Nuclear power operation license personnel capability improvement method and system based on AI big language model, medium and equipment

Abstract

The invention relates to a nuclear power operation licensor capability improvement method and system based on an AI big language model, a medium and equipment. The method comprises the following steps: S1, acquiring learning information of students from a nuclear power operation license personnel training platform; and S2, processing the learning information based on an AI large language model to generate an evaluation report. And S3, related materials are retrieved from a pre-constructed nuclear power special knowledge base according to the evaluation report to form personalized training course items, and the personalized training course items are pushed. According to the invention, more accurate, refined and personalized services can be provided for ability training, evaluation and maintenance of operation licenses, the SAT systematized training efficiency and training effect can be greatly improved, and the safety and operation performance of a power plant are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of personnel training and ability assessment in nuclear power plants, and particularly to a method, system, medium and device for improving the ability of nuclear power operation license personnel based on an AI large language model. Background Art

[0002] In the context of the rapid development of new nuclear power projects, the cultivation and reserve of talents in the nuclear power field have become increasingly important. Especially for nuclear power plant operation license personnel, the contradiction between the demand for operation license personnel in nuclear power plants and the shortage of talents is becoming increasingly large. Due to the wide range of knowledge, complex systems and high difficulty that operation license personnel need to learn, the cycle for cultivating an operation license personnel is very long.

[0003] The traditional cultivation of operation license personnel is based on the traditional SAT systematic training method, and the cultivation and maintenance of personnel capabilities are realized through the process of training - assessment - authorization - on - the - job. Training instructors need to invest a large amount of manpower and energy in training and assessing students. Due to limited human resources, instructors focus more of their energy on the training and instillation of knowledge, resulting in deficiencies in training assessment and feedback. Furthermore, it is impossible to provide personalized and precise training for each student, which is a pain point in the current training of operation license personnel. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to provide a method, system, medium and device for improving the ability of nuclear power operation license personnel based on an AI large language model, aiming at the deficiencies in the assessment and feedback of the traditional cultivation method for nuclear power operation license personnel.

[0005] The technical solution adopted by the present invention to solve its technical problems is: A method for improving the ability of nuclear power operation license personnel based on an AI large language model, comprising the following steps:

[0006] S1. Obtain the learning information of students from the training platform for nuclear power operation license personnel;

[0007] S2. Process the learning information based on the AI large language model to generate an assessment report;

[0008] S3. Retrieve relevant materials from a pre - constructed nuclear power dedicated knowledge base according to the assessment report to form a personalized training course project and push it.

[0009] Further, in the method for improving the ability of nuclear power operation license personnel based on an AI large language model of the present invention, the assessment report includes weak knowledge points and knowledge points to be improved. Step S3 includes:

[0010] Retrieve relevant learning materials and assessment materials from the nuclear power special knowledge base according to the weak knowledge points and / or the knowledge points to be improved, so as to organize and form a personalized training course project for the trainee, and push it through the trainee's learning terminal.

[0011] Further, in the method for improving the capabilities of nuclear power operation license holders based on the AI large language model of the present invention, after step S3, it further includes:

[0012] After the trainee completes the personalized training course project, steps S1 to S2 are executed again, and the generated evaluation report is used as the learning information for the next stage of training, so that the platform can push the training content for the next stage until all training sessions are completed and the license is obtained.

[0013] Further, in the method for improving the capabilities of nuclear power operation license holders based on the AI large language model of the present invention, the AI large language model is mounted with the nuclear power special knowledge base, and step S2 includes:

[0014] Send the learning information to the AI large language model, and make it analyze, sort out and summarize the learning information based on the nuclear power special knowledge base to generate an evaluation report.

[0015] Further, in the method for improving the capabilities of nuclear power operation license holders based on the AI large language model of the present invention, the learning information includes learning progress, assessment situation, and wrong question set.

[0016] Further, in the method for improving the capabilities of nuclear power operation license holders based on the AI large language model of the present invention, the nuclear power special knowledge base includes procedures, teaching materials, working documents, and assessment documents in the field of nuclear power operation.

[0017] Further, in the method for improving the capabilities of nuclear power operation license holders based on the AI large language model of the present invention, the content of the evaluation report includes the current trainee's learning progress, analysis information on the mastery of knowledge points, analysis information on wrong questions, weak knowledge points and / or knowledge points to be improved.

[0018] In addition, the present invention also provides a system for improving the capabilities of nuclear power operation license holders based on the AI large language model, including:

[0019] A learning information collection module for obtaining the learning information of trainees from the nuclear power operation license holder training platform;

[0020] An AI large language model analysis and evaluation module for processing the learning information to generate an evaluation report;

[0021] The practice push module is used to retrieve relevant materials from a pre - constructed nuclear power - specific knowledge base according to the evaluation report, form personalized training course items, and push them.

[0022] In addition, the present invention also provides a computer - readable storage medium. The computer - readable storage medium stores a computer program, and the computer program is suitable for being loaded by a processor to execute the steps of the method for improving the capabilities of nuclear power operation license holders based on an AI large - language model as described above.

[0023] In addition, the present invention also provides a computer device, including a memory and a processor. A computer program is stored in the memory, and the processor executes the steps of the method for improving the capabilities of nuclear power operation license holders based on an AI large - language model as described above by calling the computer program stored in the memory.

[0024] Implementing the method, system, medium, and device for improving the capabilities of nuclear power operation license holders based on an AI large - language model of the present invention has the following beneficial effects: By utilizing the powerful text understanding, generation, summarization, and reasoning capabilities of the AI large - language model, the present invention can provide more accurate, refined, and personalized services for the capacity training, evaluation, and maintenance of operation license holders, greatly improving the efficiency and effect of SAT systematic training, and enhancing the safety and business performance of power plants. Brief Description of the Drawings

[0025] The present invention will be further described below in conjunction with the drawings and embodiments. In the drawings:

[0026] Figure 1 is a schematic flowchart of the method for improving the capabilities of nuclear power operation license holders based on an AI large - language model provided by an embodiment of the present invention;

[0027] Figure 2 is a schematic flowchart of the method for improving the capabilities of nuclear power operation license holders based on an AI large - language model provided by an embodiment of the present invention;

[0028] Figure 3 is a schematic structural diagram of the system for improving the capabilities of nuclear power operation license holders based on an AI large - language model provided by an embodiment of the present invention. Detailed Embodiments

[0029] In order to have a clearer understanding of the technical features, objectives, and effects of the present invention, the specific embodiments of the present invention will now be described in detail with reference to the accompanying drawings. In the following description, it should be understood that the orientation or positional relationships indicated by terms such as "front", "rear", "upper", "lower", "left", "right", "longitudinal", "transverse", "vertical", "horizontal", "top", "bottom", "inner", "outer", "head", "tail", etc. are based on the orientation or positional relationships shown in the drawings and are constructed and operated in a specific orientation, and are only for the convenience of describing the present technical solution, rather than indicating that the indicated device or element must have a specific orientation. Therefore, it should not be construed as a limitation of the present invention.

[0030] It should also be noted that, unless otherwise clearly specified and defined, terms such as "install", "connect", "join", "fix", "set", etc. should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or integrated; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, and it can be the communication inside two elements or the interaction relationship between two elements. When an element is referred to as being "on" or "under" another element, the element can be "directly" or "indirectly" located above the other element, or there may also be one or more intermediate elements. Terms such as "first", "second", "third", etc. are only for the convenience of describing the present technical solution and cannot be understood as indicating or implying relative importance or implicitly indicating the quantity of the indicated technical features. Thus, the features defined with "first", "second", "third", etc. can explicitly or implicitly include one or more of such features. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0031] In the following description, specific details such as specific system structures and technologies are presented for the purpose of illustration rather than limitation, so as to thoroughly understand the embodiments of the present invention. However, those skilled in the art should clearly understand that the present invention can also be implemented in other embodiments without these specific details. In other cases, the detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from interfering with the description of the present invention.

[0032] Referring to Figure 1 , in one embodiment of the present invention, the method for improving the capabilities of nuclear power operation license personnel based on an AI large language model in this embodiment includes the following steps:

[0033] S1. Obtain the learning information of the trainees from the nuclear power operation license personnel training platform. It can be understood that in this step, the learning information of the trainees is obtained to get the initial data of the current learning progress and situation of the trainees. This data includes, but is not limited to, information such as learning progress, assessment situation, wrong question sets, and stage evaluations. Some data is provided by the users independently, such as the learning progress, which can be specifically input into the training platform (or training system) by the users through the user terminal, and the rest of the data is automatically recorded by the system in all links, such as assessment information, wrong question sets, stage evaluation information (including personal self-assessment information, weak knowledge points, knowledge points to be improved), etc.

[0034] S2. Process the learning information based on the AI large language model to generate an assessment report. It can be understood that in this step, the AI large language model analyzes, sorts out, and summarizes according to the learning information to form an assessment report. That is, using the intelligent analysis and text generation capabilities of the AI large language model to generate an assessment report. Optionally, the content of the assessment report includes the current learning progress of the trainees, information on the analysis of knowledge point mastery, analysis of wrong questions, weak knowledge points, knowledge points to be improved, suggestions for the next stage of learning, and so on.

[0035] Specifically, the AI large language model is mounted with a nuclear power dedicated knowledge base. In step S2, the learning information is sent to the AI large language model, enabling it to analyze, sort out, and summarize the learning information based on the nuclear power dedicated knowledge base to generate an assessment report.

[0036] It can be understood that the AI large language model (Artificial Intelligence Large Language Model) is a neural network model based on deep learning, usually using the Transformer architecture, and trained with a large amount of text data to learn the patterns and structures of language. These models can generate natural language text and perform well in various natural language processing tasks, such as text generation, machine translation, question answering systems, text classification, etc. The AI large language model includes, but is not limited to, the GPT series (Generative Pre-trained Transformer), BERT series (Bidirectional Encoder Representations from Transformers), T5 (Text-to-Text Transfer Transformer), LLaMA (Large Language Model Application), Kimi, Claude, Morpheus, etc.

[0037] Before using the AI large language model, it is necessary to establish a nuclear power-specific knowledge base for it so that it can become an expert in the field of nuclear power operation and understand the specific knowledge and terminology in the nuclear power field. Specifically, materials such as procedures, teaching materials, working documents, and assessment documents in the field of nuclear power operation are sent into the AI large language model for knowledge fine-tuning and memorization to form a nuclear power-specific knowledge base. That is, the nuclear power-specific knowledge base includes, but is not limited to, procedures, teaching materials, working documents, assessment documents, etc. in the field of nuclear power operation. After the nuclear power-specific knowledge base is established, the learning information of the trainees is transmitted to the AI large language model, and through the analysis and sorting functions of the AI large language model, the current assessment report of the trainees is generated.

[0038] In some embodiments, the AI large language model can adopt a reasoning large language model. It should be noted that the reasoning large language model is a subclass of the AI large language model. The Reasoning Large Language Model is a neural network model based on deep learning, usually based on the Transformer architecture, pre-trained with a large amount of text data to learn the patterns and structures of language, and specifically designed for logical reasoning and complex problem-solving. Such models can not only generate natural language text but also demonstrate reasoning capabilities when dealing with problems, such as understanding causal relationships, conducting logical deductions, and solving mathematical problems. The reasoning large language model is usually pre-trained on a large scale of text data and fine-tuned through specific reasoning tasks to improve its performance in reasoning tasks.

[0039] S3. Retrieve relevant materials from the pre-established nuclear power-specific knowledge base according to the assessment report to form a personalized training course project and push it. In some embodiments, step S3 includes: retrieving relevant learning materials and assessment materials from the nuclear power-specific knowledge base according to the weak knowledge points and / or the knowledge points to be improved to organize and form a personalized training course project for the trainee, and push it through the trainee's learning terminal.

[0040] It can be understood that in this step, the system pushes the training course project according to the results of the assessment report for the weak knowledge points or the knowledge points to be improved of the trainees for the trainees to learn online. The weak points and the points to be improved of the trainees are sorted out through the AI large language model, then relevant materials are retrieved from the nuclear power-specific knowledge base, and then the materials are organized into learning materials and assessment materials (personalized training course project) and pushed through the trainee's learning terminal. The trainees can learn anytime and anywhere, which conforms to the scenarios and habits of enterprise employees' learning and provides a more convenient and efficient learning platform.

[0041] In some embodiments, refer to Figure 2, after step S3, it further includes: S4. After the trainee completes the personalized training course project, steps S1 to S2 are executed again, and the generated evaluation report is used as the learning information for the next stage of training, so that the platform can push the training content for the next stage until all training sessions are completed and the license is obtained. That is, when the training includes multiple stages, the evaluation report generated in each stage can be used as the learning information for the next training stage. The training platform can combine the learning information of the previous stage to generate the training learning materials for the next training stage or session. And so on. Until all training sessions are completed and ended, and the license is obtained.

[0042] It can be understood that in this step, when the training, assessment, etc. of the personalized training course project are completed, the learning information of the trainee is analyzed and evaluated again to form an evaluation report. That is, after the learning of the current stage is completed, the AI large language model continuously collects and monitors information through the background, then sorts out and summarizes, analyzes and evaluates again to form an evaluation report, and the evaluation report generated this time becomes the learning information of the trainee for the next stage, which is provided to the system for accurate learning material push. Through the closed-loop operation of these four steps in the embodiment of the present invention, the learning effect of the trainee can be quickly improved.

[0043] The technical effects of this embodiment are as follows: (1) Automatically collect the learning situation information of the whole process of the trainee's learning, change the way of manually collecting the trainee's learning information in the traditional mode, and improve the monitoring efficiency of the training process. (2) Realize the real-time and automatic evaluation of the trainee's learning effect, change the traditional modes such as classroom quizzes and stage tests, and perform background evaluation and analysis by the AI large language model to give the trainee's current learning effect and learning suggestions in real time, improving the pertinence and accuracy of training. (3) Realize the intelligent push of training and assessment materials. Through the intelligent analysis, summary and push functions of the AI language model, the training materials can be accurately sorted out for the trainee's knowledge weak points or abilities to be improved, and then quickly pushed to the front end of the trainee's learning, realizing learning, testing and mastering what is desired immediately, greatly improving the training effect.

[0044] Reference Figure 3 , in one embodiment of the present invention, the nuclear power operation license personnel ability improvement system based on the AI large language model of this embodiment includes: a learning information collection module for obtaining the trainee's learning information from the nuclear power operation license personnel training platform. An AI large language model analysis and evaluation module for processing the learning information to generate an evaluation report. A practice push module for retrieving relevant materials from a pre-constructed nuclear power special knowledge base according to the evaluation report to form a personalized training course project and push it.

[0045] It is understandable that the trainee information collection module is responsible for the automatic collection and summary of trainee information in this system, which is used to obtain the initial data of the trainee's current learning progress and situation. These data include learning progress, assessment situation, wrong questions, and stage evaluation, etc. Some data are provided by users themselves, such as learning progress, and the rest of the data are automatically recorded by the system in all links, such as assessment information, weak knowledge points, and items to be improved in the next stage, etc.

[0046] The AI large language model analysis and evaluation module analyzes, sorts out, and summarizes according to the learning information to form an evaluation report. In this stage, the intelligent analysis and text generation capabilities of the AI large language model are used for generation. Before using the AI large language model analysis and evaluation module, it is necessary to establish a knowledge model for it so that it can become an expert in the field of nuclear power operation and understand the specialized knowledge and terms in the nuclear power field. By sending materials such as procedures, teaching materials, work files, and assessment files in the field of nuclear power operation into the AI large language model for knowledge fine-tuning and memory to form a nuclear power-specific knowledge base. After the nuclear power-specific knowledge base is established, the trainee learning information is transmitted to the AI large language model. Through the analysis and sorting of the AI large language model, the current evaluation report of the trainee is generated, which includes the current trainee's learning progress, analysis of knowledge point mastery, wrong question analysis, and learning suggestions for the next stage, etc.

[0047] The practice push module pushes training course items according to the results of the evaluation report for the trainee's weak items or items to be improved, and the trainee conducts online learning. The AI large language model analysis and evaluation module sorts out the trainee's weak items and items to be improved, then retrieves relevant learning materials from the knowledge base model, and then organizes the materials into learning materials and assessment materials, which are pushed through the trainee learning front end. The trainee can learn anytime and anywhere, which fits the learning scenarios and habits of enterprise employees and provides a more convenient and efficient learning platform.

[0048] In this embodiment, the AI large language model monitors the entire process of training for operating license personnel, analyzes the knowledge weak points of trainees in a timely manner, accurately generates methods for improving weak points and learning materials, quickly generates trainee learning analysis reports, and then pushes knowledge based on the feedback results of the reports, forming a closed loop of spiral upward ability cultivation. According to this method, an APP system for operating license personnel and training instructors is developed. This system is compatible with multi-terminal access technologies and enables multi-terminal access such as mobile phones and computers, allowing learning and ability improvement anytime and anywhere. Compared with the traditional teaching mode, the embodiment of the present invention can, on the one hand, release teacher resources, reduce the daily repetitive work burden of teachers, and enable them to invest more energy in training effects and ability improvement. On the other hand, by pushing precise and personalized training programs to trainees, it can improve the cultivation effect and efficiency of operating license personnel, ensure that the quantity and quality of nuclear power plant operating license personnel meet the needs of nuclear power development, and improve the safety and business performance of the power plant.

[0049] In one embodiment of the present invention, the computer-readable storage medium of this embodiment stores a computer program, and the computer program is suitable for being loaded by a processor to execute the steps of the method for improving the ability of nuclear power operating license personnel based on the AI large language model as described in the above embodiment.

[0050] In one embodiment of the present invention, the computer device of this embodiment includes a memory and a processor. The memory stores a computer program, and the processor executes the steps of the method for improving the ability of nuclear power operating license personnel based on the AI large language model as described in the above embodiment by calling the computer program stored in the memory.

[0051] The computer-readable storage medium of the present invention can be various computer-readable storage media such as USB flash drives, mobile hard disks, read-only memories (ROMs), magnetic disks, or optical discs that can store program codes.

[0052] The processor of the present invention is used to provide computing and control capabilities to support the operation of the entire system. It should be understood that in the embodiments of the present application, the processor may be a Central Processing Unit (CPU), and the processor may also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0053] Those skilled in the art can further realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of the two. To clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described according to functions in the above description. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0054] The steps of the method or algorithm described in combination with the embodiments disclosed herein can be directly implemented by hardware, a software module executed by a processor, or a combination of the two. The software module can be placed in a Random Access Memory (RAM), internal memory, Read Only Memory (ROM), Electrically Programmable ROM, Electrically Erasable Programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium well-known in the technical field.

[0055] It can be understood that the above embodiments only represent the preferred embodiments of the present invention, and the description is relatively specific and detailed, but it should not be construed as a limitation on the scope of the patent of the present invention; it should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, the above technical features can be freely combined, and several deformations and improvements can also be made, which all belong to the protection scope of the present invention; therefore, all equivalent transformations and modifications made to the scope of the claims of the present invention shall fall within the scope covered by the claims of the present invention.

Claims

1. A method for improving the capabilities of nuclear power operation license personnel based on AI large language models, characterized in that, It includes the following steps: S1. Obtain the learning information of the trainees from the training platform for nuclear power operation license holders; S2. Process the learning information based on the AI large language model to generate an evaluation report; S3. Retrieve relevant materials from the pre-constructed nuclear power-specific knowledge base according to the evaluation report to form a personalized training course project and push it.

2. The method for improving the capabilities of nuclear power operation license holders based on the AI large language model according to claim 1, wherein, The evaluation report includes weak knowledge points and knowledge points to be improved. Step S3 includes: Retrieve relevant learning materials and assessment materials from the nuclear power-specific knowledge base according to the weak knowledge points and / or the knowledge points to be improved, organize and form a personalized training course project for this trainee, and push it through the trainee's learning terminal.

3. The method for improving the capabilities of nuclear power operation license holders based on the AI large language model according to claim 1, wherein After step S3, it further includes: When the trainee completes the personalized training course project, execute steps S1 to S2 again, and the generated evaluation report is used as the learning information for the next stage of training, so that the platform can push the training content for the next stage until all training sessions are completed and the license is obtained.

4. The method for improving the capabilities of nuclear power operation license holders based on the AI large language model according to claim 1, wherein The AI large language model is mounted with the nuclear power-specific knowledge base. Step S2 includes: Send the learning information to the AI large language model, and make it analyze, sort out and summarize the learning information based on the nuclear power-specific knowledge base to generate an evaluation report.

5. The method for improving the capabilities of nuclear power operation license holders based on the AI large language model according to claim 1, wherein The learning information includes learning progress, assessment situation, and wrong question set.

6. The method for improving the capabilities of nuclear power operation license holders based on the AI large language model according to claim 1, wherein The nuclear power-specific knowledge base includes procedures, teaching materials, working documents, and assessment documents in the field of nuclear power operation.

7. The method for improving the capabilities of nuclear power operation license personnel based on the AI large language model according to claim 1, wherein The content of the evaluation report includes the learning progress of the current trainee, information on the analysis of knowledge point mastery, information on the analysis of wrong questions, weak knowledge points and / or knowledge points to be improved.

8. A nuclear power operation license personnel ability improvement system based on an AI large language model, characterized in that, It includes: A learning information collection module for obtaining the learning information of the trainees from the training platform for nuclear power operation license holders; An AI large language model analysis and evaluation module for processing the learning information to generate an evaluation report; A practice push module for retrieving relevant materials from the pre-constructed nuclear power-specific knowledge base according to the evaluation report to form a personalized training course project and push it.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, and the computer program is suitable for being loaded by a processor to execute the steps of the method for improving the capabilities of nuclear power operation license holders based on an AI large language model according to any one of claims 1 to 7.

10. A computer device, characterized in that, It includes a memory and a processor. The memory stores a computer program, and the processor executes the steps of the method for improving the capabilities of nuclear power operation license holders based on an AI large language model according to any one of claims 1 to 7 by calling the computer program stored in the memory.

Images