AI education training analysis method and system based on big data evaluation

Abstract

The invention relates to the technical field of big data evaluation, in particular to an AI educational training analysis method and system based on big data evaluation, and the method comprises the steps: obtaining a weak link of the operation of a corresponding person from historical operation data, constructing an operation weak link knowledge point graph based on the knowledge content related to the weak link, and obtaining an AI educational training analysis result; performing weak knowledge point association analysis based on the operation weak link knowledge point graph to obtain association conditions of the weak knowledge points, and performing importance weight analysis of the weak knowledge points based on the association conditions of the weak knowledge points and the risk levels of the corresponding weak links obtained through evaluation. The course resource matching analysis is carried out based on the importance weight analysis of the weak knowledge points, the danger degree of weak links is evaluated, and the course resource matching is carried out according to the importance weight of the weak knowledge points, so that personnel can learn and master key knowledge and skills in time, and the risk of accidents caused by misoperation is reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of big data evaluation, and particularly relates to an AI education training analysis method and system based on big data evaluation. BACKGROUND

[0002] In today's various industries, personnel training is a key link to improve business capacity and ensure operation safety and quality. Traditional training methods often use unified curriculum systems and teaching content, lacking precise consideration of individual differences and actual operation needs of trainees. New employees usually receive standardized training courses after joining the company. Although these courses cover the basic knowledge and general skills of the industry, they cannot provide targeted guidance for problems that different trainees may encounter in actual operations.

[0003] Currently, most training programs cannot accurately target the specific training needs of trainees. When analyzing the operation ability of trainees, there is a lack of effective use of historical operation data. For example, in some complex production and manufacturing processes, workers may frequently make mistakes in certain specific operation steps. However, due to the lack of deep mining of historical operation data, training personnel cannot timely discover these problems, resulting in the inability to design training content targeting these weak links, and the training effect is greatly discounted. Existing training needs analysis methods often only focus on surface skill deficiencies, ignoring the internal relationships between knowledge. At the same time, traditional curriculum resource allocation methods are usually based on fixed curriculum systems and experience judgments, lacking scientific evaluation and dynamic adjustment mechanisms. In terms of resource allocation, it is difficult to reasonably arrange according to the actual needs of trainees and the importance of knowledge points. For example, in internal training of enterprises, the same training courses may be provided to all employees without considering the differences between employees of different positions and skill levels. This not only causes waste of curriculum resources, but also makes trainees who really need to focus on training unable to obtain sufficient learning resources.

[0004] In summary, the existing education training analysis technology has many shortcomings and cannot meet the needs of practical applications. Therefore, there is an urgent need for an AI education training analysis method and system based on big data evaluation. SUMMARY

[0005] In order to overcome the defects and shortcomings of the prior art, the present application provides an AI education training analysis method and system based on big data evaluation.

[0006] In order to achieve the above purpose, the present application adopts the following technical solutions: In a first aspect, the present application provides an AI education training analysis method based on big data evaluation, comprising the following steps: Step S1, obtaining weak links of corresponding personnel operation from historical operation data, and constructing an operation weak link knowledge point graph based on knowledge content involved in the weak links; Step S2, performing weak knowledge point correlation analysis based on the operation weak link knowledge point graph to obtain correlation of the weak knowledge points; Step S3, performing importance weight analysis of the weak knowledge points based on the correlation of the weak knowledge points and the risk degree of the corresponding weak links obtained through evaluation; Step S4, performing course resource matching analysis based on the importance weight analysis of the weak knowledge points.

[0007] In an implementation manner of the present application, the step S1 includes the following specific contents: S11, obtaining the score of each operation step of the student, obtaining the operation link with a score less than a score threshold, and setting it as a weak link of corresponding personnel operation, wherein the score threshold is generally set as 60% of the full score, i.e., the passing score, and the passing score is generally used to evaluate whether the operation of the student meets the requirements in the prior art; S12, obtaining the knowledge points involved in the weak links of corresponding operation stored in the storage module.

[0008] In an implementation manner of the present application, the step S2 includes the following specific steps: S21, obtaining the knowledge points involved in the weak links of each operation of the operation personnel, obtaining the same knowledge points involved in the weak links of each operation, and obtaining the score data corresponding to the weak links of each operation; S22, performing weak influence analysis of the corresponding knowledge points based on the same knowledge points involved in the weak links of each operation and the score data corresponding to the weak links of each operation, wherein the weak influence formula of the corresponding knowledge points is: wherein mz is the number of weak links involving the corresponding knowledge points, pi is the number of knowledge points of the i-th weak link involving the corresponding knowledge points, Qi is the total score of the i-th weak link involving the corresponding knowledge points, and Qwi is the score of the i-th weak link involving the corresponding knowledge points, which comprehensively considers the number of knowledge points, the total score and the actual score of each weak link involving the knowledge points, so as to evaluate the negative influence degree of the knowledge points on the overall performance; S23, obtaining the sum of the weak influence results of all knowledge points, and obtaining the weak influence proportion anomaly of the corresponding knowledge points by dividing the weak influence result of the corresponding knowledge points by the sum of the weak influence results of all knowledge points.

[0009] In an implementation manner of the present application, the risk degree of the corresponding weak link in the step S3 comprises the following specific steps: S31, obtain the loss situation caused by the corresponding failure history of the corresponding weak link and the historical generation trend of the corresponding failure of the corresponding weak link to analyze the change trend of the weak link related index over time; S32, analyze the risk degree of the corresponding weak link based on the loss situation caused by the corresponding failure history of the corresponding weak link and the historical generation trend of the corresponding failure of the corresponding weak link, wherein the calculation formula of the risk degree of the i-th weak link is: , wherein Ri is the loss situation caused by the corresponding failure history of the i-th weak link, Rm is the loss situation caused by all failure history, xt is the number of times of corresponding failure generated in the current period, x(t-1) is the number of times of corresponding failure generated in the last period, wherein Ri / Rm is the risk degree proportion of the i-th weak link in the historical data causing a dangerous event, and xt / x(t-1) is the historical generation trend of the corresponding failure.

[0010] In an implementation manner of the present application, the importance weight analysis of the weak knowledge point in the step S3 comprises the following specific contents: S33, obtain the risk degree of all weak links, and obtain the same knowledge point situation involved in the weak link, the score situation data of the weak link corresponding to each operation, and the weak impact proportion weight of the corresponding knowledge point; S34, obtain the risk degree of all weak links, the same knowledge point situation involved in the weak link, and the score situation data of the weak link corresponding to each operation to analyze the risk degree of the weak knowledge point, wherein the corresponding weak knowledge point risk degree analysis formula is: , wherein Si is the risk degree of the i-th weak link, and this formula is used to analyze the risk degree caused by the corresponding weak knowledge point. Through the analysis of the risk degree of the weak knowledge point, those knowledge points which may have a significant impact on the system or operation can be focused on; S35, obtain the sum of the risk degree analysis results of all knowledge points, and then divide the risk degree analysis result of the corresponding knowledge point by the sum of the risk degree analysis results of all knowledge points to obtain the risk degree impact anomaly of the corresponding knowledge point. Through the calculation of the risk degree impact anomaly, the contribution size of each knowledge point to the overall risk degree can be clearly understood, which helps to identify those key knowledge points which have a greater impact on the risk degree of the system or operation; S36, obtain the weak impact anomaly of the corresponding knowledge point and the risk degree impact anomaly of the corresponding knowledge point, and then obtain the importance weight of the corresponding knowledge point after weighted summation, wherein the weighted summation formula is: , wherein, is the weak impact anomaly proportion weight, Ps is a weak influence anomaly of the corresponding knowledge point, and Qs is a dangerous degree influence anomaly, wherein, The weak influence and the dangerous degree influence of the knowledge point are comprehensively considered, and the importance of the knowledge point in the whole system or operation is reflected.

[0011] In an implementation manner of the present application, the course resource matching analysis based on the importance weight analysis of the weak knowledge point in the step S4 comprises the following specific contents: The importance weight of the corresponding knowledge point is obtained, and the corresponding proportion of the course time is arranged for teaching according to the proportion of the importance weight of the corresponding knowledge point in the importance weight of all the knowledge points.

[0012] In a second aspect, the present application further provides an AI education training analysis system based on big data evaluation, comprising: A weak link acquisition module is configured to acquire weak links of corresponding personnel operation from historical operation data; A graph construction module is configured to construct an operation weak link knowledge point graph based on knowledge content related to the weak links; An association analysis module is configured to perform weak knowledge point association analysis based on the operation weak link knowledge point graph to obtain an association of the weak knowledge points; An importance weight analysis module is configured to perform importance weight analysis of the weak knowledge points based on the association of the weak knowledge points and the dangerous degree of the corresponding weak links obtained by evaluation; A course matching analysis module is configured to perform course resource matching analysis based on the importance weight analysis of the weak knowledge points.

[0013] In a third aspect, the present application provides an electronic device, comprising a processor and a memory, wherein the memory stores a computer program that can be called by the processor, and the processor executes an AI education training analysis method based on big data evaluation by calling the computer program stored in the memory.

[0014] In a fourth aspect, the present application provides a computer readable storage medium storing instructions, which, when executed on a computer, cause the computer to execute an AI education training analysis method based on big data evaluation.

[0015] Compared with the prior art, the present application has the following advantages and beneficial effects: The application obtains weak links of corresponding personnel operation from historical operation data, constructs an operation weak link knowledge point graph based on knowledge content related to the weak links, performs weak knowledge point correlation analysis based on the operation weak link knowledge point graph, obtains correlation of the weak knowledge points, performs importance weight analysis of the weak knowledge points based on the correlation of the weak knowledge points and the risk degree of the corresponding weak links obtained by evaluation, performs course resource matching analysis based on the importance weight analysis of the weak knowledge points, evaluates the risk degree of the weak links, and matches the course resources according to the importance weight of the weak knowledge points, so that the personnel can learn and master the key knowledge and skills in time, and the risk of accidents caused by operation failure is reduced. BRIEF DESCRIPTION OF DRAWINGS

[0016] Other features, objects, and advantages of the application will become more apparent from the following detailed description of non-limiting embodiments with reference to the drawings: Figure 1 It is a schematic diagram of the overall process of the method embodiment of the application; Figure 2 It is a schematic diagram of the S3 step process of the method embodiment of the application; Figure 3 It is a schematic diagram of the knowledge point graph structure example of the method embodiment of the application; Figure 4 It is a structural schematic diagram in the system embodiment of the application. DETAILED DESCRIPTION

[0017] In order to make the above-mentioned purposes, features and advantages of the application more apparent and easy to understand, the specific embodiments of the application will be described in detail below with reference to the drawings of the specification.

[0018] In the following description, many specific details are set forth in order to provide a thorough understanding of the application, but the application can also be practiced without these details, which are not described in other ways, and those skilled in the art can make similar generalizations without departing from the scope of the application. Therefore, the application is not limited to the specific embodiments disclosed below.

[0019] Secondly, the "one embodiment" or "embodiment" referred to herein means that the specific features, structures or characteristics can be included in at least one implementation of the application. "In one embodiment" appearing in different places in the specification does not mean the same embodiment, nor is it an embodiment that is separate or selectively excluded from other embodiments.

[0020] Embodiment 1

[0021] As shown in the figure, the present embodiment provides an AI education training analysis method based on big data evaluation, which specifically includes the following steps: Figures 1 to 3 ​Step S1, obtaining weak links of corresponding personnel operation from historical operation data, and constructing operation weak link knowledge point graph based on knowledge content involved in the weak links; In one specific embodiment, step S1 includes the following specific content: S11, the student performs the actual operation step, and the score of each operation step of the student is obtained. The score here can be artificial scoring or machine scoring. The evaluation of the learning degree of the operation step through the conventional rule scoring method is also a conventional technical means, and this is not the main invention point of the present application, so it is not described in detail here. The operation link with a score less than the score threshold is set as the weak link of the corresponding personnel operation. The score threshold is generally set to 60% of the full score, i.e. the passing score. In the prior art, the passing score is generally used to evaluate whether the operation of the student meets the requirements; S12, obtaining the knowledge points involved in the weak links of the corresponding operation stored in the storage module, such as which knowledge points are involved in the weak links of the corresponding operation, or which knowledge structures are needed, for example, the water power unit maintenance operation knowledge points: the knowledge type specific content example is: fluid mechanics (water turbine efficiency curve), material science (runner stainless steel), mechanical dynamics (critical speed calculation) and electrical insulation (partial discharge detection). These operation knowledge points are stored in the corresponding storage component in advance. Based on the obtained knowledge points involved in the weak links of the corresponding operation, the operation weak link knowledge point graph is constructed, and the corresponding knowledge point graph is shown in FIG. 2. Figure 3 Step S2, performing weak knowledge point correlation analysis based on the operation weak link knowledge point graph to obtain the correlation of the weak knowledge points; In one specific embodiment, the weak knowledge point correlation analysis based on the operation weak link knowledge point graph in step S2 includes the following specific steps: S21, obtaining the knowledge points involved in the weak links of each operation of the operation personnel, obtaining the same knowledge points involved in the weak links of each operation, and obtaining the score data corresponding to the weak links of each operation; For example, fluid mechanics (water turbine efficiency curve), mechanical dynamics (critical speed calculation) and electrical insulation (partial discharge detection) are needed in the water power unit impeller maintenance operation and the water power unit shaft maintenance operation. Therefore, the same knowledge points of the water power unit maintenance operation and the water power unit maintenance operation are fluid mechanics (water turbine efficiency curve), mechanical dynamics (critical speed calculation) and electrical insulation (partial discharge detection). S22, performing weak influence analysis of the corresponding knowledge points based on the same knowledge points involved in the weak links of each operation and the score data corresponding to the weak links of each operation, wherein the weak influence formula of the corresponding knowledge points is:​ wherein, mz is the number of weak links related to the corresponding knowledge point, pi is the number of knowledge points related to the i-th weak link of the corresponding knowledge point, Qi is the total score related to the i-th weak link of the corresponding knowledge point, Qwi is the score related to the i-th weak link of the corresponding knowledge point, in the formula, the number of weak links is considered: through the parameter mz, the formula can summarize the influence of the knowledge point in multiple different scenarios, if a knowledge point is related to multiple weak links, then its weak influence value will increase accordingly, which helps to identify key knowledge points that are prone to cause problems in multiple aspects, and the introduction as a weight, can adjust the influence degree of the knowledge point according to the complexity of each weak link, in the weak link with less number of knowledge points, the influence of the knowledge point will be amplified, because it is relatively more important in these links; while in the weak link with more number of knowledge points, its influence will be relatively reduced, directly reflects the loss of each weak link, which can accurately measure the negative influence of the knowledge point on the performance in each specific link, and comprehensively considers the number of knowledge points, total score and actual score of each weak link related to the knowledge point, so as to evaluate the negative influence degree of the knowledge point on the overall performance; S23, after summing up the weak influence results of all knowledge points, the weak influence proportion of the corresponding knowledge point is obtained by dividing the weak influence result of the corresponding knowledge point by the sum of the weak influence of all knowledge points; Step S3, based on the correlation of weak knowledge points and the risk degree of corresponding weak links obtained by evaluation, the importance weight of weak knowledge points is analyzed; In one specific embodiment, the risk degree of the corresponding weak link in step S3 includes the following specific steps: S31, the loss caused by the corresponding failure history of the corresponding weak link and the historical trend of the corresponding failure of the corresponding weak link are obtained, so as to analyze the change trend of the weak link related index with time; S32, based on the loss caused by the corresponding failure history of the corresponding weak link and the historical trend of the corresponding failure of the corresponding weak link, the risk degree of the corresponding weak link is analyzed, wherein the calculation formula of the risk degree of the i-th weak link is: wherein, Ri is the loss caused by the corresponding failure history of the i-th weak link, Rm is the loss caused by all failure history, xt is the number of corresponding failures in the current period, x(t-1) is the number of corresponding failures in the last period, wherein Ri / Rm is the risk degree proportion of the i-th weak link in the historical data to cause dangerous events, and xt / x(t-1) is the historical trend of the corresponding failure.

[0022] In an implementation form of the present application, the importance weight analysis of the weak knowledge points in step S3 comprises the following specific contents: S33, acquire the risk degree of all weak links, and acquire the same knowledge point situation involved in the weak links, the score situation data of the weak links of each operation, and the weak impact proportion weight of the corresponding knowledge points; S34, acquire the risk degree of all weak links, the same knowledge point situation involved in the weak links, and the score situation data of the weak links of each operation, and perform weak knowledge point risk degree analysis, wherein the corresponding weak knowledge point risk degree analysis formula is: , wherein Si is the risk degree of the i-th weak link, which is an index for measuring the risk degree of each specific weak link. Different weak links may cause different degrees of threat to the safety of the entire operation process or system due to different properties, occurrence scenarios, and other factors. This formula is used to analyze the risk degree caused by the corresponding weak knowledge points. Through the analysis of the risk degree of the weak knowledge points, those knowledge points that may have a significant impact on the system or operation can be focused on; S35, after summing the risk degree analysis results of all knowledge points, divide the risk degree analysis result of the corresponding knowledge point by the sum of the risk degree analysis results of all knowledge points to obtain the risk degree impact anomaly of the corresponding knowledge point. Through the calculation of the risk degree impact anomaly, the contribution size of each knowledge point to the overall risk degree can be clearly understood, which helps to identify those key knowledge points that have a greater impact on the risk degree of the system or operation; S36, acquire the weak impact anomaly of the corresponding knowledge point and the risk degree impact anomaly of the corresponding knowledge point, and perform weighted summation to obtain the importance weight of the corresponding knowledge point, wherein the weighted summation formula is: , wherein is the weak impact anomaly proportion weight, is the risk degree impact proportion weight, Ps is the weak impact anomaly of the corresponding knowledge point, and Qs is the risk degree impact anomaly, wherein , which comprehensively considers the weak impact and risk degree impact of the knowledge point and reflects the importance of the knowledge point in the entire system or operation; It should be noted that the weak impact anomaly proportion weight is a pre-set weight value, and the value range is usually between 0 and 1, indicating the proportion of the weak impact anomaly in the calculation of the importance weight of the knowledge point, which reflects the importance of the weak knowledge of the students. The risk degree impact proportion weight is also a pre-set weight value, and the value range is between 0 and 1, and satisfies , it represents the proportion of abnormal degree of dangerous degree in the calculation of the importance weight of knowledge points, and reflects the importance of the importance of knowledge points, and the acquisition method can be expert experience method: invite experienced experts, scholars or practitioners with rich practical experience in this field, determine the two weights according to their years of professional knowledge and practical experience, these experts have a deeper understanding of the importance of each knowledge point and the possible impact in the industry, can comprehensively consider from the macro and micro levels, give relatively reasonable weight suggestion, in the specific operation, invited 5 experts, the values given by them are 0.5, 0.6, 0.55, 0.65, 0.58, then the average value (0.5+0.6+0.55+0.65+0.58) ÷5=0.576 can be taken as the final value; Step S4, course resource matching analysis based on importance weight analysis of weak knowledge points; In one specific embodiment, the following specific contents are included: The importance weight of the corresponding knowledge point calculated is obtained, and the corresponding proportion of course time is arranged for teaching according to the proportion of the importance weight of the corresponding knowledge point among the importance weights of all knowledge points, for example, the importance weight proportion of fluid mechanics knowledge point is 0.2, so 0.2 times the total course time is arranged for fluid mechanics knowledge point teaching; It needs to be explained in this embodiment that this embodiment has the following advantages and advantages: obtaining the weak link of corresponding personnel operation from historical operation data, constructing operation weak link knowledge point graph based on the knowledge content involved in the weak link, performing weak knowledge point correlation analysis based on the operation weak link knowledge point graph, obtaining the correlation of weak knowledge points, performing importance weight analysis of weak knowledge points based on the correlation of weak knowledge points and the risk degree of the corresponding weak link obtained by evaluation, performing course resource matching analysis based on the importance weight analysis of weak knowledge points, evaluating the risk degree of the weak link, and matching the course resources according to the importance weight of the weak knowledge points, so that the personnel can learn and master the key knowledge and skills in time, and reduce the risk of accidents caused by operation errors.

[0023] Embodiment 2

[0024] As shown in Figure 4 , the present embodiment provides an AI education and training analysis system based on big data evaluation, which is realized based on the AI education and training analysis method based on big data evaluation in embodiment 1, comprising: a weak link acquisition module for obtaining the weak link of corresponding personnel operation from historical operation data; A graph construction module constructs an operation weak link knowledge point graph based on the knowledge content involved in the weak link;​ The correlation situation analysis module performs weak knowledge point correlation analysis based on the weak link knowledge point graph, and obtains the correlation situation of the weak knowledge points; The importance weight analysis module performs weak knowledge point importance weight analysis based on the correlation situation of the weak knowledge points and the risk degree of the corresponding weak links obtained through evaluation; The course matching analysis module performs course resource matching analysis based on the importance weight analysis of the weak knowledge points. The specific steps of each module of the embodiment of the system are as described in the specific steps of the method embodiment of the embodiment 1, and will not be repeated here.

[0025] Embodiment 3

[0026] The electronic device of the embodiment of the application comprises a processor and a memory, wherein the memory stores a computer program that can be called by the processor, and the processor executes the AI education training analysis method based on big data evaluation by calling the computer program stored in the memory. It should be noted that all computer programs of the AI education training analysis method based on big data evaluation are implemented using C language.

[0027] Embodiment 4

[0028] The embodiment provides a computer readable storage medium, which stores an erasable computer program. When the computer program runs on the computer device, the computer device executes the AI education training analysis method based on big data evaluation described above.

[0029] The above embodiments can be realized by software, hardware, firmware or any combination thereof, in whole or in part. When realized by software, the above embodiments can be realized in the form of a computer program product in whole or in part. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the flow or function according to the embodiment of the application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network or other programmable devices. The computer instructions can be stored in a computer readable storage medium or transferred from one computer readable storage medium to another, for example, the computer instructions can be transferred from one website, computer, server or data center to another website, computer, server or data center through a wired network or / and a wireless network. The computer readable storage medium can be any available medium accessible by a computer or a data storage device such as a server, data center and the like containing one or more available medium sets. The available medium can be a magnetic medium (e.g. floppy disk, hard disk, magnetic tape), an optical medium (e.g. DVD) or a semiconductor medium. The semiconductor medium can be a solid state disk.

[0030] Those skilled in the art can clearly understand that the units and algorithm steps of each example described in combination with the embodiments disclosed in the present application can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0031] Those skilled in the art can clearly understand that, for the convenience and brevity of the description, the specific working processes of the above-described system, device and unit can refer to the corresponding processes in the foregoing method embodiments, which will not be repeated here.

[0032] In several embodiments provided by the present application, it should be understood that the disclosed system, device and method can be realized by other ways. For example, the device embodiments described above are only schematic, and the division of units is only one, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interface, device or unit, and can be electrical, mechanical or other forms.

[0033] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be 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 embodiment.

[0034] In addition, each functional unit in each embodiment of the present application can be integrated into a processing unit, or each unit can exist physically, or two or more units can be integrated into one unit.

[0035] In the description of the specification, the description of the terms "one embodiment", "example", "specific example" and the like means that the specific features, structures, materials or characteristics described in combination with the embodiment or example are included in at least one embodiment or example of the present application. In the specification, the illustrative description of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0036] The above shows and describes the basic principles and main features of the present application and the advantages of the present application. Those skilled in the art should understand that the present application is not limited to the above embodiments, and the above embodiments and descriptions in the specification are only to illustrate the principles of the present application. Without departing from the spirit and scope of the present application, various changes and improvements can be made to the present application, and these changes and improvements all fall within the scope of the claimed present application. The scope of protection of the present application is defined by the appended claims and their equivalents.

Claims

1. An AI-based education and training analysis method based on big data evaluation, characterized in that: Includes the following steps: Step S1: Identify the weak points in the operation of the corresponding personnel from historical operation data, and construct a knowledge point map of the weak points based on the knowledge content involved in the weak points. Step S2: Based on the knowledge point map of operational weaknesses, perform correlation analysis on the weak knowledge points to obtain the correlation status of the weak knowledge points; Step S3: Based on the correlation of weak knowledge points and the risk level of the corresponding weak links obtained from the assessment, conduct an importance weight analysis of the weak knowledge points; Step S4: Conduct course resource matching analysis based on the importance weight analysis of weak knowledge points.

2. The AI ​​education and training analysis method based on big data evaluation according to claim 1, characterized in that, Step S2 involves performing a correlation analysis of weak knowledge points based on the knowledge point map of operational weaknesses, including the following specific steps: The system identifies the knowledge points involved in each operator's weak points, identifies the common knowledge points involved in each operator's weak points, and also obtains the score data corresponding to each operator's weak points. Based on the common knowledge points involved in the weak links of each operation and the corresponding score data of each operation, we conduct a weak impact analysis on the corresponding knowledge points. After summing the results of the weak impact of all knowledge points, the percentage of the weak impact of the corresponding knowledge point is obtained by dividing the result of the weak impact of the corresponding knowledge point by the sum of the results of the weak impact of all knowledge points.

3. The AI ​​education and training analysis method based on big data evaluation according to claim 1, characterized in that, The degree of danger corresponding to the weak link in step S3 includes the following specific steps: Obtain the historical losses caused by the corresponding failures of the corresponding weak links, as well as the historical trends of the corresponding failures of the corresponding weak links. The risk level of the corresponding weak link is analyzed based on the historical losses caused by the corresponding failures in the corresponding weak link and the historical trend of the corresponding failures in the corresponding weak link.

4. The AI ​​education and training analysis method based on big data evaluation according to claim 3, characterized in that, The importance weight analysis of weak knowledge points in step S3 includes the following specific contents: Obtain the risk level of all weak links, and at the same time obtain the situation of the same knowledge points involved in the weak links, the score data of the weak links of each operation, and the weight of the weak impact of the corresponding knowledge points. To analyze the risk level of weak knowledge points, we need to obtain data on the risk level of all weak links, the common knowledge points involved in the weak links, and the scores corresponding to the weak links in each operation. After summing the risk level analysis results of all knowledge points, the risk level impact anomaly of the corresponding knowledge point is obtained by dividing the risk level analysis result of the corresponding knowledge point by the sum of the risk level analysis results of all knowledge points. The importance weight of the corresponding knowledge point is obtained by acquiring the anomalies of the weakness of the knowledge point and the anomalies of the danger of the knowledge point, and then summing them by weight.

5. The AI ​​education and training analysis method based on big data evaluation according to claim 1, characterized in that, Step S4, which involves course resource matching analysis based on the importance weight analysis of weak knowledge points, includes the following specific content: Obtain the calculated importance weight of the corresponding knowledge point, and arrange the corresponding proportion of class time for teaching according to the proportion of the importance weight of all knowledge points.

6. The AI ​​education and training analysis method based on big data evaluation according to claim 2, characterized in that, The formula for the weak impact of the corresponding knowledge point is: Where mz is the number of weak points related to the corresponding knowledge point, pi is the number of knowledge points related to the i-th weak point of the corresponding knowledge point, Qi is the total score related to the i-th weak point of the corresponding knowledge point, and Qwi is the score related to the i-th weak point of the corresponding knowledge point.

7. The AI ​​education and training analysis method based on big data evaluation according to claim 1, characterized in that, Step S1 includes the following specific contents: Trainees perform actual operation steps, and scores are obtained for each step. To obtain the knowledge points involved in the weak links of the corresponding operations stored in the storage module.

8. An AI-based education and training analysis system based on big data evaluation, implemented according to any one of claims 1-7, characterized in that, The system includes: The vulnerability identification module is used to identify the vulnerabilities in the operations of corresponding personnel from historical operation data; The graph construction module constructs a knowledge point graph of operational weaknesses based on the knowledge content involved in the weak links. The correlation analysis module performs correlation analysis on weak knowledge points based on the knowledge point graph of operational weaknesses, and obtains the correlation status of weak knowledge points. The importance weight analysis module analyzes the importance weight of weak knowledge points based on their correlation with each other and the risk level of the corresponding weak links as assessed. The course matching analysis module performs course resource matching analysis based on the importance weight analysis of weak knowledge points.

9. An electronic device, comprising: A processor and a memory, wherein the memory stores a computer program that can be called by the processor; characterized in that the processor executes the AI ​​education and training analysis method based on big data evaluation as described in any one of claims 1-7 by calling the computer program stored in the memory.

Images