A power distribution network intelligent operation and maintenance closed-loop decision method and system

Abstract

The application provides a power distribution network intelligent operation and maintenance closed-loop decision method and system, and relates to the technical field of power system operation and maintenance management. The method comprises the following steps: calculating the matching degree of operation and maintenance personnel and maintenance tasks; determining potential executors according to the matching degree; determining target operation items according to the skill depth of the potential executors; obtaining key operation items and complexity indexes of the maintenance tasks; guiding the potential executors to perform the maintenance tasks according to the key operation items and the complexity indexes; collecting execution feedback of the maintenance tasks, and updating the skill depth of the operation and maintenance personnel performing the maintenance tasks according to the execution feedback. The method of the application aims to solve the problem of dynamic adaptation of personnel capability and task complexity in the prior art, avoids equipment damage or power supply interruption accidents caused by personnel misoperation, and improves the efficiency and safety of power distribution network operation and maintenance.

Description

Technical Field

[0001] This invention relates to the field of power system operation and maintenance management technology, and more specifically, to a closed-loop decision-making method and system for intelligent operation and maintenance of distribution networks. Background Technology

[0002] With the deepening of smart grid construction, distribution network operation and maintenance management faces technical challenges brought about by the mixed operation of traditional and new equipment. Existing intelligent operation and maintenance systems have revealed three key technical deficiencies in the process of equipment upgrades: First, the data parsing mechanism fails to adapt to the unique high-frequency, multi-dimensional characteristics of new equipment, leading to misjudgments or loss of key data such as transient parameter drift and electromagnetic interference characteristics of equipment like solid-state switches during the preprocessing stage. Second, health assessment models are still based on the failure modes of traditional equipment, failing to effectively identify the hidden degradation characteristics of new equipment such as composite material insulators, resulting in systematic biases in risk assessment results. Finally, the personnel skills management system has a blind spot in identifying theoretical training and practical operational capabilities; when core technical personnel are occupied with high-priority tasks, the system cannot accurately identify the actual operational capabilities of replacement personnel for specific new equipment.

[0003] More specifically, existing operation and maintenance decision-making systems suffer from broken closed-loop chains: in the task allocation stage, matching is based solely on static skill tags, failing to dynamically assess the real-time fit between personnel capabilities and task complexity; in the resource support stage, there is a lack of precise assistance mechanisms targeting skill gaps, making it difficult to obtain timely and effective technical support when personnel face operations beyond their capabilities; and in the feedback and optimization stage, a dynamic skill level update mechanism based on task execution results has not yet been established, leading to a disconnect between personnel capability assessments and actual performance. These problems are particularly prominent in the maintenance of new power distribution equipment, easily causing equipment damage or power outages due to human error.

[0004] There is currently no effective technical solution to the above problems. Summary of the Invention

[0005] The purpose of this invention is to provide a closed-loop decision-making method and system for intelligent operation and maintenance of power distribution networks, which aims to solve the problem of dynamic adaptation between personnel capabilities and task complexity in the prior art, avoid equipment damage or power outage accidents caused by personnel misoperation, and improve the efficiency and safety of power distribution network operation and maintenance.

[0006] In a first aspect, the present invention provides a closed-loop decision-making method for intelligent operation and maintenance of distribution networks, comprising the following steps: S1. Obtain the maintenance task for the target device and calculate the matching degree of all currently available maintenance personnel for the maintenance task; S2. If there is a target executor whose matching degree is greater than or equal to the preset matching degree threshold, then the target executor is assigned to perform the maintenance task; otherwise, steps S31-S37 are executed. S31. When the matching degree of all currently available maintenance personnel for the maintenance task is less than the preset matching degree threshold, resulting in the inability to assign a target executor to perform the maintenance task, the maintenance personnel with the highest matching degree among the currently available maintenance personnel shall be selected as potential executors. S32. Based on the potential executor's skill level regarding each operation of the target device, determine the operation items where the potential executor has skill deficiencies and designate them as target operation items; S33. Obtain the key operation items and complexity index of the maintenance task; S34. If the target operation item is related to the key operation item, and the complexity index is less than or equal to a preset index threshold, a first auxiliary resource package is generated based on the skill deficiency and the key operation, and the first auxiliary resource package is sent to the potential executor to guide the potential executor to perform the maintenance task; S35. If the target operation item is related to the key operation item, and the complexity index is greater than the preset index threshold, determine whether there are currently available operation and maintenance personnel who have a higher skill level in the target operation item than the potential executor and serve as assistant executors. S36. If it is determined that the auxiliary executor exists, then the auxiliary executor is assigned to jointly perform the maintenance task with the potential executor; otherwise, a second auxiliary resource package is generated and sent to the potential executor to guide the potential executor in performing the maintenance task. S37. Collect execution feedback of the maintenance task, and update the skill level of the maintenance personnel performing the maintenance task based on the execution feedback.

[0007] The intelligent operation and maintenance closed-loop decision-making method for distribution networks provided by this invention solves the problems in the prior art by dynamically evaluating the matching degree between the capabilities of operation and maintenance personnel and the complexity of maintenance tasks, and providing precise auxiliary resources when no personnel can be assigned.

[0008] Secondly, the present invention provides a closed-loop decision-making system for intelligent operation and maintenance of power distribution networks, comprising: The first acquisition module is used to acquire the maintenance tasks of the target device and calculate the matching degree of all currently available maintenance personnel for the maintenance tasks. The first matching module is used to assign the target executor to perform the maintenance task if there is a target executor whose matching degree is greater than or equal to a preset matching degree threshold; otherwise, the following second matching module, first determining module, second obtaining module, first control module, second determining module, second control module, and update module are run. The second matching module is used to select the operation and maintenance personnel with the highest matching degree from the currently available operation and maintenance personnel as potential executors when the matching degree of all the currently available operation and maintenance personnel for the maintenance task is less than the preset matching degree threshold, resulting in the inability to assign a target executor to perform the maintenance task. The first determining module is used to determine the operation items in which the potential executor has skill deficiencies based on the potential executor's skill depth in relation to various operations of the target device, and to designate them as target operation items; The second acquisition module is used to acquire the key operation items and complexity index of the maintenance task; The first control module is used to generate a first auxiliary resource package based on the skill deficiency and the key operation if the target operation item is related to the key operation item and the complexity index is less than or equal to a preset index threshold, and to send the first auxiliary resource package to the potential executor to guide the potential executor to perform the maintenance task. The second determining module is used to determine whether there are any maintenance personnel among the currently available maintenance personnel whose skill depth for the target operation item is higher than that of the potential executor, and to act as auxiliary executors, if the target operation item is related to the key operation item and the complexity index is greater than the preset index threshold. The second control module is configured to, if it is determined that the auxiliary executor exists, assign the auxiliary executor to perform the maintenance task together with the potential executor; otherwise, generate a second auxiliary resource package and send the second auxiliary resource package to the potential executor to guide the potential executor in performing the maintenance task. The update module is used to collect execution feedback of the maintenance task and update the skill level of the operation and maintenance personnel who perform the maintenance task based on the execution feedback.

[0009] As can be seen from the above, the intelligent operation and maintenance closed-loop decision-making method for distribution networks provided by the present invention effectively solves the core pain points in the operation and maintenance of new equipment through precise matching, dynamic assistance and closed-loop learning, significantly improves the intelligence level and reliability of distribution network operation and maintenance, and avoids equipment damage and power outage accidents caused by human error.

[0010] Other features and advantages of the invention will be set forth in the following description, and will be apparent in part from the description, or may be learned by practicing embodiments of the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the written description and the accompanying drawings. Attached Figure Description

[0011] Figure 1 This is a flowchart of a closed-loop decision-making method for intelligent operation and maintenance of power distribution networks provided in an embodiment of the present invention.

[0012] Figure 2 This is a schematic diagram of a closed-loop decision-making system for intelligent operation and maintenance of power distribution networks provided in an embodiment of the present invention.

[0013] Label Explanation: 100. First Acquisition Module; 200. First Matching Module; 300. Second Matching Module; 400. First Determination Module; 500. Second Acquisition Module; 600. First Control Module; 700. Second Determination Module; 800. Second Control Module; 900. Update Module. Detailed Implementation

[0014] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0015] It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this invention, terms such as "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0016] In the closed-loop decision-making process of intelligent operation and maintenance in power distribution networks, the introduction of new compact power distribution equipment presents a problem of mismatch between the data parsing logic and equipment characteristics in the existing system. Specifically, the data format, sampling frequency, and internal state parameters of the new equipment differ significantly from those of traditional equipment. This causes the data timing alignment logic to fail to correctly handle high-frequency data points, and the data parsing protocol to fail to identify unique parameters, resulting in deviations in the output of the comprehensive health status scoring function. Furthermore, the weight allocation of the scoring function is optimized for traditional equipment and cannot effectively capture early degradation signals of the new equipment, leading to the risk level determination rules incorrectly classifying high-risk tasks as low-priority tasks. Moreover, the matching table between personnel skills and task types uses coarse-grained recording, failing to distinguish between theoretical training and practical operational experience. This results in an inability to accurately assess the proficiency of maintenance personnel with specific new equipment during task allocation, thereby increasing the risk of operational errors.

[0017] For example, in a scenario where modular gas-insulated switchgear is deployed in a regional power distribution network, the equipment transmits multi-channel sensor data, including internal trace gas concentration and partial discharge spectrum, via a high-speed bus. However, the traditional timing alignment logic used by the system is based on fixed-period interpolation, causing key high-frequency data points to be ignored and discrepancies to occur in the time axis of data from different sensors. The data parsing protocol lacks a semantic definition for the characteristics of trace gas leakage, causing relevant data to be misjudged as noise and discarded. Consequently, the health scoring function, which does not incorporate this characteristic, continuously outputs a "normal" assessment result, and the risk assessment rules accordingly set the maintenance task as a low priority. Simultaneously, the personnel skills table only marks "gas-insulated switchgear maintenance" as "possible," without recording the engineer's operational experience with specific models. When core technical personnel are handling other high-priority tasks, the system assigns routine maintenance tasks to inexperienced teams. During parameter calibration, maintenance personnel, unfamiliar with the internal structure of the equipment, incorrectly adjust the configuration of the internal control unit, causing unexpected damage to the equipment.

[0018] If the above problems are not addressed, the hidden fault mechanisms of new equipment cannot be identified in a timely manner, and the deterioration process will continue to develop until a sudden failure occurs; mismatch of personnel skills will increase the probability of misoperation, leading to equipment damage and partial power outages; the closed-loop decision-making capability of intelligent operation and maintenance systems will be unable to adapt to the evolution of power grid equipment, affecting the overall reliability of power supply.

[0019] For reference, see the appendix. Figure 1 This invention provides a closed-loop decision-making method for intelligent operation and maintenance of power distribution networks, comprising the following steps: S1. Obtain the maintenance tasks for the target device and calculate the matching degree of all currently available maintenance personnel for the maintenance tasks. Specific steps include: S11. Obtain the capability level of all currently available maintenance personnel regarding the target equipment from the preset personnel capability information storage system; the capability level is calculated by weighted summation of the maintenance personnel's skill depth for each operation of the target equipment. S12. Calculate the complexity index of the maintenance task based on preset consideration dimensions; S13. Calculate the matching degree of each available operations and maintenance personnel for the maintenance task based on their capability level and complexity index; S2. If there is a target executor with a matching degree greater than or equal to the preset matching degree threshold, then assign the target executor to perform the maintenance task; otherwise, proceed to steps S31-S37. S31. When the matching degree of all currently available operation and maintenance personnel for maintenance tasks is less than the preset matching degree threshold, making it impossible to assign the target executor to perform the maintenance task, select the operation and maintenance personnel with the highest matching degree from the currently available operation and maintenance personnel as the potential executor. S32. Based on the potential executor's skill level regarding the various operations of the target equipment, identify the operational items where the potential executor has skill deficiencies and designate them as target operational items; S33. Obtain the key operational items and complexity index of the maintenance task; S34. If the target operation item is related to the key operation item, and the complexity index is less than or equal to the preset index threshold, a first auxiliary resource package is generated based on the skill gap and the key operation, and the first auxiliary resource package is distributed to the potential executor to guide the potential executor to perform the maintenance task; the first auxiliary resource package contains augmented reality operation guidance; S35. If the target operation item is related to the key operation item and the complexity index is greater than the preset index threshold, determine whether there are currently available operation and maintenance personnel who have a higher skill level in the target operation item than the potential executor and serve as assistant executors. S36. If an auxiliary executor is identified, the auxiliary executor is assigned to perform the maintenance task together with the potential executor; otherwise, a second auxiliary resource package is generated and distributed to the potential executor to guide the potential executor in performing the maintenance task; the second auxiliary resource package contains a video call link connecting with a remote auxiliary expert; S37. Collect execution feedback on maintenance tasks and update the skill level of the operations and maintenance personnel performing the maintenance tasks based on the execution feedback.

[0020] It should be noted that steps S31-S37 are steps performed when the matching degree of all available maintenance personnel for the maintenance task is less than the preset matching degree threshold, resulting in the inability to assign a target executor to perform the maintenance task. If a target executor can be assigned to perform the maintenance task in step S2, then steps S31-S37 do not need to be performed. Furthermore, this embodiment does not limit the updating of the target executor's skill depth. That is, in actual application, after performing the maintenance task and collecting the execution feedback of the maintenance task, the skill depth of the target executor can be updated, but it can also be left unupdated.

[0021] For ease of understanding, the following explains some key terms in this embodiment: "Maintenance tasks" refer to a series of operations involving the inspection, repair, maintenance, or replacement of equipment in a power distribution network. These tasks may include preventative maintenance, emergency repairs, and equipment upgrades, with the aim of ensuring the normal operation of power distribution network equipment and the reliability of power supply.

[0022] "Operation and maintenance personnel" refers to professional technicians responsible for performing distribution network maintenance tasks. These personnel typically possess certain electrical knowledge and operational skills, and are able to operate and maintain equipment in accordance with procedures.

[0023] "Matching degree" refers to the degree of fit between the skill level of operations and maintenance personnel and the requirements of maintenance tasks. A high matching degree indicates that the skills and experience of operations and maintenance personnel can well meet the task requirements, thereby improving the efficiency and quality of task execution.

[0024] "Preset matching threshold" refers to a matching standard value set by the system. When the matching degree of the maintenance personnel reaches or exceeds this threshold, it indicates that they have the ability to independently perform the maintenance task.

[0025] "Target executor" refers to the operation and maintenance personnel whose matching degree reaches or exceeds the preset matching degree threshold and who are assigned by the system to perform maintenance tasks.

[0026] The "Personnel Capability Information Storage System" is a database used to store and manage information such as the skills, experience, and qualifications of all operations and maintenance personnel. This information is an important basis for assessing the capability level of operations and maintenance personnel.

[0027] "Capability level" refers to the comprehensive skills and experience of operations and maintenance personnel in specific equipment or operations. It reflects the level of proficiency and professional knowledge that operations and maintenance personnel have in completing specific tasks.

[0028] "Skill depth" refers to the proficiency and mastery level of maintenance personnel in specific operations. For example, for a certain equipment operation, skill depth can be quantified by the degree of theoretical knowledge mastery, simulated operation proficiency, the quality and efficiency of actual maintenance task completion, and performance feedback automatically generated by senior experts or the system. These quantitative assessment results are stored in the personnel capability information storage system in the form of numerical values ​​(e.g., 0-100 points) or levels (e.g., L1-L5), and are associated with specific equipment models and operation types. For example, maintenance personnel Zhang San's skill depth in "parameter calibration of new solid-state switches" is L3 (independent operation), and his skill depth in "SF6 gas leakage detection of new gas-insulated switchgear" is L2 (auxiliary operation).

[0029] "Consideration dimensions" refers to the various factors considered when assessing the complexity of maintenance tasks, such as task type, equipment model, environmental conditions, and required tools.

[0030] The "complexity index" is a quantitative indicator of the difficulty and complexity of maintenance tasks. A high complexity index indicates that the task is difficult and requires a high level of skill from maintenance personnel.

[0031] "Potential executor" refers to the operations and maintenance personnel with the highest matching degree selected from the currently available personnel when no operations and maintenance personnel meet the preset threshold. Although this person may not fully meet the task requirements, they have relatively high execution potential.

[0032] "Skill gaps" refer to the lack of skills or experience that a potential performer has when performing a specific maintenance task, relative to the task requirements.

[0033] "Target operation item" refers to the specific operational steps where potential executors have skill gaps.

[0034] "Critical operation items" refer to the operation steps in maintenance tasks that have the greatest impact on the function, safety, or performance of the equipment.

[0035] The "preset index threshold" refers to a standard value used to judge the complexity of a task. When the complexity index is lower than or equal to this threshold, the task is considered relatively simple; otherwise, it is considered complex.

[0036] The "first support resource package" refers to the support resources provided to potential executors when the task complexity index is relatively low, such as augmented reality operation instructions.

[0037] "Augmented Reality Operation Guide" refers to the use of augmented reality technology to overlay virtual operation steps and prompts onto real devices, providing real-time and intuitive operation guidance for maintenance personnel.

[0038] "Assistant executor" refers to operations and maintenance personnel who are assigned to perform tasks jointly with potential executors when the task complexity is high. This person usually has a higher level of skill in areas where the potential executor has a skill gap.

[0039] The "second auxiliary resource package" refers to the auxiliary resources provided to potential executors when the task is highly complex and no auxiliary executor can be found, such as a video call link to connect with a remote auxiliary expert.

[0040] "Execution feedback" refers to the information collected by the system after a maintenance task is completed, including the task execution process, results, problems encountered, and the performance of the maintenance personnel.

[0041] "Update" refers to adjusting and optimizing the skill level of operations and maintenance personnel based on execution feedback, in order to achieve continuous improvement in personnel capabilities.

[0042] This application proposes a closed-loop decision-making method for intelligent operation and maintenance of distribution networks, which aims to solve the problems of data parsing mismatch, inaccurate health assessment, misjudgment of task priorities and mismatch of personnel skills caused by the introduction of new equipment in the intelligent operation and maintenance of distribution networks, thereby avoiding misoperation and equipment failure in maintenance tasks.

[0043] In practice, this method first acquires the maintenance tasks for the target equipment and calculates the matching degree of all available maintenance personnel for the tasks. The matching degree can be calculated in various ways. For example, it can simply compare the maintenance personnel's skill level with the skill level required for the task, or it can use a preset function model to weight the personnel's skill depth with the task's complexity indicators. Subsequently, the system assigns the maintenance task to a target executor with a matching degree greater than or equal to a preset matching degree threshold. For example, the system can convert the personnel's skill depth level for relevant equipment models and operation types into numerical values ​​based on their skill profiles, compare this value with the task complexity index, and select the maintenance personnel with the highest matching degree score (greater than or equal to 1) as the first choice. If multiple personnel meet the criteria, further filtering can be performed based on other factors (e.g., proximity to the task location, least recent workload).

[0044] When calculating the matching degree of maintenance personnel for maintenance tasks, the specific steps include: First, retrieving the capability levels of all currently available maintenance personnel regarding the target equipment from a pre-set personnel capability information storage system. Capability levels can be obtained in various ways, such as directly reading personnel skill levels stored in the system, or through a comprehensive evaluation of personnel's historical task performance, training records, etc. The capability level is calculated by weighted summation of the maintenance personnel's skill depth for each operation on the target equipment. For example, suppose the maintenance task of a new type of power distribution equipment includes three key operation items: operation item A (high-precision parameter calibration), operation item B (routine component inspection), and operation item C (complex fault diagnosis). The system pre-sets different weights for these operation items based on their complexity and importance: operation item A has a weight of 0.5, operation item B has a weight of 0.2, and operation item C has a weight of 0.3. Now consider maintenance personnel Zhang San. According to the personnel competency information storage system, Zhang San's skill depth in "New Solid State Switch Parameter Calibration" (corresponding to operation item A) is L3 (independent operation, quantifiable as 80 points), his skill depth in "New Gas Insulated Switchgear SF6 Gas Leakage Detection" (corresponding to operation item C) is L2 (auxiliary operation, quantifiable as 60 points), and his skill depth in "Routine Component Inspection" (corresponding to operation item B) is L4 (proficient operation, quantifiable as 90 points). Therefore, Zhang San's overall competency level for this new type of power distribution equipment can be calculated using a weighted summation: Competency Level = (Skill Depth of Operation Item A × Weight A) + (Skill Depth of Operation Item B × Weight B) + (Skill Depth of Operation Item C × Weight C) = (80 × 0.5) + (90 × 0.2) + (60 × 0.3) = 40 + 18 + 18 = 76 points. By using this weighted summation method, the system can obtain a value that accurately reflects Zhang San's comprehensive ability in handling the maintenance task of this new type of power distribution equipment, rather than just a general judgment of "can" or "cannot".

[0045] Secondly, based on preset consideration dimensions, the complexity index of the maintenance task is calculated. These dimensions can include task type, equipment model, environmental conditions, required tools, etc. The complexity index can be calculated using various methods such as expert scoring, analytic hierarchy process (AHP), or machine learning models. Finally, based on the capability level and complexity index, the matching degree of each available maintenance personnel for the maintenance task is calculated. The matching degree can be calculated using a simple ratio method, for example, matching degree = (capability level / complexity index), or a more complex fuzzy comprehensive evaluation method.

[0046] When the matching degree of all currently available operations and maintenance personnel for a maintenance task is less than a preset matching degree threshold, making it impossible to assign a target executor to perform the maintenance task, the system will select the operations and maintenance personnel with the highest matching degree from the currently available personnel as the potential executor. For example, the system can iterate through the matching degree of all available operations and maintenance personnel and select the one with the largest value as the potential executor.

[0047] Subsequently, based on the potential executor's skill level in each operation of the target equipment, the system identifies the operation items where the potential executor has skill gaps and designates them as target operation items. For example, the system can compare the potential executor's skill level in each operation with the minimum skill level required by the task, marking operation items below the minimum requirement as skill gaps.

[0048] Next, the system obtains the key operation items and complexity index of the maintenance task. The key operation items can be obtained based on preset task templates, expert experience, or historical data analysis. The complexity index is obtained in the same way as the calculation in the above steps.

[0049] If the target operation is related to a key operation and its complexity index is less than or equal to a preset threshold, the system will generate a first auxiliary resource package based on skill gaps and key operations. This first auxiliary resource package will then be distributed to potential executors to guide them in performing maintenance tasks. The first auxiliary resource package includes augmented reality operation guidance. For example, the auxiliary resource package may include step-by-step operation video tutorials or AR operation guidance. The resource library stores standardized video tutorials (e.g., MP4 format) and AR model data (e.g., GLTF format 3D models and ARKit / ARCore compatible overlay instructions) for various operations of new equipment. The system will automatically select the corresponding video or AR guidance based on the key operation points of the task and package them. For example, for "replacing the SF6 gas pressure sensor in a new type of gas-insulated switchgear," the system will provide a detailed AR operation guide, overlaying virtual disassembly and installation steps onto the real equipment through AR glasses and displaying bolt torque values ​​in real time.

[0050] It's important to clarify that "target operation item" refers to a specific operational step identified by the system based on a deep analysis of the potential executor's skills regarding various operations on the target equipment, indicating a lack of skill or proficiency on that step. This represents a specific weakness in the maintenance personnel's capabilities when performing a particular maintenance task. Secondly, "critical operation item" refers to the operational step within the maintenance task that has the most significant impact on equipment functionality, safe operation, or overall performance, and carries the highest operational requirements and risks. These critical operation items are typically identified by querying task operation specification databases, expert experience, or analyzing historical fault data. Therefore, "if the target operation item is related to the critical operation item" means that the potential executor's identified skill deficiency (i.e., the target operation item) happens to be one of the operational steps (i.e., the critical operation item) in the maintenance task that requires the highest skill and carries the greatest risk. This "relatedness" is not a vague connection, but rather a direct match or overlap between the skill deficiency and the task's critical points. For example, if a maintenance task is "replacing the internal control board of a new solid-state switch," and the potential executor lacks sufficient skill in "precision welding," the system will mark "precision welding" as the target operation item. Meanwhile, the system identified "control board welding" as a key operation point in the task of "replacing the internal control board of the new solid-state switch". In this case, "precision welding" as the target operation item and "control board welding" as the key operation item are defined as "related".

[0051] If the target operation is related to a critical operation and its complexity index exceeds a preset threshold, the system will determine whether there are currently available operations and maintenance (O&M) personnel whose skill level in the target operation is higher than that of the potential executor, and then act as assistant executors. For example, the system can iterate through the skill maps of all available O&M personnel to find those whose skill level in the target operation is higher than that of the potential executor.

[0052] If an auxiliary executor is identified, they are assigned to perform the maintenance task jointly with the potential executor. Otherwise, the system generates a second auxiliary resource package and distributes it to the potential executor to guide them in performing the maintenance task. The second auxiliary resource package contains a video call link connecting to a remote auxiliary expert. For example, the auxiliary resource package may contain a real-time video call link with a remote expert. The system generates a video call link with a unique session ID (e.g., a WebRTC-based link) and embeds it into the maintenance personnel's mobile application. When the maintenance personnel click the link, the system automatically connects to a currently online remote auxiliary expert with relevant "local skill depth" (e.g., theoretical knowledge or auxiliary operation experience with the new equipment). The remote expert can view the situation on-site in real-time via video and provide guidance.

[0053] Finally, the system collects execution feedback on maintenance tasks and updates the skill level of the maintenance personnel performing the tasks based on this feedback. For example, after completing a task on a mobile application, maintenance personnel will fill out a structured task feedback form. The form includes: task completion status (success / failure), main problems encountered, solutions taken, whether auxiliary resource packages were used, evaluation of the effectiveness of auxiliary resources, and a self-assessment of their skill level in the task. Simultaneously, the system automatically records the actual task time and geographical location information. If remote expert support is initiated during task execution, the remote expert will evaluate the effectiveness of the support, the performance of the maintenance personnel, and the task resolution through the expert feedback interface after the video call ends. The expert's evaluation results (e.g., rating the maintenance personnel's operational standardization, evaluating the accuracy of problem diagnosis) will be associated with the task record. Furthermore, new diagnostic ideas and maintenance techniques generated by the expert during the guidance process can be prompted by the system and structuredly entered into the "Activated Knowledge Base" for use in the subsequent generation of auxiliary resource packages. The system's background service will periodically (e.g., triggered immediately after task completion) process this feedback information. The system analyzes task completion quality, efficiency, problem-solving status, and expert evaluation results. For example, if an operations and maintenance (O&M) personnel successfully and efficiently completes a complex operation after using AR guidance, the system will determine that their "simulated operation proficiency" or "actual maintenance task completion quality" in that operation has improved. The system will fine-tune the depth of the O&M personnel's skill map based on a preset skill depth adjustment algorithm. For example, a simple incremental update rule can be used: New Skill Depth = Old Skill Depth + (Performance Score - Old Skill Depth) Learning Factor. Here, "Performance Score" is a quantitative value calculated based on task feedback and expert evaluation, and "Learning Factor" is a constant between 0 and 1 used to control the step size of skill depth updates. Through this continuous feedback and mechanism, the depth of the O&M personnel's skill map can accurately reflect their latest capability level. This not only provides a more accurate basis for subsequent task assignment but also incentivizes continuous learning and growth among O&M personnel, thereby effectively improving the entire O&M team's ability to maintain new equipment.

[0054] The following example will provide a more detailed explanation of the above technical solution: Suppose that in a certain power distribution network area, a new type of intelligent circuit breaker (target device) needs to undergo a complex firmware upgrade and maintenance task. This task requires a high level of professional skills from the operators and involves multiple high-precision operations.

[0055] First, the system acquires the firmware upgrade and maintenance task. The system retrieves the skill levels of all available maintenance personnel (e.g., maintenance personnel A, B, and C) regarding the new smart circuit breaker from the personnel capability information storage system. Maintenance personnel A's skill depth on this device is L3 (independent operation), maintenance personnel B's is L2 (assisted operation), and maintenance personnel C's is L1 (theoretical understanding). Simultaneously, based on preset consideration dimensions (e.g., firmware upgrade complexity, potential risks, required tools, etc.), the system calculates the complexity index of this maintenance task to be 0.7.

[0056] Next, the system calculates the matching degree of each operations and maintenance personnel for the task based on their skill level and task complexity index. Let's assume the calculation results are: operations and maintenance personnel A has a matching degree of 0.85, operations and maintenance personnel B has a matching degree of 0.6, and operations and maintenance personnel C has a matching degree of 0.3. The preset matching degree threshold is 0.8.

[0057] Because the matching score of maintenance personnel A (0.85) is greater than or equal to the preset matching score threshold of 0.8, the system assigns maintenance personnel A as the target executor to perform the firmware upgrade and maintenance task. After receiving the task, maintenance personnel A goes to the site to perform the task according to the operation instructions provided by the system.

[0058] In another scenario, suppose the complexity index of the firmware upgrade task is higher, at 0.9. In this case, the matching degree of operations personnel A might only be 0.75, that of operations personnel B might be 0.5, and that of operations personnel C might be 0.2. Since the matching degree of all operations personnel is less than the preset matching degree threshold of 0.8, it is impossible to assign a target executor.

[0059] In this scenario, the system will select the most compatible operations and maintenance personnel (A) from the currently available personnel as the potential executor.

[0060] Subsequently, based on the skill level of maintenance personnel A regarding various operations of the new intelligent circuit breaker, the system identified the operation items where their skills were lacking. For example, the system analysis found that maintenance personnel A's skill level in the operation item "configuring the communication module parameters of the new intelligent circuit breaker" was only L2, while the task requirement was L3. Therefore, "configuring the communication module parameters" was identified as the target operation item.

[0061] Meanwhile, the system obtains the key operation items for this firmware upgrade and maintenance task, which includes "communication module parameter configuration," and the complexity index of this task is 0.9. The preset index threshold is 0.6.

[0062] Since the target operation item "Communication Module Parameter Configuration" is related to critical operation items, and its complexity index of 0.9 is greater than the preset index threshold of 0.6, the system will further determine whether there are any available maintenance personnel whose skill depth in the target operation item is higher than that of maintenance personnel A, and who can then act as an assistant executor. The system query found that maintenance personnel B's skill depth in "Communication Module Parameter Configuration" is L3, which is higher than that of maintenance personnel A (L2).

[0063] Therefore, the system assigns maintenance personnel B as an assistant executor to jointly perform the firmware upgrade and maintenance task with the potential executor, maintenance personnel A. Maintenance personnel A and B collaborate, with B responsible for the crucial and complex step of "communication module parameter configuration," while A handles other operations, ensuring the task is completed successfully.

[0064] If the system query finds that none of the currently available operations and maintenance (O&M) personnel possess a higher skill level than O&M personnel A for the target operation, the system will generate a second auxiliary resource package and distribute it to the potential executor, O&M personnel A. This second auxiliary resource package contains a video call link connecting with a remote expert. When O&M personnel A executes the "communication module parameter configuration" step, they can use this link to conduct a real-time video call with the remote expert, obtaining remote guidance and support, thereby overcoming skill gaps and completing the task.

[0065] Upon completion of the task, the system will collect execution feedback on the firmware upgrade and maintenance task, including task completion status, problems encountered, and the performance of maintenance personnel A and B. Based on this execution feedback, the system will update the skill depth of maintenance personnel A and B in various operations of the new smart circuit breaker. For example, maintenance personnel A's skill depth in "communication module parameter configuration" may increase from L2 to L2.5, and maintenance personnel B's skill depth may also be consolidated or improved due to successful assistance.

[0066] The above technical solution achieves intelligent matching of operation and maintenance tasks and personnel through a closed-loop decision-making process, and dynamically provides auxiliary resources, effectively solving the risk of misoperation caused by the conflict between the characteristics of new equipment and traditional rules.

[0067] Compared with traditional existing operation and maintenance methods, the solution proposed in this application has significant technical contributions. Traditional methods, when faced with new equipment, often suffer from incompatible data parsing and inaccurate health assessments, leading to misjudgments of task priorities. This results in complex maintenance tasks being assigned to maintenance personnel with incompatible skills, potentially causing operational errors and equipment failures. For example, in traditional solutions, if a firmware upgrade task for a new smart circuit breaker is incorrectly assessed as low-risk, the system may assign it to any available maintenance personnel without thoroughly analyzing their skill gaps.

[0068] This application achieves precise matching between operations and maintenance (O&M) personnel and tasks by introducing a refined assessment of their skill levels and a task complexity index calculation. When the initial matching is insufficient, the system can intelligently identify potential skill gaps in executors and dynamically provide differentiated auxiliary resources based on task complexity. For example, for tasks with low complexity but skill gaps, augmented reality operation guidance is provided, enabling O&M personnel to receive visual, real-time operational instructions on-site to compensate for skill deficiencies. For tasks with high complexity, priority is given to mobilizing auxiliary executors with complementary skills for collaborative work, or remote expert support is provided to ensure the safe execution of high-risk tasks. This dynamic and intelligent auxiliary mechanism is unmatched by traditional solutions that simply assign tasks or provide only static documents.

[0069] Furthermore, this application introduces a mechanism for collecting task execution feedback and updating the skill depth of operations and maintenance personnel, forming a closed loop of continuous learning and optimization. This allows the capabilities of operations and maintenance personnel to continuously improve as tasks are completed, and the system's assessment of personnel capabilities becomes more accurate, thereby fundamentally reducing the risk of operational errors caused by mismatched personnel skills. Traditional solutions often lack this dynamic learning and feedback mechanism, resulting in lagging updates to personnel skill maps and an inability to adapt to the rapidly evolving needs of new equipment.

[0070] In summary, the intelligent operation and maintenance closed-loop decision-making method for distribution networks proposed in this application effectively solves the core pain points in the operation and maintenance of new equipment through precise matching, dynamic assistance, and closed-loop learning. It significantly improves the intelligence level and reliability of distribution network operation and maintenance, and avoids equipment damage and power outages caused by human error. It has outstanding technological progress and practical value.

[0071] In some embodiments, the specific steps in step S13 include: S131. Based on the capability level and complexity index, calculate the skill gap of each available maintenance personnel for maintenance tasks; S132. Based on the skill gap, assess the potential for skill improvement that each maintenance personnel may gain after performing maintenance tasks; where the skill gap is within a preset challenge range, the potential for skill improvement is high; when the skill gap exceeds the challenge range, the potential for skill improvement is low. S133. Using skill enhancement potential as a weighting factor, combined with ability level and complexity index, calculate the matching degree of each currently available operations and maintenance personnel for maintenance tasks.

[0072] The competence level of maintenance personnel refers to their comprehensive skill proficiency in specific equipment or operations. It reflects their theoretical knowledge, practical experience, and problem-solving abilities regarding various operations of the target equipment. Competence levels can be assessed through methods including, but not limited to: regular skills assessments and certifications, evaluations based on historical task completion and training records, or weighted summation calculations of skill depth across different operations using expert systems. The complexity index of a maintenance task is a quantitative indicator measuring the difficulty, breadth, and depth of skills required for that task. It can be calculated based on preset consideration dimensions, including but not limited to: the type of equipment involved, the number of operational steps, operational precision requirements, potential risk levels, and the specialization of required tools. The complexity index can be calculated through expert scoring, historical task data analysis, or comprehensive evaluation of task characteristics using machine learning models. The skills gap refers to the difference between the competence level of maintenance personnel and the complexity index of maintenance tasks. This indicator quantifies the distance between the current skills of maintenance personnel and the skills required to complete a specific maintenance task. Skill gaps can be calculated by directly subtracting or ratioing the numerical value of an operations and maintenance (O&M) personnel's skill level to the complexity index of the maintenance task. Skill improvement potential refers to the potential increase or learning value an O&M personnel's skill level can achieve after performing a specific maintenance task. This potential is not fixed but closely related to the skill gap. When the difficulty of the task matches the O&M personnel's current capabilities—that is, when the skill gap is within a moderately challenging range—the O&M personnel can overcome difficulties and achieve significant improvement through effort, resulting in high potential. If the task is too easy or too difficult, the improvement potential is low. A preset challenge range is a threshold range defining the scope of the skill gap. This range aims to identify maintenance tasks that are neither too easy (leading to no learning value) nor too difficult (leading to incompetence or frustration) for the O&M personnel. For example, this range can be set based on historical data analysis, expert experience, or educational psychology theories to ensure that the tasks have an appropriate level of challenge, thereby maximizing the skill improvement effect. A weighting factor is a multiplier or coefficient used to adjust the matching degree calculation. In this scheme, skill enhancement potential is used as a weighting factor to adjust the traditional matching degree calculation results based on the growth value that operations and maintenance personnel may gain in the task. For example, when the skill enhancement potential is high, the weighting factor can be a value greater than 1, thereby improving the matching degree of the operations and maintenance personnel; when the potential is low, the weighting factor can be a value less than or equal to 1. The matching degree is a comprehensive indicator that measures the suitability between operations and maintenance personnel and maintenance tasks. In this scheme, the matching degree not only considers the direct relationship between the operations and maintenance personnel's ability level and the task complexity index, but also incorporates the dynamic factor of skill enhancement potential.By using skill enhancement potential as a weighting factor, the matching degree can more comprehensively reflect the rationality of task assignment, taking into account both the current task completion efficiency and the long-term development of operations and maintenance personnel.

[0073] The solution in this application, through the aforementioned mechanism, ensures that the matching degree calculation is not merely a reflection of current competence, but incorporates personnel development potential. Specifically, in the process of acquiring the maintenance task for the target equipment, calculating the matching degree of all currently available maintenance personnel for the maintenance task, and assigning a target executor with a matching degree greater than or equal to a preset matching degree threshold to perform the maintenance task, the system first calculates the competence level based on a weighted sum of the skill depth of each currently available maintenance personnel regarding various operations on the target equipment, and the complexity index of the maintenance task calculated based on preset consideration dimensions. Based on this, the solution in this application calculates the skill gap of each currently available maintenance personnel for the maintenance task. This skill gap directly quantifies the difference between the maintenance personnel's current capabilities and the task requirements, providing an accurate basis for subsequent potential assessment. Subsequently, based on this skill gap, the system assesses the potential for skill improvement that each maintenance personnel may gain after performing the maintenance task. Specifically, when the skill gap falls within a preset challenge range, the system determines that the task presents a moderate challenge to maintenance personnel, effectively promoting their skill improvement, thus indicating a high potential for skill enhancement. Conversely, when the skill gap exceeds the challenge range (i.e., the task is too easy or too difficult), the potential for skill enhancement is low. Ultimately, the system uses the assessed skill enhancement potential as a weighting factor, combining it with the maintenance personnel's skill level and the complexity index of the maintenance task, to recalculate the matching degree of each available maintenance personnel for the maintenance task. When a maintenance personnel's skill level and the task complexity index have a moderate skill gap, indicating a high potential for skill enhancement, even if their initial matching degree is not the highest, their weighted matching degree will be improved. This allows the system to balance the immediate completion efficiency of tasks with the long-term training of maintenance personnel when assigning maintenance tasks, thereby avoiding resource waste or operational risks and promoting skill improvement and efficient task execution. This decision-making mechanism helps build a continuously learning and growing maintenance team, reduces over-reliance on a few core personnel, and enhances the resilience and adaptability of the entire power distribution network maintenance system.

[0074] As a specific implementation method, suppose a power distribution network intelligent operation and maintenance system receives a "parameter calibration" maintenance task for a new type of solid-state switch, with a complexity index of 0.7. Three maintenance personnel, A, B, and C, are currently available. The system first retrieves the skill depth of the three personnel regarding the "new type of solid-state switch parameter calibration" operation from the personnel capability information storage system and calculates their capability level. For example, maintenance personnel A's capability level is 0.9 (experienced), maintenance personnel B's capability level is 0.6 (some experience), and maintenance personnel C's capability level is 0.3 (newcomer). Next, the system calculates the skill gap for each maintenance personnel for this maintenance task based on their capability level and complexity index. For example, maintenance personnel A's skill gap is 0.9 - 0.7 = 0.2; maintenance personnel B's skill gap is 0.6 - 0.7 = -0.1; and maintenance personnel C's skill gap is 0.3 - 0.7 = -0.4. Then, the system assesses the skill improvement potential of each operations and maintenance (O&M) personnel based on a preset challenge range (e.g., a higher skill improvement potential when the skill gap is between -0.2 and 0.1). For example, O&M personnel A has a skill gap of 0.2, exceeding the challenge range, therefore their skill improvement potential is low (e.g., a weighting factor of 1.0); O&M personnel B has a skill gap of -0.1, within the challenge range, therefore their skill improvement potential is high (e.g., a weighting factor of 1.2); O&M personnel C has a skill gap of -0.4, exceeding the challenge range (the task may be too difficult), therefore their skill improvement potential is low (e.g., a weighting factor of 0.9). Finally, the system uses the skill improvement potential as a weighting factor, combined with the capability level and complexity index, to calculate the matching degree of each O&M personnel for the maintenance task. The basic matching degree calculation formula is assumed to be: Basic Matching Degree = Capability Level / Complexity Index. The weighted matching degree for operations and maintenance personnel A is (0.9 / 0.7)*1.0≈1.28; the weighted matching degree for operations and maintenance personnel B is (0.6 / 0.7)*1.2≈1.03; and the weighted matching degree for operations and maintenance personnel C is (0.3 / 0.7)*0.9≈0.39. Through the above calculations, although operations and maintenance personnel A has the highest basic matching degree, their weighted matching degree is significantly improved, even surpassing that of operations and maintenance personnel A, because operations and maintenance personnel B has higher potential for skill improvement in this task. Therefore, when assigning tasks, the system can prioritize operations and maintenance personnel B, thus promoting their skill development while completing the task.

[0075] Through the aforementioned technical solution, this application effectively addresses the problem in traditional methods where the potential value of tasks for improving the skills of maintenance personnel is not considered, leading to a tendency for the system to repeatedly assign experienced personnel while neglecting the development of newcomers through reasonably challenging tasks. Specifically, by introducing the calculation of skill gaps, the difference between the current capabilities of maintenance personnel and task requirements can be accurately quantified, laying the foundation for subsequent potential assessment. Based on this, by evaluating skill improvement potential and incorporating it as a weighting factor into the matching degree calculation, task assignment decisions are no longer solely based on immediate competence but also consider the long-term development and training value of maintenance personnel. This allows the system to identify and prioritize tasks that are moderately challenging for maintenance personnel and can effectively promote their skill improvement, thus avoiding the drawback of overburdening experienced personnel while depriving newcomers of growth opportunities. Ultimately, the solution proposed in this application optimizes the task allocation for maintenance personnel, promotes a balanced improvement in the overall skill level of the maintenance team, enhances the team's adaptability and resilience, reduces reliance on a few core personnel, and provides more reliable human resource support for the long-term stable operation of the power distribution network.

[0076] In some embodiments, the specific steps in step S34 include: S341. For high-precision operation items in maintenance tasks, obtain the operation point environmental parameters of the high-precision operation items, and calculate the rate of change of the operation point environmental parameters; S342. Determine the stability of the operating environment based on the rate of change; S343. When the stability of the operating environment does not meet the preset high-precision operation requirements, generate an augmented reality operation guide containing an operation timing lock instruction so that the augmented reality terminal can pause high-precision operation; S344. When the stability of the operating environment meets the requirements of high-precision operation, determine whether there is an environmental deviation between the actual environment and the ideal standard environment, and when there is an environmental deviation, calculate the calibration parameter compensation value for high-precision operation based on the environmental deviation, and generate augmented reality operation guidance containing the calibration parameter compensation value so that the augmented reality terminal displays the calibration parameter compensation value on the augmented reality interface. S345. A first auxiliary resource package containing operation timing lockout instructions or calibration parameter compensation values ​​is sent to potential executors to guide them in performing maintenance tasks.

[0077] In step S341, "high-precision operation items" refer to maintenance task sub-items that have strict requirements on operating environment conditions, the precision of operating steps, and the accuracy of operating results, such as sensor calibration and the installation and debugging of precision components in new power distribution equipment. "Operating point environmental parameters" refer to physical environmental quantities that directly affect the accuracy of operation and equipment performance when performing high-precision operation items, and may include, but are not limited to, temperature, humidity, air pressure, and light intensity. These parameters can be obtained through a dedicated sensor network deployed near the operating point, or through real-time data collection via environmental sensors integrated into augmented reality terminals worn by maintenance personnel. "Calculating the rate of change of the operating point environmental parameters" refers to calculating the time derivative of the real-time acquired environmental parameters to quantify how quickly the environmental parameters change over time. For example, for temperature parameters, the instantaneous rate of temperature change (dT / dt) can be calculated to capture the dynamic trend of environmental changes.

[0078] It's important to note that in practical applications, a "preset task operation specification database" can be used to identify or determine which operations are considered high-precision. This database stores the operation specifications for various maintenance tasks and their sub-items, and quantifies the "operational precision" of each operation. "Operational precision" is a dimension considered in calculating the complexity index of a maintenance task; it directly reflects the precision requirements of the operation. For maintenance task sub-items with strict requirements on operating environment conditions, the precision of operating steps, and the accuracy of operating results, a higher "operational precision" value will be assigned in the preset task operation specification database. For example, in the database, operations like "parameter calibration" might be set with a high operational precision value because it requires precise adjustment of equipment parameters; any slight deviation can affect equipment performance. In contrast, operations like "visual inspection" have lower precision requirements, and therefore their operational precision values ​​in the database will be correspondingly lower. Therefore, when the system acquires a maintenance task, it will query the "operational precision" values ​​of each operation included in the task in the "preset task operation specification database." Operations marked as having high operational precision are identified by the system as "high-precision operations." This pre-setting and quantification mechanism ensures consistency and objectivity in the identification of high-precision operations, providing a basis for subsequent environmental stability assessments and calibration parameter compensation.

[0079] In step S342, "judging the stability of the operating environment" refers to assessing whether the current operating environment meets the environmental conditions required for high-precision operation based on the calculated rate of change of environmental parameters. The judgment criterion is usually a preset critical threshold. For example, if the absolute value of the temperature change rate remains below a certain small threshold, the environment is considered stable; conversely, if the change rate exceeds this threshold, the environment is considered unstable. This judgment can be implemented using rule-based logic or fuzzy logic.

[0080] In step S343, "generating augmented reality operation guidance containing an operation timing lock instruction" means that when environmental instability is detected, the system automatically generates and updates the content of the augmented reality operation guidance to include a clear instruction to temporarily interrupt or prevent maintenance personnel from continuing to perform the current high-precision operation. This instruction can manifest as a visual warning, an auditory warning, or an operation disablement. "Pausing the high-precision operation on the augmented reality terminal" means that after receiving the operation timing lock instruction, the augmented reality terminal, through its display interface and interactive functions, prevents maintenance personnel from performing the next operation, such as disabling operation buttons on the AR interface or freezing the display of operation steps.

[0081] In step S344, "determining whether there is an environmental deviation between the actual environment and the ideal standard environment" refers to further comparing the differences between the environmental parameters of the current operating point and the ideal standard environmental parameters required for the high-precision operation after confirming environmental stability. The ideal standard environmental parameters are usually specified by the equipment manufacturer or industry standards. "Calculating the calibration parameter compensation value for the high-precision operation" means that when an environmental deviation exists, the system dynamically calculates the correction value for the calibration parameters required for the high-precision operation based on the amount of deviation. For example, for sensor calibration, it may be necessary to adjust the zero-point drift or range coefficient accordingly. The calculation can be based on a pre-established environment-calibration parameter compensation model. "Generating augmented reality operation guidance containing the calibration parameter compensation value" means that the system integrates the calculated calibration parameter compensation value into the augmented reality operation guidance, presenting it to maintenance personnel in an intuitive and clear manner. "Displaying the calibration parameter compensation value on the augmented reality interface" means that the augmented reality terminal displays the received guidance containing the compensation value to maintenance personnel in real time through its optical display or projection system, overlaying virtual information onto the real-world view.

[0082] In step S345, "issuing the first auxiliary resource package containing the operation timing lock command or the calibration parameter compensation value to the potential executor" means that the system will transmit augmented reality operation instructions containing specific instructions, dynamically generated according to the current environmental conditions, to the augmented reality terminal worn by the potential executor via a wireless network. "To guide the potential executor in performing the maintenance task" means that by issuing these dynamically adjusted augmented reality operation instructions, precise and real-time operation guidance is provided to the potential executor, ensuring that they can accurately and safely complete the high-precision maintenance task.

[0083] The entire process forms a dynamic, adaptive closed loop, integrating environmental perception, intelligent judgment, operational intervention, and precise guidance. In this way, the proposed solution effectively addresses the impact of external environmental factors on high-precision maintenance tasks, ensuring that even those with skill deficiencies can complete tasks in a controlled and accurate environment, significantly improving the reliability and accuracy of intelligent operation and maintenance of the distribution network.

[0084] The following is a concrete example. In a maintenance task involving zero-point drift calibration of the SF6 gas pressure sensor in a new modular gas-insulated switchgear, this task was identified as a high-precision operation. First, a network of miniature high-frequency environmental sensors deployed near the switchgear's operating point collects parameters such as ambient temperature, humidity, and air pressure in real time. For example, a MEMS-based temperature sensor collects temperature data 10 times per second. An integrated low-power edge computing unit calculates the instantaneous rate of temperature change (dT / dt) in real time, for example, by dividing the difference between the current temperature and the temperature one second ago by the sampling time interval. If the absolute value of the temperature change rate is less than 0.01 degrees Celsius per second for five consecutive seconds, the edge computing unit initially marks it as "preliminarily stable environment." This pre-processed environmental data and stability markers are transmitted in real time via the LoRaWAN protocol to an augmented reality terminal worn by maintenance personnel. The augmented reality terminal worn by the maintenance personnel, such as a Microsoft HoloLens 2, runs an AR operation guidance application that receives this environmental data in real time. The calibration condition judgment logic within this AR application determines whether the rate of change of ambient temperature meets the critical threshold according to the stringent requirements of the SF6 gas pressure sensor calibration procedure. For example, if the procedure requires a temperature change rate of less than 0.5 degrees Celsius per minute (i.e., 0.0083 degrees Celsius per second), and the real-time dT / dt received by the AR application exceeds this value, the environment is deemed unstable. When the environment is unstable, the AR application immediately activates a timing lockout mechanism. At this time, the AR interface will display a prominent red flashing "Pause" icon and the text "Environment unstable, calibration operation paused, please wait" superimposed on the sensor location of the switch cabinet in the operator's field of vision. Simultaneously, a voice warning will be played through the AR terminal's speaker: "Attention! Ambient temperature fluctuations are too rapid, unsuitable for high-precision calibration, please wait for the environment to stabilize." Furthermore, the AR application will temporarily disable all interactive buttons or gesture recognition related to the current calibration step, preventing the operator from continuing to the next step. Only when the environmental stability judgment logic reconfirms that the environmental conditions meet the calibration requirements will the AR application automatically release the timing lock and display a green message "Environment stable, operation can continue," while simultaneously re-enabling the operation interaction. When the environmental conditions meet the calibration requirements but there are still minor environmental deviations, such as a stable temperature but a difference of 2 degrees Celsius from the standard calibration temperature, the AR operation guidance system will activate the dynamic compensation mechanism for calibration parameters. This mechanism is based on an "environment-calibration parameter compensation model" pre-stored on the AR terminal or obtained from the cloud.For example, the model might be a function: P_compensated = P_nominal + C_T(T_current - T_reference), where P_compensated is the compensated calibration parameter, P_nominal is the nominal calibration parameter under standard conditions (the nominal calibration parameter under standard conditions refers to the reference calibration value that a high-precision operation item (such as sensor calibration) should achieve under ideal or standard environmental conditions. It represents the theoretical or expected calibration result of the device when there is no environmental interference or when it is in its optimal design environment. This parameter is usually predefined and provided by the device manufacturer in its technical specifications and calibration manual. It can also be determined by conducting extensive experimental tests in a strictly controlled standard laboratory environment to ensure that the calibration results under standard conditions have a high degree of accuracy and repeatability), and C_T is the temperature compensation coefficient (temperature compensation coefficient). The coefficient of performance (T_compensation) refers to the scaling factor that the calibration parameters need to be adjusted as the temperature changes. It quantifies the extent to which the calibration parameters need to be corrected when the actual ambient temperature deviates from the standard calibration reference temperature. The temperature compensation coefficient is generally obtained directly from experiments or equipment manufacturer data. T_current is the current ambient temperature, and T_reference is the standard calibration reference temperature (the standard calibration reference temperature is the reference temperature used for high-precision operations (such as sensor calibration). It is a reference point in the compensation model used to measure the degree of deviation of the current ambient temperature from the standard. This parameter is usually specified by the equipment manufacturer in its technical specifications or calibration procedures. It can also be a temperature point that best represents the stable working state of the equipment or the best calibration effect, determined according to industry standards or through extensive experiments on the performance characteristics of the equipment at different temperatures). Ambient deviation = T_current - T_reference. The AR application will obtain the current ambient temperature T_current in real time and substitute it into the compensation model to calculate the accurate P_compensated value. Then, the AR interface will display this dynamically compensated calibration parameter in the form of virtual text in real time in the view of the maintenance personnel, for example: "Please adjust the zero drift compensation value to: +0.025kPa". Maintenance personnel can directly input or adjust the compensation values ​​displayed in AR. Finally, the system will send a first auxiliary resource package containing the above-mentioned operation timing lockout command or calibration parameter compensation values ​​to the potential executor to guide them in performing the maintenance task of zero-point drift calibration of the SF6 gas pressure sensor.

[0085] Through the above technical solution, this application effectively addresses the operational accuracy issues arising from dynamic external environmental factors when performing high-precision maintenance tasks on new power distribution equipment in intelligent operation and maintenance of power distribution networks. By sensing environmental parameters at the operation point in real time and calculating their rate of change, the system can dynamically assess the stability of the operating environment, thereby avoiding high-risk operations during environmental fluctuations. When the environment is unstable, the operation timing lockout command can forcibly suspend high-precision operations, effectively preventing potential operator errors due to environmental factors. When the environment is stable but deviations exist, the generation and display of calibration parameter compensation values ​​provide precise correction guidance for maintenance personnel, ensuring the actual accuracy of high-precision operations. This dynamic and adaptive auxiliary mechanism significantly improves the success rate and safety of high-precision maintenance tasks, avoids the persistence of calibration deviations caused by environmental factors, thus ensuring the accuracy of equipment health assessments and providing a reliable basis for subsequent operation and maintenance decisions.

[0086] In some embodiments, the specific steps in step S35 include: S351. Obtain the real-time location information of all currently available maintenance personnel; S352. Obtain the on-site location information for the maintenance task; S353. Based on the real-time location information of each available maintenance personnel and the on-site location information of the maintenance task, calculate the estimated travel time for each available maintenance personnel to reach the on-site location; S354. Obtain the current task load information of each available maintenance personnel; S355. Assess the auxiliary response capabilities of each available maintenance personnel by comprehensively considering the estimated travel time, current task load information, and skill depth of the target operation item; S356. Based on the auxiliary response capability, determine whether there are currently available operations and maintenance personnel whose skill depth for the target operation item is higher than that of the potential executor, and serve as auxiliary executors.

[0087] This solution aims to acquire the geographic coordinates of all maintenance personnel currently available for dispatch to perform auxiliary tasks. Real-time location information can be obtained from various positioning technologies, such as GPS or BeiDou satellite navigation modules built into the smart terminals worn by maintenance personnel; approximate locations can be obtained through mobile communication networks; or precise location sensing can be achieved indoors or in localized areas using Bluetooth beacons or RFID tags deployed within the power distribution network. This location data is typically uploaded in real-time to the central dispatch system or location service platform via a wireless network in the form of latitude and longitude coordinates. Simultaneously, this solution aims to pinpoint the specific location of the maintenance tasks requiring assistance. The on-site location information of maintenance tasks can be pre-stored in the task management system. For example, dispatchers can manually input the geographic coordinates or detailed address of the equipment when the task is created; alternatively, integration with the power distribution network geographic information system (GIS) can automatically query the precise geographic coordinates of the target equipment based on its unique identifier. This location information also exists in the form of latitude and longitude coordinates or addresses that can be converted to coordinates, serving as the basis for calculating the distance between maintenance personnel and the task location. Based on this, the solution aims to quantify the time required for maintenance personnel to travel from their current location to the task site. The calculation of estimated travel time can be based on various algorithms and data sources. One approach is to utilize online map service APIs, inputting the real-time location of the operations and maintenance personnel and the location of the task site, and considering real-time traffic conditions, vehicle type, and a preset travel speed model for estimation. Another approach combines historical traffic data and machine learning models to predict travel time for different time periods and road segments. The calculation results are typically expressed in minutes or hours, reflecting the physical accessibility of the operations and maintenance personnel. Furthermore, this solution aims to understand the current workload of operations and maintenance personnel. Current task load information can include the number of tasks being performed by the personnel, the urgency of the tasks, the estimated completion time, and the total workload allocated to them within the current work cycle. This information can be obtained from task scheduling systems, personnel scheduling systems, or workflow management systems. For example, the system can record the list of unfinished tasks currently being processed by each operations and maintenance personnel and calculate a comprehensive task load index based on the complexity and priority of the tasks. Ultimately, this solution aims to quantitatively assess the comprehensive ability of operations and maintenance personnel to provide auxiliary support. The assessment of auxiliary response capability is a multi-dimensional decision-making process that integrates time costs, workload, and professional skill levels. For example, a weighted summation model can be used, assigning different weights to the estimated travel time, current task load, and skill depth of the target operation, and then calculating a comprehensive score. Alternatively, fuzzy logic or machine learning models can be employed to learn the impact of these factors on responsiveness based on historical data, thus providing a more accurate assessment. This solution aims to select the most suitable operations and maintenance personnel to provide auxiliary support based on the comprehensive assessment results.The selection process begins by screening all maintenance personnel whose auxiliary response capabilities meet a preset threshold. Next, it checks whether any of these personnel possess a higher level of skill in the target operation than the potential executors. If multiple qualified personnel exist, the system ranks them based on their auxiliary response capability scores and selects the one or more with the highest scores as auxiliary executors. This process ensures that the selected auxiliary executors not only possess the required skills but also have the time and workload to respond promptly and effectively execute auxiliary tasks.

[0088] This application's solution refines and automates the selection process of auxiliary executors by introducing multi-dimensional dynamic information. First, the system proactively acquires the real-time location information of all available maintenance personnel and the on-site location information of the maintenance tasks to be performed. Based on this geographic data, the system can accurately calculate the estimated travel time for each available maintenance personnel to reach the task site, thus quantifying accessibility in the time dimension. Simultaneously, the system also acquires the current real-time task load information of each available maintenance personnel, reflecting their current workload and preventing overload from affecting the assistance effect. After acquiring this dynamic information, the system comprehensively considers the estimated travel time, current task load information, and the skill depth of the auxiliary personnel corresponding to the potential executor's skill gaps in the target operation, conducting a comprehensive evaluation of the auxiliary response capability of each available maintenance personnel. This evaluation not only considers skill matching but also incorporates time costs and workload, making the selection of auxiliary executors more closely aligned with reality. Finally, based on the evaluated auxiliary response capability, the system intelligently determines whether there is a maintenance personnel with a higher skill depth than the potential executor and the best overall response capability to serve as the auxiliary executor. This combination transforms the selection of auxiliary executors from a static skill match into a dynamic, real-time, and comprehensive decision. When the system identifies potential executors with skill deficiencies and a high task complexity index, external assistance is required. In this case, this solution ensures that the selected auxiliary executor not only compensates for the potential executor's shortcomings in terms of skills but also can arrive at the site promptly and is not currently overburdened, thus providing efficient support. This dynamic evaluation and selection mechanism effectively avoids situations where auxiliary personnel, despite possessing the necessary skills, are unable to provide timely and effective assistance due to distance or being preoccupied with other tasks. This significantly improves the real-time nature and effectiveness of auxiliary decision-making, ensuring the smooth progress of maintenance tasks and the stable operation of the power distribution network.

[0089] As a specific implementation method, when the distribution network intelligent operation and maintenance closed-loop decision-making method needs to determine whether there is an auxiliary executor in step S35, it can be done in the following way. Assume that the potential executor has a skill gap in the target operation item of "calibrating new solid-state switch parameters," and that the complexity of this maintenance task is high. The system first obtains the real-time location information of currently available operation and maintenance personnel through various methods. For example, an APP installed on the operation and maintenance personnel's smartphone can report their GPS location data to the backend server every 30 seconds; or, in a specific area of ​​the distribution network, Bluetooth beacons can be deployed, and when the operation and maintenance personnel enter or leave the specific area, their smart badges will interact with the beacons to update their location information. Simultaneously, the system will query the distribution network geographic information system (GIS) to obtain the precise latitude and longitude coordinates of the equipment site corresponding to the "calibrating new solid-state switch parameters" task. Next, the system can call third-party map service APIs, such as the route planning interface provided by the Gaode Map Open Platform, taking the real-time location and task location of each available maintenance personnel as input, and specifying "driving" as the mode of transportation, to calculate the estimated travel time for each maintenance personnel to reach the site. For example, maintenance personnel A's estimated travel time is 15 minutes, and maintenance personnel B's estimated travel time is 45 minutes. Simultaneously, the system will query the internal task scheduling database to obtain the current task load information for each available maintenance personnel. For example, maintenance personnel A is currently handling a low-priority inspection task, estimated to be completed in 30 minutes; maintenance personnel B currently has no tasks executing. Subsequently, the system will integrate this information to evaluate the auxiliary response capability of each maintenance personnel. For example, the system can use a weighted scoring model: Auxiliary Response Capability Score = (1 / Estimated Travel Time) * W1 + (1 / (Current Task Load + 1)) * W2 + Target Operation Item Skill Depth * W3, where W1, W2, and W3 are preset weights. Assume that maintenance personnel A has a skill level of L4 (proficient) in "calibrating new solid-state switch parameters," while maintenance personnel B has a skill level of L5 (expert). After calculation, maintenance personnel A's auxiliary response capability score is X, and maintenance personnel B's auxiliary response capability score is Y. The system will determine the final auxiliary executor based on these scores, combined with whether the maintenance personnel's skill level in the target operation item "calibrating new solid-state switch parameters" is higher than that of the potential executor (e.g., the potential executor's skill level is L2). For example, if maintenance personnel B's skill level is L5, and their auxiliary response capability score Y is higher than maintenance personnel A's score X, then the system will prioritize recommending maintenance personnel B as the auxiliary executor.

[0090] Through the aforementioned technical solution, this application, in determining the auxiliary executor, not only considers the skill depth of the maintenance personnel in the target operation item, but also incorporates dynamic factors such as real-time location, estimated travel time, and current task load. This multi-dimensional, real-time evaluation mechanism enables the system to more accurately identify maintenance personnel who not only possess the required skills but also have the physical capacity for rapid response and are not overburdened in terms of time as auxiliary executors. This effectively avoids situations where auxiliary personnel, despite matching skills, are unable to provide timely and effective assistance due to distance or being preoccupied with other tasks, significantly improving the real-time nature and effectiveness of auxiliary decision-making. Ultimately, it ensures that when potential executors have skill deficiencies and the task is complex, timely and efficient on-site support can be obtained, thereby guaranteeing the smooth completion of maintenance tasks, reducing the risk of misoperation, and improving the overall maintenance efficiency and reliability of the distribution network.

[0091] In some embodiments, the specific steps in step S37 include: S371. Collect feedback on the execution of maintenance tasks; S372. Obtain the skill level of the operations and maintenance personnel performing the maintenance task before the task is executed; S373. Calculate the performance score of the maintenance personnel based on their skill depth and complexity index before task execution; whereby, when the matching degree between the maintenance personnel's skill depth and complexity index before task execution is less than or equal to the first preset target value and the maintenance task is successfully completed, the performance score is increased; when the matching degree between the maintenance personnel's skill depth and complexity index before task execution is greater than the first preset target value and the maintenance task is successfully completed, the performance score is decreased. S374. Calculate the learning factor for adjusting the skill depth of operations and maintenance personnel based on their skill depth and complexity index before task execution; wherein, when the matching degree between the skill depth of operations and maintenance personnel and the task complexity index before task execution is less than or equal to the second preset target value and the maintenance task is successfully completed, the learning factor is increased; when the matching degree between the skill depth of operations and maintenance personnel and the task complexity index before task execution is greater than the second preset target value and the maintenance task is successfully completed, the learning factor is decreased. S375. Update the skill depth of operations and maintenance personnel performing maintenance tasks based on performance scores and learning factors.

[0092] The purpose of collecting execution feedback for the maintenance tasks is to obtain detailed information on the execution process and results, providing a data foundation for subsequent skill depth updates. Execution feedback may include task completion status, problems encountered during task execution, solutions taken, whether auxiliary resource packages were used and their effectiveness evaluation, and the maintenance personnel's self-assessment of their skill level. This feedback information can be collected through structured forms filled out by maintenance personnel on mobile terminal applications, or obtained through automatic recording of sensor data, operation logs, etc. Obtaining the skill depth of the maintenance personnel performing the maintenance tasks before task execution aims to accurately record their initial skill level on specific equipment and operations. This skill depth can be obtained from a pre-set personnel capability information storage system, which may store the maintenance personnel's skill depth for various operations on the target equipment, such as numerical values ​​or levels quantified through theoretical knowledge mastery, simulated operation proficiency, and historical task completion quality. Obtaining this initial skill depth is the basis for subsequent dynamic adjustment of performance scores and learning factors, ensuring personalized and accurate skill updates. Based on the skill level and complexity index of the operations and maintenance personnel before task execution, a performance score is calculated for each personnel. This step aims to dynamically evaluate their performance in the task based on their initial skill level and the complexity of the task. The performance score calculation no longer considers a simple success or failure, but rather the level of challenge. When an operations and maintenance personnel successfully completes a challenging (low-match) task, their performance score is increased to encourage them to challenge themselves and improve their abilities. Conversely, if they successfully complete a task that is too easy (high-match), their performance score is decreased to avoid over-rewarding and to more fairly reflect their actual contribution and growth in the task. The performance score can be calculated using various methods such as weighted average, fuzzy logic, or machine learning models. Based on the skill level and complexity index of the operations and maintenance personnel before task execution, a learning factor for adjusting the personnel's skill level is calculated. This step is used to determine the rate or magnitude of skill level updates. The learning factor is a value between 0 and 1, used to control the step size of skill level updates. When an operations and maintenance (O&M) personnel successfully completes a challenging task, their learning factor increases, meaning their skill depth is updated more significantly to reflect their rapid learning and growth capabilities. Conversely, when the task is relatively simple, the learning factor decreases, resulting in a smaller update in skill depth. This prevents excessive skill inflation and ensures a more robust and reasonable update of the skill map. The learning factor can be calculated based on a preset function curve, a rule engine, or an adaptive algorithm. Based on the performance score and the learning factor, the skill depth of the O&M personnel performing the maintenance task is updated; this step is the final execution stage of the skill depth update.By combining calculated performance scores and learning factors, the system can dynamically adjust the skill depth of operations and maintenance personnel. For example, an incremental update rule can be used, such as "new skill depth = old skill depth + (performance score - old skill depth) * learning factor". This update mechanism ensures that the skill map of operations and maintenance personnel can continuously and accurately reflect their latest ability level.

[0093] This application's solution addresses the limitations in efficiency and accuracy of traditional skills depth update methods, which fail to adequately consider task complexity and the initial skill level of operations and maintenance (O&M) personnel, by introducing a dynamically adjusted performance score and learning factor mechanism. After an O&M task is completed, the system collects execution feedback. This feedback includes not only the task's success or failure but also the problems encountered by O&M personnel, the measures taken, the use of auxiliary resources, and expert evaluations, providing comprehensive and multi-dimensional real-world data for subsequent skills assessments. Based on this, the system obtains the O&M personnel's skill depth before the task execution. This initial skill depth serves as a benchmark for evaluating the personnel's growth and performance in this task, ensuring the personalization and fairness of subsequent assessments. Subsequently, the system dynamically calculates the O&M personnel's performance score based on their pre-task skill depth and the complexity index of the maintenance task. The core principle is that when the O&M personnel's pre-task skill depth has a low match with the task complexity index (i.e., the task is challenging for them) and the task is successfully completed, the system increases their performance score. This effectively incentivizes operations and maintenance (O&M) personnel to challenge their own capabilities and rapidly improve their skills by completing more challenging tasks. Conversely, if a task with a high degree of matching (relatively simple) is successfully completed, the performance score is reduced to avoid over-rewarding simple tasks, making performance evaluation more objective and accurate. Simultaneously, the system dynamically calculates a learning factor to adjust the O&M personnel's skill depth based on their skill depth and task complexity index before task execution. Similar to performance scores, when an O&M personnel successfully completes a challenging task, the learning factor increases, meaning their skill depth is updated more significantly to reflect their rapid learning and growth capabilities. Conversely, when the task is relatively simple, the learning factor decreases, reducing the magnitude of skill depth updates and controlling the update step size to ensure a more robust and reasonable skill map update. Finally, the system updates the skill depth of the O&M personnel performing the maintenance task based on the performance score and the learning factor. This update mechanism, combining dynamic performance evaluation and adaptive learning factors, ensures that the O&M personnel's skill map continuously and accurately reflects their latest capability level. This solution is closely integrated with the task assignment mechanism in the aforementioned closed-loop decision-making method for intelligent operation and maintenance of distribution networks. During the task assignment phase, the system calculates the matching degree based on the skill level of the maintenance personnel and the task complexity index, and assigns the personnel with the highest matching degree. When a target executor cannot be assigned, a potential executor is selected and auxiliary resources are provided. Through the dynamic updating of skill level in this solution, it ensures that the skill map of maintenance personnel remains up-to-date and accurate.This means that in the next task assignment, the system can match tasks based on more precise skill data, thereby more effectively identifying the most suitable maintenance personnel to perform the task, or more accurately determining when auxiliary resources are needed, or even when auxiliary personnel are required. This continuous optimization of the skill map enables the entire intelligent maintenance closed-loop decision-making system to better adapt to the growth of maintenance personnel and changes in tasks, improving the accuracy and efficiency of task allocation, and ultimately enhancing the overall maintenance capabilities and reliability of the power distribution network.

[0094] As a specific implementation method, suppose the intelligent operation and maintenance system of the distribution network needs to update the skill level of maintenance personnel Xiao Li in the "parameter calibration" operation of the new solid-state switch.

[0095] S371. Collect execution feedback for the maintenance task: Xiao Li completed a parameter calibration task for a new type of solid-state switch. After completing the task, Xiao Li submitted a task feedback form via a mobile terminal application, which included a task completion status of "success" and uploaded a photo of the calibration results. The remote expert reviewed Xiao Li's operation report and gave it a "good" rating.

[0096] S372. Obtain the skill depth of the maintenance personnel performing the maintenance task before the task execution: The system queries the personnel ability information storage system and obtains that Xiao Li's skill depth before performing this "new solid-state switch parameter calibration" task is L2 (auxiliary operation), with a corresponding value of 0.3.

[0097] S373. Calculate the performance score of the maintenance personnel based on their skill depth before task execution and the complexity index; wherein, when the matching degree between the maintenance personnel's skill depth and the complexity index before task execution is less than or equal to a first preset target value and the maintenance task is successfully completed, the performance score is increased; when the matching degree between the maintenance personnel's skill depth and the complexity index before task execution is greater than the first preset target value and the maintenance task is successfully completed, the performance score is decreased: The system obtains the complexity index of this "parameter calibration" task as 0.775. The matching degree between Xiao Li's skill depth (0.3) before the task and the task complexity index (0.775) is 0.3 / 0.775=0.387. Assume the first preset target value is 0.5. Since 0.387 is less than 0.5, and the task is successfully completed, the system judges that Xiao Li successfully challenged a relatively difficult task, therefore increasing his performance score, for example, setting the performance score to 0.8.

[0098] S374. Calculate the learning factor for adjusting the skill depth of the maintenance personnel based on their skill depth before task execution and the complexity index; wherein, when the matching degree between the maintenance personnel's skill depth before task execution and the task complexity index is less than or equal to a second preset target value and the maintenance task is successfully completed, the learning factor is increased; when the matching degree between the maintenance personnel's skill depth before task execution and the task complexity index is greater than the second preset target value and the maintenance task is successfully completed, the learning factor is decreased: assuming the second preset target value is 0.6. Since Xiao Li's matching degree of 0.387 is less than 0.6, and the task was successfully completed, the system determines that Xiao Li gained a significant learning opportunity in this task, therefore increasing his learning factor, for example, setting the learning factor to 0.2.

[0099] S375. Based on the performance score and the learning factor, update the skill depth of the maintenance personnel performing the maintenance task: The system updates Xiao Li's skill depth from 0.3 to 0.3 + (0.8 - 0.3) * 0.2 = 0.3 + 0.1 = 0.4 according to a preset skill depth adjustment algorithm (e.g., new skill depth = old skill depth + (performance score - old skill depth) * learning factor). After the update, Xiao Li's skill depth in "New Solid State Switch Parameter Calibration" increases from L2 to L3 (independent operation).

[0100] Through the above technical solution, this application can solve the problem that when updating the skill depth of maintenance personnel based on execution feedback, the performance score or learning factor used to calculate the skill depth adjustment fails to dynamically adjust according to the task type, the current skill level of the maintenance personnel, or the complexity of the task, resulting in limited efficiency or accuracy of skill depth updates. Specifically, by collecting execution feedback of maintenance tasks, the system can obtain the true situation of task completion, providing a reliable basis for skill updates. By obtaining the skill depth of maintenance personnel before task execution, the system can establish personalized skill assessment benchmarks. Based on the skill depth of maintenance personnel before the task and the task complexity index, the system dynamically calculates performance scores, making the evaluation of maintenance personnel more fair and motivating. When maintenance personnel successfully complete challenging tasks, their performance scores increase, encouraging them to challenge themselves; when they complete simple tasks, their performance scores decrease, avoiding over-rewarding. At the same time, the dynamic calculation of learning factors allows the skill depth update rate to adapt to the challenge of the task. For successful completion of challenging tasks, the learning factor increases, accelerating skill improvement; for simple tasks, the learning factor decreases, controlling the update range and ensuring the rationality of skill adjustments. This dynamically adjusted performance score and learning factor mechanism makes the skill depth update process for operations and maintenance (O&M) personnel more accurate and efficient. It more realistically reflects the actual improvement in O&M personnel's capabilities, avoiding the lag or distortion of skill maps. In the closed-loop decision-making method for intelligent O&M in distribution networks, this precisely updated skill depth data provides a more accurate basis for subsequent task assignment, ensuring that the most suitable O&M personnel are assigned to specific tasks, or that appropriate auxiliary resources are provided when necessary. This significantly improves the accuracy of task allocation and overall O&M efficiency, ultimately enhancing the reliability and security of the distribution network.

[0101] Reference Appendix Figure 2 This invention provides a closed-loop decision-making system for intelligent operation and maintenance of power distribution networks (this system adopts the closed-loop decision-making method for intelligent operation and maintenance of power distribution networks described in the above embodiments; the specific process is described in the corresponding steps above), comprising: The first acquisition module 100 is used to acquire the maintenance tasks of the target device and calculate the matching degree of all currently available maintenance personnel for the maintenance tasks; The first matching module 200 is used to assign the target executor to perform the maintenance task if there is a target executor whose matching degree is greater than or equal to a preset matching degree threshold; otherwise, it runs the following second matching module, first determining module, second obtaining module, first control module, second determining module, second control module and update module. The second matching module 300 is used to select the operation and maintenance personnel with the highest matching degree as the potential executor when all available operation and maintenance personnel have a matching degree of less than the preset matching degree threshold, making it impossible to assign the target executor to perform the maintenance task. The first determining module 400 is used to determine the operation items in which the potential executor has skill deficiencies based on the potential executor's skill depth regarding various operations of the target device, and to designate them as target operation items. The second acquisition module 500 is used to acquire the key operation items and complexity index of the maintenance task; The first control module 600 is used to generate a first auxiliary resource package based on skill deficiencies and key operations when the target operation item is related to the key operation item and the complexity index is less than or equal to a preset index threshold, and to distribute the first auxiliary resource package to potential executors to guide them in performing maintenance tasks. The second determination module 700 is used to determine whether there are any maintenance personnel among the currently available maintenance personnel whose skill depth for the target operation item is higher than that of the potential executor, and to act as auxiliary executors, if the target operation item is related to the key operation item and the complexity index is greater than the preset index threshold. The second control module 800 is used to assign the auxiliary executor to perform the maintenance task together with the potential executor if it is determined that there is an auxiliary executor; otherwise, it generates a second auxiliary resource package and sends the second auxiliary resource package to the potential executor to guide the potential executor to perform the maintenance task. The update module 900 is used to collect execution feedback of maintenance tasks and update the skill level of the maintenance personnel performing the maintenance tasks based on the execution feedback.

[0102] In this document, relational terms such as first and second are used only to distinguish one entity or operation from another entity or operation, without necessarily requiring or implying any such actual relationship or order between these entities or operations.

[0103] The above description is merely an embodiment of the present invention and is not intended to limit the scope of protection of the present invention. For those skilled in the art, the present invention can have various modifications and variations. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A closed-loop decision-making method for intelligent operation and maintenance of power distribution networks, characterized in that, Includes the following steps: S1. Obtain the maintenance task for the target device and calculate the matching degree of all currently available maintenance personnel for the maintenance task; S2. If there is a target executor whose matching degree is greater than or equal to the preset matching degree threshold, then the target executor is assigned to perform the maintenance task; otherwise, steps S31-S37 are executed. S31. When the matching degree of all currently available maintenance personnel for the maintenance task is less than the preset matching degree threshold, resulting in the inability to assign a target executor to perform the maintenance task, the maintenance personnel with the highest matching degree among the currently available maintenance personnel shall be selected as potential executors. S32. Based on the potential executor's skill level regarding each operation of the target device, determine the operation items where the potential executor has skill deficiencies and designate them as target operation items; S33. Obtain the key operation items and complexity index of the maintenance task; S34. If the target operation item is related to the key operation item, and the complexity index is less than or equal to a preset index threshold, a first auxiliary resource package is generated based on the skill deficiency and the key operation, and the first auxiliary resource package is sent to the potential executor to guide the potential executor to perform the maintenance task; S35. If the target operation item is related to the key operation item, and the complexity index is greater than the preset index threshold, determine whether there are currently available operation and maintenance personnel who have a higher skill level in the target operation item than the potential executor and serve as assistant executors. S36. If it is determined that the auxiliary executor exists, then the auxiliary executor and the potential executor are assigned to jointly perform the maintenance task; Otherwise, a second auxiliary resource package is generated and distributed to the potential executor to guide the potential executor in performing the maintenance task; S37. Collect execution feedback of the maintenance task, and update the skill level of the maintenance personnel performing the maintenance task based on the execution feedback; The first auxiliary resource package contains augmented reality operation instructions; The specific steps in step S34 include: S341. For the high-precision operation items in the maintenance task, obtain the operation point environmental parameters of the high-precision operation items, and calculate the rate of change of the operation point environmental parameters; S342. Determine the stability of the operating environment based on the rate of change; S343. When the stability of the operating environment does not meet the preset high-precision operation requirements, an augmented reality operation guide containing an operation timing lock instruction is generated so that the augmented reality terminal suspends the high-precision operation. S344. When the stability of the operating environment meets the high-precision operation requirements, determine whether there is an environmental deviation between the actual environment and the ideal standard environment, and when there is an environmental deviation, calculate the calibration parameter compensation value of the high-precision operation based on the environmental deviation, and generate an augmented reality operation guide containing the calibration parameter compensation value so that the augmented reality terminal displays the calibration parameter compensation value on the augmented reality interface; S345. A first auxiliary resource package containing the operation timing lockout command or the calibration parameter compensation value is sent to the potential executor to guide the potential executor to perform the maintenance task.

2. The intelligent operation and maintenance closed-loop decision-making method for distribution networks according to claim 1, characterized in that, The specific steps in step S1 include: S11. Obtain the capability levels of all currently available maintenance personnel regarding the target equipment from the preset personnel capability information storage system; S12. Calculate the complexity index of the maintenance task based on preset consideration dimensions; S13. Based on the capability level and the complexity index, calculate the matching degree of each of the currently available maintenance personnel for the maintenance task.

3. The intelligent operation and maintenance closed-loop decision-making method for distribution networks according to claim 2, characterized in that, The capability level is calculated by weighted summation of the skill depth of the maintenance personnel for each operation of the target equipment.

4. The intelligent operation and maintenance closed-loop decision-making method for distribution networks according to claim 2, characterized in that, The specific steps in step S13 include: S131. Based on the capability level and the complexity index, calculate the skill gap of each of the currently available maintenance personnel for the maintenance task; S132. Based on the skill gap, assess the potential for skill enhancement that each of the aforementioned operations and maintenance personnel may gain after performing the aforementioned maintenance task; S133. Using the skill enhancement potential as a weighting factor, and combining the ability level and the complexity index, calculate the matching degree of each of the currently available maintenance personnel for the maintenance task.

5. The intelligent operation and maintenance closed-loop decision-making method for distribution networks according to claim 1, characterized in that, The specific steps in step S35 include: S351. Obtain the real-time location information of each of the currently available maintenance personnel; S352. Obtain the on-site location information of the maintenance task; S353. Based on the real-time location information of each available maintenance personnel and the on-site location information of the maintenance task, calculate the estimated travel time for each available maintenance personnel to reach the on-site location; S354. Obtain the current task load information of each available maintenance personnel; S355. Based on the estimated travel time, the current task load information, and the skill depth of the target operation item, assess the auxiliary response capability of each of the available maintenance personnel; S356. Based on the auxiliary response capability, determine whether there are any currently available operations and maintenance personnel whose skill depth for the target operation item is higher than that of the potential executor, and serve as auxiliary executors.

6. The intelligent operation and maintenance closed-loop decision-making method for distribution networks according to claim 1, characterized in that, The second auxiliary resource package includes a video call link connecting to a remote assistance expert.

7. The intelligent operation and maintenance closed-loop decision-making method for distribution networks according to claim 1, characterized in that, The specific steps in step S37 include: S371. Collect execution feedback for the maintenance task; S372. Obtain the skill level of the maintenance personnel performing the maintenance task before the task is executed; S373. Calculate the performance score of the maintenance personnel based on their skill depth before task execution and the complexity index; wherein, when the matching degree between the maintenance personnel's skill depth and the complexity index before task execution is less than or equal to a first preset target value and the maintenance task is successfully completed, the performance score is increased; when the matching degree between the maintenance personnel's skill depth and the complexity index before task execution is greater than the first preset target value and the maintenance task is successfully completed, the performance score is decreased. S374. Calculate a learning factor for adjusting the skill depth of the maintenance personnel based on their skill depth before task execution and the complexity index; wherein, when the matching degree between the maintenance personnel's skill depth and the complexity index before task execution is less than or equal to a second preset target value and the maintenance task is successfully completed, increase the learning factor; when the matching degree between the maintenance personnel's skill depth and the complexity index before task execution is greater than the second preset target value and the maintenance task is successfully completed, decrease the learning factor. S375. Update the skill depth of the operations and maintenance personnel performing the maintenance task based on the performance score and the learning factor.

8. A distribution network intelligent operation and maintenance closed-loop decision-making system employing the distribution network intelligent operation and maintenance closed-loop decision-making method as described in any one of claims 1-7, characterized in that, include: The first acquisition module is used to acquire the maintenance tasks of the target device and calculate the matching degree of all currently available maintenance personnel for the maintenance tasks. The first matching module is used to assign the target executor to perform the maintenance task if there is a target executor whose matching degree is greater than or equal to a preset matching degree threshold; otherwise, the following second matching module, first determining module, second obtaining module, first control module, second determining module, second control module, and update module are run. The second matching module is used to select the operation and maintenance personnel with the highest matching degree from the currently available operation and maintenance personnel as potential executors when the matching degree of all the currently available operation and maintenance personnel for the maintenance task is less than the preset matching degree threshold, resulting in the inability to assign a target executor to perform the maintenance task. The first determining module is used to determine the operation items in which the potential executor has skill deficiencies based on the potential executor's skill depth in relation to various operations of the target device, and to designate them as target operation items; The second acquisition module is used to acquire the key operation items and complexity index of the maintenance task; The first control module is used to generate a first auxiliary resource package based on the skill deficiency and the key operation if the target operation item is related to the key operation item and the complexity index is less than or equal to a preset index threshold, and to send the first auxiliary resource package to the potential executor to guide the potential executor to perform the maintenance task. The second determining module is used to determine whether there are any maintenance personnel among the currently available maintenance personnel whose skill depth for the target operation item is higher than that of the potential executor, and to act as auxiliary executors, if the target operation item is related to the key operation item and the complexity index is greater than the preset index threshold. The second control module is used to assign the auxiliary executor and the potential executor to jointly perform the maintenance task if it is determined that the auxiliary executor exists. Otherwise, a second auxiliary resource package is generated and distributed to the potential executor to guide the potential executor in performing the maintenance task; The update module is used to collect execution feedback of the maintenance task and update the skill level of the operation and maintenance personnel who perform the maintenance task based on the execution feedback.

Images