A training control method and training system based on artificial intelligence

Abstract

The present invention proposes a training control method and training system based on artificial intelligence. The training terminal sets a learning plan according to the basic information and learning goals of the trainees, and feeds back the learning plan to the trainee terminal; the learning progress data of each trainee is monitored in real time through the trainee terminal, and the learning progress data of the trainee is stored in the cloud through the cloud platform; when the trainee terminal sends a data sharing request, the training terminal shares the learning progress data according to the data sharing request sent by the trainee terminal; the data cloud storage operation parameters of the cloud platform are monitored in real time, and the data sharing operation strategy of the cloud platform is adjusted according to the data cloud storage operation parameters. The system includes modules corresponding to the steps of the method.

Description

Technical Field

[0001] The invention proposes a training control method and a training system based on artificial intelligence, belonging to the technical field of intelligent control. Background Art

[0002] With the rapid development of science and technology, artificial intelligence (AI) technology is increasingly used in various fields, and the education and training industry is no exception. The traditional education and training model usually adopts a "one-size-fits-all" teaching method, ignoring the differences between individual students, which limits the training effect to a certain extent. The introduction of artificial intelligence technology has brought unprecedented changes to the education and training industry, especially its application in training control methods, making training more efficient, personalized and intelligent. The application of artificial intelligence technology in education and training is mainly reflected in personalized learning support, intelligent tutoring and evaluation, and adaptive learning systems. Personalized learning support can provide customized learning plans and resources based on students' learning habits, abilities and interests, so as to achieve teaching in accordance with their aptitude. The intelligent tutoring and evaluation system can provide 24 / 7 online tutoring and monitor students' learning progress and results in real time through the intelligent evaluation system. The adaptive learning system can automatically adjust the teaching content and difficulty according to the students' learning performance to ensure that students are always at a learning level suitable for them.

[0003] In the current training environment, although there are some AI-based training control methods, these methods are still insufficient in some aspects. For example, they may not fully utilize the basic information and learning goals of the trainees to accurately formulate learning plans, or have limitations in real-time monitoring and storage of learning progress data. In addition, data sharing and cloud platform data storage and sharing strategies may not be flexible enough to meet the learning needs of trainees in different scenarios. Summary of the invention

[0004] The present invention provides a training control method and a training system based on artificial intelligence to solve the above technical problems existing in the prior art. The technical solutions adopted are as follows: A training control method based on artificial intelligence, the training control method based on artificial intelligence comprising: The training terminal sets a learning plan according to the basic information and learning objectives of the trainee, and feeds back the learning plan to the trainee terminal; Monitor each student's learning progress data in real time through the student terminal, and store the student's learning progress data in the cloud through the cloud platform; When the trainee terminal sends a data sharing request, the training terminal shares the learning progress data according to the data sharing request sent by the trainee terminal; Monitor the data cloud storage operating parameters of the cloud platform in real time, and adjust the data sharing operating strategy of the cloud platform based on the data cloud storage operating parameters.

[0005] Furthermore, the training terminal sets a learning plan according to the basic information and learning objectives of the trainee, and feeds back the learning plan to the trainee terminal, including: The student registers through the student terminal, and the student terminal obtains the student's basic information and learning goals; wherein the basic information includes name, age and academic qualifications; The student terminal sends the student's basic information and learning objectives to the training terminal; After receiving the basic information and learning objectives of the trainee, the training terminal analyzes the basic information and learning objectives of the trainee, obtains an analysis result report, and generates a learning plan according to the analysis result; The training terminal feeds back the learning plan to the trainee terminal for visual display.

[0006] Furthermore, after receiving the basic information and learning objectives of the trainee, the training terminal analyzes the basic information and learning objectives of the trainee, obtains an analysis result report, and generates a learning plan according to the analysis result, including: After receiving the basic information and learning objectives of the trainee, the training terminal preprocesses the basic information and learning objectives of the trainee to obtain the preprocessed basic information and learning objectives of the trainee; wherein the preprocessing includes data cleaning processing and data format conversion processing; The training terminal uses a personalized analysis model to perform data analysis on the pre-processed basic information and learning objectives of the trainees to obtain the trainees' learning background information, learning interest information, learning difficulty information and learning expectation information; wherein the personalized analysis model includes but is not limited to a data mining model, a Kano model, utility theory, a QFD model, an aggregation model and a personalized learning analysis model; Generate an analysis result report based on the student's learning background information, learning interest information, learning difficulty information and learning expectation information; Generate a learning path according to the analysis result report, wherein the learning path includes multiple learning stages and the learning content and learning duration corresponding to each learning stage; The analysis result report and learning path are used to generate a learning plan document.

[0007] Furthermore, the learning progress data of each student is monitored in real time through the student terminal, and the learning progress data of the student is stored in the cloud through the cloud platform, including: After each learning is completed, the student terminal obtains the learning progress data corresponding to the current learning completion content according to the current learning completion content; The trainee terminal sends the learning progress data to the training terminal; The training terminal stores the learning progress data in a database, and sends the learning progress data to a cloud platform for data storage.

[0008] Furthermore, when the trainee terminal sends a data sharing request, the training terminal shares the learning progress data according to the data sharing request sent by the trainee terminal, including: When the student terminal needs to share the learning progress data with a third-party terminal, it sends a pairing code to the third-party terminal and receives a pairing confirmation receipt code fed back by the third-party terminal in real time; wherein the third-party terminal includes but is not limited to smart mobile terminals such as tablet computers, laptop computers and smart phones; When the trainee terminal receives the pairing confirmation receipt code fed back by the third-party terminal, the pairing confirmation receipt code and the pairing code are sent together with the data sharing request to the training terminal and the cloud platform; After receiving the pairing confirmation receipt code, the pairing code and the data sharing request, the training terminal detects the loading operation load of the database corresponding to the training terminal and the loading operation load of the cloud platform, and determines the data sharing execution subject according to the loading operation load of the database corresponding to the training terminal and the loading operation load of the cloud platform; The data sharing execution subject retrieves the learning progress data that the student terminal needs to share; After the learning progress data is retrieved, the data sharing execution subject sends a pairing confirmation receipt code sending request to the third-party terminal; When the third-party terminal receives the pairing confirmation receipt code sending request, it sends the pairing confirmation receipt code to the data sharing execution entity; After receiving the pairing confirmation receipt code, the data sharing execution entity compares the pairing confirmation receipt code with the pairing confirmation receipt code sent by the student terminal; when the pairing confirmation receipt code sent by the third-party terminal is consistent with that sent by the student terminal, the data sharing execution entity shares the retrieved learning progress data with the third-party terminal.

[0009] Further, after receiving the pairing confirmation receipt code, the pairing code and the data sharing request, the training terminal detects the retrieval operation load level of the database corresponding to the training terminal and the retrieval operation load level of the cloud platform, and determines the data sharing execution subject according to the retrieval operation load level of the database corresponding to the training terminal and the retrieval operation load level of the cloud platform, including: After receiving the pairing confirmation receipt code, the pairing code and the data sharing request, the training terminal retrieves the retrieval operation load parameters of the database corresponding to the training terminal and the retrieval operation load parameters of the cloud platform; wherein the retrieval operation load parameters of the database corresponding to the training terminal include memory utilization, the number of concurrent executions of data retrieval and cache hit rate; the retrieval operation load parameters of the cloud platform include transaction processing volume, query processing volume, node replication delay rate, intranet inlet bandwidth and intranet outlet bandwidth; The first operation load evaluation parameter corresponding to the database is obtained by using the operation load parameter retrieved from the database corresponding to the training terminal; wherein the first operation load evaluation parameter corresponding to the database is obtained by the following formula: Among them, S 01 represents the first operation load evaluation parameter corresponding to the database; H represents the cache hit rate of the database at the current moment; M represents the memory utilization rate of the database at the current moment; M y represents the optimal memory utilization that meets the database operation requirements; n represents the number of unit times experienced during the database operation process, and the value of the unit time is 1s; C represents the number of concurrent executions of data retrieval from the database at the current moment; C i H represents the number of concurrent executions of data retrieval corresponding to the i-th unit time; f Indicates the maximum floating value of the cache hit rate between two adjacent units of time during database operation; The second operation load evaluation parameter corresponding to the cloud platform is obtained by using the operation load parameter retrieved by the cloud platform; wherein the second operation load evaluation parameter corresponding to the cloud platform is obtained by the following formula: Among them, S 02 represents the second operation load evaluation parameter corresponding to the cloud platform; K represents the transaction processing volume of the cloud platform at the current moment; Q represents the query processing volume of the cloud platform at the current moment; D represents the node replication delay rate of the cloud platform at the current moment; B in and B out They respectively represent the intranet ingress bandwidth and intranet egress bandwidth of the cloud platform at the current moment; When the first operation load evaluation parameter corresponding to the database and the second operation load evaluation parameter corresponding to the cloud platform meet the first constraint condition, the database is determined to be the data sharing execution subject; When the first operation load evaluation parameter corresponding to the database and the second operation load evaluation parameter corresponding to the cloud platform meet the second constraint condition, the cloud platform is determined as the data sharing execution subject.

[0010] Furthermore, the first constraint condition is as follows: Among them, S 01 represents the first operation load evaluation parameter corresponding to the database; S 02 represents the second operation load evaluation parameter corresponding to the cloud platform; α, β and γ represent the first constant coefficient, the second constant coefficient and the third constant coefficient respectively, and the value ranges of the first constant coefficient, the second constant coefficient and the third constant coefficient are: [0.24, 3.52], (0, 100] and (0, 10] respectively; The second constraint is as follows: Among them, S 01 represents the first operation load evaluation parameter corresponding to the database; S 02 represents the second operating load evaluation parameter corresponding to the cloud platform; α, β and γ represent the first constant coefficient, the second constant coefficient and the third constant coefficient respectively, and the value ranges of the first constant coefficient, the second constant coefficient and the third constant coefficient are: [0.24, 3.52], (0, 100] and (0, 10] respectively.

[0011] Furthermore, the data cloud storage operation parameters of the cloud platform are monitored in real time, and the data sharing operation strategy of the cloud platform is adjusted according to the data cloud storage operation parameters, including: Real-time monitoring of the data cloud storage operating parameters of the cloud platform, wherein the data cloud storage operating parameters include data storage delay rate, data storage compression rate and number of concurrent data storage connections; The second constraint condition is adjusted using the data cloud storage operating parameters of the cloud platform.

[0012] Further, the second constraint condition is adjusted using the data cloud storage operation parameters of the cloud platform, including: The constraint adjustment coefficient is obtained by using the data cloud storage operation parameters of the cloud platform; wherein the constraint adjustment coefficient is obtained by the following formula: Where J represents the constraint adjustment coefficient; L represents the data storage delay rate of the cloud platform at the current moment; N represents the number of concurrent data storage connections of the cloud platform at the current moment; N max represents the maximum number of concurrent data storage connections that can satisfy the optimal operation of the cloud platform; Y represents the data storage compression rate of the cloud platform at the current moment; Y min Indicates the minimum data storage compression ratio that satisfies the optimal state of data storage on the cloud platform; The first constant coefficient of the second constraint condition is adjusted by using the constraint condition adjustment coefficient to obtain the adjusted first constant coefficient; wherein the adjusted first constant coefficient is obtained by the following formula: Among them, α t represents the adjusted first constant coefficient; α represents the first constant coefficient; α max and α min Indicates the maximum value and the minimum value of the coefficient appearing in the historical adjustment record of the first constant coefficient; The adjusted second constraint condition is obtained according to the adjusted first constant coefficient, and whether the cloud platform can serve as the data sharing execution subject is determined according to the adjusted second constraint condition.

[0013] A training control system based on artificial intelligence, the training control system based on artificial intelligence comprising: A learning plan generation module is used for the training terminal to set a learning plan according to the basic information and learning objectives of the trainee, and to feed back the learning plan to the trainee terminal; The data cloud storage module is used to monitor the learning progress data of each student in real time through the student terminal, and store the learning progress data of the students in the cloud through the cloud platform; A mathematics sharing module, configured to enable the training terminal to share learning progress data according to the data sharing request sent by the trainee terminal when the trainee terminal sends a data sharing request; The sharing strategy adjustment module is used to monitor the data cloud storage operating parameters of the cloud platform in real time, and adjust the data sharing operating strategy of the cloud platform according to the data cloud storage operating parameters.

[0014] Beneficial effects of the present invention: The training control method and training system based on artificial intelligence proposed by the present invention set a personalized learning plan according to the basic information and learning goals of the trainees through the training terminal, and timely feed back the learning plan to the trainee terminal. The personalized learning ability of artificial intelligence is fully utilized, so that each trainee can obtain a learning path and resources suitable for him. In terms of real-time monitoring and storage of learning progress data, the present invention monitors the learning progress data of each trainee in real time through the trainee terminal, and uses the cloud platform to perform data cloud storage on these data. This real-time monitoring and cloud storage method not only improves the accuracy and reliability of the data, but also provides a basis for subsequent data analysis and sharing. In terms of data sharing, the present invention allows the trainee terminal to send a data sharing request when necessary, and the training terminal shares the learning progress data according to these requests. This function enhances the learning communication and cooperation between trainees, and helps to improve the overall learning effect. In addition, the present invention also monitors the data cloud storage operation parameters of the cloud platform in real time, and adjusts the data sharing operation strategy of the cloud platform according to these parameters. This dynamic adjustment strategy ensures the efficient operation of the cloud platform and the security of data, and provides a more stable and reliable learning environment for students. Therefore, the artificial intelligence-based training control method and control system proposed in the present invention have been optimized and innovated in the formulation of personalized learning plans, real-time monitoring and storage of learning progress data, data sharing, and data storage and sharing strategies of cloud platforms, bringing a more efficient, personalized and intelligent training control method to the education and training industry. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 is a flow chart of the method of the present invention; Figure 2 The system block diagram of the system of the present invention. DETAILED DESCRIPTION

[0016] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0017] The embodiment of the present invention proposes a training control method based on artificial intelligence, such as Figure 1 As shown, the training control method based on artificial intelligence includes: S1. The training terminal sets a learning plan according to the basic information and learning objectives of the trainee, and feeds back the learning plan to the trainee terminal; S2. Monitor the learning progress data of each student in real time through the student terminal, and store the learning progress data of the student in the cloud through the cloud platform; S3, when the trainee terminal sends a data sharing request, the training terminal shares the learning progress data according to the data sharing request sent by the trainee terminal; S4. Monitor the data cloud storage operating parameters of the cloud platform in real time, and adjust the data sharing operating strategy of the cloud platform according to the data cloud storage operating parameters.

[0018] The working principle of the above technical solution is as follows: the training terminal first collects the basic information of the trainees, such as age, education, professional background, etc., as well as the learning goals of the trainees, such as the skills they hope to master and the professional level they expect to achieve. Based on this information, the training terminal uses artificial intelligence technology to analyze and process it and formulates a personalized learning plan for each trainee. This plan includes recommended learning resources, learning paths, learning schedules, etc. The formulated learning plan is fed back to the trainee terminal through the training terminal, and the trainee can view and execute the plan on the trainee terminal.

[0019] During the learning process, the student terminal will monitor the student's learning progress data in real time, such as learning time, learning progress, test scores, etc. These data will be uploaded to the cloud platform in real time for data cloud storage. The cloud platform has powerful data storage and processing capabilities to ensure the security and reliability of data. Through the cloud platform, both the training terminal and the student terminal can access and view the data at any time, providing a basis for subsequent learning analysis and evaluation.

[0020] When students need to share their learning progress data with other students or teachers, they can send a data sharing request through the student terminal. After receiving the data sharing request, the training terminal will filter and process the learning progress data according to the content and scope of the request, and then share it with the requesting party. The data sharing function helps to enhance communication and cooperation among students and promote the sharing and optimization of learning resources.

[0021] The cloud platform will monitor the operating parameters of data cloud storage in real time, such as storage capacity, storage speed, data access frequency, etc. According to the changes in these operating parameters, the cloud platform will automatically adjust the data sharing operation strategy to ensure the efficient operation of data cloud storage and the security of data.

[0022] The effect of the above technical solution is: through the formulation of personalized learning plans and real-time monitoring of learning progress data, it can ensure that students always move in the right direction during the learning process, avoid ineffective learning and repeated learning, and thus improve training efficiency. The data cloud storage function of the cloud platform can realize the centralized management and efficient use of learning resources. Through data analysis and mining, it can be found which learning resources are more popular and which learning resources need to be updated or optimized, so as to provide students with better learning resources. The data sharing function helps to enhance communication and cooperation among students. Students can understand the learning situation and experience of others by sharing their own learning progress data, so as to learn from each other, inspire each other, and improve together. The data cloud storage and data sharing strategies of the cloud platform have undergone rigorous security design and testing, which can ensure that students' learning data will not be leaked or damaged during storage and sharing. At the same time, by real-time monitoring of the operating parameters of the data cloud storage, potential security risks can be discovered and handled in a timely manner.

[0023] In summary, this AI-based training control method has significant technical effects and application value, and can bring a more efficient, personalized and intelligent training experience to the education and training industry.

[0024] In one embodiment of the present invention, a training terminal sets a learning plan according to basic information and learning objectives of a trainee, and feeds back the learning plan to the trainee terminal, including: S101, a student registers through a student terminal, and the student terminal obtains basic information and learning goals of the student; wherein the basic information includes name, school age and academic qualifications; S102, the student terminal sends the basic information and learning objectives of the student to the training terminal; S103, after receiving the basic information and learning objectives of the trainee, the training terminal analyzes the basic information and learning objectives of the trainee, obtains an analysis result report, and generates a learning plan according to the analysis result; S104: The training terminal feeds back the learning plan to the trainee terminal for visual display.

[0025] The working principle of the above technical solution is as follows: students first register through the student terminal (such as mobile phone APP, computer web page, etc.) and fill in the necessary personal information, including basic information such as name, school age, and education. During or after the registration process, students must also clarify their learning goals, such as the skills they want to master, the learning level they expect to achieve, or the direction of career development. The student terminal is responsible for collecting this information and ensuring its accuracy and completeness. The student terminal sends the collected basic information and learning goals of the students to the training terminal through the network. The training terminal is a specially designed system for processing and analyzing student information to generate a personalized learning plan. After receiving the student information, the training terminal first cleans and preprocesses the information to ensure the accuracy and consistency of the data.

[0026] Next, the training terminal uses artificial intelligence technology (such as machine learning, natural language processing, etc.) to conduct an in-depth analysis of the trainee's basic information and learning goals. Based on the analysis results, the training terminal generates a personalized learning plan, which includes recommended learning resources, learning paths, learning schedules, etc. The training terminal sends the generated learning plan back to the trainee terminal via the network. After receiving the learning plan, the trainee terminal displays it visually, so that the trainee can clearly understand his or her own learning plan, including the content to be learned every day, the learning time, and the learning goals.

[0027] The effect of the above technical solution is: by collecting and analyzing the basic information and learning goals of the trainees, the training terminal can generate a personalized learning plan to meet the personalized learning needs of the trainees. This personalized learning method helps to improve the students' interest and enthusiasm in learning, thereby improving the learning effect. The learning paths and resources in the learning plan are carefully selected and optimized, which can help students master knowledge and skills more efficiently. At the same time, the learning plan also takes into account the students' learning ability and time arrangement, avoids ineffective learning and repeated learning, and further improves learning efficiency. Students can view and modify their learning plans anytime and anywhere through the student terminal without tedious communication with training teachers or managers. This convenience enables students to arrange their learning time and progress more flexibly, improving the autonomy and flexibility of learning. The training terminal uses artificial intelligence technology to analyze and process learning data, and can understand the students' learning situation and progress in real time. These data can be used for subsequent learning evaluation and optimization to provide students with more accurate learning suggestions and resource recommendations.

[0028] In summary, this technical solution collects and analyzes students' basic information and learning goals, generates personalized learning plans, and feeds them back to students' terminals for visual display, thus achieving a personalized, efficient, convenient and data-driven learning experience.

[0029] In one embodiment of the present invention, after receiving the basic information and learning objectives of the trainee, the training terminal analyzes the basic information and learning objectives of the trainee, obtains an analysis result report, and generates a learning plan according to the analysis result, including: S1031. After receiving the basic information and learning objectives of the trainee, the training terminal preprocesses the basic information and learning objectives of the trainee to obtain the preprocessed basic information and learning objectives of the trainee; wherein the preprocessing includes data cleaning processing and data format conversion processing; S1032, the training terminal uses a personalized analysis model to perform data analysis on the pre-processed basic information and learning objectives of the trainees, and obtains the trainees' learning background information, learning interest information, learning difficulty information, and learning expectation information; wherein the personalized analysis model includes but is not limited to a data mining model, a Kano model, utility theory, a QFD model, an aggregation model, and a personalized learning analysis model; S1033, generating an analysis result report based on the student's learning background information, learning interest information, learning difficulty information, and learning expectation information; S1034. Generate a learning path according to the analysis result report, wherein the learning path includes multiple learning stages and the learning content and learning duration corresponding to each learning stage; S1035: Generate a learning plan document using the analysis result report and the learning path.

[0030] The working principle of the above technical solution is as follows: the training terminal first receives the basic information and learning objectives of the trainees. Then, the received data is preprocessed, including data cleaning and data format conversion. Data cleaning aims to remove invalid, erroneous or redundant data to ensure the accuracy and completeness of the data. Data format conversion converts the data into a format recognizable by the system for subsequent analysis. The preprocessed data is input into the personalized analysis model for analysis. The personalized analysis model uses methods such as data mining, Kano model, utility theory, QFD model, aggregation model and personalized learning analysis model to conduct in-depth mining and analysis of the trainees' learning background information, learning interest information, learning difficulty information and learning expectation information. This information helps the system to have a more comprehensive understanding of the trainees' learning needs and characteristics.

[0031] Based on the results of personalized analysis, the system generates a detailed analysis report. The report covers the learner's learning background, interests, difficulties, and expectations, providing strong support for the subsequent learning plan formulation. Based on the analysis report, the system formulates a personalized learning path for the learner. The learning path includes multiple learning stages, each with corresponding learning content and learning duration. Finally, the system integrates the analysis report and the learning path into a complete learning plan document for the learner's reference and execution.

[0032] The effect of the above technical solution is: through the personalized analysis model, the system can accurately grasp the learning needs and characteristics of students and provide students with tailored learning plans. This personalized learning experience helps to stimulate students' learning interest and improve learning results. The system recommends suitable learning content and resources based on the students' learning background and interests. At the same time, through reasonable learning path planning, it ensures that students can master the required knowledge and skills within a limited time. These measures help improve students' learning efficiency and shorten the learning cycle. The system can intelligently allocate training resources according to students' learning needs and difficulties. This helps to ensure the effective use of training resources and avoid waste of resources and repeated investment. By generating detailed learning plan documents, the system can provide students with clear learning goals and paths. This helps to guide students to maintain the motivation for continuous learning and continuously improve their knowledge and skills.

[0033] In summary, this technical solution provides students with personalized learning plans and learning paths through personalized analysis models and data preprocessing technology. This can not only improve students' learning efficiency and satisfaction, but also optimize the allocation and utilization of training resources and promote students' continuous learning and development.

[0034] In one embodiment of the present invention, the learning progress data of each student is monitored in real time through the student terminal, and the learning progress data of the student is stored in the cloud through the cloud platform, including: S201, after each learning is completed, the student terminal obtains the learning progress data corresponding to the current learning completion content according to the current learning completion content; S202, the student terminal sends the learning progress data to the training terminal; S203: The training terminal stores the learning progress data in a database, and sends the learning progress data to a cloud platform for data storage.

[0035] The working principle of the above technical solution is: after each learning is completed, the student terminal will automatically or manually (according to the system design) obtain the corresponding learning progress data according to the current learning content. These data may include multiple dimensions such as learning time, completed chapters, scores, and mastery. After the student terminal obtains the learning progress data, it will send these data to the training terminal. This step is usually achieved through a network connection to ensure the real-time and accuracy of the data. After the training terminal receives the learning progress data sent by the student terminal, it will first store these data in the local database to ensure data backup and security. At the same time, the training terminal will also send these learning progress data to the cloud platform for data storage. The cloud platform has powerful data storage and processing capabilities, and can support the storage and efficient access of large-scale data.

[0036] The effect of the above technical solution is: by monitoring the learning progress data of each student in real time through the student terminal, the learning situation of the student can be reflected in real time, and timely feedback can be provided to teachers and training institutions. This helps teachers to adjust teaching strategies in time and provide more personalized guidance and help to students. Storing learning progress data in the cloud platform can realize centralized management and efficient access to data. The cloud platform usually adopts advanced data encryption and backup technology to ensure the security and reliability of data. The learning progress data stored in the cloud platform can be deeply analyzed through big data analysis and mining technology. This helps to discover the learning rules and characteristics of students and provide strong support for teaching improvement and course optimization. The cloud platform supports multi-terminal access, and teachers and students can view learning progress data anytime and anywhere through mobile phones, computers and other devices. This improves the accessibility and convenience of data, and helps to promote students' independent learning and teachers' remote guidance. Through the learning progress data stored on the cloud platform, teachers can interact and collaborate with students in real time.

[0037] In summary, this technical solution achieves real-time feedback, secure storage and efficient access to data by monitoring students’ learning progress data in real time and storing it on the cloud platform. This not only helps teachers adjust teaching strategies in a timely manner and improve teaching effectiveness, but also provides students with a more convenient and personalized learning experience.

[0038] In one embodiment of the present invention, when the trainee terminal sends a data sharing request, the training terminal shares the learning progress data according to the data sharing request sent by the trainee terminal, including: S301, when the student terminal needs to share the learning progress data with a third-party terminal, a pairing code is sent to the third-party terminal, and a pairing confirmation receipt code fed back by the third-party terminal is received in real time; wherein the third-party terminal includes but is not limited to a tablet computer, a laptop computer, a smart phone and other smart mobile terminals; S302: When the trainee terminal receives the pairing confirmation receipt code fed back by the third-party terminal, the pairing confirmation receipt code and the pairing code are sent together with a data sharing request to the training terminal and the cloud platform; S303, after receiving the pairing confirmation receipt code, the pairing code and the data sharing request, the training terminal detects the retrieval operation load level of the database corresponding to the training terminal and the retrieval operation load level of the cloud platform, and determines the data sharing execution subject according to the retrieval operation load level of the database corresponding to the training terminal and the retrieval operation load level of the cloud platform; S304, the data sharing execution subject retrieves the learning progress data that the student terminal needs to share; S305: After the learning progress data is retrieved, the data sharing execution entity sends a pairing confirmation receipt code sending request to the third-party terminal; S306: When receiving the pairing confirmation receipt code sending request, the third-party terminal sends the pairing confirmation receipt code to the data sharing execution entity; S307. After receiving the pairing confirmation receipt code, the data sharing execution entity compares the pairing confirmation receipt code with the pairing confirmation receipt code sent by the student terminal; when the pairing confirmation receipt code sent by the third-party terminal is consistent with that sent by the student terminal, the data sharing execution entity shares the retrieved learning progress data with the third-party terminal.

[0039] The working principle of the above technical solution is as follows: when the student terminal needs to share the learning progress data with the third-party terminal, a pairing code is first sent to the third-party terminal. After receiving the pairing code, the third-party terminal confirms and feeds back a pairing confirmation receipt code to the student terminal. After receiving the pairing confirmation receipt code from the third-party terminal, the student terminal sends this receipt code together with the original pairing code and the data sharing request to the training terminal and the cloud platform. After receiving this information, the training terminal will detect the load level of the retrieval operation of its own database and the cloud platform. According to the load level, the training terminal will determine which is more suitable as the execution subject of data sharing. The determined data sharing execution subject will retrieve the learning progress data that the student terminal needs to share data. After the data retrieval is completed, the data sharing execution subject will send a pairing confirmation receipt code to the third-party terminal. After receiving this request, the third-party terminal will send the pairing confirmation receipt code to the data sharing execution subject again. After receiving this receipt code, the data sharing execution subject will compare the consistency with the pairing confirmation receipt code initially sent by the student terminal. If the two are consistent, the data sharing executor will share the retrieved learning progress data to the third-party terminal.

[0040] The effect of the above technical solution is: through the two-way confirmation mechanism of pairing code and pairing confirmation receipt code, the security and privacy protection in the data sharing process are ensured. Only third-party terminals confirmed by both parties can obtain learning progress data, which effectively prevents data leakage and illegal access. The technical solution supports multiple types of third-party terminals, such as tablets, laptops, and smart mobile terminals such as smartphones. This allows students to choose appropriate terminals for data sharing according to their needs, improving the flexibility and scalability of the system.

[0041] By detecting the load level of the training terminal database and the cloud platform, the data sharing execution subject is determined. This ensures the efficiency of the data sharing process and avoids system bottlenecks caused by overload of a single execution subject. The entire data sharing process is designed to be relatively concise and clear, and users only need to perform simple operations to complete data sharing. This improves the user experience and enables students and third-party terminals to more conveniently obtain and share learning progress data. This technical solution facilitates teaching interaction and collaboration between students, teachers and third parties (such as parents, tutoring institutions, etc.). Through data sharing, teachers can better understand the students' learning situation, parents can pay more attention to their children's learning progress, and tutoring institutions can provide more accurate tutoring services.

[0042] In summary, this technical solution achieves data security, efficiency, flexibility and scalability through the confirmation mechanism of pairing code and receipt code, flexible and diverse third-party terminal support, efficient load-balanced data sharing execution subject determination and concise and clear data sharing process design. This not only improves the user experience, but also provides strong support for teaching interaction and collaboration.

[0043] In one embodiment of the present invention, after receiving the pairing confirmation receipt code, the pairing code and the data sharing request, the training terminal detects the call operation load level of the database corresponding to the training terminal and the call operation load level of the cloud platform, and determines the data sharing execution subject according to the call operation load level of the database corresponding to the training terminal and the call operation load level of the cloud platform, including: S3031, after receiving the pairing confirmation receipt code, pairing code and data sharing request, the training terminal retrieves the retrieval operation load parameters of the database corresponding to the training terminal and the retrieval operation load parameters of the cloud platform; wherein the retrieval operation load parameters of the database corresponding to the training terminal include memory utilization, number of concurrent executions of data retrieval and cache hit rate; the retrieval operation load parameters of the cloud platform include transaction processing volume, query processing volume, node replication delay rate, intranet inlet bandwidth and intranet outlet bandwidth; S3032. Obtain a first operation load evaluation parameter corresponding to the database by using the operation load parameter retrieved from the database corresponding to the training terminal; wherein the first operation load evaluation parameter corresponding to the database is obtained by the following formula: Among them, S 01 represents the first operation load evaluation parameter corresponding to the database; H represents the cache hit rate of the database at the current moment; M represents the memory utilization rate of the database at the current moment; M y represents the optimal memory utilization that meets the database operation requirements; n represents the number of unit times experienced during the database operation process, and the value of the unit time is 1s; C represents the number of concurrent executions of data retrieval from the database at the current moment; C i H represents the number of concurrent executions of data retrieval corresponding to the i-th unit time; f Indicates the maximum floating value of the cache hit rate between two adjacent units of time during database operation; S3033. Obtain a second operation load evaluation parameter corresponding to the cloud platform using the operation load parameter retrieved by the cloud platform; wherein the second operation load evaluation parameter corresponding to the cloud platform is obtained by the following formula: Among them, S 02 represents the second operation load evaluation parameter corresponding to the cloud platform; K represents the transaction processing volume of the cloud platform at the current moment; Q represents the query processing volume of the cloud platform at the current moment; D represents the node replication delay rate of the cloud platform at the current moment; B in and B out They respectively represent the intranet ingress bandwidth and intranet egress bandwidth of the cloud platform at the current moment; S3034: When the first operation load evaluation parameter corresponding to the database and the second operation load evaluation parameter corresponding to the cloud platform meet the first constraint condition, the database is determined to be the data sharing execution subject; S3035. When the first operation load evaluation parameter corresponding to the database and the second operation load evaluation parameter corresponding to the cloud platform meet the second constraint condition, the cloud platform is determined to be the data sharing execution subject.

[0044] The first constraint condition is as follows: Among them, S 01 represents the first operation load evaluation parameter corresponding to the database; S 02represents the second operation load evaluation parameter corresponding to the cloud platform; α, β and γ represent the first constant coefficient, the second constant coefficient and the third constant coefficient respectively, and the value ranges of the first constant coefficient, the second constant coefficient and the third constant coefficient are: [0.24, 3.52], (0, 100] and (0, 10] respectively; The second constraint is as follows: Among them, S 01 represents the first operation load evaluation parameter corresponding to the database; S 02 represents the second operating load evaluation parameter corresponding to the cloud platform; α, β and γ represent the first constant coefficient, the second constant coefficient and the third constant coefficient respectively, and the value ranges of the first constant coefficient, the second constant coefficient and the third constant coefficient are: [0.24, 3.52], (0, 100] and (0, 10] respectively.

[0045] The working principle of the above technical solution is as follows: the training terminal first obtains the call operation load parameters of its own database and cloud platform. These parameters include the memory utilization rate of the database, the number of concurrent executions of data retrieval and the cache hit rate, as well as the transaction processing volume, query processing volume, node replication delay rate, intranet inlet bandwidth and intranet outlet bandwidth of the cloud platform. Then, the training terminal uses the acquired load parameters to calculate the operation load evaluation parameters of the database and the cloud platform. These parameters are calculated by the above formula and are intended to comprehensively reflect the current operation status of the database and the cloud platform. For the database, the operation load evaluation parameters take into account factors such as cache hit rate, memory utilization, number of concurrent executions of data retrieval and its changes. For the cloud platform, the operation load evaluation parameters take into account factors such as transaction processing volume, query processing volume, node replication delay rate and intranet bandwidth. Finally, the training terminal determines the execution subject of data sharing based on the calculated operation load evaluation parameters, combined with the preset first constraint and second constraint. If the operation load evaluation parameters of the database meet the first constraint relative to the evaluation parameters of the cloud platform, the database is determined as the execution subject of data sharing. If the cloud platform's operating load evaluation parameter satisfies the second constraint condition relative to the database's evaluation parameter, the cloud platform is determined to be the data sharing execution subject.

[0046] The effect of the above technical solution is: by real-time monitoring of the operating load of the database and the cloud platform, and dynamically determining the execution subject of data sharing according to the load situation, the dynamic load balancing of the system is realized. This helps to avoid overloading of a single execution subject and improve the overall performance and stability of the system. Determining the execution subject according to the operating load evaluation parameters can ensure the efficient use of resources. When the load of the database or cloud platform is low, they are more likely to be selected as the execution subject, thereby making full use of existing resources and avoiding resource waste. The technical solution can flexibly adapt to different load conditions and dynamically adjust according to actual conditions. At the same time, it also supports possible future expansions, such as adding new execution subjects or adjusting load evaluation parameters. By optimizing the execution subject selection process of data sharing, the waiting time and transmission delay in the data sharing process are reduced, thereby improving the efficiency of data sharing. Dynamic load balancing and efficient resource utilization help to enhance the stability of the system. Even under high load conditions, the system can maintain normal operation by intelligently selecting the execution subject to avoid system crashes or performance degradation caused by overload.

[0047] At the same time, the technical solution can dynamically evaluate the operating status of the database and cloud platform corresponding to the training terminal by retrieving the operating load parameters of the two in real time. This includes database parameters such as memory utilization, number of concurrent executions of data retrieval, cache hit rate, and cloud platform parameters such as transaction processing volume, query processing volume, node replication delay rate, intranet inlet bandwidth, and intranet outlet bandwidth. This dynamic evaluation helps to timely discover and respond to potential performance bottlenecks. By calculating the first and second operating load evaluation parameters of the database and cloud platform through the above formulas, the technical solution can accurately quantify the operating load of the two. These formulas comprehensively consider multiple key performance indicators, such as cache hit rate, memory utilization, number of concurrent executions of data retrieval, etc., as well as transaction processing volume, query processing volume, node replication delay rate and network bandwidth of the cloud platform, thereby providing a comprehensive performance evaluation. According to the operating load evaluation parameters of the database and cloud platform, as well as the preset first and second constraints, the technical solution can intelligently select the data sharing execution subject. When the operating load of the database is relatively low and the operating load of the cloud platform is relatively high, the database will serve as the data sharing execution subject; otherwise, the cloud platform will assume this role. This intelligent selection helps optimize resource utilization and improve the efficiency of data sharing. By dynamically evaluating the operating load, accurately quantifying the operating load, and intelligently selecting the data sharing execution subject, this technical solution can significantly improve the stability and reliability of the system. It helps to avoid system crashes or performance degradation caused by overload of a single component, thereby ensuring the smooth progress of the data sharing process. This technical solution also has certain scalability and flexibility. As the performance of the training terminal and the cloud platform improves or expands, the calculation formula and constraints of the operating load evaluation parameters can be adjusted accordingly to adapt to new performance requirements. This helps ensure that the system can continue to provide efficient and stable data sharing services in the future.

[0048] In summary, the technical effects of this technical solution in terms of performance indicators are mainly reflected in the dynamic evaluation of operating load, accurate quantification of operating load, intelligent selection of data sharing execution subjects, improvement of system stability and reliability, and enhancement of system scalability and flexibility. These effects together provide strong support for the data sharing process and ensure the efficient and stable operation of the system. At the same time, this technical solution achieves dynamic load balancing, efficient resource utilization and data sharing efficiency improvement of the system by real-time monitoring of load, dynamic determination of execution subjects and optimization of resource utilization. This not only improves the overall performance and stability of the system, but also provides possibilities for future expansion and optimization.

[0049] In one embodiment of the present invention, the data cloud storage operation parameters of the cloud platform are monitored in real time, and the data sharing operation strategy of the cloud platform is adjusted according to the data cloud storage operation parameters, including: S401, real-time monitoring of data cloud storage operating parameters of the cloud platform, wherein the data cloud storage operating parameters include data storage delay rate, data storage compression rate and number of concurrent data storage connections; S402: Adjust the second constraint condition using the data cloud storage operation parameters of the cloud platform.

[0050] The second constraint condition is adjusted using the data cloud storage operation parameters of the cloud platform, including: S4021. Obtain constraint adjustment coefficients using the data cloud storage operation parameters of the cloud platform; wherein the constraint adjustment coefficients are obtained by the following formula: Where J represents the constraint adjustment coefficient; L represents the data storage delay rate of the cloud platform at the current moment; N represents the number of concurrent data storage connections of the cloud platform at the current moment; N max represents the maximum number of concurrent data storage connections that can satisfy the optimal operation of the cloud platform; Y represents the data storage compression rate of the cloud platform at the current moment; Y min Indicates the minimum data storage compression ratio that satisfies the optimal state of data storage on the cloud platform; S4022. Use the constraint adjustment coefficient to adjust the first constant coefficient of the second constraint to obtain an adjusted first constant coefficient; wherein the adjusted first constant coefficient is obtained by the following formula: Among them, α t represents the adjusted first constant coefficient; α represents the first constant coefficient; α max and α min Indicates the maximum value and the minimum value of the coefficient appearing in the historical adjustment record of the first constant coefficient; S4023. Obtain an adjusted second constraint condition according to the adjusted first constant coefficient, and determine whether the cloud platform can serve as a data sharing execution subject according to the adjusted second constraint condition.

[0051] The working principle of the above technical solution is: the system monitors the data cloud storage operation parameters of the cloud platform in real time, including data storage delay rate, data storage compression rate and number of concurrent data storage connections. These parameters can reflect the current operation status and performance of the data cloud storage of the cloud platform.

[0052] Specifically, the constraint adjustment coefficient is calculated by a specific formula using the data cloud storage operation parameters monitored in real time. This coefficient is used to reflect the degree of influence of the current data cloud storage operation status of the cloud platform on the second constraint. The formula takes into account the data storage delay rate, the ratio of the number of concurrent data storage connections to the maximum number of concurrent connections, and the ratio of the data storage compression rate to the minimum compression rate. These factors jointly determine the size of the constraint adjustment coefficient. According to the calculated constraint adjustment coefficient, the first constant coefficient in the second constraint is adjusted. The adjusted first constant coefficient can more accurately reflect the current data cloud storage operation status of the cloud platform. During the adjustment process, the historical adjustment records of the first constant coefficient are taken into account to ensure that the adjusted coefficient fluctuates within a reasonable range and avoids excessive or too small adjustments that adversely affect system stability. The adjusted second constraint is used to determine whether the cloud platform can serve as the data sharing execution subject. This step ensures that the data sharing strategy can be dynamically adjusted according to the current data cloud storage operation status of the cloud platform, thereby optimizing data sharing efficiency and system performance.

[0053] The effect of the above technical solution is: by real-time monitoring of data cloud storage operating parameters and dynamically adjusting data sharing operating strategies, the system can better adapt to the current data storage status of the cloud platform and ensure the efficiency and stability of data sharing. Dynamic adjustment of the data sharing execution subject can make full use of the resources of the cloud platform and avoid resource waste. When the data cloud storage status of the cloud platform is good, it is more likely to be selected as the data sharing execution subject, thereby improving resource utilization. By adjusting the first constant coefficient in the second constraint, the system can maintain the stability of the system while ensuring data sharing efficiency. This helps to avoid system crashes or performance degradation caused by improper data sharing strategies. The technical solution uses real-time monitoring of data cloud storage operating parameters for intelligent decision-making, avoiding the tediousness and uncertainty of manual intervention. This improves the automation and intelligence level of the system. The design idea of ​​the technical solution is scalable, and more monitoring parameters and adjustment strategies can be added in the future according to actual needs to adapt to more complex data sharing scenarios and cloud platform operating status.

[0054] By real-time monitoring of the cloud platform's data cloud storage operating parameters (such as data storage delay rate, data storage compression rate, and number of concurrent data storage connections), the technical solution can respond to changes in the data storage status of the cloud platform in real time. This real-time performance ensures that the system can dynamically adjust the data sharing operation strategy according to the current operation status, thereby improving the flexibility and response speed of the system. By adjusting the second constraint condition using the cloud platform's data cloud storage operation parameters, it is possible to more accurately determine whether the cloud platform is suitable as a data sharing execution subject. By introducing the constraint adjustment coefficient, the technical solution can comprehensively consider multiple data storage performance indicators to formulate a more reasonable and efficient data sharing strategy. By dynamically adjusting the first constant coefficient of the second constraint condition, the technical solution can timely relax or tighten the judgment criteria for the data sharing execution subject according to the actual operation status of the cloud platform. This helps to avoid data sharing interruptions or performance degradation caused by fluctuations in the performance of the cloud platform, thereby improving the stability and reliability of the system. By real-time monitoring and adjusting the data cloud storage operation parameters, the technical solution can more reasonably allocate and utilize system resources. When the data storage performance of the cloud platform is good, it can take on more data sharing tasks; when the performance decreases, it can appropriately reduce its task volume to avoid resource overload and performance bottlenecks. This dynamic resource allocation method helps to improve the overall resource utilization of the system. By optimizing data sharing strategies and improving system stability, this technical solution can provide users with smoother and more efficient data sharing services. This helps to improve user satisfaction and loyalty, thereby bringing better market reputation and competitive advantages to enterprises.

[0055] In summary, the technical effects of this technical solution in terms of performance indicators are mainly reflected in real-time response and dynamic adjustment, optimization of data sharing strategy, improvement of system stability and reliability, enhancement of system resource utilization, and improvement of user experience. These effects together provide strong support for the data sharing service of the cloud platform and ensure the efficient and stable operation of the system.

[0056] At the same time, the technical solution achieves dynamic adaptability, resource optimization, system stability, intelligent decision-making and scalability of the system by real-time monitoring of data cloud storage operating parameters and dynamically adjusting data sharing operation strategies. These technical effects jointly improve the overall performance of the system and user experience.

[0057] The embodiment of the present invention proposes a training control system based on artificial intelligence, such as Figure 2 As shown, the training control system based on artificial intelligence includes: A learning plan generation module is used for the training terminal to set a learning plan according to the basic information and learning objectives of the trainee, and to feed back the learning plan to the trainee terminal; The data cloud storage module is used to monitor the learning progress data of each student in real time through the student terminal, and store the learning progress data of the students in the cloud through the cloud platform; A mathematics sharing module, configured to enable the training terminal to share learning progress data according to the data sharing request sent by the trainee terminal when the trainee terminal sends a data sharing request; The sharing strategy adjustment module is used to monitor the data cloud storage operating parameters of the cloud platform in real time, and adjust the data sharing operating strategy of the cloud platform according to the data cloud storage operating parameters.

[0058] The working principle of the above technical solution is as follows: the training terminal first collects the basic information of the trainees, such as age, education, professional background, etc., as well as the learning goals of the trainees, such as the skills they hope to master and the professional level they expect to achieve. Based on this information, the training terminal uses artificial intelligence technology to analyze and process it and formulates a personalized learning plan for each trainee. This plan includes recommended learning resources, learning paths, learning schedules, etc. The formulated learning plan is fed back to the trainee terminal through the training terminal, and the trainee can view and execute the plan on the trainee terminal.

[0059] During the learning process, the student terminal will monitor the student's learning progress data in real time, such as learning time, learning progress, test scores, etc. These data will be uploaded to the cloud platform in real time for data cloud storage. The cloud platform has powerful data storage and processing capabilities to ensure the security and reliability of data. Through the cloud platform, both the training terminal and the student terminal can access and view the data at any time, providing a basis for subsequent learning analysis and evaluation.

[0060] When students need to share their learning progress data with other students or teachers, they can send a data sharing request through the student terminal. After receiving the data sharing request, the training terminal will filter and process the learning progress data according to the content and scope of the request, and then share it with the requesting party. The data sharing function helps to enhance communication and cooperation among students and promote the sharing and optimization of learning resources.

[0061] The cloud platform will monitor the operating parameters of data cloud storage in real time, such as storage capacity, storage speed, data access frequency, etc. According to the changes in these operating parameters, the cloud platform will automatically adjust the data sharing operation strategy to ensure the efficient operation of data cloud storage and the security of data.

[0062] The effect of the above technical solution is: through the formulation of personalized learning plans and real-time monitoring of learning progress data, it can ensure that students always move in the right direction during the learning process, avoid ineffective learning and repeated learning, and thus improve training efficiency. The data cloud storage function of the cloud platform can realize the centralized management and efficient use of learning resources. Through data analysis and mining, it can be found which learning resources are more popular and which learning resources need to be updated or optimized, so as to provide students with better learning resources. The data sharing function helps to enhance communication and cooperation among students. Students can understand the learning situation and experience of others by sharing their own learning progress data, so as to learn from each other, inspire each other, and improve together. The data cloud storage and data sharing strategies of the cloud platform have undergone rigorous security design and testing, which can ensure that students' learning data will not be leaked or damaged during storage and sharing. At the same time, by real-time monitoring of the operating parameters of the data cloud storage, potential security risks can be discovered and handled in a timely manner.

[0063] In summary, this AI-based training control method has significant technical effects and application value, and can bring a more efficient, personalized and intelligent training experience to the education and training industry.

[0064] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A training control method based on artificial intelligence, characterized in that: The training control method based on artificial intelligence includes: The training terminal sets a learning plan according to the basic information and learning objectives of the trainee, and feeds back the learning plan to the trainee terminal; Monitor each student's learning progress data in real time through the student terminal, and store the student's learning progress data in the cloud through the cloud platform; When the trainee terminal sends a data sharing request, the training terminal shares the learning progress data according to the data sharing request sent by the trainee terminal; Monitor the data cloud storage operating parameters of the cloud platform in real time, and adjust the data sharing operating strategy of the cloud platform based on the data cloud storage operating parameters.

2. The training control method based on artificial intelligence according to claim 1 is characterized in that: The training terminal sets a learning plan based on the basic information and learning objectives of the trainee, and feeds back the learning plan to the trainee terminal, including: The student registers through the student terminal, and the student terminal obtains the student's basic information and learning goals; wherein the basic information includes name, age and academic qualifications; The student terminal sends the student's basic information and learning objectives to the training terminal; After receiving the basic information and learning objectives of the trainee, the training terminal analyzes the basic information and learning objectives of the trainee, obtains an analysis result report, and generates a learning plan according to the analysis result; The training terminal feeds back the learning plan to the trainee terminal for visual display.

3. The training control method based on artificial intelligence according to claim 2 is characterized in that: After receiving the basic information and learning objectives of the trainee, the training terminal analyzes the basic information and learning objectives of the trainee, obtains an analysis result report, and generates a learning plan according to the analysis result, including: After receiving the basic information and learning objectives of the trainee, the training terminal preprocesses the basic information and learning objectives of the trainee to obtain the preprocessed basic information and learning objectives of the trainee; wherein the preprocessing includes data cleaning processing and data format conversion processing; The training terminal uses a personalized analysis model to perform data analysis on the pre-processed basic information and learning goals of the trainees to obtain the trainees' learning background information, learning interest information, learning difficulty information, and learning expectation information; Generate an analysis result report based on the student's learning background information, learning interest information, learning difficulty information and learning expectation information; Generate a learning path according to the analysis result report, wherein the learning path includes multiple learning stages and the learning content and learning duration corresponding to each learning stage; The analysis result report and learning path are used to generate a learning plan document.

4. The training control method based on artificial intelligence according to claim 1 is characterized in that: The learning progress data of each student is monitored in real time through the student terminal, and the learning progress data of the student is stored in the cloud through the cloud platform, including: After each learning is completed, the student terminal obtains the learning progress data corresponding to the current learning completion content according to the current learning completion content; The trainee terminal sends the learning progress data to the training terminal; The training terminal stores the learning progress data in a database, and sends the learning progress data to a cloud platform for data storage.

5. The training control method based on artificial intelligence according to claim 1 is characterized in that: When the trainee terminal sends a data sharing request, the training terminal shares the learning progress data according to the data sharing request sent by the trainee terminal, including: When the student terminal needs to share the learning progress data with a third-party terminal, it sends a pairing code to the third-party terminal and receives a pairing confirmation receipt code fed back by the third-party terminal in real time; When the trainee terminal receives the pairing confirmation receipt code fed back by the third-party terminal, the pairing confirmation receipt code and the pairing code are sent together with the data sharing request to the training terminal and the cloud platform; After receiving the pairing confirmation receipt code, the pairing code and the data sharing request, the training terminal detects the loading operation load of the database corresponding to the training terminal and the loading operation load of the cloud platform, and determines the data sharing execution subject according to the loading operation load of the database corresponding to the training terminal and the loading operation load of the cloud platform; The data sharing execution subject retrieves the learning progress data that the student terminal needs to share; After the learning progress data is retrieved, the data sharing execution subject sends a pairing confirmation receipt code sending request to the third-party terminal; When the third-party terminal receives the pairing confirmation receipt code sending request, it sends the pairing confirmation receipt code to the data sharing execution entity; After receiving the pairing confirmation receipt code, the data sharing execution entity compares the pairing confirmation receipt code with the pairing confirmation receipt code sent by the student terminal; when the pairing confirmation receipt code sent by the third-party terminal is consistent with that sent by the student terminal, the data sharing execution entity shares the retrieved learning progress data with the third-party terminal.

6. The training control method based on artificial intelligence according to claim 5 is characterized in that: After receiving the pairing confirmation receipt code, the pairing code and the data sharing request, the training terminal detects the call operation load level of the database corresponding to the training terminal and the call operation load level of the cloud platform, and determines the data sharing execution subject according to the call operation load level of the database corresponding to the training terminal and the call operation load level of the cloud platform, including: After receiving the pairing confirmation receipt code, the pairing code and the data sharing request, the training terminal retrieves the retrieval operation load parameters of the database corresponding to the training terminal and the retrieval operation load parameters of the cloud platform; wherein the retrieval operation load parameters of the database corresponding to the training terminal include memory utilization, the number of concurrent executions of data retrieval and cache hit rate; the retrieval operation load parameters of the cloud platform include transaction processing volume, query processing volume, node replication delay rate, intranet inlet bandwidth and intranet outlet bandwidth; The first operation load evaluation parameter corresponding to the database is obtained by using the operation load parameter retrieved from the database corresponding to the training terminal; wherein the first operation load evaluation parameter corresponding to the database is obtained by the following formula: Among them, S 01 represents the first operation load evaluation parameter corresponding to the database; H represents the cache hit rate of the database at the current moment; M represents the memory utilization rate of the database at the current moment; M y represents the optimal memory utilization that meets the database operation requirements; n represents the number of unit times experienced during the database operation process, and the value of the unit time is 1s; C represents the number of concurrent executions of data retrieval from the database at the current moment; C i H represents the number of concurrent executions of data retrieval corresponding to the i-th unit time; f Indicates the maximum floating value of the cache hit rate between two adjacent units of time during database operation; The second operation load evaluation parameter corresponding to the cloud platform is obtained by using the operation load parameter retrieved by the cloud platform; wherein the second operation load evaluation parameter corresponding to the cloud platform is obtained by the following formula: Among them, S 02 represents the second operation load evaluation parameter corresponding to the cloud platform; K represents the transaction processing volume of the cloud platform at the current moment; Q represents the query processing volume of the cloud platform at the current moment; D represents the node replication delay rate of the cloud platform at the current moment; B in and B out They respectively represent the intranet ingress bandwidth and intranet egress bandwidth of the cloud platform at the current moment; When the first operation load evaluation parameter corresponding to the database and the second operation load evaluation parameter corresponding to the cloud platform meet the first constraint condition, the database is determined to be the data sharing execution subject; When the first operation load evaluation parameter corresponding to the database and the second operation load evaluation parameter corresponding to the cloud platform meet the second constraint condition, the cloud platform is determined as the data sharing execution subject.

7. The training control method based on artificial intelligence according to claim 6 is characterized in that: The first constraint is as follows: Among them, S 01 represents the first operation load evaluation parameter corresponding to the database; S 02 represents the second operation load evaluation parameter corresponding to the cloud platform; α, β and γ represent the first constant coefficient, the second constant coefficient and the third constant coefficient respectively, and the value ranges of the first constant coefficient, the second constant coefficient and the third constant coefficient are: [0.24, 3.52], (0, 100] and (0, 10] respectively; The second constraint is as follows: Among them, S 01 represents the first operation load evaluation parameter corresponding to the database; S 02 represents the second operating load evaluation parameter corresponding to the cloud platform; α, β and γ represent the first constant coefficient, the second constant coefficient and the third constant coefficient respectively, and the value ranges of the first constant coefficient, the second constant coefficient and the third constant coefficient are: [0.24, 3.52], (0, 100] and (0, 10] respectively.

8. The training control method based on artificial intelligence according to claim 1 is characterized in that: Monitor the cloud platform's data cloud storage operating parameters in real time, and adjust the cloud platform's data sharing operating strategy based on the data cloud storage operating parameters, including: Real-time monitoring of the data cloud storage operating parameters of the cloud platform, wherein the data cloud storage operating parameters include data storage delay rate, data storage compression rate and number of concurrent data storage connections; The second constraint condition is adjusted using the data cloud storage operating parameters of the cloud platform.

9. The training control method based on artificial intelligence according to claim 8 is characterized in that: The second constraint condition is adjusted using the data cloud storage operation parameters of the cloud platform, including: The constraint adjustment coefficient is obtained by using the data cloud storage operation parameters of the cloud platform; wherein the constraint adjustment coefficient is obtained by the following formula: Where J represents the constraint adjustment coefficient; L represents the data storage delay rate of the cloud platform at the current moment; N represents the number of concurrent data storage connections of the cloud platform at the current moment; N max represents the maximum number of concurrent data storage connections that can satisfy the optimal operation of the cloud platform; Y represents the data storage compression rate of the cloud platform at the current moment; Y min Indicates the minimum data storage compression ratio that satisfies the optimal state of data storage on the cloud platform; The first constant coefficient of the second constraint condition is adjusted by using the constraint condition adjustment coefficient to obtain the adjusted first constant coefficient; wherein the adjusted first constant coefficient is obtained by the following formula: Among them, α t represents the adjusted first constant coefficient; α represents the first constant coefficient; α max and α min Indicates the maximum value and the minimum value of the coefficient appearing in the historical adjustment record of the first constant coefficient; The adjusted second constraint condition is obtained according to the adjusted first constant coefficient, and whether the cloud platform can serve as the data sharing execution subject is determined according to the adjusted second constraint condition.

10. A training control system based on artificial intelligence, characterized in that: The training control system based on artificial intelligence includes: A learning plan generation module is used for the training terminal to set a learning plan according to the basic information and learning objectives of the trainee, and to feed back the learning plan to the trainee terminal; The data cloud storage module is used to monitor the learning progress data of each student in real time through the student terminal, and store the learning progress data of the students in the cloud through the cloud platform; A mathematics sharing module, configured to enable the training terminal to share learning progress data according to the data sharing request sent by the trainee terminal when the trainee terminal sends a data sharing request; The sharing strategy adjustment module is used to monitor the data cloud storage operating parameters of the cloud platform in real time, and adjust the data sharing operating strategy of the cloud platform according to the data cloud storage operating parameters.

Images