Training system for economic management teaching based on cloud service

Abstract

The invention discloses a training system for economic management teaching based on cloud service. The training system comprises a biological signal acquisition module, an electroencephalogram signal processing module and a dynamic difficulty adjustment module, the invention relates to the technical field of educational training. According to the training system for economic management teaching based on the cloud service, the cognitive load degree of a student is clearly judged by collecting electroencephalogram signals of the student, and corresponding intervention of the difficulty of an economic management teaching course is performed according to the cognitive load degree of the student, so that personalized teaching of the student can be realized, and the teaching efficiency is improved. In addition, the system can assist students in high-efficiency learning, achieves the purpose of better adapting to individual differences and teaching stage changes, and provides effective support for improving intervention accuracy, enhancing system adaptability and optimizing learning experience.

Description

Technical Field

[0001] The present invention relates to the technical field of education and training, and specifically to a training system for economic management teaching based on cloud services. Background Art

[0002] Economic management mainly studies the laws and methods for reasonably organizing and regulating social and economic activities. It includes two major aspects: macroeconomic management, that is, the control, guidance, regulation, and supervision of the national economic system and social and economic activities by the state; microeconomic management, that is, the operation management of various enterprises, cooperative economic organizations, and individual laborers. Economic management is a comprehensive applied discipline that integrates the disciplinary knowledge of various social sciences and natural sciences, and pays attention to summarizing practical experience and feasibility studies.

[0003] Traditional economic management teaching methods often adopt a "one-size-fits-all" model, which is difficult to dynamically adjust according to the individual differences and real-time cognitive states of students. This teaching model may lead to poor learning effects for some students due to excessive cognitive load, or loss of learning interest due to overly simple content. With the continuous development of educational technology, personalized teaching has gradually become a research hotspot. However, most existing personalized teaching systems are based on static data such as students' learning history and grades, and it is difficult to reflect students' cognitive states in real time.

[0004] In view of this, a training system for economic management teaching based on cloud services is specifically proposed. By collecting the electroencephalogram signals of students, judging the degree of students' cognitive load, and dynamically intervening in the difficulty of teaching content, the learning efficiency of students can be improved. Summary of the Invention

[0005] Aiming at the deficiencies of the prior art, the present invention provides a training system for economic management teaching based on cloud services, which solves the problem that traditional economic management teaching methods are difficult to dynamically adjust according to the individual differences and real-time cognitive states of students.

[0006] To achieve the above objectives, the present invention is realized through the following technical solutions: A training system for economic management teaching based on cloud services, comprising: A bio-signal acquisition module, which is used to acquire the electroencephalogram signals of students; An electroencephalogram signal processing module, and the neural efficiency index calculation module is used to extract the features of the electroencephalogram signals of students and calculate the real-time neural efficiency index; A dynamic difficulty adjustment module, which is used to judge the degree of students' cognitive load according to the real-time neural efficiency index, and perform difficulty intervention on the economic management teaching content during the teaching process according to the judgment result.

[0007] The present invention is further configured such that the method for extracting features from the EEG signals of the trainees includes: Using independent component analysis to remove electrooculogram artifacts from the EEG signals; Adopting wavelet packet transform to extract waves, waves, waves, and the band features of waves.

[0008] The present invention is further configured such that the calculation formula of the real-time neural efficiency index includes: In the formula, is the real-time neural efficiency index, is wave power, is wave power, is wave power, is wave power, is the behavior deviation attenuation coefficient, is the behavior deviation index.

[0009] The present invention is further configured such that the method for judging the cognitive load level of the trainees according to the real-time neural efficiency index includes: Presetting a neural efficiency index threshold and a judgment duration, dynamically adjusting the preset neural efficiency index threshold according to the class progress, and when the real-time neural efficiency index continuously falls below the dynamically adjusted neural efficiency index threshold and reaches the judgment duration, it is judged that the trainee is in a high cognitive load state; Combining the dynamically adjusted neural efficiency index threshold to perform gradient grading on the neural efficiency index, and when it is judged that the trainee is in a high cognitive load state, performing first-level intervention, second-level intervention, and third-level intervention judgments on the corresponding real-time neural efficiency index, where the cognitive load levels corresponding to the first-level intervention, second-level intervention, and third-level intervention gradually deepen.

[0010] The present invention is further configured such that the method for dynamically adjusting the preset neural efficiency index threshold according to the class progress includes: In the formula, is the dynamically adjusted neural efficiency index threshold, is the preset neural efficiency index threshold, is the current class progress, is the total class length.

[0011] The present invention is further configured such that the method for intervening in the difficulty of the economic management teaching content during the teaching process according to the judgment result includes: When the judgment result is a first-level intervention, visual simplification is initiated to hide the secondary information on the teaching interface; When the judgment result is a second-level intervention, auditory adjustment is initiated, and 10 Hz binaural beat wave music is output through bone conduction headphones; When the judgment result is a third-level intervention, decision support is initiated, and a probabilistic strategy prompt box is displayed on the interface.

[0012] The present invention is further configured such that when outputting 10 Hz binaural beat wave music through bone conduction headphones, dynamic adjustment of the volume is performed, and the volume dynamic adjustment formula includes: In the formula, is the adjusted wave music volume, is the reference volume, is the real-time neural efficiency index.

[0013] The present invention is further configured such that when the probabilistic strategy prompt box is displayed on the interface, the decision prompt confidence calculation formula includes: In the formula, is the confidence of the decision prompt, is the sensitivity coefficient, taking 3.5, is the baseline neural efficiency index of the trainee in a 5-minute resting state, that is, the baseline cognitive efficiency value.

[0014] The present invention provides a training system for economic management teaching based on cloud services. It has the following beneficial effects: By collecting the electroencephalogram signals of the trainees, the present invention clearly judges the cognitive load level of the trainees, and at the same time intervenes in the corresponding difficulty of the economic management teaching curriculum according to the cognitive load level of the trainees. In this way, not only can personalized teaching of the trainees be realized, but also the trainees can be assisted to learn efficiently, achieving the purpose of better adapting to individual differences and changes in the teaching stage, and providing effective support for improving the intervention accuracy, enhancing the system adaptability, and optimizing the learning experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 is a schematic diagram of the system architecture of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0016] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention.

[0017] Please refer to Figure 1 , the embodiments of the present invention provide the following technical solutions. A training system for economic management teaching based on cloud services includes a bio-signal acquisition module, an electroencephalogram (EEG) signal processing module, and a dynamic difficulty adjustment module.

[0018] As a preferred solution, the bio-signal acquisition module is used to collect the EEG signals of the trainees. Specifically, the EEG signals of the prefrontal cortex, anterior cingulate gyrus, and ventromedial prefrontal cortex are collected through a 64-channel high-density EEG electrode cap, and the sampling rate is 1000Hz.

[0019] Subsequently, the neural efficiency index calculation module is used to extract features from the EEG signals of the trainees. The methods for feature extraction include: Using independent component analysis to remove electrooculogram (EOG) artifacts from the EEG signals; Adopting wavelet packet transform to extract the wave band features of 4 - 8Hz, the wave band features of 8 - 12Hz, the

[0020] As a detailed description, the wave band features of 4 - 8Hz reflect the concentration and relaxation state of the trainees; the wave band features of 8 - 12Hz reflect the activity and cognitive processing intensity of the trainees; the wave band features of 13 - 30Hz reflect the fatigue and mild cognitive load of the trainees; the wave band features of 30 - 50Hz reflect the higher cognitive functions of the trainees, including but not limited to memory and perception.

[0021] Furthermore, for the extracted features, calculate the real-time neural efficiency index. The calculation formula includes: In the formula, is the real-time neural efficiency index, is the wave power, is the wave power, is the wave power, is the wave power, is the behavior deviation attenuation coefficient, is the behavior deviation index.

[0022] Specifically, the behavior deviation index reflects the degree of behavior deviation of the trainee during the decision-making process. By analyzing the decision-making data of the trainee, the deviation between their decision and the Nash equilibrium is calculated, that is, the behavior deviation index is obtained; The behavior deviation attenuation coefficient is used to adjust the influence degree of the behavior deviation index on the real-time neural efficiency index, ensuring that the real-time neural efficiency index can accurately reflect the cognitive load state of the trainee. It is determined through behavioral experiments to make the correlation coefficient between the real-time neural efficiency index and the subjective cognitive load score such as the NASA-TLX scale reach the preset standard.

[0023] As an optimal solution, the dynamic difficulty adjustment module is used to judge the cognitive load degree of the trainee according to the real-time neural efficiency index. The specific methods include: Preset the neural efficiency index threshold and the judgment duration, and dynamically adjust the preset neural efficiency index threshold according to the class progress. The ways of dynamic adjustment include: In the formula, is the dynamically adjusted neural efficiency index threshold, is the preset neural efficiency index threshold, is the current class progress, is the total class length. Among them, when the preset neural efficiency index threshold is 0.60, the total class length is 60 min, and the current class progress is 30 min. At this time, the dynamically adjusted neural efficiency index threshold is 0.63; When the real-time neural efficiency index continuously remains lower than the dynamically adjusted neural efficiency index threshold and reaches the judgment duration, it is judged that the trainee is in a high cognitive load state; Combined with the dynamically adjusted neural efficiency index threshold, the neural efficiency index is graded in gradients. When it is judged that the trainee is in a high cognitive load state, the first-level intervention, second-level intervention, and third-level intervention judgments of the corresponding real-time neural efficiency index are carried out, where the cognitive load degrees corresponding to the first-level intervention, second-level intervention, and third-level intervention increase in turn.

[0024] Specifically, the gradient grading uses 0.1 as the gradient interval. Taking the dynamically adjusted neural efficiency index threshold of 0.63 as an example, the reference threshold for the first-level intervention judgment is: The reference threshold for the second-level intervention judgment is: The reference threshold for the third-level intervention judgment is: .

[0025] The dynamic difficulty adjustment module is also used to perform difficulty intervention on the economic management teaching content during the teaching process according to the judgment result. Specifically, it includes: When the judgment result is a first-level intervention, visual simplification is initiated to hide the secondary information on the teaching interface. The judgment methods for secondary information include: Build a market information importance matrix, including four dimensions: price main chart, order flow, news announcements, and social sentiment. The weights of the price main chart, order flow, news announcements, and social sentiment are 0.4, 0.3, 0.2, and 0.1 respectively. Use the fuzzy clustering algorithm to calculate the display priority of each information module in real time. When entering the first-level intervention, hide the information modules with a priority less than 0.3; When the judgment result is a second-level intervention, auditory adjustment is initiated, and 10Hz binaural beat music is output through bone conduction headphones During the process, dynamic adjustment of the volume is performed. The volume dynamic adjustment formula includes: In the formula, is the adjusted binaural beat music volume, is the reference volume, is the real-time neural efficiency index. It should be noted that has a maximum value , such as 75dB. At , take as the adjusted binaural beat music volume; It should be noted that when the binaural beat binaural beat music is played, the phase difference Δφ between the left and right channels is 180° ± 5%. And for the music, it is stored in the music therapy database. In the music therapy database, the binaural beat music is classified and stored according to the rhythm pattern (isochronous / gradually increasing) and instrument combination (natural sound effects / electronic synthesis). The best music type is automatically selected according to the trainee's biological characteristics. The selection logic is: When the judgment result is a third-level intervention, decision support is initiated, and a probabilistic strategy prompt box is displayed on the interface. Specifically, deploy the Monte Carlo tree search algorithm, generate a candidate strategy set based on the current market state, and sort the strategies through the Q-learning algorithm. The Q-value update formula is: In the formula, is the Q-value of taking the current action in the current state , that is, the expected return, is the learning rate, is the immediate reward, is the discount factor, is the next state, is the next action; When the probabilistic strategy prompt box is displayed on the interface, a progressive display mechanism is adopted. The initial display strategy confidence level is 70%, increasing by 5% every 5 seconds until the confidence level reaches 95% or the trainee performs an operation. The decision prompt confidence level calculation formula includes: In the formula, is the confidence level of the decision prompt, is the sensitivity coefficient, taking 3.5, is the trainee's baseline neural efficiency index in a 5-minute resting state, that is, the baseline cognitive efficiency value.

[0026] Simulation Experiment 1 To verify whether the neural efficiency index calculated from EEG signals can accurately judge the cognitive load state of trainees, the following simulation experiment was carried out: According to the preset wave and the power ratio of the wave, 50 test trainees were divided into low, medium, and high cognitive load groups. The trainees sequentially completed low, medium, and high-difficulty economic management decision-making tasks for 30 minutes. During the process, EEG signals were collected in real time, and the neural efficiency index per second was calculated. According to the neural efficiency index, the cognitive state of the trainees per second was classified as low, medium, and high load. The preset cognitive load state was compared with the judgment result of the neural efficiency index, and the accuracy rate was calculated. The results are shown in Table 1: Cognitive load state Preset sample number Number of correct judgments Accuracy rate Low load 15 14 93.3% Medium load 20 18 90.0% High load 15 13 86.7% Total 50 45 90.0% Table 1 As can be seen from Table 1, the present invention can judge the cognitive load state of trainees through the neural efficiency index calculated from EEG signals.

[0027] Simulation Experiment 2 To verify whether dynamically adjusting the teaching difficulty based on the neural efficiency index can improve the learning efficiency of trainees, the following simulation experiment was carried out: According to the initial neural efficiency index, the trainees were divided into a dynamic adjustment group and a fixed difficulty group to ensure that the cognitive abilities of the two groups were matched. The dynamic adjustment group adjusted the teaching difficulty in real time according to the neural efficiency index, and the fixed difficulty group always maintained a medium difficulty. The neural efficiency index, decision-making accuracy rate, and task completion time of the trainees at each decision point were recorded. The average decision-making accuracy rate, average task completion time, and peak cognitive load of the two groups of trainees were calculated, and the t-test was used to compare the differences in the learning efficiency indicators of the two groups of trainees. The results are shown in Table 2: Efficiency index Dynamic adjustment group Fixed difficulty group Improvement range Improvement range 85.2±3.1 78.9±4.2 +7.9% Task completion time (s) 420±25 485±30 -13.4% Peak cognitive load 0.52±0.04 0.45±0.06 -15.7% Table 2 As can be seen from Table 2, dynamically adjusting the teaching difficulty can significantly improve the learning efficiency of trainees, specifically manifested as an increase in the decision-making accuracy rate, a shortening of the task completion time, and a decrease in the peak cognitive load.

[0028] In summary, by collecting the EEG signals of students, the present invention can clearly judge the cognitive load level of students, and at the same time, corresponding interventions can be made on the difficulty of economic management teaching courses according to the cognitive load level of students. In this way, not only can personalized teaching for students be realized, but also students can be assisted in learning efficiently.

[0029] Although the embodiments of the present invention have been shown and described, for those of ordinary skill in the art, it can be understood that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A training system for economic management teaching based on cloud services, characterized in that, Including: A bio-signal acquisition module for acquiring the electroencephalogram (EEG) signals of students; An EEG signal processing module, and a neural efficiency index calculation module for extracting features from the EEG signals of students and calculating the real-time neural efficiency index; A dynamic difficulty adjustment module for judging the cognitive load level of students according to the real-time neural efficiency index and performing difficulty intervention on the economic management teaching content during the teaching process according to the judgment result.

2. The training system for economic management teaching based on cloud service according to claim 1, characterized in that, The method for extracting features from the EEG signals of students includes: Using independent component analysis to remove electrooculogram artifacts from the EEG signals; Extract using wavelet packet transform wave, wave, wave and the band characteristics of the wave.

3. The training system for economic management teaching based on cloud service according to claim 1, characterized in that, The calculation formula of the real-time neural efficiency index includes: Wherein, is the real-time neural efficiency index, is wave power, is wave power, is wave power, is wave power, is the behavior deviation attenuation coefficient, is the behavior deviation index.

4. A training system for economic management teaching based on cloud services according to claim 1, characterized in that, The method for judging the cognitive load level of students according to the real-time neural efficiency index includes: Presetting a neural efficiency index threshold and a judgment duration, dynamically adjusting the preset neural efficiency index threshold according to the class progress, and judging that the student is in a high cognitive load state when the real-time neural efficiency index continuously falls below the dynamically adjusted neural efficiency index threshold and reaches the judgment duration; Combining the dynamically adjusted neural efficiency index threshold to perform gradient grading on the neural efficiency index, and performing first-level intervention, second-level intervention, and third-level intervention judgments on the corresponding real-time neural efficiency index when it is judged that the student is in a high cognitive load state, where the cognitive load levels corresponding to the first-level intervention, second-level intervention, and third-level intervention gradually deepen.

5. An economic management teaching training system based on cloud services according to claim 4, characterized in that, The method for dynamically adjusting the preset neural efficiency index threshold according to the class progress includes: In the formula, is the threshold of the neural efficiency index after dynamic adjustment, is the preset threshold of the neural efficiency index, is the current class progress, is the total class length.

6. An economic management teaching training system based on cloud services according to claim 5, characterized in that, The method for performing difficulty intervention on the economic management teaching content during the teaching process according to the judgment result includes: When the judgment result is a first-level intervention, start visual simplification and hide the secondary information of the teaching interface; When the judgment result is a secondary intervention, start auditory adjustment and output 10Hz binaural beat wave music through bone conduction headphones ; When the judgment result is a third-level intervention, start decision support and display a probabilistic strategy prompt box on the interface.

7. An economic management teaching training system based on cloud services according to claim 6, characterized in that, Outputting 10 Hz binaural beat When playing wave music through bone conduction headphones, perform dynamic adjustment of the volume. Among them, the volume dynamic adjustment formula includes: Wherein, is the adjusted wave music volume, is the reference volume, is the real-time neural efficiency index.

8. An economic management teaching training system based on cloud services according to claim 6, characterized in that, When the probabilistic strategy prompt box is displayed on the interface, the decision prompt confidence calculation formula includes: wherein, is the confidence level of the decision-making prompt, is the sensitivity coefficient, is the baseline neural efficiency index of the trainee under a 5-minute resting state, that is, the baseline cognitive efficiency value.

Images