CN115841403A - AI training method and system based on big data - Google Patents
AI training method and system based on big data Download PDFInfo
- Publication number
- CN115841403A CN115841403A CN202211623500.1A CN202211623500A CN115841403A CN 115841403 A CN115841403 A CN 115841403A CN 202211623500 A CN202211623500 A CN 202211623500A CN 115841403 A CN115841403 A CN 115841403A
- Authority
- CN
- China
- Prior art keywords
- data
- training
- teaching
- information
- test question
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Electrically Operated Instructional Devices (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an AI practical training method and system based on big data, which are characterized in that AI test question data are obtained by screening multi-module test questions from AI teaching big data, the AI test question data are sent to terminal equipment of a target student for multi-module test, multi-module comprehensive analysis is carried out according to the test question completion data of the target student, learning progress evaluation data of the target student are obtained, and practical training content analysis and retrieval are further carried out according to the learning progress evaluation data of the target student, so that teaching practical training scheme information of different students is obtained. The invention improves the training efficiency of the student AI, reduces the workload of teachers and further realizes the purpose of improving the training capacity of the student AI.
Description
Technical Field
The invention relates to the field of big data, in particular to an AI practical training method and system based on big data.
Background
Artificial Intelligence (AI) is a popular focus in the field of computers today. In the continuous development of social economy, artificial intelligence is taken as the focus of industry attention, and is applied to different fields, so that the industry can be promoted to be upgraded, the quality development requirements of the industry can be fully met, and the competitiveness of the industry is gradually improved. Meanwhile, along with the development of big data in the internet, the industry application of AI and big data together becomes a popular technology for enterprise research at present.
However, in some education institutions engaged in the AI field, due to the limitation of the traditional education mode, teaching efficiency is low in the AI practical training teaching, the practical training ability of students is difficult to improve, and the efficiency of teachers writing practical training contents by means of manual experience is low, so that practical training learning of the students on the AI is greatly hindered. Therefore, a method for improving the AI training efficiency of the trainees is needed.
Disclosure of Invention
In order to solve at least one technical problem, the invention provides an AI training method and system based on big data.
The invention provides an AI practical training method based on big data in a first aspect, which comprises the following steps:
obtaining AI teaching big data;
multi-module test question screening is carried out on the AI teaching big data to obtain AI test question data, and the AI test question data are sent to target student terminal equipment;
performing multi-module comprehensive analysis according to the target student test question completion data to obtain target student learning progress evaluation data;
carrying out practical training content analysis and retrieval according to the target student learning progress evaluation data to obtain teaching practical training scheme information;
generating AI comprehensive practical training data according to the teaching practical training scheme information, sending the AI comprehensive practical training data to target student terminal equipment for practical training test, and generating student practical training evaluation information according to a test result.
In this scheme, carry out the screening of many module examination questions from AI teaching big data, obtain AI examination questions data, with AI examination questions data send target student terminal equipment, include before:
carrying out artificial intelligent teaching content retrieval from the Internet to obtain initial retrieval data;
carrying out data classification on the initial retrieval data in a preset big data classification mode to obtain AI content classification data;
and carrying out test question simulation analysis and data integration according to the AI content classification data to obtain AI teaching big data.
In the scheme, multi-module test question screening is performed on the AI big teaching data to obtain AI test question data, and the AI test question data are sent to the target student terminal equipment, specifically:
classifying and screening the content of preset learning modules from the AI teaching big data to obtain the teaching module data of each learning module;
converting the teaching module data into test question formats to obtain module test question data;
and integrating the data of all the module test question data to obtain AI test question data.
In the scheme, the multi-module comprehensive analysis is performed according to the target student test question completion data to obtain target student learning progress evaluation data, which specifically comprises the following steps:
the AI test question data are sent to the target student terminal equipment for test question testing;
and acquiring target student test question completion data, and performing comprehensive evaluation of a preset learning module on the target student test question completion data to obtain target student learning progress evaluation data.
In this scheme, the analyzing and retrieving of the practical training content is performed according to the learning progress evaluation data of the target trainee to obtain teaching practical training scheme information, which specifically includes:
carrying out practical training content retrieval on specific learning module contents according to the learning progress evaluation data of the target trainee to obtain practical training frame information, practical training algorithm information and practical training model information;
carrying out practical training capability evaluation on the target student according to the learning progress evaluation data of the target student and generating corresponding practical training requirement information;
and carrying out scheme integration on the practical training frame information, the practical training algorithm information, the practical training model information and the practical training requirement information to obtain teaching practical training scheme information.
In this scheme, the generating of AI comprehensive practical training data according to teaching practical training scheme information and sending to target trainee terminal equipment for practical training test, and generating trainee practical training evaluation information according to the test result specifically include:
converting the terminal format according to the teaching training scheme information to obtain training outline data and training flow data;
performing data visualization integration on the training outline data and the training flow data to obtain AI comprehensive training data;
and sending the AI comprehensive training data to target student terminal equipment for display.
In this scheme, the generating AI comprehensive practical training data according to teaching practical training scheme information and sending to target trainee terminal equipment for practical training test, and generating trainee practical training evaluation information according to the test result, further includes:
acquiring design data of a training frame and design data of a training algorithm of a target user;
the training frame design data and the training algorithm design data are imported into a training test module for testing, and tested trainee algorithm hardware resource consumption information, trainee algorithm efficiency information, trainee algorithm accuracy and trainee training model error rate information are obtained;
according to the trainee algorithm hardware resource consumption information, the trainee algorithm efficiency information, the trainee algorithm accuracy and the trainee training model error rate information, carrying out training comprehensive capability evaluation on the trainee to obtain trainee training evaluation information;
and sending the trainee training evaluation information to trainee terminal equipment and teacher terminal equipment for display.
The second aspect of the present invention further provides an AI training system based on big data, including: the memory comprises a big data-based AI training program, and the big data-based AI training program realizes the following steps when executed by the processor:
obtaining AI teaching big data;
multi-module test question screening is carried out on the AI big teaching data to obtain AI test question data, and the AI test question data are sent to target student terminal equipment;
performing multi-module comprehensive analysis according to the target student test question completion data to obtain target student learning progress evaluation data;
analyzing and retrieving practical training contents according to the learning progress evaluation data of the target trainee to obtain teaching practical training scheme information;
generating AI comprehensive training data according to the teaching training scheme information, sending the AI comprehensive training data to target student terminal equipment for training test, and generating student training evaluation information according to a test result.
In this scheme, carry out the screening of many module examination questions from AI teaching big data, obtain AI examination questions data, with AI examination questions data send target student terminal equipment, include before:
carrying out artificial intelligent teaching content retrieval from the Internet to obtain initial retrieval data;
carrying out data classification on the initial retrieval data in a preset big data classification mode to obtain AI content classification data;
and carrying out test question simulation analysis and data integration according to the AI content classification data to obtain AI teaching big data.
In the scheme, the multi-module test question screening is performed on the AI big teaching data to obtain AI test question data, and the AI test question data is sent to the target student terminal equipment, specifically:
classifying and screening the content of preset learning modules from the AI teaching big data to obtain the teaching module data of each learning module;
converting the teaching module data into test question formats to obtain module test question data;
and integrating the data of all the module test question data to obtain AI test question data.
The invention discloses an AI practical training method and system based on big data, which are characterized in that AI test question data are obtained by screening multi-module test questions from AI teaching big data, the AI test question data are sent to terminal equipment of a target student for multi-module test, multi-module comprehensive analysis is carried out according to the test question completion data of the target student, learning progress evaluation data of the target student are obtained, and practical training content analysis and retrieval are further carried out according to the learning progress evaluation data of the target student, so that teaching practical training scheme information of different students is obtained. The invention improves the training efficiency of the student AI, reduces the workload of teachers and further realizes the purpose of improving the training capacity of the student AI.
Drawings
FIG. 1 is a flow chart illustrating a big data-based AI training method according to the present invention;
FIG. 2 illustrates a flow diagram for obtaining AI instructional big data according to the invention;
FIG. 3 is a flow chart illustrating the process of obtaining AI test question data according to the present invention;
fig. 4 shows a block diagram of an AI training system based on big data according to the present invention.
Detailed Description
In order that the above objects, features and advantages of the present invention can be more clearly understood, a more particular description of the invention, taken in conjunction with the accompanying drawings and detailed description, is set forth below. It should be noted that the embodiments and features of the embodiments of the present application may be combined with each other without conflict.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced in other ways than those specifically described herein, and therefore the scope of the present invention is not limited by the specific embodiments disclosed below.
Fig. 1 shows a flowchart of an AI training method based on big data according to the present invention.
As shown in fig. 1, a first aspect of the present invention provides an AI training method based on big data, including:
s102, obtaining AI teaching big data;
s104, multi-module test question screening is carried out on the AI teaching big data to obtain AI test question data, and the AI test question data are sent to target student terminal equipment;
s106, performing multi-module comprehensive analysis according to the target student test question completion data to obtain target student learning progress evaluation data;
s108, analyzing and retrieving practical training contents according to the learning progress evaluation data of the target trainees to obtain teaching practical training scheme information;
and S110, generating AI comprehensive training data according to the teaching training scheme information, sending the AI comprehensive training data to target student terminal equipment for training test, and generating student training evaluation information according to a test result.
It should be noted that the target student terminal device is generally a computer terminal, and the system terminal device includes a student terminal device, a teacher terminal device, and an administrator terminal device.
FIG. 2 shows a flow chart for obtaining AI instruction big data according to the present invention.
According to the embodiment of the invention, the multi-module test question screening is performed on the AI teaching big data to obtain AI test question data, and the AI test question data is sent to the target student terminal equipment, wherein the method comprises the following steps:
s202, retrieving artificial intelligent teaching contents from the Internet to obtain initial retrieval data;
s204, performing data classification on the initial retrieval data in a preset big data classification mode to obtain AI content classification data;
and S206, performing test question simulation analysis and data integration according to the AI content classification data to obtain AI teaching big data.
It should be noted that the data classification is performed by a preset big data classification method, specifically, the initial retrieval data is classified by a big data classification algorithm, and the big data classification algorithm includes a KNN algorithm, a bayesian classification algorithm, and the like. The AI content classification data are classified data obtained by classifying AI practical training course contents, and the AI practical training course contents comprise basic concepts, frames, algorithms, model construction and the like of AI. And performing test question simulation analysis and data integration on the AI content classification data, specifically performing test question conversion on the AI content classification data to obtain corresponding AI teaching big data.
FIG. 3 is a flow chart illustrating the process of obtaining AI test question data according to the present invention.
According to the embodiment of the invention, the multi-module examination question screening is carried out on the AI big teaching data to obtain AI examination question data, and the AI examination question data are sent to the target student terminal equipment, specifically:
s302, classifying and screening the content of the preset learning module from the AI teaching big data to obtain the teaching module data of each learning module;
s304, performing test question format conversion on the teaching module data to obtain module test question data;
and S306, integrating the data of all the module test question data to obtain AI test question data.
The learning module comprises a basic concept module, a frame module, an algorithm module, a model building learning module, a model training capacity module and the like.
According to the embodiment of the invention, the multi-module comprehensive analysis is carried out according to the target student test question completion data to obtain the target student learning progress evaluation data, and the method specifically comprises the following steps:
the AI test question data are sent to the target student terminal equipment for test question testing;
and acquiring target student test question completion data, and performing comprehensive evaluation of a preset learning module on the target student test question completion data to obtain target student learning progress evaluation data.
It should be noted that the target student learning progress evaluation data includes progress evaluation of each learning module of the target student, and the target student learning progress evaluation data can grasp the specific learning conditions of the student on an AI basic concept, an AI framework, an AI algorithm, model building and model practical training, so as to formulate a learning scheme of the student.
According to the embodiment of the invention, the training content analysis and retrieval are performed according to the target trainee learning progress evaluation data to obtain teaching training scheme information, and the method specifically comprises the following steps:
carrying out practical training content retrieval on specific learning module contents according to the learning progress evaluation data of the target trainee to obtain practical training frame information, practical training algorithm information and practical training model information;
carrying out practical training capability evaluation on the target student according to the learning progress evaluation data of the target student and generating corresponding practical training requirement information;
and carrying out scheme integration on the practical training frame information, the practical training algorithm information, the practical training model information and the practical training requirement information to obtain teaching practical training scheme information.
According to the embodiment of the invention, the generating of the AI comprehensive practical training data according to the teaching practical training scheme information, the sending of the AI comprehensive practical training data to the target student terminal equipment for practical training test, and the generating of the student practical training evaluation information according to the test result specifically comprise:
converting the terminal format according to the teaching training scheme information to obtain training outline data and training flow data;
performing data visualization integration on the practical training outline data and the practical training process data to obtain AI comprehensive practical training data;
and sending the AI comprehensive training data to target student terminal equipment for display.
It should be noted that, in the data visualization integration of the practical training outline data and the practical training process data, the practical training outline data is specifically used to generate the AI comprehensive practical training data visualized for the terminal device according to the practical training process data.
According to the embodiment of the invention, the generating of the AI comprehensive practical training data according to the teaching practical training scheme information, sending the AI comprehensive practical training data to the target student terminal equipment for practical training test, and generating the trainee practical training evaluation information according to the test result further comprises:
acquiring design data of a training frame and design data of a training algorithm of a target user;
the training frame design data and the training algorithm design data are imported into a training test module for testing, and tested trainee algorithm hardware resource consumption information, trainee algorithm efficiency information, trainee algorithm accuracy and trainee training model error rate information are obtained;
according to the trainee algorithm hardware resource consumption information, the trainee algorithm efficiency information, the trainee algorithm accuracy and the trainee training model error rate information, carrying out training comprehensive capability evaluation on the trainee to obtain trainee training evaluation information;
and sending the trainee training evaluation information to trainee terminal equipment and teacher terminal equipment for display.
It should be noted that the hardware resource consumption information of the student algorithm includes hardware consumption information such as a processor comprehensive utilization rate, a memory utilization rate, a GPU utilization rate, and the like, and the GPU utilization rate is specifically a utilization rate of a computer graphics processor.
According to the embodiment of the present invention, the scheme integration is performed on the training frame information, the training algorithm information, the training model information, and the training requirement information to obtain the teaching training scheme information, and the method further includes:
transmitting the training frame information, the training algorithm information and the training model information to a teacher client;
a teacher checks the training frame information, the training algorithm information and the training model information through a teacher client and inputs application scene data through the teacher client;
the system acquires the application scene data and generates application scene additional data by combining the practical training frame information, the practical training algorithm information and the practical training model information;
and adding the application scene additional data to the teaching practical training scheme information to form the teaching practical training scheme information with the application scene.
It should be noted that, the practical training frame information, the practical training algorithm information and the practical training model information are sent to the teacher client, the teacher checks and compiles the scene of the practical training information and inputs the application scene data.
According to the embodiment of the invention, the method further comprises the following steps:
acquiring trainee algorithm hardware resource consumption information and trainee training model error rate information;
if the hardware consumption of the trainee algorithm hardware resource consumption information is higher than a preset condition and the error rate of the trainee training model is higher than a preset error rate;
acquiring AI test data of a target student, and intelligently intercepting the AI test data to obtain intercepted AI test data;
the intercepted AI test data is used as new test data to carry out secondary practical training comprehensive capability evaluation to obtain the practical training evaluation information of a secondary student;
and sending the secondary trainee training evaluation information to trainee terminal equipment and teacher terminal equipment for displaying.
It should be noted that, in the training test process, since hardware consumption of the tested trainee algorithm hardware resource consumption information and errors of the trainee training model are high in the beginner stage of some trainees, and it is difficult to grasp the AI training situation of the beginner in a segmented manner, the invention reduces the test difficulty by intercepting the AI test data with intelligent data, so that the trainee of the beginner AI can be evaluated in a relatively accurate training capacity, and the accurate star of the training comprehensive evaluation of the invention is increased. The intelligent data intercepting process is specifically to intercept the AI test data in a data volume halving way, and the intercepted AI test data obtained each time needs to circularly judge and compare the student algorithm hardware resource consumption information and the student training model error rate until the hardware consumption of the student algorithm hardware resource consumption information is lower than or equal to a preset condition and the student training model error rate is lower than or equal to a preset error rate, wherein the preset condition and the preset error rate are generally set by a teacher.
According to the embodiment of the invention, the generating of the AI comprehensive practical training data according to the teaching practical training scheme information and the sending of the AI comprehensive practical training data to the target student terminal device for practical training test further comprises:
monitoring the answering condition of a target student in real time through the system during the practical training test;
acquiring the total test answering time, the frame construction time and the algorithm improvement time of a target student in the training process;
performing information integration on the overall test response time, the frame construction time and the algorithm improvement time to obtain practical training monitoring data;
comparing the average data of the target trainees according to the training monitoring data to obtain the proficiency of the training algorithm of the target trainees;
analyzing the test items according to the proficiency of the target student training algorithm and the target student training evaluation information to obtain additional test items;
and generating an additional training plan of the target trainee according to the additional test items.
It should be noted that the student average data is specifically an average value in the student monitoring data, that is, average overall test response time, average framework building time, average algorithm improvement time, and the like. According to the method and the device, the multi-dimensional trainee algorithm capability evaluation is carried out on the test monitoring data of the target trainee, so that the target trainee additional training plan which is specific to the target trainee can be obtained, and the trainee training capability is enhanced.
According to the embodiment of the invention, the method further comprises the following steps:
acquiring an additional test item;
extracting knowledge points according to the additional test items to obtain test knowledge points;
according to the test knowledge points, extracting similar training items from AI teaching big data to obtain training similar test items;
and correcting the target student additional training plan according to the training similar test item to form a new target student additional training plan.
It should be noted that the training similar test items specifically attach test items similar to the test items, the similar test items have an effect of strengthening exercise on the trainee, and the trainee can further consolidate the understanding of the trainee on the unfamiliar algorithm through the training similar test items, so that the AI training capability is improved.
Fig. 4 shows a block diagram of an AI training system based on big data according to the present invention.
The second aspect of the present invention further provides an AI practical training system 4 based on big data, which includes: the memory 41 and the processor 42, the memory includes a big data based AI training program, and when executed by the processor, the big data based AI training program implements the following steps:
obtaining AI teaching big data;
multi-module test question screening is carried out on the AI teaching big data to obtain AI test question data, and the AI test question data are sent to target student terminal equipment;
performing multi-module comprehensive analysis according to the target student test question completion data to obtain target student learning progress evaluation data;
carrying out practical training content analysis and retrieval according to the target student learning progress evaluation data to obtain teaching practical training scheme information;
generating AI comprehensive training data according to the teaching training scheme information, sending the AI comprehensive training data to target student terminal equipment for training test, and generating student training evaluation information according to a test result.
It should be noted that the target trainee terminal device is generally a computer terminal, and the terminal device of the system includes a trainee terminal device, a teacher terminal device, and an administrator terminal device.
According to the embodiment of the invention, the multi-module test question screening is performed on the AI teaching big data to obtain AI test question data, and the AI test question data is sent to the target student terminal equipment, wherein the method comprises the following steps:
carrying out artificial intelligent teaching content retrieval from the Internet to obtain initial retrieval data;
carrying out data classification on the initial retrieval data in a preset big data classification mode to obtain AI content classification data;
and carrying out test question simulation analysis and data integration according to the AI content classification data to obtain AI teaching big data.
It should be noted that the data classification is performed by a preset big data classification method, specifically, the initial retrieval data is classified by a big data classification algorithm, and the big data classification algorithm includes a KNN algorithm, a bayesian classification algorithm, and the like. The AI content classification data are classified data obtained by classifying AI practical training course contents, and the AI practical training course contents comprise basic concepts, frames, algorithms, model construction and the like of AI. And performing test question simulation analysis and data integration on the AI content classification data, specifically performing test question conversion on the AI content classification data to obtain corresponding AI teaching big data.
According to the embodiment of the invention, the multi-module examination question screening is carried out on the AI big teaching data to obtain AI examination question data, and the AI examination question data are sent to the target student terminal equipment, specifically:
classifying and screening the content of preset learning modules from the AI teaching big data to obtain the teaching module data of each learning module;
converting the test question format of the teaching module data to obtain module test question data;
and integrating the data of all the module test question data to obtain AI test question data.
The learning module comprises a basic concept module, a frame module, an algorithm module, a model building learning module, a model training capacity module and the like.
According to the embodiment of the invention, the multi-module comprehensive analysis is carried out according to the target student test question completion data to obtain the target student learning progress evaluation data, and the method specifically comprises the following steps:
the AI test question data are sent to the target student terminal equipment for test question testing;
and acquiring target student test question completion data, and performing comprehensive evaluation of a preset learning module on the target student test question completion data to obtain target student learning progress evaluation data.
It should be noted that the learning progress evaluation data of the target student comprises progress evaluation of each learning module of the target student, and the learning progress evaluation data of the target student can master the specific learning conditions of the student on the AI basic concept, the AI frame, the AI algorithm, the model building and the model practical training, so that the learning scheme of the student is formulated.
According to the embodiment of the invention, the training content analysis and retrieval are performed according to the target trainee learning progress evaluation data to obtain teaching training scheme information, and the method specifically comprises the following steps:
carrying out practical training content retrieval on specific learning module contents according to the learning progress evaluation data of the target trainee to obtain practical training frame information, practical training algorithm information and practical training model information;
carrying out practical training capability evaluation on the target student according to the learning progress evaluation data of the target student and generating corresponding practical training requirement information;
and carrying out scheme integration on the practical training frame information, the practical training algorithm information, the practical training model information and the practical training requirement information to obtain teaching practical training scheme information.
According to the embodiment of the invention, the generating of AI comprehensive practical training data according to the teaching practical training scheme information, the sending of the AI comprehensive practical training data to the target student terminal equipment for practical training test and the generating of student practical training evaluation information according to the test result are specifically as follows:
converting the terminal format according to the teaching training scheme information to obtain training outline data and training flow data;
performing data visualization integration on the training outline data and the training flow data to obtain AI comprehensive training data;
and sending the AI comprehensive practical training data to target student terminal equipment for display.
It should be noted that, in the data visualization integration of the practical training outline data and the practical training process data, the practical training outline data is specifically to generate AI comprehensive practical training data for visualizing the terminal device according to the practical training process data.
According to the embodiment of the invention, the generating of the AI comprehensive practical training data according to the teaching practical training scheme information, sending the AI comprehensive practical training data to the target student terminal equipment for practical training test, and generating the trainee practical training evaluation information according to the test result further comprises:
acquiring design data of a practical training frame and practical training algorithm of a target user;
the training frame design data and the training algorithm design data are imported into a training test module for testing, and tested trainee algorithm hardware resource consumption information, trainee algorithm efficiency information, trainee algorithm accuracy and trainee training model error rate information are obtained;
according to the trainee algorithm hardware resource consumption information, the trainee algorithm efficiency information, the trainee algorithm accuracy and the trainee training model error rate information, carrying out training comprehensive capability evaluation on the trainee to obtain trainee training evaluation information;
and sending the trainee training evaluation information to trainee terminal equipment and teacher terminal equipment for display.
It should be noted that the hardware resource consumption information of the student algorithm includes hardware consumption information such as a processor comprehensive utilization rate, a memory utilization rate, a GPU utilization rate, and the like, and the GPU utilization rate is specifically a utilization rate of a computer graphics processor.
According to the embodiment of the present invention, the scheme integration is performed on the training frame information, the training algorithm information, the training model information, and the training requirement information to obtain the teaching training scheme information, and the method further includes:
transmitting the training frame information, the training algorithm information and the training model information to a teacher client;
a teacher checks the training frame information, the training algorithm information and the training model information through a teacher client and inputs application scene data through the teacher client;
the system acquires the application scene data and generates application scene additional data by combining the practical training frame information, the practical training algorithm information and the practical training model information;
and adding the application scene additional data to the teaching practical training scheme information to form the teaching practical training scheme information with the application scene.
It should be noted that, the practical training frame information, the practical training algorithm information and the practical training model information are sent to the teacher client, the teacher checks and compiles the scene of the practical training information and inputs the application scene data.
According to the embodiment of the invention, the method further comprises the following steps:
acquiring trainee algorithm hardware resource consumption information and trainee training model error rate information;
if the hardware consumption of the trainee algorithm hardware resource consumption information is higher than a preset condition and the error rate of the trainee training model is higher than a preset error rate;
acquiring AI test data of a target student, and intelligently intercepting the AI test data to obtain intercepted AI test data;
the intercepted AI test data is used as new test data to carry out secondary practical training comprehensive capability evaluation to obtain the practical training evaluation information of a secondary student;
and sending the secondary trainee training evaluation information to trainee terminal equipment and teacher terminal equipment for displaying.
It should be noted that, in the training test process, since hardware consumption of the tested trainee algorithm hardware resource consumption information and errors of the trainee training model are high in the beginner stage of some trainees, and it is difficult to grasp the AI training situation of the beginner in a segmented manner, the invention reduces the test difficulty by intercepting the AI test data with intelligent data, so that the trainee of the beginner AI can be evaluated in a relatively accurate training capacity, and the accurate star of the training comprehensive evaluation of the invention is increased. The intelligent data intercepting process is specifically to intercept the AI test data in a data volume halving way, and the intercepted AI test data obtained each time needs to circularly judge and compare the student algorithm hardware resource consumption information and the student training model error rate until the hardware consumption of the student algorithm hardware resource consumption information is lower than or equal to a preset condition and the student training model error rate is lower than or equal to a preset error rate, wherein the preset condition and the preset error rate are generally set by a teacher.
According to the embodiment of the invention, the generating of the AI comprehensive practical training data according to the teaching practical training scheme information and the sending of the AI comprehensive practical training data to the target student terminal device for practical training test further comprises:
monitoring the answering condition of a target student in real time through the system during the practical training test;
acquiring the total test response time, the frame construction time and the algorithm improvement time of a target student in the training process;
performing information integration on the overall test response time, the frame construction time and the algorithm improvement time to obtain practical training monitoring data;
comparing the average data of the target trainees according to the training monitoring data to obtain the proficiency of the training algorithm of the target trainees;
analyzing the test items according to the proficiency of the target student training algorithm and the target student training evaluation information to obtain additional test items;
and generating an additional training plan of the target trainee according to the additional test items.
It should be noted that the student average data is specifically an average value in the student monitoring data, that is, average overall test response time, average framework building time, average algorithm improvement time, and the like. According to the invention, the multi-dimensional trainee algorithm capability evaluation is carried out on the test monitoring data of the target trainee, so that a target trainee additional training plan with pertinence to the target trainee can be obtained, and the trainee training capability is enhanced.
According to the embodiment of the invention, the method further comprises the following steps:
acquiring an additional test item;
extracting knowledge points according to the additional test items to obtain test knowledge points;
according to the test knowledge points, extracting similar training items from AI teaching big data to obtain training similar test items;
and correcting the target student additional training plan according to the training similar test item to form a new target student additional training plan.
It should be noted that the training similar test items specifically attach test items similar to the test items, the similar test items have an effect of strengthening exercise on the trainee, and the trainee can further consolidate the understanding of the trainee on the unfamiliar algorithm through the training similar test items, so that the AI training capability is improved.
The invention discloses an AI practical training method and system based on big data, which are characterized in that AI test question data are obtained by screening multi-module test questions from AI teaching big data, the AI test question data are sent to terminal equipment of a target student for multi-module test, multi-module comprehensive analysis is carried out according to the test question completion data of the target student, learning progress evaluation data of the target student are obtained, and practical training content analysis and retrieval are further carried out according to the learning progress evaluation data of the target student, so that teaching practical training scheme information of different students is obtained. The invention improves the training efficiency of the student AI, reduces the workload of teachers and further realizes the purpose of improving the training capacity of the student AI.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other manners. The above-described device embodiments are merely illustrative, for example, the division of the unit is only a logical functional division, and there may be other division ways in actual implementation, such as: multiple units or components may be combined, or may be integrated into another system, or some features may be omitted, or not implemented. In addition, the coupling, direct coupling or communication connection between the components shown or discussed may be through some interfaces, and the indirect coupling or communication connection between the devices or units may be electrical, mechanical or in other forms.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units; can be located in one place or distributed on a plurality of network units; some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, all the functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately regarded as one unit, or two or more units may be integrated into one unit; the integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional unit.
Those of ordinary skill in the art will understand that: all or part of the steps of implementing the method embodiments may be implemented by hardware related to program instructions, and the program may be stored in a computer-readable storage medium, and when executed, executes the steps including the method embodiments; and the aforementioned storage medium includes: a mobile storage device, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and various media capable of storing program codes.
Alternatively, the integrated unit of the present invention may be stored in a computer-readable storage medium if it is implemented in the form of a software functional module and sold or used as a separate product. Based on such understanding, the technical solutions of the embodiments of the present invention may be essentially implemented or a part contributing to the prior art may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the methods described in the embodiments of the present invention. And the aforementioned storage medium includes: a removable storage device, a ROM, a RAM, a magnetic or optical disk, or various other media that can store program code.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and all the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims.
Claims (10)
1. An AI training method based on big data is characterized by comprising the following steps:
obtaining AI teaching big data;
multi-module test question screening is carried out on the AI teaching big data to obtain AI test question data, and the AI test question data are sent to target student terminal equipment;
performing multi-module comprehensive analysis according to the target student test question completion data to obtain target student learning progress evaluation data;
carrying out practical training content analysis and retrieval according to the target student learning progress evaluation data to obtain teaching practical training scheme information;
generating AI comprehensive training data according to the teaching training scheme information, sending the AI comprehensive training data to target student terminal equipment for training test, and generating student training evaluation information according to a test result.
2. The AI training method based on big data according to claim 1, wherein the AI training method comprises the steps of screening multiple module test questions from AI teaching big data to obtain AI test question data, and sending the AI test question data to a target student terminal device, wherein the AI training method comprises the following steps:
carrying out artificial intelligent teaching content retrieval from the Internet to obtain initial retrieval data;
carrying out data classification on the initial retrieval data in a preset big data classification mode to obtain AI content classification data;
and carrying out test question simulation analysis and data integration according to the AI content classification data to obtain AI teaching big data.
3. The AI training method based on big data as claimed in claim 1, wherein the AI teaching big data is screened by multi-module test questions to obtain AI test question data, and the AI test question data is sent to the target student terminal device, specifically:
classifying and screening the content of preset learning modules from the AI teaching big data to obtain the teaching module data of each learning module;
converting the teaching module data into test question formats to obtain module test question data;
and integrating the data of all the module test question data to obtain AI test question data.
4. The AI training method based on big data as claimed in claim 1, wherein the multi-module analysis is performed according to the target student question completion data to obtain the target student learning progress evaluation data, specifically:
the AI test question data are sent to the target student terminal equipment for test question testing;
and acquiring target student test question completion data, and performing comprehensive evaluation of a preset learning module on the target student test question completion data to obtain target student learning progress evaluation data.
5. The AI training method based on big data as claimed in claim 1, wherein the training content analysis and retrieval is performed according to the target trainee learning progress evaluation data to obtain teaching training scheme information, specifically:
carrying out practical training content retrieval on specific learning module contents according to the learning progress evaluation data of the target trainee to obtain practical training frame information, practical training algorithm information and practical training model information;
carrying out practical training capability evaluation on the target student according to the learning progress evaluation data of the target student and generating corresponding practical training requirement information;
and carrying out scheme integration on the practical training frame information, the practical training algorithm information, the practical training model information and the practical training requirement information to obtain teaching practical training scheme information.
6. The AI practical training method based on big data according to claim 1, wherein the AI comprehensive practical training data is generated according to teaching practical training scheme information and sent to a target trainee terminal device for practical training test, and trainee practical training evaluation information is generated according to a test result, specifically:
converting the terminal format according to the teaching training scheme information to obtain training outline data and training flow data;
performing data visualization integration on the training outline data and the training flow data to obtain AI comprehensive training data;
and sending the AI comprehensive training data to target student terminal equipment for display.
7. The AI training method based on big data according to claim 6, wherein said generating AI comprehensive training data according to teaching training scheme information and sending to target trainee terminal equipment for training test, and generating trainee training evaluation information according to the test result, further comprising:
acquiring design data of a training frame and design data of a training algorithm of a target user;
the training frame design data and the training algorithm design data are imported into a training test module for testing, and tested trainee algorithm hardware resource consumption information, trainee algorithm efficiency information, trainee algorithm accuracy and trainee training model error rate information are obtained;
according to the trainee algorithm hardware resource consumption information, the trainee algorithm efficiency information, the trainee algorithm accuracy and the trainee training model error rate information, carrying out training comprehensive capability evaluation on the trainee to obtain trainee training evaluation information;
and sending the trainee training evaluation information to trainee terminal equipment and teacher terminal equipment for display.
8. An AI training system based on big data, which is characterized in that the system comprises: the memory comprises a big data-based AI training program, and the big data-based AI training program realizes the following steps when executed by the processor:
obtaining AI teaching big data;
multi-module test question screening is carried out on the AI teaching big data to obtain AI test question data, and the AI test question data are sent to target student terminal equipment;
performing multi-module comprehensive analysis according to the target student test question completion data to obtain target student learning progress evaluation data;
carrying out practical training content analysis and retrieval according to the target student learning progress evaluation data to obtain teaching practical training scheme information;
generating AI comprehensive training data according to the teaching training scheme information, sending the AI comprehensive training data to target student terminal equipment for training test, and generating student training evaluation information according to a test result.
9. The AI training system based on big data according to claim 8, wherein the AI training system performs multi-module test question screening from the AI teaching big data to obtain AI test question data, and sends the AI test question data to the target student terminal device, and the AI training system based on big data comprises:
carrying out artificial intelligent teaching content retrieval from the Internet to obtain initial retrieval data;
carrying out data classification on the initial retrieval data in a preset big data classification mode to obtain AI content classification data;
and carrying out test question simulation analysis and data integration according to the AI content classification data to obtain AI teaching big data.
10. The AI training system based on big data according to claim 8, wherein the AI training system performs multi-module test question screening from the AI teaching big data to obtain AI test question data, and sends the AI test question data to a target student terminal device, specifically:
classifying and screening the content of preset learning modules from the AI teaching big data to obtain the teaching module data of each learning module;
converting the teaching module data into test question formats to obtain module test question data;
and integrating the data of all the module test question data to obtain AI test question data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211623500.1A CN115841403B (en) | 2022-12-16 | 2022-12-16 | AI practical training method and system based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211623500.1A CN115841403B (en) | 2022-12-16 | 2022-12-16 | AI practical training method and system based on big data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115841403A true CN115841403A (en) | 2023-03-24 |
| CN115841403B CN115841403B (en) | 2023-09-05 |
Family
ID=85578780
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211623500.1A Active CN115841403B (en) | 2022-12-16 | 2022-12-16 | AI practical training method and system based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115841403B (en) |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107025816A (en) * | 2017-06-12 | 2017-08-08 | 河南中医药大学 | A kind of interactive learning aid system of English |
| KR20170103586A (en) * | 2016-02-24 | 2017-09-13 | 라인 가부시키가이샤 | Method and system for artificial intelligence learning using messaging service and method and system for relaying answer using artificial intelligence |
| CN107993169A (en) * | 2017-11-27 | 2018-05-04 | 郝力云 | Foreign trade teaching platform and system |
| CN111798222A (en) * | 2020-08-05 | 2020-10-20 | 江苏经贸职业技术学院 | Teaching mode for enterprise management |
| CN111915458A (en) * | 2020-07-13 | 2020-11-10 | 同济大学 | On-line experiment teaching system for exploration type and personalized learning |
| CN112258357A (en) * | 2020-10-28 | 2021-01-22 | 山东职业学院 | Entrepreneurship training management system |
| CN112434206A (en) * | 2019-12-11 | 2021-03-02 | 沈阳工业大学 | Question bank generating system based on web crawler and application method |
| CN112651857A (en) * | 2020-04-07 | 2021-04-13 | 卫宁健康科技集团股份有限公司 | Training method and device for sudden public health event |
| US20210304630A1 (en) * | 2020-03-27 | 2021-09-30 | Coursera, Inc. | Interpretable machine learning algorithms for identifying at-risk students in online degree programs |
| CN113822774A (en) * | 2021-09-20 | 2021-12-21 | 曹庆恒 | Financial teaching system, using method thereof and computer readable storage medium |
| CN114550510A (en) * | 2022-01-26 | 2022-05-27 | 重庆三峡职业学院 | Big data artificial intelligence teaching training system |
| CN114913728A (en) * | 2022-05-09 | 2022-08-16 | 欧吉 | Vocational skill training system based on internet platform |
-
2022
- 2022-12-16 CN CN202211623500.1A patent/CN115841403B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20170103586A (en) * | 2016-02-24 | 2017-09-13 | 라인 가부시키가이샤 | Method and system for artificial intelligence learning using messaging service and method and system for relaying answer using artificial intelligence |
| CN107025816A (en) * | 2017-06-12 | 2017-08-08 | 河南中医药大学 | A kind of interactive learning aid system of English |
| CN107993169A (en) * | 2017-11-27 | 2018-05-04 | 郝力云 | Foreign trade teaching platform and system |
| CN112434206A (en) * | 2019-12-11 | 2021-03-02 | 沈阳工业大学 | Question bank generating system based on web crawler and application method |
| US20210304630A1 (en) * | 2020-03-27 | 2021-09-30 | Coursera, Inc. | Interpretable machine learning algorithms for identifying at-risk students in online degree programs |
| CN112651857A (en) * | 2020-04-07 | 2021-04-13 | 卫宁健康科技集团股份有限公司 | Training method and device for sudden public health event |
| CN111915458A (en) * | 2020-07-13 | 2020-11-10 | 同济大学 | On-line experiment teaching system for exploration type and personalized learning |
| CN111798222A (en) * | 2020-08-05 | 2020-10-20 | 江苏经贸职业技术学院 | Teaching mode for enterprise management |
| CN112258357A (en) * | 2020-10-28 | 2021-01-22 | 山东职业学院 | Entrepreneurship training management system |
| CN113822774A (en) * | 2021-09-20 | 2021-12-21 | 曹庆恒 | Financial teaching system, using method thereof and computer readable storage medium |
| CN114550510A (en) * | 2022-01-26 | 2022-05-27 | 重庆三峡职业学院 | Big data artificial intelligence teaching training system |
| CN114913728A (en) * | 2022-05-09 | 2022-08-16 | 欧吉 | Vocational skill training system based on internet platform |
Non-Patent Citations (2)
| Title |
|---|
| SONG LIU 等: "AI Quality Cultivation and Application Ability Training for Normal University Students", 《2021 7TH ANNUAL INTERNATIONAL CONFERENCE ON NETWORK AND INFORMATION SYSTEMS FOR COMPUTERS (ICNISC)》, pages 116 - 120 * |
| 黄剑锋 等: "可视化WebIDE编程实训***的构建与教学实践", 《实验技术与管理》, vol. 38, no. 07, pages 166 - 171 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115841403B (en) | 2023-09-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2019218426A1 (en) | Method and apparatus for generating lesson plan for teaching preparation | |
| CN115544241B (en) | Intelligent pushing method and device for online operation | |
| Ni et al. | Deepqr: Neural-based quality ratings for learnersourced multiple-choice questions | |
| CN110263328A (en) | A kind of disciplinary capability type mask method, device, storage medium and terminal device | |
| CN113257060A (en) | Question answering solving method, device, equipment and storage medium | |
| CN110688480A (en) | Real-time teaching evaluation method and system based on message | |
| CN113160009A (en) | Information pushing method, related device and computer medium | |
| CN112836994A (en) | Big data visualization method for online remote education and online education server | |
| CN112215506A (en) | Intelligent digital education AI classroom big data management platform and device | |
| CN115841403B (en) | AI practical training method and system based on big data | |
| CN110673742A (en) | System and method for evaluating learning ability of students in classroom based on virtual reality | |
| CN111415283A (en) | Factor analysis method and device for effective online teaching | |
| CN113010687B (en) | Exercise label prediction method and device, storage medium and computer equipment | |
| CN112785039B (en) | Prediction method and related device for answer score rate of test questions | |
| CN115018676A (en) | Interactive equipment is used in online education based on VR technique | |
| KR101245824B1 (en) | Method, system and computer-readable recording medium for providing study information | |
| CN113919983A (en) | Test question portrait method, device, electronic equipment and storage medium | |
| CN113822589A (en) | Intelligent interviewing method, device, equipment and storage medium | |
| TWI529650B (en) | Intelligent adaptive evaluation system using fuzzy markup language and its application method | |
| CN116187533B (en) | Big data trend prediction method and system based on deep learning | |
| Zhang et al. | Research on practical teaching of cross-border e-commerce in applied universities based on big data technology | |
| CN113223356B (en) | Skill training and checking system for PLC control technology | |
| CN117455126B (en) | Ubiquitous practical training teaching and evaluation management system and method | |
| CN114969660B (en) | Online interactive dynamic statistics education method, platform, device and storage medium | |
| CN115393133A (en) | Digital twin practical exercise question bank development platform and method for training |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |