technical field of intelligent teaching data analysis, in particular to a teaching behavior analysis system based on knowledge base teaching feature fusion and modeling.
Background
Education has been a focus of attention, and is closely related to every family, and in recent years, attention has been paid to education quality. The classroom is used as a main place for teachers to learn knowledge and students to learn knowledge, and is a space for interaction between teachers and students, and is a main channel for students to learn knowledge and explore knowledge. However, the assessment of the teaching quality of the classroom depends on the inspection of the teaching assessment group, the teaching quality of the teacher is assessed by the hearing of other teachers, the problems existing in the teaching process of the teacher are discovered, and the class-listening state of the students in the teaching process is analyzed, so that the teaching quality is assessed. However, the sampling is too small, a small amount of teaching data is used as evaluation data, the evaluation conclusion is provided with insufficient data support, the evaluation conclusion is distorted, and the practical applicability of the proposed teaching improvement suggestion is low; and the evaluation mode needs to consume a large amount of manpower and material resources, and has higher cost.
Disclosure of Invention
The invention provides a teaching behavior analysis system based on knowledge base teaching feature fusion and modeling, which can comprehensively analyze teaching process according to classroom teaching data and teaching resource data and analyze classroom behaviors, thereby being beneficial to improving teaching quality.
In order to achieve the above object, the basic scheme of the present invention is as follows:
The teaching behavior analysis system based on knowledge base teaching feature fusion and modeling is characterized in that: the system comprises a data acquisition module, a knowledge base construction module, a feature extraction module, a feature fusion module and a modeling analysis module;
The data acquisition module is used for acquiring classroom teaching data and teaching resource data;
the knowledge base construction module is used for constructing a multi-mode knowledge base according to classroom teaching data and teaching resource data;
the feature extraction module is used for carrying out feature extraction on classroom teaching data according to the multi-mode knowledge base to generate a feature extraction result;
The feature fusion module is used for carrying out feature mapping and fusion analysis on the feature extraction result to form a feature fusion result;
the modeling analysis module is used for modeling and analyzing the classroom behaviors according to the feature fusion result and the classroom behavior analysis model to form an analysis result.
The principle and the advantages of the invention are as follows: the teaching content in the classroom is extracted by acquiring the classroom teaching data and the teaching resource data, so that the comprehensive analysis and structure of the teaching process are facilitated. The modeling analysis module carries out modeling analysis on the classroom behaviors according to the feature fusion result and the classroom behavior analysis model and generates an analysis result, and compared with the teaching evaluation carried out by patrol of a teaching evaluation group, the modeling analysis module has the advantages of lower cost, higher efficiency and more comprehensive analysis.
Further, the classroom teaching data comprises classroom audio data and classroom video data; the multi-mode knowledge base comprises an image data set, a teaching corpus, a subject knowledge map and a subject study database;
The knowledge base construction module comprises:
the image data set construction module is used for sampling according to the classroom video data according to a preset sampling frequency, identifying and marking the classroom behaviors in the sampled image, and forming an image data set;
The corpus construction module is used for processing the classroom audio data through a voice recognition algorithm to form a teaching corpus;
The discipline knowledge graph construction module is used for establishing a discipline knowledge point front-back relation according to teaching resource data, completing fine-granularity modeling of discipline knowledge and forming a discipline knowledge graph;
And the examination question library construction module is used for forming an examination question library according to the teaching resource data.
The beneficial effects are that: and constructing a knowledge base according to the image data set constructed by the classroom teaching video and the teaching corpus constructed by the classroom audio data, the discipline knowledge graph and the scientific examination question base, so as to be beneficial to comprehensively analyzing and constructing the teaching.
Further, the feature extraction result comprises image features and voice features; the feature extraction module includes:
The image feature extraction module is used for extracting image features of both the teacher and the student through an image detection and identification algorithm; the image features comprise identity information, spatial position information, expression information, gesture information and behavior information;
and the voice characteristic extraction module is used for extracting voice characteristics of both a teacher and students in the classroom audio data through a voice processing algorithm.
The beneficial effects are that: the method comprises the steps of extracting image features and voice features of both the teacher and the student, and specifically comprises identity information, spatial position information, expression information, gesture information, behavior information and voice features of both the teacher and the student, so that comprehensive analysis of teaching conditions is facilitated, subsequent classroom quality analysis is facilitated, and targeted guidance is provided for teaching of the teacher.
Further, the voice features include voice characterization features and text semantic features, and the voice feature extraction module includes:
The voice characteristic feature extraction module is used for extracting voice characteristic features of teachers and students according to classroom audio data, wherein the voice characteristic features comprise speech speed features, volume features and tone features;
the text semantic feature extraction module is used for converting the classroom audio data into voice text data and extracting text semantic features of the voice text data, wherein the text semantic features comprise sentence segmentation information, entity identification information, phrase identification information and part-of-speech tagging information.
The beneficial effects are that: in the teaching process, the voice characterization features of teachers and students are extracted, the classroom audio data are converted into voice text data, and the text semantic features of the voice text data are extracted, so that the communication content and the communication atmosphere of the teachers and students in the teaching process can be fully mastered.
Further, the image characteristics of the teacher include teacher identity information, teacher position information, teacher expression information, teacher posture information, teacher behavior information and teacher track information; the voice characteristics of the teacher comprise characteristics of voice characterization of the teacher and semantic characteristics of text of the teacher;
The image features of the students comprise student identity information, student position information, student expression information, student posture information and student behavior information; the student's speech features include student speech characterization features and student text semantic features.
The beneficial effects are that: and the image characteristics of both the teacher and the student are fully extracted and analyzed, so that the states of both the teacher and the student can be mastered conveniently.
Further, the feature fusion module includes:
The multi-mode teaching emotion calculating module is used for calculating the comprehensive emotion state distribution trend of the students in the class according to the image characteristics and the voice characteristics of the teachers and the students;
And the multi-mode teaching process calculation module is used for matching the text semantic features of the teacher with the discipline knowledge patterns, analyzing the fore-and-aft relation of the knowledge points and correspondingly counting the image features and the voice features of the students in each time period of the classroom.
The beneficial effects are that: according to the image characteristics and the voice characteristics of teachers and students, the comprehensive emotion state distribution trend of the students in the class is calculated, so that emotion changes of the students in the teaching process can be known.
Further, the analysis results comprise learning state analysis results, the modeling analysis module comprises a student learning state analysis module, and the student learning state analysis module is used for generating learning state analysis results according to the image characteristics and the voice characteristics of the students;
The student learning state analysis module comprises:
the student emotion state analysis module is used for generating a student class emotion analysis result according to the statistical result of the student expression information;
the fatigue state analysis module is used for generating student classroom fatigue state analysis results according to the statistical results of student behavior information;
the sitting posture habit analysis module is used for generating a student classroom sitting posture habit analysis result according to the statistical result of the student posture information;
The participation degree analysis module is used for generating a student class participation degree analysis result according to the statistical result of the student text semantic features;
The concentration analysis module is used for generating a student classroom concentration analysis result according to the statistical result of the head orientation in the student posture information and the teacher track information;
The learning preference analysis module generates a student learning preference analysis result according to student class emotion analysis results, student class participation analysis results and student class concentration analysis results of students in classes of different disciplines;
The learning state analysis results comprise a student classroom emotion analysis result, a student classroom fatigue state analysis result, a student classroom sitting habit analysis result, a student classroom participation analysis result, a student classroom concentration analysis result and a student learning preference analysis result.
The beneficial effects are that: the learning state of the student is analyzed according to relatively comprehensive data extraction, and the learning state analysis method specifically comprises emotion state analysis, fatigue state analysis, sitting habit analysis, participation degree analysis, concentration degree analysis and learning preference analysis of the student, so that objective assessment of the learning state of the student is facilitated.
Further, the analysis result comprises a teaching state analysis result, the modeling analysis module further comprises a teacher teaching state analysis module, and the teacher teaching state analysis module is used for generating the teaching state analysis result according to the image characteristics and the voice characteristics of the teacher;
The teacher teaching state analysis module comprises:
The teacher emotion state analysis module is used for generating a teacher class emotion state analysis result according to the teacher expression information, the teacher voice characterization characteristics and the teacher gesture information;
The behavior pattern analysis module is used for generating a teacher behavior pattern analysis result according to the teacher posture information and the teacher track information;
the teaching mode analysis module is used for generating a teaching mode analysis result of the teacher according to the teacher behavior information and the student behavior information;
The teaching state analysis results comprise a teacher class emotion state analysis result, a teacher behavior mode analysis result and a teacher teaching mode analysis result.
The beneficial effects are that: according to the characteristic data of the teacher, the teaching state of the teacher is analyzed, and the teaching state analysis method specifically comprises the analysis of the teaching state of the teacher, the analysis of the behavior mode of the teacher and the analysis of the teaching mode of the teacher, so that the teaching state and the teaching habit of the teacher can be mastered, and the teaching quality of the teacher can be evaluated conveniently.
Further, the analysis result comprises a classroom teaching process analysis result, and the modeling analysis module further comprises a classroom teaching process analysis module, wherein the classroom teaching process analysis module is used for generating a classroom teaching process analysis result according to image characteristics and voice characteristics of teachers and students;
the classroom teaching process analysis module comprises:
the interaction participation analysis module is used for generating an interaction participation analysis result according to the student classroom participation analysis result;
The teaching concentration analysis module is used for generating a teaching concentration analysis result according to the student classroom concentration analysis result and the number of students;
The teaching progress analysis module is used for matching the text semantic features of the teacher with the discipline knowledge patterns, positioning the front-back relation of the high-frequency keywords of the lesson in the knowledge patterns, and analyzing to obtain a teaching progress analysis result;
The classroom teaching process analysis results comprise interaction participation analysis results, teaching concentration analysis results and teaching progress analysis results.
The beneficial effects are that: in the scheme, the teaching process of the classroom is analyzed, and the method specifically comprises interaction participation degree analysis, teaching concentration degree analysis and teaching progress analysis, so that the teaching process of the classroom is evaluated.
Further, the system also comprises a teaching evaluation module for generating a teaching evaluation result according to the analysis result;
The teaching evaluation module comprises a student learning ability evaluation module, a teacher teaching ability evaluation module and a classroom teaching quality evaluation module;
the student learning ability evaluation module is used for generating learning ability evaluation according to the learning state analysis result;
the teacher teaching ability evaluation module is used for generating teaching ability evaluation according to the teaching state analysis result;
the classroom teaching quality evaluation module is used for generating classroom teaching quality comprehensive evaluation according to analysis results of the classroom teaching process;
The teaching evaluation result comprises learning ability evaluation, teaching ability evaluation and classroom teaching quality comprehensive evaluation.
The beneficial effects are that: and according to the states of students and teachers in the teaching process and the teaching process of the classroom, assessment is made for teaching in the classroom, and decision basis is provided for improvement of teaching methods.
Drawings
Fig. 1 is a logic block diagram of a teaching behavior analysis system based on knowledge base teaching feature fusion and modeling in accordance with a first embodiment of the present invention.
Fig. 2 is a logic block diagram of a teaching behavior analysis system based on knowledge base teaching feature fusion and modeling in a second embodiment of the present invention.
Detailed Description
The following is a further detailed description of the embodiments:
Example 1:
Example 1 is substantially as shown in figure 1:
the teaching behavior analysis system based on knowledge base teaching feature fusion and modeling in the embodiment comprises a data acquisition module, a knowledge base construction module, a feature extraction module, a feature fusion module and a modeling analysis module.
The data acquisition module is used for acquiring classroom teaching data and teaching resource data; the classroom teaching data comprises classroom audio data and classroom video data; in this embodiment, the teaching resource data includes data such as a teaching plan and discipline data. The data acquisition module comprises a video data acquisition module, an image data acquisition module and an audio data acquisition module. In this embodiment, through the student way high definition digtal camera that highly is about 2 meters in classroom the place ahead blackboard both sides position installs the adapter additional to and the teacher way high definition digtal camera of the place installation of highly is about 2.2 meters in classroom directly behind, thereby can gather teacher and student's video and audio data, and then acquire more comprehensive classroom audio data and classroom video data.
The knowledge base construction module is used for constructing a multi-mode knowledge base according to classroom teaching data and teaching resource data; the multi-mode knowledge base in the embodiment comprises an image data set, a teaching corpus, a subject knowledge map and a subject study library;
the knowledge base construction module comprises:
the image data set construction module is used for sampling according to the classroom video data according to a preset sampling frequency, identifying and marking the classroom behaviors in the sampled image, and forming an image data set;
The corpus construction module is used for processing the classroom audio data through a voice recognition algorithm to form a teaching corpus;
The discipline knowledge graph construction module is used for establishing a discipline knowledge point front-back relation according to teaching resource data, completing fine-granularity modeling of discipline knowledge and forming a discipline knowledge graph;
And the examination question library construction module is used for forming an examination question library according to the teaching resource data.
Specifically, in this embodiment, an image dataset is built according to collected classroom video data at a sampling frequency of three seconds and one frame, and for typical classroom behaviors in each frame of image, such as hand lifting, standing, yawning, sleeping, mobile phone playing and other behaviors, target behaviors are manually marked by a marking tool; and converting the classroom audio data into text data through a voice recognition algorithm. Distinguishing teacher sound and student sound through tone recognition, and constructing a teaching corpus; establishing a discipline knowledge graph, establishing a relationship between the front and rear of knowledge points, completing the modeling of a discipline knowledge ontology, and providing a priori knowledge source for the analysis of the subsequent teaching process; and carrying out data tag management on the subject examination database according to knowledge points, difficulty, subject types, scores and the like, and constructing the subject examination database.
The feature extraction module is used for carrying out feature extraction on classroom teaching data according to the multi-mode knowledge base to generate a feature extraction result; the feature extraction result comprises image features and voice features; the feature extraction module comprises an image feature extraction module and a voice feature extraction module.
The image feature extraction module is used for extracting image features of both a teacher and a student through an image detection and identification algorithm; the image features comprise identity information, spatial position information, expression information, gesture information and behavior information, and correspondingly comprise an identity information extraction module, a spatial position information extraction module, an expression information extraction module, a gesture information extraction module and a behavior information extraction module.
The voice feature extraction module is used for extracting voice features of both a teacher and students in the classroom audio data through a voice processing algorithm. The voice feature comprises a voice characterization feature and a text semantic feature, and the voice feature extraction module comprises a voice characterization feature extraction module and a text semantic feature extraction module.
The voice characteristic feature extraction module is used for extracting voice characteristic features of teachers and students according to classroom audio data, wherein the voice characteristic features comprise speech speed features, volume features and tone features; the text semantic feature extraction module is used for converting classroom audio data into voice text data through a voice recognition algorithm, extracting text semantic features of the voice text data, wherein the text semantic features comprise sentence segmentation information, entity recognition information, phrase recognition information and part-of-speech tagging information.
In this embodiment, the image features of the teacher include teacher identity information, teacher position information, teacher expression information, teacher posture information, teacher behavior information, and teacher trajectory information; the voice characteristics of the teacher comprise characteristics of voice characterization of the teacher and semantic characteristics of text of the teacher; the image features of the students comprise student identity information, student position information, student expression information, student posture information and student behavior information; the student's speech features include student speech characterization features and student text semantic features.
Specifically, in this embodiment, by using a target detection and recognition algorithm, the process of recognizing the image features of the student in the class scene is as follows:
identifying student identity information by using a face detection and identification algorithm;
Positioning position information of students in a teaching space based on coordinate information of student identity information identification detection results, forming a position matrix R by taking the upper left corner of a classroom plane as an origin of coordinates, wherein the positions of the students are defined as M rows and N columns, and are recorded as R m,n; obtaining student position information;
on the basis of the face recognition step, student facial expression recognition is carried out to obtain student expression information, and class facial surface moods are classified into positive (positive, pleasant), neutral and negative (puzzled) moods;
Based on the face recognition step, 3D pose estimation of the head of the student is performed, and the three-dimensional deflection angle P x,y,z of the head of the student is calculated and calibrated so as to calculate the concentration area of the student later.
On the basis of the face recognition step, the posture of the trunk of the student is detected, 16 skeleton key points of the human body are recognized, 16 key points are marked according to the sequence of A-P, and a human trunk diagram is drawn to obtain student posture information;
On the basis of the face recognition step, typical behaviors of students, including but not limited to six behavior modes of hand lifting, standing, yawning, sleeping, reading and writing, are recognized.
The process of identifying the image features of the teacher in the class scene by using the target detection and identification algorithm is as follows:
using a face detection and recognition algorithm to identify and position the teacher in the initial position to obtain teacher identity information and teacher position information;
Carrying out expression recognition on teachers, and classifying the expression of the teachers into three types: selecting seven types of universal expression recognition methods to be used in positive, neutral and negative directions, and mapping the detected results into three types of final expression categories to be used as output results to obtain teacher expression information;
on the basis of face recognition, carrying out gesture detection on a teacher, identifying 16 key points of a human body, marking the 16 key points according to the sequence of A-P, and drawing a human body trunk graph to obtain teacher gesture information;
The teacher gesture information comprises teacher gesture information, and typical arm-holding, back-hand, waist-crossing and hand-lifting gestures are detected and identified on the basis of the steps, so that the teacher gesture information is further distinguished;
On the basis of face recognition, the position of a teacher in an image is abstracted into a point through a target tracking algorithm, and then projected to a two-dimensional plane under a overlooking view angle through perspective transformation, and an indoor walking track of the teacher is drawn to obtain teacher track information.
And carrying out relevant voice engineering and text content analysis processing on classroom audio data of teachers and students, wherein the process of extracting voice characteristics of both the teachers and the students in the classroom audio data is as follows:
Converting the collected classroom audio data into text data through voice recognition;
on the basis of the steps, teacher voice and student voice are distinguished through tone color recognition, and a classroom dialogue text is formed;
on the basis of the steps, collected classroom audio data are used for detecting voice characterization of a teacher, such as the speed, the volume, the tone level and the like, so as to obtain the voice characterization characteristics of the teacher and the voice characterization characteristics of students.
On the basis of the steps, sentence segmentation, entity recognition, phrase recognition, part-of-speech tagging and other information extraction are carried out on the recognized teaching voice text data, so that fine granularity structural analysis of teaching contents is realized, and teacher text semantic features and student text semantic features are obtained.
The feature fusion module is used for carrying out feature mapping and fusion analysis on the feature extraction result to form a feature fusion result;
the feature fusion module comprises:
The multi-mode teaching emotion calculating module is used for calculating the comprehensive emotion state distribution trend of the students in the class according to the image characteristics and the voice characteristics of the teachers and the students;
And the multi-mode teaching process calculation module is used for matching the text semantic features of the teacher with the discipline knowledge patterns, analyzing the fore-and-aft relation of the knowledge points and correspondingly counting the image features and the voice features of the students in each time period of the classroom.
The data of different modes has different importance and significance for researching teaching process behaviors, and after the heterogeneous data acquired by different information sources are converted into structured data from unstructured data, data synchronization and feature fusion analysis are performed on the basis of feature extraction;
In the embodiment, the multi-mode teaching emotion calculating module calculates the comprehensive emotion state distribution trend of the student class by integrating the facial expression characteristics and limb expressions (gesture characteristic detection) of the teachers and students and the voice emotion characteristic recognition result and the distribution rule of three expression indexes; the multi-mode teaching process calculation module disassembles the classroom teaching according to the equal time period, performs keyword analysis on teaching contents of teachers in the time period by taking the time period as a unit, matches the teaching contents with knowledge points in the knowledge graph, analyzes the fore-and-aft relation of the knowledge points, and correspondingly counts the number of positive behaviors and negative behaviors of students in the time period, and response time (student mixed sound) and response contents (student individual sound) of the student audio data.
And the modeling analysis module is used for modeling and analyzing the classroom behaviors according to the feature fusion result and the classroom behavior analysis model to form an analysis result. By modeling and analyzing teaching behavior. From three dimensions of a learner, a learner and a teaching group, through defining indexes such as emotion states, fatigue states, sitting habits, participation, concentration, learning preference, teacher emotion, teacher behavior mode, teaching progress and the like, learning behavior analysis based on teaching scenes is performed.
The analysis results comprise learning state analysis results, teaching state analysis results and classroom teaching process analysis results, and the modeling analysis module comprises a student learning state analysis module, a teacher teaching state analysis module and a classroom teaching process analysis module.
The student learning state analysis module is used for generating a learning state analysis result according to the image characteristics and the voice characteristics of the students; the student learning state analysis module comprises:
the student emotion state analysis module is used for generating a student class emotion analysis result according to the statistical result of the student expression information;
the fatigue state analysis module is used for generating student classroom fatigue state analysis results according to the statistical results of student behavior information;
the sitting posture habit analysis module is used for generating a student classroom sitting posture habit analysis result according to the statistical result of the student posture information;
The participation degree analysis module is used for generating a student class participation degree analysis result according to the statistical result of the student text semantic features;
The concentration analysis module is used for generating a student classroom concentration analysis result according to the statistical result of the head orientation in the student posture information and the teacher track information;
The learning preference analysis module generates a student learning preference analysis result according to student class emotion analysis results, student class participation analysis results and student class concentration analysis results of students in classes of different disciplines;
The learning state analysis results comprise a student classroom emotion analysis result, a student classroom fatigue state analysis result, a student classroom sitting habit analysis result, a student classroom participation analysis result, a student classroom concentration analysis result and a student learning preference analysis result.
In this embodiment, for student dimensions, modeling and analysis of student classroom behaviors are completed from six indexes of emotion state, fatigue state, sitting habit, participation, concentration and learning preference, and specific calculation modes and processes are as follows:
The emotional state is mainly defined from the fluctuation trend of the facial expression of the students;
The fatigue state is defined by the recognition and statistics times of negative behaviors such as yawning, lying on a desk and the like of students;
sitting habits are defined from the straightness of limb detection;
the engagement is defined from how frequently students engage in teacher class teaching activities. Participation= (student audio interaction duration U student active image frame number 3 seconds)/percentage of classroom duration;
Concentration is defined from student concentration area distribution. And according to the calculation of the orientation and posture angles of the heads of the students, the students are projected to a teaching area in front of the classrooms and a teacher track walking area, and the teaching area and the teacher track walking area are regarded as the attention projection area of the students. Concentration= (number of image frames meeting the attention projection area x 3 seconds)/percentage of classroom time;
The learning preference is used for carrying out difference comparison on the classroom performances among the subjects of the students from three dimensions of the emotion state, participation degree and concentration degree of the students church nave class.
The teacher teaching state analysis module is used for generating teaching state analysis results according to the image characteristics and the voice characteristics of the teacher; the teacher teaching state analysis module comprises:
The teacher emotion state analysis module is used for generating a teacher class emotion state analysis result according to the teacher expression information, the teacher voice characterization characteristics and the teacher gesture information;
The behavior pattern analysis module is used for generating a teacher behavior pattern analysis result according to the teacher posture information and the teacher track information;
the teaching mode analysis module is used for generating a teaching mode analysis result of the teacher according to the teacher behavior information and the student behavior information;
The teaching state analysis results comprise a teacher class emotion state analysis result, a teacher behavior mode analysis result and a teacher teaching mode analysis result.
In this embodiment, after feature extraction is performed for expressions, postures, behaviors and the like in the teaching process of a teacher, personal teaching habit analysis is performed, and the method mainly includes emotion analysis, behavior pattern analysis and teaching pattern analysis of the teacher, and specific analysis modes and processes are as follows:
Obtaining the comprehensive emotion state distribution of the teacher in the class according to the classification standards of the positive, neutral and negative from three dimensions of the facial expression, the voice emotion and the limb expression of the teacher;
observing the habit gestures (arm holding, back hand, waist forking and hand lifting) of the teacher through the detection of the gestures of the upper limbs of the teacher, and carrying out behavior pattern analysis of the teacher by combining the indoor walking track;
Based on an S-T teaching analysis method, sampling the T behaviors of a teacher and the S behaviors of students at fixed intervals, drawing an S-T graph, calculating index data Rt and Ch values according to a calculation model, wherein the Rt values reflect the activity proportion of the teacher, and the Ch values reflect the interaction proportion of the teacher and the students, so that a teaching mode analysis graph of the teacher is obtained. The teaching modes of teachers are classified into practice type, teaching type, dialogue type and hybrid type.
The classroom teaching process analysis module is used for generating a classroom teaching process analysis result according to the image characteristics and the voice characteristics of teachers and students; the classroom teaching process analysis module comprises:
the interaction participation analysis module is used for generating an interaction participation analysis result according to the student classroom participation analysis result;
The teaching concentration analysis module is used for generating a teaching concentration analysis result according to the student classroom concentration analysis result and the number of students;
The teaching progress analysis module is used for matching the text semantic features of the teacher with the discipline knowledge patterns, positioning the front-back relation of the high-frequency keywords of the lesson in the knowledge patterns, and analyzing to obtain a teaching progress analysis result;
The classroom teaching process analysis results comprise interaction participation analysis results, teaching concentration analysis results and teaching progress analysis results.
In this embodiment, for a classroom teacher and student group, the whole classroom teaching process is analyzed from the aspects of teaching participation, teaching concentration, teaching progress and the like, and the specific analysis mode and process are as follows:
The teaching participation is defined from the frequency with which students participate in teacher class teaching activities. Participation= (student audio interaction duration U student active image frame number 3 seconds)/percentage of classroom duration;
Teaching focus is defined from student attention area distribution. And according to the calculation of the orientation and posture angles of the heads of the students, the students are projected to a teaching area in front of the classrooms and a teacher track walking area, and the teaching area and the teacher track walking area are regarded as the attention projection area of the students. Concentration= (number of students per single frame of student meeting the concentration projection area/total number of students 3 seconds)/percentage of classroom time;
Aiming at teaching audio, after information extraction such as word segmentation, entity recognition, phrase recognition, part-of-speech tagging and the like is carried out on teaching audio text data subjected to speech recognition, the teaching audio text data is matched with entities in a subject knowledge graph by taking knowledge points as units, the front-back relation of the high-frequency keywords of the class in the knowledge graph is positioned, and then the teaching progress is analyzed.
Example 2:
As shown in fig. 2, the difference between embodiment 2 and embodiment 1 is that in this embodiment, the system further includes a teaching evaluation module, configured to generate a teaching evaluation result according to the analysis result;
The teaching evaluation module comprises a student learning ability evaluation module, a teacher teaching ability evaluation module and a classroom teaching quality evaluation module;
The student learning ability evaluation module is used for generating learning ability evaluation according to the learning state analysis result;
The teacher teaching ability evaluation module is used for generating teaching ability evaluation according to the teaching state analysis result;
The classroom teaching quality evaluation module is used for generating classroom teaching quality comprehensive evaluation according to analysis results of the classroom teaching process;
The teaching evaluation result comprises learning ability evaluation, teaching ability evaluation and classroom teaching quality comprehensive evaluation.
Specifically, according to each analysis result in the learning state analysis results, each analysis result in the teaching state analysis results and each analysis result in the classroom teaching process analysis results respectively, generating learning ability evaluation, teaching ability evaluation and classroom teaching quality comprehensive evaluation, wherein each analysis result in the learning state analysis results, each analysis result in the teaching state analysis results and each analysis result in the classroom teaching process analysis results are respectively used as input of an input layer in each model, and the learning ability evaluation, the teaching ability evaluation and the classroom teaching quality comprehensive evaluation are respectively used as output of an output layer in each model. The specific implementation mode is a student voice recognition module.
Example 3:
Embodiment 3 has the same basic principle as embodiment 2, and is different in that the teaching evaluation module in embodiment 3 performs AI evaluation of the teaching process by using an AI domain algorithm, including but not limited to a classification algorithm, regression prediction, a clustering algorithm, relation mining, text mining, and the like, and specifically includes the following steps.
1.1, Evaluating learning ability of students, including classroom understanding evaluation, knowledge mastery evaluation, and carrying out classroom performance and score association analysis in combination with stage evaluation;
1.1.1 learning effects depend on understanding the classroom content, namely understanding the ability of the internal relation of discipline knowledge, namely, the assessment of understanding ability is the assessment of the ability;
1.1.1.1 first, establishing a subject understanding force expression standard, wherein the expression standard comprises three parts of contents including a target dimension, a learning target and an index description; in the teaching process, the evaluation should be performed in high conformity with the teaching target. Therefore, the design of the teaching target in class is accurate and specific, has observability, operability and detectability, and is used as an evaluation model according to the design understanding force so as to carry out multiple evaluation on students;
1.1.1.2 establishing an understanding force grade evaluation model based on the 1.1.1.1 discipline understanding force expression standard, and implementing the understanding force evaluation; in the reference type rating based on the standard, the reference standard is not a specific normal mode, is not a 60-point passing standard, but is a specific index description of the subject comprehension performance standard in 1.1.1.1;
The assessment model is divided into five classes: H. s, N, B, L;
Model level interpretation:
h: above standard level, the student answers beyond basic standards or exhibit advanced knowledge and skills, etc.;
s: reaching the standard, the student's performance meets the requirements specified by the capability performance standard;
N: near reaching the standard, the student's performance almost but not entirely meets the performance criteria;
b: below the standard level, the student's performance is clearly out of compliance with the performance criteria;
l: no achievement exists, and the students do not have knowledge and skills required by the ability expression standard at all;
1.1.2 according to the cognitive ability model, five grades of knowledge mastery degree are used for describing the assessment of the student's discipline knowledge mastery degree; the five levels of cognition are divided into knowledge, familiarity, proficiency, and expertise;
1.1.3, through 1.1.1 to the understanding force of student class and 1.1.2 to the establishment of the knowledge mastery model of student class discipline knowledge, synthesize 5.1 to the analysis of the appearance of the learning state of student class, carry on the comprehensive evaluation of student's learning ability;
1.1.3.1 inputting student stage test results, carrying out data association analysis on daily learning performance and learning results of students by using an association analysis algorithm, mining and finding key association factors, and providing data support and basis for specific implementation of teaching in accordance with the material;
1.1.3.2 carrying out clustering analysis on the evaluation data generated by the subitem evaluation model by utilizing a clustering algorithm to find out a class performance rule and mainly analyzing outlier data;
1.2, teacher teaching ability evaluation, including teaching ability evaluation, teaching style evaluation and the like;
1.2.1, establishing a teacher capability model and an evaluation method, refining the evaluation method into specific indexes, and carrying out teacher teaching capability evaluation according to the capability evaluation model through data acquisition and analysis of the indexes in the teaching process;
1.2.2, performing cluster analysis on index data collected in a teacher teaching process by using a big data statistical analysis algorithm, and mining teaching style trend of a teacher group to provide reference data support for defining teaching styles;
1.3 comprehensive evaluation of classroom teaching quality, including teaching and learning matching degree evaluation, teacher teaching mode individual difference evaluation, discipline cross evaluation, grade cross evaluation and other contents;
1.3.1 assessment of teaching matching degree, based on the personal teaching style and teaching ability of a teacher and the individuality style of a student, carrying out assessment of teaching matching degree between the teacher and the student, and using the assessment of teaching matching degree as a reference basis for class division in a school to promote individualized talent cultivation;
1.3.2, based on the personal teaching style and teaching ability data results of teachers, applying a cluster analysis algorithm to mine teaching rules of excellent teachers among teacher groups, and providing data references for excellent teacher culture;
1.3.3 cross analysis and evaluation of the horizontal discipline teaching quality between the disciplines of the same year of the first education;
1.3.4 longitudinal scientific and teaching quality cross analysis and evaluation are performed between subjects of different grades in schools.
The foregoing is merely exemplary of the present application, and specific structures and features well known in the art will not be described in detail herein, so that those skilled in the art will be aware of all the prior art to which the present application pertains, and will be able to ascertain the general knowledge of the technical field in the application or prior art, and will not be able to ascertain the general knowledge of the technical field in the prior art, without using the prior art, to practice the present application, with the aid of the present application, to ascertain the general knowledge of the same general knowledge of the technical field in general purpose. It should be noted that modifications and improvements can be made by those skilled in the art without departing from the structure of the present application, and these should also be considered as the scope of the present application, which does not affect the effect of the implementation of the present application and the utility of the patent. The protection scope of the present application is subject to the content of the claims, and the description of the specific embodiments and the like in the specification can be used for explaining the content of the claims.
Claims (9)
1. The teaching behavior analysis system based on knowledge base teaching feature fusion and modeling is characterized in that: the system comprises a data acquisition module, a knowledge base construction module, a feature extraction module, a feature fusion module and a modeling analysis module;
The data acquisition module is used for acquiring classroom teaching data and teaching resource data;
the knowledge base construction module is used for constructing a multi-mode knowledge base according to classroom teaching data and teaching resource data;
the feature extraction module is used for carrying out feature extraction on classroom teaching data according to the multi-mode knowledge base to generate a feature extraction result;
The feature fusion module is used for carrying out feature mapping and fusion analysis on the feature extraction result to form a feature fusion result;
The modeling analysis module is used for modeling and analyzing the classroom behaviors according to the feature fusion result and the classroom behavior analysis model to form an analysis result;
The feature fusion module comprises:
The multi-mode teaching emotion calculating module is used for calculating the comprehensive emotion state distribution trend of the students in the class according to the image characteristics and the voice characteristics of the teachers and the students;
The multi-mode teaching process calculation module is used for matching the text semantic features of the teacher with the discipline knowledge patterns, analyzing the front-back sequence relation of the knowledge points and correspondingly counting the image features and the voice features of the students in each time period of the classroom;
The multi-mode teaching emotion calculating module calculates the comprehensive emotion state distribution trend of the student class through integrating the facial expression characteristics, limb expressions and voice emotion characteristic recognition results and the distribution rules of three expression indexes; the multi-mode teaching process calculation module disassembles the classroom teaching according to the equal time period, analyzes keywords of teaching contents of teachers in the time period by taking the time period as a unit, matches the teaching contents with knowledge points in a knowledge graph, analyzes the front-back sequence relation of the knowledge points, and correspondingly counts the number of positive behaviors and negative behaviors of students in the time period, and the response time length and the response content of audio data of the students;
The modeling analysis module comprises a student learning state analysis module, a teacher teaching state analysis module and a classroom teaching process analysis module;
the student learning state analysis module is used for generating a learning state analysis result according to the image characteristics and the voice characteristics of the students;
the teacher teaching state analysis module is used for generating teaching state analysis results according to the image characteristics and the voice characteristics of the teacher;
The classroom teaching process analysis module is used for generating classroom teaching process analysis results according to the image characteristics and the voice characteristics of teachers and students.
2. The knowledge base based teaching feature fusion and modeling teaching behavior analysis system of claim 1, wherein: the classroom teaching data comprises classroom audio data and classroom video data; the multi-mode knowledge base comprises an image data set, a teaching corpus, a subject knowledge map and a subject study database;
The knowledge base construction module comprises:
the image data set construction module is used for sampling according to the classroom video data according to a preset sampling frequency, identifying and marking the classroom behaviors in the sampled image, and forming an image data set;
The corpus construction module is used for processing the classroom audio data through a voice recognition algorithm to form a teaching corpus;
The discipline knowledge graph construction module is used for establishing a discipline knowledge point front-back relation according to teaching resource data, completing fine-granularity modeling of discipline knowledge and forming a discipline knowledge graph;
And the examination question library construction module is used for forming an examination question library according to the teaching resource data.
3. The knowledge base based teaching feature fusion and modeling teaching behavior analysis system of claim 2, wherein: the feature extraction result comprises image features and voice features; the feature extraction module includes:
The image feature extraction module is used for extracting image features of both the teacher and the student through an image detection and identification algorithm; the image features comprise identity information, spatial position information, expression information, gesture information and behavior information;
and the voice characteristic extraction module is used for extracting voice characteristics of both a teacher and students in the classroom audio data through a voice processing algorithm.
4. A knowledge base based teaching feature fusion and modeling teaching behavior analysis system as claimed in claim 3, wherein: the voice feature comprises a voice characterization feature and a text semantic feature, and the voice feature extraction module comprises:
The voice characteristic feature extraction module is used for extracting voice characteristic features of teachers and students according to classroom audio data, wherein the voice characteristic features comprise speech speed features, volume features and tone features;
the text semantic feature extraction module is used for converting the classroom audio data into voice text data and extracting text semantic features of the voice text data, wherein the text semantic features comprise sentence segmentation information, entity identification information, phrase identification information and part-of-speech tagging information.
5. The knowledge base based teaching feature fusion and modeling teaching behavior analysis system of claim 4, wherein: the image features of the teacher comprise teacher identity information, teacher position information, teacher expression information, teacher posture information, teacher behavior information and teacher track information; the voice characteristics of the teacher comprise characteristics of voice characterization of the teacher and semantic characteristics of text of the teacher;
The image features of the students comprise student identity information, student position information, student expression information, student posture information and student behavior information; the student's speech features include student speech characterization features and student text semantic features.
6. The knowledge base based teaching feature fusion and modeling teaching behavior analysis system of claim 5, wherein: the analysis result comprises a learning state analysis result;
The student learning state analysis module comprises:
the student emotion state analysis module is used for generating a student class emotion analysis result according to the statistical result of the student expression information;
the fatigue state analysis module is used for generating student classroom fatigue state analysis results according to the statistical results of student behavior information;
the sitting posture habit analysis module is used for generating a student classroom sitting posture habit analysis result according to the statistical result of the student posture information;
The participation degree analysis module is used for generating a student class participation degree analysis result according to the statistical result of the student text semantic features;
The concentration analysis module is used for generating a student classroom concentration analysis result according to the statistical result of the head orientation in the student posture information and the teacher track information;
The learning preference analysis module generates a student learning preference analysis result according to student class emotion analysis results, student class participation analysis results and student class concentration analysis results of students in classes of different disciplines;
The learning state analysis results comprise a student classroom emotion analysis result, a student classroom fatigue state analysis result, a student classroom sitting habit analysis result, a student classroom participation analysis result, a student classroom concentration analysis result and a student learning preference analysis result.
7. The knowledge base based teaching feature fusion and modeling teaching behavior analysis system of claim 6, wherein: the analysis result comprises a teaching state analysis result;
The teacher teaching state analysis module comprises:
The teacher emotion state analysis module is used for generating a teacher class emotion state analysis result according to the teacher expression information, the teacher voice characterization characteristics and the teacher gesture information;
The behavior pattern analysis module is used for generating a teacher behavior pattern analysis result according to the teacher posture information and the teacher track information;
the teaching mode analysis module is used for generating a teaching mode analysis result of the teacher according to the teacher behavior information and the student behavior information;
The teaching state analysis results comprise a teacher class emotion state analysis result, a teacher behavior mode analysis result and a teacher teaching mode analysis result.
8. The knowledge base based teaching feature fusion and modeling teaching behavior analysis system of claim 7, wherein: the analysis result comprises a classroom teaching process analysis result;
the classroom teaching process analysis module comprises:
the interaction participation analysis module is used for generating an interaction participation analysis result according to the student classroom participation analysis result;
The teaching concentration analysis module is used for generating a teaching concentration analysis result according to the student classroom concentration analysis result and the number of students;
The teaching progress analysis module is used for matching the text semantic features of the teacher with the discipline knowledge patterns, positioning the front-back relation of the high-frequency keywords of the lesson in the knowledge patterns, and analyzing to obtain a teaching progress analysis result;
The classroom teaching process analysis results comprise interaction participation analysis results, teaching concentration analysis results and teaching progress analysis results.
9. The knowledge base based teaching feature fusion and modeling teaching behavior analysis system of claim 8, wherein: the teaching evaluation module is used for generating a teaching evaluation result according to the analysis result;
The teaching evaluation module comprises a student learning ability evaluation module, a teacher teaching ability evaluation module and a classroom teaching quality evaluation module;
the student learning ability evaluation module is used for generating learning ability evaluation according to the learning state analysis result;
the teacher teaching ability evaluation module is used for generating teaching ability evaluation according to the teaching state analysis result;
the classroom teaching quality evaluation module is used for generating classroom teaching quality comprehensive evaluation according to analysis results of the classroom teaching process;
The teaching evaluation result comprises learning ability evaluation, teaching ability evaluation and classroom teaching quality comprehensive evaluation.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210829198.9A CN115239527B (en) | 2022-06-27 | 2022-06-27 | Teaching behavior analysis system based on knowledge base teaching feature fusion and modeling |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210829198.9A CN115239527B (en) | 2022-06-27 | 2022-06-27 | Teaching behavior analysis system based on knowledge base teaching feature fusion and modeling |
Publications (2)
Publication Number | Publication Date |
---|---|
CN115239527A CN115239527A (en) | 2022-10-25 |
CN115239527B true CN115239527B (en) | 2024-05-07 |
Family
ID=83672724
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210829198.9A Active CN115239527B (en) | 2022-06-27 | 2022-06-27 | Teaching behavior analysis system based on knowledge base teaching feature fusion and modeling |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115239527B (en) |
Families Citing this family (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115909152B (en) * | 2022-11-16 | 2023-08-29 | 北京师范大学 | Intelligent teaching scene analysis system based on group behaviors |
CN115984956B (en) * | 2022-12-16 | 2023-08-29 | 北京师范大学 | Multi-mode visual analysis system for class investment of students through man-machine cooperation |
CN115936944B (en) * | 2023-01-31 | 2023-10-13 | 西昌学院 | Virtual teaching management method and device based on artificial intelligence |
CN116523371A (en) * | 2023-03-23 | 2023-08-01 | 华南师范大学 | Teaching language specification level analysis method, system, device and medium |
CN117152688A (en) * | 2023-10-31 | 2023-12-01 | 江西拓世智能科技股份有限公司 | Intelligent classroom behavior analysis method and system based on artificial intelligence |
CN117557008B (en) * | 2024-01-11 | 2024-03-29 | 深圳市博安智控科技有限公司 | Intelligent education scheme pushing method and system based on user characteristics |
CN117994098A (en) * | 2024-03-05 | 2024-05-07 | 江苏薪传科技有限公司 | Teaching index data determining method, device, computer equipment and medium |
CN118138794A (en) * | 2024-05-08 | 2024-06-04 | 深圳市科路教育科技有限公司 | Mobile network-based teaching video live broadcast control method |
Citations (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106874477A (en) * | 2017-02-17 | 2017-06-20 | 重庆市科学技术研究院 | The shared tutoring system of one kind composition material and its composition material sharing method |
CN107609478A (en) * | 2017-08-09 | 2018-01-19 | 广州思涵信息科技有限公司 | A kind of real-time analysis of the students system and method for matching classroom knowledge content |
CN108228655A (en) * | 2016-12-21 | 2018-06-29 | 青岛祥智电子技术有限公司 | A kind of preposition processing method of text emotion analysis signature verification |
CN109345104A (en) * | 2018-09-25 | 2019-02-15 | 博跃恒民康(深圳)智能化科技有限公司 | A kind of user capability method for improving, system and storage medium |
CN110334610A (en) * | 2019-06-14 | 2019-10-15 | 华中师范大学 | A kind of various dimensions classroom based on computer vision quantization system and method |
CN110443733A (en) * | 2019-08-05 | 2019-11-12 | 衡阳师范学院 | A kind of psychology vocational ability evaluation system |
CN110992741A (en) * | 2019-11-15 | 2020-04-10 | 深圳算子科技有限公司 | Learning auxiliary method and system based on classroom emotion and behavior analysis |
CN111027486A (en) * | 2019-12-11 | 2020-04-17 | 李思娴 | Auxiliary analysis and evaluation system and method for big data of teaching effect of primary and secondary school classroom |
CN111046823A (en) * | 2019-12-19 | 2020-04-21 | 东南大学 | Student classroom participation degree analysis system based on classroom video |
CN112487949A (en) * | 2020-11-27 | 2021-03-12 | 华中师范大学 | Learner behavior identification method based on multi-modal data fusion |
CN112766173A (en) * | 2021-01-21 | 2021-05-07 | 福建天泉教育科技有限公司 | Multi-mode emotion analysis method and system based on AI deep learning |
CN112989968A (en) * | 2021-02-26 | 2021-06-18 | 深圳市爱云信息科技有限公司 | Intelligent education AIOT AI intelligent brain analysis platform and device |
CN113592251A (en) * | 2021-07-12 | 2021-11-02 | 北京师范大学 | Multi-mode integrated teaching state analysis system |
US11281945B1 (en) * | 2021-02-26 | 2022-03-22 | Institute Of Automation, Chinese Academy Of Sciences | Multimodal dimensional emotion recognition method |
CN114582372A (en) * | 2022-03-03 | 2022-06-03 | 广州大学 | Multi-mode driver emotional feature recognition method and system |
CN114596619A (en) * | 2022-05-09 | 2022-06-07 | 深圳市鹰瞳智能技术有限公司 | Emotion analysis method, device and equipment based on video stream and storage medium |
-
2022
- 2022-06-27 CN CN202210829198.9A patent/CN115239527B/en active Active
Patent Citations (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108228655A (en) * | 2016-12-21 | 2018-06-29 | 青岛祥智电子技术有限公司 | A kind of preposition processing method of text emotion analysis signature verification |
CN106874477A (en) * | 2017-02-17 | 2017-06-20 | 重庆市科学技术研究院 | The shared tutoring system of one kind composition material and its composition material sharing method |
CN107609478A (en) * | 2017-08-09 | 2018-01-19 | 广州思涵信息科技有限公司 | A kind of real-time analysis of the students system and method for matching classroom knowledge content |
CN109345104A (en) * | 2018-09-25 | 2019-02-15 | 博跃恒民康(深圳)智能化科技有限公司 | A kind of user capability method for improving, system and storage medium |
CN110334610A (en) * | 2019-06-14 | 2019-10-15 | 华中师范大学 | A kind of various dimensions classroom based on computer vision quantization system and method |
CN110443733A (en) * | 2019-08-05 | 2019-11-12 | 衡阳师范学院 | A kind of psychology vocational ability evaluation system |
CN110992741A (en) * | 2019-11-15 | 2020-04-10 | 深圳算子科技有限公司 | Learning auxiliary method and system based on classroom emotion and behavior analysis |
CN111027486A (en) * | 2019-12-11 | 2020-04-17 | 李思娴 | Auxiliary analysis and evaluation system and method for big data of teaching effect of primary and secondary school classroom |
CN111046823A (en) * | 2019-12-19 | 2020-04-21 | 东南大学 | Student classroom participation degree analysis system based on classroom video |
CN112487949A (en) * | 2020-11-27 | 2021-03-12 | 华中师范大学 | Learner behavior identification method based on multi-modal data fusion |
CN112766173A (en) * | 2021-01-21 | 2021-05-07 | 福建天泉教育科技有限公司 | Multi-mode emotion analysis method and system based on AI deep learning |
CN112989968A (en) * | 2021-02-26 | 2021-06-18 | 深圳市爱云信息科技有限公司 | Intelligent education AIOT AI intelligent brain analysis platform and device |
US11281945B1 (en) * | 2021-02-26 | 2022-03-22 | Institute Of Automation, Chinese Academy Of Sciences | Multimodal dimensional emotion recognition method |
CN113592251A (en) * | 2021-07-12 | 2021-11-02 | 北京师范大学 | Multi-mode integrated teaching state analysis system |
CN114582372A (en) * | 2022-03-03 | 2022-06-03 | 广州大学 | Multi-mode driver emotional feature recognition method and system |
CN114596619A (en) * | 2022-05-09 | 2022-06-07 | 深圳市鹰瞳智能技术有限公司 | Emotion analysis method, device and equipment based on video stream and storage medium |
Non-Patent Citations (3)
Title |
---|
Multimodal Sentiment Intensity Analysis in Videos: Facial Gestures and Verbal Messages;Amir Zadeh 等;《IEEE Intelligent Systems》;20161231;第31卷(第6期);第82-88页 * |
基于多模态生物电信号的情绪识别方法研究;刘勇;《中国优秀硕士学位论文全文数据库信息科技辑》;20220215(第2期);第I136-91页 * |
迁移教学模式在初中人工智能课程中的研究;鲁思炜;《中国优秀硕士学位论文全文数据库 社会科学Ⅱ辑》;20210915(第9期);第H130-946页 * |
Also Published As
Publication number | Publication date |
---|---|
CN115239527A (en) | 2022-10-25 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN115239527B (en) | Teaching behavior analysis system based on knowledge base teaching feature fusion and modeling | |
CN110992741B (en) | Learning auxiliary method and system based on classroom emotion and behavior analysis | |
CN111027865B (en) | Teaching analysis and quality assessment system and method based on behavior and expression recognition | |
CN112908355B (en) | System and method for quantitatively evaluating teaching skills of teacher and teacher | |
CN112163162A (en) | Portrait recognition-based selected course recommendation method, storage medium and electronic equipment | |
CN113627779A (en) | Teaching management and quality evaluation system based on big data and AI technology | |
Munoz et al. | Development of a software that supports multimodal learning analytics: A case study on oral presentations | |
Quan | Development of computer aided classroom teaching system based on machine learning prediction and artificial intelligence KNN algorithm | |
CN110956142A (en) | Intelligent interactive training system | |
CN116050892A (en) | Intelligent education evaluation supervision method based on artificial intelligence | |
Zhao et al. | A study on posture-based teacher-student behavioral engagement pattern | |
Mohammad et al. | Clustering of slow learners behavior for discovery of optimal patterns of learning | |
WO2023019652A1 (en) | Method and system for constructing classroom teaching behavior event description model | |
CN116226410B (en) | Teaching evaluation and feedback method and system for knowledge element connection learner state | |
CN111563697A (en) | Online classroom student emotion analysis method and system | |
Chai et al. | SignInstructor: an effective tool for sign language vocabulary learning | |
CN115689340A (en) | Classroom quality monitoring system based on colorful dynamic human face features | |
CN111460245A (en) | Multi-dimensional crowd characteristic measuring method | |
CN115527404A (en) | Artificial intelligence self-adaptation interactive teaching system | |
Sun et al. | Research on the Application of Students' Answered Record Analyze Model and Question Automatic Classify Based on K-Means Clustering Algorithm | |
Zheng et al. | Automated Multi-Mode Teaching Behavior Analysis: A Pipeline Based Event Segmentation and Description | |
Zhang | RETRACTED: Cultivation and interpretation of students' psychological quality: Vocal psychological model | |
CN111461153A (en) | Crowd characteristic deep learning method | |
Huang et al. | [Retracted] Analysis of Ideological and Political Classroom Based on Artificial Intelligence and Data Mining Technology | |
Zhao et al. | Design and Implementation of a Teaching Verbal Behavior Analysis Aid in Instructional Videos |
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 |