Financial training examination management system based on cloud platform

Abstract

The invention relates to the technical field of accounting training, in particular to a financial training assessment management system based on a cloud platform, and the system comprises a data acquisition module which is used for obtaining the exercise assessment data of each student in a financial training course from a cloud server in real time; the financial training module is used for carrying out financial training on each trainee through the adjusted trainee financial training scheme; the examination and evaluation module is used for carrying out examination and evaluation on each student according to the financial training result and the multi-dimensional analysis result; and the cloud control module is used for feeding back a financial training instruction to the financial training module through the examination and evaluation result, and controlling the financial training module to feed back financial training suggestions to the trainees through the financial training instruction. The financial knowledge level condition of the training object can be analyzed, the requirements of different learners are effectively met, and then the actual effect of financial training is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of accounting training, and particularly to a financial training assessment management system based on a cloud platform. Background Art

[0002] Currently, the financial training assessment system often designs unified teaching content and forms based on group commonalities, but it is difficult to take into account the personalized needs and dynamic learning processes of training objects. In addition, there is a lack of real-time data analysis and intelligent intervention means during the training process, and it is impossible to accurately identify the weak links of training objects and adjust teaching strategies in a timely manner, resulting in a significant reduction in the training effect.

[0003] Chinese Patent Publication No. CN119359109A discloses an accounting and financial training assessment method, system and storage medium based on a neural network model, including: obtaining the login information of a training object and the training rating information of the most recent time, and requesting to configure simulated original bills to be processed by simulated customers corresponding to simulated customer grading; obtaining on-site training images and simulated original bill images; obtaining a first recognition result and a second recognition result; obtaining the voucher entry information manually input by the training object, and performing difference detection on the second recognition result and the voucher entry information in real time; when it is detected that a second behavior pre-determined by the first recognition result ends, comparing the first input data after the end of the second behavior and the last input data before the second behavior, and issuing a first instruction if they are different; calculating the training accuracy evaluation value of the training object; determining the training rating of the training object. However, this solution cannot analyze the financial knowledge level of training objects, resulting in the difficulty of effectively meeting the needs of different learners with unified training content and methods, thereby affecting the actual effect of financial training. Summary of the Invention

[0004] Therefore, the present invention provides a financial training assessment management system based on a cloud platform to overcome the problem in the prior art that due to the analysis of the financial knowledge level of training objects, the unified training content and methods are difficult to effectively meet the needs of different learners, thereby affecting the actual effect of financial training.

[0005] To achieve the above object, the present invention provides a financial training assessment management system based on a cloud platform, and the system includes: A data acquisition module, configured to obtain the practice assessment data of each student in the financial training course from the cloud server in real time, and preprocess the practice assessment data to obtain actual practice assessment data; A financial training module, which is used to perform multi-dimensional analysis on the financial knowledge levels of each trainee according to the actual practice assessment data, obtain the multi-dimensional analysis results corresponding to each trainee, and adjust the trainee financial training plan corresponding to each trainee in real time according to the multi-dimensional analysis results to obtain the adjusted trainee financial training plan, and conduct financial training on each trainee through the adjusted trainee financial training plan to obtain financial training results; An assessment module, which is used to assess each trainee according to the financial training results and multi-dimensional analysis results to obtain assessment results; A cloud control module, which is used to feedback data display information to the data acquisition module according to the user request instruction corresponding to the actual practice assessment data, feedback a financial training instruction to the financial training module through the assessment result, and control the financial training module to feedback financial training suggestions to the trainee through the financial training instruction.

[0006] Furthermore, the financial training module includes a trainee financial level analysis unit. The trainee financial level analysis unit classifies and marks the actual practice assessment data according to a preset financial knowledge dimension system to obtain a multi-dimensional standardized data set, and establishes a multi-dimensional evaluation matrix including knowledge breadth, depth mastery, and comprehensive application ability based on the multi-dimensional standardized data set, and performs multi-dimensional analysis on the financial knowledge levels of each trainee according to the multi-dimensional evaluation matrix to obtain the multi-dimensional analysis results corresponding to each trainee.

[0007] Furthermore, the financial training module also includes a training plan adjustment unit. The training plan adjustment unit obtains the financial knowledge scores of each dimension of each trainee according to the multi-dimensional analysis results and calculates the financial knowledge comprehensive ability evaluation index SQ of each trainee according to the financial knowledge scores of each dimension of each trainee , sets , represents the weight coefficient used to adjust the financial knowledge scores of each dimension of each trainee , n represents the total number of dimensions of the financial knowledge scores, compares the financial knowledge comprehensive ability evaluation index SQ with the preset financial knowledge comprehensive ability evaluation index SQ0, judges the financial knowledge comprehensive application situation of each trainee according to the comparison result, and adjusts the trainee financial training plan corresponding to each trainee in real time according to the judgment result to obtain the adjusted trainee financial training plan corresponding to each trainee, where: When SQ ≥ SQ0, the training program adjustment unit determines that the comprehensive application of financial knowledge of the trainee meets the standard of financial knowledge level, and outputs the preset standard trainee financial training program corresponding to the preset financial knowledge comprehensive ability evaluation index SQ0 as the adjusted trainee financial training program of the trainee; When SQ < SQ0, the training program adjustment unit determines that the comprehensive application of financial knowledge of the trainee does not meet the standard of financial knowledge level, trains the convolutional neural network model according to the historical primary financial training program data set, outputs the convolutional neural network model that meets the preset correct rate as the primary financial training program recognition model, and identifies the actual practice evaluation data according to the primary financial training program recognition model to obtain the primary trainee financial training program of the trainee, and outputs the primary trainee financial training program as the adjusted trainee financial training program of the trainee.

[0008] Furthermore, the financial training module further includes a financial training unit. When the training program adjustment unit determines that the financial knowledge level of the trainee meets the standard of financial knowledge level, the financial training unit conducts financial training on the trainee according to the preset standard trainee financial training program to obtain the first financial training result, and outputs the first financial training result as the financial training result. When the training program adjustment unit determines that the financial knowledge level of the trainee does not meet the standard of financial knowledge level, the financial training unit conducts financial training on the trainee according to the primary trainee financial training program to obtain the second financial training result, and outputs the second financial training result as the financial training result.

[0009] Furthermore, the assessment and evaluation module performs data fusion on the financial training result and the multi-dimensional analysis result to obtain the first data fusion result, and extracts the z-th financial training result according to the first data fusion result 、the z-th multi-dimensional analysis result and the dynamic adjustment factor of the z-th learning behavior , and according to the z-th financial training result 、the z-th multi-dimensional analysis result and the dynamic adjustment factor of the z-th learning behavior calculate the trainee suitability assessment index PX of each trainee, and set , where b1 represents the weight of the z-th financial training result ,b2 represents the weight of the z-th multi-dimensional analysis result ,m represents the type of actual practice evaluation data indicators, represents the dynamic adjustment factor of the z-th learning behavior The weights are set such that b1 + b2 = 1. The candidate suitability evaluation index PX of the trainee is compared with the preset candidate suitability evaluation index PX0. Based on the comparison result, the suitability of each trainee is judged, and each trainee is evaluated according to the judgment result to obtain the corresponding evaluation result for each trainee, where: When PX ≥ PX0, the assessment module determines that the trainee's suitability is a suitable situation, and evaluates the trainee according to the assessment plan corresponding to the preset candidate suitability evaluation index to obtain the corresponding assessment result for the trainee; When PX < PX0, the assessment module determines that the trainee's suitability is an unsuitable situation and does not evaluate the trainee.

[0010] Furthermore, the system further includes a learning behavior warning module. The learning behavior warning module establishes the learning behavior habit curve of each trainee according to the learning behavior curve preparation method, and the learning behavior curve preparation method includes: Step A1, extract the learning progress completion rate C(t) of each trainee at time t, the total progress T of the financial training course, the average answering speed of each trainee at time t and the standard answering speed from the financial training results, and calculate the trainee training effect data P(t) of each trainee according to the learning progress completion rate C(t) of each trainee at time t, the total progress T of the financial training course, the average answering speed of each trainee at time t and the standard answering speed . Set , where represents the learning progress of each trainee, represents the ratio of the answering speed of each trainee to the standard answering speed; Step A2, establish the learning behavior habit curve of each trainee with the training time t of each trainee as the abscissa and the current observed behavior value B of each trainee at time t as the ordinate. The mathematical expression of the learning behavior habit curve is: B , where represents the actual practice evaluation data index of each trainee at time t. Set m represents the type of the actual practice evaluation data index, represents the weight of the jth actual practice evaluation data index, represents the occurrence frequency of the jth actual practice evaluation data index at time t, represents the weight used to adjust the trainee training effect data P(t) of each trainee, Denotes the weight used to adjust the actual practice evaluation data indicators of each trainee at time t. Denotes the rate of change of the training effect data of each trainee with the training time. Denotes the weight used to adjust the rate of change of the training effect data of each trainee with the training time, and is set .

[0011] Furthermore, the learning behavior warning module extracts the current observed behavior value B of each trainee at time t according to the learning behavior habit curve of each trainee. , and calculates the trainee behavior deviation index BDI of each trainee according to the current observed behavior value B of each trainee at time t. Set BDI = |B - JZ| / BZ × W, where W represents the trainee learning stage weight, JZ represents the historical baseline mean value, and is set , g represents the number of time units used to calculate the historical baseline mean value. , Denotes the learning progress completion rate of the trainee at time , BZ represents the historical baseline standard deviation, and is set B . Denotes the square of the difference between the learning progress of each time unit and the historical baseline mean value. The learning behavior warning module compares the trainee behavior deviation index BDI with the first preset trainee behavior deviation index BDI1 and the second preset trainee behavior deviation index BDI2, judges the learning behavior situation of each trainee according to the comparison result, and warns the learning behavior of the trainee according to the judgment result to obtain the learning behavior warning result. Set BDI1 < BDI2, where: When BDI < BDI1, the learning behavior warning module determines that the learning behavior situation of the trainee is normal and does not warn the learning behavior of the trainee. When BDI1 ≤ BDI < BDI2, the learning behavior warning module determines that the learning behavior situation of the trainee is a moderate deviation situation, pushes a yellow warning message to the trainee, and outputs the yellow warning message as the learning behavior warning result. When BDI ≥ BDI2, the learning behavior warning module determines that the learning behavior situation of the trainee is a severe deviation situation, pushes a red warning message to the trainee, and outputs the red warning message as the learning behavior warning result.

[0012] Furthermore, the cloud control module includes a cloud server. The cloud server feeds back data display information to the data acquisition module according to the data display method. The data display method includes: Step B1: Obtain the corresponding user request instruction according to the actual practice evaluation data, parse the data of the user request instruction to obtain the key request instruction information, and perform data mapping between the key request instruction information and the interface of the data acquisition module to obtain the data interface information corresponding to the key request instruction information; Step B2: Generate standardized query parameters according to the key request instruction information, and call the data interface information according to the standardized query parameters to obtain the original data; Step B3: Conduct data verification on the original data, and display the original data that meets the verification conditions to obtain the data display information.

[0013] Furthermore, the cloud control module further includes a learning behavior warning feedback unit. The learning behavior warning feedback unit compares the learning behavior warning result with the preset learning behavior standard, judges the learning situation of each student according to the comparison result, and feeds back the learning behavior warning information to each student according to the judgment result, where: When the learning behavior warning result is consistent with the preset learning behavior standard, the learning behavior warning feedback unit determines that the learning situation of this student is in a normal state and does not feed back the learning behavior warning information to this student; When the learning behavior warning result is inconsistent with the preset learning behavior standard, the learning behavior warning feedback unit determines that the learning situation of this student is in an abnormal state. The learning behavior warning feedback unit sends the learning behavior warning information to the learning behavior warning module and controls the learning behavior warning module to display the learning behavior warning information through the display device.

[0014] Furthermore, the cloud control module further includes a student assessment feedback unit. The student assessment feedback unit performs data fusion on the learning behavior warning information and the assessment result to obtain a second data fusion result, compares the second data fusion result with the preset assessment benchmark, judges the assessment situation of each student according to the comparison result, and feeds back financial training suggestions to this student according to the judgment result, where: When the second data fusion result is consistent with the preset assessment benchmark, the student assessment feedback unit determines that the assessment situation of this student is a qualified assessment situation and does not feed back financial training suggestions to this student; When the second data fusion result is inconsistent with the preset assessment benchmark, the student assessment feedback unit determines that the assessment situation of this student is an unqualified assessment situation, generates a financial training instruction according to the preset assessment benchmark, feeds back the financial training instruction to the financial training module, and controls the financial training module to feed back financial training suggestions to this student through the financial training instruction.

[0015] Compared with the prior art, the beneficial effects of the present invention are as follows. Through the data acquisition module, the system can obtain and preprocess the practice and evaluation data of trainees in real time, ensuring that subsequent analysis and training program adjustments are based on accurate and standardized data, improving data processing efficiency and reliability. Through the financial training module, the system can obtain and preprocess the practice and evaluation data of trainees in real time, ensuring that subsequent analysis and training program adjustments are based on accurate and standardized data, improving data processing efficiency and reliability. Through the assessment module, the system combines the financial training results with multi-dimensional analysis results to comprehensively and quantitatively evaluate the abilities of trainees, providing a scientific basis for training effects and data support for subsequent optimization of training programs and adjustment of learning paths. Through the cloud control module, the system integrates user requests, assessment results, and training instructions to achieve data linkage and closed-loop control between modules, ensuring that training suggestions are matched with trainee needs in real time. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 FIG. is a schematic structural diagram of a financial training assessment management system based on a cloud platform according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0017] The following is a further detailed description through specific embodiments: Please refer to Figure 1 as shown, a schematic structural diagram of a financial training assessment management system based on a cloud platform, the system includes: A data acquisition module, configured to obtain in real time the practice and evaluation data of each trainee in a financial training course from a cloud server, and preprocess the practice and evaluation data to obtain actual practice and evaluation data; A financial training module, configured to perform multi-dimensional analysis on the financial knowledge level of each trainee according to the actual practice and evaluation data to obtain multi-dimensional analysis results corresponding to each trainee, and adjust the financial training plan of each trainee in real time according to the multi-dimensional analysis results to obtain an adjusted financial training plan for the trainee, and perform financial training on each trainee through the adjusted financial training plan for the trainee to obtain financial training results; An assessment module, configured to assess each trainee according to the financial training results and multi-dimensional analysis results to obtain assessment results; A cloud control module, configured to feedback data display information to the data acquisition module according to a user request instruction corresponding to the actual practice and evaluation data, feedback a financial training instruction to the financial training module through the assessment result, and control the financial training module to feedback financial training suggestions to the trainee through the financial training instruction.

[0018] Specifically, the system is applied to the financial training and assessment system of colleges and universities. By obtaining the practice assessment data of each student in the financial training course in real time and combining with the adjusted financial training plan for students, the system can comprehensively evaluate the training effect of students, which helps to improve the learning efficiency and training effect of students. Through the data acquisition module, the system can obtain and preprocess the practice assessment data of students in real time, ensuring that subsequent analysis and training plan adjustment are based on accurate and standardized data, and improving the data processing efficiency and reliability. Through the financial training module, the system can obtain and preprocess the practice assessment data of students in real time, ensuring that subsequent analysis and training plan adjustment are based on accurate and standardized data, and improving the data processing efficiency and reliability. Through the assessment module, the system combines the financial training results with the multi-dimensional analysis results to comprehensively and quantitatively evaluate the students' abilities, providing a scientific basis for the training effect and at the same time providing data support for subsequent optimization of the training plan and adjustment of the learning path. Through the cloud control module, the system integrates user requests, assessment results and training instructions to realize data linkage and closed-loop control between modules, ensuring that training suggestions are matched with students' needs in real time.

[0019] Specifically, the data acquisition module performs outlier detection on the practice assessment data to obtain corresponding data outliers, processes the data outliers according to the corresponding data outlier processing scheme for the practice assessment data to obtain corresponding outlier processing results, and performs data conversion on the outlier processing results to obtain corresponding actual practice assessment data.

[0020] Specifically, the cloud server refers to a computer server used to manage the practice assessment data. The financial training course refers to a financial training course provided to students. The practice assessment data is the data generated by students during the financial training course, including learning behavior data, learning result data, and learning environment data. The learning behavior data refers to the data generated by the behaviors directly related to learning activities during the financial training assessment process, including the current chapter stay time, the number of repeated learning times, the number of times the hot area of the courseware is clicked, and the learning progress. The current chapter stay time refers to the length of time that a student spends on the current learning chapter. The number of repeated learning times refers to the number of times a student repeats the learning of a certain chapter or content. The number of times the hot area of the courseware is clicked refers to the number of times the area where the student clicks most frequently in the courseware. The learning progress refers to the progress of a student in completing the entire course or a specific chapter. The learning result data refers to the data generated by a student through answering questions, taking tests, or assessments during the financial training assessment process, including the answer correct rate, the submission time, the answering speed, and the assessment feedback. The answer correct rate refers to the proportion of questions that a student answers correctly in the assessment or practice. The submission time refers to the time when a student completes the assessment or practice and submits the answers. The answering speed refers to the speed at which a student completes the questions. The assessment feedback refers to the detailed feedback on the student's answering situation. The learning environment data refers to the data related to the learning environment during the financial training assessment process, including the device type, the network status, and the learning time period. The device type refers to the type of device used by a student for learning. In this embodiment, the specific type of learning device is not specifically limited. For example, the device type can be set as a mobile phone, a tablet, and a computer. The network status refers to the network connection status when a student is learning, such as stable, unstable, and offline. The learning time period refers to the time period when a student conducts learning. In this embodiment, the specific implementation manner of outlier detection is not limited. For example, it can be set to perform outlier detection on the practice assessment data through the Isolation Forest algorithm. The data outlier refers to the value obtained by performing outlier detection on the practice assessment data. The data outlier processing scheme refers to a strategy for processing the data outlier. In this embodiment, the specific implementation manner of the data outlier processing scheme is not limited. Those skilled in the art can freely set it according to the actual situation as long as it meets the requirement of processing the data outlier. For example, it can be set to process the data outlier through the 3-sigma method. The outlier processing result refers to the result obtained by processing the data outlier according to the corresponding data outlier processing scheme of the practice assessment data. In this embodiment, the specific implementation manner of data conversion is not limited. For example, it can be set to perform data conversion on the outlier processing result through the Z-score method. The actual practice assessment data refers to the data obtained by performing data conversion on the outlier processing result.

[0021] Specifically, the accuracy and reliability of the practice assessment data are improved through outlier detection and processing, and actual valid data is obtained through data conversion to ensure that the final practice assessment data obtained meets actual needs.

[0022] Specifically, the financial training module includes a student financial level analysis unit, which classifies and labels the actual practice assessment data according to a preset financial knowledge dimension system to obtain a multi-dimensional standardized data set, and establishes a multi-dimensional evaluation matrix including knowledge breadth, depth of mastery and comprehensive application ability based on the multi-dimensional standardized data set, and conducts a multi-dimensional analysis of the financial knowledge level of each student based on the multi-dimensional evaluation matrix to obtain a multi-dimensional analysis result corresponding to each student.

[0023] Specifically, the preset financial knowledge dimension system refers to a preset standard system for dividing different aspects of financial knowledge, including basic accounting knowledge, tax knowledge and auditing knowledge. This embodiment does not limit the specific implementation methods of classification marking. For example, it can be set to predefine a keyword library for each financial knowledge dimension. Through a text matching algorithm, the questions or answers in the actual practice assessment data are compared with the keywords to determine the dimension to which they belong. The multi-dimensional standardized data set refers to a data set formed after the actual practice assessment data is classified and marked according to the preset financial knowledge dimension system. The multi-dimensional evaluation matrix refers to a matrix model established based on the multi-dimensional standardized data set and used to evaluate the financial knowledge level of students. The financial knowledge level of each student refers to the specific performance of each student in each dimension of financial knowledge. and mastery, including the breadth of knowledge, depth of mastery and comprehensive application ability. This embodiment does not limit the specific implementation method of the multi-dimensional analysis. For example, it can be set to count the question coverage of the statisticians on each financial knowledge dimension, and calculate the breadth index of their knowledge coverage. For example, the proportion of the number of dimensions involved by the trainees to the total number of dimensions is calculated, and the mastery of the knowledge is evaluated according to the scores of the trainees on the questions on each dimension. The average score, score rate and other indicators can be used for measurement. By analyzing the performance of the trainees in solving complex financial problems or comprehensive cases, their ability to comprehensively apply financial knowledge can be evaluated. Expert scoring, case analysis reports and other methods can be used for evaluation. The multi-dimensional analysis results corresponding to each trainee refer to the specific conclusions drawn after analyzing the financial knowledge level of each trainee according to the multi-dimensional evaluation matrix.

[0024] Specifically, the student financial level analysis unit classifies and labels the actual assessment data according to the preset financial knowledge dimension system to form a standardized data set, and then constructs a multi-dimensional evaluation matrix, which can accurately and comprehensively analyze the financial knowledge level of each student and produce multi-dimensional analysis results.

[0025] Specifically, the financial training module further includes a training program adjustment unit, and the training program adjustment unit obtains the financial knowledge scores of each dimension of each trainee according to the multi-dimensional analysis result , and according to the financial knowledge scores of each dimension of each trainee , calculates the comprehensive financial knowledge ability evaluation index SQ of each trainee, and sets , represents the weight coefficient used to adjust the financial knowledge scores of each dimension of each trainee , n represents the total number of dimensions of the financial knowledge scores, compares the comprehensive financial knowledge ability evaluation index SQ with the preset comprehensive financial knowledge ability evaluation index SQ0, judges the comprehensive application situation of the financial knowledge of each trainee according to the comparison result, and adjusts the trainee financial training plan corresponding to each trainee in real time according to the judgment result to obtain the adjusted trainee financial training plan corresponding to each trainee, where: When SQ≥SQ0, the training program adjustment unit determines that the comprehensive application situation of the financial knowledge of this trainee meets the standard of financial knowledge level, and outputs the preset standard trainee financial training plan corresponding to the preset comprehensive financial knowledge ability evaluation index SQ0 as the adjusted trainee financial training plan of this trainee; When SQ<SQ0, the training program adjustment unit determines that the comprehensive application situation of the financial knowledge of this trainee does not meet the standard of financial knowledge level, trains the convolutional neural network model according to the historical primary financial training program data set, outputs the convolutional neural network model that meets the preset correct rate as the primary financial training program recognition model, and recognizes the actual practice evaluation data according to the primary financial training program recognition model to obtain the primary trainee financial training plan of this trainee, and outputs the primary trainee financial training plan as the adjusted trainee financial training plan of this trainee.

[0026] Specifically, the financial knowledge scores of each dimension of each trainee It refers to the quantified scores obtained by each trainee in each specific financial knowledge dimension (such as basic accounting knowledge, financial management, tax knowledge, audit knowledge, etc.) under the preset financial knowledge dimension system. The comprehensive application of financial knowledge of each trainee refers to the ability and level of each trainee to comprehensively apply the knowledge of each financial knowledge dimension they have mastered in actual situations. The preset financial knowledge comprehensive ability evaluation index SQ0 refers to a preset value used to compare with the financial knowledge comprehensive ability evaluation index SQ of each trainee, such as 75 points. The adjusted trainee financial training plan refers to a new plan obtained by making targeted modifications and improvements to the original trainee financial training plan based on the judgment result of the comprehensive application of trainee financial knowledge. The primary financial training plan recognition model refers to a model that meets the preset accuracy rate obtained by training a convolutional neural network model based on the historical primary financial training plan dataset. The historical primary financial training plan dataset refers to a dataset preset for training a convolutional neural network model in the storage form of historical primary financial training plan data - trainee financial training plan. The convolutional neural network model refers to a machine learning model used to extract features from actual practice evaluation data and predict the primary trainee financial training plan. In this embodiment, the training method of the convolutional neural network model is not limited, and those skilled in the art can freely set it as long as it meets the requirement of identifying the actual practice evaluation data. For example, 75% of the historical primary financial training plan dataset can be divided into a training plan data training set, and 25% can be divided into a training plan data test set. The training plan data training set is input into the convolutional neural network model for training, and the training plan data test set is input into the trained convolutional neural network model to optimize and iterate the parameters in the convolutional neural network model until the accuracy rate of the output result of the training plan data test set of the convolutional neural network model reaches the preset accuracy rate. Then, the convolutional neural network model is output as the primary financial training plan recognition model. The preset accuracy rate refers to a preset value reflecting the training situation of the convolutional neural network model. In this embodiment, the value of the preset accuracy rate is not limited, and relevant technical personnel in the art can freely set it as long as it meets the requirement of reflecting the training situation of the convolutional neural network model. For example, the preset accuracy rate can be set to 95%. The preset standard trainee financial training plan refers to a standard training plan preset for qualified trainees when the trainee's financial knowledge level is qualified. In this embodiment, the specific implementation method of the preset standard trainee financial training plan is not limited. For example, it can be set to design in-depth training courses focusing on advanced applications such as financial analysis, tax planning, and risk management, and adopt forms such as actual case analysis, group discussion, expert lectures, and project practice to improve the trainee's ability to solve complex financial problems and provide strategic decision-making support.The junior trainee financial training plan refers to the training plan obtained by identifying the actual practice assessment data through the junior financial training plan identification model. In this embodiment, the specific implementation method of the junior trainee financial training plan is not limited. For example, it can be set to carry out a systematic introductory training centered on basic financial concepts and basic accounting treatment processes, and help trainees build a financial knowledge framework and master basic skills through a combination of theoretical explanations, simple case simulations, and practical exercises.

[0027] Specifically, through the training plan adjustment unit, it is possible to accurately determine a suitable training plan for trainees with different financial knowledge levels, which helps to improve the effect of trainee financial training.

[0028] Specifically, the financial training module further includes a financial training unit. When the training plan adjustment unit determines that the financial knowledge level of the trainee reaches the standard, the financial training unit conducts financial training on the trainee according to the preset standard trainee financial training plan, obtains the first financial training result, and outputs the first financial training result as the financial training result. When the training plan adjustment unit determines that the financial knowledge level of the trainee does not reach the standard, the financial training unit conducts financial training on the trainee according to the junior trainee financial training plan, obtains the second financial training result, and outputs the second financial training result as the financial training result.

[0029] Specifically, the first financial training result refers to the result obtained by conducting financial training on trainees whose financial knowledge level is determined to reach the standard according to the preset standard trainee financial training plan. The second financial training result refers to the result obtained by conducting financial training on trainees whose financial knowledge level is determined not to reach the standard according to the junior trainee financial training plan. The financial training result refers to the result obtained by conducting financial training on each trainee through the adjusted trainee financial training plan.

[0030] Specifically, through the financial training unit, different levels of financial training plans are flexibly adopted according to the financial knowledge level of the trainees to achieve personalized financial training, thereby effectively improving the financial knowledge and skills level of the trainees and enhancing the quality and effect of training.

[0031] Specifically, the assessment and evaluation module performs data fusion on the financial training result and the multi-dimensional analysis result to obtain the first data fusion result, and extracts the z-th financial training result according to the first data fusion result and the z-th multi-dimensional analysis result and the dynamic adjustment factor of the z-th learning behavior , and according to the z-th financial training result and the z-th multi-dimensional analysis result and the dynamic adjustment factor of the z-th learning behavior Calculate the student suitability assessment index PX for each student and set , where b1 represents the z-th financial training result weight, b2 represents the weight of the z-th multi-dimensional analysis result , m represents the type of actual practice assessment data indicators represents the dynamic adjustment factor of the z-th learning behavior weight, set b1 + b2 = 1, compare the student suitability assessment index PX with the preset student suitability assessment index PX0, judge the suitability of each student according to the comparison result, and conduct a performance assessment on each student according to the judgment result to obtain the performance assessment result corresponding to each student, where: When PX ≥ PX0, the performance assessment module determines the suitability of the student as a suitable situation, and conducts a performance assessment on the student according to the performance assessment plan corresponding to the preset student suitability assessment index to obtain the performance assessment result corresponding to the student; When PX < PX0, the performance assessment module determines the suitability of the student as an unsuitable situation and does not conduct a performance assessment on the student.

[0032] Specifically, the first data fusion result refers to the result obtained by fusing the financial training result and the multi-dimensional analysis result. In this embodiment, the specific implementation scheme of data fusion for the financial training result and the multi-dimensional analysis result is not limited. For example, it can be set that the feature vectors of the financial training result and the multi-dimensional analysis result are concatenated to form a new feature vector as the fusion result. The dynamic adjustment factor of the z-th learning behavior refers to the parameter used to adjust the student suitability assessment index. The preset student suitability assessment index PX0 refers to the preset value compared with the student suitability assessment index PX, such as 0.9. The performance assessment plan refers to the assessment plan and evaluation criteria formulated for suitable students. For example, it is stipulated that the assessment content includes a theoretical knowledge exam (accounting for 60% weight) and an actual operation assessment (accounting for 40% weight). The theoretical knowledge exam adopts a closed-book written test form, and the actual operation assessment requires the student to complete a specific financial task within a specified time. The evaluation criteria are scored according to the completion of the exam and the operation according to the pre-set scoring rules, and finally the student's assessment score is obtained.

[0033] Specifically, through the performance assessment module, it is possible to accurately judge whether a student meets the conditions for taking the assessment, avoid ineffective assessments of unsuitable students, improve the pertinence and effectiveness of the assessment, and at the same time ensure that suitable students receive reasonable performance assessments, which helps to improve the training quality and the accuracy of the assessment results.

[0034] Specifically, the system further includes a learning behavior warning module. The learning behavior warning module establishes the learning behavior habit curves of each student according to the learning behavior curve preparation method. The learning behavior curve preparation method includes: Step A1: Extract the learning progress completion rate C(t) of each student at time t, the total progress T of the financial training course, the average answering speed of each student at time t and the standard answering speed , and calculate the student training effect data P(t) of each student according to the learning progress completion rate C(t) of each student at time t, the total progress T of the financial training course, the average answering speed of each student at time t and the standard answering speed . Set , where represents the learning progress of each student, represents the ratio of the answering speed of each student to the standard answering speed; Step A2: Establish the learning behavior habit curves of each student with the training time t of each student as the abscissa and the current observed behavior value B of each student at time t as the ordinate. The mathematical expression of the learning behavior habit curve is: B , where represents the actual practice evaluation data index of each student at time t. Set m represents the types of actual practice evaluation data indexes, represents the weight of the jth actual practice evaluation data index, represents the occurrence frequency of the jth actual practice evaluation data index at time t, represents the weight used to adjust the student training effect data P(t) of each student, represents the weight used to adjust the actual practice evaluation data index of each student at time t, represents the change rate of the training effect data of each student with the training time, represents the weight used to adjust the change rate of the training effect data of each student with the training time. Set .

[0035] Specifically, the learning progress completion rate C(t) of each student at time t refers to the ratio of the financial training course progress completed by each student at time t to the total progress. The total progress T of the financial training course refers to all the content from the start to the end of the financial training course. The average answering speed of each student at time t Refers to the average speed of each trainee during the answering process at time t, and the standard answering speed Refers to the preset answering speed standard for reference, such as 1.5 questions per minute. The training time t refers to the specific time point when each trainee participates in the training. The learning behavior habit curve of each trainee refers to a curve with the training time as the abscissa and the current observed behavior value B of each trainee at time t As the ordinate, which is used to visually display the change trend of each trainee's learning behavior over time. The actual practice evaluation data index of each trainee at time t Refers to the data index generated by the interaction behavior between the trainee and the financial training course at time t, such as the number of logins, page views, video viewing duration, etc. The type m of the actual practice evaluation data index refers to different types of actual practice evaluation data indexes, such as login behavior, learning behavior, answering behavior, etc.

[0036] Specifically, through the learning behavior warning module, the learning behavior habit curve of each trainee can be constructed, and the learning behavior of each trainee can be comprehensively and dynamically warned, thereby improving the training quality and efficiency.

[0037] Specifically, the learning behavior warning module extracts the current observed behavior value B of each trainee at time t according to the learning behavior habit curve of each trainee , and according to the current observed behavior value B of each trainee at time t Calculate the trainee behavior deviation index BDI of each trainee, and set BDI = |B - JZ| / BZ × W, where W represents the trainee learning stage weight, JZ represents the historical baseline mean, and set , g represents the number of time units used to calculate the historical baseline mean Represents the learning progress completion rate of the trainee at time , BZ represents the historical baseline standard deviation, and set B , Represents the square of the difference between the learning progress of each time unit and the historical baseline mean; The learning behavior warning module compares the trainee behavior deviation index BDI with the first preset trainee behavior deviation index BDI1 and the second preset trainee behavior deviation index BDI2, judges the learning behavior of each trainee according to the comparison result, and warns the learning behavior of the trainee according to the judgment result to obtain the learning behavior warning result, and set BDI1 < BDI2, where: When BDI < BDI1, the learning behavior warning module determines that the learning behavior of the trainee is normal and does not warn the learning behavior of the trainee; When BDI1 ≤ BDI < BDI2, the learning behavior warning module determines that the learning behavior of the student is moderately deviated, and pushes a yellow warning message to the student, and outputs the yellow warning message as the learning behavior warning result; When BDI ≥ BDI2, the learning behavior warning module determines that the learning behavior of the student is severely deviated, and pushes a red warning message to the student, and outputs the red warning message as the learning behavior warning result.

[0038] Specifically, the historical baseline mean JZ refers to the average value calculated by statistically analyzing the learning behavior data of each student over a period of time in the past. For example, by statistically analyzing the daily learning duration of a student on the learning platform in the past 30 days, the average daily learning duration is calculated to be 1.5 hours, and this 1.5 hours is the historical baseline mean JZ. The historical baseline standard deviation BZ is also calculated based on the student's past learning behavior data. For example, according to the above 30-day learning duration data, the standard deviation is calculated to be 0.5 hours, and this 0.5 hours is the historical baseline standard deviation BZ. In this embodiment, the number of time units is not specifically limited, and can be set to 7 days, for example. The first preset student behavior deviation index BDI1 refers to the minimum preset value used to judge the deviation degree of the student's learning behavior, such as 0.5. The second preset student behavior deviation index BDI2 refers to the maximum preset value used to judge the deviation degree of the student's learning behavior, such as 1.5. The yellow warning message refers to the warning message pushed to the student when the student behavior deviation index BDI is in the range of BDI1 ≤ BDI < BDI2. For example, a message "Your learning behavior has deviated moderately. Please arrange your learning time reasonably and improve your learning efficiency" is pushed. The red warning message refers to the warning message pushed to the student when the student behavior deviation index BDI ≥ BDI2. For example, a message "Your learning behavior seriously deviates from normal. Please immediately adjust your learning state, otherwise it may affect your learning effect" is pushed.

[0039] Specifically, through the real-time warning of the student's learning behavior by the learning behavior warning module, abnormal situations in the student's learning process can be discovered in time, and the student can be helped to adjust their learning behavior through warning messages, ensuring the smooth progress of the learning process.

[0040] Specifically, the cloud control module includes a cloud server, and the cloud server feeds back data display information to the data acquisition module according to the data display method, and the data display method includes: Step B1: Obtain the corresponding user request instruction according to the actual practice evaluation data, parse the data of the user request instruction to obtain key request instruction information, and perform data mapping between the key request instruction information and the interface of the data acquisition module to obtain data interface information corresponding to the key request instruction information; Step B2: Generate standardized query parameters according to the key request instruction information, and call the data interface information according to the standardized query parameters to obtain the original data; Step B3: Perform data verification on the original data, and perform data display on the original data that meets the verification conditions to obtain data display information.

[0041] Specifically, the user request instruction refers to the instruction for the user to request data from the cloud server. In this embodiment, the specific implementation scheme of data parsing is not limited. For example, it can be set to extract key request instruction information from the user request instruction by using methods such as string parsing, regular expressions, or JSON parsing. The key request instruction information refers to the key information parsed from the user request instruction and used to determine the specific data request. The interface of the data acquisition module refers to the interface provided by the data acquisition module for receiving external requests and returning data. In this embodiment, the specific implementation scheme of data mapping is not limited. For example, it can be set to match the key request instruction information with the interface of the data acquisition module according to predefined mapping rules or configuration files to obtain specific data interface information. The data interface information refers to the specific data interface information obtained after mapping the key request instruction information with the interface of the data acquisition module, including interface address, request method, etc. The standardized query parameters refer to the query parameters generated according to the key request instruction information and meeting the requirements of the data interface. The original data refers to the data obtained by calling the data interface and not processed. The verification condition refers to the condition used to verify whether the original data meets specific requirements or formats. The data display information refers to the original data that has been verified and meets the conditions, and is the information used for display after being processed. In this embodiment, the specific implementation scheme of data verification is not limited. For example, it can be set to verify the original data by using methods such as conditional judgment, data validation library, or custom validation function. In this embodiment, the specific implementation scheme of data display is not limited. For example, it can be set to render the data display information to the user interface by using a front-end framework (such as React, Vue, etc.) or a template engine.

[0042] Specifically, by clarifying the association between user types and permissions through the cloud server, accurate permission allocation based on user characteristics is achieved, ensuring that users can obtain financial training assessment permissions that match their identities and needs, improving the security of the system and the standardization of management, and at the same time enhancing the user experience and the pertinence of training assessment.

[0043] Specifically, the cloud control module further includes a learning behavior warning feedback unit. The learning behavior warning feedback unit compares the learning behavior warning result with a preset learning behavior standard, judges the learning situation of each student according to the comparison result, and feeds back learning behavior warning information to each student according to the judgment result, where: When the learning behavior warning result is consistent with the preset learning behavior standard, the learning behavior warning feedback unit determines that the learning situation of this student is in a normal state and does not feed back learning behavior warning information to this student; When the learning behavior warning result is inconsistent with the preset learning behavior standard, the learning behavior warning feedback unit determines that the learning situation of this student is in an abnormal state. The learning behavior warning feedback unit sends the learning behavior warning information to the learning behavior warning module and controls the learning behavior warning module to display the learning behavior warning information through a display device.

[0044] Specifically, the preset learning behavior standard refers to a standard preset for measuring whether a student's learning behavior is normal. For example, it includes that the number of logins per week is not less than 3 times, the learning duration each time is not less than 1 hour, and the timely submission rate of homework reaches more than 90%. The learning behavior warning information refers to a reminder message sent to a student when the learning behavior monitoring result of the student is inconsistent with the preset learning behavior standard, which is used to inform the student that there is an abnormality in their learning behavior. For example, if a student locks the frequency continuously more than 3 times, the system will generate learning behavior warning information such as "You have locked the frequency continuously more than 3 times. Please adjust in time to avoid affecting the learning effect". The display device refers to a device used to display information or conduct interactions. For example, when the learning behavior monitoring module receives the learning behavior warning information, it is displayed through a display screen to inform the student that there is an abnormality in the learning behavior.

[0045] Specifically, through the learning behavior warning feedback unit, it is possible to warn students' learning behavior in real time, discover abnormal situations in time and feedback warning information to students, which helps students adjust their learning behavior in time and improve the learning effect.

[0046] Specifically, the cloud control module further includes a student assessment feedback unit. The student assessment feedback unit performs data fusion on the learning behavior warning information and the assessment result, obtains a second data fusion result, compares the second data fusion result with a preset assessment benchmark, judges the assessment situation of each student according to the comparison result, and feeds back financial training suggestions to this student according to the judgment result, where: When the second data fusion result is consistent with the preset assessment benchmark, the student assessment feedback unit determines that the assessment situation of this student is an assessment passing situation and does not feed back financial training suggestions to this student; When the second data fusion result is inconsistent with the preset assessment benchmark, the student assessment feedback unit determines that the assessment of this student fails to meet the standard, generates a financial training instruction according to the preset assessment benchmark, feeds back the financial training instruction to the financial training module, and controls the financial training module to feed back financial training suggestions to this student through the financial training instruction.

[0047] Specifically, the second data fusion result refers to the result obtained from the learning behavior warning information and the assessment result. The specific implementation scheme of data fusion for the learning behavior warning information and the assessment result is not limited in this embodiment. For example, it can be set that a machine learning model is used to fuse the learning behavior monitoring result and the student training result. The preset assessment benchmark refers to the standard preset for measuring whether the assessment result meets the standard. The financial training suggestion refers to the targeted suggestion generated according to the specific assessment situation of each student and the preset assessment benchmark when the assessment result of each student is inconsistent with the preset assessment benchmark, aiming to help students improve the financial training effect and ability level. For example, if a student's theoretical exam score is low, the financial training suggestion can be "It is recommended to strengthen the study of financial theory knowledge, and systematic review can be carried out with reference to the specified financial textbooks, and do more relevant exercises"; if there are problems in the practical operation assessment, the suggestion can be "It is recommended to participate in more practical financial project operations to accumulate practical experience, and at the same time, you can watch the operation demonstration videos for learning".

[0048] Specifically, through the assessment result, the assessment situation of students can be accurately judged. Providing personalized financial training suggestions for students who fail to meet the standard helps students clarify their own deficiencies and formulate improvement plans, improve the financial training effect, and promote the improvement of students' financial capabilities.

[0049] The above are only the embodiments of the present invention. Common general knowledge such as the specific structure and characteristics in the solution is not described in detail here. Those of ordinary skill in the art know all the common general knowledge in the technical field to which the invention belongs before the application date or the priority date, can know all the existing technologies in this field, and have the ability to apply the conventional experimental means before this date. Those of ordinary skill in the art can, under the inspiration given in this application, combine their own abilities to improve and implement this solution. Some typical well-known structures or well-known methods should not be an obstacle to those of ordinary skill in the art to implement this application. It should be noted that for those skilled in the art, without departing from the structure of the present invention, several deformations and improvements can also be made, and these should also be regarded as the protection scope of the present invention, and these will not affect the implementation effect of the present invention and the practicality of the patent. The protection scope required by this application should be based on the content of its claims, and the specific implementation manners and the like recorded in the specification can be used to interpret the content of the claims.

Claims

1. A financial training assessment management system based on a cloud platform, characterized in that: The system includes: A data acquisition module, which is used to obtain the practice evaluation data of each student in the financial training course from the cloud server in real time, and preprocess the practice evaluation data to obtain actual practice evaluation data; A financial training module, which is used to perform multi-dimensional analysis on the financial knowledge level of each student according to the actual practice evaluation data, obtain the multi-dimensional analysis results corresponding to each student, and adjust the student financial training plan corresponding to each student in real time according to the multi-dimensional analysis results to obtain the adjusted student financial training plan, and conduct financial training on each student through the adjusted student financial training plan to obtain financial training results; A learning behavior warning module, which is used to establish a learning behavior habit curve for each student according to the financial training results, judge the learning behavior of each student according to the learning behavior habit curve, and give a warning to the learning behavior of each student according to the judgment result to obtain a learning behavior warning result; An assessment module, which is used to assess each student according to the financial training results and multi-dimensional analysis results to obtain assessment results; A cloud control module, which is used to feedback data display information to the data acquisition module according to the user request instruction corresponding to the actual practice evaluation data, feedback learning behavior warning information to each student through the learning behavior warning result, and feedback financial training instructions to the financial training module through the assessment result and learning behavior warning information, and control the financial training module to feedback financial training suggestions to the students through the financial training instructions.

2. The financial training assessment management system based on a cloud platform according to claim 1, wherein: The financial training module includes a student financial level analysis unit. The student financial level analysis unit classifies and marks the actual practice evaluation data according to a preset financial knowledge dimension system to obtain a multi-dimensional standardized data set, and establishes a multi-dimensional evaluation matrix including knowledge breadth, depth mastery degree, and comprehensive application ability based on the multi-dimensional standardized data set, and performs multi-dimensional analysis on the financial knowledge level of each student according to the multi-dimensional evaluation matrix to obtain the multi-dimensional analysis results corresponding to each student.

3. The financial training assessment management system based on a cloud platform according to claim 2, wherein: The financial training module further includes a training plan adjustment unit, and the training plan adjustment unit obtains the financial knowledge scores of each dimension of each trainee according to the multi-dimensional analysis result , and calculates the comprehensive financial knowledge ability evaluation index SQ of each trainee according to the financial knowledge scores of each dimension of each trainee , and sets , represents the weight coefficient used to adjust the financial knowledge scores of each dimension of each trainee , n represents the total number of dimensions of the financial knowledge scores, compares the comprehensive financial knowledge ability evaluation index SQ with the preset comprehensive financial knowledge ability evaluation index SQ0, judges the comprehensive application situation of the financial knowledge of each trainee according to the comparison result, and adjusts the trainee financial training plan corresponding to each trainee in real time according to the judgment result to obtain the adjusted trainee financial training plan corresponding to each trainee, where: When SQ≥SQ0, the training plan adjustment unit determines that the comprehensive application of financial knowledge of this student meets the financial knowledge level standard, and outputs the preset standard student financial training plan corresponding to the preset financial knowledge comprehensive ability evaluation index SQ0 as the adjusted student financial training plan of this student; When SQ<SQ0, the training plan adjustment unit determines that the comprehensive application of financial knowledge of this student does not meet the financial knowledge level standard, trains the convolutional neural network model according to the historical primary financial training plan data set, outputs the convolutional neural network model that meets the preset correct rate as the primary financial training plan recognition model, and identifies the actual practice evaluation data according to the primary financial training plan recognition model to obtain the primary student financial training plan of this student, and outputs the primary student financial training plan as the adjusted student financial training plan of this student.

4. The financial training assessment management system based on a cloud platform according to claim 3, characterized in that: The financial training module further includes a financial training unit. When the training program adjustment unit determines that the financial knowledge level of the trainee meets the standard, the financial training unit conducts financial training on the trainee according to the preset standard trainee financial training program, obtains the first financial training result, and outputs the first financial training result as the financial training result. When the training program adjustment unit determines that the financial knowledge level of the trainee does not meet the standard, the financial training unit conducts financial training on the trainee according to the primary trainee financial training program, obtains the second financial training result, and outputs the second financial training result as the financial training result.

5. The financial training assessment management system based on a cloud platform according to claim 1, wherein: The assessment and evaluation module performs data fusion on the financial training results and multi-dimensional analysis results to obtain a first data fusion result, and extracts the z-th financial training result according to the first data fusion result 、the z-th multi-dimensional analysis result and the dynamic adjustment factor of the z-th learning behavior , and according to the z-th financial training result 、the z-th multi-dimensional analysis result and the dynamic adjustment factor of the z-th learning behavior calculate the student suitability assessment index PX for each student, and set , where b1 represents the weight of the z-th financial training result , b2 represents the weight of the z-th multi-dimensional analysis result , m represents the types of actual practice assessment data indicators represents the weight of the dynamic adjustment factor of the z-th learning behavior , set b1 + b2 = 1, compare the student suitability assessment index PX with the preset student suitability assessment index PX0, judge the suitability of each student according to the comparison result, and conduct assessment and evaluation on each student according to the judgment result to obtain the assessment and evaluation results corresponding to each student, where When PX≥PX0, the assessment module determines the exam suitability of the trainee as suitable, and conducts an assessment of the trainee according to the assessment plan corresponding to the preset trainee exam suitability assessment indicators, obtaining the assessment result corresponding to the trainee; When PX<PX0, the assessment module determines the exam suitability of the trainee as unsuitable and does not conduct an assessment of the trainee.

6. The financial training assessment management system based on a cloud platform according to claim 1, characterized in that: The learning behavior warning module establishes the learning behavior habit curve of each trainee according to the learning behavior curve preparation method, and the learning behavior curve preparation method includes: Step A1, extract the learning progress completion rate C(t) of each trainee at time t, the total progress T of the financial training course, the average answering speed of each trainee at time t and the standard answering speed , and calculate the trainee training effect data P(t) of each trainee according to the learning progress completion rate C(t) of each trainee at time t, the total progress T of the financial training course, the average answering speed of each trainee at time t and the standard answering speed . Set , where represents the learning progress of each trainee, and represents the ratio of the answering speed of each trainee to the standard answering speed; Step A2, establish a learning behavior habit curve for each student, with the training time t of each student as the abscissa and the current observed behavior value B of each student at time t as the ordinate. The mathematical expression of the learning behavior habit curve is as follows: For the ordinate of each student, the mathematical expression of the learning behavior habit curve is: B , where represents the actual practice assessment data index of each trainee at time t, and it is set that m represents the type of actual practice assessment data index, represents the weight of the j-th type of actual practice assessment data index, represents the occurrence frequency of the j-th type of actual practice assessment data index at time t, represents the weight used to adjust the trainee training effect data P(t) of each trainee, represents the weight used to adjust the actual practice assessment data index of each trainee at time t, represents the change rate of the training effect data of each trainee with the training time, represents the weight used to adjust the change rate of the training effect data of each trainee with the training time, and it is set that .

7. The financial training assessment management system based on a cloud platform according to claim 6, wherein: The learning behavior warning module extracts the current observed behavior value B of each student at time t according to the learning behavior habit curve of each student , and calculates the student behavior deviation index BDI of each student according to the current observed behavior value B of each student at time t . Set BDI = |B - JZ| / BZ × W, where W represents the student learning stage weight, JZ represents the historical baseline mean, and set , g represents the number of time units used to calculate the historical baseline mean represents the learning progress completion rate of the student at time , BZ represents the historical baseline standard deviation, and set B , represents the square of the difference between the learning progress of each time unit and the historical baseline mean The learning behavior warning module compares the trainee behavior deviation index BDI with the first preset trainee behavior deviation index BDI1 and the second preset trainee behavior deviation index BDI2, judges the learning behavior of each trainee according to the comparison result, and warns the learning behavior of the trainee according to the judgment result, obtaining the learning behavior warning result. It is set that BDI1<BDI2, where: When BDI<BDI1, the learning behavior warning module determines that the learning behavior of the trainee is normal and does not warn the learning behavior of the trainee; When BDI1≤BDI<BDI2, the learning behavior warning module determines that the learning behavior of the trainee is moderately deviated, pushes a yellow warning message to the trainee, and outputs the yellow warning message as the learning behavior warning result; When BDI≥BDI2, the learning behavior warning module determines that the learning behavior of the trainee is severely deviated, pushes a red warning message to the trainee, and outputs the red warning message as the learning behavior warning result.

8. The financial training assessment management system based on a cloud platform according to claim 1, characterized in that: The cloud control module includes a cloud server, and the cloud server feeds back data display information to the data acquisition module according to the data display method, and the data display method includes: Step B1, obtain the corresponding user request instruction according to the actual practice test data, perform data parsing on the user request instruction to obtain the key request instruction information, and perform data mapping on the key request instruction information and the interface of the data acquisition module to obtain the data interface information corresponding to the key request instruction information; Step B2, generate standardized query parameters according to the key request instruction information, and call the data interface information according to the standardized query parameters to obtain the original data; Step B3: Conduct data verification on the original data, and display the original data that meets the verification conditions to obtain data display information.

9. The financial training assessment management system based on a cloud platform according to claim 8, wherein: The cloud control module further includes a learning behavior warning feedback unit. The learning behavior warning feedback unit compares the learning behavior warning result with a preset learning behavior standard, judges the learning situation of each student according to the comparison result, and feeds back learning behavior warning information to each student according to the judgment result, where: When the learning behavior warning result is consistent with the preset learning behavior standard, the learning behavior warning feedback unit determines that the learning situation of the student is in a normal state and does not feed back learning behavior warning information to the student; When the learning behavior warning result is inconsistent with the preset learning behavior standard, the learning behavior warning feedback unit determines that the learning situation of the student is in an abnormal state. The learning behavior warning feedback unit sends the learning behavior warning information to the learning behavior warning module and controls the learning behavior warning module to display the learning behavior warning information through a display device.

10. The financial training assessment management system based on a cloud platform according to claim 9, characterized in that: The cloud control module further includes a student assessment feedback unit. The student assessment feedback unit performs data fusion on the learning behavior warning information and the assessment result to obtain a second data fusion result, compares the second data fusion result with a preset assessment benchmark, judges the assessment situation of each student according to the comparison result, and feeds back financial training suggestions to the student according to the judgment result, where: When the second data fusion result is consistent with the preset assessment benchmark, the student assessment feedback unit determines that the assessment situation of the student is a qualified assessment situation and does not feed back financial training suggestions to the student; When the second data fusion result is inconsistent with the preset assessment benchmark, the student assessment feedback unit determines that the assessment situation of the student is an unqualified assessment situation, generates a financial training instruction according to the preset assessment benchmark, feeds back the financial training instruction to the financial training module, and controls the financial training module to feed back financial training suggestions to the student through the financial training instruction.

Images