Online education method and system based on big data

Abstract

The present invention provides an online education method and system based on big data, the method comprising: determining target students according to online education instructions; if the education type is consolidation education or preview education, determining the target subject according to the online education instructions, and determining the target teaching video in the teaching database according to the teaching progress of the target subject; determining the video playback mode according to the environmental information of the learning device, and playing the target teaching video on the learning device according to the video playback mode; if the education type is examination education, determining the test question set according to the teaching progress and student information of the target subject; generating the test paper according to the test question type and the test question set, and sending the test paper to the learning device. The present invention can effectively determine the education needs of students based on the education type, and can effectively determine the target teaching video in the teaching database based on the teaching progress of the target subject, thereby improving the adaptability and teaching quality of online education.

Description

Technical Field

[0001] The present invention relates to the field of big data technology, and in particular to an online education method and system based on big data. Background Art

[0002] With the continuous development of the Internet, online education has also gone through three stages: from distance education platforms and training institutions to online, to the current involvement of Internet companies in online education. During this development process, the forms and contents of online education have become more and more diversified, and the level of convenience has been continuously improving.

[0003] In the existing online education process, fixed teaching videos or test papers are generally played according to the teacher's teaching plan to achieve the effect of online education. However, since students' learning speeds are different in the existing online education process, it is impossible to adapt education according to students' needs, which reduces the teaching quality. Summary of the invention

[0004] The purpose of the embodiments of the present invention is to provide an online education method and system based on big data, aiming to solve the problem of low quality of existing online education and teaching.

[0005] The embodiment of the present invention is implemented as follows: an online education method based on big data, the method comprising:

[0006] receiving online education instructions, and determining target students according to the online education instructions;

[0007] Determine the teaching progress of each subject according to the student information of the target student, and determine the type of education according to the online education instruction, wherein the type of education includes consolidation education, preview education and examination education;

[0008] If the education type is the consolidation education or the preparatory education, a target subject is determined according to the online education instruction, and a target teaching video is determined in a teaching database according to the teaching progress of the target subject;

[0009] Acquire environmental information of a learning device of the target student, determine a video playback mode according to the environmental information, and play the target teaching video on the learning device according to the video playback mode;

[0010] If the education type is the examination education, determining a set of examination questions in the teaching database according to the teaching progress of the target subject and the student information;

[0011] The test question type is determined according to the online education instruction, a test paper is generated according to the test question type and the test question set, and the test paper is sent to the learning device.

[0012] Furthermore, after playing the target teaching video on the learning device according to the video playing mode, the method further includes:

[0013] Capturing images of the target students to obtain facial images, and performing expression analysis on each facial image to obtain expression types;

[0014] If any of the expression types is a preset expression, marking the facial image corresponding to the expression type as a questionable image;

[0015] Determine the questionable knowledge points in the target teaching video according to each questionable image, and determine the knowledge point video and the knowledge point test points in the teaching database according to the questionable knowledge points;

[0016] The knowledge point video and the knowledge point test points are sent to the learning device for playback.

[0017] Furthermore, determining the questionable knowledge points in the target teaching video according to each questionable image includes:

[0018] Obtaining the acquisition time of each question image respectively, and determining the video image in the target teaching video according to each acquisition time;

[0019] Searching for video knowledge points of each video image respectively, and sorting the searched video knowledge points by quantity to obtain a first knowledge point sorting;

[0020] The questionable knowledge point is determined according to the first knowledge point sorting.

[0021] Furthermore, after sending the test paper to the learning device, the method further includes:

[0022] Obtaining answer information of the target student on the test paper, and determining incorrect answers based on the answer information;

[0023] Obtain explanation videos, knowledge point information, and similar wrong questions for each wrong answer, generate wrong question QR codes based on the explanation videos, knowledge point information, and similar wrong questions for each wrong answer, and store each wrong question QR code with the student information;

[0024] When an access instruction to the wrong question QR code is received from any access device, the analysis video of the wrong answer, knowledge point information and similar wrong questions corresponding to the wrong question QR code are sent to the access device.

[0025] Furthermore, after playing the target teaching video on the learning device according to the video playing mode, the method further includes:

[0026] Capturing an image of the target student to obtain a facial image, and acquiring a pupil image in the facial image;

[0027] Determining pupil sight lines of the target student according to the pupil image, and determining the fixation point coordinates of the video image in the target teaching video according to each pupil sight line;

[0028] Performing gaze point detection on the corresponding video image according to the coordinates of each gaze point, and determining a distracting image in the video image according to the gaze point detection result;

[0029] A secondary explanation video is determined in the teaching database according to the knowledge points of each distracting image, and the secondary explanation video is sent to the learning device for playback.

[0030] Furthermore, performing gaze point detection on the corresponding video image according to the gaze point coordinates, and determining the distracting image in the video image according to the gaze point detection result, includes:

[0031] querying the valid area of ​​each video image respectively, and judging whether the gaze point coordinates are within the valid area for the same video image;

[0032] If the gaze point coordinates are not within the valid area, the video image is determined as the distracting image.

[0033] Furthermore, the determining of a secondary explanation video in the teaching database according to the knowledge points of each distracting image includes:

[0034] Merging adjacent distracting images to obtain a merged video, and performing video screening on the merged video;

[0035] Respectively query the knowledge points of each merged video after screening, and sort the knowledge points of each merged video found by quantity to obtain a second knowledge point ranking;

[0036] The secondary explanation video is determined in the teaching database according to the ranking of the second knowledge points.

[0037] Furthermore, the video screening of the merged video includes:

[0038] Get the video duration of each merged video respectively;

[0039] If the video length of any of the merged videos is less than the length threshold, the merged video is deleted.

[0040] Furthermore, generating the test paper according to the test question type and the test question set includes:

[0041] If the test question type is a knowledge point type, then respectively obtaining test questions of each knowledge point in the test question set, and generating the test paper according to the obtained test questions;

[0042] If the test question type is a wrong question type, rank the wrong questions in the test question set, and generate the test paper according to the rank of the wrong questions;

[0043] If the test question type is a consolidation type, the consolidation knowledge points are determined according to the teaching progress of the target subject and the student information, the test questions of each consolidation knowledge point in the test question set are obtained respectively, and the test paper is generated according to the obtained test questions.

[0044] Another object of an embodiment of the present invention is to provide an online education system based on big data, the system comprising:

[0045] A student determination module, used for receiving online education instructions and determining target students according to the online education instructions;

[0046] A type determination module, used to determine the teaching progress of each subject according to the student information of the target student, and determine the education type according to the online education instruction, wherein the education type includes consolidation education, preview education and examination education;

[0047] A video determination module, for determining a target subject according to the online education instruction if the education type is the consolidation education or the preview education, and determining a target teaching video in a teaching database according to the teaching progress of the target subject;

[0048] A video playing module, used for obtaining the environment information of the learning device of the target student, determining the video playing mode according to the environment information, and playing the target teaching video on the learning device according to the video playing mode;

[0049] An examination question determination module, for determining an examination question set in the teaching database according to the teaching progress of the target subject and the student information if the education type is the examination education;

[0050] The test paper generating module is used to determine the test question type according to the online education instruction, generate the test paper according to the test question type and the test question set, and send the test paper to the learning device.

[0051] The embodiments of the present invention can effectively determine the type of education based on online education instructions, can effectively determine the education needs of students based on the education type, can determine the teaching progress of each subject through the student information of the target student, can effectively determine the target teaching video in the teaching database based on the teaching progress of the target subject, and then can effectively query the corresponding target teaching video according to the learning speed of each student, thereby improving the adaptability of online education and the teaching quality, and improving the accuracy of the target teaching video playback based on the environmental information by obtaining the environmental information of the target student's learning device, and determining the test question set in the teaching database through the teaching progress and student information of the target subject, so as to determine the test question set in a big data manner, thereby improving the accuracy of the test paper. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 is a flow chart of an online education method based on big data provided by a first embodiment of the present invention;

[0053] Figure 2 is a flow chart of an online education method based on big data provided by a second embodiment of the present invention;

[0054] Figure 3 is a structural diagram of an online education system based on big data provided by a third embodiment of the present invention;

[0055] Figure 4 It is a schematic diagram of the structure of a terminal device provided in the fourth embodiment of the present invention. DETAILED DESCRIPTION

[0056] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0057] In order to illustrate the technical solution of the present invention, a specific embodiment is provided below for illustration.

[0058] Embodiment 1

[0059] See also Figure 1 , is a flow chart of an online education method based on big data provided by a first embodiment of the present invention. The online education method based on big data can be applied to any online education system. The online education method based on big data includes the following steps:

[0060] Step S10, receiving an online education instruction, and determining a target student according to the online education instruction;

[0061] The online education instruction can be transmitted in the form of voice instruction, gesture instruction or key instruction. In this step, when the online education system receives the online education instruction sent by any terminal device, the student identifier stored in the online education instruction is matched with the student database to determine the target student;

[0062] Optionally, the student identifier may be stored in the form of a digital number, an alphabetic number, text or an image, and the student database stores the correspondence between different student identifiers and corresponding target students, and the terminal device includes a mobile phone, a computer, a tablet or a wearable smart device, etc.;

[0063] Step S20, determining the teaching progress of each subject according to the student information of the target student, and determining the education type according to the online education instruction;

[0064] The education types include consolidation education, preparatory education and examination education. The student information includes gender, age, class information and curriculum information. The teaching progress of the target student corresponding to each subject is determined by matching the student information of the target student with a pre-stored progress query table. The corresponding relationship between different learning information and the teaching progress of each subject is stored in the progress query table.

[0065] In this step, the education type is determined through the online education instruction, which can effectively determine the education needs of the target students. For example, when the education type is consolidation education, it is determined that the target students need to conduct consolidation learning for the knowledge points before the teaching progress. When the education type is preview education, it is determined that the target students need to conduct preview learning for the knowledge points after the teaching progress. When the education type is examination education, it is determined that the target students need to study for the examination.

[0066] Step S30, if the education type is the consolidation education or the preview education, determining the target subject according to the online education instruction, and determining the target teaching video in the teaching database according to the teaching progress of the target subject;

[0067] Among them, the teaching progress of each subject is determined by the student information of the target students. Based on the teaching progress of the target subject, the target teaching video can be effectively determined in the teaching database, and then the corresponding target teaching video can be effectively queried according to the learning speed of each student, which improves the adaptability of online education and improves the teaching quality;

[0068] Step S40, obtaining the environment information of the learning device of the target student, determining the video playing mode according to the environment information, and playing the target teaching video on the learning device according to the video playing mode;

[0069] Among them, by obtaining the environment information of the target student's learning device, the video playback mode of the target teaching video can be effectively determined based on the environment information, and the accuracy of the target teaching video playback is improved based on the video playback mode;

[0070] In this step, different video playback modes are set for different learning environments. The environment information includes environment images and background audio information. Based on the environment images and background audio information, the environment type of the current environment of the learning device is determined, and the environment type is matched with a pre-stored playback mode query table to obtain the video playback mode of the target teaching video. The playback mode query table stores the corresponding relationship between different environment types and corresponding video playback modes.

[0071] Step S50, if the education type is the examination education, determining a set of examination questions in the teaching database according to the teaching progress of the target subject and the student information;

[0072] If the education type is exam education, it is determined that the target students have a need for exam practice. The test question set can be automatically determined in the teaching database based on the teaching progress and student information of the target subject. Based on the test set, the accuracy of subsequent test paper generation is improved.

[0073] Step S60, determining the type of test questions according to the online education instruction, generating a test paper according to the test question type and the test question set, and sending the test paper to the learning device;

[0074] The test question types include knowledge point types, wrong question types and consolidation types. When the test type is a knowledge point type, it is determined that the target student needs to practice test questions on knowledge points. When the test type is a wrong question type, it is determined that the target student needs to practice test questions on wrong questions. When the test type is a consolidation type, it is determined that the target student needs to practice test questions to consolidate previous learning courses.

[0075] Optionally, in this step, after sending the test paper to the learning device, the step further includes:

[0076] Obtaining answer information of the target student on the test paper, and determining incorrect answers based on the answer information;

[0077] The answer information stores the answer options of the target student to the test questions, searches for the correct answer to the test questions, matches the correct answer with the answer information, and determines the test questions that are not matched correctly as the wrong answers;

[0078] Obtain explanation videos, knowledge point information, and similar wrong questions for each wrong answer, generate wrong question QR codes based on the explanation videos, knowledge point information, and similar wrong questions for each wrong answer, and store each wrong question QR code with the student information;

[0079] Among them, by obtaining the explanation video, knowledge point information and similar wrong questions of each wrong answer, based on the explanation video, knowledge point information and similar wrong questions of each wrong answer, the generation of the wrong question QR code is improved;

[0080] When receiving an access instruction to the wrong question QR code from any access device, the analysis video of the wrong answer, the knowledge point information and similar wrong questions corresponding to the wrong question QR code are sent to the access device;

[0081] When receiving an access instruction to a QR code from any access device, the analysis video of the wrong answer corresponding to the wrong question QR code, the knowledge point information and similar wrong questions are sent to the access device, so as to facilitate the learning of the wrong answer by the student corresponding to the access device;

[0082] Furthermore, in this embodiment, after playing the target teaching video on the learning device according to the video playing mode, it also includes:

[0083] Capturing an image of the target student to obtain a facial image, and acquiring a pupil image in the facial image;

[0084] The learning device is provided with an image acquisition device, through which the image acquisition device is used to acquire images of the target student in real time to obtain the facial image, and the pupil image is obtained by screenshotting the pupil area in the facial image;

[0085] Determining pupil sight lines of the target student according to the pupil image, and determining the fixation point coordinates of the video image in the target teaching video according to each pupil sight line;

[0086] Among them, the pupil sight line of the target student can be effectively determined through the pupil image, and based on the pupil sight line, the coordinates of the gaze point in the corresponding video image can be effectively determined;

[0087] Performing gaze point detection on the corresponding video image according to the coordinates of each gaze point, and determining a distracting image in the video image according to the gaze point detection result;

[0088] The corresponding video image is subjected to gaze point detection through the gaze point coordinates to detect whether the target student is distracted when watching the video image, and the distracting image in the video image is determined according to the gaze point detection result;

[0089] Determining a secondary explanation video in the teaching database according to the knowledge points of each distracting image, and sending the secondary explanation video to the learning device for playback;

[0090] Among them, a secondary explanation video is determined in the teaching database through the knowledge points of each distracting image. Based on the secondary explanation video, the knowledge points that the target students are distracted from can be effectively explained again, thereby improving the teaching quality;

[0091] Furthermore, performing gaze point detection on the corresponding video image according to the gaze point coordinates, and determining the distracting image in the video image according to the gaze point detection result, includes:

[0092] querying the valid area of ​​each video image respectively, and judging whether the gaze point coordinates are within the valid area for the same video image;

[0093] Wherein, each video image is matched with a pre-stored effective area query table to obtain the effective area, wherein the effective area query table stores the correspondence between different video images and corresponding effective areas, and determines whether the viewpoint coordinates are within the effective area;

[0094] If the gaze point coordinates are within the valid area, it is determined that the target student is not in a distracted state when watching the video image; if the gaze point coordinates are not within the valid area, the video image is determined to be the distracting image.

[0095] Preferably, determining a secondary explanation video in the teaching database according to the knowledge points of each distracting image includes:

[0096] Merging the adjacent distracting images to obtain a merged video, and performing video screening on the merged video; wherein, by performing video screening on the merged video, the accuracy of the merged video can be effectively improved;

[0097] Respectively query the knowledge points of each merged video after screening, and sort the knowledge points of each merged video found out by quantity, so as to obtain a second knowledge point sorting; wherein, by sorting the knowledge points of each merged video found out by quantity, the knowledge points with a larger quantity among the knowledge points of the merged video are determined;

[0098] Determine the secondary explanation video in the teaching database according to the second knowledge point ranking; wherein the first three knowledge points in the second knowledge point ranking are matched with a video query table in the teaching database to obtain the secondary explanation video, wherein the video query table stores the correspondence between different knowledge points and corresponding videos;

[0099] Optionally, the video screening of the merged video includes: respectively obtaining the video duration of each merged video; if the video duration of any of the merged videos is less than a duration threshold, deleting the merged video;

[0100] In this embodiment, generating the test paper according to the test question type and the test question set includes:

[0101] If the test question type is a knowledge point type, then the test questions for each knowledge point in the test question set are obtained respectively, and the test paper is generated based on the obtained test questions; if the test question type is a wrong question type, then the wrong questions in the test question set are sorted, and the test paper is generated based on the sorting of the wrong questions; if the test question type is a consolidation type, then the consolidation knowledge points are determined based on the teaching progress of the target subject and the student information, and the test questions for each consolidation knowledge point in the test question set are obtained respectively, and the test paper is generated based on the obtained test questions.

[0102] In this embodiment, the type of education can be effectively determined based on online education instructions, the educational needs of students can be effectively determined based on the education type, the teaching progress of each subject can be determined through the student information of the target students, and the target teaching video can be effectively determined in the teaching database based on the teaching progress of the target subject. Then, the corresponding target teaching video can be effectively queried according to the learning speed of each student, thereby improving the adaptability of online education and the teaching quality. By acquiring the environmental information of the target student's learning device, the accuracy of the target teaching video playback is improved based on the environmental information, and the test question set is determined in the teaching database through the teaching progress and student information of the target subject. The test question set is determined in a big data manner, thereby improving the accuracy of the test paper.

[0103] Embodiment 2

[0104] See also Figure 2 , is a flow chart of an online education method based on big data provided by a second embodiment of the present invention, and this embodiment is used to further refine the steps after step S60, including the steps of:

[0105] Step S70, collecting images of the target students to obtain facial images, and performing expression analysis on each facial image to obtain expression types;

[0106] Among them, each facial image can be input into the pre-trained expression recognition model for expression analysis to obtain the expression type, which is used to characterize the expression state of the target student at the corresponding moment, and the expression state includes a state of doubt, a state of happiness, and a state of concentration, etc.;

[0107] Step S80, if any of the expression types is a preset expression, marking the facial image corresponding to the expression type as a question image;

[0108] The preset expression can be set according to the requirements. In this step, the preset expression is set to a doubt state, that is, when the expression type of any facial image is identified as a doubt state, the facial image is marked as a questionable image;

[0109] Step S90, determining the questionable knowledge points in the target teaching video according to each questionable image, and determining the knowledge point video and the knowledge point test point in the teaching database according to the questionable knowledge point;

[0110] Among them, each questionable knowledge point is matched with a pre-stored video query table to obtain the knowledge point video and knowledge point test point, and the video query table stores the correspondence between different questionable knowledge points and the corresponding knowledge point videos and knowledge point test points;

[0111] Optionally, in this step, determining the questionable knowledge points in the target teaching video according to each questionable image includes:

[0112] The acquisition time of each question image is obtained respectively, and the video image in the target teaching video is determined according to each acquisition time; wherein, the image at each acquisition time in the target teaching video is obtained respectively to obtain the video image;

[0113] Searching for video knowledge points of each video image respectively, sorting the searched video knowledge points by quantity, obtaining a first knowledge point sorting, and determining the question knowledge points according to the first knowledge point sorting; wherein the top three knowledge points in the first knowledge point sorting are determined as question knowledge points;

[0114] Step S100, sending the knowledge point video and the knowledge point test points to the learning device for playback;

[0115] In this embodiment, the target student's image is captured to obtain the target student's facial image, and the facial expression state of the target student at each moment is obtained by performing expression analysis on each facial image. When the expression type of any facial image is identified as a state of doubt, the facial image is marked as a question image, thereby improving the accuracy of question image marking. The question knowledge points in the target teaching video can be effectively determined through each question image, and the knowledge point video and knowledge point test points can be effectively determined in the teaching database based on the question knowledge points. By sending the knowledge point video and knowledge point test points to the learning device for playback, the knowledge point content that the target student has not understood can be effectively played back for learning, thereby improving the teaching quality.

[0116] Embodiment 3

[0117] See also Figure 3 , is a schematic diagram of the structure of an online education system 100 based on big data provided by a third embodiment of the present invention, comprising: a student determination module 10, a type determination module 11, a video determination module 12, a video playback module 13, a test question determination module 14 and a test paper generation module 15, wherein:

[0118] The student determination module 10 is used to receive online education instructions and determine target students according to the online education instructions.

[0119] The type determination module 11 is used to determine the teaching progress of each subject according to the student information of the target student, and determine the education type according to the online education instruction, and the education type includes consolidation education, preview education and examination education.

[0120] The video determination module 12 is used to determine the target subject according to the online education instruction if the education type is the consolidation education or the preview education, and to determine the target teaching video in the teaching database according to the teaching progress of the target subject.

[0121] The video playing module 13 is used to obtain the environment information of the learning device of the target student, determine the video playing mode according to the environment information, and play the target teaching video on the learning device according to the video playing mode.

[0122] Optionally, the video playback module 13 is further used to: collect images of the target students to obtain facial images, and perform expression analysis on each facial image to obtain expression types;

[0123] If any of the expression types is a preset expression, marking the facial image corresponding to the expression type as a questionable image;

[0124] Determine the questionable knowledge points in the target teaching video according to each questionable image, and determine the knowledge point video and the knowledge point test points in the teaching database according to the questionable knowledge points;

[0125] The knowledge point video and the knowledge point test points are sent to the learning device for playback.

[0126] Furthermore, the video playback module 13 is also used to: respectively obtain the acquisition time of each question image, and determine the video image in the target teaching video according to each acquisition time;

[0127] Searching for video knowledge points of each video image respectively, and sorting the searched video knowledge points by quantity to obtain a first knowledge point sorting;

[0128] The questionable knowledge point is determined according to the first knowledge point sorting.

[0129] Furthermore, the video playback module 13 is also used to: collect images of the target student to obtain a facial image, and obtain a pupil image in the facial image;

[0130] Determining pupil sight lines of the target student according to the pupil image, and determining the fixation point coordinates of the video image in the target teaching video according to each pupil sight line;

[0131] Performing gaze point detection on the corresponding video image according to the coordinates of each gaze point, and determining a distracting image in the video image according to the gaze point detection result;

[0132] A secondary explanation video is determined in the teaching database according to the knowledge points of each distracting image, and the secondary explanation video is sent to the learning device for playback.

[0133] Preferably, the video playback module 13 is further used to: query the valid area of ​​each video image respectively, and for the same video image, determine whether the gaze point coordinates are within the valid area;

[0134] If the gaze point coordinates are not within the valid area, the video image is determined as the distracting image.

[0135] In this embodiment, the video playback module 13 is further used to: merge the adjacent distracting images to obtain a merged video, and perform video screening on the merged video;

[0136] Respectively query the knowledge points of each merged video after screening, and sort the knowledge points of each merged video found by quantity to obtain a second knowledge point ranking;

[0137] The secondary explanation video is determined in the teaching database according to the ranking of the second knowledge points.

[0138] Optionally, the video playback module 13 is further used to: obtain the video duration of each merged video respectively;

[0139] If the video length of any of the merged videos is less than the length threshold, the merged video is deleted.

[0140] The test question determination module 14 is used to determine a test question set in the teaching database according to the teaching progress of the target subject and the student information if the education type is the examination education.

[0141] The test paper generating module 15 is used to determine the test question type according to the online education instruction, generate the test paper according to the test question type and the test question set, and send the test paper to the learning device.

[0142] Optionally, the test paper generating module 15 is further used to: obtain the answer information of the target student for the test paper, and determine the wrong answers according to the answer information;

[0143] Obtain explanation videos, knowledge point information, and similar wrong questions for each wrong answer, generate wrong question QR codes based on the explanation videos, knowledge point information, and similar wrong questions for each wrong answer, and store each wrong question QR code with the student information;

[0144] When an access instruction to the wrong question QR code is received from any access device, the analysis video of the wrong answer, knowledge point information and similar wrong questions corresponding to the wrong question QR code are sent to the access device.

[0145] Furthermore, the test paper generating module 15 is further configured to: if the test question type is a knowledge point type, respectively obtain test questions of each knowledge point in the test question set, and generate the test paper according to the obtained test questions;

[0146] If the test question type is a wrong question type, rank the wrong questions in the test question set, and generate the test paper according to the rank of the wrong questions;

[0147] If the test question type is a consolidation type, the consolidation knowledge points are determined according to the teaching progress of the target subject and the student information, the test questions of each consolidation knowledge point in the test question set are obtained respectively, and the test paper is generated according to the obtained test questions.

[0148] In this embodiment, the type of education can be effectively determined based on online education instructions, the educational needs of students can be effectively determined based on the education type, the teaching progress of each subject can be determined through the student information of the target students, and the target teaching video can be effectively determined in the teaching database based on the teaching progress of the target subject. Then, the corresponding target teaching video can be effectively queried according to the learning speed of each student, thereby improving the adaptability of online education and the teaching quality. By acquiring the environmental information of the target student's learning device, the accuracy of the target teaching video playback is improved based on the environmental information, and the test question set is determined in the teaching database through the teaching progress and student information of the target subject. The test question set is determined in a big data manner, thereby improving the accuracy of the test paper.

[0149] Embodiment 4

[0150] Figure 4 2 is a block diagram of a terminal device 2 provided in the fourth embodiment of the present application. Figure 4As shown, the terminal device 2 of this embodiment includes: a processor 20, a memory 21, and a computer program 22 stored in the memory 21 and executable on the processor 20, such as a program of an online education method based on big data. When the processor 20 executes the computer program 22, the steps in each embodiment of the online education method based on big data are implemented, such as Figure 1 S10 to S60 as shown, or Figure 2 Alternatively, the processor 20 implements the above when executing the computer program 22 Figure 3 For details on the functions of each unit in the corresponding embodiment, please refer to Figure 3 The relevant descriptions in the corresponding embodiments are not repeated here.

[0151] Exemplarily, the computer program 22 may be divided into one or more units, which are stored in the memory 21 and executed by the processor 20 to complete the present application. The one or more units may be a series of computer program instruction segments capable of completing specific functions, which are used to describe the execution process of the computer program 22 in the terminal device 2. For example, the computer program 22 may be divided into a student determination module 10, a type determination module 11, a video determination module 12, a video playback module 13, a test question determination module 14, and a test paper generation module 15, and the specific functions of each unit are as described above.

[0152] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. An online education method based on big data, characterized in that: The method comprises: receiving online education instructions, and determining target students according to the online education instructions; Determine the teaching progress of each subject according to the student information of the target student, and determine the type of education according to the online education instruction, wherein the type of education includes consolidation education, preview education and examination education; If the education type is the consolidation education or the preparatory education, a target subject is determined according to the online education instruction, and a target teaching video is determined in a teaching database according to the teaching progress of the target subject; Acquire environmental information of a learning device of the target student, determine a video playback mode according to the environmental information, and play the target teaching video on the learning device according to the video playback mode; After playing the target teaching video on the learning device according to the video playing mode, the method further includes: Capturing images of the target students to obtain facial images, and performing expression analysis on each facial image to obtain expression types; If any of the expression types is a preset expression, marking the facial image corresponding to the expression type as a questionable image; Determine the questionable knowledge points in the target teaching video according to each questionable image, and determine the knowledge point video and the knowledge point test points in the teaching database according to the questionable knowledge points; Sending the knowledge point video and the knowledge point test points to the learning device for playback; The step of determining the questionable knowledge points in the target teaching video according to each questionable image includes: Obtaining the acquisition time of each question image respectively, and determining the video image in the target teaching video according to each acquisition time; Searching for video knowledge points of each video image respectively, and sorting the searched video knowledge points by quantity to obtain a first knowledge point sorting; Determine the questionable knowledge point according to the first knowledge point ranking; After playing the target teaching video on the learning device according to the video playing mode, the method further includes: Capturing an image of the target student to obtain a facial image, and acquiring a pupil image in the facial image; Determining pupil sight lines of the target student according to the pupil image, and determining the gaze point coordinates of the video image in the target teaching video according to each pupil sight line; Performing gaze point detection on the corresponding video image according to the gaze point coordinates, and determining a distracting image in the video image according to the gaze point detection result; Determining a secondary explanation video in the teaching database according to the knowledge points of each distracting image, and sending the secondary explanation video to the learning device for playback; The step of performing gaze point detection on the corresponding video image according to the gaze point coordinates, and determining the distracting image in the video image according to the gaze point detection result includes: querying the valid area of ​​each video image respectively, and judging whether the gaze point coordinates are within the valid area for the same video image; If the gaze point coordinates are not within the valid area, determining the video image as the distracting image; The determining of the secondary explanation video in the teaching database according to the knowledge points of each distracting image comprises: Merging adjacent distracting images to obtain a merged video, and performing video screening on the merged video; Respectively query the knowledge points of each merged video after screening, and sort the knowledge points of each merged video found by quantity to obtain a second knowledge point ranking; Determine the secondary explanation video in the teaching database according to the ranking of the second knowledge points; If the education type is the examination education, determining a set of examination questions in the teaching database according to the teaching progress of the target subject and the student information; The test question type is determined according to the online education instruction, a test paper is generated according to the test question type and the test question set, and the test paper is sent to the learning device.

2. The online education method based on big data as claimed in claim 1, characterized in that: After sending the test paper to the learning device, the method further includes: Obtaining answer information of the target student for the test paper, and determining incorrect answers based on the answer information; Obtain explanation videos, knowledge point information, and similar wrong questions for each wrong answer, generate wrong question QR codes based on the explanation videos, knowledge point information, and similar wrong questions for each wrong answer, and store each wrong question QR code with the student information; When an access instruction to the wrong question QR code is received from any access device, the analysis video of the wrong answer, knowledge point information and similar wrong questions corresponding to the wrong question QR code are sent to the access device.

3. The online education method based on big data as claimed in claim 1, characterized in that: The step of screening the merged video includes: Get the video duration of each merged video respectively; If the video length of any of the merged videos is less than the length threshold, the merged video is deleted.

4. The online education method based on big data as claimed in claim 1, characterized in that: Generating the examination paper according to the examination question type and the examination question set includes: If the test question type is a knowledge point type, then respectively obtaining test questions of each knowledge point in the test question set, and generating the test paper according to the obtained test questions; If the test question type is a wrong question type, rank the wrong questions in the test question set, and generate the test paper according to the rank of the wrong questions; If the test question type is a consolidation type, the consolidation knowledge points are determined according to the teaching progress of the target subject and the student information, the test questions of each consolidation knowledge point in the test question set are obtained respectively, and the test paper is generated according to the obtained test questions.

5. An online education system based on big data, used to implement an online education method based on big data as described in any one of claims 1 to 4, characterized in that: The system comprises: A student determination module, used for receiving online education instructions and determining target students according to the online education instructions; A type determination module, used to determine the teaching progress of each subject according to the student information of the target student, and determine the education type according to the online education instruction, wherein the education type includes consolidation education, preview education and examination education; A video determination module, for determining a target subject according to the online education instruction if the education type is the consolidation education or the preview education, and determining a target teaching video in a teaching database according to the teaching progress of the target subject; A video playing module, used for obtaining the environment information of the learning device of the target student, determining the video playing mode according to the environment information, and playing the target teaching video on the learning device according to the video playing mode; An examination question determination module, for determining an examination question set in the teaching database according to the teaching progress of the target subject and the student information if the education type is the examination education; The test paper generating module is used to determine the test question type according to the online education instruction, generate the test paper according to the test question type and the test question set, and send the test paper to the learning device.

Images