CN108647657A - A kind of high in the clouds instruction process evaluation method based on pluralistic behavior data - Google Patents
A kind of high in the clouds instruction process evaluation method based on pluralistic behavior data Download PDFInfo
- Publication number
- CN108647657A CN108647657A CN201810467548.5A CN201810467548A CN108647657A CN 108647657 A CN108647657 A CN 108647657A CN 201810467548 A CN201810467548 A CN 201810467548A CN 108647657 A CN108647657 A CN 108647657A
- Authority
- CN
- China
- Prior art keywords
- learner
- state
- data
- learning
- eye
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 48
- 230000008569 process Effects 0.000 title claims abstract description 29
- 238000011156 evaluation Methods 0.000 title claims abstract description 21
- 230000013016 learning Effects 0.000 claims abstract description 52
- 230000006399 behavior Effects 0.000 claims abstract description 14
- 230000010365 information processing Effects 0.000 claims abstract description 7
- 230000009471 action Effects 0.000 claims description 6
- 230000004424 eye movement Effects 0.000 claims description 5
- 230000004438 eyesight Effects 0.000 claims description 4
- 230000035045 associative learning Effects 0.000 claims description 3
- 230000008859 change Effects 0.000 claims description 3
- 230000002996 emotional effect Effects 0.000 claims description 3
- 230000007935 neutral effect Effects 0.000 claims description 3
- 230000007958 sleep Effects 0.000 claims description 3
- 230000001960 triggered effect Effects 0.000 claims 1
- 210000003128 head Anatomy 0.000 description 8
- 238000010586 diagram Methods 0.000 description 2
- 230000001815 facial effect Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 241001269238 Data Species 0.000 description 1
- 241000287181 Sturnus vulgaris Species 0.000 description 1
- 230000003542 behavioural effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000003238 somatosensory effect Effects 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/174—Facial expression recognition
-
- 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
-
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/18—Eye characteristics, e.g. of the iris
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Health & Medical Sciences (AREA)
- Strategic Management (AREA)
- Educational Administration (AREA)
- General Health & Medical Sciences (AREA)
- Tourism & Hospitality (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Educational Technology (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Ophthalmology & Optometry (AREA)
- Social Psychology (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Psychiatry (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Electrically Operated Instructional Devices (AREA)
Abstract
The present invention proposes a kind of high in the clouds instruction process evaluation method based on pluralistic behavior data, it is desirable to provide a method of pluralistic behavior data in learner's learning process are recorded and evaluated, to realize the overall merit of high in the clouds teaching process.The present invention includes student information harvester, information processing and evaluation system, by being acquired the use data in conjunction with student to cloud system to student's posture, expression, eye state, the information of sight, the study situation of learner is handled and analyzed using information processing system, and high in the clouds teaching process is evaluated by evaluation system.High in the clouds instruction process evaluation method proposed by the present invention based on pluralistic behavior data can have great importance for service hoisting teaching efficiency and the instructional decisions etc. for formulating science to provide the reference data of students ' behavior state with relevant tutoring system of imparting knowledge to students.
Description
Technical field
The present invention relates to intelligent online learning information recording method field, and in particular to a kind of based on pluralistic behavior data
High in the clouds instruction process evaluation method.
Background technology
It is difficult to accomplish comprehensively to pay close attention to whether student conscientiously listens while taking into account lesson presentation in classroom teaching teacher
It says.The video or picture that teaching research worker is listened to the teacher by acquiring student, are analyzed using image recognition and Expression Recognition
The classroom performance situation of student assesses the study situation of student in turn.But it depends merely on student's expression in learning process and assesses
Study situation there is certain one-sidedness and limitation.With the diversification of technological means and carrying for instrument and equipment performance
It is high so as to acquire the comprehensive status data of student such as attitude data in teaching process, expression data, eye status data, regard
Line eye movement status data is possibly realized.Therefore, using much information data certain is used come comprehensive judgement student learning state all Billys
Single data, which carry out judgement, will seem more rationally and accurate.
It is found in teaching practice, the state of listening to the teacher of student can be reflected from his basic status.But if
Only judge that learner's state of listening to the teacher just easily causes erroneous judgement by status information in a certain respect.For example, learner closes
Eyes do not represent him and are deserting, and learner, which stares at screen and also do not represent him, conscientiously to pay attention to the class.Therefore, only one or
Two status informations are to be not enough to the learning state of judgement learner, so needing fully getting learner's learning state
After carrying out comprehensive judgement after information, the learning state of learner could be relatively accurately judged.
It is the continuous status information of acquisition in default situations, the problem of this brings is exactly that data volume is huge.In order to reduce
The scale of data processing may be used the interval time for increasing acquisition, for example acquire a data every 1 second.But it is most important
Thing be that the status data of acquisition must have timestamp information, timestamp is easy for carrying out with cloud system use state same
What step judged.
Invention content
The present invention provides a kind of high in the clouds instruction process evaluation method based on pluralistic behavior data, is existed by acquiring learner
The status number that attitude data, expression data, eye status data in learning process, eye sight line data and cloud system use
According to making overall merit to the learning process situation of learner after being analyzed.This method has supervision for Faculty and Students
It is supported with invigoration effect and for instructional decisions service providing data.
A kind of high in the clouds instruction process evaluation method of pluralistic behavior data proposed by the present invention, includes the following steps：
(1) data acquire：Acquire the head pose data of learner, expression data, eye status data, sight data,
The status data that cloud system uses；
(2) learner's status information is handled：Carry out learner's status information processing, analytic learning person's head pose Shead、
Expression Sface, eye state Seye, sight data Sgaze, the current learning state of learner is judged according to the information of analysis, it is described
Learner's learning state is always divided into absorbed, tired, three kinds of states of diverting attention, and is in addition stupefied and absorbed in state of diverting attention
State needs to be detected by the sight data of learner, if it find that learner's sight blinkpunkt in the case where being absorbed in state
It does not change in 5 seconds, pops up a sliding unlock window and be detected, otherwise user must unlock in setting time
Then it is considered that learner is in stupefied state；By detect learner operation with mouse and keyboard be this moment to judge learner
It is no that cloud system is used, it can trigger a countdown after each mouse action or keyboard action generation of learner
Device, any mouse-keyboard operation then countdown again has occurred in count-down device in the process, if there are no any when the countdown concluded
Mouse or keyboard operation occur it is assumed that system is not used for learner；
(3) learner's status information is analyzed：The use of the status information and cloud system of comprehensive each moment learner
State judges and records to the study condition of moment learner.Judge that learner is presently in absorbed, tired or
The state diverted attention, condition adjudgement determined by following decision table,
, the learning state sequence table for combining cloud system use state to form learner after learner's learning state is obtained,
The field that the learning state sequence table gauge outfit includes has：Timestamp, learner's learning state, if use cloud system；
(4) the learner's status information for exceptional value occur is labeled and is recorded；
(5) learning process of student is evaluated in the learning state list of associative learning person.
By said program, analytic learning person head pose data are used using posture identification method in the step 2)
In nine kinds of head positions of detection learner：Positive face, it is to the left, to the left it is upper, to the right, to the right it is upper, on the lower side, to the left under, it is on the upper side, to the right
Under；Analytic learning person expression data is using expression recognition method, the seven of scholar kind emotional state for identification：It is neutral, frightened
Very, frightened, detest, indignation, glad, sadness；Eye status data is analyzed using method for recognizing human eye state, for detecting
Three kinds of eye states of learner's eye：It sleeps, is dimmed, awake；Analytic learning person's eye sight line data using eye movement with
Track method shares two states for determining whether the sight of learner rests in screen ranges：It rests in screen ranges
Or it rests on outside screen ranges.
Include following sub-step by said program, in the step (3)：
(3.1) learner's posture is identified；
(3.2) learner's expression is identified；
(3.3) learner's eye state is identified；
(3.4) learner's eye movement is identified；
(3.5) learner is identified using the state of cloud system；
(3.6) comprehensive analysis is carried out to all status informations, judges the learning state of learner.
By said program, in the step (3), step (3.1) can be exchanged to (3.5) five kinds of recognition sequences of step.
Beneficial effects of the present invention：
The present invention avoids piece caused by a single state data by recording a variety of learner's status datas and being analyzed
Face property.Meanwhile comprehensive analysis judgement is carried out using all status informations, increase the accuracy of learner's learning state identification.
Description of the drawings
Fig. 1 is that the present invention is based on the overall procedure schematic diagrames of the high in the clouds instruction process evaluation method of pluralistic behavior data；
Fig. 2 is that the present invention is based on the acquisitions of the multi-state data of the high in the clouds instruction process evaluation method of pluralistic behavior data to illustrate
Figure.
Specific implementation mode
The present invention will be further described below.
Fig. 1 is that the present invention is based on the overall procedure schematic diagrames of the high in the clouds instruction process evaluation method of pluralistic behavior data.Side
There is required hardware in method, video camera or camera, the high in the clouds teaching platform system for being equipped with starC applications, Tobii eye trackers,
Kinect etc..Wherein Tobii eye trackers are for detecting human eye state, sight and the instrument and equipment of blinkpunkt, and Kinect is one
Kind 3D somatosensory devices can be used for detecting human body attitude；All instrument and equipments are mounted on the both sides of classroom front end or double screen with can
It takes subject to positive face of the student in face of double screen when；Information collecting device is connected with information processing equipment and information storing device
Connect, information processing equipment may be used computer, high-performance server, information storing device may be used large capacity disk or
Disk array.
Fig. 2 is that the present invention is based on multi-pose data acquisition signals in the high in the clouds instruction process evaluation method of pluralistic behavior data
Figure.Wherein Kinect acquires learner's attitude data, and camera acquires learner's expression data, and Tobii acquires eye state number
According to the status data learnt using starC with sight eye movement data, high in the clouds tutoring system acquisition learner.
A kind of high in the clouds instruction process evaluation method of pluralistic behavior data, includes the following steps：
(1) data acquire：Acquire the head pose data of learner, expression data, eye status data, sight data,
The status data that cloud system uses；
(2) learner's status information is handled：Carry out learner's status information processing, analytic learning person's head pose Shead、
Expression Sface, eye state Seye, sight data Sgaze, the current learning state of learner is judged according to the information of analysis, it is described
Learner's learning state is always divided into absorbed, tired, three kinds of states of diverting attention, and is in addition stupefied and absorbed in state of diverting attention
State needs to be detected by the sight data of learner, if it find that learner's sight blinkpunkt in the case where being absorbed in state
It does not change in 5 seconds, pops up a sliding unlock window and be detected, otherwise user must unlock in setting time
Then it is considered that learner is in stupefied state；By detect learner operation with mouse and keyboard be this moment to judge learner
It is no that cloud system is used, it can trigger a countdown after each mouse action or keyboard action generation of learner
Device, any mouse-keyboard operation then countdown again has occurred in count-down device in the process, if there are no any when the countdown concluded
Mouse or keyboard operation occur it is assumed that system is not used for learner；
(3) learner's status information is analyzed：The use of the status information and cloud system of comprehensive each moment learner
State judges and records to the study condition of moment learner.Judge that learner is presently in absorbed, tired or
The state diverted attention, condition adjudgement determined by following decision table,
, the learning state sequence table for combining cloud system use state to form learner after learner's learning state is obtained,
The field that the learning state sequence table gauge outfit includes has：Timestamp, learner's learning state, if use cloud system；
(4) the learner's status information for exceptional value occur is labeled and is recorded；
(5) learning process of student is evaluated in the learning state list of associative learning person.
Analytic learning person head pose data are using posture identification method in step 2), and nine for detecting learner
Kind head position：Positive face, it is to the left, to the left it is upper, to the right, to the right it is upper, on the lower side, to the left under, it is on the upper side, to the right under；Analytic learning person's table
Feelings data are using expression recognition method, the seven of scholar kind emotional state for identification：Neutral, surprised, frightened, detest, anger
Anger, happiness, sadness；Eye status data is analyzed using method for recognizing human eye state, three for detecting learner's eye
Kind eye state：It sleeps, is dimmed, awake；Analytic learning person's eye sight line data are using eye-tracking method, for determining
Whether the sight of learner rests in screen ranges, shares two states：Rest in screen ranges or rest on screen model
It encloses outer.
Gesture recognition of the present invention, generally includes following steps：
(a) depth image of learner is obtained；
(b) global feature identifies, the method for common extraction contour feature includes：HOG features, edgelet features, small baud
Sign, shapelet features；
(c) classification of posture is carried out using SVM；
(d) it carries out gesture recognition and exports.
Expression Recognition of the present invention, generally includes following steps：
(a) facial image is pre-processed.Geometry is carried out to facial image using three kinds of translation, rotation, scaling modes
Normalization；
(b) Haar characteristic sets, training AdaBoost graders are generated.Using AdaBoost algorithms to the notable of each details
Property assessed and selected distinguishing mark of the representative details as profile, carry out recognition of face；
(c) expressive features are extracted, discriminant classification is carried out to expression using SVM；
(d) it carries out Expression Recognition and exports result.
Human eye state identification of the present invention, generally includes following steps：
(a) recognition of face is carried out, human eye is positioned using the half-tone information of human eye and intercepts human eye area；
(b) eye state characteristic set, training human eye state recognition classifier are generated；
(c) eye state feature is extracted, is classified using human eye state recognition classifier；
(d) it carries out Eye state recognition and exports.
Learning state evaluation method of the present invention, generally includes following steps：
(a) it is status switch table by the status data acquired and acquisition time Data Integration；
(b) definition study state evaluation standard scale, so-called learning state evaluation criterion table refers to that may go out all students
Existing combinations of states is assessed and a state table making；
(c) student's status data of acquisition is assessed according to learning state evaluation criterion table.
The present invention realizes the overall merit to learner's learning process by polynary behavioral data, to realize to whole
A teaching process is objective and comprehensively evaluates.
Examples detailed above is only the description of preferred embodiments of the present invention, not limiting the scope of the invention, all in this hair
Any variation, modification and the improvement etc. done within bright spirit and principle, should all be within protection scope of the present invention.
Claims (3)
1. a kind of high in the clouds instruction process evaluation method based on pluralistic behavior data, which is characterized in that include the following steps：
(1) data acquire：The head pose data of acquisition learner, expression data, eye status data, sight data, high in the clouds
The status data that system uses；
(2) learner's status information is handled：Carry out learner's status information processing, analytic learning person's head pose Shead, expression
Sface, eye state Seye, sight data Sgaze, the current learning state of learner, the study are judged according to the information of analysis
Person's learning state is always divided into absorbed, tired, three kinds of states of diverting attention, and is in addition the stupefied and absorbed shape in state of diverting attention
State needs to be detected by the sight data of learner, if it find that learner be absorbed in state under sight blinkpunkt 5
It does not change in second, pops up a sliding unlock window and be detected, otherwise user must unlock in setting time then to be recognized
To be that learner is in stupefied state；Judge learner this moment whether just by detecting the operation with mouse and keyboard of learner
A count-down device can be triggered after occurring using each mouse action or keyboard action of cloud system, learner,
Any mouse-keyboard operation then countdown again has occurred during count-down device, if there are no any mouses when the countdown concluded
Or keyboard operation occurs it is assumed that system is not used for learner；
(3) learner's status information is analyzed：The status information of comprehensive each moment learner and the use state of cloud system
The study condition of moment learner is judged and recorded；Judge that learner is presently in absorbed, tired is diverted attention
State, obtain the learning state sequence table for combining after learner's learning state cloud system use state to form learner, institute
Stating the field that learning state sequence table gauge outfit includes has：Timestamp, learner's learning state, if use cloud system；
(4) the learner's status information for exceptional value occur is labeled and is recorded；
(5) learning process of student is evaluated in the learning state list of associative learning person.
2. instruction process evaluation method in high in the clouds according to claim 1, which is characterized in that analytic learning in the step 2)
Person's head pose data are using posture identification method, nine kinds of head positions for detecting learner：It is positive face, to the left, inclined
Upper left, it is to the right, to the right it is upper, on the lower side, to the left under, it is on the upper side, to the right under；Analytic learning person's expression data is using Expression Recognition side
Method, for identification the seven of scholar kind emotional state：Neutral, surprised, fear is detested, is angry, is glad, is sad；Analyze eye state
Data are using method for recognizing human eye state, three kinds of eye states for detecting learner's eye：It sleeps, is dimmed, awake；
Analytic learning person's eye sight line data are using eye-tracking method, for determining whether the sight of learner rests on screen
In range, two states are shared：It rests in screen ranges or rests on outside screen ranges.
3. instruction process evaluation method in high in the clouds according to claim 1 or 2, which is characterized in that include in the step (3)
Following sub-step：
(3.1) learner's posture is identified；
(3.2) learner's expression is identified；
(3.3) learner's eye state is identified；
(3.4) learner's eye movement is identified；
(3.5) learner is identified using the state of cloud system；
(3.6) comprehensive analysis is carried out to all status informations, judges the learning state of learner.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710336180 | 2017-05-12 | ||
| CN2017103361804 | 2017-05-12 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108647657A true CN108647657A (en) | 2018-10-12 |
Family
ID=63756114
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810467548.5A Pending CN108647657A (en) | 2017-05-12 | 2018-05-11 | A kind of high in the clouds instruction process evaluation method based on pluralistic behavior data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108647657A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109919079A (en) * | 2019-03-05 | 2019-06-21 | 百度在线网络技术（北京）有限公司 | Method and apparatus for detecting learning state |
| CN110865790A (en) * | 2019-11-21 | 2020-03-06 | 京东方科技集团股份有限公司 | Working method of electronic painted screen and electronic painted screen |
| CN110991277A (en) * | 2019-11-20 | 2020-04-10 | 湖南检信智能科技有限公司 | Multidimensional and multitask learning evaluation system based on deep learning |
| CN111369140A (en) * | 2020-03-04 | 2020-07-03 | 四川宇德中创信息科技有限公司 | Teaching evaluation system and method |
| CN111986530A (en) * | 2019-05-23 | 2020-11-24 | 深圳市希科普股份有限公司 | Interactive learning system based on learning state detection |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2014127333A1 (en) * | 2013-02-15 | 2014-08-21 | Emotient | Facial expression training using feedback from automatic facial expression recognition |
| CN105493130A (en) * | 2013-10-07 | 2016-04-13 | 英特尔公司 | Adaptive learning environment driven by real-time identification of engagement level |
| CN105516280A (en) * | 2015-11-30 | 2016-04-20 | 华中科技大学 | Multi-mode learning process state information compression recording method |
| CN106599881A (en) * | 2016-12-30 | 2017-04-26 | 首都师范大学 | Student state determination method, device and system |
-
2018
- 2018-05-11 CN CN201810467548.5A patent/CN108647657A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2014127333A1 (en) * | 2013-02-15 | 2014-08-21 | Emotient | Facial expression training using feedback from automatic facial expression recognition |
| CN105493130A (en) * | 2013-10-07 | 2016-04-13 | 英特尔公司 | Adaptive learning environment driven by real-time identification of engagement level |
| CN105516280A (en) * | 2015-11-30 | 2016-04-20 | 华中科技大学 | Multi-mode learning process state information compression recording method |
| CN106599881A (en) * | 2016-12-30 | 2017-04-26 | 首都师范大学 | Student state determination method, device and system |
Non-Patent Citations (1)
| Title |
|---|
| 新启科技研发部: "在线学习智能防挂机系统", 《HTTP://WWW.NEWSTARTSOFT.COM/HTML/FANGGUAJI.HTML》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109919079A (en) * | 2019-03-05 | 2019-06-21 | 百度在线网络技术（北京）有限公司 | Method and apparatus for detecting learning state |
| CN111986530A (en) * | 2019-05-23 | 2020-11-24 | 深圳市希科普股份有限公司 | Interactive learning system based on learning state detection |
| CN110991277A (en) * | 2019-11-20 | 2020-04-10 | 湖南检信智能科技有限公司 | Multidimensional and multitask learning evaluation system based on deep learning |
| CN110991277B (en) * | 2019-11-20 | 2023-09-22 | 湖南检信智能科技有限公司 | Multi-dimensional multi-task learning evaluation system based on deep learning |
| CN110865790A (en) * | 2019-11-21 | 2020-03-06 | 京东方科技集团股份有限公司 | Working method of electronic painted screen and electronic painted screen |
| CN111369140A (en) * | 2020-03-04 | 2020-07-03 | 四川宇德中创信息科技有限公司 | Teaching evaluation system and method |
| CN111369140B (en) * | 2020-03-04 | 2024-02-27 | 四川宇德中创信息科技有限公司 | Teaching evaluation system and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Fridman et al. | Cognitive load estimation in the wild | |
| CN108647657A (en) | A kind of high in the clouds instruction process evaluation method based on pluralistic behavior data | |
| JP6929366B2 (en) | Driver monitoring and response system | |
| Nojavanasghari et al. | Emoreact: a multimodal approach and dataset for recognizing emotional responses in children | |
| CN105516280B (en) | A kind of Multimodal Learning process state information packed record method | |
| Ishimaru et al. | Towards reading trackers in the wild: Detecting reading activities by EOG glasses and deep neural networks | |
| CN108399376A (en) | Student classroom learning interest intelligent analysis method and system | |
| Ahmed et al. | Kinect-based gait recognition using sequences of the most relevant joint relative angles | |
| Raudonis et al. | Evaluation of human emotion from eye motions | |
| CN105893942B (en) | A kind of sign Language Recognition Method of the adaptive H MM based on eSC and HOG | |
| CN102930270A (en) | Method and system for identifying hands based on complexion detection and background elimination | |
| Florea et al. | Can Your Eyes Tell Me How You Think? A Gaze Directed Estimation of the Mental Activity. | |
| Noman et al. | Mobile-based eye-blink detection performance analysis on android platform | |
| Alyuz et al. | An unobtrusive and multimodal approach for behavioral engagement detection of students | |
| Shi et al. | Automatic academic confusion recognition in online learning based on facial expressions | |
| CN114821753B (en) | Eye movement interaction system based on visual image information | |
| CN109726713A (en) | User's area-of-interest detection system and method based on consumer level Eye-controlling focus instrument | |
| Yasser et al. | Detection of confusion behavior using a facial expression based on different classification algorithms | |
| Huang et al. | Real‐Time Precise Human‐Computer Interaction System Based on Gaze Estimation and Tracking | |
| Suganya et al. | Design Of a Communication aid for physically challenged | |
| Das | Activity recognition using histogram of oriented gradient pattern history | |
| Kaur et al. | Domain adaptation based topic modeling techniques for engagement estimation in the wild | |
| CN111507555B (en) | Human body state detection method, classroom teaching quality evaluation method and related device | |
| CN112084814B (en) | Learning assisting method and intelligent device | |
| Nguyen et al. | Lightweight CNN-Based Driver Eye Status Surveillance for Smart Vehicles |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181012 |