Intelligent supervision method and system for learning course users based on image recognition

Abstract

The present invention discloses a method and system for intelligent supervision of learning course users based on image recognition, which relates to the technical field of learning status supervision. The method comprises collecting user learning performance level data, user learning image data and user learning range course data; based on the user learning image data and micro-expression type image data, performing micro-expression type analysis and processing during user learning, and generating user micro-expression type change characteristic data; the method and system for intelligent supervision of learning course users based on image recognition, by collecting user micro-expression data and analyzing the characteristics of micro-expression changes of users during the learning process, judges the learning efficiency of users, facilitates understanding the learning efficiency of each user student in the learning course, and recommends methods for adjusting the learning status to users when the user's learning efficiency is reduced, so as to ensure that users learn in a good learning state, and recommends more suitable courses to users when the user's learning efficiency is extremely low.

Description

Technical Field

[0001] The present invention relates to the technical field of learning status supervision, and in particular to an intelligent supervision method and system for learning course users based on image recognition. Background Art

[0002] In order to ensure that users can learn effectively, intelligent means are now used to monitor, evaluate and optimize learners' online learning behavior and status during their learning period, which is mainly used in online education platforms. The existing technology with publication number CN114612271A discloses an online course intelligent supervision system, method and storage medium, which belongs to the field of online supervision technology, including a photo pre-storage device, a first image detection device, an authority judgment device, a human body detection device, an automatic pause device, a second image detection device, and an automatic resume device. By controlling the orderly startup of each device, it can be effectively guaranteed that the online course learning user is the one who is learning online, and it can also prevent the online course learning user from failing the course. After the online course learning user leaves, the learning course will be automatically paused. After the user comes back, it will continue to determine whether it is the online course learning user himself. After the face recognition is completed, it will be determined whether the online course learning user has annotated the online course direction to determine whether it has entered the learning state. If all requirements are met, the learning course will be automatically resumed. In addition, the orderly startup of each device can greatly reduce the energy consumption of the entire system and prevent some devices from being in an invalid working state.

[0003] However, judging whether a user is learning only by whether their gaze is focused cannot determine whether the user is distracted or focused on learning, nor can it adjust the user's learning rhythm according to the user's learning status to ensure the user's learning efficiency. Summary of the Invention

[0004] The purpose of the present invention is to provide a method and system for intelligent supervision of learning course users based on image recognition to solve the above-mentioned deficiencies in the prior art.

[0005] In order to achieve the above-mentioned object, the present invention provides the following technical solution: a method for intelligent supervision of users of learning courses based on image recognition, comprising the following steps:

[0006] S1, collect user learning performance level data, user learning image data and user learning range course data;

[0007] S2. Analyzing and processing the micro-expression type of the user during learning based on the user learning image data and the micro-expression type image data to generate characteristic data of changes in the user's micro-expression type;

[0008] S3. Based on the recently set time-length user micro-expression type change feature data and abnormal type micro-expression type change feature data, perform user abnormal learning state type analysis processing to generate user abnormal learning state type analysis data;

[0009] S4. Based on the change characteristics of the user's abnormal learning state type analysis data and the change characteristics of the high-efficiency and low-efficiency learning abnormal learning state type, perform user high-efficiency and low-efficiency learning analysis;

[0010] S5. If the user is an inefficient learner, based on the user's learning performance level data, the user's learning scope course data, and the non-inefficient learner's scope course performance level data, search for non-inefficient learner courses with the same learning scope and user's learning performance level, and generate user recommended course data;

[0011] S6. If the user is not an inefficient learner, then based on the change characteristics of the user's abnormal learning state type analysis data and the abnormal learning state type characteristic data of the adjustment plan user, perform an adjustment plan analysis that matches the user's abnormal learning state, and generate adjustment plan analysis data;

[0012] S7. Build management data and perform user learning management tasks based on the management data.

[0013] Furthermore, the S1 includes the following steps:

[0014] S11. Collect user learning performance level data and generate user learning performance level data set , , Represents the learning performance level data of the i-th user, is the maximum number of users;

[0015] S12. Generate a user learning image data set by collecting monitoring videos of the user learning , , represents the w-th user learning image data of the i-th user, The maximum number of user learning image data for the i-th user;

[0016] S13. Collect user learning scope course data and generate user learning scope course data set , , represents the pth course in the oth category of learning, Indicates the maximum number of course types in the oth learning scope.

[0017] Furthermore, the S2 includes the following steps:

[0018] S21. Collect micro-expression type image data and generate a micro-expression type image data set , , represents the u-th type of micro-expression image data, Indicates the maximum number of micro-expression types;

[0019] S22, after extracting features from the user learning image data set B and the micro-expression type image data set D, search for the user image data in the user image data set B based on the nearest neighbor search algorithm. Matching micro-expression type image data , generate a data set of user micro-expression type change characteristics ; Feature extraction can be done by using a pre-trained deep convolutional neural network (such as ResNet, VGG, EfficientNet) to extract the high-dimensional feature vector of the image, such as inputting all images in B and D into the model and extracting the features of the last fully connected layer or pooling layer as representation.

[0020] Furthermore, the S3 includes the following steps:

[0021] S31, using a sliding window of a set length to collect the user's micro-expression type change feature data set Swipe up to generate the current user's micro-expression type change feature data ;

[0022] S32: Collect abnormal micro-expression type change feature data and generate abnormal micro-expression type change feature data set , , Represents the characteristic data of the micro-expression type change of the wth abnormal type, Indicates the maximum number of exception types;

[0023] S33, based on the ant colony search algorithm, searching for the characteristic data of the micro-expression type change of the current user Matched abnormal type micro-expression type change feature data , generate user abnormal learning status type analysis data , specifically including the following steps:

[0024] S331, initialize algorithm parameters, pheromones, number of abnormal type search ants N, maximum number of iterations T, the algorithm parameters include pheromone volatility coefficient (Usually 0< <1) Importance of pheromones , the importance of heuristic factors , pheromone enhancement constant ;

[0025] S332, let each abnormal type search ant start from the starting point, select the next node to reach according to the probability selection rule formula, until the complete path is completed, and calculate the complete path distance , the probability selection rule formula is as follows:

[0026] ,

[0027] in, represents the probability that the abnormal type search ant k at node i chooses to move to node j, represents the pheromone concentration of path (i, j) at the tth iteration, is the heuristic factor, u is the point not visited by the abnormal type search ant k;

[0028] S333. Update the pheromone concentration according to the proportional volatilization of pheromones on all edges. The formula is as follows:

[0029] ;

[0030] S334. Simulate the abnormal type search ant to release pheromone on the path (i, j) to update the pheromone. The formula is as follows:

[0031] ;

[0032] in,

[0033] ;

[0034] S335. If the maximum number of iterations T is reached, the complete path distance is output. Abnormal type micro-expression type change feature data corresponding to the shortest complete path , generate user abnormal learning status type analysis data , otherwise return to step S332.

[0035] Furthermore, the S4 includes the following steps:

[0036] S41, collect high-efficiency learning abnormal learning state type change feature data and low-efficiency learning abnormal learning state type change feature data set to generate high-efficiency learning abnormal learning state type change feature data ,in Indicates the characteristic data of the type change of efficient learning abnormal learning state, Indicates the characteristic data of the type change of inefficient learning and abnormal learning state;

[0037] S42. Collect the user's abnormal learning status type analysis data for the most recent set duration according to the set frequency , generate analysis data on abnormal learning status types of users in the current period ;

[0038] S43, based on the ant colony search algorithm, use the abnormal abnormal learning state type change feature search ant search and the current period user abnormal learning state type analysis data Match high-efficiency and low-efficiency learning abnormal learning state type change feature data to generate high-efficiency and low-efficiency learning state judgment data If no analysis data related to the abnormal learning status of users in the current period is found, Matching high and low efficiency learning abnormal learning state type change feature data, then is 0.

[0039] Furthermore, the S5 includes the following steps:

[0040] S51, judging data on the high and low efficiency learning state , user learning performance level data and user learning scope course data Collect and combine to generate learning user range course performance level data G=( , , );

[0041] S52, the high and low efficiency learning state judgment data Not for inefficient learning Abnormal learning state type change feature data Learning user range course grade level data G, marked as non-inefficient learning user range course grade level data ;

[0042] S53, the user's learning performance level data and user learning scope course data Collect and combine to generate user learning performance level range course data H=( , );

[0043] S54, if the high-low efficiency learning state judgment data is low-efficiency learning abnormal learning state type change characteristic data, , then based on the double pointer algorithm, search for non-inefficient learning user range course score level data with the same labels i and o in the user learning score level range course data H , generate user recommended course data L.

[0044] Furthermore, the step S6 includes the following steps:

[0045] S61. Collect abnormal learning state type feature data of adjustment plan users and generate an abnormal learning state type feature data set of adjustment plan users , , Represents the user abnormal learning state type feature data corresponding to the rth adjustment plan, Indicates the maximum number of adjustment options;

[0046] S62, if the high-low efficiency learning state judgment data is not low-efficiency learning abnormal learning state type change characteristic data, , then search for the abnormal learning status type analysis data of users in the current period Matching adjustment plan user abnormal learning status type feature data , generate adjustment plan analysis data .

[0047] Furthermore, the step S7 includes the following steps:

[0048] S71, recommending course data L and adjustment plan analysis data to the user Collect and combine to generate user course learning management data K=(L, );

[0049] S72, based on the L and Provide course recommendations and adjustment plan feedback to users.

[0050] The intelligent supervision system for learning course users based on image recognition includes a monitoring module, a data input module, a storage, a processor, and a management feedback module.

[0051] The monitoring module is used to monitor the user's learning status and generate user learning image data;

[0052] The data input module is used to input the collected data, such as user learning performance level data, user learning image data, user learning range course data, micro-expression type image data, abnormal type micro-expression type change feature data, high-efficiency learning abnormal learning state type change feature data, adjustment plan user abnormal learning state type feature data, etc. into the system;

[0053] The memory is used to store computer programs;

[0054] The processor is used to run a computer program to execute the method for intelligent supervision of users of learning courses based on image recognition provided by the present invention, and generate user course learning management data;

[0055] The management feedback module is used to provide users with recommended courses and adjustment plans based on their course learning management data.

[0056] 1. Compared with the existing technology, the method and system for intelligent supervision of learning course users based on image recognition provided by the present invention collects user micro-expression data and analyzes the changing characteristics of users' micro-expressions during the learning process to judge the efficiency of users' learning, making it convenient to understand the learning efficiency of each user student in the learning course.

[0057] 2. Compared with the existing technology, the method and system for intelligent supervision of learning course users based on image recognition provided by the present invention can also monitor the changing characteristics of users' micro-expressions and recommend methods for users to adjust their learning status when their learning efficiency decreases, so as to ensure that users learn in a good learning state.

[0058] 3. Compared with the existing technology, the method and system for intelligent supervision of learning course users based on image recognition provided by the present invention also judges the adaptability of the course to users of different grades by understanding the learning efficiency of users of different grades in each course, so as to recommend more suitable courses to users when the user's learning efficiency is extremely low. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments described in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0060] Figure 1 A diagram of method steps provided by an embodiment of the present invention;

[0061] Figure 2 This is a system structure block diagram provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0062] In order to enable those skilled in the art to better understand the technical solution of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings.

[0063] Example embodiments will be described more fully hereinafter with reference to the accompanying drawings, but the example embodiments may be embodied in different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete and will fully convey the scope of this disclosure to those skilled in the art.

[0064] In the absence of conflict, the various embodiments of the present disclosure and the various features therein may be combined with each other.

[0065] As used herein, the term "and / or" includes any and all combinations of one or more of the associated listed items.

[0066] The terms used herein are used only to describe specific embodiments and are not intended to limit the present disclosure. As used herein, the singular forms "a," "an," and "the" are also intended to include the plural forms, unless the context clearly indicates otherwise. It will also be understood that when the terms "comprising" and / or "made of" are used in this specification, the presence of the features, wholes, steps, operations, elements, and / or components is specified, but the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or groups thereof is not excluded.

[0067] The embodiments described herein may be described with reference to plan views and / or cross-sectional views, with the aid of idealized schematic diagrams of the present disclosure. Thus, the example illustrations may be modified based on manufacturing techniques and / or tolerances. Therefore, the embodiments are not limited to the embodiments shown in the accompanying drawings, but include modifications of the configurations formed based on the manufacturing process. Therefore, the regions illustrated in the accompanying drawings are schematic in nature, and the shapes of the regions shown in the drawings illustrate specific shapes of the regions of the elements, but are not intended to be limiting.

[0068] See also Figure 1 ,The intelligent supervision method for learning course users based on image recognition ,includes the following steps:

[0069] S1, collecting user learning performance level data, user learning image data and user learning range course data, including the following steps:

[0070] S11. Collect user learning performance level data and generate user learning performance level data set , , Represents the learning performance level data of the i-th user, is the maximum number of users; further, the learning performance level data of each user can be the average value or median value of the test scores of the user in each subject for the most recent set number of times.

[0071] S12. Generate a user learning image data set by collecting monitoring videos of the user learning , , represents the w-th user learning image data of the i-th user, The maximum number of user learning image data for the i-th user, where each user learning image data can be a frame in the surveillance video of the user.

[0072] S13. Collect user learning scope course data and generate user learning scope course data set , , represents the pth course in the oth category of learning, It represents the maximum number of course types in the oth learning scope, where the learning scope refers to the teaching content scope of the course. That is, the teaching content of the courses in each learning scope is the same, but the teaching methods, styles, and difficulty of understanding are different.

[0073] S2. Analyzing and processing the micro-expression type of the user during learning based on the user learning image data and the micro-expression type image data to generate characteristic data of changes in the user's micro-expression type, including the following steps:

[0074] S21. Collect micro-expression type image data and generate a micro-expression type image data set , , represents the u-th type of micro-expression image data, Indicates the maximum number of micro-expression types;

[0075] S22, after extracting features from the user learning image data set B and the micro-expression type image data set D, search for the user image data in the user image data set B based on the nearest neighbor search algorithm. Matching micro-expression type image data , generate a data set of user micro-expression type change characteristics ; Feature extraction can be done by using a pre-trained deep convolutional neural network (such as ResNet, VGG, EfficientNet) to extract the high-dimensional feature vector of the image, such as inputting all images in B and D into the model and extracting the features of the last fully connected layer or pooling layer as representation.

[0076] S3, based on the user's micro-expression type change feature data and abnormal type micro-expression type change feature data of the most recently set duration, performing user abnormal learning state type analysis processing to generate user abnormal learning state type analysis data, including the following steps:

[0077] S31, using a sliding window of a set length to collect the user's micro-expression type change feature data set Swipe up to generate the current user's micro-expression type change feature data , that is, the current user's micro-expression type change feature data The feature data of the user's micro-expression type changes within the sliding window when the right end of the sliding window is aligned with the current time;

[0078] S32: Collect abnormal micro-expression type change feature data and generate abnormal micro-expression type change feature data set , , Represents the characteristic data of the wth abnormal micro-expression type change, that is, The characteristic data cluster of micro-expression type changes representing the wth abnormal type, Indicates the maximum number of exception types;

[0079] S33, based on the ant colony search algorithm, searching for the characteristic data of the micro-expression type change of the current user Matched abnormal type micro-expression type change feature data , generate user abnormal learning status type analysis data , specifically including the following steps:

[0080] S331, initialize algorithm parameters, pheromones, number of abnormal type search ants N, maximum number of iterations T, the algorithm parameters include pheromone volatility coefficient (Usually 0< <1) Importance of pheromones , the importance of heuristic factors , pheromone enhancement constant ;

[0081] S332, let each abnormal type search ant start from the starting point, select the next node to reach according to the probability selection rule formula, until the complete path is completed, and calculate the complete path distance , the probability selection rule formula is as follows:

[0082] ,

[0083] in, represents the probability that the abnormal type search ant k at node i chooses to move to node j, represents the pheromone concentration of path (i, j) at the tth iteration, is the heuristic factor, u is the point not visited by the abnormal type search ant k;

[0084] S333. Update the pheromone concentration according to the proportional volatilization of pheromones on all edges. The formula is as follows:

[0085] ;

[0086] S334. Simulate the abnormal type search ant to release pheromone on the path (i, j) to update the pheromone. The formula is as follows:

[0087] ;

[0088] in,

[0089] ;

[0090] S335. If the maximum number of iterations T is reached, the complete path distance is output. Abnormal type micro-expression type change feature data corresponding to the shortest complete path , generate user abnormal learning status type analysis data , otherwise return to step S332.

[0091] S4. Based on the change characteristics of the user's abnormal learning state type analysis data and the high- and low-efficiency learning abnormal learning state type change characteristic data, perform user high- and low-efficiency learning analysis, including the following steps:

[0092] S41, collect high-efficiency learning abnormal learning state type change feature data and low-efficiency learning abnormal learning state type change feature data set to generate high-efficiency learning abnormal learning state type change feature data ,in Indicates the characteristic data of the type change of efficient learning abnormal learning state, Indicates the characteristic data of the type change of inefficient learning and abnormal learning state;

[0093] S42. Collect the user's abnormal learning status type analysis data for the most recent set duration according to the set frequency , generate analysis data on abnormal learning status types of users in the current period ;

[0094] S43, based on the ant colony search algorithm, use the abnormal abnormal learning state type change feature search ant search and the current period user abnormal learning state type analysis data Match high-efficiency and low-efficiency learning abnormal learning state type change feature data to generate high-efficiency and low-efficiency learning state judgment data The principle of the steps is the same as S331-S335, so I will not elaborate on them here. Matching high and low efficiency learning abnormal learning state type change feature data, then is 0.

[0095] S5. If the user is an inefficient learner, based on the user's learning performance level data, the user's learning scope course data, and the non-inefficient learner's scope course performance level data, search for non-inefficient learner courses with the same learning scope and user's learning performance level, and generate user recommended course data, including the following steps:

[0096] S51, judging data on the high and low efficiency learning state , user learning performance level data and user learning scope course data Collect and combine to generate learning user range course performance level data G=( , , );

[0097] S52, the high and low efficiency learning state judgment data Not for inefficient learning Abnormal learning state type change feature data Learning user range course grade level data G, marked as non-inefficient learning user range course grade level data ;

[0098] S53, the user's learning performance level data and user learning scope course data Collect and combine to generate user learning performance level range course data H=( , );

[0099] S54, if the high-low efficiency learning state judgment data is low-efficiency learning abnormal learning state type change characteristic data, , then based on the double pointer algorithm, search for non-inefficient learning user range course score level data with the same labels i and o in the user learning score level range course data H , generate user recommended course data L.

[0100] S6. If the user is not an inefficient learner, then based on the change characteristics of the user's abnormal learning state type analysis data and the abnormal learning state type characteristic data of the adjustment plan user, an adjustment plan analysis is performed to match the user's abnormal learning state, and adjustment plan analysis data is generated, including the following steps:

[0101] S61. Collect abnormal learning state type feature data of adjustment plan users and generate an abnormal learning state type feature data set of adjustment plan users , , Represents the user abnormal learning state type feature data corresponding to the rth adjustment plan, Indicates the maximum number of adjustment options;

[0102] S62, if the high-low efficiency learning state judgment data is not low-efficiency learning abnormal learning state type change characteristic data, , based on the ant colony search algorithm, use the adjustment scheme to search ant search and the current period user abnormal learning state type analysis data Matching adjustment plan user abnormal learning status type feature data , generate adjustment plan analysis data The principles of the steps are the same as S331-S335 and will not be elaborated on here.

[0103] S7. Construct management data and perform user learning management tasks based on the management data, including the following steps:

[0104] S71, recommending course data L and adjustment plan analysis data to the user Collect and combine to generate user course learning management data K=(L, );

[0105] S72, based on the L and Recommend courses to users and provide feedback on adjustment plans. When recommending courses to users, if there is non-inefficient learning user range course grade level data in the user recommended course data L, in To efficiently learn abnormal learning state type change feature data , it will be recommended to users first To efficiently learn abnormal learning state type change feature data of User learning scope course data in .

[0106] See also Figure 2 The present invention also provides an intelligent supervision system for learning course users based on image recognition, which includes a monitoring module, a data input module, a storage, a processor, and a management feedback module.

[0107] Among them, the monitoring module is used to monitor the user's learning status and generate user learning image data;

[0108] The data input module is used to input the collected data, such as user learning performance level data, user learning image data, user learning range course data, micro-expression type image data, abnormal type micro-expression type change feature data, high-efficiency learning abnormal learning state type change feature data, adjustment plan user abnormal learning state type feature data, etc. into the system;

[0109] The memory is used to store computer programs;

[0110] The processor is used to run a computer program to execute the method for intelligent supervision of users of learning courses based on image recognition provided by the present invention, and generate user course learning management data;

[0111] The management feedback module is used to provide users with recommended courses and adjustment plans based on their course learning management data.

[0112] The above description is merely illustrative of certain exemplary embodiments of the present invention. It goes without saying that those skilled in the art will be able to modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and description are illustrative in nature and should not be construed as limiting the scope of protection of the claims.

Claims

1. An intelligent supervision method for learning course users based on image recognition, characterized by: The following steps are involved: S1, collect user learning performance level data, user learning image data and user learning range course data; S2. Analyzing and processing the micro-expression type of the user during learning based on the user learning image data and the micro-expression type image data to generate characteristic data of changes in the user's micro-expression type; The S2 comprises the following steps: S21. Collect micro-expression type image data and generate a micro-expression type image data set , , represents the u-th type of micro-expression image data, Indicates the maximum number of micro-expression types; S22, after extracting features from the user learning image data set B and the micro-expression type image data set D, search for the user image data in the user learning image data set B based on the nearest neighbor search algorithm. Matching micro-expression type image data , generate a data set of user micro-expression type change characteristics ; The user learning image data set B includes ,in represents the w-th user learning image data of the i-th user; S3, based on the user's micro-expression type change feature data and abnormal type micro-expression type change feature data of the most recently set duration, performing user abnormal learning state type analysis processing to generate user abnormal learning state type analysis data; The S3 includes the following steps: S31, using a sliding window of a set length to collect the user's micro-expression type change feature data set Swipe up to generate the current user's micro-expression type change feature data ; S32: Collect abnormal micro-expression type change feature data and generate abnormal micro-expression type change feature data set , , Represents the characteristic data of the micro-expression type change of the wth abnormal type, Indicates the maximum number of exception types; S33, based on the ant colony search algorithm, searching for the characteristic data of the micro-expression type change of the current user Matched abnormal type micro-expression type change feature data , generate user abnormal learning status type analysis data , specifically including the following steps: S331, initialize algorithm parameters, pheromones, number of abnormal type search ants N, and maximum number of iterations T; S332, let each abnormal type search ant start from the starting point, select the next node to reach according to the probability selection rule formula, until the complete path is completed, and calculate the complete path distance ; S333, updating the pheromone concentration according to the proportional volatilization of the pheromones on all edges; S334, simulate the abnormal type search ant to release pheromone on the path (i, j) to update the pheromone; S335. If the maximum number of iterations T is reached, the complete path distance is output. Abnormal type micro-expression type change feature data corresponding to the shortest complete path , generate user abnormal learning status type analysis data , otherwise return to step S332; S4. Based on the change characteristics of the user's abnormal learning state type analysis data and the change characteristics of the high-efficiency and low-efficiency learning abnormal learning state type, perform user high-efficiency and low-efficiency learning analysis; The S4 comprises the following steps: S41, collect high-efficiency learning abnormal learning state type change feature data and low-efficiency learning abnormal learning state type change feature data set to generate high-efficiency learning abnormal learning state type change feature data ,in Indicates the characteristic data of the type change of efficient learning abnormal learning state, Indicates the characteristic data of the type change of inefficient learning and abnormal learning state; S42. Collect the user's abnormal learning status type analysis data for the most recent set duration according to the set frequency , generate analysis data of abnormal learning status type of users in the current period ; S43, based on the ant colony search algorithm, use the abnormal learning state type change characteristics to search ant search and the abnormal learning state type analysis data of users in the current period Match high-efficiency and low-efficiency learning abnormal learning state type change feature data to generate high-efficiency and low-efficiency learning state judgment data ; S5. If the user is an inefficient learner, based on the user's learning performance level data, the user's learning scope course data, and the non-inefficient learner's scope course performance level data, search for non-inefficient learner courses with the same learning scope and user's learning performance level, and generate user recommended course data; S6. If the user is not an inefficient learner, then based on the change characteristics of the user's abnormal learning state type analysis data and the abnormal learning state type characteristic data of the adjustment plan user, perform an adjustment plan analysis that matches the user's abnormal learning state, and generate adjustment plan analysis data; S7. Build management data and perform user learning management tasks based on the management data.

2. The method for intelligent supervision of users of learning courses based on image recognition according to claim 1 is characterized by: Said S1 comprises the following steps: S11. Collect user learning performance level data and generate user learning performance level data set , , Represents the learning performance level data of the i-th user, is the maximum number of users; S12. Generate a user learning image data set by collecting monitoring videos of the user learning , , represents the w-th user learning image data of the i-th user, The maximum number of user learning image data for the i-th user; S13. Collect user learning scope course data and generate user learning scope course data set , , represents the pth course in the oth category of learning, Indicates the maximum number of course types in the oth learning scope.

3. The method for intelligent supervision of users of learning courses based on image recognition according to claim 2 is characterized by: The S5 comprises the following steps: S51, judging data on the high and low efficiency learning state , user learning performance level data and user learning scope course data Collect and combine to generate learning user range course performance level data G=( , , ); S52, the high and low efficiency learning state judgment data Not for inefficient learning Abnormal learning state type change feature data Learning user range course grade level data G, marked as non-inefficient learning user range course grade level data ; S53, the user's learning performance level data and user learning scope course data Collect and combine to generate user learning performance level range course data H=( , ); S54, if the high-low efficiency learning state judgment data is low-efficiency learning abnormal learning state type change characteristic data, , then based on the double pointer algorithm, search for non-inefficient learning user range course score level data with the same labels i and o in the user learning score level range course data H , generate user recommended course data L.

4. The method for intelligent supervision of users of learning courses based on image recognition according to claim 3 is characterized by: The S6 comprises the following steps: S61. Collect abnormal learning state type feature data of adjustment plan users and generate an abnormal learning state type feature data set of adjustment plan users , , Represents the user abnormal learning state type feature data corresponding to the rth adjustment plan, Indicates the maximum number of adjustment options; S62, if the high-low efficiency learning state judgment data is not low-efficiency learning abnormal learning state type change characteristic data, , then search for the abnormal learning status type analysis data of users in the current period Matching adjustment plan user abnormal learning status type feature data , generate adjustment plan analysis data .

5. The method for intelligent supervision of users of learning courses based on image recognition according to claim 4 is characterized in that: The S7 comprises the following steps: S71, recommending course data L and adjustment plan analysis data to the user Collect and combine to generate user course learning management data K=(L, ); S72, based on the L and Provide course recommendations and adjustment plan feedback to users.

6. An intelligent supervision system for learning course users based on image recognition, configured to execute the intelligent supervision method for learning course users based on image recognition according to any one of claims 1 to 5, characterized in that: The system includes a monitoring module, a data input module, a storage, a processor, and a management feedback module; The monitoring module is used to monitor the user's learning status and generate user learning image data; The data input module is used to input the collected data, including user learning performance level data, user learning image data, user learning range course data, micro-expression type image data, abnormal type micro-expression type change feature data, high-efficiency learning abnormal learning state type change feature data, and adjustment plan user abnormal learning state type feature data into the system; The memory is used to store computer programs; The processor is used to run a computer program to execute the method for intelligent supervision of users of learning courses based on image recognition, and generate user course learning management data; The management feedback module is used to provide users with recommended courses and adjustment plans based on their course learning management data.

Images