Log management method and system based on nuclear power personnel management
Through real-time data analysis and task log management, combined with evaluation and learning models, timely monitoring and security threat detection of nuclear power personnel operations are achieved, solving the problem that existing methods cannot effectively detect operational personnel operations, and improving safety and employee skills.
Patent Information
- Application Number
- CN202411685391.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-22
- Publication Date
- 2025-04-29
AI Technical Summary
The existing nuclear power personnel management methods cannot achieve timely and effective detection of operation personnel, resulting in the inability to effectively monitor and early warning of potential security threats.
By obtaining real-time data from the sensor network, extracting staff's characteristic parameters, performing analysis mechanisms to detect potential security threats, and generating task logs for visual presentation, while establishing evaluation learning models to achieve staff evaluation and training.
Real-time monitoring of nuclear power personnel operations and timely detection of safety threats has been achieved, operational safety has been improved, and through personalized training paths and performance evaluation, employees' skills and team collaboration efficiency have been enhanced.
Smart Images
Figure CN119904129A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of nuclear power plant operation management, and in particular to a log management method and system based on nuclear power personnel management. Background Art
[0002] The log management of nuclear power personnel management is not only related to the operational safety of nuclear power plants, but also closely related to the economic benefits of nuclear power plants. At present, the nuclear power industry has adopted a number of advanced technologies and methods in the log system of personnel management to improve management efficiency and ensure operational safety;
[0003] In the prior art, although the system includes historical playback and log query functions based on the KNS system, these functions rely on manual inspections. Detecting abnormal operations requires personnel with senior background knowledge and understanding of the specific operating status of the unit. The workload is huge, and it is impossible to achieve timely and effective detection of the operations of the operating personnel. At the same time, the threshold of the monitored parameter variable is used to monitor the abnormality or diagnose the fault of nuclear power equipment. When faced with complex data interfaces and multivariate data, this method is too simple and the evaluation effect is poor. Most of them focus on the matching between preventive maintenance and fault maintenance, but often adopt a conservative regular parts replacement strategy, which has the problem of over-maintenance. A more reasonable maintenance strategy should gradually increase the maintenance means or frequency as the product ages. Therefore, we propose a log management method based on nuclear power personnel management. Summary of the invention
[0004] In view of the above-mentioned problems, the present invention is proposed.
[0005] Therefore, the technical problem solved by the present invention is that the existing management method cannot realize timely and effective detection of the operation of the operating personnel.
[0006] To solve the above technical problems, the present invention provides the following technical solutions: a log management method based on nuclear power personnel management, comprising: acquiring real-time data of a sensor network; extracting characteristic parameters of staff members according to the real-time data, and executing a first analysis mechanism to obtain analysis results; generating task logs based on the characteristic parameters of staff members and performing visual display, and establishing an evaluation learning model to realize evaluation training of staff members.
[0007] As a preferred solution of the log management method based on nuclear power personnel management described in the present invention, wherein: the acquisition of real-time data of the sensor network includes preprocessing and standardizing the collected real-time data.
[0008] As a preferred solution of the log management method based on nuclear power personnel management described in the present invention, the characteristic parameters of the staff include parameters reflecting the status of the staff and the environment in which they are located.
[0009] As a preferred solution of the log management method based on nuclear power personnel management described in the present invention, wherein: the first analysis mechanism includes detecting potential security threats based on characteristic parameters of the staff.
[0010] As a preferred solution of the log management method based on nuclear power personnel management described in the present invention, the task log includes task data of individual staff members and teams.
[0011] As a preferred solution of the log management method based on nuclear power personnel management described in the present invention, wherein: the evaluation learning model includes a front-end user unit and a back-end management unit.
[0012] As a preferred solution of the log management method based on nuclear power personnel management described in the present invention, wherein: the front-end user unit includes but is not limited to generating a personalized training path based on the characteristic parameters of the staff; the back-end management unit includes but is not limited to updating the training content and evaluating the training results of the staff.
[0013] A log management system based on nuclear power personnel management using any of the methods described in the present invention, wherein: a collection module obtains real-time data from a sensor network and performs preprocessing; an analysis module extracts characteristic parameters of staff members based on real-time data, and implements safety detection and early warning through a first analysis mechanism; a training module generates task logs based on the characteristic parameters of staff members and displays them visually, and establishes an evaluation learning model to implement evaluation training for staff members.
[0014] A computer device comprises: a memory and a processor; the memory stores a computer program, comprising: the steps of implementing any one of the methods of the present invention when the processor executes the computer program.
[0015] A computer-readable storage medium stores a computer program, comprising: when the computer program is executed by a processor, the steps of implementing any one of the methods of the present invention are implemented.
[0016] Beneficial effects of the invention: The method of the invention realizes the intelligent and efficient management of nuclear power personnel by combining sensor networks, real-time data analysis and log management. Its innovation lies in the multi-dimensional dynamic monitoring of personnel behavior status and working environment, which can detect security threats in real time and trigger early warnings, effectively improving operational safety. At the same time, through the visualization of task logs and the evaluation learning model, it provides personalized training paths and performance evaluation, enhancing employee skill levels and team collaboration efficiency. BRIEF DESCRIPTION OF THE DRAWINGS
[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them:
[0018] Figure 1 An overall flow chart of a log management method based on nuclear power personnel management provided by an embodiment of the present invention;
[0019] Figure 2 A basic architecture diagram of a log management system of a log management method based on nuclear power personnel management provided in the third embodiment of the present invention. DETAILED DESCRIPTION
[0020] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.
[0021] Example 1, reference Figure 1 , as an embodiment of the present invention, provides a log management method based on nuclear power personnel management, comprising:
[0022] S1: Obtain real-time data from the sensor network.
[0023] Furthermore, a biometric unit is used in combination with a personal identification code for double verification to ensure that only authorized personnel can access the system.
[0024] Specifically, when a user accesses the system, he or she first authenticates his or her identity through a biometric unit, including fingerprint scanning, face recognition or iris scanning. After the biometric identification is passed, the user needs to enter the personal identification code bound to him or her, and the system verifies the uniqueness and validity of the identification code through a unified identity management system; if both steps of verification are passed, the system assigns the user operating permissions that match his or her role permissions.
[0025] The personal identity code is a unique identity created by the system for each user. Initial permissions are assigned to users through the personal identity code, and the scope of permissions is dynamically adjusted based on roles and work requirements.
[0026] Furthermore, real-time data of the sensor network is obtained, and the real-time data includes but is not limited to real-time tracking of the location data of the staff using sensors, and monitoring of key indicator data such as radiation level and temperature in the working area through environmental sensors.
[0027] The collected real-time data is preprocessed and standardized. Specifically, outliers are detected and removed from the raw data collected by the sensor, such as eliminating radiation levels or position data that are beyond a reasonable range. Secondly, the data collected by different types of sensors are uniformly converted into a standardized format, such as converting temperature data into standard units (Celsius) or mapping position data to a unified coordinate system. The time series data is then denoised to filter out fluctuations caused by sensor noise or short-term interference.
[0028] S2: Extract characteristic parameters of the staff according to the real-time data, and execute the first analysis mechanism to obtain the analysis results.
[0029] The characteristic parameters of the staff include parameters that reflect the staff's status and the environment they are in. The location information, environmental data (such as radiation level, temperature, etc.) and log information (such as task start / end time) collected by the sensor are integrated, and the corresponding real-time data is matched through the timestamp to ensure data synchronization and integrity.
[0030] Based on location information, determine whether the staff is in the designated work area and record their activity trajectory in the work area; compare the task execution time with the assigned task plan to extract the task completion status (such as task progress, delays, etc.). Record each employee's entry and exit time, work area, task execution status and any abnormal events, encrypt and store log data, and support fast retrieval and analysis.
[0031] Furthermore, the first analysis mechanism is executed to detect potential security threats based on the characteristic parameters of the staff. When potential security threats or operational abnormalities are detected, the system can immediately issue an early warning to relevant personnel and provide preset emergency plan guidance to quickly respond to possible crises.
[0032] In one embodiment of the present invention, the first analysis mechanism may be an analysis mechanism based on a rule engine. Specifically, the system establishes a set of multi-dimensional safety rule bases according to the safety specifications and risk assessment standards of nuclear power management, including environmental rules, behavioral rules and task rules, such as the radiation level shall not be higher than a specified threshold (such as >10μSv / h) and the temperature range shall be maintained at 15°C to 35°C.
[0033] The feature parameters extracted in real time are compared with the conditions in the rule base one by one to obtain the analysis results. For example, if a worker enters a high-radiation area marked as dangerous, the "entering a high-risk area" rule is triggered; if the task completion time exceeds expectations, the "task delay" rule is triggered. Based on the analysis results, the events that meet the rule conditions are classified and marked to determine whether to trigger an early warning.
[0034] In another embodiment of the present invention, the first analysis mechanism can also be implemented through a machine learning anomaly detection model. Using historical data collected by sensors (including environmental radiation levels, worker location trajectories, task execution progress, etc.), an anomaly detection model based on unsupervised learning (such as an autoencoder or an isolation forest) is constructed to learn the characteristic distribution of normal behaviors and environmental parameters. After the characteristic parameters of the staff are input in real time, the model compares the characteristics. If a behavior or environmental state that exceeds the normal distribution range is detected, it is marked as a potential threat and triggers an early warning.
[0035] The model can evaluate the degree of abnormality of events based on real-time data (such as increased radiation levels, location deviation from the mission area, mission delays, etc.), and combine it with preset threshold rules to improve detection accuracy and flexibility. For example, when it is detected that staff frequently enter non-designated work areas or environmental parameters are continuously abnormal, the system determines the threat level through model scoring and generates an accurate emergency response plan.
[0036] S3: Generate task logs based on the characteristic parameters of the staff and display them visually, and establish an evaluation learning model to implement evaluation training for the staff.
[0037] The task log includes the task data of individual staff members and teams. Specifically, the task log is generated based on the characteristic parameters of the staff members, including the number of completed tasks and the number of deferred tasks of individuals and teams, and supports the generation of customized reports. Task managers can export task reports within a specific time period as needed; TLS / SSL protocol is used to encrypt data transmission to ensure the security of data during transmission. When storing sensitive data, AES encryption algorithm is used for encryption to protect data from unauthorized access.
[0038] The automated logging module reduces the workload of manual recording and reduces the error rate; the interactive task management module enables employees to intuitively view their task lists, completion status, and the work progress of their colleagues, promoting team collaboration.
[0039] Furthermore, the assessment learning model integrates online training materials and simulation test functions to help employees understand the latest safety regulations and operational skills, while regularly evaluating employees' performance and knowledge mastery through the system.
[0040] In one embodiment of the present invention, the evaluation learning model includes a front-end user unit and a back-end management unit. The front-end user unit includes, but is not limited to, generating a personalized training path according to the characteristic parameters of the staff; the back-end management unit includes, but is not limited to, updating the training content and evaluating the training results of the staff.
[0041] Specifically, the front-end user unit dynamically generates personalized learning paths based on the employee's role, historical learning outcomes and performance data, integrates an interactive simulation environment, simulates actual operations through virtual scenes, and provides instant feedback; the front-end user unit uses collaborative filtering or content-based recommendation methods to recommend relevant courses based on the employee's historical learning and performance data, expressed as:
[0042] R(u,i)=∑ v∈N(u) W uv ·S vi
[0043] Where R(u,i) is the score of recommending item i to user u; N(u) is the neighbor set of user u; W uv is the weight between users u and v; S vi is the rating of item i by user v.
[0044] The back-end management system ensures timely updating and accurate distribution of training content, including changes in safety regulations and the introduction of new technologies, analyzes employees’ learning progress and test scores, and generates detailed learning reports and performance evaluations. The back-end management system combines employees’ test scores, course completion, and work performance, and uses a weighted average performance evaluation model, expressed as:
[0045] P(e)=ω1·T(e)+ω2·C(e)+ω3·W(e)
[0046] Where P(e) is the performance score of employee e; T(e), C(e) and W(e) represent test scores, course completion and work performance, respectively; ω1, ω2 and ω3 are the weights of test scores, course completion and work performance, respectively.
[0047] In another embodiment of the present invention, the evaluation learning model can also be a dynamic learning path optimization model based on reinforcement learning to achieve real-time feedback and dynamic improvement. By continuously monitoring the learning progress, test results and task performance data of the staff, the learning path and training content are optimized using reinforcement learning algorithms or data mining techniques.
[0048] Specifically, the Deep Q Network (DQN) or Multi-Armed Bandit model is used to dynamically adjust the training content. The system defines the difficulty or focus of the training content as a set of "actions", and the real-time performance of employees (such as test error rate, task completion efficiency) as "states", and optimizes the strategy through reward feedback for each state-action pair. For example, when the employee has a high error rate in the test, the system chooses to increase the content of related knowledge points; when the task completion efficiency is significantly improved, the system reduces the content in this area and introduces more advanced tasks. Through continuous training, the model continuously optimizes the decision-making strategy so that the training content always adapts to the current learning needs of employees.
[0049] During the implementation process, the system initially sets up a reward mechanism based on rules, such as giving high rewards when employees complete the test and the error rate decreases, and reducing rewards when they delay the task or the test error rate increases. The model updates the Q value or reward estimate based on real-time data, and selects the optimal action through exploration and utilization balance. Through iterative training, the system gradually forms a dynamic adjustment mechanism that can accurately match the learning level of employees, and realizes personalized and adaptive training content optimization.
[0050] Example 2 is an embodiment of the present invention, which provides a log management method based on nuclear power personnel management. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.
[0051] The experiment selected 6 staff members as experimental subjects, covering different job roles, simulating the task execution, environmental anomaly detection and skill improvement needs that may occur in daily work. The location, environmental data (radiation level, temperature) and task progress of each test subject were collected in real time through the sensor network. The experiment was divided into two stages: the first stage evaluated the initial performance of the test subjects, including task completion rate and test error rate; the second stage was trained through the personalized learning path generated by the system, using the rule engine and reinforcement learning model to optimize the training content, and combining the virtual scene simulation operation environment for real-time feedback. During the experiment, the real-time behavior and abnormal response ability of the test subjects were recorded, and knowledge tests and task evaluations were conducted regularly. Finally, the system compared the data of the two stages to generate task logs and personalized reports. The experimental data is shown in Table 1.
[0052] Table 1 Experimental data table
[0053]
[0054] The tabular data shows the significant differences in the initial task completion rate and test error rate of the six test subjects, as well as the improvement effect after system optimization training. For example, the task completion rate of employee 1 increased from 60% to 85%, and the test error rate decreased from 20% to 5%, proving the effectiveness of personalized learning paths for skill improvement. In addition, the system's real-time anomaly detection and task management functions showed extremely high practicality in the experiment, and the number of abnormal alarms resolved during the training phase increased significantly, indicating that employees' safety awareness and processing capabilities have been significantly enhanced.
[0055] Embodiment 3, as Figure 2 As shown, in an exemplary embodiment, a log management system based on nuclear power personnel management is also provided, including:
[0056] Intelligent identity authentication and authority allocation module: The system should use biometric units combined with personal identification codes for double verification to ensure that only authorized personnel can access the system; the specific structure of the intelligent identity authentication and authority allocation module includes biometric units, personal identification code verification, and unified identity management system.
[0057] Certification and audit management module: including personal certification management, organization certification management and qualification audit management, ensuring that all accounts and organizations go through a strict audit process;
[0058] Permission visualization management unit: realize centralized, automated and standardized management of permissions through the intelligent permission management system, and improve the transparency and efficiency of permission management;
[0059] Authority compliance audit module: Establish compliance audit rules, regularly review and audit authority and position compliance content, and ensure the compliance of authority granting and management.
[0060] Real-time location tracking and environmental monitoring module: Use sensors to track the location of workers in real time, and use environmental sensors to monitor key indicators such as radiation levels and temperature in the work area to ensure personnel safety;
[0061] Interactive task management module: enables employees to intuitively view their task lists, completion status, and the work progress of their colleagues, promoting team collaboration;
[0062] Furthermore, the system provides reports on task completion, including key performance indicators such as the number of completed tasks and the number of deferred tasks for individuals and teams, and supports the generation of customized reports. Task managers can export task reports within a specific time period as needed. The system uses TLS / SSL protocol to encrypt data transmission to ensure the security of data during transmission. When storing sensitive data, it uses the AES encryption algorithm to encrypt the data to protect it from unauthorized access.
[0063] Early warning and emergency response module: When potential security threats or operational anomalies are detected, the system can immediately issue an early warning to relevant personnel and provide preset emergency plan guidance to quickly respond to possible crises.
[0064] Training and evaluation module: Integrates online training materials and simulation test functions to help employees understand the latest safety regulations and operating skills, and regularly evaluates employees' performance and knowledge through the system. Specifically, the training and evaluation module includes:
[0065] The front-end user unit dynamically generates personalized learning paths based on employees' roles, historical learning outcomes and performance data, integrates an interactive simulation environment, simulates actual operations through virtual scenes, and provides instant feedback; the front-end user unit uses collaborative filtering or content-based recommendation methods to recommend relevant courses based on employees' historical learning and performance data.
[0066] The back-end management system ensures timely updating and accurate distribution of training content, including changes in safety regulations and introduction of new technologies, analyzes employees' learning progress and test scores, and generates detailed learning reports and performance evaluations; the back-end management system combines employees' test scores, course completion and work performance, and uses a weighted average performance evaluation model.
[0067] The data storage unit encrypts and stores employees’ learning records, test results, and personal feedback to ensure data security and privacy, and implements strict data access control to ensure that only authorized personnel can access sensitive data.
[0068] Data Protection and Privacy Module: Ensure that all personal and work data is encrypted to the highest standards and complies with national and international data protection regulations to protect employee privacy.
[0069] If the above functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.
[0070] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.
[0071] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.
[0072] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.
[0073] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.
Claims
1. A log management method based on nuclear power personnel management, characterized in that: include: Get real-time data from sensor networks; Extracting characteristic parameters of the staff member according to the real-time data, and executing the first analysis mechanism to obtain the analysis results; Based on the characteristic parameters of the staff, task logs are generated and visualized, and an evaluation learning model is established to implement evaluation training for the staff.
2. The log management method based on nuclear power personnel management according to claim 1, characterized in that: The obtaining of real-time data of the sensor network includes preprocessing and standardizing the collected real-time data.
3. The log management method based on nuclear power personnel management according to claim 2, characterized in that: The characteristic parameters of the worker include parameters reflecting the worker's status and the environment in which he / she is located.
4. The log management method based on nuclear power personnel management as claimed in claim 3 is characterized by: The first analysis mechanism includes detecting potential security threats based on characteristic parameters of the staff.
5. The log management method based on nuclear power personnel management according to claim 4, characterized in that: The task log includes task data of individual staff members and teams.
6. The log management method based on nuclear power personnel management according to claim 5, characterized in that: The evaluation learning model includes a front-end user unit and a back-end management unit.
7. The log management method based on nuclear power personnel management according to claim 6, characterized in that: The front-end user unit includes, but is not limited to, generating a personalized training path according to the characteristic parameters of the staff; The back-end management unit includes, but is not limited to, updating the training content and evaluating the training results of the staff.
8. A log management system based on nuclear power personnel management using any of the methods of claims 1 to 7, characterized in that: include, Acquisition module, which obtains real-time data from the sensor network and performs preprocessing; The analysis module extracts characteristic parameters of the staff according to the real-time data and implements safety detection and early warning through the first analysis mechanism; The training module generates task logs based on the characteristic parameters of the staff and displays them visually, and establishes an evaluation learning model to realize the evaluation training of the staff.
9. A computer device comprising: Memory and processor; The memory stores a computer program, characterized in that: when the processor executes the computer program, the steps of the log management method based on nuclear power personnel management as described in any one of claims 1-7 are implemented.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the log management method based on nuclear power personnel management as described in any one of claims 1 to 7 are implemented.