Intelligent scheduling method and system applied to cable operation and maintenance

Abstract

This invention provides an intelligent scheduling method and system for cable operation and maintenance. First, the migration knowledge elements in the cable operation and maintenance migration knowledge base are deconstructed, dividing them into resource adaptation, process adaptation, and risk adaptation knowledge elements, and generating a knowledge element classification set. A dynamic portrait of the operation and maintenance scenario of the cable to be scheduled is constructed, integrating operational characteristics, operation and maintenance task requirements, and historical operation and maintenance performance data to generate a 3D scene portrait. The adaptation coefficient between each migration knowledge element and the portrait is calculated, and target knowledge element combinations are selected. Based on the target knowledge element combinations, an initial operation and maintenance scheduling scheme framework is constructed, incorporating various adaptation rules. Through multiple rounds of portrait iterative updates and adjustments, the scheme framework is adjusted, optimizing resource allocation, step sequence, and anomaly response plans, resulting in the final scheme and generating operation and maintenance scheduling instructions which are sent to the operation and maintenance execution terminal. This invention achieves intelligent, precise, and efficient cable operation and maintenance scheduling.

Description

Technical Field

[0001] This invention relates to the field of cable operation and maintenance technology, and more specifically, to an intelligent scheduling method and system for cable operation and maintenance. Background Technology

[0002] In the operation and maintenance of cables in power systems, the increasing scale and complexity of cable networks present numerous challenges. Traditional cable operation and maintenance scheduling methods often rely on the experience of maintenance personnel, lacking systematic and scientific rigor. On the one hand, different cable operation and maintenance scenarios have their own unique characteristics, including differences in cable type, laying environment, and operating load. These differences make it difficult to unify and standardize operation and maintenance practices. For example, underground cables and overhead cables face vastly different risks of natural disasters and maintenance difficulties during operation and maintenance, but traditional methods have failed to fully consider these scenario differences, resulting in a lack of targeted operation and maintenance scheduling solutions. On the other hand, cable operation and maintenance involves multiple aspects such as resource allocation, process arrangement, and risk response. Traditional methods lack effective integration mechanisms for resource adaptation, process adaptation, and risk adaptation. In resource allocation, it may be impossible to reasonably allocate human, material, and financial resources according to the actual operation and maintenance task requirements; in process arrangement, it is difficult to determine the optimal sequence of steps, which may easily lead to confusion in procedures or repetitive work; in terms of risk response, there is a lack of effective contingency plans for possible abnormal situations, and once a failure occurs, it is often impossible to deal with it in a timely and effective manner, thereby affecting the normal operation of cables and the stability of the power system. Summary of the Invention

[0003] In view of the aforementioned problems, and in conjunction with the first aspect of the present invention, embodiments of the present invention provide an intelligent scheduling method for cable operation and maintenance, the method comprising:

[0004] The migration knowledge elements in the cable operation and maintenance migration knowledge base are deconstructed and divided into resource adaptation knowledge elements, process adaptation knowledge elements and risk adaptation knowledge elements, generating a set of knowledge element classifications. The cable operation and maintenance migration knowledge base stores migration knowledge elements for different cable operation and maintenance scenarios, and the migration knowledge elements record scenario-based operation and maintenance practice rules.

[0005] Construct a dynamic profile of the operation and maintenance scenario of the cable to be scheduled, integrate the operation characteristic data, operation and maintenance task requirement data and historical operation and maintenance performance data of the cable to be scheduled, and generate a three-dimensional scene profile including scenario feature dimension, requirement feature dimension and performance feature dimension.

[0006] Calculate the adaptation coefficient between each transferred knowledge element in the knowledge element classification set and the dynamic profile of the operation and maintenance scenario, and select the target knowledge element combination based on the adaptation coefficient. The adaptation coefficient reflects the degree of matching between the transferred knowledge element and the dynamic profile of the operation and maintenance scenario in each dimension.

[0007] The initial operation and maintenance scheduling scheme framework is constructed based on the combination of target knowledge elements, and incorporates the resource configuration rules of resource adaptation knowledge elements, the step sequence rules of process adaptation knowledge elements, and the abnormal response rules of risk adaptation knowledge elements.

[0008] The initial operation and maintenance scheduling scheme framework is adjusted by iteratively updating the dynamic profile of the operation and maintenance scenario through multiple rounds. The resource allocation ratio, step execution order and abnormal response plan are optimized by combining the feature changes of the dynamic profile of the operation and maintenance scenario. The final cable operation and maintenance scheduling scheme is obtained. Based on the final cable operation and maintenance scheduling scheme, operation and maintenance scheduling instructions are generated and sent to the operation and maintenance execution terminal.

[0009] In another aspect, embodiments of the present invention also provide an intelligent scheduling system for cable maintenance, including a processor and a machine-readable storage medium connected to the processor. The machine-readable storage medium is used to store programs, instructions, or code, and the processor is used to execute the programs, instructions, or code in the machine-readable storage medium to implement the above-described method.

[0010] Based on the above, firstly, the migration knowledge elements in the cable operation and maintenance migration knowledge base are deconstructed, dividing them into resource adaptation knowledge elements, process adaptation knowledge elements, and risk adaptation knowledge elements. This generates a knowledge element classification set, constructs a dynamic portrait of the operation and maintenance scenario for the cable to be scheduled, and integrates multi-dimensional data to generate a three-dimensional scene portrait. This makes the description of the operation and maintenance scenario more comprehensive, accurate, and dynamic, reflecting the cable's operating status and operation and maintenance needs in real time. The adaptation coefficient between each migration knowledge element and the dynamic portrait of the operation and maintenance scenario is calculated, and target knowledge element combinations are selected, improving the targeting and accuracy of scheduling. Based on the target knowledge element combinations, an initial operation and maintenance scheduling scheme framework is constructed, incorporating rules for various adaptation knowledge elements. Through multiple rounds of iterative updates and adjustments to the dynamic portrait of the operation and maintenance scenario, and by optimizing various rules in conjunction with feature changes, the operation and maintenance scheduling scheme can be adjusted in real time according to actual conditions, ensuring it always remains in an optimal state. Finally, the generated operation and maintenance scheduling instructions are sent to the operation and maintenance execution terminal, realizing intelligent, precise, and efficient cable operation and maintenance scheduling. This significantly improves the quality and efficiency of cable operation and maintenance, reduces operation and maintenance costs and risks, and ensures the safe and stable operation of the power system. Attached Figure Description

[0011] Figure 1 This is a schematic diagram of the execution flow of the intelligent scheduling method for cable operation and maintenance provided in an embodiment of the present invention.

[0012] Figure 2 This is a schematic diagram of exemplary hardware and software components of an intelligent scheduling system for cable maintenance provided in an embodiment of the present invention. Detailed Implementation

[0013] The present invention will now be described in detail with reference to the accompanying drawings. Figure 1 This is a flowchart illustrating an intelligent scheduling method for cable maintenance provided in one embodiment of the present invention. The intelligent scheduling method for cable maintenance will be described in detail below.

[0014] Step S110: Deconstruct the migration knowledge elements in the cable operation and maintenance migration knowledge base, divide them into resource adaptation knowledge elements, process adaptation knowledge elements and risk adaptation knowledge elements, and generate a knowledge element classification set. The cable operation and maintenance migration knowledge base stores migration knowledge elements for different cable operation and maintenance scenarios, and the migration knowledge elements record scenario-based operation and maintenance practice rules.

[0015] This embodiment uses the operation and maintenance of a 10kV underground cable network in a core urban area as a scenario. In this scenario, cables are mostly laid underground along main traffic arteries and commercial complexes, and are prone to "multi-factor coupled insulation failure anomalies" due to multiple factors such as soil corrosion, construction disturbance, load fluctuations, and material aging. The migration knowledge elements in the cable operation and maintenance migration knowledge base are deconstructed and classified to provide a scheduling scheme that matches the complex anomaly handling requirements in this scenario.

[0016] Step S111: Retrieve all migration knowledge elements from the cable maintenance migration knowledge base, extract the knowledge content description, applicable scenario tags, and application effect records for each migration knowledge element, and form the original dataset of migration knowledge elements.

[0017] All migration knowledge elements were retrieved in batches from the cable operation and maintenance migration knowledge base, which covers operation and maintenance practices for different laying environments and fault types in urban cable networks. For each migration knowledge element, its knowledge content description was extracted one by one, such as the diagnostic process description and resource allocation scheme description for "multi-factor coupled insulation failure anomaly"; applicable scenario tags were extracted, such as "underground direct burial laying - high load area - acidic soil environment" and "underground pipeline laying - commercial core area - high electromagnetic interference environment"; application effect records were extracted, including data such as resource utilization rate, task completion rate, and anomaly handling success rate in past applications of this knowledge element. The extracted information was integrated to form a raw dataset of migration knowledge elements containing multiple fields, with each record corresponding to the complete information of one migration knowledge element.

[0018] Step S112: Perform semantic parsing on the knowledge content description of each transfer knowledge element in the original dataset of transfer knowledge elements, and identify the resource configuration-related statements, step sequence-related statements, and anomaly response-related statements contained therein.

[0019] A semantic parsing algorithm is used to process the knowledge content description of each transferred knowledge element in the original dataset. First, the text is segmented, part-of-speech tagging is performed, and syntactic analysis is conducted. Then, based on a pre-defined keyword database, three types of expressions are identified. Keywords related to resource allocation include "human resources," "detection equipment," "repair materials," and "allocation route." For example, "Two maintenance personnel with partial discharge detection qualifications, one X-ray detection device, and a quantity of insulation repair materials need to be allocated and transported from maintenance station A to the fault site via main road B" is identified as a resource allocation-related expression. Keywords related to step-sequence include "execute first," "start later," "detection phase," "repair phase," and "duration." For example, "First, perform partial discharge detection on the cable, lasting for one detection cycle. After the detection is completed, start the insulation repair process" is identified as a step-sequence-related expression. Keywords related to anomaly response include "anomaly type," "handling measures," "recovery verification," and "emergency plan." For example, "If a sudden increase in partial discharge occurs during detection, immediately stop the detection and activate nitrogen protection measures. Reassess the insulation status after the parameters stabilize" is identified as an anomaly response-related statement. The three types of statements identified are marked, and their location and specific content within the knowledge content description are recorded.

[0020] Step S113: Calculate the proportion of the three types of expressions in each migration knowledge element. If the proportion of resource configuration-related expressions is the highest, then mark the migration knowledge element as a resource adaptation knowledge element. The resource adaptation knowledge element includes operation and maintenance resource type selection rules, resource quantity allocation rules, and resource allocation path rules.

[0021] For each migrated knowledge element, the proportion of words in its knowledge content description related to resource configuration, step sequence, and anomaly response is calculated to the total number of words in the description. If the proportion of resource configuration-related descriptions is higher than the other two types, the migrated knowledge element is marked as a resource adaptation knowledge element. This type of knowledge element specifies the resource management rules in the operation and maintenance process. Among them, the operation and maintenance resource selection rules specify the types of human resources (such as personnel with partial discharge detection qualifications and cable splicing qualifications), equipment resource types (such as partial discharge detectors, infrared thermal imagers, and cable fault location instruments), and material resource types (such as insulating tape, cable intermediate joints, and nitrogen cylinders) to be used in different scenarios; the resource quantity allocation rules determine the quantity of each type of resource based on the task scale and fault severity, for example, "For multi-factor coupled insulation failure anomalies, 2 detection personnel, 1 partial discharge detector, and 3 sets of insulation repair kits are required"; the resource allocation path rules plan resource transportation routes based on geographical location and traffic conditions, for example, "Starting from the Xicheng District Operation and Maintenance Center, via Yingbin Avenue and Keji Road to the fault point, avoiding the morning rush hour congestion sections."

[0022] Step S114: If the proportion of time-related descriptions of steps is the highest, then mark the migration knowledge element as a process adaptation knowledge element. The process adaptation knowledge element includes the order rules of operation and maintenance steps, the rules for allocating the execution time of steps, and the rules for step connection and transition.

[0023] If the proportion of step-sequence related descriptions is the highest in a certain migration knowledge element, it is marked as a process adaptation knowledge element. This type of knowledge element focuses on the time sequence management of operation and maintenance processes. The rules for the order of operation and maintenance steps clearly define the logical order of each operation step. For example, "The operation and maintenance process for multi-factor coupled insulation failure anomalies is as follows: on-site safety isolation - cable parameter detection (partial discharge, insulation resistance, dielectric loss value) - fault location - insulation layer repair - parameter retest - safe evacuation"; the rules for allocating the execution time of each step specify the expected execution time range of each step. For example, "The execution time of the on-site safety isolation step is one preparation cycle, the execution time of the cable parameter detection step is two detection cycles, and the execution time of the fault location step is one location cycle"; the rules for step connection and transition clearly define the conversion conditions and connection methods between steps. For example, "After the cable parameter detection step is completed and the detection data is uploaded to the backend system and passes the validity verification, the fault location step start command is automatically triggered, and a step switching notification is sent to the operation and maintenance personnel."

[0024] Step S115: If the description related to anomaly response has the highest proportion, then mark the migration knowledge element as a risk adaptation knowledge element. The risk adaptation knowledge element includes anomaly type identification rules, anomaly handling measures rules, and anomaly recovery verification rules.

[0025] When the proportion of anomaly response-related statements is highest in a certain migration knowledge element, it is marked as a risk-adaptive knowledge element. This type of knowledge element formulates response strategies for potential anomalies in the operation and maintenance process. The anomaly type identification rule defines the anomaly type based on parameter change characteristics. For example, "derived anomalies of multi-factor coupled insulation failure anomalies include: partial discharge surge anomaly (discharge exceeds the baseline value and the rise rate exceeds the threshold), detection equipment failure anomaly (instrument display value fluctuation exceeds the normal range), and repair material failure anomaly (insulation tape adhesion strength is lower than the standard requirement)." The anomaly handling measures rule specifies the specific handling method for each anomaly. For example, "If a partial discharge surge anomaly occurs, immediately cut off the detection power supply, turn on the on-site ventilation equipment, use nitrogen to purge the local area of ​​the cable, and adjust the detection parameters and re-detect after the discharge drops to a safe range." The anomaly recovery verification rule clarifies the effectiveness verification standard after anomaly handling. For example, "After handling the partial discharge surge anomaly, the discharge data for three consecutive cycles needs to be monitored. If all data are stable within the safe range and without fluctuation, it is determined that normal has been restored."

[0026] Step S116: Perform attribute annotation on the three types of migration knowledge elements after marking. Annotate resource adaptation dimension parameters for resource adaptation knowledge elements, process adaptation dimension parameters for process adaptation knowledge elements, and risk adaptation dimension parameters for risk adaptation knowledge elements.

[0027] For the marked resource-adaptation, process-adaptation, and risk-adaptation knowledge elements, attribute annotations are performed to supplement adaptation dimension parameter information. For resource-adaptation knowledge elements, resource adaptation dimension parameters are annotated, covering resource type coverage, resource allocation accuracy, and resource allocation response speed. For process-adaptation knowledge elements, process adaptation dimension parameters are annotated, including step coverage completeness, timing control accuracy, and fault tolerance capability. For risk-adaptation knowledge elements, risk adaptation dimension parameters are annotated, involving anomaly identification coverage, effectiveness of handling measures, and reliability of recovery verification. Each parameter must be annotated in conjunction with the specific content of the knowledge element to ensure that the parameter value accurately reflects the adaptation characteristics of the knowledge element.

[0028] Step S1161: For the resource adaptation knowledge element, extract the number of resource types, resource allocation accuracy, and resource allocation response time involved, and use them as the resource adaptation dimension parameters of the resource adaptation knowledge element. Set a specific value range for each resource adaptation dimension parameter.

[0029] Resource adaptation dimension parameters are extracted from the knowledge content description of resource adaptation knowledge elements. The number of resource types refers to the specific number of categories of human resources, equipment resources, and material resources covered by the knowledge element. For example, if a resource adaptation knowledge element involves 3 types of human resources, 5 types of equipment resources, and 4 types of material resources, its resource type quantity parameter is counted according to this classification. Resource allocation accuracy refers to the precision of resource quantity allocation. For example, "precisely allocate the number of testing equipment according to the distance to the fault point and the detection difficulty coefficient," and its value range can be set to three levels: "low accuracy - medium accuracy - high accuracy." Resource allocation response time refers to the time range from issuing a resource allocation command to the resource arriving at the site. The value range can be divided into "short response - medium response - long response," for example, "short response" corresponds to "arrival within one traffic cycle," and "medium response" corresponds to "arrival within two traffic cycles." These parameters and their value ranges are then bound and labeled with the resource adaptation knowledge element.

[0030] Step S1162: For the process adaptation knowledge element, extract the number of steps, the precision of the step sequence, and the fault tolerance rate of the step connection, and use them as the process adaptation dimension parameters of the process adaptation knowledge element. Set specific quantitative standards for each process adaptation dimension parameter.

[0031] Extract process adaptation dimension parameters from the process adaptation knowledge element. The number of steps refers to the total number of main steps and sub-steps contained in the knowledge element. For example, if a process adaptation knowledge element contains 5 main steps, each with 2-3 sub-steps, the total number of main steps and sub-steps needs to be calculated as the number of steps parameter. Step timing accuracy refers to the allowable deviation range between the step execution time and the planned time. Quantification standards can be set as "deviation ratio ≤ a certain ratio" or "absolute deviation ≤ a certain time unit," etc. Step connection fault tolerance rate refers to the proportion of allowed anomalies during step connection to the total number of connections. Quantification standards can be set as "fault tolerance rate ≤ a certain ratio," such as "the proportion of anomalies caused by data transmission delays during step connection does not exceed a certain proportion of the total number of connections." Clearly define quantification standards for each parameter to ensure the accuracy of annotation.

[0032] Step S1163: For the risk adaptation knowledge element, extract the anomaly identification accuracy, anomaly handling time and anomaly recovery success rate involved in it, and use them as risk adaptation dimension parameters of the risk adaptation knowledge element. Set specific evaluation indicators for each risk adaptation dimension parameter.

[0033] Risk adaptation dimension parameters are extracted from the risk adaptation knowledge element. Anomaly identification accuracy refers to the accuracy with which the identification rules defined by this knowledge element identify actual anomalies. Evaluation indicators can be set as "identification accuracy rate," "missed identification rate," and "false identification rate," for example, "the identification accuracy rate for anomalies derived from multi-factor coupled insulation failure anomalies should not be lower than a certain percentage, and the missed identification rate should not be higher than a certain percentage." Anomaly handling time refers to the time range from the occurrence of an anomaly to its completion. Evaluation indicators are "average handling time" and "longest handling time," for example, "the average handling time for a sudden increase in partial discharge should not exceed a certain time unit." Anomaly recovery success rate refers to the percentage of cases that meet the recovery standard after anomaly handling. Evaluation indicators are "success rate" and "reproducibility rate," for example, "the recovery success rate after anomaly handling should not be lower than a certain percentage." The above evaluation indicators are then labeled with the corresponding risk adaptation dimension parameters.

[0034] Step S1164: Establish the annotation rules for migration knowledge element parameters. The number of resource types in the resource adaptation dimension parameters of the resource adaptation knowledge element is annotated according to the number of categories of human resources, equipment resources, and material resources. The resource allocation accuracy is annotated according to percentage accuracy, and the resource allocation response time is annotated according to time unit.

[0035] Establish unified rules for annotating migration knowledge element parameters and standardize the annotation format. For resource adaptation knowledge elements, the number of resource types should be separately annotated in three categories, for example, "Number of human resource categories: 3; Number of equipment resource categories: 5; Number of material resource categories: 4." Resource allocation accuracy should be annotated with percentage precision, for example, "Resource quantity allocation error ≤ a certain percentage." Resource allocation response time should be annotated with a specific time unit, for example, "Resource allocation response time ≤ 2 hours." The annotation rules should clearly define the units, formats, and value ranges of parameters to ensure consistency and comparability of parameter annotations for different knowledge elements.

[0036] Step S1165: The number of steps in the process adaptation dimension parameters of the process adaptation knowledge element is marked by the number of main steps and the number of sub-steps respectively, the step timing accuracy is marked by the time deviation range, and the step connection fault tolerance rate is marked by the allowable deviation ratio.

[0037] The parameter annotation rules for process adaptation knowledge elements stipulate that the number of steps must be labeled separately for the number of main steps and the number of sub-steps, for example, "Number of main steps: 5; Number of sub-steps: 12". Step timing precision is labeled according to the time deviation range, for example, "Step execution time deviation ± a certain time unit". Step connection error tolerance is labeled according to the allowable deviation percentage, for example, "Step connection error tolerance ≤ a certain percentage". The method for calculating deviation is also clearly defined, for example, time deviation is "(actual execution time - planned execution time) / planned execution time × 100%", ensuring the accuracy of the annotation results.

[0038] Step S1166: In the risk adaptation dimension parameters of the risk adaptation knowledge element, the anomaly identification accuracy is marked by the identification accuracy rate, the anomaly handling time is marked by the time range of the handling process, and the anomaly recovery success rate is marked by the percentage of successful cases.

[0039] The parameter annotation rules for risk-adaptive knowledge elements stipulate that anomaly identification accuracy is labeled as identification accuracy rate, calculated as "number of correctly identified anomaly cases / total number of anomaly cases × 100%", for example, "anomaly identification accuracy rate ≥ a certain percentage". Anomaly handling time is labeled according to the time range of the handling process, for example, "anomaly handling time is from a certain time unit to a certain time unit". Anomaly recovery success rate is labeled according to the percentage of successful cases, calculated as "number of cases that recovered to normal after handling / total number of handled cases × 100%", for example, "anomaly recovery success rate ≥ a certain percentage". The statistical period and sample size requirements must be specified during annotation to ensure the reliability of the parameters.

[0040] Step S1167: Add parameter source identifiers to the adaptation dimension parameters of each migration knowledge element, and indicate the parameter update cycle.

[0041] For all adaptation dimension parameters of each migrated knowledge element, a parameter source identifier is added to clearly state the basis for obtaining the parameter value, such as "from the statistics of cable operation and maintenance cases in urban core areas in 2023-2024," "from the industry standard 'Power Cable Operation and Maintenance Regulations'," or "from expert review opinions." The update cycle of the parameters is also indicated, with the update frequency set according to the stability of the parameters. For example, "the update cycle for the resource allocation response time parameter is six months," "the update cycle for the anomaly identification accuracy parameter is one year," and "the update cycle for the step sequence accuracy parameter is two years." When the update cycle is reached, data needs to be re-collected or expert evaluation organized to update the parameter values ​​to ensure their timeliness.

[0042] Step S117: Construct an index system for the knowledge element classification set, establish a retrieval path based on applicable scenario tags and adaptation dimension parameters, record the relationship and collaborative application logic between the three types of migrated knowledge elements, and generate a knowledge element classification set.

[0043] An index system for the knowledge element classification set is constructed, employing a multi-level index structure. The first-level index is divided by knowledge element type (resource adaptation, process adaptation, risk adaptation), the second-level index by applicable scenario tags, and the third-level index by adaptation dimension parameters. For example, the second-level index under the resource adaptation knowledge element includes "underground direct burial laying - high-load areas" and "underground pipeline laying - commercial core areas," etc., and the third-level index under each second-level index includes "resource type quantity ≥ 5 categories" and "resource allocation response time ≤ 2 hours," etc. Based on this index system, a search path is established, allowing users to quickly locate the required knowledge element through scenario tags and parameter conditions. Simultaneously, the relationships between the three types of knowledge elements are clarified. For example, "for multi-factor coupled insulation failure anomalies, resource adaptation knowledge element A needs to be used in conjunction with process adaptation knowledge element B and risk adaptation knowledge element C," recording the collaborative application logic and clarifying the usage order and interaction rules of knowledge element combinations. The index system, relationships, and collaborative logic are integrated with the classified knowledge elements to generate a complete knowledge element classification set, stored in a structured database, supporting rapid retrieval and retrieval.

[0044] Step S120: Construct a dynamic profile of the operation and maintenance scenario of the cable to be scheduled, integrate the operation characteristic data, operation and maintenance task requirement data and historical operation and maintenance performance data of the cable to be scheduled, and generate a three-dimensional scene profile including scene feature dimension, requirement feature dimension and performance feature dimension.

[0045] For a specific cable in the 10kV underground cable network in the urban core area that requires operation and maintenance scheduling, a dynamic profile of the operation and maintenance scenario is constructed. By integrating multi-dimensional data of the cable, a three-dimensional profile is formed that comprehensively reflects its operation and maintenance scenario characteristics, task requirements, and historical performance.

[0046] Step S121: Obtain the operation characteristic data of the cable to be scheduled, extract the key parameter values ​​of each characteristic to form the basic data of the scene characteristic dimension of the operation and maintenance scenario dynamic profile. The operation characteristic data includes voltage stability characteristics, current load characteristics, temperature distribution characteristics and insulation performance characteristics.

[0047] Operational characteristic data is acquired through monitoring equipment deployed on the cables to be scheduled. Voltage stability characteristic data is collected by voltage sensors, including key parameters such as real-time voltage value, voltage fluctuation amplitude, and voltage sag count; current load characteristic data is collected by current transformers, including key parameters such as real-time current value, load factor, three-phase current imbalance, and harmonic content; temperature distribution characteristic data is collected by fiber optic temperature sensors, including key parameters such as cable conductor temperature, insulation layer temperature, joint temperature, and temperature gradient; insulation performance characteristic data is collected by insulation monitoring devices, including key parameters such as insulation resistance value, partial discharge quantity, and dielectric loss value. The acquired operational characteristic data is preprocessed to remove noise and outliers, and then the key parameter values ​​of each characteristic are extracted, such as the maximum, average, and standard deviation of voltage fluctuation amplitude, and the peak and average values ​​of partial discharge quantity. These parameter values ​​are used as the basic data for the characteristic dimensions of the dynamic profile of the operation and maintenance scenario.

[0048] Step S122: Collect the operation and maintenance task requirement data of the cable to be scheduled, convert the operation and maintenance task requirement data into quantitative indicators of the feature dimensions of the dynamic profile requirements of the operation and maintenance scenario, and determine the weight coefficient of each quantitative indicator. The operation and maintenance task requirement data includes task priority, task coverage and task completion time limit.

[0049] The system collects maintenance task requirements data for cables to be scheduled from the cable maintenance management system. Task priority is determined based on the cable's importance and fault risk level; for example, if the cable supplies power to a commercial core area, the task priority is set to high. Task coverage includes the cable section length, number of monitoring points, and number of auxiliary devices involved in the maintenance operation. Task completion timeframe refers to the time range within which the maintenance task must be completed, such as within a specific time period. The task requirement data is converted into quantitative indicators; for example, task priority is converted into a numerical indicator of 0-10, and high priority corresponds to a value of 8-10. Task coverage is converted into quantitative values ​​for section length, number of monitoring points, etc., respectively. Task completion timeframe is converted into an indicator of the ratio of remaining time to the total task duration. The analytic hierarchy process (AHP) is used to determine the weight coefficients of each quantitative indicator; for example, the weight coefficient for task priority is higher than that for task coverage and task completion timeframe. In practice, a hierarchical model is first constructed, with "determining the weight of maintenance task requirements" as the target layer, and task priority, task coverage, and task completion timeframe as the criterion layer. Cable maintenance experts are then invited to compare the importance of each indicator in the criterion layer pairwise to form a judgment matrix. By calculating the largest eigenvalue of the judgment matrix and its corresponding eigenvector, and normalizing the eigenvector, the weight coefficients of each quantitative indicator are obtained, ensuring that the sum of the weight coefficients is 1. For example, the weight coefficient of task priority is set to a relatively high value, while the weight coefficients of task coverage and task completion time are set to relatively low values, and the sum of the three equals 1.

[0050] Step S123: Retrieve historical operation and maintenance performance data of the cable to be scheduled, calculate the statistical feature values ​​of the historical operation and maintenance performance data to form reference data for the performance feature dimensions of the dynamic profile of the operation and maintenance scenario. The historical operation and maintenance performance data includes the resource utilization rate, step execution efficiency and abnormal response speed of past operation and maintenance tasks.

[0051] Historical maintenance performance data for the cables to be dispatched over the past three years were retrieved from the historical database of the cable maintenance management system. Resource utilization data includes the ratio of actual to planned working hours of human resources for each maintenance task, the ratio of actual to available equipment time, and the ratio of actual to planned material consumption. Step execution efficiency data includes the ratio of actual to standard execution time for each maintenance step, the percentage of steps completed ahead of schedule, and the percentage of steps completed late. Anomaly response speed data includes the time interval from anomaly occurrence to anomaly identification, the time interval from anomaly identification to initiation of processing, and the time interval from anomaly processing to restoration to normal. Statistical analysis was performed on the above historical data, calculating statistical characteristic values ​​for each data type, such as mean, median, standard deviation, maximum, and minimum. These statistical characteristic values ​​were used as reference data for the dynamic profile performance dimension of the maintenance scenario.

[0052] Step S124: Establish the basic framework of the three-dimensional scene profile for dynamic profile of operation and maintenance scenarios, set the hierarchical structure of scene feature dimension, requirement feature dimension and performance feature dimension, divide each dimension into multiple sub-dimensions, and each sub-dimension corresponds to a specific type of feature data.

[0053] A three-dimensional framework for constructing dynamic profiles of operation and maintenance scenarios is established, clearly defining the hierarchical structure across three dimensions. The scenario characteristic dimension is further divided into sub-dimensions: voltage stability, current load, temperature distribution, and insulation performance. The voltage stability sub-dimension corresponds to data such as voltage fluctuation amplitude and voltage sag frequency; the current load sub-dimension corresponds to data such as load factor and three-phase current imbalance; the temperature distribution sub-dimension corresponds to data such as conductor temperature and joint temperature; and the insulation performance sub-dimension corresponds to data such as insulation resistance and partial discharge. The requirement characteristic dimension is further divided into sub-dimensions: task priority, task coverage, and task completion time, each corresponding to converted quantitative indicators and weighting coefficients. The performance characteristic dimension is further divided into sub-dimensions: resource utilization, step execution efficiency, and anomaly response speed, each corresponding to statistical characteristic values ​​of historical data. Each sub-dimension has a defined data storage format and update frequency to ensure the framework's standardization and scalability.

[0054] Step S125: Fill the basic data of the scene feature dimension, the quantitative indicators of the demand feature dimension, and the reference data of the performance feature dimension into the corresponding sub-dimensions of the dynamic profile of the operation and maintenance scenario, and set an update timestamp for the data of each sub-dimension.

[0055] Following the hierarchical structure of the 3D scene profiling framework, basic data from the scene feature dimensions are populated into the sub-dimensions of voltage stability, current load, temperature distribution, and insulation performance. For example, the maximum and average values ​​of voltage fluctuations are populated into the voltage stability sub-dimension, and the peak and standard deviation of partial discharge are populated into the insulation performance sub-dimension. Quantitative indicators and weighting coefficients from the demand feature dimension are populated into the task priority, task coverage, and task completion deadline sub-dimensions. For example, the quantified values ​​and corresponding weighting coefficients of task priority are populated into the task priority sub-dimension. Reference data from the performance feature dimension are populated into the resource utilization, step execution efficiency, and anomaly response speed sub-dimensions. For example, the average and standard deviation of equipment resource utilization are populated into the resource utilization sub-dimension. An update timestamp is added to each data entry in each sub-dimension to record the data collection and population time, facilitating subsequent tracking of data timeliness.

[0056] Step S126: Define the association rules between the dimensions of the dynamic profile of the operation and maintenance scenario. Changes in the voltage stability feature sub-dimension data of the dynamic profile of the operation and maintenance scenario trigger the adjustment of the weight of the task priority sub-dimension of the demand feature dimension. Changes in the resource utilization sub-dimension data of the performance feature dimension trigger the update of the current load feature sub-dimension parameter of the scenario feature dimension.

[0057] Establish association rules across the three dimensions of the dynamic profile of the operation and maintenance scenario, clarifying the triggering conditions and response actions for data changes. One core rule is: when the changes in data such as voltage fluctuation amplitude and voltage sag frequency in the voltage stability sub-dimensional of the scenario feature dimension exceed a preset threshold, automatically triggering an adjustment of the weight coefficients in the task priority sub-dimensional of the demand feature dimension. Another core rule is: when the changes in statistical characteristic values ​​of data such as human resource utilization rate and equipment resource utilization rate in the resource utilization sub-dimensional of the performance feature dimension exceed a preset threshold, automatically triggering updates to parameters such as load rate and three-phase current imbalance in the current load sub-dimensional of the scenario feature dimension. The association rules must clearly define the specific judgment criteria for triggering conditions, the execution flow of response actions, and the interface specifications for data interaction.

[0058] Step S1261: Establish a correlation model between the scene feature dimension and the demand feature dimension of the dynamic profile of the operation and maintenance scenario. Take the fluctuation amplitude level of the voltage stability feature sub-dimension of the scene feature dimension of the dynamic profile of the operation and maintenance scenario as the input variable, and the weight adjustment amplitude of the task priority sub-dimension of the demand feature dimension of the dynamic profile of the operation and maintenance scenario as the output variable.

[0059] A correlation model is constructed between the scenario feature dimension and the demand feature dimension, employing a data-driven modeling approach. The fluctuation amplitude level of the voltage stability sub-dimensional is used as the model's input variable. The fluctuation amplitude level is divided into multiple levels based on the magnitude of voltage fluctuations, such as slight fluctuation, moderate fluctuation, and severe fluctuation. The weight adjustment magnitude of the task priority sub-dimensional is used as the model's output variable. The weight adjustment magnitude is the change in the weight coefficients, which can be positive or negative; a positive value indicates an increase in weight, and a negative value indicates a decrease. By collecting historical operational data samples showing the correspondence between voltage fluctuation amplitude levels and task priority weight adjustment magnitudes, the correlation model is trained, enabling it to accurately output the corresponding weight adjustment magnitude based on the input fluctuation amplitude level.

[0060] Step S1262: Set the correspondence between fluctuation amplitude level and weight adjustment amplitude. When the fluctuation amplitude level of the voltage stability feature sub-dimension of the dynamic profile scenario feature dimension is the first level, the weight of the task related to voltage regulation in the task priority sub-dimension of the dynamic profile scenario requirement feature dimension is increased by the first proportion.

[0061] The specific correspondence between fluctuation amplitude levels and weight adjustment magnitudes is clearly defined. Fluctuation amplitude levels are divided into three levels: Level 1 (slight fluctuation), Level 2 (moderate fluctuation), and Level 3 (severe fluctuation). When the fluctuation amplitude level of the voltage stability sub-dimensional is Level 1, it indicates that the voltage fluctuation is small and has a limited impact on power supply stability. In this case, the weight of tasks related to voltage regulation in the task priority sub-dimensional of the demand characteristic dimension is increased by a first proportion. This first proportion is a small value to appropriately increase the priority of voltage regulation tasks. For example, if the original weight coefficient of a voltage regulation-related task is a certain value, after increasing the first proportion, the weight coefficient becomes the original value plus the product of the original value and the first proportion.

[0062] Step S1263: When the fluctuation amplitude level of the voltage stability feature sub-dimension of the dynamic profile scenario feature dimension of the operation and maintenance scenario is the second level, the weight of the task related to voltage regulation in the task priority sub-dimension of the dynamic profile scenario demand feature dimension of the operation and maintenance scenario is increased by a second proportion, and the second proportion is greater than the first proportion.

[0063] When the fluctuation level of the voltage stability sub-dimensional is at level two, it indicates that the voltage fluctuation is moderate, but it may affect the power supply to some sensitive users. In this case, the weight of tasks related to voltage regulation needs to be increased more significantly. The weight of tasks related to voltage regulation in the task priority sub-dimensional is increased by a second percentage, which is greater than the first percentage. For example, if the original weight coefficient of a task related to voltage regulation is a certain value, after increasing the second percentage, the weight coefficient becomes the original value plus the product of the original value and the second percentage, and the increased weight coefficient is higher than the weight coefficient when the fluctuation level is level one.

[0064] Step S1264: Establish a correlation model between the dynamic profile performance feature dimension and the scene feature dimension of the operation and maintenance scenario. Take the deviation rate between the actual value and the theoretical value of the resource utilization rate sub-dimension of the dynamic profile performance feature dimension of the operation and maintenance scenario as the input variable, and the parameter adjustment level of the current load feature sub-dimension of the scene feature dimension of the dynamic profile performance feature dimension of the operation and maintenance scenario as the output variable.

[0065] A data-driven modeling approach is also used to construct a correlation model between the performance feature dimension and the scene feature dimension. The deviation rate between the actual and theoretical values ​​of the resource utilization sub-dimensional is used as the model's input variable. The deviation rate is calculated as (actual value - theoretical value) / theoretical value × 100%, with a positive value indicating that the actual utilization rate is higher than the theoretical value, and a negative value indicating that the actual utilization rate is lower than the theoretical value. The parameter adjustment level of the current load sub-dimensional is used as the model's output variable. The parameter adjustment level is divided into multiple levels based on the adjustment magnitude of the load rate and the three-phase current imbalance, for example, fine adjustment, medium adjustment, and large adjustment. The model is trained using corresponding samples of deviation rate and parameter adjustment level from historical data, enabling the model to output an appropriate parameter adjustment level based on the input deviation rate.

[0066] Step S1265: Set the correspondence between the deviation rate range and the parameter adjustment level. When the deviation rate of the resource utilization sub-dimension of the dynamic profile of the operation and maintenance scenario is positive and within the first range, the rated load parameter adjustment level of the current load sub-dimension of the dynamic profile of the operation and maintenance scenario is set to the first level, and the first value is lowered accordingly.

[0067] Different ranges for the deviation rate are defined, and the correspondence between each range and the adjustment level of the current load parameter is established. When the deviation rate of the resource utilization sub-dimensional is positive and within the first range, it indicates that the actual resource utilization is slightly higher than the theoretical value, and resource usage is relatively tight. In this case, the adjustment level of the rated load parameter of the current load sub-dimensional is set to the first level (fine-tuning), correspondingly lowering the first value. For example, if the original value of the rated load parameter is a certain value, after lowering the first value, the new rated load parameter is the original value minus the first value, so as to appropriately reduce the load pressure and alleviate the tight resource situation.

[0068] Step S1266: When the deviation rate of the resource utilization sub-dimension of the dynamic profile of the operation and maintenance scenario is negative and within the second range, the rated load parameter adjustment level of the current load feature sub-dimension of the dynamic profile of the operation and maintenance scenario is set to the second level, and the second value is adjusted upward accordingly.

[0069] When the deviation rate of the resource utilization sub-dimension is negative and falls within the second range, it indicates that the actual resource utilization rate is lower than the theoretical value, and resources are idle. In this case, the adjustment level of the rated load parameter of the current load sub-dimension is set to the second level (medium adjustment), correspondingly increasing the second value. For example, if the original value of the rated load parameter is a certain value, after increasing the second value, the new rated load parameter is the original value plus the second value, in order to make full use of idle resources and improve resource utilization efficiency.

[0070] Step S1267: Encode the correspondence between the set fluctuation amplitude level and the weight adjustment amplitude, as well as the correspondence between the deviation rate range and the parameter adjustment level, into an executable association rule script, embed it into the update module of the dynamic profile of the operation and maintenance scenario, and automatically execute the corresponding weight adjustment or parameter update operation when the trigger condition is met, and record the time, input data and output results of each association rule execution.

[0071] The correspondence between fluctuation amplitude levels and weight adjustment ranges, and between deviation rate ranges and parameter adjustment levels, is transformed into computer-executable association rule scripts. These scripts are written in a scripting language, clearly defining the judgment logic for trigger conditions, the data calculation process, and the storage method for output results. The completed scripts are embedded into the update module of the dynamic profile of the operation and maintenance scenario. This update module monitors data changes in the scenario feature dimensions and performance feature dimensions in real time. When the fluctuation amplitude level of the voltage stability sub-dimensional reaches the trigger condition, the update module automatically executes the association rule script and adjusts the weight coefficient of the task priority sub-dimensional. When the deviation rate of the resource utilization sub-dimensional reaches the trigger condition, the script is automatically executed to update the rated load parameters of the current load sub-dimensional. After each execution of the association rule, the execution time, the input data for the trigger condition (such as fluctuation amplitude level and deviation rate value), and the output results after execution (such as the adjusted weight coefficient and the updated rated load parameters) are recorded, forming an association rule execution log for subsequent auditing and analysis.

[0072] Step S127: Set the trigger conditions for iterative updates of the dynamic profile of the operation and maintenance scenario. When the change of any sub-dimension data exceeds the preset threshold, the overall update of the dynamic profile of the operation and maintenance scenario is triggered. Record the changes of dimensional data after each update to complete the construction of the dynamic profile of the operation and maintenance scenario.

[0073] Preset thresholds for changes in data across various sub-dimensions are established, such as the threshold for voltage fluctuation amplitude changes in the voltage stability sub-dimension, the threshold for load rate changes in the current load sub-dimension, the threshold for quantitative indicator changes in the task priority sub-dimension, and the threshold for statistical characteristic value changes in the resource utilization sub-dimension. The monitoring module of the dynamic profile of the operation and maintenance scenario collects the latest data for each sub-dimension in real time and calculates the magnitude of change between the latest data and the previous update. When the magnitude of change in any sub-dimension exceeds its corresponding preset threshold, a comprehensive update of the dynamic profile of the operation and maintenance scenario is triggered. During the update process, the data of the sub-dimension that triggered the change is updated first, then the data of other related sub-dimensions are updated according to association rules, and finally the overall data of the three dimensions are updated synchronously. After each update, the update time, the sub-dimension that triggered the update, the specific values ​​before and after the data change, and the execution status of the association rules are recorded to form an update record. Through continuous iterative updates, it is ensured that the dynamic profile of the operation and maintenance scenario can reflect the changes in the operation and maintenance scenario of the cables to be scheduled in real time, thus completing the construction of the dynamic profile of the operation and maintenance scenario.

[0074] Step S130: Calculate the adaptation coefficient between each migrated knowledge element in the knowledge element classification set and the dynamic profile of the operation and maintenance scenario, and select the target knowledge element combination based on the adaptation coefficient. The adaptation coefficient reflects the degree of matching between the migrated knowledge element and each dimension of the dynamic profile of the operation and maintenance scenario.

[0075] Based on the completed dynamic profile of the operation and maintenance scenario, the adaptation coefficient of each migration knowledge element in the knowledge element classification set and the profile is calculated. The degree of matching between the knowledge element and the scenario is quantified by the adaptation coefficient, and then the combination of resource adaptation, process adaptation and risk adaptation knowledge elements most suitable for the current operation and maintenance scenario is selected.

[0076] Step S131: Extract the key parameters of the scenario feature dimension, the quantitative indicators of the requirement feature dimension, and the statistical feature values ​​of the performance feature dimension from the dynamic profile of the operation and maintenance scenario to form the feature vector of the dynamic profile of the operation and maintenance scenario.

[0077] Key parameters for the dynamic profile of the operation and maintenance scenario are extracted from the following dimensions: voltage stability (average voltage fluctuation amplitude, number of voltage sags), current load (median load rate, standard deviation of three-phase current imbalance), temperature distribution (maximum conductor temperature, average joint temperature), and insulation performance (median insulation resistance, peak partial discharge). Quantitative indicators and weighting coefficients for the demand characteristic dimension are also extracted, including quantified values ​​for task priority, task coverage, and task completion time, along with their respective weighting coefficients. Statistical feature values ​​for the performance characteristic dimension are also extracted, including average resource utilization, standard deviation of step execution efficiency, and median anomaly response speed. The extracted data are then arranged in a preset order to form a multi-dimensional feature vector for the dynamic profile of the operation and maintenance scenario, with each data point corresponding to one dimension of the feature vector.

[0078] Step S132: Extract the adaptation dimension parameters of each transfer knowledge element in the knowledge element classification set, and convert the resource adaptation dimension parameters of the resource adaptation knowledge element, the process adaptation dimension parameters of the process adaptation knowledge element, and the risk adaptation dimension parameters of the risk adaptation knowledge element into transfer knowledge element feature vectors respectively.

[0079] For each transferable knowledge element in the knowledge element classification set, its adaptation dimension parameters are extracted. For resource adaptation knowledge elements, parameters such as the number of resource types, resource allocation accuracy, and resource allocation response time are extracted; for process adaptation knowledge elements, parameters such as the number of steps, step sequence accuracy, and step connection fault tolerance rate are extracted; for risk adaptation knowledge elements, parameters such as anomaly identification accuracy, anomaly handling time, and anomaly recovery success rate are extracted. Following the same dimensional order and data format as the dynamic profile feature vector of the operation and maintenance scenario, the adaptation dimension parameters of each transferable knowledge element are converted into transferable knowledge element feature vectors, ensuring that the number of dimensions is consistent for subsequent similarity calculations.

[0080] Step S133: Calculate the cosine similarity between the feature vector of each transferred knowledge element and the feature vector of the dynamic profile of the operation and maintenance scenario, and use the cosine similarity value as the adaptation coefficient between the transferred knowledge element and the dynamic profile of the operation and maintenance scenario.

[0081] The cosine similarity algorithm is used to calculate the similarity between the feature vector of each migrated knowledge element and the feature vector of the dynamic profile of the operation and maintenance scenario.

[0082] The calculation process begins by first calculating the dot product of the two vectors, which is the sum of the product of the corresponding dimensions. Next, the magnitudes of the two vectors are calculated separately, which is the square root of the sum of the squares of the data in each dimension. Finally, the dot product is divided by the product of the two magnitudes to obtain the cosine similarity value, which ranges from 0 to 1. This cosine similarity value is then directly used as the adaptation coefficient between the transferred knowledge element and the dynamic profile of the operational scenario. A coefficient closer to 1 indicates a higher degree of matching between the transferred knowledge element and the current operational scenario; a coefficient closer to 0 indicates a lower degree of matching.

[0083] Step S134: Select resource adaptation knowledge elements, process adaptation knowledge elements, and risk adaptation knowledge elements with adaptation coefficients higher than the adaptation coefficient threshold, and form three categories of candidate migration knowledge element subsets respectively.

[0084] A preset adaptation coefficient threshold is established, set based on historical operational experience and scheduling accuracy requirements. All resource adaptation knowledge elements in the knowledge element category set are traversed, and those with adaptation coefficients higher than the threshold are selected to form a resource adaptation candidate subset. Similarly, process adaptation knowledge elements with adaptation coefficients higher than the threshold are selected to form a process adaptation candidate subset, and risk adaptation knowledge elements with adaptation coefficients higher than the threshold are selected to form a risk adaptation candidate subset. If no knowledge element in a certain category has an adaptation coefficient higher than the threshold, the adaptation coefficient threshold for that category is appropriately lowered, and the selection is repeated to ensure that each candidate subset contains at least one migration knowledge element.

[0085] Step S135: Sort the transfer knowledge elements in each candidate transfer knowledge element subset from high to low according to their adaptation coefficients, and select the top N transfer knowledge elements in each candidate transfer knowledge element subset.

[0086] For the candidate subsets of resource adaptation, process adaptation, and risk adaptation, the transferable knowledge elements within each subset are sorted from highest to lowest according to their adaptation coefficients. The selection quantity N is set based on actual scheduling needs. The value of N is determined by the size of the candidate subset; if the number of knowledge elements in a candidate subset is large, N can be appropriately larger; if the number of knowledge elements in a candidate subset is small, N is smaller. The top N transferable knowledge elements from each sorted candidate subset are selected as candidate knowledge elements for subsequent combination evaluation. For example, if N is set to 3, then the 3 transferable knowledge elements with the highest adaptation coefficients are selected from each candidate subset.

[0087] Step S136: Analyze the collaborative compatibility among the selected transfer knowledge elements, calculate the collaborative adaptation coefficient among different categories of transfer knowledge elements, and screen out the combinations of transfer knowledge elements with a collaborative adaptation coefficient higher than the collaborative threshold.

[0088] One knowledge element from each of the selected resource adaptation, process adaptation, and risk adaptation categories is chosen to form a combination of transferable knowledge elements to be evaluated, generating all possible combinations. For each combination to be evaluated, the collaborative compatibility between different categories of knowledge elements is analyzed, and the degree of compatibility is quantified by calculating a collaborative adaptation coefficient. The calculation of the collaborative adaptation coefficient is based on factors such as the degree of parameter matching between knowledge elements, rule conflicts, and past collaborative application effects; the specific calculation logic will be explained in detail in subsequent steps. A preset collaborative threshold is set, and the collaborative adaptation coefficient of each combination to be evaluated is compared with the collaborative threshold. Combinations with collaborative adaptation coefficients higher than the threshold are selected; these combinations are the collaboratively compatible knowledge element combinations.

[0089] Step S1361: Select one resource adaptation knowledge element, one process adaptation knowledge element, and one risk adaptation knowledge element to form a combination of migration knowledge elements to be evaluated. Extract the resource allocation time parameters of the resource adaptation knowledge element, the step start time parameters of the process adaptation knowledge element, and the exception handling start time parameters of the risk adaptation knowledge element within the combination of migration knowledge elements to be evaluated.

[0090] One knowledge element is randomly selected from each of the resource adaptation selection knowledge elements, process adaptation selection knowledge elements, and risk adaptation selection knowledge elements to form a combination of migration knowledge elements to be evaluated. For example, resource adaptation knowledge element R1, process adaptation knowledge element P1, and risk adaptation knowledge element F1 are selected to form the combination R1-P1-F1. For this combination, the resource allocation time parameter is extracted from the adaptation dimension parameters of resource adaptation knowledge element R1. This resource allocation time parameter is the estimated time from issuing the resource allocation instruction to all resources arriving at the operation and maintenance site. The step start time parameter is extracted from the adaptation dimension parameters of process adaptation knowledge element P1. This step start time parameter is the planned start time of each main operation and maintenance step. The exception handling start time parameter is extracted from the adaptation dimension parameters of risk adaptation knowledge element F1. This exception handling start time parameter is the response time from identifying the exception to starting the exception handling process. The three extracted parameters are stored together according to the combination identifier.

[0091] Step S1362: Calculate the time difference between the resource allocation time parameter of the resource adaptation knowledge element and the step start time parameter of the process adaptation knowledge element. If the time difference is within the allowable range, the first collaborative adaptation score of the combination of migration knowledge elements to be evaluated is recorded as the first score; otherwise, it is recorded as the second score. The second score is lower than the first score.

[0092] Taking the combination R1-P1-F1 as an example, the resource allocation time parameter of resource adaptation knowledge element R1 is subtracted from the start time parameter of the first main step in process adaptation knowledge element P1 to obtain the time difference. An allowable range for this time difference is preset. If the calculated time difference is within the allowable range, it indicates that resource allocation can meet the time requirement for step start, and the first collaborative adaptation score of this combination is recorded as the first score. If the time difference exceeds the allowable range, it indicates that resources cannot arrive on time, which will delay step start, and the first collaborative adaptation score is recorded as the second score. The second score is set lower than the first score to reflect the difference in the degree of collaborative matching.

[0093] Step S1363: Calculate the time difference between the step start time parameter of the process adaptation knowledge element and the anomaly handling start time parameter of the risk adaptation knowledge element. If the time difference is within the allowable range, the second collaborative adaptation score of the combination of transfer knowledge elements to be evaluated is recorded as the third score; otherwise, it is recorded as the fourth score. The fourth score is lower than the third score.

[0094] For the combination R1-P1-F1, the start time parameter of the key detection step in the process adaptation knowledge element P1 is selected, and the difference is calculated with the start time parameter of the exception handling in the risk adaptation knowledge element F1. An allowable range for this time difference is set. If the difference is within the allowable range, it means that the start of the exception handling process will not conflict with the key operation and maintenance steps, and can respond promptly to any exceptions that may occur during the execution of the steps. The second collaborative adaptation score is recorded as the third score. If the difference exceeds the allowable range, it may cause a delay in exception handling or interfere with the normal execution of steps. The second collaborative adaptation score is recorded as the fourth score, which is lower than the third score.

[0095] Step S1364: Calculate the time difference between the resource allocation time parameter of the resource adaptation knowledge element and the anomaly handling start time parameter of the risk adaptation knowledge element. If the time difference is within the allowable range, the third collaborative adaptation score of the combination of migration knowledge elements to be evaluated is recorded as the fifth score; otherwise, it is recorded as the sixth score. The sixth score is lower than the fifth score.

[0096] Continuing with the combination R1-P1-F1, calculate the difference between the resource allocation time parameter of resource adaptation knowledge element R1 and the anomaly handling start-up time parameter of risk adaptation knowledge element F1. A preset allowable range is established. If the difference is within the allowable range, it indicates that if an anomaly occurs during resource allocation, the anomaly handling process can be initiated promptly to ensure uninterrupted resource supply, and the third collaborative adaptation score is recorded as the fifth score. If the difference exceeds the allowable range, it may lead to the inability to handle resource allocation anomalies in a timely manner, affecting the overall operation and maintenance progress; the third collaborative adaptation score is recorded as the sixth score, which is lower than the fifth score.

[0097] Step S1365: The first, second, and third collaborative adaptation scores of the transferable knowledge element combination to be evaluated are weighted and summed. The weights are determined based on the importance of the three types of collaborative relationships to obtain the collaborative adaptation coefficient of the transferable knowledge element combination to be evaluated.

[0098] Based on the operational requirements, the weight coefficients of the first, second, and third collaboration adaptation scores are determined. Among them, the collaboration between resources and processes (the first collaboration adaptation score) has the greatest impact on the operational progress and has the highest weight coefficient; the collaboration between processes and risks (the second collaboration adaptation score) has the next highest weight; and the collaboration between resources and risks (the third collaboration adaptation score) has a relatively low weight. The sum of the weight coefficients of the three is 1. Taking the combination R1-P1-F1 as an example, the first collaboration adaptation score, the second collaboration adaptation score, and the third collaboration adaptation score are multiplied by their corresponding weights, and then the three products are added together to obtain the collaboration adaptation coefficient of the combination.

[0099] Step S1366: If the collaborative adaptation coefficient of the transfer knowledge element combination to be evaluated is higher than the collaborative threshold, the transfer knowledge element combination to be evaluated is determined to be collaboratively compatible; if it is lower than the collaborative threshold, the corresponding class of transfer knowledge element in the transfer knowledge element combination to be evaluated is replaced, and the collaborative adaptation coefficient is recalculated.

[0100] A preset collaboration threshold is set based on successful case data of historical collaborative applications. The collaboration adaptation coefficient of the combination R1-P1-F1 is compared with the collaboration threshold. If it is higher than the threshold, the combination is determined to be collaboratively compatible and retained as a candidate combination; if it is lower than the threshold, one knowledge element in the combination needs to be replaced, for example, replacing the process adaptation knowledge element P1 with P2 to form a new combination R1-P2-F1. The calculation process of steps S1361 to S1365 is repeated to obtain the collaboration adaptation coefficient of the new combination, and then compared with the collaboration threshold.

[0101] Step S1367: Repeat the above evaluation process until a combination of transferable knowledge elements with a synergy coefficient higher than the synergy threshold is found. Record the synergy coefficient and the score of each sub-item for each qualified combination of transferable knowledge elements.

[0102] The above evaluation process is executed for each possible combination of knowledge elements. If a combination meets the standard on the first calculation, its synergy adaptation coefficient and the scores for the first, second, and third synergy adaptations are directly recorded. If it meets the standard after multiple replacements, the composition of the final combination, its synergy adaptation coefficient, and the scores for each sub-item must be recorded. For example, if the synergy adaptation coefficient of combination R1-P2-F1 is higher than the threshold, the identifiers of R1, P2, and F1 in this combination, along with their corresponding synergy adaptation coefficients and the scores for the three sub-items, are recorded to form a list of compliant combinations.

[0103] Step S137: From the combinations of transferable knowledge elements that meet the criteria for collaborative adaptation coefficient, select the combination with the highest comprehensive adaptation coefficient as the target knowledge element combination. The comprehensive adaptation coefficient is the weighted average of the adaptation coefficients of each transferable knowledge element in the combination, and the weighting is determined based on the importance of the transferable knowledge element category.

[0104] Weighted averages are assigned to the comprehensive adaptation coefficients of knowledge elements for resource adaptation, process adaptation, and risk adaptation. The process adaptation knowledge element has the greatest impact on operational logic and therefore the highest weight; the resource adaptation knowledge element has the next highest weight; and the risk adaptation knowledge element has a relatively low weight. The sum of the weights of the three is 1. For each combination in the list of compliant combinations, such as R1-P2-F1, the adaptation coefficients of R1, P2, and F1 are extracted, multiplied by their respective weights, and then summed to obtain the comprehensive adaptation coefficient for that combination. The comprehensive adaptation coefficients of all compliant combinations are compared, and the combination with the highest value is selected as the target knowledge element combination.

[0105] Step S140: Construct an initial operation and maintenance scheduling scheme framework based on the combination of target knowledge elements, and incorporate resource configuration rules of resource adaptation knowledge elements, step sequence rules of process adaptation knowledge elements, and exception handling rules of risk adaptation knowledge elements.

[0106] Based on the selected combination of target knowledge elements, the core rules of the three types of knowledge elements are integrated into the scheduling scheme framework to build an initial framework covering three dimensions: resources, processes, and risks, ensuring that the framework can cover the key needs of the entire operation and maintenance process.

[0107] Step S141: Analyze the resource allocation rules of resource-adaptive knowledge elements in the target knowledge element combination, and extract the resource type selection conditions, resource quantity calculation methods and resource allocation path planning logic.

[0108] The resource adaptation knowledge element in the target knowledge element combination is analyzed by rules to extract resource type selection conditions. These conditions specify the standards for selecting human resources (such as testing engineers and emergency repair personnel), equipment resources (such as partial discharge detectors and insulation repair equipment), and material resources (such as insulating tape and sealant) based on the type of operation and maintenance task and the severity of the fault. The resource quantity calculation method is extracted, which determines the specific quantity of each type of resource based on the length of the operation and maintenance section and the number of equipment. The resource allocation path planning logic is extracted, which plans the optimal transportation path based on real-time traffic data and resource storage location.

[0109] Step S142: Match the types of human resources, equipment resources and material resources required for the operation and maintenance of the cable to be scheduled according to the resource type selection conditions, determine the specific quantity of each type of resource based on the resource quantity calculation method, and design the resource transportation and allocation route according to the resource allocation path planning logic.

[0110] Based on the resource selection criteria, the types of human resources (e.g., 2 engineers with partial discharge detection qualifications, 3 emergency repair personnel), equipment resources (e.g., 1 partial discharge detector, 1 set of insulation repair equipment), and material resources (e.g., 5 rolls of insulating tape, 2 bottles of sealant) required for the operation and maintenance of the cables to be dispatched are matched. The specific quantities of each type of resource are determined through resource quantity calculation methods. According to the resource allocation path planning logic and combined with real-time traffic information, the transportation route from the resource warehouse to the operation and maintenance site is designed, and the allocation order of on-site resources is planned to ensure that key equipment is delivered with priority.

[0111] Step S143: Analyze the step sequence rules of the process adaptation knowledge elements in the target knowledge element combination, and extract the step sequence constraint relationship, step duration calculation model and step connection conditions.

[0112] The process adaptation knowledge elements in the target knowledge element combination are analyzed, and the sequential constraints of the steps are extracted. These constraints clarify the logical order of the operation and maintenance steps, such as "security isolation - parameter detection - fault location - repair - retest - withdrawal". The step duration calculation model is extracted, which calculates the estimated duration of each step based on historical execution data and task complexity. The step connection conditions are extracted, which clarify the judgment criteria for the completion of the previous step and the triggering conditions for the start of the next step.

[0113] Step S144: Determine the basic sequence of operation and maintenance steps based on the step sequence constraint relationship, calculate the expected execution time of each step using the step duration calculation model, and design the transition connection method between steps in combination with the step connection conditions.

[0114] Based on the constraints of the step sequence, the basic steps for the operation and maintenance of the cable to be scheduled are determined as follows: "On-site safety isolation - cable insulation resistance detection - partial discharge detection - fault location - insulation layer repair - parameter retest - safe evacuation". The expected execution time of each step is obtained through the step duration calculation model. Based on the step connection conditions, the connection method is designed, such as "after the insulation resistance detection data is uploaded and passes the validity verification, a partial discharge detection start notification is automatically sent to the operation and maintenance personnel".

[0115] Step S145: Analyze the anomaly response rules of the risk-adaptive knowledge elements in the target knowledge element combination, and extract the anomaly type judgment basis, anomaly handling measure list and anomaly recovery verification standard.

[0116] The system analyzes the risk-adaptive knowledge elements in the target knowledge element combination, extracts the criteria for judging anomaly types, and defines the anomaly types based on parameter change characteristics, such as "a sudden increase in partial discharge exceeding a certain percentage of the baseline value within 10 minutes is judged as an anomaly." It also extracts a list of anomaly handling measures, which clarifies the handling process for each type of anomaly, such as "immediately stop detection and activate nitrogen protection when partial discharge suddenly increases." Finally, it extracts anomaly recovery verification standards, which clarify the verification requirements after anomaly handling, such as "three consecutive tests showing the discharge level stabilized within a safe range are considered a return to normal."

[0117] Step S146: Based on the criteria for judging the anomaly type, sort out the possible anomaly types that may occur during the operation and maintenance of the cable to be scheduled, match the corresponding processing flow for each anomaly type based on the anomaly handling measures list, and formulate a method for verifying the effect of anomaly handling in combination with the anomaly recovery verification standard.

[0118] Based on the criteria for judging anomalies, the possible types of anomalies that may occur during the operation and maintenance of cables to be scheduled are identified, including "sudden increase in partial discharge," "detection equipment failure," and "repair material failure." A handling process is matched for each type of anomaly, such as the "switching to backup equipment - calibrating parameters - re-detecting" process for "detection equipment failure." In conjunction with the recovery verification standards, an effectiveness verification method is developed. For example, after handling "repair material failure," the repair effect is verified by "insulation resistance retesting + visual inspection."

[0119] Step S147: Construct a three-layer structure for the initial operation and maintenance scheduling scheme framework. The resource configuration layer of the initial operation and maintenance scheduling scheme framework stores data on resource types, quantities, and allocation paths. The step sequence layer of the initial operation and maintenance scheduling scheme framework stores data on step order, execution duration, and connection methods. The exception handling layer of the initial operation and maintenance scheduling scheme framework stores data on exception types, processing procedures, and verification methods.

[0120] The initial operation and maintenance scheduling scheme framework is constructed using a three-layer structure: the resource configuration layer stores data on the types and quantities of matched human resources, equipment resources, and material resources, as well as the designed allocation paths; the step sequence layer stores data on the determined order of operation and maintenance steps, the estimated execution time of each step, and the designed connection methods; and the anomaly response layer stores data on the identified anomaly types, matching processing procedures, and established effectiveness verification methods. Data in each layer is stored in a structured format to ensure data standardization and accessibility.

[0121] Step S148: Set the data flow interaction rules between the three layers of the initial operation and maintenance scheduling scheme framework. The resource availability signal of the resource configuration layer of the initial operation and maintenance scheduling scheme framework triggers the step start instruction of the step timing layer of the initial operation and maintenance scheduling scheme framework. The abnormal monitoring signal of the step timing layer of the initial operation and maintenance scheduling scheme framework triggers the processing flow start instruction of the abnormal response layer of the initial operation and maintenance scheduling scheme framework, thus completing the construction of the initial operation and maintenance scheduling scheme framework.

[0122] A three-tiered data flow interaction rule is established: Once all resources in the resource configuration layer arrive at the site and send an arrival signal, a trigger command is automatically sent to the step sequence layer to initiate the first maintenance step. If the step sequence layer detects an anomaly during step execution and sends an anomaly monitoring signal, it automatically sends a command to the anomaly response layer to initiate the corresponding anomaly handling process. After the anomaly response layer completes the anomaly handling and verification, it sends a recovery signal to the step sequence layer to restart the interrupted maintenance step. This interaction rule enables the collaborative operation of the three-tiered structure, completing the initial maintenance scheduling scheme framework.

[0123] Step S150: Adjust the initial operation and maintenance scheduling scheme framework by iteratively updating the dynamic profile of the operation and maintenance scenario through multiple rounds of operation and maintenance scenario. Optimize the resource allocation ratio, step execution order and abnormal response plan by combining the feature changes of the dynamic profile of the operation and maintenance scenario to obtain the final cable operation and maintenance scheduling scheme. Generate operation and maintenance scheduling instructions based on the final cable operation and maintenance scheduling scheme and send them to the operation and maintenance execution terminal.

[0124] Based on the real-time changes of the dynamic profile of the operation and maintenance scenario, the initial framework is iterated and adjusted in multiple rounds to continuously adapt the scheduling scheme to the needs of the scenario, and finally generate and issue executable scheduling instructions.

[0125] Step S151: Monitor the feature changes of the dynamic profile of the operation and maintenance scenario. When the absolute value of the change in the voltage stability feature parameter of the dynamic profile of the operation and maintenance scenario exceeds the preset voltage change threshold, the first round of iterative adjustment is triggered.

[0126] The system monitors voltage stability characteristic parameters (such as voltage fluctuation amplitude and voltage sag count) in the dynamic profile of the operation and maintenance scenario in real time, and calculates the absolute value of the difference between the real-time value of the parameter and the value at the time of the last framework adjustment. If this absolute value exceeds the preset voltage change threshold, it indicates that the voltage stability has changed significantly, triggering the first round of iterative adjustment to the initial operation and maintenance scheduling scheme framework.

[0127] Step S152: In the first round of iterative adjustment, analyze the impact of changes in voltage stability characteristic parameters on resource demand. Based on the dynamic adjustment rules of resource adaptation knowledge elements in the target knowledge element combination, calculate the linear relationship between voltage change and equipment resource demand change, and adjust the equipment resource configuration ratio related to voltage regulation according to the linear relationship.

[0128] The impact of changes in voltage stability characteristic parameters on resource demand is analyzed. For example, increased voltage fluctuations mean a greater need for voltage monitoring equipment. Based on the dynamic adjustment rules in the resource adaptation knowledge element, the linear relationship between voltage change and equipment resource demand change is calculated. According to this linear relationship, the configuration ratio of voltage regulation-related equipment resources (such as voltage monitors and voltage regulators) is adjusted. For instance, if the voltage fluctuation increases by a certain magnitude, the proportion of voltage monitors should be increased accordingly.

[0129] Step S153: When the absolute value of the change in the task priority index of the dynamic profile requirement feature dimension of the operation and maintenance scenario exceeds the preset priority change threshold, the second round of iterative adjustment is triggered. Based on the priority adjustment rules of the process adaptation knowledge element, the priority score of each operation and maintenance step is recalculated according to the numerical change of the task priority index, and the execution order of the operation and maintenance steps is reordered in descending order of priority score.

[0130] The system monitors task priority metrics based on demand characteristics. When the absolute value of the difference between the current value and the value at the time of the last adjustment exceeds a preset threshold, a second round of iterative adjustment is triggered. Based on the priority adjustment rules of the process adaptation knowledge element and the changes in task priority metrics, the priority score for each maintenance step is recalculated. The score calculation comprehensively considers factors such as the step's impact on task completion and execution difficulty. Maintenance steps are then reordered from highest to lowest priority score; for example, the "partial discharge detection" step, with the highest score, is adjusted to be the first execution step.

[0131] Step S154: When the absolute value of the change in the statistical value of the abnormal response speed of the dynamic profile of the operation and maintenance scenario exceeds the preset response speed change threshold, the third round of iterative adjustment is triggered. Based on the contingency plan optimization rules of the risk adaptation knowledge element, the link in the abnormal handling process that exceeds the preset time efficiency threshold is identified. The process is simplified by merging or removing the links that exceed the execution time standard, thereby shortening the abnormal response time.

[0132] The system monitors the statistical values ​​of abnormal response speeds across performance characteristics. When the absolute value of the difference between this value and the value at the time of the last adjustment exceeds a preset threshold, a third round of iterative adjustments is triggered. Based on the contingency plan optimization rules of the risk-adaptive knowledge element, the system analyzes the execution logs of each abnormal handling process to identify steps whose execution time exceeds a preset time efficiency threshold, such as the "abnormal cause analysis" step taking too long. By merging similar steps (e.g., merging "cause analysis" with "measure formulation") or removing redundant steps (e.g., duplicate parameter verification steps), the abnormal handling process is simplified, and the overall abnormal response time is shortened.

[0133] Step S155: After each round of iterative adjustment, calculate the fit degree between the adjusted initial operation and maintenance scheduling scheme framework and the updated operation and maintenance scenario dynamic profile. The fit degree is the sum of the matching degree between the data of each layer of the adjusted initial operation and maintenance scheduling scheme framework and the corresponding dimension data of the updated operation and maintenance scenario dynamic profile.

[0134] After each round of iteration and adjustment, the fit between the adjusted framework and the updated profile is calculated. The matching degree between resource configuration layer data and scene feature dimension data, the matching degree between step sequence layer data and requirement feature dimension data, and the matching degree between exception handling layer data and performance feature dimension data are calculated separately. The three matching degrees are added together to obtain the overall fit.

[0135] For example, step S1551: Extract the resource types, quantities, and allocation path data of the resource configuration layer in the adjusted initial operation and maintenance scheduling scheme framework, compare them with the resource requirement parameters of the scene feature dimension of the updated operation and maintenance scenario dynamic profile, and calculate the resource matching degree; the calculation method of resource matching degree is: the proportion of the number of matched resource types to the total number of requirement types multiplied by the resource quantity matching accuracy, and then multiplied by the resource allocation path matching accuracy.

[0136] Extract the resource types, quantities, and allocation paths data from the adjusted resource configuration layer and compare them with the resource requirement parameters (such as required resource types, quantity range, and recommended paths) in the updated profile scene feature dimensions. Calculate the proportion of matched resource types to the total number of required types, and then calculate the resource quantity matching accuracy (the proportion of actual configured quantities within the required range) and the resource allocation path matching accuracy (the overlap between actual and recommended paths). Multiply these three values ​​to obtain the resource matching degree.

[0137] Step S1552: Extract the step sequence, execution duration, and connection method data from the step sequence layer of the adjusted initial operation and maintenance scheduling scheme framework, compare them with the task priority and completion time limit data of the updated operation and maintenance scenario dynamic profile requirement feature dimension, and calculate the sequence matching degree; the sequence matching degree is calculated as follows: the proportion of steps that meet the priority is multiplied by the matching ratio of execution duration and time limit requirements, and then multiplied by the connection method adaptation rate.

[0138] Extract the adjusted step sequence layer's step order, execution duration, and connection method data, and compare them with the updated profile's requirement feature dimension's task priority and completion deadline. Calculate the percentage of steps matching the priority (the proportion of steps ordered by priority that are consistent with the framework order), the matching ratio of execution duration to deadline requirements (the proportion of total step duration within the task deadline), and the connection method adaptation rate (the proportion of connection methods that meet scenario requirements and step transition logic). Multiply these three ratios to obtain the sequence matching degree. For example, if the percentage of steps matching the priority is a certain percentage, the matching ratio of execution duration to deadline requirements is a certain percentage, and the connection method adaptation rate is a certain percentage, the product of these three is the sequence matching degree after this round of adjustments.

[0139] Step S1553: Extract the anomaly types, processing procedures, and verification methods data from the anomaly response layer in the adjusted initial operation and maintenance scheduling scheme framework, compare them with the anomaly response requirements data in the dynamic profile performance feature dimension of the updated operation and maintenance scenario, and calculate the risk matching degree. The risk matching degree is calculated as follows: the proportion of the number of covered anomaly types to the total number of possible anomaly types multiplied by the processing procedure adaptation rate, and then multiplied by the verification method effectiveness rate.

[0140] Extract the list of anomaly types, the corresponding handling procedures, and the effectiveness verification methods recorded in the adjusted anomaly response layer. Compare this list with the anomaly response requirements data (such as the range of anomaly types to be covered, the time requirements of the handling procedures, and the reliability standards of the verification methods) in the updated dynamic profile of the operation and maintenance scenario. Calculate the proportion of covered anomaly types to the total number of possible anomaly types (the number of anomaly types covered by the anomaly response layer divided by the total number of possible anomaly types mentioned in the profile), the handling procedure adaptation rate (the proportion of handling procedures that meet the time requirements and scenario logic), and the verification method effectiveness rate (the proportion of verification methods that meet the reliability standards). Multiply these three proportions to obtain the risk matching degree.

[0141] Step S1554: Multiply the resource matching degree, time sequence matching degree and risk matching degree by their respective weight coefficients and sum them to obtain the adaptability of the adjusted initial operation and maintenance scheduling scheme framework and the updated operation and maintenance scenario dynamic profile; record the adaptability value and the matching degree value of each item calculated each time, and compare the difference between the adaptability and the target value.

[0142] Based on the core requirements of operation and maintenance scheduling, weight coefficients are assigned to resource matching degree, time sequence matching degree, and risk matching degree. Among them, time sequence matching degree directly affects the execution rhythm of operation and maintenance tasks, and has the highest weight coefficient; resource matching degree ensures the basic conditions of operation and maintenance, and has the next highest weight coefficient; risk matching degree improves the stability of operation and maintenance, and has a relatively low weight coefficient, and the sum of the weight coefficients of the three is 1. The calculated resource matching degree, time sequence matching degree, and risk matching degree are multiplied by their corresponding weights, and then the three products are added together to obtain the adaptation degree of the adjusted framework and the updated profile. The specific values ​​of adaptation degree, resource matching degree, time sequence matching degree, and risk matching degree are recorded for each calculation, and the adaptation degree is compared with the preset adaptation degree target value to clarify the gap between the current framework and the scenario requirements.

[0143] Step S156: If the adaptation degree between the initial operation and maintenance scheduling scheme framework after iterative adjustment and the updated operation and maintenance scenario dynamic profile reaches the adaptation degree standard, then stop the iteration; if it does not reach the standard, continue to monitor the changes in the characteristics of the operation and maintenance scenario dynamic profile, trigger the next round of iterative adjustment, until the adaptation degree reaches the standard; record the triggering conditions, adjustment content and adaptation degree change data of each round of iterative adjustment to form an iterative adjustment log.

[0144] The adjusted fit is compared with the preset fit threshold. If the fit reaches or exceeds the threshold, it indicates that the current initial operation and maintenance scheduling framework has fully adapted to the updated dynamic profile of the operation and maintenance scenario, and the iterative adjustment process stops. If the fit does not reach the threshold, the process returns to step S151 and continues to monitor the feature changes of the scenario feature dimension, requirement feature dimension, and performance feature dimension in the dynamic profile of the operation and maintenance scenario in real time. When the change of any feature dimension exceeds the corresponding threshold, a new round of iterative adjustment is triggered, and the adjustment and fit calculation process of steps S152 to S155 is repeated. After each round of iterative adjustment, the specific conditions that triggered the adjustment (such as the voltage stability feature parameter change exceeding the standard, the task priority indicator change exceeding the standard, etc.), the specific content of the adjustment (such as the adjusted resource configuration ratio, the step execution order, the exception handling process, etc.), and the change data of the fit (such as the fit before adjustment, the fit after adjustment, and the change of each sub-item matching degree) are recorded to form an iterative adjustment log. This iterative adjustment log can be used to trace the adjustment process and optimize the iterative strategy.

[0145] Step S157: After the iterative adjustment stops, extract the resource configuration ratio, step execution order and abnormal response plan data at this time, and integrate them into the adjusted initial operation and maintenance scheduling scheme framework.

[0146] Once the iterative adjustments cease due to met suitability standards, the following data is extracted from the current initial operation and maintenance scheduling framework: resource allocation ratios (e.g., the quantity ratios of human resources, equipment resources, and material resources) at the resource allocation layer; the execution sequence of steps at the step timing layer (a complete sequence of operation and maintenance steps ordered by priority); and contingency plan data for anomalies at the anomaly response layer (covering the handling process, division of responsibilities, and verification standards for various anomalies). This data is then integrated according to the collaborative logic of "resource-process-risk" to ensure that resource allocation supports step execution and that anomalies during step execution are addressed promptly. This results in an adjusted initial operation and maintenance scheduling framework that is highly adaptable to the current operation and maintenance scenario.

[0147] Step S158: Obtain the final cable operation and maintenance scheduling plan, generate operation and maintenance scheduling instructions based on the final cable operation and maintenance scheduling plan, and send them to the operation and maintenance execution terminal.

[0148] The revised initial operation and maintenance (O&M) scheduling framework was further refined, supplementing specific execution details such as resource scheduling times, responsible persons for each step, and communication mechanisms for handling anomalies, resulting in a complete and directly executable final cable O&M scheduling plan. Following the instruction format requirements of the O&M execution terminal, the core information in the final cable O&M scheduling plan (such as task name, execution time, resource list, step sequence, and key points for anomaly handling) was converted into structured O&M scheduling instructions. These instructions were then sent to the O&M execution terminal via an encrypted communication network. Upon receiving the instructions, the terminal automatically parsed and displayed key information, guiding O&M personnel to execute cable O&M tasks according to the instructions.

[0149] Figure 2 The illustration shows exemplary hardware and software components of an intelligent scheduling system 100 for cable maintenance that can implement the ideas of this application, according to some embodiments of this application. For example, processor 120 can be used in the intelligent scheduling system 100 for cable maintenance and to perform the functions described in this application.

[0150] The intelligent scheduling system 100 for cable maintenance can be a general-purpose server or a special-purpose server; both can be used to implement the intelligent scheduling method for cable maintenance described in this application. Although only one server is shown in this application, for convenience, the functions described in this application can be implemented in a distributed manner on multiple similar platforms to balance the load.

[0151] For example, the intelligent scheduling system 100 for cable maintenance may include a network port 110 connected to a network, one or more processors 120 for executing program instructions, a communication bus 130, and various forms of storage media 140, such as a disk, ROM, or RAM, or any combination thereof. Exemplarily, the intelligent scheduling system 100 for cable maintenance may also include program instructions stored in ROM, RAM, or other types of non-transitory storage media, or any combination thereof. The methods of this application can be implemented according to these program instructions. The intelligent scheduling system 100 for cable maintenance also includes an I / O interface 150 between the computer and other input / output devices.

[0152] For ease of explanation, only one processor is described in the intelligent scheduling system 100 for cable maintenance. However, it should be noted that the intelligent scheduling system 100 for cable maintenance in this application may also include multiple processors. Therefore, the steps executed by one processor as described in this application may also be executed jointly by multiple processors or individually. For example, if the processor of the intelligent scheduling system 100 for cable maintenance executes steps A and B, it should be understood that steps A and B may also be executed jointly by two different processors or individually by one processor. For example, the first processor executes step A, the second processor executes step B, or the first processor and the second processor jointly execute steps A and B.

[0153] It should be noted that, in order to simplify the description of the present invention and thus help to understand one or more embodiments of the invention, multiple features may sometimes be grouped into one embodiment, drawing or description thereof in the foregoing description of the embodiments of the present invention.

Claims

1. An intelligent scheduling method for cable operation and maintenance, characterized in that, The method includes: The migration knowledge elements in the cable operation and maintenance migration knowledge base are deconstructed and divided into resource adaptation knowledge elements, process adaptation knowledge elements and risk adaptation knowledge elements, generating a set of knowledge element classifications. The cable operation and maintenance migration knowledge base stores migration knowledge elements for different cable operation and maintenance scenarios, and the migration knowledge elements record scenario-based operation and maintenance practice rules. Construct a dynamic profile of the operation and maintenance scenario of the cable to be scheduled, integrate the operation characteristic data, operation and maintenance task requirement data and historical operation and maintenance performance data of the cable to be scheduled, and generate a three-dimensional scene profile including scenario feature dimension, requirement feature dimension and performance feature dimension. Calculate the adaptation coefficient between each transferred knowledge element in the knowledge element classification set and the dynamic profile of the operation and maintenance scenario, and select the target knowledge element combination based on the adaptation coefficient. The adaptation coefficient reflects the degree of matching between the transferred knowledge element and the dynamic profile of the operation and maintenance scenario in each dimension. The initial operation and maintenance scheduling scheme framework is constructed based on the combination of target knowledge elements, and incorporates the resource configuration rules of resource adaptation knowledge elements, the step sequence rules of process adaptation knowledge elements, and the abnormal response rules of risk adaptation knowledge elements. The initial operation and maintenance scheduling scheme framework is adjusted by iteratively updating the dynamic profile of the operation and maintenance scenario through multiple rounds of operation and maintenance scenario. The resource allocation ratio, step execution order and abnormal response plan are optimized by combining the feature changes of the dynamic profile of the operation and maintenance scenario. The final cable operation and maintenance scheduling scheme is obtained. Based on the final cable operation and maintenance scheduling scheme, operation and maintenance scheduling instructions are generated and sent to the operation and maintenance execution terminal. The construction of a dynamic profile of the operation and maintenance scenario for the cable to be scheduled integrates the operational characteristic data, operation and maintenance task requirement data, and historical operation and maintenance performance data of the cable to be scheduled, generating a three-dimensional scene profile including scenario feature dimensions, requirement feature dimensions, and performance feature dimensions, including: The operation characteristic data of the cable to be scheduled is obtained, and the key parameter values ​​of each characteristic are extracted to form the basic data of the scene characteristic dimension of the dynamic profile of the operation and maintenance scenario. The operation characteristic data includes voltage stability characteristics, current load characteristics, temperature distribution characteristics and insulation performance characteristics. Collect maintenance task requirement data for cables to be scheduled, convert the maintenance task requirement data into quantitative indicators of feature dimensions of dynamic profile requirements for maintenance scenarios, and determine the weight coefficient of each quantitative indicator. The maintenance task requirement data includes task priority, task coverage and task completion time limit. Retrieve historical operation and maintenance performance data of the cable to be scheduled, calculate the statistical feature values ​​of the historical operation and maintenance performance data to form reference data for the performance feature dimensions of the dynamic profile of the operation and maintenance scenario. The historical operation and maintenance performance data includes the resource utilization rate, step execution efficiency and abnormal response speed of past operation and maintenance tasks. Establish a three-dimensional scene profiling framework for dynamic profiling of operation and maintenance scenarios, set up a hierarchical structure of scene feature dimensions, requirement feature dimensions, and performance feature dimensions, and divide each dimension into multiple sub-dimensions, with each sub-dimension corresponding to a specific type of feature data. Fill the corresponding sub-dimensions with the basic data of the scenario feature dimension, the quantitative indicators of the requirement feature dimension, and the reference data of the performance feature dimension of the dynamic profile of the operation and maintenance scenario, and set an update timestamp for the data of each sub-dimension. Define the association rules between the dimensions of the dynamic profile of the operation and maintenance scenario. Changes in the voltage stability feature sub-dimension data of the dynamic profile of the operation and maintenance scenario trigger the adjustment of the weight of the task priority sub-dimension of the demand feature dimension. Changes in the resource utilization sub-dimension data of the performance feature dimension trigger the update of the current load feature sub-dimension parameter of the scenario feature dimension. Set the trigger conditions for the iterative update of the dynamic profile of the operation and maintenance scenario. When the change of any sub-dimensional data exceeds the preset threshold, the overall update of the dynamic profile of the operation and maintenance scenario is triggered. Record the changes of dimensional data after each update to complete the construction of the dynamic profile of the operation and maintenance scenario. The adaptation coefficients of each transferred knowledge element in the computational knowledge element classification set and the dynamic profile of the operation and maintenance scenario are used to select target knowledge element combinations based on the adaptation coefficients, including: Extract key parameters of the scenario feature dimension, quantitative indicators of the requirement feature dimension, and statistical feature values ​​of the performance feature dimension from the dynamic profile of the operation and maintenance scenario to form a feature vector of the dynamic profile of the operation and maintenance scenario. Extract the adaptation dimension parameters of each transfer knowledge element in the knowledge element classification set, and convert the resource adaptation dimension parameters of the resource adaptation knowledge element, the process adaptation dimension parameters of the process adaptation knowledge element, and the risk adaptation dimension parameters of the risk adaptation knowledge element into transfer knowledge element feature vectors respectively. Calculate the cosine similarity between the feature vector of each transferred knowledge element and the feature vector of the dynamic profile of the operation and maintenance scenario, and use the cosine similarity value as the adaptation coefficient between the transferred knowledge element and the dynamic profile of the operation and maintenance scenario. Resource adaptation knowledge elements, process adaptation knowledge elements, and risk adaptation knowledge elements with adaptation coefficients higher than the adaptation coefficient threshold are selected to form three categories of candidate migration knowledge element subsets. For each subset of candidate transferable knowledge elements, sort the transferable knowledge elements from high to low according to their fit coefficients, and select the top N transferable knowledge elements from each subset of candidate transferable knowledge elements. Analyze the synergistic compatibility among the selected transferable knowledge elements, calculate the synergistic adaptation coefficient among different categories of transferable knowledge elements, and screen out the combinations of transferable knowledge elements with synergistic adaptation coefficients higher than the synergistic threshold. From the combinations of transferable knowledge elements that meet the criteria for collaborative adaptation coefficient, the combination with the highest comprehensive adaptation coefficient is selected as the target knowledge element combination. The comprehensive adaptation coefficient is the weighted average of the adaptation coefficients of each transferable knowledge element in the combination, and the weighting is determined based on the importance of the transferable knowledge element category.

2. The intelligent scheduling method for cable operation and maintenance according to claim 1, characterized in that, The migration knowledge elements in the cable operation and maintenance migration knowledge base are deconstructed, and divided into resource adaptation knowledge elements, process adaptation knowledge elements, and risk adaptation knowledge elements, generating a set of knowledge element classifications, including: Retrieve all migration knowledge elements from the cable maintenance migration knowledge base, extract the knowledge content description, applicable scenario tags, and application effect records of each migration knowledge element, and form the original dataset of migration knowledge elements. Semantic parsing is performed on the knowledge content description of each transfer knowledge element in the original dataset of transfer knowledge elements to identify the resource configuration-related statements, step sequence-related statements, and anomaly response-related statements contained therein; The proportion of the three types of expressions in each migration knowledge element is counted. If the proportion of resource configuration-related expressions is the highest, the migration knowledge element is marked as a resource adaptation knowledge element. The resource adaptation knowledge element includes operation and maintenance resource type selection rules, resource quantity allocation rules, and resource allocation path rules. If the sequence-related descriptions of steps account for the highest proportion, then the migration knowledge element is marked as a process adaptation knowledge element. The process adaptation knowledge element includes the order rules of operation and maintenance steps, the rules for allocating the execution time of steps, and the rules for step connection and transition. If the description related to anomaly response accounts for the highest proportion, then the migration knowledge element is marked as a risk adaptation knowledge element. The risk adaptation knowledge element includes anomaly type identification rules, anomaly handling measure rules, and anomaly recovery verification rules. The three types of migration knowledge elements after being marked are labeled with attributes: resource adaptation dimension parameters are labeled for resource adaptation knowledge elements, process adaptation dimension parameters are labeled for process adaptation knowledge elements, and risk adaptation dimension parameters are labeled for risk adaptation knowledge elements. An index system for knowledge element classification sets is constructed, a search path is established based on applicable scenario tags and adaptation dimension parameters, the relationship between the three types of migrated knowledge elements and the collaborative application logic are recorded, and a knowledge element classification set is generated.

3. The intelligent scheduling method for cable operation and maintenance according to claim 2, characterized in that, The process of annotating the three types of transfer knowledge elements after labeling includes: annotating resource adaptation dimension parameters for resource adaptation knowledge elements, process adaptation dimension parameters for process adaptation knowledge elements, and risk adaptation dimension parameters for risk adaptation knowledge elements. For resource adaptation knowledge elements, the number of resource types, resource allocation accuracy, and resource allocation response time involved are extracted and used as resource adaptation dimension parameters of the resource adaptation knowledge elements. A specific value range is set for each resource adaptation dimension parameter. For process adaptation knowledge elements, the number of steps, the precision of step sequence, and the fault tolerance rate of step connection are extracted and used as process adaptation dimension parameters of the process adaptation knowledge elements. Specific quantitative standards are set for each process adaptation dimension parameter. For risk adaptation knowledge elements, the anomaly identification accuracy, anomaly handling time, and anomaly recovery success rate involved are extracted and used as risk adaptation dimension parameters of the risk adaptation knowledge elements. Specific evaluation indicators are set for each risk adaptation dimension parameter. Establish rules for labeling migration knowledge element parameters. The number of resource types in the resource adaptation dimension parameters of resource adaptation knowledge elements are labeled separately according to the number of categories of human resources, equipment resources, and material resources. Resource allocation accuracy is labeled according to percentage accuracy, and resource allocation response time is labeled according to time unit. The number of steps in the process adaptation dimension parameters of the process adaptation knowledge element is marked separately according to the number of main steps and the number of sub-steps; the step timing accuracy is marked according to the time deviation range; and the step connection fault tolerance rate is marked according to the allowable deviation ratio. In the risk adaptation dimension parameters of the risk adaptation knowledge element, the anomaly identification accuracy is marked by the identification accuracy rate, the anomaly handling time is marked by the time range of the handling process, and the anomaly recovery success rate is marked by the percentage of successful cases. Add parameter source identifiers to the adaptation dimension parameters of each migrated knowledge element, and indicate the parameter update cycle.

4. The intelligent scheduling method for cable operation and maintenance according to claim 1, characterized in that, The defined association rules between the dimensions of the dynamic profile of the operation and maintenance scenario include: changes in the voltage stability feature sub-dimension of the scenario feature dimension trigger adjustments to the weights of the task priority sub-dimension of the demand feature dimension; and changes in the resource utilization sub-dimension of the performance feature dimension trigger updates to the parameters of the current load feature sub-dimension of the scenario feature dimension. Define the association rules between the dimensions of the dynamic profile of the operation and maintenance scenario. Changes in the voltage stability feature sub-dimension data of the dynamic profile of the operation and maintenance scenario trigger the adjustment of the weight of the task priority sub-dimension of the demand feature dimension. Changes in the resource utilization sub-dimension data of the performance feature dimension trigger the update of the current load feature sub-dimension parameter of the scenario feature dimension. Establish a correlation model between the scenario feature dimension and the demand feature dimension of the dynamic profile of the operation and maintenance scenario. Take the fluctuation level of the voltage stability feature sub-dimension of the scenario feature dimension of the dynamic profile of the operation and maintenance scenario as the input variable, and the weight adjustment range of the task priority sub-dimension of the demand feature dimension of the dynamic profile of the operation and maintenance scenario as the output variable. Set the correspondence between fluctuation amplitude level and weight adjustment range. When the fluctuation amplitude level of the voltage stability feature sub-dimension of the dynamic profile scenario feature dimension is the first level, the weight of the tasks related to voltage regulation in the task priority sub-dimension of the dynamic profile scenario feature dimension is increased by the first proportion. When the fluctuation amplitude level of the voltage stability feature sub-dimension of the dynamic profile of the operation and maintenance scenario is the second level, the weight of the task related to voltage regulation in the task priority sub-dimension of the demand feature dimension of the dynamic profile of the operation and maintenance scenario is increased by the second proportion, which is greater than the first proportion. Establish a correlation model between the dynamic profile performance feature dimension and the scene feature dimension of the operation and maintenance scenario. Take the deviation rate between the actual value and the theoretical value of the resource utilization rate sub-dimensional of the dynamic profile performance feature dimension of the operation and maintenance scenario as the input variable, and the parameter adjustment level of the current load feature sub-dimensional of the scene feature dimension of the dynamic profile performance feature dimension of the operation and maintenance scenario as the output variable. Set the correspondence between the deviation rate range and the parameter adjustment level. When the deviation rate of the resource utilization sub-dimension of the dynamic profile of the operation and maintenance scenario is positive and within the first range, the rated load parameter adjustment level of the current load feature sub-dimension of the dynamic profile of the operation and maintenance scenario is set to the first level, and the first value is lowered accordingly. When the deviation rate of the resource utilization sub-dimension of the dynamic profile of the operation and maintenance scenario is negative and within the second range, the rated load parameter adjustment level of the current load feature sub-dimension of the dynamic profile of the operation and maintenance scenario is set to the second level, and the second value is adjusted accordingly. The correspondence between the set fluctuation level and the weight adjustment level, as well as the correspondence between the deviation rate range and the parameter adjustment level, are encoded into an executable association rule script and embedded into the update module of the dynamic profile of the operation and maintenance scenario. When the trigger condition is met, the corresponding weight adjustment or parameter update operation is automatically executed, and the time, input data and output results of each association rule execution are recorded.

5. The intelligent scheduling method for cable operation and maintenance according to claim 1, characterized in that, The analysis selects the collaborative compatibility among the transferred knowledge elements, calculates the collaborative adaptation coefficients among different categories of transferred knowledge elements, and filters out combinations of transferred knowledge elements with collaborative adaptation coefficients higher than a collaborative threshold, including: Select one resource adaptation knowledge element, one process adaptation knowledge element, and one risk adaptation knowledge element to form a migration knowledge element combination to be evaluated. Extract the resource allocation time parameter of the resource adaptation knowledge element, the step start time parameter of the process adaptation knowledge element, and the exception handling start time parameter of the risk adaptation knowledge element within the migration knowledge element combination to be evaluated. The time difference between the resource allocation time parameter of the resource adaptation knowledge element and the step start time parameter of the process adaptation knowledge element is calculated. If the time difference is within the allowable range, the first collaborative adaptation score of the combination of migration knowledge elements to be evaluated is recorded as the first score; otherwise, it is recorded as the second score. The second score is lower than the first score. The time difference between the start time parameter of the calculation process adaptation knowledge element and the start time parameter of the exception handling of the risk adaptation knowledge element is calculated. If the time difference is within the allowable range, the second collaborative adaptation score of the combination of transfer knowledge elements to be evaluated is recorded as the third score; otherwise, it is recorded as the fourth score. The fourth score is lower than the third score. The time difference between the resource allocation time parameter of the resource adaptation knowledge element and the anomaly handling start time parameter of the risk adaptation knowledge element is calculated. If the time difference is within the allowable range, the third collaborative adaptation score of the combination of migration knowledge elements to be evaluated is recorded as the fifth score; otherwise, it is recorded as the sixth score. The sixth score is lower than the fifth score. The first, second, and third collaborative adaptation scores of the combination of transferable knowledge elements to be evaluated are weighted and summed. The weights are determined based on the importance of the three types of collaborative relationships to obtain the collaborative adaptation coefficient of the combination of transferable knowledge elements to be evaluated. If the synergy adaptation coefficient of the transfer knowledge element combination to be evaluated is higher than the synergy threshold, the transfer knowledge element combination to be evaluated is determined to be synergistically compatible; if it is lower than the synergy threshold, the corresponding class of transfer knowledge element in the transfer knowledge element combination to be evaluated is replaced and the synergy adaptation coefficient is recalculated. Repeat the above evaluation process until a combination of transferable knowledge elements with a synergy fit coefficient higher than the synergy threshold is found. Record the synergy fit coefficient and the score of each sub-item for each qualified combination of transferable knowledge elements.

6. The intelligent scheduling method for cable operation and maintenance according to claim 1, characterized in that, The initial operation and maintenance scheduling scheme framework, constructed based on the combination of target knowledge elements, incorporates resource configuration rules of resource adaptation knowledge elements, step sequence rules of process adaptation knowledge elements, and anomaly response rules of risk adaptation knowledge elements, including: Analyze the resource allocation rules of resource-adaptive knowledge elements in the target knowledge element combination, and extract the resource type selection conditions, resource quantity calculation methods and resource allocation path planning logic; Match the types of human resources, equipment resources and material resources required for the operation and maintenance of the cable to be scheduled according to the resource type selection conditions, determine the specific quantity of each type of resource based on the resource quantity calculation method, and design the resource transportation and allocation route according to the resource allocation path planning logic. Analyze the step sequence rules of process adaptation knowledge elements in the target knowledge element combination, and extract the step sequence constraint relationship, step duration calculation model and step connection condition; The basic steps of operation and maintenance are determined based on the constraints of step sequence. The expected execution time of each step is calculated using the step duration calculation model. The transition connection method between steps is designed in combination with the step connection conditions. Analyze the anomaly response rules of risk-adaptive knowledge elements in the target knowledge element combination, and extract the anomaly type judgment criteria, anomaly handling measure list and anomaly recovery verification standards. Based on the criteria for judging anomalies, we sort out the types of anomalies that may occur during the operation and maintenance of cables to be scheduled. Based on the list of anomaly handling measures, we match the corresponding handling process for each type of anomaly and formulate a method for verifying the effect of anomaly handling in conjunction with the anomaly recovery verification standard. The initial operation and maintenance scheduling scheme framework is constructed in three layers: the resource configuration layer stores the resource types, quantities and allocation paths; the step sequence layer stores the step order, execution time and connection method; and the exception handling layer stores the exception types, processing flow and verification method. The data flow interaction rules between the three layers of the initial operation and maintenance scheduling scheme framework are set. The resource availability signal of the resource configuration layer of the initial operation and maintenance scheduling scheme framework triggers the step start instruction of the step timing layer of the initial operation and maintenance scheduling scheme framework. The abnormal monitoring signal of the step timing layer of the initial operation and maintenance scheduling scheme framework triggers the processing flow start instruction of the abnormal response layer of the initial operation and maintenance scheduling scheme framework, thus completing the construction of the initial operation and maintenance scheduling scheme framework.

7. The intelligent scheduling method for cable operation and maintenance according to claim 1, characterized in that, The initial operation and maintenance scheduling scheme framework is adjusted through multiple rounds of dynamic profile updates for operation and maintenance scenarios. Resource allocation ratios, step execution sequences, and contingency plans for handling anomalies are optimized based on the characteristics of the dynamic profiles of operation and maintenance scenarios. This includes: Monitor the feature changes of the dynamic profile of the operation and maintenance scenario. When the absolute value of the change of the voltage stability feature parameter of the dynamic profile of the operation and maintenance scenario exceeds the preset voltage change threshold, the first round of iterative adjustment is triggered. In the first round of iterative adjustment, the impact of changes in voltage stability characteristic parameters on resource demand is analyzed. Based on the dynamic adjustment rules of resource adaptation knowledge elements in the target knowledge element combination, the linear relationship between voltage change and equipment resource demand change is calculated. The equipment resource configuration ratio related to voltage regulation is adjusted according to the linear relationship. When the absolute value of the change in the task priority index of the dynamic profile requirement feature dimension of the operation and maintenance scenario exceeds the preset priority change threshold, the second round of iterative adjustment is triggered. Based on the priority adjustment rules of the process adaptation knowledge element, the priority score of each operation and maintenance step is recalculated according to the numerical change of the task priority index, and the execution order of the operation and maintenance steps is reordered in descending order of priority score. When the absolute value of the abnormal response speed statistical value of the dynamic profile of the operation and maintenance scenario exceeds the preset response speed change threshold, the third round of iterative adjustment is triggered. Based on the contingency plan optimization rules of risk adaptation knowledge elements, the steps in the abnormal handling process that exceed the preset time efficiency threshold are identified. The process is simplified by merging or removing steps that exceed the execution time standard, thereby shortening the abnormal response time. After each round of iterative adjustments, the fit degree between the adjusted initial operation and maintenance scheduling scheme framework and the updated operation and maintenance scenario dynamic profile is calculated. The fit degree is the sum of the matching degree between the data of each layer of the adjusted initial operation and maintenance scheduling scheme framework and the corresponding dimension data of the updated operation and maintenance scenario dynamic profile. If the adaptation of the initial operation and maintenance scheduling scheme framework after iterative adjustment and the updated dynamic profile of the operation and maintenance scenario reach the adaptation standard, the iteration stops; if not, the monitoring of the changes in the characteristics of the dynamic profile of the operation and maintenance scenario continues, triggering the next round of iterative adjustment until the adaptation standard is met. Record the triggering conditions, adjustment content, and adaptation changes for each round of iterations to form an iteration adjustment log; Once the iterative adjustments cease, extract the resource allocation ratio, step execution order, and contingency plan data at that time, and integrate them into the adjusted initial operation and maintenance scheduling scheme framework.

8. An intelligent dispatching system for cable operation and maintenance, characterized in that, The intelligent scheduling system for cable maintenance includes a processor and a memory, the memory and the processor being connected. The memory is used to store programs, instructions or code, and the processor is used to execute the programs, instructions or code in the memory to implement the intelligent scheduling method for cable maintenance as described in any one of claims 1-7.

Images