Education data management system based on artificial intelligence

Abstract

The invention relates to the technical field of education data processing, in particular to an artificial intelligence-based education data management system, which comprises an education data acquisition module for acquiring course information, teaching information and classroom information in a school; the education data numbering module is used for numbering the collected course information, teaching information and classroom information in the school to obtain an education data number; the course information analysis module is used for analyzing complicated features of the course; the teaching planning analysis module is used for analyzing the teaching planning parameters and the planning completion parameters; the classroom information analysis module is used for analyzing the classroom popularity parameters, the classroom video features and the classroom audio features; the teaching comprehensive analysis module is used for analyzing the teaching quality parameters; and the data storage management module is used for classifying and storing the classroom information to obtain a classroom data category. According to the invention, accurate storage management of education data is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of educational data processing, and in particular to an educational data management system based on artificial intelligence. Background Art

[0002] Educational data storage management mainly involves cloud computing and hierarchical storage technology. Cloud computing provides efficient and flexible storage solutions, while hierarchical storage technology achieves cost optimization and performance improvement through the combination of online, near-line and offline storage, ensuring the long-term preservation and rapid access of audio and video data.

[0003] Chinese Patent Publication No.: CN116701707A discloses an educational big data management system, including a video acquisition unit, a summary extraction unit, a user information acquisition unit and a course matching unit; the video acquisition unit is used to obtain a teaching video set, and generate a teaching video key frame for each teaching video in the teaching video set; the summary extraction unit is used to generate a teaching summary for each teaching video key frame; the user information acquisition unit is used to obtain a user's course search keyword set; the course matching unit is used to match the user with the optimal teaching video according to the teaching summary corresponding to each teaching video key frame and the user's course search keyword set. The educational big data management system determines the optimal teaching video by calculating the search weight sequence and the summary weight sequence. This method realizes the analysis of videos that meet user needs based on the key frames in the collected video content, but does not realize the classified storage of educational data in combination with course content, course planning and audio and video information in the classroom. There are problems of low efficiency in educational data analysis and inaccurate storage and management of educational data. Summary of the invention

[0004] The object of the present invention is to provide an educational data management system based on artificial intelligence to solve at least one of the problems existing in the prior art.

[0005] To achieve the above object, the present invention adopts the following technical solutions: An education data management system based on artificial intelligence, comprising: Education data collection module, used to collect course information, teaching information and classroom information within the school; An education data numbering module is used to number course information, teaching information and classroom information to obtain an education data number; Course information analysis module, used to analyze the complex characteristics of courses based on education data number, course information and teaching information; Teaching plan analysis module, used to analyze teaching plan parameters and plan completion parameters according to education data number and teaching information; A classroom information analysis module is used to analyze classroom popularity parameters according to the education data number, classroom information and course information, and is also used to analyze classroom video features and classroom audio features according to the classroom information; Comprehensive teaching analysis module, used to analyze teaching quality parameters based on course complexity characteristics, teaching planning parameters, planning completion parameters, classroom popularity parameters, classroom video characteristics and classroom audio characteristics; The data storage management module is used to classify classroom information according to teaching quality parameters to obtain classroom data categories, and store classroom information and teaching information according to the classroom data categories.

[0006] Furthermore, the course information analysis module analyzes the course complexity feature according to the education data number, course information and the number of teaching nodes NC(k) to obtain the course complexity feature H(k).

[0007] Further, the teaching planning analysis module is provided with a first planning analysis unit, which is used to analyze the teaching planning parameters according to the education data number, the number of teaching nodes NC(k) and the planning progress Z1(i) to obtain the teaching planning parameters Q1(k); The teaching planning analysis module is also provided with a second planning analysis unit, which is used to analyze the planning completion parameters according to the education data number, the teaching progress Z1(i) and the actual progress Z2(i) to obtain the planning completion parameters Q2(k,i).

[0008] Furthermore, the classroom information analysis module is provided with a classroom heat analysis unit, which is used to analyze the classroom heat parameter according to the classroom number NR(k,i,t) and the course number M(k) to obtain the classroom heat parameter R(k,i).

[0009] Furthermore, the classroom information analysis module is also provided with a classroom video analysis unit, which is used to analyze the classroom video features according to the front grayscale parameters A1(k,i,t)(x,y) and the rear grayscale parameters A2(k,i,t)(x,y) to obtain the classroom video features D(k,i), and set D(k,i)=[d1(k,i)×ω1+d2(k,i)×ω2] / NT, wherein d1(k,i) represents the first video parameter, d2(k,i) represents the second video parameter, ω1 represents the first video weight, and ω2 represents the second video weight.

[0010] Furthermore, the classroom information analysis module is further provided with a classroom audio analysis unit, which is used to compare the classroom audio loudness V1(k,i,u) and V2(k,i,u) with the loudness threshold v, and analyze the loudness type according to the comparison result to obtain the loudness type, and the loudness type includes Class I and Class II; The classroom audio analysis unit analyzes the classroom audio features according to the loudness type and the classroom audio loudness to obtain the classroom audio features B(k,i), and sets B(k,i)=b1(k,i)×ω1+b2(k,i)×ω2-b3(k,i), wherein b1(k,i) represents the first audio parameter, b2(k,i) represents the second audio parameter, and b3(k,i) represents the third audio parameter.

[0011] Furthermore, the teaching comprehensive analysis module is provided with a teaching quality analysis unit, which is used to analyze the teaching quality parameters according to the course complexity feature H(k), the planning completion parameter Q2(k,i), the classroom video feature D(k,i) and the classroom audio feature B(k,i) to obtain the teaching quality parameter F(k,i).

[0012] Furthermore, the teaching comprehensive analysis module is also provided with a teaching planning analysis unit, which is used to compare the teaching planning parameter Q1(k) with the planning threshold q, and adjust the analysis process of the teaching quality parameter according to the comparison result. When the teaching planning parameter does not meet the threshold, the analysis process of the teaching quality parameter is adjusted, and the adjusted teaching planning parameter is F1(k,i).

[0013] Furthermore, the comprehensive teaching analysis module is also provided with a heat correlation analysis unit, which is used to compare the classroom heat parameter R(k,i) with the heat threshold r, and optimize the adjustment process of the teaching quality parameter according to the comparison result. When the classroom heat parameter meets the threshold, the adjustment process of the teaching quality parameter is optimized, and the optimized teaching quality parameter is F2(k,i).

[0014] Furthermore, the data storage management module compares the teaching quality parameter F(k,i) with the quality comparison threshold f, and classifies the classroom information according to the comparison result to obtain the classroom data category of the classroom information. The classroom data category of the classroom information includes category one and category two. The data storage management module stores the classroom information and teaching material information whose classroom data category is category two.

[0015] The beneficial effects of the present invention are as follows: through the collection of course information, teaching information and classroom information within the school by the education data collection module, and the comprehensive analysis of the collected information by other modules, it is possible to realize the classified storage of classroom information according to course information and audio and video information in the classroom, and to extract high-quality classroom information for users to learn and use, thereby improving the system's analysis efficiency of education data and improving the accuracy of education data storage and management. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0017] Figure 1 This is a structural diagram of the artificial intelligence-based education data management system of this embodiment.

[0018] Figure 2 Schematic diagram of the structure of the teaching planning analysis module of this embodiment.

[0019] Figure 3 This is a structural diagram of the classroom information analysis module of this embodiment.

[0020] Figure 4 Schematic diagram of the structure of the comprehensive analysis module of teaching in this embodiment. DETAILED DESCRIPTION

[0021] In order to more clearly illustrate the present invention, the present invention is further described below in conjunction with preferred embodiments and accompanying drawings. Similar components in the accompanying drawings are represented by the same reference numerals. It should be understood by those skilled in the art that the content specifically described below is illustrative rather than restrictive, and should not be used to limit the scope of protection of the present invention.

[0022] It should be noted that, although the terms first, second, third, etc. may be used to describe in the embodiments of the present application, these descriptions should not be limited to these terms. These terms are only used to distinguish the descriptions. For example, without departing from the scope of the embodiments of the present application, the first may also be referred to as the second, and similarly, the second may also be referred to as the first.

[0023] See also Figure 1 As shown, it is an education data management system based on artificial intelligence in this embodiment, including: The education data collection module is used to collect course information, teaching information and classroom information in the school. The course information includes course name, course time, number of students in the course and course duration. The course time is the class time of each course in the system, the number of students in the course is the number of students who should attend the class of each course in the system, and the course duration is the class duration of each course in the system. The course information is collected by importing data from the school's academic affairs system. The teaching information includes teaching material information and teaching progress information. The teaching material information includes but is not limited to materials such as ppt and documents used by teachers to assist teaching. The teaching progress information includes the number of teaching nodes, planned progress and actual progress. The planned progress and actual progress are percentage values, which represent the percentage of completion of the entire teaching task. The number of teaching nodes is the number of teaching tasks that the teacher needs to perform in the entire course. For example, when the course name is mathematics and its teaching tasks include functions and geometry, the number of teaching nodes is 2, and the planned progress is the number of teaching nodes planned by the teacher. the teaching progress at the end of each course, the actual progress is the actual teaching progress of the teacher at the end of each course, the teaching information is collected by interactive input by the teacher, the classroom information includes classroom video information and classroom audio loudness, the classroom video information includes video information before class and video information after class, the classroom audio loudness includes audio loudness before class and audio loudness after class, the video information before class is the video in the classroom taken by a camera installed on one side of the podium in the classroom, the audio loudness before class is the audio in the classroom collected by a microphone installed on one side of the podium in the classroom, the video information after class is the video in the classroom taken by a camera installed on one side of the back door in the classroom, the audio loudness after class is the audio in the classroom collected by a microphone installed on one side of the back door in the classroom, the classroom audio loudness is the loudness of the collected sound, in dB, and the classroom information is collected by importing the school's surveillance video data.

[0024] Specifically, this embodiment is applied to the school's data management platform cloud, which obtains and analyzes the course data and classroom video data in the school to extract and store high-quality educational data, thereby providing students with appropriate learning materials for reviewing and previewing courses.

[0025] Please continue reading Figure 1 As shown, the artificial intelligence-based education data management system also includes: The education data numbering module is used to number the course information, teaching information and classroom information to obtain the education data number. The education data number includes the course number, section number, node number and time number. The education data numbering module is connected to the education data acquisition module.

[0026] Specifically, the education data numbering module in this embodiment sets different course names to different course numbers, and sets the course number to k, k∈N + , such as k=1 means the course name is mathematics, k=2 means the course name is Chinese; the education data numbering module counts the number of course time of each course as the number of course sessions, and sets the session number according to the sequence of course time, setting the session number to i, i∈N + , i≤Ni, the course sections of each course at different times are indicated by the section number, Ni indicates the number of course sections; the education data numbering module sets a time node every T time in the course information, and numbers the time nodes in the order of the time nodes to obtain the node number, and sets the node number to t, t∈N + , t≤NT, NT=KT / T, use node numbers to distinguish classroom information corresponding to different time nodes, NT represents the number of time nodes, NT is rounded down, KT represents the course duration, T represents the node extraction parameter, 5≤T≤10; the education data numbering module sets a time number for the collected classroom audio loudness every second, and sets the time number to u, u∈N + , using time numbers to distinguish the classroom audio loudness per second. The unit of the course duration and node extraction parameters is minutes. It can be understood that the value of the node extraction parameter is not specifically limited in this embodiment, and those skilled in the art can set it freely, as long as the setting of the time node is satisfied. The optimal value of the node extraction parameter is: T=10.

[0027] Specifically, in this embodiment, the collected information is numbered by the education data numbering module to uniformly number different data according to their collection characteristics, making subsequent analysis of the collected data clearer and more accurate, thereby improving the system's analysis efficiency of education data and improving the accuracy of education data storage and management.

[0028] Please continue reading Figure 1 As shown, the artificial intelligence-based education data management system also includes: The course information analysis module is used to analyze the complex characteristics of the course according to the education data number, course information and teaching information. The course information analysis module is connected to the education data number module.

[0029] Specifically, the course information analysis module described in this embodiment analyzes the course complexity characteristics according to the education data number, course information and the number of teaching nodes, sets the course complexity characteristics to H(k), and sets H(k)=NC(k)×lnKT / Ni, where NC(k) represents the number of teaching nodes.

[0030] Specifically, in this embodiment, the course information analysis module analyzes the education data number, course information and teaching information to analyze the course complexity characteristics, and uses the course complexity characteristics to represent the characteristic relationship between the number of teaching task nodes of each course and the course hours, thereby realizing the analysis of the diversity of course content, thereby improving the system's analysis efficiency of education data and improving the accuracy of education data storage and management.

[0031] Please continue reading Figure 1 As shown, the artificial intelligence-based education data management system also includes: The teaching plan analysis module is used to analyze the teaching plan parameters and plan completion parameters according to the education data number and teaching information. The teaching plan analysis module is connected to the education data number module.

[0032] See also Figure 2 As shown, the teaching planning analysis module includes: The first planning analysis unit is used to analyze the teaching planning parameters according to the education data number, the number of teaching nodes and the planning progress.

[0033] Specifically, in this embodiment, the first planning analysis unit analyzes the teaching planning parameters according to the education data number, the number of teaching nodes and the planning progress, and sets the teaching planning parameters as Q1(k). , where Z1(i) represents the planning progress.

[0034] Specifically, in this embodiment, the first planning analysis unit analyzes the education data number, the number of teaching nodes and the planning progress to analyze the teaching planning parameters, and uses the teaching planning parameters to represent the proportional relationship between the number of teaching task nodes and the progress that needs to be completed in each class, thereby realizing the analysis of the teacher's task planning situation, thereby improving the system's analysis efficiency of education data and improving the accuracy of education data storage and management.

[0035] Please continue reading Figure 2 As shown, the teaching planning analysis module also includes: The second planning analysis unit is used to analyze the planning completion parameters according to the education data number, teaching progress and actual progress, and the second planning analysis unit is connected to the first planning analysis unit.

[0036] Specifically, in this embodiment, the second planning analysis unit analyzes the planning completion parameter according to the education data number, teaching progress and actual progress, and sets the planning completion parameter to Q2(k,i). , where Z2(i) represents the actual progress.

[0037] Specifically, in this embodiment, the second planning analysis unit analyzes the education data number, teaching progress and actual progress to analyze the planning completion parameters. The planning completion parameters are used to represent the changing characteristics of the task progress completion of each course, so as to analyze whether the actual teaching progress is completed as planned, thereby improving the system's analysis efficiency of education data and improving the accuracy of education data storage and management.

[0038] Specifically, when the second planning analysis unit in this embodiment analyzes the planning completion parameters, if the actual progress of the analysis is a null value, the actual progress is set to be the same as the planning progress corresponding to its section number, that is, Z2(i)=Z1(i), and the null value is data that the teacher has not interactively input.

[0039] Please continue reading Figure 1 As shown, the artificial intelligence-based education data management system also includes: The classroom information analysis module is used to analyze classroom popularity parameters according to the education data number, classroom information and course information, and is also used to analyze classroom video features and classroom audio features according to the classroom information. The classroom information analysis module is connected to the education data number module.

[0040] See also Figure 3 As shown, the classroom information analysis module includes: The class population analysis unit is used to analyze the class population based on pre-class video information.

[0041] Specifically, the classroom student analysis unit described in this embodiment extracts the image in the video corresponding to each time node in the pre-class video information as the pre-class analysis image, and inputs the pre-class analysis image into the target detection model to analyze the number of targets in the image as the number of students in the classroom.

[0042] Specifically, in this embodiment, the classroom number analysis unit analyzes the pre-class video information to extract the pre-class analysis image, and extracts images at different time nodes in each class, so as to analyze the number of people in the pre-class analysis image, and implement statistical analysis of the number of people based on the image, thereby improving the system's analysis efficiency of educational data and improving the accuracy of educational data storage and management.

[0043] Specifically, the target detection model described in this embodiment is an image face recognition model based on OpenCV. The model is trained using the FaceDataset face database to identify faces in images, and the target is a human face. It can be understood that the analysis process of the number of students in the classroom is not specifically limited in this embodiment, and technicians in this field can set it freely, as long as it meets the needs of counting the number of people in the video before the class. For example, a target detection model based on YoloV5 can also be used to count the number of people in the video.

[0044] Please continue reading Figure 3 As shown, the classroom information analysis module also includes: The classroom heat analysis unit is used to analyze classroom heat parameters according to the number of students in the classroom and the number of students in the course. The classroom heat analysis unit is connected to the classroom number analysis unit.

[0045] Specifically, the classroom heat analysis unit in this embodiment analyzes the classroom heat parameter according to the number of students in the classroom and the number of students in the course, sets the classroom heat parameter to R(k,i), and sets , where NR(k,i,t) represents the number of students in the classroom and M(k) represents the number of students in the course.

[0046] Specifically, in this embodiment, the classroom heat analysis unit analyzes the number of students in the classroom and the number of students in the course to analyze the classroom heat parameters. The classroom heat parameters are used to represent the proportional relationship between the number of students in the classroom analyzed by image and the actual number of students who should attend the class. This enables the judgment of students' enthusiasm for the course to be made, so as to map out whether the teaching content of the course meets the students' interests, thereby improving the system's analysis efficiency of educational data and improving the accuracy of educational data storage and management.

[0047] Please continue reading Figure 3 As shown, the classroom information analysis module also includes: The classroom video analysis unit is used to analyze classroom video features according to classroom video information, and the classroom video analysis unit is connected to the classroom heat analysis unit.

[0048] Specifically, the classroom video analysis unit described in this embodiment extracts the image in the video corresponding to each time node in the post-class video information as the post-class analysis image, and converts the classroom analysis image and the post-class analysis image into grayscale images for analysis. The classroom video analysis unit uses the lower left corner pixel point of the classroom analysis image and the post-class analysis image as the coordinate origin, and the two sides adjacent to the coordinate origin as the x-axis and y-axis. The x-axis increases from left to right, and the y-axis increases from bottom to top. The unit length is 1 pixel. A plane rectangular coordinate system is established, and the coordinate points are used to represent the position of each pixel point in the pre-class analysis image and the post-class analysis image.

[0049] Specifically, the classroom video analysis unit described in this embodiment analyzes the front grayscale parameter and the rear grayscale parameter according to the pre-class analysis image and the post-class analysis image, sets the front grayscale parameter to A1(k,i,t)(x,y), and sets A1(k,i,t)(x,y)=[L1(k,i,t)(x,y)-L1(k,i,t)(x,y) min ] / [L1(k,i,t)(x,y) max -L1(k,i,t)(x,y) min ], the grayscale parameter is set to A2(k,i,t)(x,y), set A2(k,i,t)(x,y)=[L2(k,i,t)(x,y)-L2(k,i,t)(x,y) min ] / [L2(k,i,t)(x,y) max -L2(k,i,t)(x,y) min ], where L1(k,i,t)(x,y) represents the grayscale value of each pixel in the image analyzed before class, and L1(k,i,t)(x,y) min Indicates the minimum gray value of each pixel in the image analyzed before class, L1(k,i,t)(x,y) max represents the maximum value of the grayscale value of each pixel in the image analyzed before class, L2(k,i,t)(x,y) represents the grayscale value of each pixel in the image analyzed after class, L2(k,i,t)(x,y) min Represents the minimum gray value of each pixel in the image analyzed after class, L2(k,i,t)(x,y) max It represents the maximum value of the gray value of each pixel in the image analyzed after class.

[0050] Specifically, the classroom video analysis unit in this embodiment analyzes the classroom video features according to the front grayscale parameter and the rear grayscale parameter, sets the classroom video features to D(k,i), and sets D(k,i)=[d1(k,i)×ω1+d2(k,i)×ω2] / NT, where d1(k,i) represents the first video parameter, , d2(k,i) represents the second video parameter, , ω1 represents the weight of the first video, 0.5≤ω1≤0.7, ω2 represents the weight of the second video, 0.3≤ω2≤0.5, ω1+ω2=1. It can be understood that the value of the video weight is not specifically limited in this embodiment, and those skilled in the art can freely set it as long as it meets the analysis of the characteristics of the classroom video. The optimal value of the video weight is: ω1=0.6, ω2=0.4.

[0051] Specifically, in this embodiment, the classroom video analysis unit analyzes the classroom video information to perform normalized analysis on the grayscale values ​​of the image pixels extracted from the video to analyze the front grayscale parameters and the back grayscale parameters, thereby narrowing the scope of data analysis and ensuring the accuracy of data analysis, thereby analyzing the classroom video features, and using the classroom video features to represent the grayscale value change characteristics of each pixel in the images before and after the classroom, thereby improving the system's analysis efficiency of educational data and improving the accuracy of educational data storage and management.

[0052] Please continue reading Figure 3 As shown, the classroom information analysis module also includes: The classroom audio analysis unit is used to analyze classroom audio features according to classroom audio loudness, and the classroom audio analysis unit is connected to the classroom video analysis unit.

[0053] Specifically, the classroom audio analysis unit described in this embodiment compares the classroom audio loudness with the loudness threshold, and analyzes the loudness type according to the comparison result. If V1(k,i,u)≤v and V2(k,i,u)≤v, the classroom audio analysis unit sets the loudness type corresponding to the current time number to category one; otherwise, the classroom audio analysis unit sets the loudness type corresponding to the current time number to category two; wherein, V1(k,i,u) represents the audio loudness before the class, V2(k,i,u) represents the audio loudness after the class, and v represents the loudness threshold, 20≤v≤40. It can be understood that the value of the loudness threshold is not specifically limited in this embodiment, and those skilled in the art can freely set it as long as it satisfies the analysis of the loudness type. The optimal value of the loudness threshold is: v=30.

[0054] Specifically, the classroom audio analysis unit described in this embodiment analyzes the classroom audio feature according to the loudness type and the classroom audio loudness, sets the classroom audio feature to B(k,i), and sets B(k,i)=b1(k,i)×ω1+b2(k,i)×ω2-b3(k,i), wherein b1(k,i) represents the first audio parameter, , b2(k,i) represents the second audio parameter, , b3(k,i) represents the third audio parameter, , where U1(k,i) represents the set of time numbers with loudness type one, NU1(k,i) represents the number of time numbers with loudness type one, U2(k,i) represents the set of time numbers with loudness type two, and NU2(k,i) represents the number of time numbers with loudness type two.

[0055] Specifically, in this embodiment, the classroom audio analysis unit analyzes the classroom audio loudness to analyze the loudness type corresponding to each time number, and divides the loudness type into two categories according to the size of the audio loudness before and after the class. The first category indicates that the sound signal intensity in the classroom is relatively low, and the second category indicates that the sound signal intensity in the classroom is relatively high, thereby analyzing the classroom audio characteristics, and using the classroom audio characteristics to represent the changing fluctuation characteristics of the audio loudness in each class, thereby improving the system's analysis efficiency of educational data and improving the accuracy of educational data storage and management.

[0056] Please continue reading Figure 1 As shown, the artificial intelligence-based education data management system also includes: The teaching comprehensive analysis module is used to analyze the teaching quality parameters according to the course complexity characteristics, teaching planning parameters, planning completion parameters, classroom popularity parameters, classroom video characteristics and classroom audio characteristics. The teaching comprehensive analysis module is connected with the course information analysis module, the teaching planning analysis module and the classroom information analysis module.

[0057] See also Figure 4 As shown, the teaching comprehensive analysis module includes: The teaching quality analysis unit is used to analyze the teaching quality parameters according to the complexity of the course, the planning completion parameters, the classroom video characteristics and the classroom audio characteristics. The teaching quality parameters are used to represent the analysis of the course quality based on the comprehensive course content, classroom audio and video information and the teaching plan completion status data.

[0058] Specifically, the teaching quality analysis unit in this embodiment analyzes the teaching quality parameters according to the course complexity characteristics, planning completion parameters, classroom video characteristics and classroom audio characteristics, and sets the teaching quality parameters as F(k,i), and sets F(k,i)=e H(k)+D(k,i) ×Q2(k,i)×lgB(k,i).

[0059] Please continue reading Figure 4 As shown, the teaching comprehensive analysis module also includes: The teaching planning analysis unit is used to adjust the analysis process of the teaching quality parameters according to the teaching planning parameters so that the adjusted teaching quality parameters are related to the teaching task planning situation. The teaching planning analysis unit is connected to the teaching quality analysis unit.

[0060] Specifically, the teaching planning analysis unit in this embodiment compares the teaching planning parameters with the planning threshold, and adjusts the analysis process of the teaching quality parameters according to the comparison result. If Q1(k)<q, the teaching planning analysis unit determines that the teaching planning parameters do not meet the threshold, and adjusts the analysis process of the teaching quality parameters. The adjusted teaching planning parameters are F1(k,i), and F1(k,i)=F(k,i)×e Q1(k)-1 ; If Q1(k)≥q, the teaching planning analysis unit determines that the teaching planning parameters meet the threshold value and does not adjust the analysis process of the teaching quality parameters; wherein q represents the planning threshold value, 0.5≤q≤0.8; the teaching planning analysis unit analyzes the teaching planning parameters to adjust the analysis process of the teaching quality parameters. When there are fewer teaching task nodes to be completed in each course, the teaching quality parameters are adjusted to ensure that the teaching quality parameters are related to the content data in the teaching course, thereby improving the system's analysis efficiency of educational data and improving the accuracy of educational data storage management; it can be understood that in this embodiment, the value of the planning threshold is not specifically limited, and technical personnel in this field can set it freely, as long as the adjustment of the teaching quality parameter analysis process is satisfied. The optimal value of the planning threshold is: q=0.6.

[0061] Please continue reading Figure 4 As shown, the teaching comprehensive analysis module also includes: The heat correlation analysis unit is used to optimize the adjustment process of the teaching quality parameters according to the classroom heat parameters, so that the optimized teaching quality parameters are related to the number of people in the classroom and the number of people who should attend. The heat correlation analysis unit is connected to the teaching planning analysis unit.

[0062] Specifically, the heat correlation analysis unit described in this embodiment compares the classroom heat parameter with the heat threshold, and optimizes the adjustment process of the teaching quality parameter according to the comparison result. If R(k,i)≤r, the heat correlation analysis unit determines that the classroom heat parameter does not meet the threshold, and does not optimize the adjustment process of the teaching quality parameter; if R(k,i)>r, the heat correlation analysis unit determines that the classroom heat parameter meets the threshold, and optimizes the adjustment process of the teaching quality parameter. The optimized teaching quality parameter is F2(k,i), and F2(k,i)=F1(k,i)×ln[e+R(k,i)] is set; wherein r represents Heat threshold, 0.9≤r≤1; the heat correlation analysis unit analyzes the classroom heat parameters to optimize the adjustment process of the teaching quality parameters. When there are a large number of students in the classroom, the adjustment process of the teaching quality parameters is optimized to achieve the comprehensive impact of the students' enthusiasm for class on the analysis of teaching quality parameters, thereby improving the system's analysis efficiency of educational data and improving the accuracy of educational data storage and management; it can be understood that the value of the heat threshold is not specifically limited in this embodiment, and technical personnel in this field can set it freely, as long as the optimization of the teaching quality parameter adjustment process is satisfied. The optimal value of the heat threshold is: r=0.95.

[0063] Please continue reading Figure 1 As shown, the artificial intelligence-based education data management system also includes: The data storage management module is used to classify classroom information according to teaching quality parameters to obtain classroom data categories, and store classroom information and teaching information according to the classroom data categories. The data storage management module is connected to the teaching comprehensive analysis module.

[0064] Specifically, the data storage management module described in this embodiment compares the teaching quality parameters with the quality comparison threshold, and classifies the classroom information according to the comparison results. If F(k,i)<f, the data storage management module determines that the classroom data category of the classroom information is one category; if F(k,i)≥f, the data storage management module determines that the classroom data category of the classroom information is two categories; the data storage management module stores the classroom information and teaching material information of the classroom data category two; wherein, f represents the quality comparison threshold, 1.5≤f≤2. It can be understood that the value of the quality comparison threshold is not specifically limited in this embodiment, and those skilled in the art can freely set it as long as the classification storage of classroom information is satisfied. The optimal value of the quality comparison threshold is: f=1.7.

[0065] Specifically, in this embodiment, the data storage management module analyzes the teaching quality parameters to divide the classroom information into two categories. One category indicates that the audio and video data content of the current course is poor and is not suitable for storage as reference data. The second category indicates that the audio and video data content of the current course is good and meets the needs of students. It can be stored as reference material for students to preview and review, thereby improving the system's analysis efficiency of educational data and improving the accuracy of educational data storage management.

[0066] Obviously, the above embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not limitations on the embodiments of the present invention. For those skilled in the art, other different forms of changes or modifications can be made based on the above description. It is impossible to list all the embodiments here. All obvious changes or modifications derived from the technical solution of the present invention are still within the protection scope of the present invention.

Claims

1. An educational data management system based on artificial intelligence, characterized in that: include: Education data collection module, used to collect course information, teaching information and classroom information within the school; An education data numbering module is used to number course information, teaching information and classroom information to obtain an education data number; Course information analysis module, used to analyze the complex characteristics of courses based on education data number, course information and teaching information; Teaching plan analysis module, used to analyze teaching plan parameters and plan completion parameters according to education data number and teaching information; A classroom information analysis module is used to analyze classroom popularity parameters according to the education data number, classroom information and course information, and is also used to analyze classroom video features and classroom audio features according to the classroom information; Comprehensive teaching analysis module, used to analyze teaching quality parameters based on course complexity characteristics, teaching planning parameters, planning completion parameters, classroom popularity parameters, classroom video characteristics and classroom audio characteristics; The data storage management module is used to classify classroom information according to teaching quality parameters to obtain classroom data categories, and store classroom information and teaching information according to the classroom data categories.

2. The artificial intelligence-based education data management system according to claim 1, characterized in that: The course information analysis module analyzes the course complexity feature according to the education data number, course information and the number of teaching nodes NC(k) to obtain the course complexity feature H(k).

3. The artificial intelligence-based education data management system according to claim 2, characterized in that: The teaching planning analysis module is provided with a first planning analysis unit, which is used to analyze the teaching planning parameters according to the education data number, the number of teaching nodes NC(k) and the planning progress Z1(i) to obtain the teaching planning parameters Q1(k); The teaching planning analysis module is also provided with a second planning analysis unit, which is used to analyze the planning completion parameters according to the education data number, the teaching progress Z1(i) and the actual progress Z2(i) to obtain the planning completion parameters Q2(k,i).

4. The artificial intelligence-based education data management system according to claim 3, characterized in that: The classroom information analysis module is provided with a classroom heat analysis unit, which is used to analyze the classroom heat parameter according to the classroom number NR(k,i,t) and the course number M(k) to obtain the classroom heat parameter R(k,i).

5. The artificial intelligence-based education data management system according to claim 4, characterized in that: The classroom information analysis module is also provided with a classroom video analysis unit, which is used to analyze the classroom video features according to the front grayscale parameters A1(k,i,t)(x,y) and the rear grayscale parameters A2(k,i,t)(x,y) to obtain the classroom video features D(k,i), and set D(k,i)=[d1(k,i)×ω1+d2(k,i)×ω2] / NT, wherein d1(k,i) represents the first video parameter, d2(k,i) represents the second video parameter, ω1 represents the first video weight, and ω2 represents the second video weight.

6. The artificial intelligence-based education data management system according to claim 5, characterized in that: The classroom information analysis module is further provided with a classroom audio analysis unit, which is used to compare the classroom audio loudness V1(k,i,u) and V2(k,i,u) with the loudness threshold v, and analyze the loudness type according to the comparison result to obtain the loudness type, and the loudness type includes Class I and Class II; The classroom audio analysis unit analyzes the classroom audio features according to the loudness type and the classroom audio loudness to obtain the classroom audio features B(k,i), and sets B(k,i)=b1(k,i)×ω1+b2(k,i)×ω2-b3(k,i), wherein b1(k,i) represents the first audio parameter, b2(k,i) represents the second audio parameter, and b3(k,i) represents the third audio parameter.

7. The artificial intelligence-based education data management system according to claim 6, characterized in that: The teaching comprehensive analysis module is provided with a teaching quality analysis unit, which is used to analyze the teaching quality parameters according to the course complexity feature H(k), the planning completion parameter Q2(k,i), the classroom video feature D(k,i) and the classroom audio feature B(k,i) to obtain the teaching quality parameter F(k,i).

8. The artificial intelligence-based education data management system according to claim 7, characterized in that: The teaching comprehensive analysis module is also provided with a teaching planning analysis unit, which is used to compare the teaching planning parameter Q1(k) with the planning threshold q, and adjust the analysis process of the teaching quality parameter according to the comparison result. When the teaching planning parameter does not meet the threshold, the analysis process of the teaching quality parameter is adjusted, and the adjusted teaching planning parameter is F1(k,i).

9. The artificial intelligence-based education data management system according to claim 8, characterized in that: The comprehensive teaching analysis module is also provided with a heat correlation analysis unit, which is used to compare the classroom heat parameter R(k,i) with the heat threshold r, and optimize the adjustment process of the teaching quality parameter according to the comparison result. When the classroom heat parameter meets the threshold, the adjustment process of the teaching quality parameter is optimized, and the optimized teaching quality parameter is F2(k,i).

10. The artificial intelligence-based education data management system according to claim 9, characterized in that: The data storage management module compares the teaching quality parameter F(k,i) with the quality comparison threshold f, and classifies the classroom information according to the comparison result to obtain the classroom data category of the classroom information. The classroom data category of the classroom information includes category one and category two. The data storage management module stores the classroom information and teaching material information of category two.

Images