Energy service task-oriented equipment maintenance personnel automatic selection method and system

Abstract

The invention discloses an energy service task-oriented equipment maintenance personnel automatic selection method and system, and relates to the technical field of data processing, and the method comprises the steps: setting segmented selection configuration parameters according to maintenance task demand parameters and personnel qualification access conditions of energy service equipment; setting a correction coefficient based on the semantic matching characteristics of the maintenance resources and task execution efficiency parameters; reversely analyzing the optimized selection configuration parameters, and generating a personnel automatic selection execution scheme; and acquiring task matching influence area data in real time, and dynamically refreshing and optimizing the selection configuration parameters according to a preset matching threshold value and an adaptive deviation. The technical problems that an existing equipment maintenance personnel selection method cannot dynamically adapt to task demand changes, and personnel selection precision and efficiency are low are solved, and the technical effect of improving personnel selection precision and response speed through automatic selection and dynamic optimization based on task demands and real-time data is achieved.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and more specifically to a method and system for automatically selecting equipment maintenance personnel for energy service tasks. Background Technology

[0002] With the rapid development of the energy services industry, the complexity and diversity of equipment maintenance tasks are constantly increasing. However, traditional personnel selection methods are no longer sufficient to meet the demands for efficient and accurate matching. Existing technologies mostly rely on manual selection or simple rule engines, which often cannot adapt to changes in task requirements in real time, leading to inefficient personnel selection and potential mismatches or resource waste. Furthermore, the lack of a unified dynamic optimization mechanism prevents the effective integration of multiple factors such as equipment fault type, personnel skills, and task urgency, impacting the efficiency and quality of maintenance task execution. Summary of the Invention

[0003] This application provides an automatic selection method and system for equipment maintenance personnel for energy service tasks, which solves the technical problem that existing equipment maintenance personnel selection methods cannot dynamically adapt to changes in task requirements and have low accuracy and efficiency in personnel selection.

[0004] The first aspect of this application provides an automatic selection method for equipment maintenance personnel for energy service tasks. The method includes: setting segmented selection configuration parameters associated with skill certification segments, historical maintenance adaptation segments, and task response capability segments based on maintenance task requirements parameters of energy service equipment and personnel qualification access conditions; setting a first correction coefficient and a second correction coefficient based on the semantic matching characteristics of the maintenance resource knowledge graph and task execution efficiency parameters; back-analyzing the optimized selection configuration parameter combination into the segmented selection configuration parameters based on the first correction coefficient and the second correction coefficient to generate an automatic personnel selection execution plan; collecting real-time monitoring data of each task matching influence area, including personnel skill status, equipment fault type, and task urgency data; and dynamically refreshing and continuously optimizing the selection configuration parameter combination based on the preset matching threshold and actual adaptation deviation of the automatic personnel selection execution plan.

[0005] The second aspect of this application provides an automatic selection system for equipment maintenance personnel for energy service tasks. The system includes: a selection configuration parameter setting module, used to set segmented selection configuration parameters associated with skill certification segments, historical maintenance adaptation segments, and task response capability segments based on the maintenance task requirements parameters of energy service equipment and personnel qualification access conditions; a correction coefficient setting module, used to set a first correction coefficient and a second correction coefficient based on the semantic matching characteristics of the maintenance resource knowledge graph and task execution efficiency parameters; an execution plan generation module, used to reverse-parse the optimized selection configuration parameter combination into the segmented selection configuration parameters based on the first correction coefficient and the second correction coefficient to generate an automatic personnel selection execution plan; and a selection parameter optimization module, used to collect real-time monitoring data of each task matching influence area, including personnel skill status, equipment fault type, and task urgency data, and dynamically refresh and continuously optimize the selection configuration parameter combination based on the preset matching threshold and actual adaptation deviation of the automatic personnel selection execution plan.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0007] The automatic selection method and system for equipment maintenance personnel for energy service tasks provided in this application relate to the field of data processing technology. By constructing segmented selection configuration parameters and knowledge graph-based correction coefficients, combined with a dynamic refresh and rolling optimization mechanism for real-time monitoring data, it achieves accurate and efficient automatic selection of energy service equipment maintenance personnel. This solves the technical problem that existing equipment maintenance personnel selection methods cannot dynamically adapt to changes in task requirements, resulting in low accuracy and efficiency in personnel selection. It achieves the technical effect of improving personnel selection accuracy and response speed through automated selection and dynamic optimization based on task requirements and real-time data, thereby enhancing the overall execution efficiency and quality of maintenance tasks. Attached Figure Description

[0008] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0009] Figure 1 A schematic flowchart of an automatic selection method for equipment maintenance personnel for energy service tasks provided in this application embodiment;

[0010] Figure 2 A schematic diagram of the structure of an automatic selection system for equipment maintenance personnel for energy service tasks provided in this application embodiment.

[0011] Figure labeling: Selection configuration parameter setting module 11, correction coefficient setting module 12, execution scheme generation module 13, selection parameter optimization module 14. Detailed Implementation

[0012] This application provides an automatic selection method and system for equipment maintenance personnel for energy service tasks, which solves the technical problem that existing equipment maintenance personnel selection methods cannot dynamically adapt to changes in task requirements and have low accuracy and efficiency in personnel selection.

[0013] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0014] It should be noted that the terms "first," "second," etc., in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules not explicitly listed or inherent to such processes, methods, products, or devices.

[0015] Example 1, as Figure 1 As shown, this application provides an automatic selection method for equipment maintenance personnel for energy service tasks, the method comprising:

[0016] P10: Based on the maintenance task requirements of energy service equipment and the access conditions for personnel qualifications, set segmented selection configuration parameters that are associated with skill certification segments, historical maintenance adaptation segments, and task response capability segments.

[0017] Furthermore, step P10 in this embodiment of the application also includes:

[0018] P11: Based on the maintenance task requirements parameters of energy service equipment and the access conditions for personnel qualifications, a time-series equivalent analysis and sensitive matching point identification are performed on the fluctuation range of task complexity and the prediction error of personnel skill adaptation, and the skill gap and supply-demand matching critical point are calculated for each time period; P12: Through the skill gap and supply-demand matching critical point for each time period, the equipment maintenance task cycle is divided into skill certification segment, historical maintenance adaptation segment, and task response capability segment.

[0019] It should be understood that in-depth analysis of the requirements parameters for energy service equipment maintenance tasks and the access conditions for personnel qualifications, by analyzing the relationship between task complexity fluctuations and personnel skill suitability, and dynamically adjusting personnel selection strategies during task execution, can ensure that tasks can be completed efficiently with optimal personnel allocation.

[0020] First, based on the maintenance task requirements parameters of energy service equipment and the personnel qualification access conditions, time-series isovaluation analysis and sensitive matching point identification are performed on the fluctuation range of task complexity and the prediction error of personnel skill matching. The fluctuation range of task complexity refers to the degree to which the difficulty and requirements of maintenance tasks change over different time periods. For example, some equipment may experience more complex fault types during specific seasons or operating phases, leading to a significant increase in task complexity. The prediction error of personnel skill matching refers to the potential deviation in predicting the degree of matching between personnel skills and task requirements. Through time-series isovaluation analysis, these fluctuations and errors can be isovalued over time, allowing for a more intuitive observation of their changing patterns.

[0021] Building upon this foundation, we further identify sensitive matching points. Sensitive matching points are critical nodes in the task execution process, representing moments when significant changes may occur, such as sudden equipment malfunctions or changes in task urgency. For instance, when task complexity suddenly increases while the prediction error for personnel skill suitability also increases, a critical point may emerge. If personnel allocation is not adjusted promptly at this point, the task may fail to execute smoothly. By identifying these sensitive matching points, we can accurately calculate skill gaps and supply-demand matching critical points for each time period. A skill gap refers to the difference between the skills of existing personnel and task requirements within a given timeframe. A supply-demand matching critical point refers to the point at which the system needs to take adjustment measures when the skill gap reaches a certain threshold, such as reallocating tasks or allocating more qualified personnel.

[0022] Next, based on the calculation results of skill gaps and supply-demand matching critical points in each time period, the equipment maintenance task cycle is divided into skill certification segments, historical maintenance adaptation segments, and task response capability segments. Skill certification segments divide the task cycle into different stages based on personnel's skill certification levels and types, allowing for the selection of personnel with corresponding skill certifications at each stage. For example, for high-complexity task stages, personnel with advanced skill certifications may be prioritized; while for relatively simple task stages, personnel with intermediate or basic skill certifications can be selected. Historical maintenance adaptation segments further subdivide the task cycle based on personnel's historical maintenance records and experience. In some stages, the task may involve the maintenance of specific equipment or fault types, where personnel with relevant historical experience will have an advantage. Historical maintenance adaptation segments ensure that personnel with relevant experience are selected at each stage, improving the efficiency and quality of task execution. Task response capability segments divide the task cycle into different response stages based on personnel's response speed and processing efficiency. For example, in emergency task stages, personnel with high response capabilities are prioritized to ensure the task can be quickly initiated and effectively executed.

[0023] Ultimately, by dividing the task cycle into skill certification segments, historical maintenance adaptation segments, and task response capability segments, the system can accurately match different personnel with task requirements, ensuring that the task at each stage can be performed by the most suitable personnel.

[0024] P20: Based on the semantic matching characteristics of the maintenance resource knowledge graph and the task execution efficiency parameters, set the first correction coefficient and the second correction coefficient.

[0025] Furthermore, step P20 in this embodiment of the application also includes:

[0026] P21: Based on the semantic matching characteristics of the maintenance resource knowledge graph and combined with the task matching accuracy requirements, the knowledge graph correlation parameters and semantic mapping efficiency are detected in all dimensions to obtain the first correction coefficient; P22: Based on the task execution efficiency parameters and combined with historical task execution loop data, the adaptation decay amount of different skill proficiency ranges is dynamically deduced to obtain the second correction coefficient.

[0027] Optionally, to further optimize the automatic selection process of equipment maintenance personnel, semantic matching and task execution efficiency analysis can be performed based on the knowledge graph of maintenance resources, and a first correction coefficient and a second correction coefficient can be set to optimize the selection of personnel and resource allocation for task execution.

[0028] First, task matching optimization is achieved by constructing and analyzing a knowledge graph of maintenance resources. This knowledge graph encompasses information on personnel, skills, and equipment. During implementation, the maintenance resource knowledge graph deeply integrates information such as personnel skill certifications, historical maintenance experience, and equipment fault types through a semantic association network structure. Based on the semantic matching characteristics of this knowledge graph, combined with the task's matching accuracy requirements, the matching accuracy requirements during task execution can be analyzed to further optimize the matching effect.

[0029] Specifically, a comprehensive evaluation of the knowledge graph's correlation parameters is conducted to assess the degree of connection between nodes within the knowledge graph. These correlation parameters reflect the close relationship between elements such as equipment fault type, personnel skills, and task requirements. During task matching, these correlation parameters are analyzed to determine the match between task requirements and resources. A low correlation between task requirements and resources may lead to deviations in task matching results, affecting task execution efficiency. Therefore, a comprehensive evaluation of the correlation parameters is necessary to ensure a sufficiently high match between tasks and resources.

[0030] Simultaneously, the efficiency of semantic mapping is tested. Semantic mapping efficiency refers to the system's ability to map task requirements to relevant resources, such as personnel skills and equipment, through semantic association. The system needs to test the semantic mapping process between task requirements and resources to ensure that the mapping process is efficient and accurate. If the efficiency of semantic mapping is low, it may lead to matching errors between task requirements and resources, thereby affecting the execution effect of the task.

[0031] Based on the above analysis, and considering the task's matching accuracy requirements, the knowledge graph's relevance, and semantic mapping efficiency, a first correction coefficient can be calculated. For example, the semantic matching performance of the knowledge graph can be evaluated from multiple perspectives, including but not limited to assessing relevance, mapping speed, and matching accuracy, to obtain a quantitative indicator, namely the first correction coefficient. This coefficient is used to adjust the segmented selection configuration parameters to ensure more accurate matching of personnel who meet the task requirements during the knowledge graph's semantic matching process. When the matching degree is low, the first correction coefficient will be larger to adjust the matching strategy; conversely, when the matching degree is high, the correction coefficient will be smaller.

[0032] Secondly, based on task execution efficiency parameters and historical task execution cycle data, the adaptation decay amount for different skill proficiency ranges is dynamically extrapolated. Task execution efficiency parameters refer to indicators such as the speed and quality of task completion during actual task execution, including task completion time, task success rate, and fault repair time. Historical task execution cycle data records detailed information about past task executions, including the skill proficiency of participants, task type, task difficulty, and task completion status.

[0033] Next, the changes in task execution efficiency are extrapolated by analyzing the adaptation decay across different skill proficiency ranges. As task execution time increases or task complexity rises, the fit between personnel skills and task requirements may decrease. Therefore, adaptation decay refers to the degree of change in task execution efficiency due to differences in personnel skill proficiency during task execution. Specifically, the potential efficiency loss during task execution can be assessed by comparing the performance of personnel with different proficiency levels in historical tasks. For example, historical execution efficiency data from all personnel can be collected as sample data to train a dynamic model to extrapolate the adaptation decay across different skill proficiency ranges. This model takes task execution time and task complexity as input and adaptation decay as output, predicting the efficiency loss of different personnel at different times. For instance, a highly skilled personnel may experience skill fatigue after continuously performing a high-difficulty task for a long time, leading to a decrease in adaptation. Through dynamic extrapolation, this decay trend can be predicted, and a second correction coefficient can be determined accordingly. The second correction factor compensates for skill differences during task execution, ensuring that the system prioritizes highly skilled personnel for complex tasks, while adjusting the difficulty and requirements of tasks appropriately during the matching process for less skilled personnel. Through this correction factor, the system can achieve a balance in task efficiency among personnel with varying skill levels, maximizing overall task execution efficiency.

[0034] P30: Based on the first correction coefficient and the second correction coefficient, the optimized selection configuration parameter combination is reverse-analyzed into the segmented selection configuration parameter to generate an automatic personnel selection execution plan.

[0035] Furthermore, the optimized selection configuration parameter combination is reverse-analyzed into the segmented selection configuration parameters. In this embodiment, step P30 further includes:

[0036] P31: Construct an association mapping matrix based on the first correction coefficient and skill adaptation gradient parameters, the second correction coefficient and collaboration adaptation gap; P32: Using the coupling influence coefficient of the association mapping matrix as the fitness function weight, minimize the personnel skill matching deviation corresponding to the equipment maintenance task, maximize the collaboration utilization rate of the maintenance team, and minimize the task response delay as optimization objectives.

[0037] Specifically, based on the first and second correction coefficients, the optimized selection configuration parameter combination is reverse-analyzed into the segmented selection configuration parameters to generate an automatic personnel selection execution plan.

[0038] During implementation, a correlation mapping matrix is ​​first constructed based on the first correction coefficient and skill adaptation gradient parameter, the second correction coefficient, and the collaboration adaptation gap. The first correction coefficient reflects the matching accuracy between task requirements and personnel skills, while the second correction coefficient reflects the impact of personnel skill proficiency on task execution efficiency. The skill adaptation gradient parameter refers to the difference in the degree of adaptation between personnel skills and task requirements across different skill certification segments and historical maintenance adaptation segments. For example, from basic skill certification to advanced skill certification, a person's adaptability to a specific task gradually increases; this difference can be quantified using the gradient parameter. The collaboration adaptation gap refers to the gap between the collaboration ability of different personnel and task requirements within the task response capability segment. For example, some personnel may perform well in teamwork, while others may need to further improve their collaboration ability; this gap can be measured using the collaboration adaptation gap.

[0039] Combining these factors, an association mapping matrix can be constructed. This multi-dimensional matrix describes the complex relationship between personnel skills, collaborative abilities, and task requirements. The rows of the matrix can represent different skill certification segments and historical maintenance adaptation segments, while the columns can represent different task responsiveness segments. The elements in the matrix represent the degree of adaptation between personnel skills and task requirements, as well as the matching of collaborative abilities, under specific combinations of segments. By combining the first and second correction coefficients with the skill adaptation gradient parameters and the collaborative adaptation gap, respectively, each element in the association mapping matrix can be modified, thus more accurately reflecting the matching relationship between personnel and tasks.

[0040] Next, using the coupling influence coefficient of the association mapping matrix as the weight of the fitness function, the optimization objectives are to minimize the personnel skill matching deviation corresponding to the equipment maintenance task, maximize the utilization rate of the maintenance team collaboration, and minimize the task response delay. The coupling influence coefficient refers to the degree of mutual influence between different segment combinations in the association mapping matrix. For example, a high coupling influence coefficient between a specific skill certification segment and a task response capability segment indicates that, under this segment combination, the degree of matching between personnel skills and task requirements has a significant impact on the overall team collaboration and task response capability.

[0041] Setting the fitness function weights is a crucial step in the optimization process. By using the coupling influence coefficient as the weight, it can be ensured that the optimization focuses on the segment combinations that have a significant impact on task execution. The optimization objectives include three main aspects: minimizing personnel skill matching deviation, which means minimizing the difference between personnel skills and task requirements during the personnel selection process, ensuring that personnel in each segment can complete the task efficiently; maximizing the utilization rate of maintenance team collaboration, which means fully utilizing the collaborative ability of each member during team building to improve the overall work efficiency of the team; and minimizing task response latency, which means minimizing personnel response time during task allocation, ensuring that tasks can be started in a timely manner and executed smoothly.

[0042] By comprehensively considering these optimization goals, the system can balance multiple factors such as personnel skills, teamwork, and task response speed during execution, ensuring that each stage of task execution achieves optimal results, thereby generating the best personnel selection and execution plan.

[0043] Furthermore, in constructing the association mapping matrix, step P30 of this embodiment also includes:

[0044] P31-1: Based on the segmented selection configuration parameters, the task-driven semantic association matching flow distribution corresponding to personnel and skill association nodes is simulated and set using simulation to obtain skill adaptation gradient parameters that meet the semantic matching stability constraint; P31-2: Based on the segmented selection configuration parameters, the personnel and equipment association nodes of the maintenance resource knowledge graph are optimized using topology optimization to obtain the collaborative adaptation gap that meets the matching balance constraint, wherein the personnel and skill association nodes and the personnel and equipment association nodes are all located in the maintenance resource knowledge graph.

[0045] Optionally, the process of constructing the association mapping matrix is ​​further refined to ensure that the generated association mapping matrix can more accurately reflect the matching relationship between people and tasks.

[0046] First, based on segmented selection configuration parameters, simulation is used to model the task-driven semantic association matching flow distribution corresponding to personnel and skill-related nodes. The segmented selection configuration parameters include skill certification segments, historical maintenance adaptation segments, and task response capability segments, which provide the basic framework for the simulation. In the simulation, personnel and skill-related nodes refer to the connection points between personnel skills and task requirements in the knowledge graph, while the task-driven semantic association matching flow distribution describes the dynamic matching process between personnel skills and tasks under different task requirements. Through simulation, the matching flow between personnel skills and task requirements in different task scenarios can be simulated. For example, in a specific task scenario, it can simulate which personnel with different skill certification segments can respond quickly and effectively complete the task, and the dynamic changes between personnel skills and task requirements during task execution. Through this simulation, skill adaptation gradient parameters that conform to the semantic matching stability constraint can be obtained. The semantic matching stability constraint ensures that the semantic matching between personnel skills and task requirements remains stable within a certain period of time during the simulation, without frequent fluctuations. The skill adaptation gradient parameter quantifies the differences in the degree of adaptation between personnel skills and task requirements in different skill certification segments and historical maintenance adaptation segments, providing key data for the subsequent construction of the correlation mapping matrix.

[0047] Next, based on segmented selection and configuration parameters, topology optimization is used to optimize the personnel and equipment association nodes in the maintenance resource knowledge graph. Topology optimization is a mathematical method used to optimize network structure to achieve optimal performance while meeting specific objectives. In this application, personnel and equipment association nodes refer to the connection points between personnel and equipment in the knowledge graph, reflecting the skills and experience of personnel when maintaining equipment. Through topology optimization, the layout and connection methods of personnel and equipment association nodes in the knowledge graph can be adjusted to obtain collaborative adaptation gaps that conform to the matching balance constraint. The matching balance constraint means ensuring that the matching relationship between personnel and equipment remains balanced overall during the optimization process. That is, in different task scenarios, the matching process between personnel and equipment can fully utilize the skill advantages of each member while ensuring the reasonable allocation of resources, avoiding the burden on some personnel due to overly concentrated skills or overly complex tasks.

[0048] This optimization process ultimately yields the collaboration fit gap. This parameter reflects the collaboration potential and efficiency among members of the maintenance team, especially in the matching relationship between personnel and equipment. The collaboration fit gap quantifies the smoothness of collaboration between personnel during task execution. By optimizing the collaboration fit between personnel and equipment, it is possible to ensure efficient collaboration among team members when multiple personnel are performing tasks together, reducing collaboration resistance and efficiency losses.

[0049] Furthermore, step P31 in the embodiments of this application also includes:

[0050] P31-3: The matrix row dimension of the association mapping matrix is ​​the semantic matching compensation element category associated with the first correction coefficient, the semantic mapping efficiency compensation element category, the proficiency adaptation attenuation compensation element category associated with the second correction coefficient, and the task execution loop compensation element category; P31-4: The matrix column dimension of the association mapping matrix is ​​the matching influence area of ​​the equipment maintenance task, including the personnel qualification node of the skill certification segment, the maintenance team cluster of the historical maintenance adaptation segment, and the flexible collaborative aggregate of the task response capability segment.

[0051] It should be understood that the specific structure of the association mapping matrix can be further defined, including the definition of its row and column dimensions, to ensure that the matrix can comprehensively and accurately reflect the matching relationship between personnel and tasks.

[0052] Specifically, the row dimension of the association mapping matrix includes four main categories: semantic matching compensation elements associated with the first correction coefficient, semantic mapping efficiency compensation elements, proficiency adaptation decay compensation elements associated with the second correction coefficient, and task execution loop compensation elements. This means that when constructing the association mapping matrix, each row represents a specific compensation element category. Semantic matching compensation elements refer to factors that enhance the accuracy of semantic matching in the knowledge graph, such as improving the matching accuracy between task requirements and personnel skill descriptions by introducing more advanced natural language processing algorithms. Semantic mapping efficiency compensation elements focus on improving mapping speed, such as optimizing algorithms to reduce computation time.

[0053] Secondly, the proficiency adaptation attenuation compensation element category is related to the second correction coefficient and is mainly used to address the problem of decreased task execution efficiency caused by insufficient personnel skill proficiency. During task execution, personnel with lower proficiency may experience efficiency losses. The system uses this compensation element to quantify the impact of proficiency on task execution efficiency and compensates for this deficiency by adjusting the correction coefficient, ensuring that personnel can better adapt to task requirements.

[0054] Finally, the task execution cycle compensation element category involves the analysis of historical task data. Considering the variations in the execution cycle, complexity, and personnel skills of different tasks, the task execution cycle compensation element helps predict and compensate for changes in execution efficiency caused by different task cycles. This element, through the analysis of historical task data, helps the system dynamically adjust its task allocation strategy.

[0055] Next, the column dimensions of the association mapping matrix represent the matching influence area of ​​the equipment maintenance task, including personnel qualification nodes in the skills certification segment, maintenance team clusters in the historical maintenance adaptation segment, and flexible collaboration aggregates in the task response capability segment. This indicates that each column represents a key matching influence area for the equipment maintenance task. Personnel qualification nodes refer to personnel qualification information related to the skills certification segment, reflecting whether personnel possess the basic skills required to complete a specific task. Maintenance team clusters are associated with the historical maintenance adaptation segment, representing a set of teams that have demonstrated good collaboration and adaptability in past tasks; these teams may have a higher success rate when facing similar tasks. Flexible collaboration aggregates are related to the task response capability segment, emphasizing the team's flexibility and collaboration in responding to different task requirements; for example, a team can quickly adjust its working methods to adapt to the needs of an emergency task.

[0056] By setting the row and column dimensions of the association mapping matrix, the system can quantify and optimize the matching relationship between various factors in task execution, such as personnel skills, qualifications, historical experience, and collaboration ability, and task requirements, ensuring that personnel can be efficiently matched with task requirements.

[0057] Furthermore, step P30 in this embodiment of the application also includes:

[0058] P33: The range of values ​​for the first correction coefficient and the skill adaptation gradient parameter, and the range of values ​​for the second correction coefficient and the collaboration adaptation gap are used as the particle search space, and adaptive inertial weights are introduced for iterative optimization; P34: The selection configuration parameter combination generated in each round of optimization is verified. If the simulation verification result meets the task matching accuracy requirements, the current selection configuration parameter combination is dynamically refreshed and the selection configuration parameter combination is output.

[0059] Specifically, the process can be further refined and optimized to ensure that the generated selection configuration parameter combination can meet the task matching accuracy requirements, and to continuously optimize it through a dynamic refresh mechanism.

[0060] In the implementation process, the value ranges of the first correction coefficient and the skill adaptation gradient parameter, and the value ranges of the second correction coefficient and the collaboration adaptation gap are first defined as the particle search space. These parameter value ranges define multiple variable spaces for task-person matching, and the system will perform particle search optimization based on these ranges. Particle search is an algorithm commonly used for global optimization. By simulating the motion of multiple particles within the search space, it can explore different parameter combinations to find the optimal parameter configuration.

[0061] Specifically, the ranges of the first correction coefficient and the skill adaptation gradient parameter reflect the possible differences in the degree of adaptation between personnel skills and task requirements in different skill certification segments and historical maintenance adaptation segments; the ranges of the second correction coefficient and the collaboration adaptation gap reflect the possible gap between personnel collaboration capabilities and equipment maintenance requirements in different task response capability segments. By defining these ranges, a clear search boundary is provided for the particle swarm optimization algorithm, ensuring that the algorithm can find the optimal solution within a reasonable range.

[0062] Next, to improve the efficiency of particle search, adaptive inertia weights can be introduced. Inertia weights are a key parameter in particle swarm optimization, controlling the movement speed of particles within the search space. In each optimization round, the inertia weights are dynamically adjusted based on the current optimization process. Adaptive inertia weights mean adjusting the particle's search strategy according to the current optimization state to balance exploration and development capabilities. When particles are still within a wide range of the search space, the inertia weights are larger, resulting in faster search speeds; conversely, when particles are close to the optimal solution, the inertia weights are smaller to refine the search process and prevent excessive deviation from the optimal solution. By introducing adaptive inertia weights, the system can more flexibly adjust between large-scale search and precise localization, thereby accelerating the optimization process and improving the efficiency of finding the global optimum.

[0063] In each round of optimization, the generated selection configuration parameter combinations must be verified. The verification process is accomplished through simulation, specifically including the evaluation of key indicators such as personnel skill matching deviation, maintenance team collaboration utilization rate, and task response latency. If the simulation verification results meet the task matching accuracy requirements—that is, personnel skill matching deviation is within the allowable range, maintenance team collaboration utilization rate is high, and task response latency is low—then the current selection configuration parameter combination is considered effective. At this point, the system's selection parameters are dynamically refreshed using the current selection configuration parameter combination, ensuring the continuity and effectiveness of the optimization process. The dynamic refresh mechanism reflects the optimization results in real time, enabling the system to select personnel based on the latest parameter combinations, thereby improving the overall system's adaptability and flexibility.

[0064] Furthermore, step P30 in this embodiment of the application also includes:

[0065] P35: If the simulation verification results do not meet the task matching accuracy requirements, then based on the positioning deviation contribution of the correlation mapping matrix, sort the positioning deviation contribution from high to low to obtain the compensation element category sequence; P36: Perform local optimization based on the compensation element category sequence until the number of iterations reaches a preset threshold. Then, reverse-analyze the selection configuration parameter combination obtained by optimization into the segmented selection configuration parameters to generate an automatic personnel selection execution scheme that includes a dynamic adaptation curve for skill certification segments, a tiered team combination scheme for historical maintenance adaptation segments, and a partitioned collaborative control strategy for task response capability segments.

[0066] In one possible embodiment of this application, if the simulation verification results do not meet the task matching accuracy requirements, a sequence of compensation element categories is obtained by sorting the positioning deviation contribution rates from high to low based on the positioning deviation contribution rates of the association mapping matrix. The association mapping matrix records the degree of influence of different compensation element categories, such as semantic matching compensation and proficiency adaptation attenuation compensation, on the task matching accuracy, i.e., the positioning deviation contribution rate. By analyzing the association mapping matrix, the contribution of each compensation element category to the current matching deviation can be quantified.

[0067] For example, if a certain compensation element category has a high contribution to the positioning deviation, it indicates that this element has a significant impact on the current insufficient matching accuracy. By sorting the compensation element categories from high to low according to their contribution to the positioning deviation, a sequence of compensation element categories can be obtained. This sequence clarifies which compensation element categories need to be optimized and adjusted first in order to quickly improve the task matching accuracy.

[0068] Next, local optimization is performed based on the sequence of compensation element categories until the number of iterations reaches a preset threshold. Local optimization refers to targeted adjustments and optimizations for specific compensation element categories. For example, for semantic matching compensation element categories, optimization can be achieved by improving natural language processing algorithms or adjusting semantic matching strategies; for proficiency adaptation decay compensation element categories, optimization can be achieved by reassessing personnel skill proficiency or adjusting task allocation strategies. Based on this, local optimization is performed on each element category sequentially according to the order of the compensation element category sequence, and simulation verification is performed again after each optimization to check whether the task matching accuracy meets the requirements. This process continues until the number of iterations reaches the preset threshold. The preset threshold can be set based on the time and resource constraints in actual applications to ensure that the optimization process is completed within a reasonable timeframe.

[0069] Subsequently, the optimized selection configuration parameter combination is back-analyzed into the segmented selection configuration parameters, generating an automatic personnel selection and execution plan that includes dynamic adaptation curves for skill certification segments, tiered team combination schemes for historical maintenance adaptation segments, and regional collaboration control strategies for task response capability segments. The dynamic adaptation curves, generated for skill certification segments based on the optimized selection configuration parameter combination, reflect the changing trends in the adaptability of personnel at each skill certification segment under different task requirements. The tiered team combination scheme is based on historical maintenance adaptation segments; according to the optimization results, personnel with different historical maintenance experience are grouped into multiple teams, each with different adaptation advantages in specific task scenarios. The regional collaboration control strategy is designed for task response capability segments; based on the optimized parameter combination, collaboration control can be implemented for personnel in different task response capability segments to ensure efficient collaboration in completing tasks under varying levels of urgency.

[0070] In summary, by ranking compensation factors based on the contribution of positioning deviations according to the correlation mapping matrix, and through local optimization iterations, a comprehensive automatic personnel selection and execution scheme that considers multiple dimensions can be generated. This scheme ensures that tasks achieve optimal performance in terms of personnel matching accuracy, team collaboration efficiency, and task response speed, greatly improving the overall efficiency of equipment maintenance task execution.

[0071] P40: Collect real-time monitoring data of the matching impact area of ​​each task, including personnel skill status, equipment failure type, and task urgency. Based on the preset matching threshold of the personnel automatic selection execution plan and the actual adaptation deviation, dynamically refresh and continuously optimize the selection configuration parameter combination.

[0072] Furthermore, the selection configuration parameter combination is dynamically refreshed and continuously optimized. In this embodiment, step P40 further includes:

[0073] P41: Using the parameter sensitivity of the association mapping matrix as the network input weight, the difference between the target value and the task matching accuracy requirement is used as the network input layer variable; P42: After each round of refresh, the updated selection configuration parameter combination is substituted into the association mapping matrix for reverse verification to determine the deviation improvement rate of each task matching influence area; P43: If the deviation improvement rate is lower than the preset improvement rate threshold, the boundary constraints of the particle search space are updated using the compensation element category sequence.

[0074] Optionally, the selection configuration parameter combination can be dynamically refreshed and continuously optimized through real-time monitoring data to further optimize the personnel selection scheme and ensure that personnel matching and collaboration during task execution are more accurate and efficient.

[0075] First, the selection configuration parameters are dynamically optimized by using the parameter sensitivity of the association mapping matrix as input weights to the network. The association mapping matrix contains multiple parameters, each affecting task matching accuracy, and the degree of these effects is measured by parameter sensitivity. Parameter sensitivity reflects the contribution of different task matching factors to task execution accuracy. By using these sensitivities as input weights to the network, the system can adjust the priority of different parameters during the optimization process, ensuring that key factors in task execution receive greater attention and optimization.

[0076] Simultaneously, the difference between the target value and the required task matching accuracy is used as an input layer variable in the network. The required task matching accuracy is the ideal value set by the system, while the difference between the target value and the actual task execution is the deviation from the target value. By using this difference as input, the system can continuously adjust the configuration of various parameters during the task matching process, narrowing the gap between the actual execution accuracy and the preset target accuracy, thereby achieving more accurate personnel matching.

[0077] Next, after each refresh, the updated selection configuration parameter combination is substituted into the association mapping matrix for reverse verification. The purpose of reverse verification is to verify whether the updated selection configuration parameters can truly improve task matching accuracy. By substituting the new configuration parameters into the association mapping matrix, the system can evaluate the task deviation in different matching regions and determine the deviation improvement rate for each task matching region. The deviation improvement rate reflects the degree to which the updated configuration parameters improve task accuracy, and this indicator can be used to determine whether the optimization process is effective.

[0078] If the deviation improvement rate reaches the preset improvement rate threshold, it indicates that the current configuration has significantly improved task matching accuracy, and the system will retain the current configuration and proceed to the next round of optimization. If the deviation improvement rate is lower than the preset improvement rate threshold, it indicates that the current optimization effect is insufficient, and the optimization strategy will be further adjusted. The preset improvement rate threshold is a benchmark value set according to actual needs to determine whether the optimization effect has met expectations.

[0079] Specifically, if the deviation improvement rate is lower than a preset improvement rate threshold, the boundary constraints of the particle search space are updated with a compensation element category sequence. The compensation element category sequence is the element sequence obtained by sorting according to the contribution of positioning deviation in the preceding steps. It clarifies the order of influence of each compensation element on matching accuracy. By updating the boundary constraints, the direction and scope of the optimization search can be adjusted, guiding the optimization process towards a more effective direction. The system will update the boundary constraints of the particle search based on this sequence. For example, based on the compensation element category sequence, the boundary of the search space can be contracted or expanded to ensure that the search process can be more focused on key compensation elements, thereby improving the efficiency and accuracy of the particle search.

[0080] In summary, by comparing real-time monitoring data with preset matching thresholds, and combining dynamic refresh and rolling optimization mechanisms, the system can continuously optimize the selection of configuration parameter combinations. After each round of optimization, the system will determine whether further adjustments to the optimization strategy are needed through reverse verification and evaluation of the deviation improvement rate. If the optimization effect does not meet expectations, the system will accelerate the optimization process by updating the boundary constraints of the particle search space, ultimately ensuring that the personnel matching accuracy during task execution reaches the optimal state.

[0081] In summary, the embodiments of this application have at least the following technical effects:

[0082] This application achieves automated personnel selection by using a segmented selection configuration based on task requirements and personnel qualifications, combined with knowledge graphs and semantic matching, significantly improving the accuracy and efficiency of task matching. It ensures that personnel selection adapts to changes in task requirements by dynamically refreshing and continuously optimizing data in the task matching impact area in real time, based on preset matching thresholds and actual adaptation deviations. Furthermore, it optimizes resource allocation by considering factors such as personnel skills, equipment fault types, and task urgency, maximizing resource utilization and reducing personnel waste. Finally, by optimizing the matching of personnel skills with tasks, it reduces manual intervention, shortens task response time, and improves the overall execution efficiency of equipment maintenance tasks.

[0083] It achieves the technical effect of improving the accuracy and response speed of personnel selection through automated selection and dynamic optimization based on task requirements and real-time data.

[0084] Example 2, based on the same inventive concept as the automatic selection method for equipment maintenance personnel for energy service tasks in the foregoing examples, such as... Figure 2 As shown, this application provides an automatic selection system for equipment maintenance personnel for energy service tasks. The system and method embodiments in this application are based on the same inventive concept. The system includes:

[0085] The selection and configuration parameter setting module 11 is used to set segmented selection and configuration parameters related to skill certification segment, historical maintenance adaptation segment, and task response capability segment based on the maintenance task requirements of energy service equipment and personnel qualification access conditions.

[0086] The correction coefficient setting module 12 is used to set the first correction coefficient and the second correction coefficient based on the semantic matching characteristics of the maintenance resource knowledge graph and the task execution efficiency parameters.

[0087] The execution plan generation module 13 is used to reverse-parse the optimized selection configuration parameter combination into the segmented selection configuration parameters based on the first correction coefficient and the second correction coefficient, and generate an automatic personnel selection execution plan.

[0088] The selection parameter optimization module 14 is used to collect real-time monitoring data of various task matching influence areas, including personnel skill status, equipment failure type, and task urgency. Based on the preset matching threshold of the personnel automatic selection execution plan and the actual adaptation deviation, the selection configuration parameter combination is dynamically refreshed and continuously optimized.

[0089] Furthermore, the selection configuration parameter setting module 11 is also used to perform the following steps:

[0090] Based on the maintenance task requirements parameters of energy service equipment and the access conditions for personnel qualifications, a time-series equivalent analysis and sensitive matching point identification are performed on the fluctuation range of task complexity and the prediction error of personnel skill adaptation. Skill gaps and supply-demand matching critical points are calculated for each time period. Through the skill gaps and supply-demand matching critical points for each time period, the equipment maintenance task cycle is divided into skill certification segments, historical maintenance adaptation segments, and task response capability segments.

[0091] Furthermore, the correction coefficient setting module 12 is also used to perform the following steps:

[0092] Based on the semantic matching characteristics of the maintenance resource knowledge graph and combined with the task matching accuracy requirements, the knowledge graph correlation parameters and semantic mapping efficiency are detected in all dimensions to obtain the first correction coefficient; based on the task execution efficiency parameters and combined with historical task execution cycle data, the adaptation attenuation amount of different skill proficiency ranges is dynamically deduced to obtain the second correction coefficient.

[0093] Furthermore, the execution scheme generation module 13 is also used to perform the following steps:

[0094] Based on the first correction coefficient and skill adaptation gradient parameters, the second correction coefficient and collaboration adaptation gap, an association mapping matrix is ​​constructed; the coupling influence coefficient of the association mapping matrix is ​​used as the fitness function weight, and the minimization of personnel skill matching deviation, the maximization of collaboration utilization of the maintenance team, and the minimization of task response delay are taken as optimization objectives.

[0095] Furthermore, the execution scheme generation module 13 is also used to perform the following steps:

[0096] Based on the segmented selection configuration parameters, the task-driven semantic association matching flow distribution corresponding to personnel and skill association nodes is simulated and set using simulation to obtain skill adaptation gradient parameters that meet the semantic matching stability constraint; based on the segmented selection configuration parameters, the personnel and equipment association nodes of the maintenance resource knowledge graph are optimized using topology optimization to obtain collaborative adaptation gaps that meet the matching balance constraint, wherein the personnel and skill association nodes and the personnel and equipment association nodes are all located in the maintenance resource knowledge graph.

[0097] Furthermore, the execution scheme generation module 13 is also used to perform the following steps:

[0098] The matrix row dimension of the association mapping matrix is ​​the semantic matching compensation element category associated with the first correction coefficient, the semantic mapping efficiency compensation element category, the proficiency adaptation attenuation compensation element category associated with the second correction coefficient, and the task execution loop compensation element category; the matrix column dimension of the association mapping matrix is ​​the matching influence area of ​​the equipment maintenance task, including the personnel qualification node of the skill certification segment, the maintenance team cluster of the historical maintenance adaptation segment, and the flexible collaboration aggregate of the task response capability segment.

[0099] Furthermore, the execution scheme generation module 13 is also used to perform the following steps:

[0100] The range of values ​​for the first correction coefficient and the skill adaptation gradient parameter, and the range of values ​​for the second correction coefficient and the collaboration adaptation gap are used as the particle search space. Adaptive inertial weights are introduced for iterative optimization. The selected configuration parameter combination generated in each round of optimization is verified. If the simulation verification result meets the task matching accuracy requirement, the current selected configuration parameter combination is dynamically refreshed and the selected configuration parameter combination is output.

[0101] Furthermore, the execution scheme generation module 13 is also used to perform the following steps:

[0102] If the simulation verification results do not meet the task matching accuracy requirements, then based on the positioning deviation contribution of the correlation mapping matrix, the positioning deviation contribution is sorted from high to low to obtain the compensation element category sequence; local optimization is performed based on the compensation element category sequence until the number of iterations reaches a preset threshold. After that, the selection configuration parameter combination obtained by optimization is reverse-analyzed into the segmented selection configuration parameters to generate an automatic personnel selection execution scheme that includes a dynamic adaptation curve for skill certification segments, a tiered team combination scheme for historical maintenance adaptation segments, and a partitioned collaborative control strategy for task response capability segments.

[0103] Furthermore, the selection parameter optimization module 14 is also used to perform the following steps:

[0104] Using the parameter sensitivity of the association mapping matrix as the network input weight, the difference between the target value and the task matching accuracy requirement is used as the network input layer variable. After each round of refresh, the updated selection configuration parameter combination is substituted into the association mapping matrix for reverse verification to determine the deviation improvement rate of each task matching influence area. If the deviation improvement rate is lower than the preset improvement rate threshold, the boundary constraints of the particle search space are updated with the compensation element category sequence.

[0105] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, the above description focuses on specific embodiments of this specification. Additionally, the processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired results. In some implementations, multitasking and parallel processing are possible or may be advantageous.

[0106] The above description is only a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

[0107] This specification and accompanying drawings are merely illustrative examples of this application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from its scope. Therefore, if such modifications and variations fall within the scope of this application and its equivalents, this application intends to include such modifications and variations.

Claims

1. An automatic selection method for equipment maintenance personnel for energy service tasks, characterized in that, The method includes: Based on the maintenance task requirements of energy service equipment and the access conditions for personnel qualifications, set up segmented selection configuration parameters that are associated with skill certification segments, historical maintenance adaptation segments, and task response capability segments. Based on the semantic matching characteristics of the maintenance resource knowledge graph and the task execution efficiency parameters, a first correction coefficient and a second correction coefficient are set. Based on the first correction coefficient and the second correction coefficient, the optimized selection configuration parameter combination is reverse-analyzed into the segmented selection configuration parameter to generate an automatic personnel selection execution plan. Real-time monitoring data is collected for each task matching impact area, including personnel skill status, equipment failure type, and task urgency. Based on the preset matching threshold of the personnel automatic selection execution plan and the actual adaptation deviation, the selection configuration parameter combination is dynamically refreshed and continuously optimized.

2. The automatic selection method for equipment maintenance personnel for energy service tasks as described in claim 1, characterized in that, The method further includes setting segmented selection configuration parameters associated with skill certification segments, historical maintenance adaptation segments, and task response capability segments, and setting segmented selection parameters for each segment: Based on the maintenance task requirements of energy service equipment and the access conditions for personnel qualifications, a time series equivalence analysis and sensitive matching point identification are performed on the fluctuation range of task complexity and the prediction error of personnel skill adaptation, and the skill gap and supply-demand matching critical point are calculated for each time period. Based on the skill gaps and supply-demand matching critical points in each time period, the equipment maintenance task cycle is divided into skill certification segment, historical maintenance adaptation segment, and task response capability segment.

3. The automatic selection method for equipment maintenance personnel for energy service tasks as described in claim 1, characterized in that, The method for setting a first correction factor and a second correction factor includes: Based on the semantic matching characteristics of the maintenance resource knowledge graph and combined with the task matching accuracy requirements, the knowledge graph correlation parameters and semantic mapping efficiency are detected in all dimensions to obtain the first correction coefficient. Based on the task execution efficiency parameters and combined with historical task execution cycle data, the adaptation attenuation amount for different skill proficiency ranges is dynamically extrapolated to obtain the second correction coefficient.

4. The automatic selection method for equipment maintenance personnel for energy service tasks as described in claim 3, characterized in that, Based on the first correction coefficient and the second correction coefficient, the optimized selection configuration parameter combination is reverse-analyzed into the segmented selection configuration parameters. The method further includes: Construct an association mapping matrix based on the first correction coefficient and skill adaptation gradient parameters, the second correction coefficient and collaboration adaptation gap; Using the coupling influence coefficient of the aforementioned association mapping matrix as the fitness function weight, the optimization objectives are to minimize the personnel skill matching deviation corresponding to the equipment maintenance task, maximize the utilization rate of the maintenance team collaboration, and minimize the task response delay.

5. The automatic selection method for equipment maintenance personnel for energy service tasks as described in claim 4, characterized in that, Based on the first correction coefficient and skill adaptation gradient parameters, the second correction coefficient and collaboration adaptation gap, an association mapping matrix is ​​constructed. The method further includes: Based on the segmented selection configuration parameters, the task-driven semantic association matching flow distribution corresponding to personnel and skill association nodes is simulated and set to obtain skill adaptation gradient parameters that meet the semantic matching stability constraints. Based on the segmented selection configuration parameters, the personnel and equipment association nodes of the maintenance resource knowledge graph are optimized by topology optimization to obtain the collaborative adaptation gap that meets the matching balance constraint. The personnel and skill association nodes and the personnel and equipment association nodes are all located in the maintenance resource knowledge graph.

6. The automatic selection method for equipment maintenance personnel for energy service tasks as described in claim 5, characterized in that, The matrix row dimension of the association mapping matrix is ​​the semantic matching compensation element category associated with the first correction coefficient, the semantic mapping efficiency compensation element category, the proficiency adaptation attenuation compensation element category associated with the second correction coefficient, and the task execution loop compensation element category. The column dimension of the association mapping matrix is ​​the matching influence area of ​​the equipment maintenance task, including personnel qualification nodes of the skill certification segment, maintenance team clusters of the historical maintenance adaptation segment, and flexible collaborative aggregates of the task response capability segment.

7. The automatic selection method for equipment maintenance personnel for energy service tasks as described in claim 6, characterized in that, The method includes: The range of values ​​for the first correction coefficient and the skill adaptation gradient parameter, and the range of values ​​for the second correction coefficient and the collaborative adaptation gap are used as the particle search space, and adaptive inertia weights are introduced for iterative optimization. Each round of optimization generates a selection configuration parameter combination, which is then verified. If the simulation verification result meets the task matching accuracy requirements, the current selection configuration parameter combination is dynamically refreshed and the selection configuration parameter combination is output.

8. The automatic selection method for equipment maintenance personnel for energy service tasks as described in claim 7, characterized in that, The method further includes: If the simulation verification results do not meet the task matching accuracy requirements, then based on the positioning deviation contribution of the association mapping matrix, the compensation element category sequence is obtained by sorting the positioning deviation contribution from high to low. Local optimization is performed based on the compensation element category sequence until the number of iterations reaches a preset threshold. Then, the optimized selection configuration parameter combination is reverse-analyzed into the segmented selection configuration parameters to generate an automatic personnel selection execution plan that includes a dynamic adaptation curve for skill certification segments, a tiered team combination scheme for historical maintenance adaptation segments, and a partitioned collaborative control strategy for task response capability segments.

9. The automatic selection method for equipment maintenance personnel for energy service tasks as described in claim 8, characterized in that, The method for dynamically refreshing and continuously optimizing the selected configuration parameter combinations includes: The parameter sensitivity of the association mapping matrix is ​​used as the network input weight, and the difference between the target value and the task matching accuracy requirement is used as the network input layer variable. After each round of refresh, the updated selection configuration parameter combination is substituted into the association mapping matrix for reverse verification to determine the deviation improvement rate of each task matching influence area. If the deviation improvement rate is lower than the preset improvement rate threshold, the boundary constraints of the particle search space are updated using the compensation element category sequence.

10. An automatic selection system for equipment maintenance personnel for energy service tasks, characterized in that, The system includes: The selection and configuration parameter setting module is used to set segmented selection and configuration parameters related to skill certification segments, historical maintenance adaptation segments, and task response capability segments based on the maintenance task requirements of energy service equipment and personnel qualification access conditions. The correction coefficient setting module is used to set the first correction coefficient and the second correction coefficient based on the semantic matching characteristics of the maintenance resource knowledge graph and the task execution efficiency parameters. The execution plan generation module is used to reverse-parse the optimized selection configuration parameter combination into the segmented selection configuration parameters based on the first correction coefficient and the second correction coefficient, and generate an automatic personnel selection execution plan. The selection parameter optimization module is used to collect real-time monitoring data of various task matching influence areas, including personnel skill status, equipment failure type, and task urgency. Based on the preset matching threshold of the personnel automatic selection execution plan and the actual adaptation deviation, the module dynamically refreshes and continuously optimizes the selection configuration parameter combination.

Images