Practical training behavior correction method based on big data

Abstract

The invention belongs to the technical field of practical training behavior correction, and discloses a practical training behavior correction method based on big data. The system comprises a learning data acquisition module, a learning data preprocessing module, a user login module, a user scheme management module, a practical training analysis module, a correction suggestion generation module and a user management module, and is characterized in that a state data set and progress data are acquired, and the learning data set is preprocessed to obtain a second learning data set; collecting supervision data; analyzing the second learning data set to obtain an efficiency reference value, and introducing supervision data for processing to obtain a supervision report; processing the efficiency reference value and the supervision report to obtain a correction suggestion report; the system and the method have the remarkable advantages of being high in data overall planning and processing capacity and good in effect of assisting in behavior correction of trainees.

Description

Technical Field

[0001] The present invention relates to the technical field of training behavior correction, and more specifically, the present invention relates to a training behavior correction method based on big data. Background Art

[0002] Training refers to the teaching process of training trainees' vocational and technical application abilities according to the laws and objectives of talent cultivation under the control of schools or enterprises. Traditional training places trainees in a designated area to complete preset tasks, and then manually evaluates the completion degree of the tasks and conducts evaluations. However, due to their own factors during the training process, it is easy for trainees to have various situations during the process of completing the preset tasks, resulting in poor performance of trainees. Thanks to the rapid development of technology, the current training system can conduct more accurate behavior monitoring through various high-tech products. However, because the training process is too easily affected by its own factors, it is difficult for trainees to correct their training behaviors. Therefore, how to more accurately correct the training behaviors of different trainees based on big data is particularly important.

[0003] The patent with the application publication number CN117711231A discloses a fire training method based on XR training big data analysis. By using XR devices to obtain environmental data, perception data, and the behavior data of each fire member during fire training, integrating the environmental data, perception data, and the behavior data of each fire member, and using big data analysis methods to analyze the integrated data to obtain data analysis results, displaying the data analysis results through visualization tools, and constructing a fire training learning model based on the data analysis results to train each fire member. By analyzing big data, it can support the decision-making of educational institutions and training providers, improve courses and training plans, adjust training content in real time according to the needs and performance of trainees, provide real-time feedback, and improve teaching methods, thereby improving the learning effect of trainees.

[0004] However, for the above-mentioned fire training method based on XR training big data analysis, although it integrates and then analyzes the environmental data, perception data, and the behavior data of each fire member during fire training, and to a certain extent obtains data analysis results with reference value, during the training process, trainees are easily affected by their own factors, such as low concentration, resulting in poor training performance. Therefore, how to identify and judge the learning ability of trainees and whether it can be corrected by external factors is particularly important for schools or enterprises.

[0005] In view of this, the present invention proposes a training behavior correction method based on big data to solve the above problems. Summary of the Invention

[0006] To overcome the above-mentioned defects of the prior art and to achieve the above object, the present invention provides the following technical solutions: including:

[0007] The learning data acquisition module is used to acquire the state data set and progress data, and the state data set includes eye movement data, expression data, and operation data;

[0008] The learning data preprocessing module is used to preprocess the learning data set to obtain the second learning data set;

[0009] Further, the way to preprocess the learning data set includes:

[0010] Obtain a set of second learning data sets;

[0011] Substitute the eye movement data and operation data into the calculation formula: to obtain the processed data, where AL is the L-th parameter input in the learning data set, μ is the mean, and σ is the standard deviation;

[0012] Traverse the processed data Aa and integrate the expression data to obtain the second learning data set;

[0013] The supervision data acquisition module is used to acquire supervision data;

[0014] The user login module is used for the user to log in to the training behavior correction system and read the user information data;

[0015] The user plan management module is used to, according to the user information data sent by the user login module, read the calibration report corresponding to the user in the database;

[0016] The training analysis module is used to analyze the second learning data set and introduce the supervision data for processing to obtain the supervision report;

[0017] Further, the training analysis module further includes a historical data scheduling module, a standard data scheduling module, a model establishment module, and a data transmission module, where:

[0018] The historical data scheduling module is used to retrieve the second learning data set stored in the database;

[0019] The supervision data scheduling module is used to retrieve the supervision data obtained by the supervision data acquisition module;

[0020] The model establishment module is used to support the establishment of the models required by the system;

[0021] The data transmission module is used to output the supervision report;

[0022] Further, the steps of analyzing the second learning data set include:

[0023] Step 1: Based on the historical data scheduling module, obtain a set of historical second learning datasets, and label them as U1, U2, U3... Un from far to near based on the timestamps of the second learning datasets;

[0024] Step 2: Based on the model establishment module, establish the first efficiency calculation model according to the historical second learning datasets;

[0025] Step 3: By substituting into the calculation formula:

[0026] Obtain the efficiency reference value and correct the weights of the expression data, where Bt is the weight of the t-th training times, Bs is the total training times, Bb is the eye movement data, Bc is the expression data, Bd is the operation data, Be is the progress data, and B1, B2, B3, and B4 are the corresponding weight factors respectively, and satisfy B1 + B2 + B3 + B4 = 1;

[0027] Step 4: Based on the supervision data scheduling module, obtain the supervision data;

[0028] Step 5: By substituting into the calculation formula: Obtain the supervision reference value, where λ is the supervision gain coefficient, Bf is the supervision data, and Bfz is the total supervision duration;

[0029] Step 6: Repeat Steps 3 to 6 until the preset number of iterations is reached to obtain the second efficiency calculation model;

[0030] Step 7: Input the second learning datasets and the supervision data into the second efficiency calculation model to obtain the supervision report, and output the supervision report based on the data transmission module;

[0031] Furthermore, the method for correcting the weights of the expression data includes:

[0032] By substituting into the calculation formula: Obtain the corrected weight factor;

[0033] The correction suggestion generation module is used to process the efficiency reference value and the supervision report to obtain the correction suggestion report;

[0034] Furthermore, the method for processing the efficiency reference value and the supervision report includes:

[0035] By substituting into the calculation formula: Obtain the supervision gain value;

[0036] When the supervision gain value is less than C1, generate a negative gain report, and when the supervision gain value is greater than or equal to CI, generate a positive gain report;

[0037] The negative gain report includes an explanation that the user's training efficiency is low under the supervision state, and it is recommended that the supervisor reduce or stop the supervision behavior;

[0038] The positive gain report includes an explanation that the user's training efficiency is high under the supervision state, and it is recommended that the supervisor maintain or increase the supervision duration;

[0039] Package the negative gain report and the positive gain report to obtain a corrective suggestion report;

[0040] The user management module is used to analyze the corrective suggestion report to obtain a calibration report and transmit it to the user login module;

[0041] Furthermore, the way to analyze the corrective suggestion report includes:

[0042] Obtain the content and progress data of the corrective suggestion report;

[0043] Adjust the supervision data according to the content of the corrective suggestion report to obtain a calibration report;

[0044] Send the calibration report to the user login module and integrate it into the user information data;

[0045] Furthermore, S1: Collect the status data set and progress data. The status data set includes eye movement data, expression data, and operation data;

[0046] S2: Preprocess the learning data set to obtain a second learning data set;

[0047] S3: Collect supervision data;

[0048] S4: The user logs in to the training behavior correction system and reads the user information data;

[0049] S5: According to the user information data sent by the user login module, read the calibration report corresponding to the user in the database;

[0050] S6: Analyze the second learning data set to obtain an efficiency reference value, and introduce the supervision data for processing to obtain a supervision report;

[0051] S7: Process the efficiency reference value and the supervision report to obtain a corrective suggestion report;

[0052] S8: Analyze the corrective suggestion report to obtain a calibration report.

[0053] The technical effects and advantages of a training behavior correction method based on big data according to the present invention:

[0054] By analyzing the second learning dataset and introducing supervised data for processing, the obtained supervision report can effectively reflect the training efficiency of users under the correction of external force factors, greatly reducing the labor costs brought about by the need to collect, evaluate, and correct users in multiple aspects and with multiple data in traditional practical training. By processing the efficiency reference value and the supervision report, the obtained correction suggestion report can more intuitively show the training efficiency of users under supervised and unsupervised conditions, and can assist schools or enterprises to better implement different training correction methods for different trainees, greatly increasing the accuracy and assistance of training behavior correction. By analyzing the correction suggestion report, the obtained calibration report can enable schools or enterprises to implement targeted correction measures based on the training efficiency of different trainees, and integrating the calibration report into the user information data can enable supervisors to obtain the calibration information of the trainee in the first time, greatly increasing the intuitiveness of training behavior correction information. Generally speaking, the present invention has the remarkable advantages of strong data overall processing ability and good effect of assisting trainees in behavior correction. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 FIG. is a schematic diagram of a training behavior correction system based on big data according to the present invention;

[0056] Figure 2 FIG. is a schematic diagram of a training behavior correction method based on big data according to the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0057] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0058] The terms used in the embodiments of the present invention are only for the purpose of describing specific embodiments, and are not intended to limit the present invention. The singular forms of "a", "the" and "said" used in the embodiments of the present invention and the appended claims are also intended to include the plural forms, unless the context clearly indicates otherwise. "Plural" generally includes at least two.

[0059] Depending on the context, as used herein, the terms "if" and "when" may be interpreted as "when" or "while" or "in response to determining" or "in response to detecting". Similarly, depending on the context, the phrases "if determined" or "if detecting (stated condition or event)" may be interpreted as "when determined" or "in response to determining" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)".

[0060] In addition, the step timings in the following method embodiments are only examples and not strictly limited.

[0061] In fact, the server devices deployed by the big data-based training behavior correction system may be composed of one or more devices. The above-mentioned big data-based training behavior correction system can be implemented as: business instances, virtual machines, and hardware devices. For example, the big data-based training behavior correction system can be implemented as a business instance deployed on one or more devices in a cloud node. Simply put, the big data-based training behavior correction system can be understood as a software deployed on a cloud node for providing the big data-based training behavior correction system for each client. Alternatively, the big data-based training behavior correction system can also be implemented as a virtual machine deployed on one or more devices in a cloud node. An application software for managing each client is installed in the virtual machine. Or, the big data-based training behavior correction system can also be implemented as a server composed of many identical or different types of hardware devices, and one or more hardware devices are set to provide the big data-based training behavior correction system for each client.

[0062] In terms of implementation form, the big data-based training behavior correction system and the client adapt to each other. That is, if the big data-based training behavior correction system is an application installed on a cloud service platform, then the client is a client that establishes a communication connection with the application; or if the big data-based training behavior correction system is implemented as a website, then the client is implemented as a web page; or if the big data-based training behavior correction system is implemented as a cloud service platform, then the client is implemented as a small program in an instant messaging application.

[0063] As Figure 1 shown, it is a system architecture diagram of the big data-based training behavior correction system provided by an embodiment of the present invention.

[0064] The training behavior correction system based on big data according to the present invention can be set in a cloud server. In terms of implementation form, it can be used as one or more service devices, or can be installed as an application on the cloud (such as the server of a mobile service operator, a server cluster, etc.), or can also be developed into a website. According to the functions achieved, the training behavior correction system based on big data can include a learning data collection module, a learning data preprocessing module, a user login module, a user plan management module, a training analysis module, a correction suggestion generation module, and a user management module. The modules described in the present invention can also be referred to as units, which refer to a series of computer program segments that can be executed by a processor of an electronic device and can complete fixed functions, and are stored in the memory of the electronic device.

[0065] In the embodiment of the present invention, in the training behavior correction system based on big data, each of the above modules can be independently implemented and called by other modules. Here, the call can be understood as that a certain module can be connected to multiple modules of another type and provide corresponding services for the multiple modules it is connected to. For example, the sharing and evaluation module can call the same information collection module to obtain the information collected by the information collection module. Based on the above characteristics, in the training behavior correction system based on big data provided by the embodiment of the present invention, without modifying the program code, the applicable range of the architecture of the training behavior correction system based on big data can be adjusted by adding modules and directly calling them, so as to achieve cluster-level horizontal expansion, so as to achieve the purpose of quickly and flexibly expanding the training behavior correction system based on big data. In practical applications, the above modules can be set in the same device or different devices, or can also be set in virtual devices, such as service instances in a cloud server.

[0066] Embodiment 1

[0067] Please refer to Figure 1 As shown in the figure, a training behavior correction system based on big data in this embodiment includes:

[0068] The learning data collection module is used to collect a state data set and progress data, and the state data set includes eye movement data, expression data, and operation data;

[0069] It should be explained that by installing a camera, the user's fixation points, fixation duration, and blink frequency are collected, and weighted summation is performed to obtain eye movement data. Among them, the fixation points are specifically valid fixation points and invalid fixation points, and they are respectively assigned values. For example, valid fixation points are assigned a value of 1, and invalid fixation points are assigned a value of 0; by installing a camera and cooperating with a micro-expression analysis model, the user's micro-expression state is collected to obtain expression data. For example, the user has three states of being serious, yawning frequently, and having wandering eyes, which are respectively assigned values of 2, 1, and 0; by installing a third-party tool, the user's operation frequency, pause time, and number of operation errors are collected, and weighted summation is performed to obtain operation data. Among them, the number of operations per unit time is obtained by comparing with a preset operation threshold range. For example, if the number of operations is greater than the maximum operation threshold, the value is 1; if the number of operations is less than the minimum operation threshold, the value is 0; by reading the task status, the number of tasks completed by the user when exiting the training correction system is collected and divided by the total number of tasks to obtain progress data;

[0070] The learning data preprocessing module is used to preprocess the learning data set to obtain a second learning data set;

[0071] Furthermore, the way to preprocess the learning data set includes:

[0072] Obtain a set of second learning data sets;

[0073] Substitute the eye movement data and operation data into the calculation formula: to obtain processed data, where AL is the Lth parameter input in the learning data set, μ is the mean, and σ is the standard deviation;

[0074] Traverse the processed data Aa and integrate the expression data to obtain a second learning data set;

[0075] The supervision data collection module is used to collect supervision data;

[0076] It should be explained that by installing a camera, the duration of supervision behavior existing in the area where the user is located is collected to obtain supervision data. The supervision behavior refers to the supervision by groups such as teachers or parents near the user;

[0077] The user login module is used for the user to log in to the training behavior correction system and read the user information data;

[0078] The user solution management module is used to, based on the user information data sent by the user login module, read the calibration report corresponding to the user in the database;

[0079] The training analysis module is used to analyze the second learning data set and introduce the supervision data for processing to obtain a supervision report;

[0080] Furthermore, the training analysis module further includes a historical data scheduling module, a standard data scheduling module, a model establishment module, and a data transmission module, where:

[0081] The historical data scheduling module is used to retrieve the second learning dataset stored in the database;

[0082] The supervision data scheduling module is used to retrieve the supervision data obtained by the supervision data acquisition module;

[0083] The model establishment module is used to support the establishment of the models required by the system;

[0084] The data transmission module is used to output a supervision report;

[0085] Furthermore, the steps for analyzing the second learning dataset include:

[0086] Step 1: Based on the historical data scheduling module, obtain a set of historical second learning datasets, and based on the timestamps of the second learning datasets, label them as U1, U2, U3... Un from far to near;

[0087] Step 2: Based on the model establishment module, establish a first efficiency calculation model according to the historical second learning datasets;

[0088] Step 3: By substituting into the calculation formula:

[0089] Obtain an efficiency reference value, and perform weight correction on the expression data, where Bt is the weight of the t-th training session, Bs is the total number of training sessions, Bb is the eye movement data, Bc is the expression data, Bd is the operation data, Be is the progress data, and B1, B2, B3, and B4 are the corresponding weight factors respectively, and satisfy B1 + B2 + B3 + B4 = 1;

[0090] Step 4: Based on the supervision data scheduling module, obtain supervision data;

[0091] Step 5: By substituting into the calculation formula: Obtain a supervision reference value, where λ is the supervision gain coefficient, Bf is the supervision data, and Bfz is the total supervision duration;

[0092] It should be noted that the supervision gain coefficient is the gain value of the user's learning efficiency when there is supervision, which is calibrated through experiments and input manually;

[0093] Step 6: Repeat steps 3 to 6 until the preset number of iterations is reached to obtain a second efficiency calculation model;

[0094] Step 7: Input the second learning dataset and the supervision data into the second efficiency calculation model to obtain a supervision report, and output the supervision report based on the data transmission module;

[0095] Furthermore, the methods for weight correction of expression data include:

[0096] By substituting into the calculation formula: Obtain the corrected weight factor;

[0097] It should be explained that the corrected weight factor means that the larger the supervision data, the worse the user's autonomy. And because the expression data will be interfered by supervision, it is necessary to reduce the weight of the expression data;

[0098] The correction suggestion generation module is used to process the efficiency reference value and the supervision report to obtain a correction suggestion report;

[0099] Furthermore, the methods for processing the efficiency reference value and the supervision report include:

[0100] By substituting into the calculation formula: Obtain the supervision gain value;

[0101] When the supervision gain value is less than C1, generate a negative gain report. When the supervision gain value is greater than or equal to C1, generate a positive gain report;

[0102] The negative gain report includes an explanation that the user's training efficiency is low under the supervision state, and it is recommended that the supervisor reduce or stop the supervision behavior;

[0103] The positive gain report includes an explanation that the user's training efficiency is high under the supervision state, and it is recommended that the supervisor maintain or increase the supervision duration;

[0104] Package the negative gain report and the positive gain report to obtain a correction suggestion report;

[0105] The user management module is used to analyze the correction suggestion report to obtain a calibration report and transmit it to the user login module;

[0106] Furthermore, the methods for analyzing the correction suggestion report include:

[0107] Obtain the content and progress data of the correction suggestion report;

[0108] Adjust the supervision data according to the content of the correction suggestion report to obtain a calibration report;

[0109] Send the calibration report to the user login module and integrate it into the user information data;

[0110] In this embodiment, the beneficial effects are as follows. By analyzing the second learning dataset and introducing supervised data for processing, the obtained supervision report can effectively reflect the training efficiency of users under the correction of external force factors, greatly reducing the labor costs brought about by the need to collect, evaluate, and correct users in multiple aspects and with multiple data in traditional training. By processing the efficiency reference value and the supervision report, the obtained correction suggestion report can more intuitively display the training efficiency of users with and without supervision, which can assist schools or enterprises to better implement different training correction methods for different trainees, greatly increasing the accuracy and assistance of training behavior correction. By analyzing the correction suggestion report, the obtained calibration report enables schools or enterprises to implement targeted correction measures based on the training efficiency of different trainees, and integrating the calibration report into the user information data enables supervisors to obtain the calibration information of the trainee in the first time, greatly increasing the intuitiveness of training behavior correction information. Generally speaking, the present invention has the remarkable advantages of strong data overall processing ability and good auxiliary effect on trainees' behavior correction.

[0111] Embodiment 2

[0112] Please refer to Figure 2 As shown, for the parts not described in detail in this embodiment, refer to the description content of Embodiment 1. A training behavior correction method based on big data is provided, including: S1: Collecting a state dataset and progress data, where the state dataset includes eye movement data, expression data, and operation data;

[0113] S2: Preprocessing the learning dataset to obtain a second learning dataset;

[0114] S3: Collecting supervised data;

[0115] S4: The user logs in to the training behavior correction system and reads the user information data;

[0116] S5: According to the user information data sent by the user login module, and reading the calibration report corresponding to the user in the database;

[0117] S6: Analyzing the second learning dataset to obtain an efficiency reference value, and introducing supervised data for processing to obtain a supervision report;

[0118] S7: Processing the efficiency reference value and the supervision report to obtain a correction suggestion report;

[0119] S8: Analyzing the correction suggestion report to obtain a calibration report.

[0120] Embodiment 3

[0121] For those skilled in the art, it is obvious that the present invention is not limited to the details of the above-mentioned exemplary embodiments, and the present invention can be implemented in other specific forms without departing from the spirit or basic characteristics of the present invention.

[0122] Therefore, from any point of view, the embodiments should be regarded as exemplary and non-limiting. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, all changes falling within the meaning and scope of the equivalent elements of the claims are intended to be embraced within the present invention. Any reference signs in the claims should not be construed as limiting the claims involved.

[0123] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is a theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0124] In addition, it is obvious that the word "including" does not exclude other units or steps, and the singular does not exclude the plural. The multiple units or devices stated in the system claims can also be implemented by one unit or device through software or hardware. Words such as first and second are used to denote names and do not denote any particular order.

[0125] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A training behavior correction system based on big data, characterized in that, It includes: A learning data acquisition module, a learning data preprocessing module, a user login module, a user plan management module, a training analysis module, a correction suggestion generation module, and a user management module. Among them: The learning data acquisition module is used to acquire a status data set and progress data. The status data set includes eye movement data, expression data, and operation data; The learning data preprocessing module is used to preprocess the learning data set to obtain a second learning data set; The supervision data acquisition module is used to acquire supervision data; The user login module is used for users to log in to the training behavior correction system and read user information data; The user plan management module is used to, based on the user information data sent by the user login module, read the calibration report corresponding to the user in the database; The training analysis module is used to analyze the second learning data set and introduce supervision data for processing to obtain a supervision report; The correction suggestion generation module is used to process the efficiency reference value and the supervision report to obtain a correction suggestion report; The user management module is used to analyze the correction suggestion report to obtain a calibration report and transmit it to the user login module.

2. The training behavior correction system based on big data according to claim 1, wherein, The ways to preprocess the learning data set include: Obtain a set of second learning data sets; Substitute the eye movement data and operation data into the calculation formula: to obtain processed data, where AL is the L-th parameter input in the learning dataset, μ is the mean, and σ is the standard deviation; Traverse and process the data Aa and integrate the expression data to obtain a second learning data set.

3. The training behavior correction system based on big data according to claim 1, characterized in that, The training analysis module further includes a historical data scheduling module, a standard data scheduling module, a model establishment module, and a data transmission module. Among them: The historical data scheduling module is used to retrieve the second learning data set stored in the database; The supervision data scheduling module is used to retrieve the supervision data obtained by the supervision data acquisition module; The model establishment module is used to support the establishment of the models required by the system; The data transmission module is used to output the supervision report.

4. The training behavior correction system based on big data according to claim 3, wherein, The steps to analyze the second learning data set include: Step 1: Based on the historical data scheduling module, obtain a set of historical second learning data sets, and based on the timestamps of the second learning data sets, mark them as U1, U2, U3... Un from far to near; Step 2: Based on the model establishment module, establish a first efficiency calculation model according to the historical second learning data sets; Step 3: By substituting into the calculation formula: Obtain an efficiency reference value and perform weight correction on the expression data, where Bt is the weight of the t-th training session, Bs is the total number of training sessions, Bb is the eye movement data, Bc is the expression data, Bd is the operation data, Be is the progress data, and B1, B2, B3, and B4 are the corresponding weight factors respectively, and satisfy B1 + B2 + B3 + B4 = 1; Step 4: Based on the supervision data scheduling module, obtain the supervision data; Step 5: By substituting into the calculation formula: Obtain the supervision reference value, where λ is the supervision gain coefficient, Bf is the supervision data, and Bfz is the total supervision duration; Step 6: Repeat Steps 3 to 6 until the preset number of iterations is reached to obtain a second efficiency calculation model; Step 7: Input the second learning data set and the supervision data into the second efficiency calculation model to obtain a supervision report, and output the supervision report based on the data transmission module.

5. The training behavior correction system based on big data according to claim 4, characterized in that, The ways to correct the weights of the expression data include: By substituting into the calculation formula: The corrected weight factor is obtained.

6. The training behavior correction system based on big data according to claim 5, characterized in that, The ways to process the efficiency reference value and the supervision report include: By substituting into the calculation formula: The supervised gain value is obtained; When the supervision gain value is less than C1, generate a negative gain report. When the supervision gain value is greater than or equal to CI, generate a positive gain report; The negative gain report includes an explanation that the user's training efficiency is low under the supervision state, and it is recommended that the supervisor reduce or stop the supervision behavior; The positive gain report includes an explanation that the user's training efficiency is high under the supervision state, and it is recommended that the supervisor maintain or increase the supervision duration; Package the negative gain report and the positive gain report to obtain a correction suggestion report.

7. The training behavior correction system based on big data according to claim 6, wherein, The ways to analyze the corrective suggestion report include: Obtain the content and progress data of the corrective suggestion report; Adjust the supervision data according to the content of the corrective suggestion report to obtain a calibration report; Send the calibration report to the user login module and integrate it into the user information data.

8. A training behavior correction method based on big data, implemented according to the training behavior correction system based on big data described in any one of claims 1-7, characterized in that, Specifically, it includes the following steps: S1: Collect the status data set and progress data. The status data set includes eye movement data, expression data, and operation data; S2: Preprocess the learning data set to obtain a second learning data set; S3: Collect supervision data; S4: The user logs in to the training behavior correction system and reads the user information data; S5: According to the user information data sent by the user login module, read the calibration report corresponding to the user in the database; S6: Analyze the second learning data set to obtain an efficiency reference value, and introduce supervision data for processing to obtain a supervision report; S7: Process the efficiency reference value and the supervision report to obtain a corrective suggestion report; S8: Analyze the corrective suggestion report to obtain a calibration report.

Images