CN112862639A - Online education method and online education platform based on big data analysis - Google Patents
Online education method and online education platform based on big data analysis Download PDFInfo
- Publication number
- CN112862639A CN112862639A CN202110016118.3A CN202110016118A CN112862639A CN 112862639 A CN112862639 A CN 112862639A CN 202110016118 A CN202110016118 A CN 202110016118A CN 112862639 A CN112862639 A CN 112862639A
- Authority
- CN
- China
- Prior art keywords
- teacher
- teaching
- student
- students
- teachers
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 88
- 238000007405 data analysis Methods 0.000 title claims abstract description 24
- 238000004891 communication Methods 0.000 claims abstract description 9
- 238000012549 training Methods 0.000 claims description 34
- 238000011156 evaluation Methods 0.000 claims description 12
- 238000012163 sequencing technique Methods 0.000 claims description 7
- 239000003086 colorant Substances 0.000 claims description 6
- 238000012795 verification Methods 0.000 claims description 3
- 238000013480 data collection Methods 0.000 claims description 2
- 238000006243 chemical reaction Methods 0.000 claims 4
- 230000002194 synthesizing effect Effects 0.000 claims 1
- 238000002360 preparation method Methods 0.000 abstract description 2
- 230000000694 effects Effects 0.000 description 8
- 206010041349 Somnolence Diseases 0.000 description 7
- 238000000605 extraction Methods 0.000 description 6
- 238000004458 analytical method Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 5
- 230000002452 interceptive effect Effects 0.000 description 4
- 230000002411 adverse Effects 0.000 description 3
- 230000004397 blinking Effects 0.000 description 3
- 238000012937 correction Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 101000601855 Homo sapiens Protocadherin-1 Proteins 0.000 description 1
- 102100037551 Protocadherin-1 Human genes 0.000 description 1
- 208000032140 Sleepiness Diseases 0.000 description 1
- 206010041235 Snoring Diseases 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 230000037321 sleepiness Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
- G06Q50/205—Education administration or guidance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/71—Indexing; Data structures therefor; Storage structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/73—Querying
- G06F16/735—Filtering based on additional data, e.g. user or group profiles
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
- G09B5/00—Electrically-operated educational appliances
- G09B5/08—Electrically-operated educational appliances providing for individual presentation of information to a plurality of student stations
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Educational Administration (AREA)
- Educational Technology (AREA)
- Data Mining & Analysis (AREA)
- Tourism & Hospitality (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Strategic Management (AREA)
- Multimedia (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- General Business, Economics & Management (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Marketing (AREA)
- Human Resources & Organizations (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Electrically Operated Instructional Devices (AREA)
Abstract
The invention relates to an online education method and an online education platform based on big data analysis. The online education method and the online education platform can acquire the state of the whole learning process of the student according to a preset judgment strategy by collecting the learning process of the student as basic data, and output a video image according to a judgment result, wherein the video image can be accessed by a teacher and a manager, and a teacher can understand the teaching process of the teacher according to the output video image to obtain feedback information of the student, so that the teaching mode and/or lesson preparation mode of the teacher can be improved. In addition, the manager can also know the state of the role of the student in the learning process in real time through the acquired video images, and therefore education and the like can be conveniently tutored after class. Meanwhile, the optimal teacher can be matched with the student according to the judgment result, and the learning passion and the learning efficiency of the student are improved. In addition, the optimal teaching content of the teachers can be determined, and mutual learning and communication among the teachers are facilitated. Meanwhile, the optimal teaching content can be output in a video mode, so that a manager can conveniently check and know the teaching quality.
Description
Technical Field
The invention relates to the field of interactive teaching, in particular to an online education method and an online education platform based on big data analysis.
Background
The online training is a network learning mode, namely a brand new learning mode that students log in an online learning device or platform through online equipment such as a computer or a mobile phone and select courses, listen to courses and the like through a network to realize the learning process. Particularly, due to the influence of new crown epidemic situation in this year, centralized training and learning cannot be carried out, and the advantages of online training and learning are highlighted.
However, since the existing online education platform performs learning through the network, the teacher and/or the enterprise training manager cannot know the specific learning state of the student at any time. Or the whole learning state of the student can be monitored through the online education platform, but the learning efficiency and the learning passion of the student cannot be really and effectively improved. Meanwhile, the teaching aid can not help teachers to carry out self-checking, and the teaching quality is improved.
Disclosure of Invention
The invention aims to solve the problems in the prior art, and the online education method and the online education platform based on big data analysis can effectively improve the learning efficiency and the learning passion of students. Meanwhile, the teaching aid helps teachers to perform self-checking, improves teaching quality, and enables enterprise training managers to know the learning states of students at any time, and facilitates post-class tracking, tutoring and the like.
In order to achieve the above purpose, the invention provides the following technical scheme:
an online education platform based on big data analysis, wherein the online education platform comprises:
the system comprises an online education system, a teacher terminal, an enterprise training manager terminal, a student terminal and a server; the online education system, the teacher terminal, the enterprise training manager terminal, the student terminal and the server are connected through a network to carry out data communication; wherein the terminal includes but is not limited to: cameras, smart phones, PCs, tablets; the teacher terminal and the student terminal are used for acquiring data of a learning process of a student and a teaching process of the teacher; the method comprises the steps of collecting the learning process of a student and the teaching process of a teacher in a video mode in a whole process, and collecting the voice of the student and the voice of the teacher in a voice mode in a whole process; wherein the collected data is transmitted to a server for storage.
Preferably, the online education system includes: the data analysis module is used for analyzing the data collected by the student terminal according to a preset judgment strategy and outputting a judgment result; and the evaluation module is used for determining the best matching result of the student and the teacher and/or the best teaching content result of the teacher according to the result output by the data analysis module.
In addition, the invention also provides an online education method based on big data analysis, which comprises the following steps:
a user inputs registration information and identity verification through an online education platform, and the online education platform carries out authority management according to the registration information input by the user; wherein the users specifically include students, teachers, and corporate training managers.
Data collection is carried out on students and/or teachers; wherein, the whole learning process of students and/or the teaching process of teachers are collected in a video mode; the method comprises the steps of collecting the voice of a student and/or the voice of a teacher in an audio mode in a whole process;
analyzing the collected data of the students according to a preset judgment strategy and outputting a judgment result; when the judgment result is output, the current time sequence information of the judgment result is also recorded; and outputting the best matching result of the student and the teacher and/or the best teaching content result of the teacher according to the judgment result and/or the time sequence information and/or the teaching process.
Compared with the prior art, the online education platform provides an enterprise management trainer, a school or teacher and a student real-time or asynchronous interactive communication and learning state display platform, and communication among the three is enhanced.
The invention analyzes the sample data based on a large amount of sample data obtained by the user terminal according to the preset judgment strategy and rule, thereby determining the learning state of the student. The judgment strategy provided by the invention has the following advantages: the judgment method is simple, the state of the student can be obtained through simple calculation according to the collected data, the complex judgment process in the existing algorithm is avoided, and the calculation power is saved. The judgment result is clear, and the clear judgment result can be obtained by the judgment method provided by the invention, so that the interference of the plausible result on the subsequent analysis is avoided.
The invention adopts different modes to determine the optimal matching result between the student and the teacher according to different practical conditions, thereby being capable of individually distributing the teacher to the student, and being capable of obviously improving the learning passion and the learning efficiency of the student. Meanwhile, the invention can also determine the optimal teaching content of the teachers according to different conditions, thereby facilitating the mutual learning and communication among the teachers. Meanwhile, the optimal teaching content can be output to a server in a video mode, so that an enterprise training manager can conveniently check the content and know the teaching quality.
Secondly, the scheme of the invention is as follows for the prior art: the technical problem that the direct statistics of the concentration duration is not accurate enough is firstly found, a corresponding technical scheme is further provided, the adverse effect on the matching result caused by the sequence of teaching in the same teaching content is avoided, and the matching result is more accurate. For the extracurricular training institution, by adopting the technical scheme provided by the invention, the most matched teacher can be quickly determined through audition of different teachers giving lessons, and the quality of the lessons is improved.
In addition, the technical scheme of the invention also has the following advantages: (1) the mode of sampling students to learn in advance is adopted to obtain the most matched lessee teachers of the students at the level, and the proper resources are adapted to the specific groups, so that the learning effect is ensured; (2) aiming at different teaching contents which are good at different teachers, the optimal teaching contents are configured for students, and the optimal configuration of teaching resources is guaranteed.
Description of the drawings:
FIG. 1 is an online education platform based on big data analysis according to the present invention;
FIG. 2 is an analysis evaluation module of the present invention;
FIG. 3 is a schematic diagram of time series information according to the present invention;
FIG. 4 is a diagram of the effect of video images synthesized by the present invention
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be described clearly and completely with reference to the accompanying drawings. It is to be understood that the embodiments described are only a few embodiments of the present invention, and not all embodiments.
Thus, the following detailed description of the embodiments of the invention is not intended to limit the scope of the invention as claimed, but is merely representative of some embodiments of the invention. 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.
It should be noted that the embodiments of the present invention and the features and technical solutions thereof may be combined with each other without conflict.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures.
In the description of the present invention, it should be noted that the terms "upper", "lower", and the like refer to orientations or positional relationships based on those shown in the drawings, or orientations or positional relationships that are conventionally arranged when the products of the present invention are used, or orientations or positional relationships that are conventionally understood by those skilled in the art, and such terms are used for convenience of description and simplification of the description, and do not refer to or imply that the devices or elements referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus, should not be construed as limiting the present invention. Furthermore, the terms "first," "second," and the like are used merely to distinguish one description from another, and are not to be construed as indicating or implying relative importance.
The preferred embodiments of the present invention will now be described in detail with reference to the accompanying drawings.
Referring to fig. 1, fig. 1 shows an online education platform based on big data analysis according to the present invention. Wherein, this online education platform mainly includes:
preferably, the online education system 1, the teacher terminal 2, the enterprise training manager terminal 3, the student terminal 4 and the server 5; the online education system 1, the teacher terminal 2, the enterprise training manager terminal 3, the student terminal 4 and the server 5 are connected through a network to perform data communication; wherein, the teacher terminal 2 operating device includes but is not limited to: projector 21, camera 22, smartphone 23, PC24, tablet 25; the operation equipment of the enterprise training manager terminal 3 includes but is not limited to: smart phone 31, PC32, tablet 33; the student terminal 4 operating devices include but are not limited to: smart phone 41, PC42, tablet 43.
And the user inputs registration information, identity authentication and authority management through the terminal. The registration information specifically includes, but is not limited to: the user's name, age, contact, etc.; the authority management is used for managing the use authority of different modules in the online education platform by each role in students, enterprise training managers and teachers, for example, the teachers can access videos in the server so as to know own teaching processes and obtain feedback information of the students, the enterprise training managers can access videos in the server so as to know the training quality of the teachers and the like, and the enterprise training managers can conveniently adjust enterprise training in real time and will be specifically explained in the following.
Preferably, the teacher terminal 2 and the student terminal 4 are used for collecting data of the learning process of students and the teaching process of teachers. The method comprises the steps of collecting the learning process of a student and the teaching process of a teacher in a video mode and collecting the voice of the student and the voice of the teacher in a voice mode. Wherein the collected data is transmitted to the server 5 for storage.
Preferably, as shown in fig. 2, the online education system 1 includes an analysis and evaluation module, and the analysis and evaluation module includes: and the data analysis module 11 is used for analyzing the sample data collected by the student terminal 4 according to a preset judgment strategy and outputting a judgment result. In one embodiment of the present invention, the judgment strategy is constructed by adopting a judgment method, and the input state parameters include an eye state, a mouth state and a sound state. Specifically, the judgment method constructed in the present invention is shown in the following table:
as shown in the above table, the eye state is taken as an example, and the state of the person is determined according to the blinking state. Specifically, a person blinks at a certain frequency when in a normal state, generally about 10-15 times per minute; however, when the eyes of the person are in a closed state and a drowsy state, the eyes are in a slow blinking state, and when the eyes are in a non-blinking state, the eyes may be in a stuck state or a special case of replacing the student with a picture may occur, so that the output result is invalid at this time. In summary, the blink frequency is used as the threshold for determining the eye state, 10 to 15 times/min is used as the normal value, and if the eye state exceeds the normal value range, the eye state can be considered as a slow blink state. Of course, the above judgment threshold is only shown by way of example, and those skilled in the art may make appropriate adjustments according to actual situations. Similarly, when the person is in a normal learning state or a drowsy state, the mouth is generally in a closed state, and when the person is in an alternative on-off state, the conversation or speaking state is illustrated, and the judgment can be made according to sound information, such as when there is a snore sound or an environmental sound, the person is illustrated as possibly in a drowsy state such as drowsy state or a state of paying attention to learning, and when there is a voice, the person is illustrated as being in a conversation or speaking state, as shown in the above table. The above table is only a schematic reference for the determination method in this embodiment, and those skilled in the art can adjust the determination method according to actual needs, for example, drowsiness and drowsiness can be classified into a fatigue state, which is not described herein.
The judging method provided by the invention has the following advantages: the judgment method is simple, the state of the student can be obtained through simple calculation according to the collected data, the complex judgment process in the existing algorithm is avoided, and the calculation power is saved. The judgment result is clear, and the clear judgment result can be obtained by the judgment method provided by the invention, so that the interference of the plausible result on the subsequent analysis is avoided.
Preferably, the data analysis module 11 includes a feature information extraction module 111 and a judgment module 112, where the feature information extraction module 111 is configured to extract feature information required by the judgment policy, and the judgment module 112 is configured to output a judgment result according to a preset judgment policy according to the feature information extracted by the feature information extraction module 111. Specifically, the feature information extraction module 111 is configured to extract an eye state, a mouth state, and a sound state.
Preferably, the extraction is done by extracting key frames in the video. Specifically, taking a segment of image recorded with 150 frames as an example, extraction may be performed once every 5 frames to extract 30 frames of images in total, and using the 30 frames of images as sample data, determine the eye state and mouth state of the person in each frame of image, determine the sound state through the sound information collected by the student terminal 4 in real time, finally determine the eye state, mouth state and sound state of the person in each frame of 30 frames of image, input the above results to the determination module 112, and determine the state (e.g., state of drowsiness, concentration, distraction, etc.) of the person according to a preset determination method, that is, determine the state of the person in each frame of 30 frames. Of course, the above parameter setting is only an example, and in the actual application process, corresponding adjustment may be performed according to specific video information to ensure the accuracy of the determination result.
Preferably, the determining module 112 outputs the determining result according to a preset determining strategy, and records the current time series information of the determining result, and the time series information is further transmitted to the data converting module 113. The determining module 112 is further configured to mark the time series information with different colors, and the data converting module 113 synthesizes the time series information marked with different colors into the collected video image of the teacher's teaching process in a time series manner. Specifically, time-series information of the present invention is shown in fig. 3, in which the time-series information includes the duration of the judgment result output in time series, and the representative color of the judgment result, for example, red for drowsiness or drowsiness; yellow for distraction; green for concentration etc. The determining module 112 transmits the time series information marked with different colors to the data converting module 113, the data converting module 113 synthesizes the time series information marked with different colors into the teacher teaching video collected by the teacher terminal 2, and outputs the synthesized video image to the server 5, and the synthesized video image effect graph is shown in fig. 4. The output video images can be accessed by teachers and enterprise training managers, teachers can solve own teaching processes according to the output video images to obtain feedback information of students, so that own teaching modes and/or lesson preparation modes can be improved, and meanwhile, the best teachers can be matched for the students according to the time sequence information or the video images. In addition, the enterprise training manager can also know the state of the student role in the learning process in real time through the acquired video images, and therefore the enterprise training manager is convenient for tracking after class, tutoring education and the like.
Preferably, the online education system 1 further comprises an evaluation module 12, and the evaluation module 12 is configured to obtain a plurality of time series information output by the judgment module 112 and/or a plurality of teaching processes collected by the teacher terminal 2. It should be noted that the plurality of teaching processes include teaching processes of a plurality of different teachers, wherein the teaching processes may be the same teaching content or different teaching contents. In contrast, the time-series information includes time-series information output by a plurality of students with respect to the lecture procedure, and may be specifically shown in the following table: taking student a as an example, the evaluation module 12 may obtain time-series information corresponding to teaching contents a, B, c, and d … … of student a to teacher a or time-series information corresponding to teaching contents a, B, c, and d … … of teacher B, and so on for the rest of teachers and students. It can be known that, according to specific needs, time series information corresponding to each teaching content of different students and different teachers can be acquired, which will be specifically described in the following embodiments.
Preferably, the evaluation module 12 is configured to determine a best matching result between the student and the teacher and/or a best teaching content result of the teacher according to the time series information.
Preferably, the duration time T of the concentration state in the time series information output by the same student in the teaching process of the same and/or different teaching contents for different teachers is determined, the duration time T of the concentration state is sorted according to the size, and the teacher with the maximum value T is matched with the student, so that the best matching result between the student and the teacher is determined.
Specifically, the duration time T of the state of interest in the time series information output by the same student during the course of teaching the same teaching content by different teachers is determined. For example, the duration T of the concentration state of the teaching content a of the teacher A of the lecture by the student A is determinedADetermining the duration T of the concentration state of the teaching content a of the teacher BBDetermining the duration T of the concentration state of the teaching content a of the teacher CCDetermining the duration T of the concentration state of the teaching content a of the teacher DDAnd so on for the rest. The details are shown in the following table:
comparison TA、TB、TC、TD… …, a larger value of T indicates a better match between the teacher and the student, and therefore the teacher with the highest value of T is matched with the student.
Preferably, the teaching process of different teaching contents of different teachers by the same student is determinedAnd the duration time T of the special comment state in the output time series information. For example, the sum t of the duration of the concentration state of the teaching contents a, b, c, d … … of the student A to the teacher A is determinedADetermining the sum t of the duration of the concentration state of the teaching contents a, B, c and d … … of the teacher BBDetermining the sum t of the duration of the concentration state of the teaching contents a, b, C and d … … of the teacher CCThe duration t of the concentration state of the teaching contents a, b, c, D … … of the teacher D is determinedDAnd so on for the rest. The details are shown in the following table
Wherein, ti＝∑TjI ═ a, B, C, D …; j ═ a, b, c, d …; comparison tA、tB、tC、tD… …, a larger value of t indicates a better match between the teacher and the student, and therefore the teacher with the largest value of t is matched with the student.
Preferably, there is some error in determining the best match of the student to the teacher in the manner described above. Specifically, when statistics student is to the state duration of being absorbed in of the same content of giving lessons of different teachers, to same content of giving lessons, the student makes along with the number of times of attending to lessons to be absorbed in the degree decline, and this will lead to the matching result that obtains to be accurate inadequately. Therefore, the invention further provides a technical scheme for correcting the T value according to the sequence of teaching by the teacher. Specifically, according to the sequence of lectures, the duration T of the concentration state is multiplied by the balance coefficient pnCoefficient of equilibrium pnAnd sequencing the corrected duration time T of the concentration state according to the sequence of teaching and increasing step by step so as to determine the best matching result. For example: respectively acquiring the concentration state duration T of the teaching contents a of the teacher A-C of the student A, wherein the teaching sequence is the teacher A, the teacher B and the teacher C, and correcting the modified concentration state duration TA＝p1×TA、tB＝p2×TB、tc＝p3×TC. Wherein p is1-p3Increasing in sequence, preferably, optionally p1＝1；p2＝1.1；p31.3. By comparing the corrected duration t of the concentration stateA、tB、tCThe teacher with the largest t value is selected as the matching teacher with student A. Of course, for different teaching contents, the same method can be used for correction, which is not described again, and the correction parameters can be further determined according to the actual teaching conditions.
Compared with the prior art, the scheme comprises the following steps: the technical problem that the direct statistics of the concentration duration is not accurate enough is firstly found, a corresponding technical scheme is further provided, the adverse effect on the matching result caused by the sequence of teaching in the same teaching content is avoided, and the matching result is more accurate. For the extracurricular training institution, by adopting the technical scheme provided by the invention, the most matched teacher can be quickly determined through audition of different teachers giving lessons, the pertinence of the lessons is improved, and the teaching quality is further improved.
Preferably, the teacher to which the student is adapted differs for different bases. In addition, the teaching content that different teachers are skilled in varies. Therefore, in order to fully exert the advantages of the existing education resources and improve the overall matching effect, the invention proposes to arrange the lectures by adopting the following method:
step 1: performing a thorough examination every quarter to determine the grade ranking of all students;
step 2: the student groups are sorted according to the score sequence, the sorting is segmented, n sample students are randomly extracted from each segment, the number n of the sample students is equal to the number m of the lecture teachers, and the learning progress of the sample students leads other students in the segment by one day;
and step 3: n sample students in each subsection learn the learning content of the Q day, the n sample students respectively learn the same teaching content of m teacher giving lessons, and the result of the duration time of the concentration state corresponding to the n sample students in each subsection is determined, so that the matching result of the student and the teacher giving lessons in the subsection on the learning content of the Q day is determined, wherein Q is initialized to 1;
and 4, step 4: arranging teaching teachers of other students in the next day according to the matching teachers determined in the step 3, specifically, the matching teachers determined in the step 3 are teaching teachers of other students in the next day, and the other students in the segment learn the learning content of the teaching teachers on day Q;
and 5: if the learning in one quarter is not finished, returning to the step 3, and enabling Q to be Q + 1; if the learning for one quarter is completed, the step 1 is returned.
Preferably, the determination method in step 3 is as follows: for each segment, randomly assigning one of m teachers to the n students in the segment and learning courses of the teacher on the Q-th day (because the number of m and n is equal, each student is guaranteed to correspond to the course of one of the teachers only), and obtaining the duration of the attentiveness state of the n students. The duration of the concentration state of the n students under the segment is ranked, and the teacher with the longest duration of the concentration state is used as the matching teacher of the segment. The above technical solution is illustrated by taking the segment 1 as an example in combination with the following table: in the study of day 1, randomly distributing one teacher in m teachers to the segmented n students and studying courses of day 1 of the teacher, and obtaining the duration of the concentration state of the n students: t is1A(i.e., student n)1Duration of concentration status in teacher a lesson), T1B、T1C、T1D. Will T1A、T1B、T1C、T1DAnd sorting, and taking the teacher corresponding to the duration time of the concentration state with the largest value as the matching teacher of the segment.
For clearly illustrating the above technical solution, the following are exemplified: setting 300 students as a whole and 4 teachers as lectures, taking a thorough examination every quarter, and determining the score ranking of 300 students (step 1); by sequencing student groups according to the score sequence and dividing the sequencing into 3 segments, namely segment 1-segment 3, each segment contains 100 persons, 4 sample students are randomly selected from each segment, and the learning progress of the sample students leads other students in the segment by one day (step 2); the 4 sample students in each segment respectively learn the same learning content of 4 teacher giving lessons, and the result of the concentration state duration corresponding to the 4 sample students in each segment is determined, so that the best matching result of the student and the 4 teacher giving lessons is determined (step 3); arranging teaching teachers of other students in the next day in the section according to the matched teachers determined in the step 3; if the learning in one quarter is not finished, returning to the step 3; if the learning for one quarter is completed, the step 1 is returned.
Compared with the prior art, the technical scheme of the invention has the following advantages: (1) the mode of sampling students to learn in advance is adopted to obtain the most matched lessee teachers of the students at the level, and the proper resources are adapted to the specific groups, so that the learning effect is ensured; (2) aiming at different teaching contents which are good at different teachers, the optimal teaching contents are configured for students, and the optimal configuration of teaching resources is guaranteed.
Preferably, the size of the duration time of the concentration state in the time series information output by different students for the teaching process of the same and/or different teachers with the same and/or different teaching contents is determined, the duration time of the concentration state is sorted according to the size, the teaching content with the maximum duration time of the concentration state is used as the optimal teaching content of the teachers, and the optimal teaching content result of the teachers is output.
Specifically, the duration time T of the special attention state in the time series information output by different students in the teaching process of different teaching contents of the same teacher is determined. For example, the duration T of the concentration state of student a, student B, and student C … … for the teaching content a of teacher a is determinedAa、TBa、TCa(ii) a Determining duration T of concentration state of student A, student B, student C … … of teaching content B of teacher AAb、TBb、TCb(ii) a A student A for determining the teaching content c of the teacher A,Duration T of concentration state of student B and student C … …Ac、TBc、TCc(ii) a And so on for the rest. The details are shown in the following table:
respectively calculating the sum t of duration time of concentration states output by different students in the course of teaching the same teacher with the same teaching content, wherein t isj＝∑TijI ═ a, B, C, …; j is a, b, c, …, compare ta、tb、tc… …, respectively. And taking the maximum teaching content in the t value as the optimal teaching content result of the teacher.
Compared with the prior art, the technical scheme of the invention has the following advantages: the acquired duration of the state of concentration of the students is fully utilized to determine the teaching contents which are good at and not good at a certain teacher, and clear guidance is provided for the teacher to improve the teaching level.
Furthermore, the duration of the special attention state in the time series information output by different students for the teaching process of the same and/or different teaching contents of different teachers can be determined, so that the optimal teaching content result of the teachers can be output. Illustratively, the size of the duration of the remarking state in the time-series information outputted by the teaching process of the same teaching content by different students for different teachers is determined, more specifically, the sum T of the duration of the remarking state in the time-series information outputted by the teaching process of the same teaching content by different students for the same teacher is determined, for example, the size T of the duration of the remarking state in the time-series information outputted by the student a, the student B and the student C … … in the teaching content a of the teacher a is determined respectivelyAA、TAB、TAC… …, and calculating the sum t of the duration of the concentration stateA(ii) a Determining the teaching contents a, B and A of the teacher BSize T of duration of special note state in time series information output by raw C … …BA、TBB、TBC… … and calculating the sum t of the duration of the concentration stateB(ii) a Determining the duration T of the special comment state in the time series information output by the students A, B and C … … in the teaching content a of the teacher CCA、TCB、TCC… … and calculating the sum t of the duration of the concentration stateCSee, in particular, the following table, wherein:
ti＝∑Tij，i＝A，B，C，…；j＝A，B，C，…
comparison tA、tB、tC… …, respectively. And determining the teaching content corresponding to the teacher with the maximum value in the t value as the optimal teaching content result of the teacher.
Compared with the prior art, the technical scheme of the invention has the following advantages: the acquired duration time of the state of the concentration of the students is fully utilized to determine the optimal teacher giving lessons to a certain teaching content, and clear guidance is provided for the course selection of the students.
Preferably, in the actual teaching process, not all students can learn the same teaching content of different teachers, so that the students corresponding to the same teaching content of different teachers are grouped, the sum of the concentration state durations of the students in different groups and the same teaching content of the corresponding teachers is respectively counted, and the optimal teacher teaching content result is output according to the result. For example, the sum t of the duration of the concentration state in the group 1 (including student A and student B) under the teaching content a of teacher A is determined1And the sum t of duration of concentration states in a group 2 (including student a and student B) of the teaching contents a of teacher B2And the rest are analogized, and in order to ensure accurate results, the number of students in each group is the same, which is specifically referred to the following table, wherein:
ti＝∑Tiji ═ 1, 2, 3, …; j ═ A, B, C, … or a, B, C …
Comparison t1、t2… …, determining the teaching content corresponding to the teacher with the maximum t value as the best teaching content result of the teacher. For the above embodiment, the average value of duration time of the special notes in the time series information output in the course of teaching the teaching contents of teachers in different groups can be calculated, and the optimal teaching content result is determined according to the size of the average value, so that adverse effects caused by different numbers of students can be avoided, and the specific calculation method is not repeated.
Compared with the prior art, the scheme adopts a grouping mode for determining the optimal teaching contents of different teachers, so that the output result is more accurate. For the extraclass training institution, the optimal teaching content of different teachers can be quickly and conveniently determined by using the method, and achievement display or propaganda and the like can be conveniently carried out on the optimal teaching content.
As described above, the present invention determines the best matching result between the student and the teacher in different ways according to different practical situations, so that the teacher can be individually allocated to the student, and thus the learning enthusiasm and learning efficiency of the student can be significantly improved. Meanwhile, the invention can also determine the optimal teaching content of the teachers according to different conditions, thereby facilitating the mutual learning and communication among the teachers. Meanwhile, the optimal teaching content can be output to a server in a video mode, so that an enterprise training manager can conveniently check the content and know the teaching quality.
A server 5 for storing various data collected and/or outputted in the online education platform. Specifically, the server 5 may store various registration information input by the teacher terminal 2, the enterprise training manager terminal 3, and the student terminal 4; the teacher terminal 2 and the student terminal 4 collect the video and/or sound information; the data analysis module 11 analyzes the processed feature information, the processed video image, and the processed time series information; the duration of the concentration state and/or the best matching result between the student and the teacher and/or the best teaching content result of the teacher, etc. output by the evaluation module 12.
In addition, for the present invention, the judgment strategy may also be constructed based on a neural network model, specifically as follows:
acquiring sample data, wherein the sample data comprises video data with a face region;
labeling key points of the eye region and the mouth region in the video data, and determining a trained target region;
generating a training sample set based on the characteristics of different eye areas and mouth areas in the video data and the state types of the corresponding personnel respectively;
and training the constructed network model based on the training sample set to obtain the judgment strategy, wherein the judgment strategy enables each eye feature and mouth feature in the training sample set to be associated with the state category of the corresponding person.
And then, the constructed neural network model is used for analyzing the sample data acquired by the student terminal 4 and outputting the judgment result.
In addition, when the judgment result is obtained through the judgment strategy, the judgment result can be further verified by the collected audio data. And further correcting the judgment result by judging whether the judgment result is matched with the student state displayed by the audio data.
As described above, the present invention provides an online education platform based on big data analysis. In addition, the invention also provides an online education method based on big data analysis. The specific mode is as follows:
a user inputs registration information and identity verification in an online interactive education platform, and the online interactive education platform performs authority management according to the registration information input by the user; wherein the users specifically include students, teachers, and corporate training managers.
Carrying out data acquisition on students and/or teachers; wherein, the whole learning process of students and/or the teaching process of teachers are collected in a video mode; the voice of the student and/or the voice of the teacher are collected all the way in the form of audio.
Analyzing the collected data of the students according to a preset judgment strategy and outputting a judgment result; the input state parameters of the judgment strategy comprise an eye state, a mouth state and a sound state, and the output judgment result is the state of the student at that time, including but not limited to sleepiness, drowsiness, distraction and concentration. And outputting the time series information of the judgment result while outputting the judgment result.
As described above, the present invention determines the best matching result between the student and the teacher in different ways according to different practical situations, so that the teacher can be individually allocated to the student, and thus the learning enthusiasm and learning efficiency of the student can be significantly improved. Meanwhile, the invention can also determine the optimal teaching content of the teachers according to different conditions, thereby facilitating the mutual learning and communication among the teachers. Meanwhile, the optimal teaching content can be output to a server in a video mode, so that an enterprise training manager can conveniently check the content and know the teaching quality.
The above embodiments are only used for illustrating the invention and not for limiting the technical solutions described in the invention, and although the present invention has been described in detail in the present specification with reference to the above embodiments, the present invention is not limited to the above embodiments, and therefore, any modification or equivalent replacement of the present invention is made; all such modifications and variations are intended to be included herein within the scope of this disclosure and the appended claims.
Claims (9)
1. An online education platform based on big data analysis, the education platform comprising:
the system comprises an online education system, a teacher terminal, an enterprise training manager terminal, a student terminal and a server; the online education system, the teacher terminal, the enterprise training manager terminal, the student terminal and the server are connected through a network to carry out data communication; wherein the terminal includes but is not limited to: cameras, smart phones, PCs, tablets; the teacher terminal and the student terminal are used for acquiring data of a learning process of a student and a teaching process of the teacher; the method comprises the steps of collecting the learning process of a student and the teaching process of a teacher in a video mode in a whole process, and collecting the voice of the student and the voice of the teacher in a voice mode in a whole process; wherein the collected data is transmitted to a server for storage.
2. An online education platform based on big data analysis as claimed in claim 1 wherein: the online education system includes: the data analysis module is used for analyzing the data collected by the student terminal according to a preset judgment strategy and outputting a judgment result; and the evaluation module is used for determining the best matching result of the student and the teacher and/or the best teaching content result of the teacher according to the judgment result output by the data analysis module.
3. An online education platform based on big data analysis as claimed in claim 2 wherein: the data analysis module comprises a judgment module and a data conversion module; when the judging module outputs the judging result, the current time sequence information of the judging result is also recorded; the time sequence information is transmitted to the data conversion module, and the data conversion module is used for synthesizing the time sequence information into a teacher teaching video acquired by the teacher terminal; the judging module is further configured to mark the time sequence information in different colors, the data conversion module synthesizes the time sequence information marked in different colors into an acquired video image of the teacher's teaching process in a time sequence, and stores the synthesized video image into a server, and the synthesized video image is accessed or viewed according to different permissions of users.
4. An online education platform based on big data analysis as claimed in claim 3 wherein: the evaluation module is used for acquiring a plurality of time sequence information output by the judgment module and/or a plurality of teaching processes collected by the teacher terminal; and the evaluation module outputs the best matching result of the student and the teacher and/or the best teaching content result of the teacher based on a plurality of time series information and/or a plurality of teaching processes.
5. An education method of an online education platform based on big data analysis according to claims 1-4, comprising the steps of:
a user inputs registration information and identity verification through an online education platform, and the online education platform carries out authority management according to the registration information input by the user; wherein the users specifically include students, teachers, and corporate training managers.
Data collection is carried out on students and/or teachers; wherein, the whole learning process of students and/or the teaching process of teachers are collected in a video mode; the method comprises the steps of collecting the voice of a student and/or the voice of a teacher in an audio mode in a whole process;
analyzing the collected data of the students according to a preset judgment strategy and outputting a judgment result; when the judgment result is output, the current time sequence information of the judgment result is also recorded; and outputting the best matching result of the student and the teacher and/or the best teaching content result of the teacher according to the judgment result and/or the time sequence information and/or the teaching process.
6. The method as claimed in claim 5, wherein outputting the best matching result of the student and the teacher and/or the best lecture content result of the teacher specifically comprises:
determining the duration time of a special attention state in time series information output by the same student in the teaching process of the same and/or different teaching contents of different teachers, sequencing the duration time of the special attention state according to the size, and matching the teacher with the maximum duration time of the special attention state with the student so as to determine the best matching result of the student and the teacher; determining the duration time of the concentration state in the time series information output by different students in the teaching process of the same and/or different teachers with the same and/or different teaching contents, sequencing the duration time of the concentration state according to the size, taking the teaching content with the maximum duration time of the concentration state as the optimal teaching content of the teachers, and outputting the optimal teaching content result of the teachers.
7. The method of claims 5-6, wherein determining a best match result for the student and the teacher further comprises: when the concentration state duration of the students for the same teaching content of different teachers is counted, the concentration state duration is multiplied by a balance coefficient p according to the sequence of teachingnSaid equilibrium coefficient pnAnd gradually increasing according to the sequence of teaching, and sequencing the corrected duration time of the concentration state according to the size to determine the best matching result.
8. The method of claims 5-7, wherein determining a best match result for the student and the teacher further comprises:
step 1: performing a thorough examination every quarter to determine the grade ranking of all students;
step 2: the student groups are sorted according to the score sequence, the sorting is segmented, n sample students are randomly extracted from each segment, the number n of the sample students is equal to the number m of the lecture teachers, and the learning progress of the sample students leads other students in the segment by one day;
and step 3: n sample students in each subsection learn the learning content of the Q day, the n sample students respectively learn the same teaching content of m teacher giving lessons, and the result of the duration time of the concentration state corresponding to the n sample students in each subsection is determined, so that the matching result of the student and the teacher giving lessons in the subsection on the learning content of the Q day is determined, wherein Q is initialized to 1;
and 4, step 4: arranging teaching teachers of other students in the next day according to the matching teachers determined in the step 3, specifically, the matching teachers determined in the step 3 are teaching teachers of other students in the next day, and the other students in the segment learn the learning content of the teaching teachers on day Q;
and 5: if the learning in one quarter is not finished, returning to the step 3, and enabling Q to be Q + 1; if the learning for one quarter is completed, the step 1 is returned.
9. The method of claims 5-6, wherein: outputting the optimal teaching content result of the teacher further comprises: grouping students corresponding to the same teaching content of different teachers, wherein the number of the students in the group is the same; respectively calculating the sum of the concentration state duration time of the same teaching content of the students in different groups and the corresponding teachers, sequencing the sum of the concentration state duration time according to the size, and taking the largest teaching content in the sum of the attention state duration time as the optimal teaching content result of the teacher.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110016118.3A CN112862639B (en) | 2021-01-07 | 2021-01-07 | Education method of online education platform based on big data analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110016118.3A CN112862639B (en) | 2021-01-07 | 2021-01-07 | Education method of online education platform based on big data analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112862639A true CN112862639A (en) | 2021-05-28 |
| CN112862639B CN112862639B (en) | 2024-04-09 |
Family
ID=76004508
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110016118.3A Active CN112862639B (en) | 2021-01-07 | 2021-01-07 | Education method of online education platform based on big data analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112862639B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113570484A (en) * | 2021-09-26 | 2021-10-29 | 广州华赛数据服务有限责任公司 | Online primary school education management system and method based on big data |
| CN116227968A (en) * | 2022-12-13 | 2023-06-06 | 广州华翰教育科技股份有限公司 | Network education effect inspection system based on real-time monitoring information feedback analysis |
| CN116580608A (en) * | 2023-04-27 | 2023-08-11 | 广东科技学院 | Artificial intelligence teaching system and artificial intelligence teaching method |
| JP7458527B1 (en) | 2023-03-17 | 2024-03-29 | Ｌｉｎｅヤフー株式会社 | Information processing device, information processing method, and program |
| CN118446426A (en) * | 2024-05-28 | 2024-08-06 | 国信蓝桥教育科技股份有限公司 | Online education system and method based on generation type artificial intelligence |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20070037962A (en) * | 2005-10-04 | 2007-04-09 | 구자용 | 3step edu system |
| CN108053700A (en) * | 2018-01-02 | 2018-05-18 | 北京建筑大学 | A kind of artificial intelligence teaching auxiliary system |
| CN108281052A (en) * | 2018-02-09 | 2018-07-13 | 郑州市第十中学 | A kind of on-line teaching system and online teaching method |
| CN108520661A (en) * | 2018-04-25 | 2018-09-11 | 广州国铭职业技能培训有限公司 | A kind of web based education and training system based on cloud platform |
-
2021
- 2021-01-07 CN CN202110016118.3A patent/CN112862639B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20070037962A (en) * | 2005-10-04 | 2007-04-09 | 구자용 | 3step edu system |
| CN108053700A (en) * | 2018-01-02 | 2018-05-18 | 北京建筑大学 | A kind of artificial intelligence teaching auxiliary system |
| CN108281052A (en) * | 2018-02-09 | 2018-07-13 | 郑州市第十中学 | A kind of on-line teaching system and online teaching method |
| CN108520661A (en) * | 2018-04-25 | 2018-09-11 | 广州国铭职业技能培训有限公司 | A kind of web based education and training system based on cloud platform |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113570484A (en) * | 2021-09-26 | 2021-10-29 | 广州华赛数据服务有限责任公司 | Online primary school education management system and method based on big data |
| CN113570484B (en) * | 2021-09-26 | 2022-02-08 | 广州华赛数据服务有限责任公司 | Online primary school education management system and method based on big data |
| CN116227968A (en) * | 2022-12-13 | 2023-06-06 | 广州华翰教育科技股份有限公司 | Network education effect inspection system based on real-time monitoring information feedback analysis |
| JP7458527B1 (en) | 2023-03-17 | 2024-03-29 | Ｌｉｎｅヤフー株式会社 | Information processing device, information processing method, and program |
| CN116580608A (en) * | 2023-04-27 | 2023-08-11 | 广东科技学院 | Artificial intelligence teaching system and artificial intelligence teaching method |
| CN118446426A (en) * | 2024-05-28 | 2024-08-06 | 国信蓝桥教育科技股份有限公司 | Online education system and method based on generation type artificial intelligence |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112862639B (en) | 2024-04-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112862639A (en) | Online education method and online education platform based on big data analysis | |
| CN110991381B (en) | Real-time classroom student status analysis and indication reminding system and method based on behavior and voice intelligent recognition | |
| CN111915148B (en) | Classroom teaching evaluation method and system based on information technology | |
| CN105069294B (en) | A kind of calculation and analysis method for cognition ability value test | |
| CN108281052A (en) | A kind of on-line teaching system and online teaching method | |
| CN109657529A (en) | Classroom teaching effect evaluation system based on human facial expression recognition | |
| CN107958351A (en) | Teaching quality assessment cloud service platform | |
| CN110164213A (en) | A kind of multiple terminals distance education and training system based on AI video analysis | |
| US20210294806A1 (en) | Method for monitoring user behavior when interacting with content and a system for its implementation | |
| CN105147304B (en) | A kind of stimulus information preparation method of personal traits value test | |
| JP2003228272A (en) | Educational material learning system | |
| US20100120012A1 (en) | System for providing online learning contents | |
| JP4631014B2 (en) | Electronic teaching material learning support device, electronic teaching material learning support system, electronic teaching material learning support method, and electronic learning support program | |
| CN112837190B (en) | Training method based on online interaction training classroom training device | |
| CN110956376B (en) | Analysis method and system suitable for measuring self-adaptive student learning effect | |
| CN112001826A (en) | Educational information intelligent classification system based on big data | |
| CN111696648A (en) | Psychological consultation platform based on Internet | |
| CN116665900A (en) | Multi-mode data driven student mental health education and monitoring system | |
| CN109886255A (en) | A kind of intelligent interaction tutoring system with facial emotions identification function | |
| CN117079772A (en) | Intelligent correction system and terminal based on mental evaluation analysis of community correction object | |
| CN112116841A (en) | Personalized remote education system and method based on deep learning | |
| CN113268512B (en) | Enterprise post professional skill training system based on internet platform | |
| CN112687138B (en) | Interactive teaching platform based on Internet of things | |
| Kumari et al. | EEG cross validation of effective mobile technology by analyzing attention level in classroom | |
| CN115511670A (en) | Online education method and online education platform |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |