CN112949562A - Intelligent adaptive learning method and system - Google Patents
Intelligent adaptive learning method and system Download PDFInfo
- Publication number
- CN112949562A CN112949562A CN202110317133.1A CN202110317133A CN112949562A CN 112949562 A CN112949562 A CN 112949562A CN 202110317133 A CN202110317133 A CN 202110317133A CN 112949562 A CN112949562 A CN 112949562A
- Authority
- CN
- China
- Prior art keywords
- student object
- preset
- preset student
- value
- learning
- 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 85
- 230000003044 adaptive effect Effects 0.000 title claims abstract description 36
- 230000006399 behavior Effects 0.000 claims abstract description 60
- 230000008569 process Effects 0.000 claims abstract description 59
- 238000012937 correction Methods 0.000 claims description 51
- 230000006870 function Effects 0.000 claims description 28
- 239000000126 substance Substances 0.000 claims description 15
- 230000009471 action Effects 0.000 claims description 14
- 238000012360 testing method Methods 0.000 claims description 14
- 238000004364 calculation method Methods 0.000 claims description 11
- 238000000605 extraction Methods 0.000 claims description 6
- 230000001815 facial effect Effects 0.000 claims description 6
- 210000001364 upper extremity Anatomy 0.000 claims description 6
- 238000005516 engineering process Methods 0.000 abstract description 13
- 238000012545 processing Methods 0.000 description 8
- 230000004048 modification Effects 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
Images
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
- G06V40/20—Movements or behaviour, e.g. gesture 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
- 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
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Tourism & Hospitality (AREA)
- Strategic Management (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- Educational Technology (AREA)
- General Health & Medical Sciences (AREA)
- Educational Administration (AREA)
- Human Computer Interaction (AREA)
- Social Psychology (AREA)
- Psychiatry (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Electrically Operated Instructional Devices (AREA)
Abstract
The invention provides an intelligent adaptive learning method and system, which are characterized in that dynamic images are shot in a teaching video watching process and a question answering process of a preset student object, and the dynamic images are identified to obtain corresponding teaching video watching behavior details and question answering behavior details, so that big data about the learning ability level of the preset student object is generated, and finally learning interest knowledge points corresponding to the preset students are corrected in real time, so that the teaching scheme of the preset student object is adjusted in a targeted manner; the intelligent adaptive learning method and the intelligent adaptive learning system apply intelligent technologies (such as MCM (Multi chip Module) and the like) to analyze and process the learning behavior details of the corresponding dynamic images, so that the targeted teaching scheme adjustment can be carried out according to the learning capability levels of different preset student objects, and the learning efficiency of the different preset student objects is improved.
Description
Technical Field
The invention relates to the technical field of intelligent education, in particular to an intelligent adaptive learning method and system.
Background
In the teaching process, the students can be effectively taught with high-efficiency knowledge better by the aid of the education according to the factors, and the students' learning preference is used as a precondition for the implementation of the education according to the factors. However, different students have certain differences in learning habits and learning preferences, and such differences are usually reflected on a relatively abstract level, and cannot be measured by objective criteria. Currently, the objective judgment of learning preference cannot be effectively and accurately carried out on different individual students, which seriously restricts the targeted knowledge teaching of different individual students. Therefore, the prior art urgently needs intelligent adjustment means capable of comprehensively and accurately adjusting different student individuals.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides an intelligent adaptation learning method and system, which carry out dynamic image shooting on a teaching video watching process and a question answering process of a preset student object, identify a dynamic image to obtain corresponding teaching video watching behavior details and question answering behavior details so as to generate big data about the learning ability level of the preset student object, and finally correct learning interest knowledge points corresponding to the preset student in real time, thereby pertinently adjusting the teaching scheme of the preset student object; the intelligent adaptive learning method and the intelligent adaptive learning system apply intelligent technologies (such as MCM (Multi chip Module) and the like) to analyze and process the learning behavior details of the corresponding dynamic images, so that the targeted teaching scheme adjustment can be carried out according to the learning capability levels of different preset student objects, and the learning efficiency of the different preset student objects is improved.
The invention provides an intelligent adaptive learning method, which is characterized by comprising the following steps:
step S1, shooting a preset student object to obtain a dynamic image of the student object watching a teaching video or solving a question;
step S2, identifying the dynamic image to obtain the teaching video watching behavior details and the question answering behavior details of the preset student object;
step S3, determining learning ability level big data of the preset student object according to the teaching video watching behavior details and the question answering behavior details;
step S4, correcting the learning interest knowledge points of the preset student object according to the learning ability level big data, so as to adjust the teaching scheme aiming at the preset student object;
further, in the step S1, the capturing a preset student object to obtain a dynamic image of the student object watching a teaching video or solving a question specifically includes,
step S101, acquiring dynamic images of the preset student objects in the process of watching teaching videos of different subjects or in the process of answering homework/test paper questions of different subjects;
step S102, distinguishing the dynamic images according to the subject culture types and the age ranges of the preset student objects so as to obtain dynamic image sets of specific age groups corresponding to a plurality of specific culture/science;
step S103, picking out the dynamic images with the actual duration exceeding a preset duration threshold from each dynamic image set according to the actual duration of the dynamic images to serve as the subsequent dynamic images to be identified;
further, in step S2, the dynamic image is recognized to obtain the teaching video watching behavior details and the subject answering behavior details of the preset student object,
step S201, constructing a linerized contour of the preset student object according to facial features and upper limb features of the preset student object;
step S202, according to the line-shaped contour, the dynamic image is identified, so that the watching sight line direction and the watching duration of the preset student object in the teaching video watching process, and the hand writing action and the hand writing duration of the preset student object in the question answering process are obtained;
further, in the step S3, it is determined that the big data of the learning ability level of the preset student object specifically includes, according to the detail of the teaching video watching behavior and the detail of the topic solving behavior,
step S301, determining knowledge learning understanding ability level big data of a preset student object according to the watching sight line direction and the watching duration of the preset student object in the teaching video watching process and video knowledge content corresponding to the teaching video watched by the preset student object currently;
step S302, determining question answering ability level big data of the preset student object according to the hand writing action and the hand writing duration of the preset student object in the question answering process and the question knowledge content corresponding to the homework/test paper currently answered by the preset student object;
further, in the step S4, the modifying the learning knowledge points of interest of the preset student object according to the big data of the learning ability level to adjust the teaching plan for the preset student object specifically includes,
step S401, converting the big data of the learning ability level into a special ability value and an overall ability value aiming at the preset student object in a numerical mode, and calculating a point of interest knowledge value Q matched with the preset student object according to the following formula (1)a(t)，
In the above formula (1), Qa(t) a-th interest knowledge point score X representing the preset student object matching at the time ta(t) the ability value of the student object to specialize the a-th interest knowledge point is preset at the time t, Za(t) the integral ability value of the preset student object to the a-th interest knowledge point at the time t, QbRepresenting the b-th interest knowledge point score in the database corresponding to the learning ability level big data, wherein u () represents a step function, when the value in the bracket is greater than or equal to 0, the function value of the step function is 1, and when the value in the bracket is less than 0, the function value of the step function is 0;
step S402, according to the following formula (2), the value Q of the interest knowledge point is calculateda(t) performing real-time correction to obtainReal-time correction value delta Q of interest knowledge points matched with preset student objectsa(t+Δt)，
In the above formula (2), Δ Qa(t + Δ t) represents a real-time correction value of the a-th interest knowledge point matched with the preset student object at the time of t + Δ t, Δ Xa(t + Δ t) represents a real-time correction value of the special ability value of the a-th interest knowledge point matched with the preset student object at the time of t + Δ t, and Δ Za(t + Δ t) represents a real-time correction value of the overall capacity value of the a-th interest knowledge point matched with a preset student object at the time of t + Δ t, and Δ t represents correction time;
step S403, calculating according to the following formula (3) to obtain the value Q of the interest knowledge point matched with the preset student object after being corrected in real timea(t+Δt)，
In the above formula (3), Qa(t + Δ t) represents the value of the a-th interest knowledge point matched with a preset student object after being corrected at the t + Δ t moment; qa(t) a value of the a-th interest knowledge point matched with a preset student object at the time t is represented;
step 404, according to the real-time corrected value Q of the interest knowledge pointa(t + Δ t), adjusting a teaching plan for the preset student object.
The invention also provides an intelligent adaptive learning system, which comprises a camera module, a dynamic image identification module, a learning ability level big data determination module and a teaching scheme adjustment module; wherein the content of the first and second substances,
the camera module is used for shooting a preset student object so as to obtain a dynamic image of the student object watching a teaching video or solving a question;
the dynamic image identification module is used for identifying the dynamic image so as to obtain the teaching video watching behavior details and the question answering behavior details of the preset student object;
the learning ability level big data determining module is used for determining learning ability level big data of the preset student object according to the teaching video watching behavior details and the question answering behavior details;
the teaching scheme adjusting module is used for correcting the learning interest knowledge points of the preset student object according to the learning ability level big data so as to adjust the teaching scheme aiming at the preset student object;
furthermore, the camera module comprises a dynamic image acquisition sub-module, a dynamic image distinguishing sub-module and a dynamic image picking sub-module; wherein the content of the first and second substances,
the dynamic image acquisition sub-module is used for acquiring dynamic images of the preset student objects in the process of watching teaching videos of different subjects or in the process of answering homework/test paper questions of different subjects;
the dynamic image distinguishing submodule is used for distinguishing the dynamic images according to the subject culture types and the age ranges of the preset student objects so as to obtain a dynamic image set of a specific age range corresponding to a plurality of specific culture/science;
the dynamic image picking submodule is used for picking out a dynamic image of which the actual duration exceeds a preset duration threshold from each dynamic image set according to the actual duration of the dynamic image to be used as a subsequent dynamic image to be identified;
furthermore, the dynamic image identification module comprises a student object contour extraction sub-module and a behavior detail identification sub-module; wherein the content of the first and second substances,
the student object contour extraction submodule is used for constructing a linear contour of the preset student object according to facial features and upper limb features of the preset student object;
the behavior detail identification submodule is used for identifying the dynamic image according to the line-shaped outline so as to obtain the watching sight line direction and the watching duration of the preset student object in the teaching video watching process and the hand writing action and the hand writing duration of the preset student object in the question answering process;
further, the learning ability level big data determining module comprises a knowledge learning understanding ability level big data determining sub-module and a question answering ability level big data determining sub-module; wherein the content of the first and second substances,
the knowledge learning understanding ability level big data determining submodule is used for determining knowledge learning understanding ability level big data of the preset student object according to the watching sight line direction and the watching duration of the preset student object in the teaching video watching process and the video knowledge content corresponding to the teaching video watched by the preset student object currently;
the question answering ability level big data determining submodule is used for determining question answering ability level big data of the preset student object according to hand writing actions and hand writing duration of the preset student object in a question answering process and question knowledge content corresponding to homework/test paper answered by the preset student object currently;
furthermore, the teaching scheme adjusting module comprises an interest knowledge point score calculating sub-module, an interest knowledge point correcting sub-module, an interest knowledge point score correction value calculating sub-module and a teaching adjusting execution sub-module; wherein the content of the first and second substances,
the interest knowledge point score calculation submodule is used for converting the learning ability level big data into a special ability value and an overall ability value aiming at the preset student object in a numerical mode, and calculating an interest knowledge point score Q matched with the preset student object according to the following formula (1)a(t)，
In the above formula (1), Qa(t) a-th interest knowledge point score X representing the preset student object matching at the time ta(t) represents tThe special ability value Z of the student object to the a-th interest knowledge point is preseta(t) the integral ability value of the preset student object to the a-th interest knowledge point at the time t, QbRepresenting the b-th interest knowledge point score in the database corresponding to the learning ability level big data, wherein u () represents a step function, when the value in the bracket is greater than or equal to 0, the function value of the step function is 1, and when the value in the bracket is less than 0, the function value of the step function is 0;
the interest knowledge point correction submodule is used for correcting the score Q of the interest knowledge point according to the following formula (2)a(t) performing real-time correction to obtain real-time correction value delta Q of the interest knowledge points matched with the preset student objectsa(t+Δt)，
In the above formula (2), Δ Qa(t + Δ t) represents a real-time correction value of the a-th interest knowledge point matched with the preset student object at the time of t + Δ t, Δ Xa(t + Δ t) represents a real-time correction value of the special ability value of the a-th interest knowledge point matched with the preset student object at the time of t + Δ t, and Δ Za(t + Δ t) represents a real-time correction value of the overall capacity value of the a-th interest knowledge point matched with a preset student object at the time of t + Δ t, and Δ t represents correction time;
the interest knowledge point score correction value calculation submodule is used for calculating and obtaining an interest knowledge point score Q matched with a preset student object after real-time correction according to the following formula (3)a(t+Δt)，
In the above formula (3), Qa(t + Δ t) represents the value of the a-th interest knowledge point matched with a preset student object after being corrected at the t + Δ t moment; qa(t) a value of the a-th interest knowledge point matched with a preset student object at the time t is represented;
the teaching adjustment execution submodule is used for correcting the value Q of the interest knowledge point in real timea(t + Δ t), adjusting a teaching plan for the preset student object.
Compared with the prior art, the intelligent adaptive learning method and the intelligent adaptive learning system have the advantages that dynamic images are shot in the teaching video watching process and the question answering process of the preset student object, the dynamic images are identified to obtain the corresponding teaching video watching behavior details and the corresponding question answering behavior details, accordingly, big data about the learning capacity level of the preset student object are generated, and finally, learning interest knowledge points corresponding to the preset students are corrected in real time, so that the teaching scheme of the preset student object is adjusted in a targeted manner; the intelligent adaptive learning method and the intelligent adaptive learning system apply intelligent technologies (such as MCM (Multi chip Module) and the like) to analyze and process the learning behavior details of the corresponding dynamic images, so that the targeted teaching scheme adjustment can be carried out according to the learning capability levels of different preset student objects, and the learning efficiency of the different preset student objects is improved.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic flow chart of the intelligent adaptive learning method provided by the present invention.
Fig. 2 is a schematic structural diagram of the intelligent adaptive learning system provided by the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Fig. 1 is a schematic flow chart of an intelligent adaptive learning method according to an embodiment of the present invention. The intelligent adaptive learning method comprises the following steps:
step S1, shooting a preset student object to obtain a dynamic image of the student object watching a teaching video or solving a question;
step S2, identifying the dynamic image to obtain the teaching video watching behavior details and the question answering behavior details of the preset student object;
step S3, determining the learning ability level big data of the preset student object according to the teaching video watching behavior details and the question answering behavior details;
step S4, modifying the learning interest knowledge points of the predetermined student object according to the learning ability level big data, so as to adjust the teaching scheme for the predetermined student object.
The intelligent adaptive learning method takes the dynamic images of the student objects watching the teaching videos or answering questions as original data, and analyzes the original data to obtain the behavior details of the student objects in the learning process, and the behavior details can reflect the current learning state of the student objects or the knowledge mastering degree to a certain extent, so that the learning ability of the student objects can be restored to the maximum extent, and an intelligent technology (for example, an intelligent technology such as a statistical simulation technology of MCM Monte Carlo) is applied to carry out rapid and accurate data analysis and calculation, wherein the intelligent technology is an intelligent data statistical analysis technology so as to carry out personalized processing on different preset student objects subsequently, and thus the mode of the teaching scheme is completely adjusted subsequently.
Preferably, in the step S1, the capturing a preset student object to obtain a dynamic image of the student object watching a teaching video or solving a question specifically includes,
step S101, acquiring dynamic images of the preset student object in the process of watching teaching videos of different subjects or in the process of answering homework/test paper questions of different subjects;
step S102, according to the subject culture type and the age range of the preset student object, distinguishing the dynamic images to obtain a dynamic image set of a specific age range corresponding to a plurality of specific culture/science;
step S103, according to the actual duration of the dynamic image, picking out the dynamic image with the actual duration exceeding the predetermined duration threshold from each dynamic image set, so as to be used as the subsequent dynamic image to be identified.
By carrying out distinguishing processing on the dynamic image according to the cultural science division and the age groups of the student objects, the dynamic image can be ensured to truly reflect the difference between different student objects, thereby reducing the difficulty and the complexity of the follow-up dynamic image processing.
Preferably, in the step S2, the moving image is recognized, so as to obtain the teaching video watching behavior details and the subject answering behavior details of the preset student object,
step S201, constructing a linerized contour of the preset student object according to facial features and upper limb features of the preset student object;
step S202, according to the line outline, the dynamic image is identified, so that the watching sight line direction and the watching duration of the preset student object in the teaching video watching process, and the hand writing action and the hand writing duration of the preset student object in the question answering process are obtained.
The method can be used for conveniently and quickly determining the behavior details of the student object in the dynamic image by constructing the line drawing outline of the student object, thereby simplifying the data processing amount of recognition and improving the comprehensiveness and accuracy of recognition of different types of behavior details.
Preferably, in the step S3, the big data of learning ability level of the preset student object is determined to specifically include,
step S301, determining knowledge learning understanding ability level big data of a preset student object according to the watching sight line direction and the watching duration of the preset student object in the teaching video watching process and the video knowledge content corresponding to the teaching video watched by the preset student object currently;
step S302, determining the question answering ability level big data of the preset student object according to the hand writing action and the hand writing duration of the preset student object in the question answering process and the question knowledge content corresponding to the homework/test paper answered by the preset student object currently.
The viewing direction and the viewing duration of the student object in the process of viewing the teaching video, and the hand writing action and the hand writing duration in the question answering process have considerable relevance with the learning concentration and the knowledge mastery of the student object, and the knowledge learning understanding ability level big data and the question answering ability level big data obtained through the basic data can be matched with the real situation of the student object to the maximum extent.
Preferably, in the step S4, the modifying the learning knowledge points of interest of the preset student object according to the learning ability level big data to adjust the teaching plan for the preset student object specifically includes,
step S401, the big data of the learning ability level is converted into a special ability value and an overall ability value aiming at the preset student object in a numerical mode, and an interest knowledge point value Q matched with the preset student object is obtained through calculation according to the following formula (1)a(t)，
In the above formula (1), Qa(t) a-th interest knowledge point score X representing the preset student object matching at the time ta(t) the ability value of the student object to specialize the a-th interest knowledge point is preset at the time t, and in practice, Xa(t) the average score obtained by performing at least one of listening, speaking, and reading/writing tests on the a-th knowledge point of interest on a preset student object before the t time (e.g., within a preset time period before the t time) is directly used as the corresponding special ability value, Za(t) the overall ability value of the a-th interest knowledge point of the student object is preset at the time t, and in practice, Za(t) the average score value obtained after the student object finishes all the homework topics related to the a-th interest knowledge point is preset before the t moment as the corresponding overall capacity value, QbThe b-th interest knowledge point score in the database corresponding to the big data of the learning ability level is expressed, and in practice, QbThe average scoring value of the learning difficulty degrees of all student objects to the b-th interest knowledge point can be counted in the database to serve as the b-th interest knowledge point score, and the higher the average scoring value is, the harder the corresponding learning difficulty degree is; or QbThe average score value of the interestingness of all student objects to the b-th interest knowledge point can be counted in the database to serve as the b-th interest knowledge point score value, and the higher the average score value of the interestingness is, the higher the corresponding interestingness is; u () represents a step function, the function value of which is 1 when the value in the parentheses is greater than or equal to 0, and the function value of which is 0 when the value in the parentheses is less than 0;
step S402, the value Q of the interest knowledge point is calculated according to the following formula (2)a(t) performing real-time correction to obtain real-time correction value delta Q of the interest knowledge points matched with the preset student objecta(t+Δt)，
In the above formula (2), Δ Qa(t + Δ t) represents a real-time correction value of the a-th interest knowledge point matched with the preset student object at the time of t + Δ t, Δ Xa(t + delta t) represents a real-time correction value of the special ability value of the preset student object to the a-th interest knowledge point at the time of t + delta t, and delta Za(t + delta t) represents a real-time correction value of the integral ability value of the student object to the a-th interest knowledge point preset at the time of t + delta t, and delta t represents preset correction duration; Δ Xa(t+Δt)＝Xa(t+Δt)-Xa(t) wherein Xa(t + delta t) represents the special ability value of the student object to the a-th interest knowledge point preset at the time of t + delta t; delta Za(t+Δt)＝Za(t+Δt)-Za(t)，Za(t + delta t) represents the integral ability value of the student object to the a-th interest knowledge point preset at the time of t + delta t;
step S403, calculating according to the following formula (3) to obtain the value Q of the interest knowledge point matched with the preset student object after being corrected in real timea(t+Δt)，
In the above formula (3), Qa(t + Δ t) represents the value of the a-th interest knowledge point matched with a preset student object after being corrected at the t + Δ t moment; qa(t) a value of the a-th interest knowledge point matched with a preset student object at the time t is represented;
step 404, according to the real-time corrected value Q of the interest knowledge pointa(t + Δ t), adjusting the teaching plan for the preset student object. In the practical process, the value Q of the interest knowledge point can be corrected in real timeaAdjusting the teaching time length of the corresponding interest knowledge points of the preset student object according to the size relation between (t + delta t) and a preset threshold, wherein the value Q of the interest knowledge points after real-time correction can bea(t + delta t) is less than or equal to a preset threshold, the teaching time length of the corresponding interest knowledge point of the preset student object is reduced, and the value Q of the interest knowledge point after real-time correctiona(t + Δ t) is largeAnd increasing the teaching time of the corresponding interest knowledge points of the preset student object at a preset threshold value.
Through the calculation process, the knowledge points can be updated in real time according to the change of the special capacity value and the overall capacity value of the student object, and compared with the traditional education, the method focuses on pertinence, cultures the learning interest of the student object, improves the learning efficiency of the student object and realizes the personalized development in different directions.
Fig. 2 is a schematic structural diagram of an intelligent adaptive learning system according to an embodiment of the present invention. The intelligent adaptive learning system comprises a camera module, a dynamic image identification module, a learning ability level big data determination module and a teaching scheme adjustment module; wherein the content of the first and second substances,
the camera module is used for shooting a preset student object so as to obtain a dynamic image of the student object watching a teaching video or solving a question;
the dynamic image identification module is used for identifying the dynamic image so as to obtain the teaching video watching behavior details and the question answering behavior details of the preset student object;
the learning ability level big data determining module is used for determining the learning ability level big data of the preset student object according to the teaching video watching behavior details and the question answering behavior details;
the teaching scheme adjusting module is used for correcting the learning interest knowledge points of the preset student object according to the learning ability level big data so as to adjust the teaching scheme aiming at the preset student object.
The intelligent adaptive learning system takes the dynamic images of the student objects watching the teaching videos or answering questions as original data, and analyzes the original data to obtain the behavior details of the student objects in the learning process, and the behavior details can reflect the current learning state or the knowledge mastering degree of the student objects to a considerable extent, so that the learning ability of the student objects can be restored to the maximum extent, and an intelligent technology (such as MCM technology and the like) is applied to carry out rapid and accurate data analysis and calculation, wherein the intelligent technology is an intelligent data statistical analysis technology so as to carry out personalized processing on different preset student objects subsequently, and therefore the mode of the teaching scheme is completely and subsequently adjusted.
Preferably, the camera module comprises a dynamic image acquisition sub-module, a dynamic image distinguishing sub-module and a dynamic image picking sub-module; wherein the content of the first and second substances,
the dynamic image acquisition sub-module is used for acquiring dynamic images of the preset student object in the process of watching teaching videos of different subjects or in the process of answering homework/test paper questions of different subjects;
the dynamic image distinguishing submodule is used for distinguishing the dynamic images according to the subject culture type and the age range of the preset student object so as to obtain a dynamic image set of a specific age group corresponding to a plurality of specific culture/science;
the dynamic image picking sub-module is used for picking out the dynamic images with the actual duration exceeding the preset duration threshold from each dynamic image set according to the actual duration of the dynamic images to be used as the subsequent dynamic images to be identified.
By carrying out distinguishing processing on the dynamic image according to the cultural science division and the age groups of the student objects, the dynamic image can be ensured to truly reflect the difference between different student objects, thereby reducing the difficulty and the complexity of the follow-up dynamic image processing.
Preferably, the dynamic image recognition module comprises a student object contour extraction sub-module and a behavior detail recognition sub-module; wherein the content of the first and second substances,
the student object contour extraction submodule is used for constructing a linerized contour about the preset student object according to facial features and upper limb features of the preset student object;
the behavior detail identification submodule is used for identifying the dynamic image according to the line-shaped outline so as to obtain the watching sight line direction and the watching duration of the preset student object in the teaching video watching process and the hand writing action and the hand writing duration of the preset student object in the question answering process.
The method can be used for conveniently and quickly determining the behavior details of the student object in the dynamic image by constructing the line drawing outline of the student object, thereby simplifying the data processing amount of recognition and improving the comprehensiveness and accuracy of recognition of different types of behavior details.
Preferably, the learning ability level big data determining module comprises a knowledge learning understanding ability level big data determining sub-module and a question answering ability level big data determining sub-module; wherein the content of the first and second substances,
the knowledge learning understanding ability level big data determining submodule is used for determining knowledge learning understanding ability level big data of the preset student object according to the watching sight line direction and the watching duration of the preset student object in the teaching video watching process and the video knowledge content corresponding to the teaching video watched by the preset student object currently;
the question answering ability level big data determining submodule is used for determining the question answering ability level big data of the preset student object according to the hand writing action and the hand writing duration of the preset student object in the question answering process and the question knowledge content corresponding to the homework/test paper which is answered by the preset student object currently.
The viewing direction and the viewing duration of the student object in the process of viewing the teaching video, and the hand writing action and the hand writing duration in the question answering process have considerable relevance with the learning concentration and the knowledge mastery of the student object, and the knowledge learning understanding ability level big data and the question answering ability level big data obtained through the basic data can be matched with the real situation of the student object to the maximum extent.
Preferably, the teaching scheme adjusting module comprises an interest knowledge point score calculating sub-module, an interest knowledge point correcting sub-module, an interest knowledge point score correction value calculating sub-module and a teaching adjusting execution sub-module; wherein the content of the first and second substances,
the interest knowledge point score calculation submodule is used for converting the learning ability level big data into a special ability value and an overall ability value aiming at the preset student object in a numerical mode and according to the following stepsCalculating to obtain the value Q of the interest knowledge point matched with the preset student object by formula (1)a(t)，
In the above formula (1), Qa(t) a-th interest knowledge point score X representing the preset student object matching at the time ta(t) the ability value of the student object to specialize the a-th interest knowledge point is preset at the time t, and in practice, Xa(t) an average score obtained by performing at least one of listening, speaking, and reading/writing tests on the a-th knowledge point of interest on a preset student object before the time t is directly used as a corresponding special ability value, Za(t) the overall ability value of the a-th interest knowledge point of the student object is preset at the time t, and in practice, Za(t) the average score value of all the homework subjects of the a-th interest knowledge point can be directly used as the corresponding overall capacity value, Q, by presetting the student objects before the t momentbThe b-th interest knowledge point score in the database corresponding to the big data of the learning ability level is expressed, and in practice, QbThe average scoring value of the learning difficulty degrees of all student objects to the b-th interest knowledge point can be counted in the database to serve as the b-th interest knowledge point score, and the higher the average scoring value is, the harder the corresponding learning difficulty degree is; or QbThe b-th interest knowledge point score can be obtained by counting the average score value of the interestingness of all student objects to the b-th interest knowledge point in a database, wherein the higher the average score value of the interestingness is, the higher the corresponding interestingness is, u () represents a step function, when the value in the bracket is greater than or equal to 0, the function value of the step function is 1, and when the value in the bracket is less than 0, the function value of the step function is 0;
the interest knowledge point modification sub-module is used for scoring the interest knowledge point Q according to the following formula (2)a(t) performing real-time correction to obtain real-time correction value delta Q of the interest knowledge points matched with the preset student objecta(t+Δt)，
In the above formula (2), Δ Qa(t + Δ t) represents a real-time correction value of the a-th interest knowledge point matched with the preset student object at the time of t + Δ t, Δ Xa(t + Δ t) represents a real-time correction value of the special ability value of the a-th interest knowledge point matched with the preset student object at the time of t + Δ t, and Δ Za(t + Δ t) represents a real-time correction value of the overall capacity value of the a-th interest knowledge point matched with a preset student object at the time of t + Δ t, and Δ t represents correction time;
the interest knowledge point score correction value calculation submodule is used for calculating and obtaining an interest knowledge point score Q matched with a preset student object after real-time correction according to the following formula (3)a(t+Δt)，
In the above formula (3), Qa(t + Δ t) represents the value of the a-th interest knowledge point matched with a preset student object after being corrected at the t + Δ t moment; qa(t) a value of the a-th interest knowledge point matched with a preset student object at the time t is represented;
the teaching adjustment execution submodule is used for correcting the value Q of the interest knowledge point in real timea(t + Δ t), adjusting the teaching plan for the preset student object. In the practical process, the value Q of the interest knowledge point can be corrected in real timeaAdjusting the teaching time length of the corresponding interest knowledge points of the preset student object according to the size relation between (t + delta t) and a preset threshold, wherein the value Q of the interest knowledge points after real-time correction can bea(t + delta t) is less than or equal to a preset threshold, the teaching time length of the corresponding interest knowledge point of the preset student object is reduced, and the value Q of the interest knowledge point after real-time correctiona(t + Δ t) is greater than the preset threshold, increasing the teaching time of the corresponding interest knowledge point for the preset student objectLong.
Through the calculation process, the knowledge points can be updated in real time according to the change of the special capacity value and the overall capacity value of the student object, and compared with the traditional education, the method focuses on pertinence, cultures the learning interest of the student object, improves the learning efficiency of the student object and realizes the personalized development in different directions.
As can be seen from the content of the above embodiment, the intelligent adaptive learning method and system perform dynamic image shooting on the teaching video viewing process and the question answering process of the preset student object, recognize the dynamic image to obtain the corresponding teaching video viewing behavior details and the question answering behavior details, thereby generating big data about the learning ability level of the preset student object, and finally correct the learning interest knowledge points corresponding to the preset student in real time, thereby adjusting the teaching scheme of the preset student object in a targeted manner; the intelligent adaptive learning method and the intelligent adaptive learning system apply intelligent technologies (such as MCM (Multi chip Module) and the like) to analyze and process the learning behavior details of the corresponding dynamic images, so that the targeted teaching scheme adjustment can be carried out according to the learning capability levels of different preset student objects, and the learning efficiency of the different preset student objects is improved.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (10)
1. An intelligent adaptive learning method, characterized in that the intelligent adaptive learning method comprises the following steps:
step S1, shooting a preset student object to obtain a dynamic image of the student object watching a teaching video or solving a question;
step S2, identifying the dynamic image to obtain the teaching video watching behavior details and the question answering behavior details of the preset student object;
step S3, determining learning ability level big data of the preset student object according to the teaching video watching behavior details and the question answering behavior details;
and step S4, correcting the learning interest knowledge points of the preset student object according to the learning ability level big data, so as to adjust the teaching scheme aiming at the preset student object.
2. The intelligent adaptive learning method of claim 1, wherein:
in step S1, the capturing a preset student object to obtain a dynamic image of the student object watching a teaching video or solving a question specifically includes,
step S101, acquiring dynamic images of the preset student objects in the process of watching teaching videos of different subjects or in the process of answering homework/test paper questions of different subjects;
step S102, distinguishing the dynamic images according to the subject culture types and the age ranges of the preset student objects so as to obtain dynamic image sets of specific age groups corresponding to a plurality of specific culture/science;
step S103, according to the actual duration of the dynamic image, picking out the dynamic image with the actual duration exceeding the predetermined duration threshold from each of the dynamic image sets, so as to serve as the subsequent dynamic image to be identified.
3. The intelligent adaptive learning method of claim 1, wherein:
in step S2, the dynamic image is recognized to obtain the teaching video watching behavior details and the subject answering behavior details of the preset student object,
step S201, constructing a linerized contour of the preset student object according to facial features and upper limb features of the preset student object;
step S202, according to the line-shaped contour, the dynamic image is identified, so that the watching sight line direction and the watching duration of the preset student object in the teaching video watching process, and the hand writing action and the hand writing duration of the preset student object in the question answering process are obtained.
4. The intelligent adaptive learning method of claim 1, wherein:
in step S3, it is determined that the big data of learning ability level of the preset student object specifically includes, according to the detail of the teaching video viewing behavior and the detail of the topic solving behavior,
step S301, determining knowledge learning understanding ability level big data of a preset student object according to the watching sight line direction and the watching duration of the preset student object in the teaching video watching process and video knowledge content corresponding to the teaching video watched by the preset student object currently;
step S302, determining the question answering ability level big data of the preset student object according to the hand writing action and the hand writing duration of the preset student object in the question answering process and the question knowledge content corresponding to the homework/test paper answered by the preset student object currently.
5. The intelligent adaptive learning method of claim 1, wherein:
in step S4, modifying the learning knowledge points of interest of the preset student object according to the learning ability level big data to adjust the teaching plan for the preset student object specifically includes,
step S401, converting the big data of the learning ability level into a special ability value and an overall ability value aiming at the preset student object in a numerical mode, and calculating a point of interest knowledge value Q matched with the preset student object according to the following formula (1)a(t)，
In the above formula (1), Qa(t) a-th interest knowledge point score X representing the preset student object matching at the time ta(t) the ability value of the student object to specialize the a-th interest knowledge point is preset at the time t, Za(t) the integral ability value of the preset student object to the a-th interest knowledge point at the time t, QbRepresenting the b-th interest knowledge point score in the database corresponding to the learning ability level big data, wherein u () represents a step function, when the value in the bracket is greater than or equal to 0, the function value of the step function is 1, and when the value in the bracket is less than 0, the function value of the step function is 0;
step S402, according to the following formula (2), the value Q of the interest knowledge point is calculateda(t) performing real-time correction to obtain real-time correction value delta Q of the interest knowledge points matched with the preset student objectsa(t+Δt)，
In the above formula (2), Δ Qa(t + Δ t) represents a real-time correction value of the a-th point of interest knowledge score at the time of t + Δ t, Δ Xa(t + Δ t) represents a real-time correction value of the special ability value of the a-th interest knowledge point matched with the preset student object at the time of t + Δ t, and Δ Za(t + Δ t) represents a real-time correction value of the overall capacity value of the a-th interest knowledge point matched with a preset student object at the time of t + Δ t, and Δ t represents a preset correction duration;
step S403, calculating according to the following formula (3) to obtain the value Q of the interest knowledge point matched with the preset student object after being corrected in real timea(t+Δt)，
In the above formula (3), Qa(t + delta t) represents that the corrected time t + delta t is the same as the preset student objectMatching the a-th interest knowledge point score; qa(t) a value of the a-th interest knowledge point matched with a preset student object at the time t is represented;
step 404, according to the real-time corrected value Q of the interest knowledge pointa(t + Δ t), adjusting a teaching plan for the preset student object.
6. An intelligent learning system, which is characterized in that:
the intelligent adaptive learning system comprises a camera module, a dynamic image identification module, a learning ability level big data determination module and a teaching scheme adjustment module; wherein the content of the first and second substances,
the camera module is used for shooting a preset student object so as to obtain a dynamic image of the student object watching a teaching video or solving a question;
the dynamic image identification module is used for identifying the dynamic image so as to obtain the teaching video watching behavior details and the question answering behavior details of the preset student object;
the learning ability level big data determining module is used for determining learning ability level big data of the preset student object according to the teaching video watching behavior details and the question answering behavior details;
the teaching scheme adjusting module is used for correcting the learning interest knowledge points of the preset student objects according to the learning ability level big data so as to adjust the teaching scheme aiming at the preset student objects.
7. The intelligent adaptive learning system of claim 6, wherein:
the camera module comprises a dynamic image acquisition sub-module, a dynamic image distinguishing sub-module and a dynamic image picking sub-module; wherein the content of the first and second substances,
the dynamic image acquisition sub-module is used for acquiring dynamic images of the preset student objects in the process of watching teaching videos of different subjects or in the process of answering homework/test paper questions of different subjects;
the dynamic image distinguishing submodule is used for distinguishing the dynamic images according to the subject culture types and the age ranges of the preset student objects so as to obtain a dynamic image set of a specific age range corresponding to a plurality of specific culture/science;
the dynamic image picking submodule is used for picking out the dynamic images of which the actual duration exceeds the preset duration threshold from each dynamic image set according to the actual duration of the dynamic images so as to be used as the dynamic images to be identified subsequently.
8. The intelligent adaptive learning system of claim 6, wherein:
the dynamic image identification module comprises a student object contour extraction sub-module and a behavior detail identification sub-module; wherein the content of the first and second substances,
the student object contour extraction submodule is used for constructing a linear contour of the preset student object according to facial features and upper limb features of the preset student object;
the behavior detail identification submodule is used for identifying the dynamic image according to the line-shaped outline so as to obtain the watching sight direction and the watching duration of the preset student object in the teaching video watching process, and the hand writing action and the hand writing duration of the preset student object in the question answering process.
9. The intelligent adaptive learning system of claim 6, wherein:
the learning ability level big data determining module comprises a knowledge learning understanding ability level big data determining sub-module and a question answering ability level big data determining sub-module; wherein the content of the first and second substances,
the knowledge learning understanding ability level big data determining submodule is used for determining knowledge learning understanding ability level big data of the preset student object according to the watching sight line direction and the watching duration of the preset student object in the teaching video watching process and the video knowledge content corresponding to the teaching video watched by the preset student object currently;
and the question answering ability level big data determining submodule is used for determining the question answering ability level big data of the preset student object according to the hand writing action and the hand writing duration of the preset student object in the question answering process and the question knowledge content corresponding to the homework/test paper currently answered by the preset student object.
10. The intelligent adaptive learning system of claim 6, wherein:
the teaching scheme adjusting module comprises an interest knowledge point score calculating sub-module, an interest knowledge point correcting sub-module, an interest knowledge point score correction value calculating sub-module and a teaching adjusting execution sub-module; wherein the content of the first and second substances,
the interest knowledge point score calculation submodule is used for converting the learning ability level big data into a special ability value and an overall ability value aiming at the preset student object in a numerical mode, and calculating an interest knowledge point score Q matched with the preset student object according to the following formula (1)a(t)，
In the above formula (1), Qa(t) a-th interest knowledge point score X representing the preset student object matching at the time ta(t) the ability value of the student object to specialize the a-th interest knowledge point is preset at the time t, Za(t) the integral ability value of the preset student object to the a-th interest knowledge point at the time t, QbRepresenting the b-th interest knowledge point score in the database corresponding to the learning ability level big data, wherein u () represents a step function, when the value in the bracket is greater than or equal to 0, the function value of the step function is 1, and when the value in the bracket is less than 0, the function value of the step function is 0;
the interest knowledge point correction submodule is used for correcting the score Q of the interest knowledge point according to the following formula (2)a(t) performing a real-time correction to obtainObtaining real-time correction value delta Q of interest knowledge points matched with the preset student objecta(t+Δt)，
In the above formula (2), Δ Qa(t + Δ t) represents a real-time correction value of the a-th interest knowledge point matched with the preset student object at the time of t + Δ t, Δ Xa(t + Δ t) represents a real-time correction value of the special ability value of the a-th interest knowledge point matched with the preset student object at the time of t + Δ t, and Δ Za(t + Δ t) represents a real-time correction value of the overall capacity value of the a-th interest knowledge point matched with a preset student object at the time of t + Δ t, and Δ t represents correction time;
the interest knowledge point score correction value calculation submodule is used for calculating and obtaining an interest knowledge point score Q matched with a preset student object after real-time correction according to the following formula (3)a(t+Δt)，
In the above formula (3), Qa(t + Δ t) represents the value of the a-th interest knowledge point matched with a preset student object after being corrected at the t + Δ t moment; qa(t) a value of the a-th interest knowledge point matched with a preset student object at the time t is represented;
the teaching adjustment execution submodule is used for correcting the value Q of the interest knowledge point in real timea(t + Δ t), adjusting a teaching plan for the preset student object.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2020105140278 | 2020-06-08 | ||
| CN202010514027.8A CN111523518A (en) | 2020-06-08 | 2020-06-08 | Intelligent adaptive learning method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112949562A true CN112949562A (en) | 2021-06-11 |
Family
ID=71912682
Family Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010514027.8A Withdrawn CN111523518A (en) | 2020-06-08 | 2020-06-08 | Intelligent adaptive learning method and system |
| CN202110317133.1A Pending CN112949562A (en) | 2020-06-08 | 2021-03-25 | Intelligent adaptive learning method and system |
Family Applications Before (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010514027.8A Withdrawn CN111523518A (en) | 2020-06-08 | 2020-06-08 | Intelligent adaptive learning method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (2) | CN111523518A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115766853A (en) * | 2022-11-14 | 2023-03-07 | 电子科大科园教育中心 | Big data-based college student learning behavior analysis method |
| CN115909210A (en) * | 2022-12-02 | 2023-04-04 | 北京思想天下教育科技有限公司 | Effective learning time statistical system |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112017496B (en) * | 2020-08-30 | 2021-07-30 | 上海松鼠课堂人工智能科技有限公司 | Student computing power analysis method based on game learning |
| CN111985582B (en) * | 2020-09-27 | 2021-06-01 | 上海松鼠课堂人工智能科技有限公司 | Knowledge point mastering degree evaluation method based on learning behaviors |
| CN113409635A (en) * | 2021-06-17 | 2021-09-17 | 上海松鼠课堂人工智能科技有限公司 | Interactive teaching method and system based on virtual reality scene |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| AUPR971401A0 (en) * | 2001-12-21 | 2002-01-24 | Crankshaw, Karen | Educational software |
| US20090035733A1 (en) * | 2007-08-01 | 2009-02-05 | Shmuel Meitar | Device, system, and method of adaptive teaching and learning |
| US20200046277A1 (en) * | 2017-02-14 | 2020-02-13 | Yuen Lee Viola Lam | Interactive and adaptive learning and neurocognitive disorder diagnosis systems using face tracking and emotion detection with associated methods |
| CN108399376B (en) * | 2018-02-07 | 2020-11-06 | 华中师范大学 | Intelligent analysis method and system for classroom learning interest of students |
-
2020
- 2020-06-08 CN CN202010514027.8A patent/CN111523518A/en not_active Withdrawn
-
2021
- 2021-03-25 CN CN202110317133.1A patent/CN112949562A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115766853A (en) * | 2022-11-14 | 2023-03-07 | 电子科大科园教育中心 | Big data-based college student learning behavior analysis method |
| CN115766853B (en) * | 2022-11-14 | 2024-04-12 | 慧谷科园教育科技产业股份有限公司 | University student learning behavior analysis method based on big data |
| CN115909210A (en) * | 2022-12-02 | 2023-04-04 | 北京思想天下教育科技有限公司 | Effective learning time statistical system |
| CN115909210B (en) * | 2022-12-02 | 2023-09-01 | 北京思想天下教育科技有限公司 | Effective learning time statistics system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111523518A (en) | 2020-08-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112949562A (en) | Intelligent adaptive learning method and system | |
| CN110399558B (en) | Test question recommendation method and system | |
| CN113762107B (en) | Object state evaluation method, device, electronic equipment and readable storage medium | |
| CN108765229B (en) | Learning performance evaluation method based on big data and artificial intelligence and robot system | |
| CN111522877B (en) | Online synchronous processing system for education courses | |
| CN108829842B (en) | Learning expression image method and robot system based on big data and artificial intelligence | |
| CN110930781A (en) | Recording and broadcasting system | |
| CN111325082A (en) | Personnel concentration degree analysis method and device | |
| CN113342761B (en) | Teaching resource sharing system and method based on Internet | |
| CN110991943A (en) | Teaching quality evaluation system based on cloud computing | |
| CN111179666B (en) | Self-adaptive education system based on artificial intelligence | |
| CN116304315A (en) | Intelligent content recommendation system for online teaching | |
| CN111723288B (en) | Intelligent adaptive learning detection system and method | |
| CN112016431B (en) | Intelligent detection and analysis method and system for teaching quality | |
| CN110996128B (en) | Online teaching video push management system | |
| CN111507555B (en) | Human body state detection method, classroom teaching quality evaluation method and related device | |
| CN111078992B (en) | Dictation content generation method and electronic equipment | |
| CN113409635A (en) | Interactive teaching method and system based on virtual reality scene | |
| CN111209817A (en) | Assessment method, device and equipment based on artificial intelligence and readable storage medium | |
| CN106780207B (en) | Method and system for modifying classroom exercises | |
| CN114140282B (en) | Method and device for quickly reviewing answers of general teaching classroom based on deep learning | |
| CN114625302B (en) | Electronic question making method, device, system and storage medium | |
| CN114219460B (en) | Multimedia teaching management system based on human-computer interaction | |
| CN112883975A (en) | Dynamic knowledge point learning standard-reaching test method and system | |
| CN115115237A (en) | Online education method and system based on big data |
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 |