Electric power communication service operation and maintenance data analysis method

Abstract

The invention relates to the technical field of electric power operation and maintenance analysis, in particular to an electric power communication service operation and maintenance data analysis method. The method comprises the following steps: carrying out operation and maintenance data low-power-consumption real-time acquisition and information communication service operation and maintenance case analysis on an electric power information communication service process between electric power equipment and an information communication infrastructure so as to obtain an electric power information communication service real-time operation and maintenance case; case local fuzzy feature analysis is carried out on the real-time operation and maintenance case of the power communication service, and a historical operation and maintenance case of the power communication service is obtained to carry out real-time case local similarity reasoning analysis and operation and maintenance decision mining analysis, so that a historical similar operation and maintenance decision support scheme of the power communication service is obtained; and performing service operation and maintenance feedback optimization processing on the corresponding real-time operation and maintenance case of the power communication service according to the historical similar operation and maintenance decision support scheme of the power communication service to obtain an operation and maintenance feedback optimization management result of the power communication service. According to the invention, the operation and maintenance efficiency and decision scientificity of the power communication service can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of electric power operation and maintenance analysis, and in particular to a method for analyzing electric power information and communication business operation and maintenance data. Background Art

[0002] With the rapid development of information technology and communication technology, the complexity and data volume of power communication services are increasing, which puts higher requirements on operation and maintenance management. In modern power systems, communication services not only include power dispatching, monitoring and control, but also involve extensive communications, data transmission and information processing. How to effectively analyze and utilize massive operation and maintenance data to improve the operating efficiency and safety of power communication services has become a technical problem that needs to be solved urgently.

[0003] With the continuous development of big data technology and artificial intelligence, a unified data management platform is established to integrate multiple data sources from power equipment, communication networks and user terminals to form a comprehensive operation and maintenance data set. This integration can provide rich basic information for subsequent data analysis. At the same time, by adopting stream data processing technology, the key indicators of power information and communication services are monitored in real time. By establishing a dynamic monitoring model, the signs of system anomalies and performance degradation are captured in time to support rapid decision-making. Advanced technologies such as machine learning and deep learning are used to analyze historical operation and maintenance data and real-time monitoring data, explore potential failure modes and influencing factors, and achieve fault prediction and early warning. These intelligent algorithms can adapt to the nonlinear characteristics of data and improve the accuracy and effectiveness of analysis. However, traditional power information and communication service operation and maintenance data analysis methods mainly rely on traditional data processing methods. These methods usually perform simple statistical analysis or trend prediction for specific data sets, lack deep mining and comprehensive analysis of information and communication service operation and maintenance cases, and cannot fully reflect the operating status of the power information and communication process, resulting in low operation and maintenance efficiency and untimely decision-making response. Summary of the invention

[0004] Based on this, it is necessary for the present invention to provide a method for analyzing power information and communication business operation and maintenance data to solve at least one of the above-mentioned technical problems.

[0005] To achieve the above purpose, a method for analyzing power information and communication business operation and maintenance data includes the following steps: Step S1: low-power real-time collection of operation and maintenance data of the power communication business process between the power equipment and the communication infrastructure to obtain real-time monitoring data of power communication business operation and maintenance; analysis of communication business operation and maintenance cases on the real-time monitoring data of power communication business operation and maintenance to obtain real-time operation and maintenance cases of power communication business; Step S2: Perform local fuzzy feature analysis on the real-time operation and maintenance cases of electric power information and communication services to obtain local fuzzy features of the real-time operation and maintenance cases of electric power information and communication services; obtain historical operation and maintenance cases of electric power information and communication services, and perform local similarity reasoning analysis on the historical operation and maintenance cases of electric power information and communication services based on the local fuzzy features of the real-time operation and maintenance cases of electric power information and communication services to obtain historical similar operation and maintenance cases corresponding to the real-time operation and maintenance cases of electric power information and communication services; Step S3: Performing operation and maintenance decision mining and analysis on historical similar operation and maintenance cases corresponding to the real-time operation and maintenance cases of electric power information and communication services, and obtaining a support plan for historical similar operation and maintenance decisions of electric power information and communication services; Step S4: Perform business operation and maintenance feedback optimization processing on the corresponding real-time operation and maintenance cases of electric power communication services according to the historical similar operation and maintenance decision support scheme of electric power communication services to obtain the operation and maintenance feedback optimization management results of electric power communication services.

[0006] Further, step S1 includes the following steps: Step S11: Deploy various operation and maintenance sensors between the power equipment and the information and communication infrastructure, wherein the operation and maintenance sensors include current sensors, temperature sensors, and vibration sensors, and use low-power wide area network technology to construct an operation and maintenance monitoring network for the various operation and maintenance sensors deployed between the power equipment and the information and communication infrastructure, so as to generate an operation and maintenance monitoring network for power information and communication services; Step S12: using the power information and communication service operation and maintenance monitoring network to collect operation and maintenance data of the power information and communication service process between the power equipment and the information and communication infrastructure in real time with low power consumption, so as to obtain real-time monitoring data of power information and communication service operation and maintenance; Step S13: performing quantitative analysis of operation and maintenance indicators on the real-time monitoring data of the power information and communication service operation and maintenance to obtain a parameter set of power information and communication service operation and maintenance performance indicators; Step S14: Based on the power information and communication service operation and maintenance performance indicator parameter set, statistical analysis is performed on the power information and communication service process corresponding to the power equipment and the information and communication infrastructure to obtain the power information and communication service process operation and maintenance description characteristics; Step S15: Perform communication and information service operation and maintenance case analysis based on the power communication and information service process operation and maintenance description characteristics to obtain real-time operation and maintenance cases for the power communication and information service.

[0007] Further, step S13 includes the following steps: Step S131: converting the real-time monitoring data of the power information and communication business operation and maintenance into a time series data stream to obtain a time series data stream of the power information and communication business operation and maintenance monitoring; Step S132: Performing power information and communication operation and maintenance state variable analysis on the power information and communication business operation and maintenance monitoring time series data stream to obtain power information and communication business operation and maintenance state variables, wherein the power information and communication business operation and maintenance state variables include power information and communication operation and maintenance current fluctuation rate, power information and communication operation and maintenance fault duration, and power information and communication operation response time; Step S133: performing quantitative analysis on the availability of power communication and information service operation and maintenance for the corresponding power communication and information service process according to the power communication and information service operation and maintenance current fluctuation rate, and obtaining the power communication and information service operation and maintenance equipment availability index parameter; Step S134: quantitatively analyzing the efficiency of power communication and information service operation and maintenance and the failure rate of power communication and information service operation and maintenance on the corresponding power communication and information service process according to the duration of the power communication and information service operation and maintenance failure and the power communication and information service operation and maintenance response time, so as to obtain the power communication and information service operation and maintenance efficiency index parameter and the power communication and information service operation and maintenance failure rate index parameter; Step S135: Merge the performance indicator parameters of the electric power information and communication business operation and maintenance equipment availability indicator parameters, the electric power information and communication business operation and maintenance maintenance efficiency indicator parameters, and the electric power information and communication business operation and maintenance failure occurrence rate indicator parameters to obtain the electric power information and communication business operation and maintenance performance indicator parameter set.

[0008] Further, step S2 includes the following steps: Step S21: dividing the real-time operation and maintenance cases of electric power information and communication services into operation and maintenance attribute classes to obtain the real-time operation and maintenance case attribute data of electric power information and communication services; Step S22: performing operation and maintenance local feature clustering analysis on the corresponding real-time operation and maintenance cases of electric power information and communication services based on the attribute data of the real-time operation and maintenance cases of electric power information and communication services, and obtaining the local feature clustering results of the real-time operation and maintenance cases; Step S23: Based on the local feature clustering results of the real-time operation and maintenance cases, the local fuzzy feature analysis of the corresponding real-time operation and maintenance cases of the electric power information and communication services is performed to obtain the local fuzzy features of the real-time operation and maintenance cases of the electric power information and communication services; Step S24: obtaining historical operation and maintenance cases of electric power information and communication services, and performing consistent local fuzzy feature analysis on the historical operation and maintenance cases of electric power information and communication services to obtain local fuzzy features corresponding to each historical operation and maintenance case of electric power information and communication services; Step S25: Based on the local fuzzy features of the real-time operation and maintenance cases of the electric power information and communication services, the local fuzzy features corresponding to the historical operation and maintenance cases of the electric power information and communication services are subjected to real-time case local similarity reasoning analysis to obtain historical similar operation and maintenance cases corresponding to the real-time operation and maintenance cases of the electric power information and communication services.

[0009] Further, step S23 includes the following steps: Step S231: performing fuzzy feature space membership mapping conversion on each operation and maintenance case local feature clustering cluster in the local feature clustering result of the real-time operation and maintenance case to obtain the local fuzzy feature mapping space of each real-time operation and maintenance case; Step S232: performing fuzzy feature association analysis on each local fuzzy sub-feature of each operation and maintenance case in the local fuzzy feature mapping space of each real-time operation and maintenance case, so as to obtain a potential association relationship between different local fuzzy sub-features in each local fuzzy feature mapping space; Step S233: constructing a feature matrix connection for each operation and maintenance case local fuzzy sub-feature in the local fuzzy feature mapping space corresponding to the real-time operation and maintenance case based on the potential correlation between different local fuzzy sub-features in each local fuzzy feature mapping space, so as to generate a local fuzzy feature mapping matrix for the real-time operation and maintenance case; Step S234: Based on each local fuzzy sub-feature of the operation and maintenance case in the local fuzzy feature mapping matrix of the real-time operation and maintenance case, a fuzzy sub-feature evaluation calculation is performed on the corresponding real-time operation and maintenance case of the electric power information and communication business using the local fuzzy feature performance calculation formula to obtain the local fuzzy feature performance score of the operation and maintenance case corresponding to each local fuzzy sub-feature in the local fuzzy feature mapping matrix; Step S235: Perform local fuzzy feature screening and output according to the local fuzzy feature performance score of the operation and maintenance case corresponding to each local fuzzy sub-feature in the local fuzzy feature mapping matrix to obtain the local fuzzy features of the real-time operation and maintenance case of the electric power information and communication business.

[0010] Further, step S231 includes the following steps: Perform outlier feature elimination processing on each local feature clustering cluster of operation and maintenance cases in the local feature clustering result of real-time operation and maintenance cases to obtain local outlier optimized feature clustering clusters of each real-time operation and maintenance case; Perform local fuzzy feature matching calculation on each local sub-feature of the operation and maintenance case in the local outlier optimization feature clustering cluster of each real-time operation and maintenance case, and obtain each local fuzzy sub-feature of the operation and maintenance case corresponding to the local feature clustering cluster of each real-time operation and maintenance case; Perform triangular and Gaussian fuzzy number statistical analysis on each local fuzzy sub-feature of each operation and maintenance case corresponding to each local feature clustering cluster of each real-time operation and maintenance case, and obtain the triangular fuzzy number and Gaussian fuzzy number corresponding to each local fuzzy sub-feature of each operation and maintenance case in each local feature clustering cluster; Based on the triangular fuzzy number and Gaussian fuzzy number corresponding to each local fuzzy sub-feature of each operation and maintenance case in each local feature clustering cluster, the feature fuzzy membership quantization calculation is performed on each corresponding local fuzzy sub-feature of the operation and maintenance case to obtain the feature fuzzy membership corresponding to each local fuzzy sub-feature of the operation and maintenance case in each local feature clustering cluster; Based on the feature fuzzy membership corresponding to each local fuzzy sub-feature of each operation and maintenance case in each local feature clustering cluster, the fuzzy feature space membership mapping conversion is performed on the corresponding local fuzzy sub-feature of each operation and maintenance case to obtain the local fuzzy feature mapping space of each real-time operation and maintenance case.

[0011] Furthermore, the outlier feature elimination process for each operation and maintenance case local feature clustering cluster in the real-time operation and maintenance case local feature clustering result includes the following steps: Perform local feature mean and variance statistical calculations on each operation and maintenance case local feature clustering cluster in the real-time operation and maintenance case local feature clustering results to obtain the local feature mean and local feature variance corresponding to each operation and maintenance case local feature clustering cluster; The outlier feature discrimination threshold is calculated based on the local feature mean and local feature variance corresponding to each operation and maintenance case local feature cluster, and the local outlier feature discrimination threshold corresponding to each operation and maintenance case local feature cluster is obtained; According to the local outlier feature discrimination threshold corresponding to each operation and maintenance case local feature clustering cluster, the corresponding operation and maintenance case local sub-features in each operation and maintenance case local feature clustering cluster are identified and judged. If the corresponding operation and maintenance case local sub-feature is greater than or equal to the local outlier feature discrimination threshold, the corresponding operation and maintenance case local sub-feature in the operation and maintenance case local feature clustering cluster is marked as an outlier feature; if the corresponding operation and maintenance case local sub-feature is less than the local outlier feature discrimination threshold, the corresponding operation and maintenance case local sub-feature in the operation and maintenance case local feature clustering cluster is marked as a non-outlier feature; The local sub-features of the operation and maintenance cases corresponding to the outlier features in the local feature clustering clusters of each operation and maintenance case are eliminated and optimized to obtain the local outlier optimized feature clustering clusters of each real-time operation and maintenance case.

[0012] Furthermore, the triangular and Gaussian fuzzy number statistical analysis of each local fuzzy sub-feature of each operation and maintenance case corresponding to the local feature cluster of each real-time operation and maintenance case includes the following steps: Performing feature initial value statistical analysis on each local fuzzy sub-feature of each operation and maintenance case corresponding to each local feature clustering cluster of each real-time operation and maintenance case, and obtaining each local fuzzy sub-feature initial value corresponding to each local feature clustering cluster of each real-time operation and maintenance case; Based on the initial value of each local fuzzy sub-feature corresponding to each local feature cluster of each real-time operation and maintenance case, the fuzzy spatial distribution characteristics of the corresponding local fuzzy sub-feature of the operation and maintenance case are analyzed to obtain the fuzzy spatial distribution shape and fuzzy spatial distribution interval corresponding to each local fuzzy sub-feature in each local feature cluster; Based on the fuzzy spatial distribution shape and fuzzy spatial distribution interval corresponding to each local fuzzy sub-feature in each local feature cluster, the triangular fuzzy number statistical analysis is performed on the corresponding local fuzzy sub-features of the operation and maintenance cases, and the triangular fuzzy number corresponding to each local fuzzy sub-feature of the operation and maintenance cases in each local feature cluster is obtained; The triangular fuzzy number corresponding to the local fuzzy sub-feature of each operation and maintenance case in each local feature clustering cluster is calculated by Gaussian expansion transformation to obtain the Gaussian fuzzy number corresponding to the local fuzzy sub-feature of each operation and maintenance case in each local feature clustering cluster.

[0013] Furthermore, the calculation formula for the local fuzzy feature representation of the case described in step S234 is specifically: ; In the formula, is the local fuzzy sub-feature in the local fuzzy feature mapping matrix The local fuzzy feature performance score of the operation and maintenance case, is the input variable of the local fuzzy sub-feature, is the integral variable parameter of the local fuzzy sub-feature input variable, is the lower limit of the integration of the local fuzzy sub-characteristic input variable, is the upper limit of the integration of the local fuzzy sub-characteristic input variables, Input variables for local fuzzy sub-features in the local fuzzy feature map matrix The probability of occurrence, is the weight coefficient of the occurrence probability, Input variables for local fuzzy sub-features in the local fuzzy feature map matrix The response time, is the weight coefficient of response time, Input variables for local fuzzy sub-features in the local fuzzy feature map matrix The success rate of case problem solving, is the weight coefficient of the success rate of case problem solving, is the local fuzzy sub-feature attenuation factor, is the fuzzy mean of the operation and maintenance cases of the local fuzzy sub-feature input variables, It is the correction coefficient of the local fuzzy feature performance score of the operation and maintenance case.

[0014] Further, step S25 includes the following steps: Step S251: performing local fuzzy feature normalization processing on the local fuzzy features of the real-time operation and maintenance cases of the electric power information and communication services and the local fuzzy features corresponding to each historical operation and maintenance case of the electric power information and communication services, so as to obtain the local fuzzy features of the real-time operation and maintenance cases and the local fuzzy features of each historical operation and maintenance case under the same dimensional scale; Step S252: integrating the local fuzzy features of each historical operation and maintenance case to obtain a local fuzzy feature library of historical operation and maintenance cases; Step S253: performing local fuzzy hash mapping processing on the local fuzzy features of the real-time operation and maintenance cases and the local fuzzy feature library of the historical operation and maintenance cases respectively, so as to obtain the local fuzzy hash value of the real-time operation and maintenance cases and the local fuzzy hash table of the historical operation and maintenance cases; Step S254: Based on the local fuzzy hash table of historical operation and maintenance cases, similarity reasoning analysis is performed on the local fuzzy hash values ​​of the real-time operation and maintenance cases to obtain historical similar operation and maintenance cases corresponding to the real-time operation and maintenance cases of the electric power information and communication business.

[0015] Beneficial effects of the present invention: The power communication business operation and maintenance data analysis method proposed in the present invention, compared with the prior art, has the beneficial effect of deploying various operation and maintenance sensors (such as current sensors, temperature sensors and vibration sensors) between power equipment and communication infrastructure, and establishing a monitoring network through low-power wide area network (LPWAN) technology to collect operation and maintenance data of the power communication business process between power equipment and communication infrastructure in real time with low power consumption, so as to ensure that the operation and maintenance work of power equipment and communication infrastructure is always under monitoring. The data continuously collected by the sensors (such as current, temperature, vibration, etc.) can reflect the operating status of the equipment and infrastructure in real time. This real-time data collection not only provides the current health status of the equipment, but also provides a data basis for subsequent fault prediction and maintenance scheduling. The design of the low-power collection network enables these devices to operate for a long time without frequent battery replacement or maintenance, which greatly improves the operation and maintenance efficiency and reliability, thereby improving the stability and safety of the power communication business operation and maintenance process. At the same time, by conducting case analysis on the real-time monitoring data of power communication business operation and maintenance, representative operation and maintenance cases can be identified, which can help the team better understand and solve problems encountered in actual business. These cases can be downtime caused by equipment failure, abnormal changes in maintenance cycles, or the impact of the external environment on system operation. Operation and maintenance case analysis can provide reference for subsequent troubleshooting and business adjustments, and help form a standardized operation and maintenance processing flow. By combining typical operation and maintenance scenarios with actual business and analyzing the operation and maintenance strategies and effects under various different situations, the foresight and practicality of operation and maintenance work can be effectively improved, so that the operating status of the power communication business processing process can be monitored in real time. Secondly, by analyzing the local fuzzy features of the real-time operation and maintenance cases of the power communication business, it is helpful to further explore the deep-level features in the real-time operation and maintenance cases of the power communication business. This process helps to identify more complex feature combinations by analyzing the uncertainty and fuzziness information in the real-time operation and maintenance cases of the power communication business. The analysis of fuzzy features can reveal subtle correlations, especially in complex environments where faults occur. The key to this analysis is to improve the resolution of operation and maintenance cases, thereby providing support for the formulation of more refined operation and maintenance strategies. By obtaining the historical operation and maintenance cases of the power communication business, and based on the local fuzzy features of the real-time operation and maintenance cases of the power communication business, the local similarity reasoning analysis of the real-time operation and maintenance cases of the power communication business can be performed, so that the current operation and maintenance cases and the similar operation and maintenance cases in history can be effectively identified. This analysis not only helps to trace the root causes of the operation and maintenance problems of the power communication business, but also provides a reference for the decision support processing process of the current operation and maintenance cases. The key to this step is to improve the decision quality and efficiency of real-time operation and maintenance by drawing on historical successful cases, thereby improving the timeliness of the decision support response process of subsequent operation and maintenance cases.Then, by conducting operation and maintenance decision mining and analysis on historical similar operation and maintenance cases corresponding to real-time operation and maintenance cases of power information and communication services, successful operation and maintenance decision support solutions can be effectively extracted. This process relies on big data analysis technology. Through in-depth mining of historical similar cases, effective decision-making patterns and strategies can be found, which not only helps to form a standardized operation and maintenance decision-making process, but also provides a scientific basis for operation and maintenance personnel. In the decision-making process, data mining and machine learning algorithms can be used to evaluate the effectiveness of various historically similar operation and maintenance strategies, so as to find the optimal decision support solution. This data-driven decision support will significantly improve the accuracy of operation and maintenance decisions, reduce the bias of human judgment, and reduce operation and maintenance costs. At the same time, it can also improve the response speed of services and customer satisfaction. Finally, by optimizing the business operation and maintenance feedback of the corresponding real-time operation and maintenance cases of electric power information and communication services based on the historical similar operation and maintenance decision support scheme of electric power information and communication services, the effectiveness and efficiency of operation and maintenance can be greatly improved. By applying historical successful decisions to current operation and maintenance cases, it is possible to quickly respond to actual problems of real-time operation and maintenance cases, optimize resource allocation, and maximize the operation and maintenance efficiency of the operation and maintenance process of electric power information and communication services, so that operation and maintenance decisions are continuously iterated and optimized, thereby providing a sustainable improvement basis for subsequent business decisions and promoting the operation and maintenance process of electric power information and communication services to develop in a more intelligent and automated direction. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments thereof made with reference to the following drawings: Figure 1 A schematic diagram of the steps of the method for analyzing power telecommunication business operation and maintenance data of the present invention; Figure 2 for Figure 1 Detailed step flow diagram of step S1; Figure 3 for Figure 2 Detailed step flow chart of step S13 in FIG. DETAILED DESCRIPTION

[0017] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0018] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0019] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0020] To achieve this, please refer to Figures 1 to 3 The present invention provides a method for analyzing power information and communication business operation and maintenance data, the method comprising the following steps: Step S1: low-power real-time collection of operation and maintenance data of the power communication business process between the power equipment and the communication infrastructure to obtain real-time monitoring data of power communication business operation and maintenance; analysis of communication business operation and maintenance cases on the real-time monitoring data of power communication business operation and maintenance to obtain real-time operation and maintenance cases of power communication business; Step S2: Perform local fuzzy feature analysis on the real-time operation and maintenance cases of electric power information and communication services to obtain local fuzzy features of the real-time operation and maintenance cases of electric power information and communication services; obtain historical operation and maintenance cases of electric power information and communication services, and perform local similarity reasoning analysis on the historical operation and maintenance cases of electric power information and communication services based on the local fuzzy features of the real-time operation and maintenance cases of electric power information and communication services to obtain historical similar operation and maintenance cases corresponding to the real-time operation and maintenance cases of electric power information and communication services; Step S3: Performing operation and maintenance decision mining and analysis on historical similar operation and maintenance cases corresponding to the real-time operation and maintenance cases of electric power information and communication services, and obtaining a support plan for historical similar operation and maintenance decisions of electric power information and communication services; Step S4: Perform business operation and maintenance feedback optimization processing on the corresponding real-time operation and maintenance cases of electric power communication services according to the historical similar operation and maintenance decision support scheme of electric power communication services to obtain the operation and maintenance feedback optimization management results of electric power communication services.

[0021] In the embodiment of the present invention, please refer to Figure 1FIG. 1 is a schematic diagram of the steps of the method for analyzing the operation and maintenance data of the electric power information and communication business of the present invention. In this example, the method for analyzing the operation and maintenance data of the electric power information and communication business includes the following steps: Step S1: low-power real-time collection of operation and maintenance data of the power communication business process between the power equipment and the communication infrastructure to obtain real-time monitoring data of power communication business operation and maintenance; analysis of communication business operation and maintenance cases on the real-time monitoring data of power communication business operation and maintenance to obtain real-time operation and maintenance cases of power communication business; In the embodiment of the present invention, various operation and maintenance sensors are deployed at key nodes between power equipment and information and communication infrastructure to realize the construction of a monitoring network. Specifically, current sensors, temperature sensors and vibration sensors are selected to monitor the current, temperature and vibration status of power equipment. The current sensor uses a Hall effect sensor, which can capture current fluctuations in real time with its high sensitivity and accuracy. The temperature sensor uses a thermocouple or thermistor, which can accurately measure the temperature change of the equipment under various environmental conditions. The vibration sensor uses an accelerometer to monitor the vibration of equipment such as motors and transformers. All sensors are connected through low-power wide area network (LPWAN) technology. Connection ensures low latency and low power consumption of data transmission, thereby realizing sensor data aggregation and transmission, and through the use of the corresponding sensors in the operation and maintenance monitoring network generated by the connection, the operation and maintenance data of the power communication business process between the power equipment and the communication infrastructure is collected in real time. The collected data of each sensor is uploaded to the central data processing platform in real time using the preset collection frequency. The current sensor records the current value every second, and the collection frequency of the temperature sensor and vibration sensor is set to once every five seconds to ensure that sufficient monitoring data is obtained during the operation of the equipment, and the real-time operation and maintenance data is stored in the cloud database, thereby obtaining real-time monitoring data of the operation and maintenance of the power communication business. By conducting quantitative analysis of operation and maintenance indicators based on the acquired real-time monitoring data of power information and communication business operation and maintenance, and by setting key performance indicators (KPIs), including parameters such as current, temperature, vibration amplitude, etc. of equipment operation, an analysis model is established, and data analysis tools such as Pandas and NumPy libraries in Python are used to clean, process and statistically analyze real-time monitoring data. Data mining techniques such as cluster analysis and regression analysis are used to extract characteristic variables related to operation and maintenance indicators. For example, the K-means clustering algorithm is used to classify the equipment operation status, determine the current, temperature, and vibration characteristics under different operation status, and analyze the equipment operation status based on the K-means clustering algorithm. As a result, a detailed operation and maintenance description feature report is generated, which includes the distribution, correlation and outlier analysis of each characteristic variable. Then, the operation and maintenance description features of the power communication business process obtained by the previous statistical analysis are combined to identify and analyze the communication business operation and maintenance cases. The corresponding power communication business process operation and maintenance description features are classified and summarized by applying case analysis methods, such as the "problem-root cause-solution" framework, so as to analyze its historical monitoring data and operation and maintenance characteristics, and identify the corresponding real-time operation and maintenance cases, including cases where a certain equipment fails due to overtemperature and cases where the equipment fails due to current failure, etc. Finally, the corresponding real-time operation and maintenance cases of the power communication business are obtained.

[0022] Step S2: Perform local fuzzy feature analysis on the real-time operation and maintenance cases of electric power information and communication services to obtain local fuzzy features of the real-time operation and maintenance cases of electric power information and communication services; obtain historical operation and maintenance cases of electric power information and communication services, and perform local similarity reasoning analysis on the historical operation and maintenance cases of electric power information and communication services based on the local fuzzy features of the real-time operation and maintenance cases of electric power information and communication services to obtain historical similar operation and maintenance cases corresponding to the real-time operation and maintenance cases of electric power information and communication services; In an embodiment of the present invention, the operation and maintenance attributes of the real-time operation and maintenance cases of the electric power communication business obtained by the previous analysis are mined and divided, so as to extract key attributes from the original operation and maintenance data through data mining technology, including equipment status, fault type, processing time, operation and maintenance personnel, etc., and the Pandas library in the Python programming language is used to classify the data to form an operation and maintenance attribute data table, in which each operation and maintenance case will be marked with corresponding attributes. After completing the operation and maintenance attribute division, the K-means clustering algorithm is used to perform local feature clustering analysis on the corresponding real-time operation and maintenance cases of the electric power communication business, so as to determine the number of clusters K, evaluate the clustering effects under different K values ​​through the Elbow rule, so as to select the appropriate number of clusters, and standardize the attribute data of the operation and maintenance cases to ensure that the influence of each feature on the clustering results is relatively balanced. Clustering is performed through the KMeans model in the Scikit-learn library, and operation and maintenance cases with similar features are classified into the same group, and the local feature clustering results of real-time operation and maintenance cases are obtained. At the same time, the local fuzzy feature analysis of the corresponding real-time operation and maintenance cases of electric power communication business is performed by combining the local feature clustering results of real-time operation and maintenance cases obtained by previous clustering analysis. This step adopts the fuzzy logic system. First, the fuzzy set is defined. For example, the processing time is divided into three fuzzy categories: short, medium, and long. The fuzzy membership function is used to evaluate the membership of each operation and maintenance case in different fuzzy categories. Through the fuzzy reasoning system, combined with the clustering results, the fuzzy feature performance score of each operation and maintenance case is calculated to screen out high-performance local fuzzy sub-features through a preset threshold, thereby obtaining the local fuzzy features of the real-time operation and maintenance cases of electric power communication business. By collecting all the historical operation and maintenance cases of the electric power communication business, and also performing consistent local fuzzy feature analysis, the attribute data of the historical operation and maintenance cases are also preprocessed and divided. For each historical case, the local fuzzy features are calculated using the same fuzzy logic method as the real-time case, so as to obtain the local fuzzy features corresponding to each historical operation and maintenance case of the electric power communication business. Then, by combining the local fuzzy features of the real-time operation and maintenance cases of the electric power communication business previously screened, the local fuzzy features corresponding to each historical operation and maintenance case of the electric power communication business are analyzed for similarity inference, so as to calculate the similarity between the real-time operation and maintenance case and the historical case by using algorithms such as Euclidean distance or cosine similarity, and using the NearestNeighbors model in the Sci-kit Learn library, the historical case that is most similar to the real-time operation and maintenance case can be quickly found, so as to summarize all similarity results, to identify the historical similar operation and maintenance cases corresponding to the real-time operation and maintenance cases of the electric power communication business, and finally obtain the historical similar operation and maintenance cases corresponding to the real-time operation and maintenance cases of the electric power communication business.

[0023] Step S3: Performing operation and maintenance decision mining and analysis on historical similar operation and maintenance cases corresponding to the real-time operation and maintenance cases of electric power information and communication services, and obtaining a support plan for historical similar operation and maintenance decisions of electric power information and communication services; In an embodiment of the present invention, after obtaining historical similar operation and maintenance cases corresponding to real-time operation and maintenance cases of electric power communication services, operation and maintenance decision mining and analysis are performed to achieve in-depth statistical analysis and decision tree modeling of historical similar operation and maintenance cases, extract decision factors related to similar cases, and use data mining tools (such as WEKA, RapidMiner, etc.) to classify, regress and analyze association rules on these cases to mine effective patterns and laws of operation and maintenance decisions. In this process, a decision support system (DSS) is used to build an operation and maintenance decision support plan, which specifically includes fault handling strategies, maintenance recommendations, and resource allocation plans. These decision support plans should take into account specific needs in different scenarios and be presented through visualization tools to help operation and maintenance personnel intuitively understand and implement decisions, and finally obtain the corresponding historical similar operation and maintenance decision support plan for electric power communication services.

[0024] Step S4: Perform business operation and maintenance feedback optimization processing on the corresponding real-time operation and maintenance cases of electric power communication services according to the historical similar operation and maintenance decision support scheme of electric power communication services to obtain the operation and maintenance feedback optimization management results of electric power communication services.

[0025] In an embodiment of the present invention, the business operation and maintenance feedback of the corresponding real-time operation and maintenance cases of the electric power communication business is optimized by using the historical similar operation and maintenance decision support scheme of the electric power communication business obtained by the previous mining and analysis, so as to monitor the execution effect of the real-time operation and maintenance case and compare it with the preset target through the implementation of the feedback optimization mechanism, and use performance evaluation indicators (such as fault response time, equipment normal operation time, etc.) to evaluate the optimization effect. In the optimization process, an adaptive control strategy can be applied to dynamically adjust the operation and maintenance measures. Through the feedback loop, the optimization results are continuously integrated into the operation and maintenance process to improve the overall operation and maintenance efficiency, thereby forming an operation and maintenance feedback optimization management result, providing a basis for subsequent electric power communication business operation and maintenance activities, ensuring the efficient and stable operation of the electric power communication business, and finally obtaining the electric power communication business operation and maintenance feedback optimization management result.

[0026] Further, step S1 includes the following steps: Step S11: Deploy various operation and maintenance sensors between the power equipment and the information and communication infrastructure, wherein the operation and maintenance sensors include current sensors, temperature sensors, and vibration sensors, and use low-power wide area network technology to construct an operation and maintenance monitoring network for the various operation and maintenance sensors deployed between the power equipment and the information and communication infrastructure, so as to generate an operation and maintenance monitoring network for power information and communication services; Step S12: using the power information and communication service operation and maintenance monitoring network to collect operation and maintenance data of the power information and communication service process between the power equipment and the information and communication infrastructure in real time with low power consumption, so as to obtain real-time monitoring data of power information and communication service operation and maintenance; Step S13: performing quantitative analysis of operation and maintenance indicators on the real-time monitoring data of the power information and communication service operation and maintenance to obtain a parameter set of power information and communication service operation and maintenance performance indicators; Step S14: Based on the power information and communication service operation and maintenance performance indicator parameter set, statistical analysis is performed on the power information and communication service process corresponding to the power equipment and the information and communication infrastructure to obtain the power information and communication service process operation and maintenance description characteristics; Step S15: Perform communication and information service operation and maintenance case analysis based on the power communication and information service process operation and maintenance description characteristics to obtain real-time operation and maintenance cases for the power communication and information service.

[0027] As an embodiment of the present invention, refer to Figure 2 As shown, Figure 1 Detailed step flow diagram of step S1 in FIG. 1 , in this embodiment, step S1 includes the following steps: Step S11: Deploy various operation and maintenance sensors between the power equipment and the information and communication infrastructure, wherein the operation and maintenance sensors include current sensors, temperature sensors, and vibration sensors, and use low-power wide area network technology to construct an operation and maintenance monitoring network for the various operation and maintenance sensors deployed between the power equipment and the information and communication infrastructure, so as to generate an operation and maintenance monitoring network for power information and communication services; In an embodiment of the present invention, various operation and maintenance sensors are deployed at key nodes between power equipment and information and communication infrastructure to realize the construction of a monitoring network. Specifically, current sensors, temperature sensors and vibration sensors are selected to monitor the current, temperature and vibration status of power equipment. The current sensor uses a Hall effect sensor, which has high sensitivity and accuracy and can capture current fluctuations in real time. The temperature sensor uses a thermocouple or thermistor, which can accurately measure the temperature change of the equipment under various environmental conditions. The vibration sensor uses an accelerometer to monitor the vibration of equipment such as motors and transformers. All sensors are connected through low-power wide area network (LPWAN) technology to ensure low latency and low power consumption of data transmission, thereby realizing sensor data aggregation and transmission, and finally connecting to build a power information and communication business operation and maintenance monitoring network.

[0028] Step S12: using the power information and communication service operation and maintenance monitoring network to collect operation and maintenance data of the power information and communication service process between the power equipment and the information and communication infrastructure in real time with low power consumption, so as to obtain real-time monitoring data of power information and communication service operation and maintenance; In an embodiment of the present invention, by using corresponding sensors in the electric power communication business operation and maintenance monitoring network, real-time collection of operation and maintenance data of the electric power communication business process between the electric power equipment and the communication infrastructure is carried out, and the collected data of each sensor is uploaded to the central data processing platform in real time using a preset collection frequency. The current sensor records the current value every second, and the collection frequency of the temperature sensor and the vibration sensor is set to once every five seconds to ensure that sufficient monitoring data is obtained during the operation of the equipment. The data collected by the sensor is transmitted to the cloud server through low-power wide area network technology, and data encryption is implemented to ensure the security and integrity of data transmission, so that the real-time operation and maintenance data is stored in the cloud database, and finally the real-time monitoring data of the operation and maintenance of the electric power communication business is obtained.

[0029] Step S13: performing quantitative analysis of operation and maintenance indicators on the real-time monitoring data of the power information and communication service operation and maintenance to obtain a parameter set of power information and communication service operation and maintenance performance indicators; In an embodiment of the present invention, a quantitative analysis of operation and maintenance indicators is performed based on the acquired real-time monitoring data of operation and maintenance of electric power information and communication services, so as to establish an analysis model by setting key performance indicators (KPIs), including parameters such as current, temperature, vibration amplitude and other parameters of equipment operation, and use data analysis tools, such as Pandas and NumPy libraries in Python, to clean, process and statistically analyze the real-time monitoring data, calculate the average value, variance and peak value of each indicator through an algorithm, and finally obtain a parameter set of operation and maintenance performance indicators of electric power information and communication services.

[0030] Step S14: Based on the power information and communication service operation and maintenance performance indicator parameter set, statistical analysis is performed on the power information and communication service process corresponding to the power equipment and the information and communication infrastructure to obtain the power information and communication service process operation and maintenance description characteristics; In an embodiment of the present invention, a statistical analysis of the business operation and maintenance characteristics of the power communication business process corresponding to the power equipment and the communication infrastructure is performed by combining the power communication business operation and maintenance performance indicator parameter set obtained by previous quantitative calculation, so as to extract characteristic variables related to the operation and maintenance indicators by using data mining techniques such as cluster analysis and regression analysis. For example, the K-means clustering algorithm is used to classify the equipment operating status, determine the current, temperature, and vibration characteristics under different operating conditions, and generate a detailed operation and maintenance description feature report based on the analysis results. The report includes the distribution, correlation and outlier analysis of each characteristic variable, and finally obtains the operation and maintenance description characteristics of the power communication business process.

[0031] Step S15: Perform communication and information service operation and maintenance case analysis based on the power communication and information service process operation and maintenance description characteristics to obtain real-time operation and maintenance cases for the power communication and information service.

[0032] In an embodiment of the present invention, identification and analysis of communication business operation and maintenance cases are performed by combining the power communication business process operation and maintenance description characteristics obtained by previous statistical analysis, and the corresponding power communication business process operation and maintenance description characteristics are classified and summarized by applying case analysis methods, such as the "problem-root cause-solution" framework, so as to analyze its historical monitoring data and operation and maintenance characteristics, and identify corresponding real-time operation and maintenance cases, including cases in which a certain equipment fails due to excessive temperature, cases in which a failure is caused by current failure, etc., and finally the corresponding real-time operation and maintenance cases of power communication business are obtained.

[0033] Further, step S13 includes the following steps: Step S131: converting the real-time monitoring data of the power information and communication business operation and maintenance into a time series data stream to obtain a time series data stream of the power information and communication business operation and maintenance monitoring; Step S132: Performing power information and communication operation and maintenance state variable analysis on the power information and communication business operation and maintenance monitoring time series data stream to obtain power information and communication business operation and maintenance state variables, wherein the power information and communication business operation and maintenance state variables include power information and communication operation and maintenance current fluctuation rate, power information and communication operation and maintenance fault duration, and power information and communication operation response time; Step S133: performing quantitative analysis on the availability of power communication and information service operation and maintenance for the corresponding power communication and information service process according to the power communication and information service operation and maintenance current fluctuation rate, and obtaining the power communication and information service operation and maintenance equipment availability index parameter; Step S134: quantitatively analyzing the efficiency of power communication and information service operation and maintenance and the failure rate of power communication and information service operation and maintenance on the corresponding power communication and information service process according to the duration of the power communication and information service operation and maintenance failure and the power communication and information service operation and maintenance response time, so as to obtain the power communication and information service operation and maintenance efficiency index parameter and the power communication and information service operation and maintenance failure rate index parameter; Step S135: Merge the performance indicator parameters of the electric power information and communication business operation and maintenance equipment availability indicator parameters, the electric power information and communication business operation and maintenance maintenance efficiency indicator parameters, and the electric power information and communication business operation and maintenance failure occurrence rate indicator parameters to obtain the electric power information and communication business operation and maintenance performance indicator parameter set.

[0034] As an embodiment of the present invention, refer to Figure 3 As shown, Figure 2 FIG. 1 is a schematic diagram of a detailed step flow chart of step S13 in FIG. 1 . In this embodiment, step S13 includes the following steps: Step S131: converting the real-time monitoring data of the power information and communication business operation and maintenance into a time series data stream to obtain a time series data stream of the power information and communication business operation and maintenance monitoring; In an embodiment of the present invention, corresponding real-time monitoring data of electric power communication business operation and maintenance are collected from multiple monitoring devices and sensors. These data include parameters such as current, temperature, and vibration. The collected raw data are preprocessed by using data processing tools (such as Apache Kafka or Apache Flink) to ensure the integrity and accuracy of the data. After preprocessing, a time series database (such as InfluxDB or TimescaleDB) is used for data storage. By writing an ETL (Extract, Transform, Load) process, the real-time monitoring data is sorted by timestamp and converted into a standardized time series format, and finally a time series data stream for electric power communication business operation and maintenance monitoring is obtained.

[0035] Step S132: Performing power information and communication operation and maintenance state variable analysis on the power information and communication business operation and maintenance monitoring time series data stream to obtain power information and communication business operation and maintenance state variables, wherein the power information and communication business operation and maintenance state variables include power information and communication operation and maintenance current fluctuation rate, power information and communication operation and maintenance fault duration, and power information and communication operation response time; In an embodiment of the present invention, by performing statistical analysis of power communication operation and maintenance state variables on the power communication business operation and maintenance monitoring time series data stream obtained after the previous conversion, the time series data stream is deeply analyzed by using statistical analysis software (such as Pandas in Python or R language), and by calculating the current fluctuation rate (such as by the standard deviation calculation method), the specific value of the power communication operation and maintenance current fluctuation rate can be obtained. When analyzing the fault duration, it is necessary to detect the fault event by setting a threshold and calculate the time period from the occurrence of the fault to the restoration of normal. For the power communication operation response time, it is necessary to analyze the time from the fault report to the response. All these variables need to be recorded in the database, and finally the power communication business operation and maintenance state variables are obtained, wherein the power communication business operation and maintenance state variables include the power communication operation and maintenance current fluctuation rate, the power communication operation and maintenance fault duration and the power communication operation response time.

[0036] Step S133: performing quantitative analysis on the availability of power communication and information service operation and maintenance for the corresponding power communication and information service process according to the power communication and information service operation and maintenance current fluctuation rate, and obtaining the power communication and information service operation and maintenance equipment availability index parameter; In an embodiment of the present invention, the availability of communication and maintenance of the corresponding power communication and operation process is evaluated by combining the power communication and operation current fluctuation rate obtained by previous statistical calculations and combining the design standards and operating parameters of the power communication and operation equipment, so as to process the data by using statistical analysis tools (such as Excel or MATLAB) to calculate the availability index of the power communication and operation process, and finally obtain the availability index parameters of the power communication and operation equipment.

[0037] Step S134: quantitatively analyzing the efficiency of power communication and information service operation and maintenance and the failure rate of power communication and information service operation and maintenance on the corresponding power communication and information service process according to the duration of the power communication and information service operation and maintenance failure and the power communication and information service operation and maintenance response time, so as to obtain the power communication and information service operation and maintenance efficiency index parameter and the power communication and information service operation and maintenance failure rate index parameter; In an embodiment of the present invention, by combining the power communication operation and maintenance fault duration and the power communication operation response time obtained by previous statistical analysis, the operation and maintenance efficiency and fault occurrence rate of the corresponding power communication business process are quantitatively analyzed. First, the fault occurrence rate can be calculated by the ratio of the total number of faults to the power communication operation and maintenance fault duration, and the maintenance efficiency can be analyzed by the ratio of the fault repair time to the power communication operation response time. By using data analysis tools (such as Python's SciPy or R language's dplyr package), these data can be processed to obtain the power communication business operation and maintenance efficiency index parameters and fault occurrence rate index parameters, and finally the power communication business operation and maintenance efficiency index parameters and the power communication business operation and maintenance fault occurrence rate index parameters are obtained.

[0038] Step S135: Merge the performance indicator parameters of the electric power information and communication business operation and maintenance equipment availability indicator parameters, the electric power information and communication business operation and maintenance maintenance efficiency indicator parameters, and the electric power information and communication business operation and maintenance failure occurrence rate indicator parameters to obtain the electric power information and communication business operation and maintenance performance indicator parameter set.

[0039] In an embodiment of the present invention, the performance indicators of the power communication business operation and maintenance equipment availability index parameters, the power communication business operation and maintenance maintenance efficiency index parameters and the power communication business operation and maintenance failure rate index parameters obtained by previous quantitative calculation are merged to integrate the previously obtained availability index parameters, maintenance efficiency index parameters and failure rate index parameters, thereby generating a comprehensive performance index parameter set, and finally obtaining the power communication business operation and maintenance performance index parameter set.

[0040] Further, step S2 includes the following steps: Step S21: dividing the real-time operation and maintenance cases of electric power information and communication services into operation and maintenance attribute classes to obtain the real-time operation and maintenance case attribute data of electric power information and communication services; In an embodiment of the present invention, the operation and maintenance attributes of the real-time operation and maintenance cases of the electric power communication business obtained by previous analysis are mined and divided, so as to extract key attributes from the original operation and maintenance data through data mining technology, including equipment status, fault type, processing time, operation and maintenance personnel, etc., and classify the data using the Pandas library in the Python programming language to form an operation and maintenance attribute data table, in which each operation and maintenance case will be marked with corresponding attributes, and finally the attribute data of the real-time operation and maintenance case of the electric power communication business is obtained.

[0041] Step S22: performing operation and maintenance local feature clustering analysis on the corresponding real-time operation and maintenance cases of electric power information and communication services based on the attribute data of the real-time operation and maintenance cases of electric power information and communication services, and obtaining the local feature clustering results of the real-time operation and maintenance cases; In an embodiment of the present invention, after completing the division of operation and maintenance attributes, the K-means clustering algorithm is used to perform local feature clustering analysis on the corresponding real-time operation and maintenance cases of the electric power information and communication services, so as to determine the number of clusters K, evaluate the clustering effects under different K values ​​through the Elbow rule, select the appropriate number of clusters, and standardize the attribute data of the operation and maintenance cases to ensure that the influence of each feature on the clustering results is relatively balanced. Clustering is performed through the KMeans model in the Scikit-learn library, and operation and maintenance cases with similar features are classified into the same group, so as to obtain the local feature clustering results of the real-time operation and maintenance cases, and finally obtain the local feature clustering results of the real-time operation and maintenance cases.

[0042] Step S23: Based on the local feature clustering results of the real-time operation and maintenance cases, the local fuzzy feature analysis of the corresponding real-time operation and maintenance cases of the electric power information and communication services is performed to obtain the local fuzzy features of the real-time operation and maintenance cases of the electric power information and communication services; In an embodiment of the present invention, local fuzzy feature analysis is performed on the corresponding real-time operation and maintenance cases of electric power communication services by combining the local feature clustering results of the real-time operation and maintenance cases obtained by previous clustering analysis. This step adopts a fuzzy logic system. First, a fuzzy set is defined. For example, the processing time is divided into three fuzzy categories: short, medium, and long. The fuzzy membership function is used to evaluate the membership of each operation and maintenance case in different fuzzy categories. The fuzzy reasoning system is combined with the clustering results to calculate the fuzzy feature performance score for each operation and maintenance case, so as to screen out high-performance local fuzzy sub-features through a preset threshold, and finally obtain the local fuzzy features of the real-time operation and maintenance cases of electric power communication services.

[0043] Step S24: obtaining historical operation and maintenance cases of electric power information and communication services, and performing consistent local fuzzy feature analysis on the historical operation and maintenance cases of electric power information and communication services to obtain local fuzzy features corresponding to each historical operation and maintenance case of electric power information and communication services; In an embodiment of the present invention, all historical operation and maintenance cases of electric power communication services are collected, and consistent local fuzzy feature analysis is also performed, so that the attribute data of the historical operation and maintenance cases are also preprocessed and divided. For each historical case, the same fuzzy logic method as the real-time case is used to calculate its local fuzzy features, and the calculation and analysis of fuzzy features are implemented through Python's NumPy and SciPy libraries to ensure the consistency of the feature analysis methods of all historical cases, form a feature data set comparable to the real-time operation and maintenance cases, and finally obtain the local fuzzy features corresponding to each historical operation and maintenance case of electric power communication services.

[0044] Step S25: Based on the local fuzzy features of the real-time operation and maintenance cases of the electric power information and communication services, the local fuzzy features corresponding to the historical operation and maintenance cases of the electric power information and communication services are subjected to real-time case local similarity reasoning analysis to obtain historical similar operation and maintenance cases corresponding to the real-time operation and maintenance cases of the electric power information and communication services.

[0045] In an embodiment of the present invention, by combining the local fuzzy features of the real-time operation and maintenance cases of the electric power communication business previously screened out, the local fuzzy features corresponding to the historical operation and maintenance cases of each electric power communication business are subjected to similarity reasoning analysis, so as to calculate the similarity between the real-time operation and maintenance cases and the historical cases by adopting algorithms such as Euclidean distance or cosine similarity, and by using the NearestNeighbors model in the Sci-kit Learn library, the historical cases most similar to the real-time operation and maintenance cases can be quickly found, so as to aggregate all similarity results to identify the historically similar operation and maintenance cases corresponding to the real-time operation and maintenance cases of the electric power communication business, and finally obtain the historically similar operation and maintenance cases corresponding to the real-time operation and maintenance cases of the electric power communication business.

[0046] Further, step S23 includes the following steps: Step S231: performing fuzzy feature space membership mapping conversion on each operation and maintenance case local feature clustering cluster in the local feature clustering result of the real-time operation and maintenance case to obtain the local fuzzy feature mapping space of each real-time operation and maintenance case; In an embodiment of the present invention, a fuzzy feature space membership mapping conversion is performed on each operation and maintenance case local feature clustering cluster in the local feature clustering result of the real-time operation and maintenance case obtained after clustering, so as to construct a fuzzy membership function by mapping different local features to a common fuzzy feature space, so as to describe the position of each local feature in the fuzzy feature space, wherein the membership of each local feature is defined by using triangular fuzzy numbers and Gaussian fuzzy numbers to ensure that the performance of these features in the fuzzy space conforms to the actual fuzziness, and the fuzzy logic algorithm is used to map the local features in each clustering cluster to the fuzzy feature space, and the fuzzy membership of each feature is input into the fuzzy feature space in the form of a membership matrix to reflect the fuzzy performance of the local features of different operation and maintenance cases, and finally the local fuzzy feature mapping space of each real-time operation and maintenance case is obtained.

[0047] Step S232: performing fuzzy feature association analysis on each local fuzzy sub-feature of each operation and maintenance case in the local fuzzy feature mapping space of each real-time operation and maintenance case, so as to obtain a potential association relationship between different local fuzzy sub-features in each local fuzzy feature mapping space; In an embodiment of the present invention, fuzzy feature association mining analysis is performed on each local fuzzy sub-feature of an operation and maintenance case corresponding to the local fuzzy feature mapping space of each real-time operation and maintenance case obtained by previous conversion to identify potential feature relationships therein, and statistical methods such as correlation analysis and cluster analysis are used to analyze the sub-features in the fuzzy feature mapping space to identify the mutual relationships between the sub-features, and indicators such as the Pearson correlation coefficient, the Spearman rank correlation coefficient or the Kendall rank correlation coefficient are used to calculate the degree of correlation between each pair of local fuzzy sub-features, and visualization tools such as heat maps or network diagrams are used to display the potential correlation relationships between different local fuzzy sub-features, and finally the potential correlation relationships between different local fuzzy sub-features in each local fuzzy feature mapping space are obtained.

[0048] Step S233: constructing a feature matrix connection for each operation and maintenance case local fuzzy sub-feature in the local fuzzy feature mapping space corresponding to the real-time operation and maintenance case based on the potential correlation between different local fuzzy sub-features in each local fuzzy feature mapping space, so as to generate a local fuzzy feature mapping matrix for the real-time operation and maintenance case; In an embodiment of the present invention, a feature matrix is ​​connected and constructed for each local fuzzy sub-feature corresponding to an operation and maintenance case in the local fuzzy feature mapping space of a real-time operation and maintenance case by combining the potential correlation between different local fuzzy sub-features in each local fuzzy feature mapping space obtained by previous mining and analysis, so as to define the format of the feature matrix, including rows representing different operation and maintenance cases, columns representing various local fuzzy sub-features, and based on the results of fuzzy correlation analysis, identify local fuzzy sub-features with strong correlation for connection, and fill in the corresponding membership values ​​in the feature matrix to form a matrix that comprehensively reflects the performance of each local fuzzy sub-feature in the operation and maintenance case, thereby ensuring that the connection relationship between the fuzzy features is effectively captured, forming an overall feature mapping matrix that is helpful for subsequent evaluation and analysis, and finally connecting to generate a local fuzzy feature mapping matrix for real-time operation and maintenance cases.

[0049] Step S234: Based on each local fuzzy sub-feature of the operation and maintenance case in the local fuzzy feature mapping matrix of the real-time operation and maintenance case, a fuzzy sub-feature evaluation calculation is performed on the corresponding real-time operation and maintenance case of the electric power information and communication business using the local fuzzy feature performance calculation formula to obtain the local fuzzy feature performance score of the operation and maintenance case corresponding to each local fuzzy sub-feature in the local fuzzy feature mapping matrix; In an embodiment of the present invention, a suitable case local fuzzy feature performance calculation formula is formed by combining the input variables of the local fuzzy sub-features, the integral lower limit and integral upper limit of the local fuzzy sub-feature input variables, the occurrence probability of the local fuzzy sub-feature input variables, the response time, the case problem solving success rate, the relevant weight coefficient, the local fuzzy sub-feature attenuation factor, the operation and maintenance case fuzzy mean and related parameters to perform fuzzy sub-feature evaluation calculation on the corresponding real-time operation and maintenance cases of the electric power communication business, so as to quantitatively calculate the local fuzzy feature performance score of each operation and maintenance case, and finally obtain the local fuzzy feature performance score of the operation and maintenance case corresponding to each local fuzzy sub-feature in the local fuzzy feature mapping matrix.

[0050] Step S235: Perform local fuzzy feature screening and output according to the local fuzzy feature performance score of the operation and maintenance case corresponding to each local fuzzy sub-feature in the local fuzzy feature mapping matrix to obtain the local fuzzy features of the real-time operation and maintenance case of the electric power information and communication business.

[0051] In an embodiment of the present invention, local fuzzy features are screened and output by combining the local fuzzy feature performance scores of operation and maintenance cases corresponding to each local fuzzy sub-feature in the local fuzzy feature mapping matrix obtained by previous quantitative calculation, so as to set a scoring threshold to distinguish between high-performance and low-performance features, and use a sorting algorithm to sort the fuzzy feature performance scores to identify local fuzzy sub-features with excellent performance. At the same time, standardized processing is used to ensure the consistency and comparability of the scoring results, and to ensure that the screened features can remain representative in different operation and maintenance cases, and finally the local fuzzy features of real-time operation and maintenance cases of electric power information and communication services are screened.

[0052] Further, step S231 includes the following steps: Perform outlier feature elimination processing on each local feature clustering cluster of operation and maintenance cases in the local feature clustering result of real-time operation and maintenance cases to obtain local outlier optimized feature clustering clusters of each real-time operation and maintenance case; In the embodiment of the present invention, the local feature mean and variance of each operation and maintenance case local feature clustering cluster in the local feature clustering result of the real-time operation and maintenance case obtained by cluster analysis are statistically calculated. In the specific implementation process, the arithmetic mean and standard deviation of the feature values ​​in each clustering cluster are calculated by using a programming tool (such as Python's NumPy library), so as to obtain the local feature mean and variance, wherein the calculation formula of the mean is mean= , the calculation formula of variance is variance = , and statistically calculate the outlier feature discrimination threshold by combining the local feature mean and local feature variance obtained by previous quantitative calculation to set the discrimination standard of outlier features, and according to the normal distribution characteristics, set the outlier feature discrimination threshold as the mean plus or minus a certain multiple of the standard deviation to calculate the outlier feature threshold: upper threshold = mean + h*standard deviation, lower threshold = mean - h*standard deviation, where h is a constant for controlling the degree of outliers, usually taking a value of 2 or 3. At the same time, the local sub-features of the operation and maintenance cases in the local feature clustering clusters of each operation and maintenance case are identified by combining the local outlier feature discrimination threshold obtained by previous quantitative calculation. When implementing, each sub-feature value is compared with the corresponding The threshold of the clustering cluster is compared. If the sub-feature value is greater than or equal to the upper threshold, it is marked as an outlier feature; if the sub-feature value is less than the lower threshold, it is marked as a non-outlier feature, and the local sub-features of the operation and maintenance cases marked as outliers are eliminated and optimized. In the specific implementation, the sub-features marked as outliers are deleted from the original data set, and the clustering cluster data is updated to clean the data by using programming tools (such as Python's Pandas library), use screening operations to remove outliers, and recalculate the mean and variance of the optimized clustering cluster to ensure the accuracy and effectiveness of the data, and finally obtain the local outlier optimization feature clustering clusters of each real-time operation and maintenance case.

[0053] Preferably, a local fuzzy feature matching calculation is performed on each local sub-feature of an operation and maintenance case in each local outlier optimization feature clustering cluster of a real-time operation and maintenance case to obtain each local fuzzy sub-feature of an operation and maintenance case corresponding to each local feature clustering cluster of a real-time operation and maintenance case; In an embodiment of the present invention, a fuzzy logic control algorithm is adopted in combination with a similarity calculation method to compare each local sub-feature of an operation and maintenance case within each local outlier optimization feature clustering cluster of a real-time operation and maintenance case, so as to map each local sub-feature of an operation and maintenance case into a fuzzy space, and apply a fuzzy matching algorithm, such as fuzzy C-means clustering (FCM) or a fuzzy similarity matrix, to calculate the fuzzy similarity between each local sub-feature, and identify and generate the corresponding local fuzzy sub-features in each local clustering cluster through comprehensive analysis of the similarity matrix. This process not only ensures the correlation between features, but also enhances the accuracy of matching, and finally obtains each local fuzzy sub-feature of an operation and maintenance case within each local feature clustering cluster of a real-time operation and maintenance case.

[0054] Preferably, triangular and Gaussian fuzzy number statistical analysis is performed on each local fuzzy sub-feature of each operation and maintenance case corresponding to each local feature clustering cluster of each real-time operation and maintenance case, so as to obtain triangular fuzzy numbers and Gaussian fuzzy numbers corresponding to each local fuzzy sub-feature of each operation and maintenance case in each local feature clustering cluster; In an embodiment of the present invention, triangular and Gaussian fuzzy number statistical analysis is performed on each local fuzzy sub-feature of an operation and maintenance case corresponding to each local feature clustering cluster of each real-time operation and maintenance case obtained by fuzzy calculation previously. First, the parameters of the triangular fuzzy number and the Gaussian fuzzy number are defined. For the triangular fuzzy number, its form is three parameters (minimum value, most likely value, i.e., middle value, maximum value), which can be defined using the minimum value, mean value, and maximum value of the local sub-feature, while the Gaussian fuzzy number requires a mean value and a standard deviation. During the calculation, the statistical function of the SciPy library is used to generate corresponding triangular fuzzy numbers and Gaussian fuzzy numbers according to the distribution of the features. For each local fuzzy sub-feature, the generation of triangular fuzzy numbers and Gaussian fuzzy numbers is completed and recorded in the corresponding data structure. Finally, the triangular fuzzy number and the Gaussian fuzzy number corresponding to the local fuzzy sub-feature of each operation and maintenance case in each local feature clustering cluster are obtained.

[0055] Preferably, based on the triangular fuzzy number and Gaussian fuzzy number corresponding to each local fuzzy sub-feature of each operation and maintenance case in each local feature clustering cluster, the feature fuzzy membership quantization calculation is performed on each corresponding local fuzzy sub-feature of the operation and maintenance case, so as to obtain the feature fuzzy membership corresponding to each local fuzzy sub-feature of the operation and maintenance case in each local feature clustering cluster; In the embodiment of the present invention, the triangular fuzzy number and Gaussian fuzzy number corresponding to each local fuzzy sub-feature of each operation and maintenance case in each local feature cluster obtained by previous quantitative calculation are used to use a fuzzy membership function (such as a linear or nonlinear function), for example, membership = To calculate the membership of each fuzzy sub-feature under the corresponding fuzzy number, finally obtain the feature fuzzy membership corresponding to each local fuzzy sub-feature of each operation and maintenance case in each local feature cluster.

[0056] Preferably, based on the feature fuzzy membership corresponding to each local fuzzy sub-feature of each operation and maintenance case in each local feature clustering cluster, a fuzzy feature space membership mapping conversion is performed on each corresponding local fuzzy sub-feature of the operation and maintenance case to obtain the local fuzzy feature mapping space of each real-time operation and maintenance case.

[0057] In an embodiment of the present invention, by combining the feature fuzzy membership corresponding to each local fuzzy sub-feature of each operation and maintenance case in each local feature cluster obtained by previous quantitative calculation, the membership mapping conversion of the fuzzy feature space is performed on the corresponding local fuzzy sub-feature of each operation and maintenance case. In this process, a fuzzy logic reasoning mechanism is used to first establish a fuzzy feature space model to define the relationship between the membership of each feature and the position in the feature space, and by constructing fuzzy rules, such as "if the membership of feature A is high, the membership of feature B is also high", fuzzy reasoning is performed to map the membership of the local fuzzy sub-features to the new fuzzy feature space. At the same time, a fuzzy reasoning system (such as Mamdanis type or Sugeno type) is used to calculate the rules, and the mapping results are integrated through a fuzzy aggregation method (such as weighted average method) to form a fuzzy feature mapping space within each local cluster, and finally obtain the local fuzzy feature mapping space of each real-time operation and maintenance case.

[0058] Furthermore, the outlier feature elimination process for each operation and maintenance case local feature clustering cluster in the real-time operation and maintenance case local feature clustering result includes the following steps: Perform local feature mean and variance statistical calculations on each operation and maintenance case local feature clustering cluster in the real-time operation and maintenance case local feature clustering results to obtain the local feature mean and local feature variance corresponding to each operation and maintenance case local feature clustering cluster; In an embodiment of the present invention, by performing statistical calculations on the local feature mean and variance of each operation and maintenance case local feature clustering cluster in the local feature clustering result of the real-time operation and maintenance case previously obtained by cluster analysis, in a specific implementation process, the local feature clustering cluster of each operation and maintenance case is extracted from the data set, and the feature value of each clustering cluster is stored in a multidimensional array. At the same time, a programming tool (such as Python's NumPy library) is used to calculate the arithmetic mean and standard deviation of the feature value in each clustering cluster, thereby obtaining the local feature mean and variance, wherein the calculation formula of the mean is the mean = , the calculation formula of variance is = , and finally obtain the local feature mean and local feature variance corresponding to the local feature clustering clusters of each operation and maintenance case.

[0059] Preferably, the outlier feature discrimination threshold is calculated according to the local feature mean and the local feature variance corresponding to each operation and maintenance case local feature clustering cluster, so as to obtain the local outlier feature discrimination threshold corresponding to each operation and maintenance case local feature clustering cluster; In an embodiment of the present invention, a statistical calculation of an outlier feature discrimination threshold is performed by combining the local feature mean and the local feature variance corresponding to each operation and maintenance case local feature clustering cluster obtained by previous quantitative calculation to set the discrimination standard of the outlier feature, and according to the normal distribution characteristics, the outlier feature discrimination threshold is set to the mean plus or minus a certain multiple of the standard deviation. In a specific implementation, the mean and variance of each clustering cluster are input into the discriminant function, and for each clustering cluster, the outlier feature threshold is calculated: the upper threshold limit = mean + h*standard deviation, the lower threshold limit = mean - h*standard deviation, wherein h is a constant for controlling the degree of outliers, usually taking a value of 2 or 3, and finally the local outlier feature discrimination threshold corresponding to the local feature clustering cluster of each operation and maintenance case is obtained.

[0060] Preferably, the local sub-features of the operation and maintenance cases corresponding to each operation and maintenance case local feature clustering cluster are identified and judged according to the local outlier feature discrimination threshold corresponding to each operation and maintenance case local feature clustering cluster; if the corresponding local sub-feature of the operation and maintenance case is greater than or equal to the local outlier feature discrimination threshold, the corresponding local sub-feature of the operation and maintenance case in the operation and maintenance case local feature clustering cluster is marked as an outlier feature; if the corresponding local sub-feature of the operation and maintenance case is less than the local outlier feature discrimination threshold, the corresponding local sub-feature of the operation and maintenance case in the operation and maintenance case local feature clustering cluster is marked as a non-outlier feature; In an embodiment of the present invention, the local sub-features of the operation and maintenance cases in each local feature clustering cluster of the operation and maintenance cases are identified by combining the local outlier feature discrimination thresholds corresponding to the local feature clustering clusters of each operation and maintenance case obtained by previous quantitative calculation. During implementation, each sub-feature value is compared with the threshold of the corresponding clustering cluster. If the sub-feature value is greater than or equal to the upper threshold, it is marked as an outlier feature; if the sub-feature value is less than the lower threshold, it is marked as a non-outlier feature. The specific implementation process traverses the sub-feature values ​​of each clustering cluster and applies conditional judgment statements to mark them, thereby generating a list containing outlier features and non-outlier features to record the feature classification results within each clustering cluster.

[0061] Preferably, the local sub-features of the operation and maintenance cases marked as outlier features in the local feature clusters of each operation and maintenance case are eliminated and optimized to obtain local outlier optimized feature clusters of each real-time operation and maintenance case.

[0062] In an embodiment of the present invention, the local sub-features of the operation and maintenance cases marked as outlier features in the local feature clustering clusters of each operation and maintenance case are eliminated and optimized. In the specific implementation, the sub-features marked as outlier features are deleted from the original data set, and the clustering cluster data is updated. Data cleaning is performed by using programming tools (such as Python's Pandas library), and outlier features are removed by filtering operations to obtain more accurate local feature clustering clusters of operation and maintenance cases. After the elimination operation is completed, the mean and variance of the optimized clustering clusters are recalculated to ensure the accuracy and effectiveness of the data, and finally the local outlier optimized feature clustering clusters of each real-time operation and maintenance case are obtained.

[0063] Furthermore, the triangular and Gaussian fuzzy number statistical analysis of each local fuzzy sub-feature of each operation and maintenance case corresponding to the local feature cluster of each real-time operation and maintenance case includes the following steps: Performing feature initial value statistical analysis on each local fuzzy sub-feature of each operation and maintenance case corresponding to each local feature clustering cluster of each real-time operation and maintenance case, and obtaining each local fuzzy sub-feature initial value corresponding to each local feature clustering cluster of each real-time operation and maintenance case; In an embodiment of the present invention, a data analysis tool (such as Python's Pandas library) is used to perform statistical calculations on each local fuzzy sub-feature of an operation and maintenance case corresponding to each local feature clustering cluster of each real-time operation and maintenance case obtained after clustering, so as to use statistical methods to statistically analyze the specific values ​​of each local fuzzy sub-feature in each clustering cluster, and finally obtain the initial value of each local fuzzy sub-feature corresponding to each local feature clustering cluster of the real-time operation and maintenance case.

[0064] Preferably, based on the initial value of each local fuzzy sub-feature corresponding to each local feature cluster of each real-time operation and maintenance case, the fuzzy spatial distribution characteristics of the corresponding local fuzzy sub-feature of the operation and maintenance case are analyzed to obtain the fuzzy spatial distribution shape and fuzzy spatial distribution interval corresponding to each local fuzzy sub-feature in each local feature cluster; In an embodiment of the present invention, by combining the initial value of each local fuzzy sub-feature corresponding to each local feature cluster of each real-time operation and maintenance case obtained by previous quantitative calculation, the distribution characteristics of the local fuzzy sub-features corresponding to each cluster in the fuzzy space are statistically analyzed using fuzzy set theory to analyze and determine its fuzzy spatial distribution shape and distribution range. Specifically, with the help of a fuzzy distribution model (such as a fuzzy histogram or a fuzzy distribution function), the fuzziness and uncertainty of each local feature can be effectively identified. The fuzzy distribution shape can be graphically presented using data visualization tools (such as Matplotlib or Seaborn), which helps analysts intuitively understand the fuzzy spatial characteristics of the features, and finally obtains the fuzzy spatial distribution shape and fuzzy spatial distribution range corresponding to each local fuzzy sub-feature in each local feature cluster.

[0065] Preferably, based on the fuzzy spatial distribution shape and fuzzy spatial distribution interval corresponding to each local fuzzy sub-feature in each local feature cluster, triangular fuzzy number statistical analysis is performed on the corresponding local fuzzy sub-feature of the operation and maintenance case, so as to obtain the triangular fuzzy number corresponding to each local fuzzy sub-feature of the operation and maintenance case in each local feature cluster; In the embodiment of the present invention, by combining the fuzzy space distribution shape and fuzzy space distribution interval corresponding to each local fuzzy sub-feature in each local feature cluster obtained by previous analysis, the corresponding local fuzzy sub-feature of the operation and maintenance case is statistically analyzed in the fuzzy space, wherein each local fuzzy sub-feature is represented as a triangular fuzzy number, and its minimum value, maximum value and intermediate value are defined by fuzzy number theory. The distribution characteristics of each feature can be converted into a triangular fuzzy number by the formula, for example , is the minimum value, is the middle value, The specific implementation can be achieved by constructing a corresponding mathematical model and combining data processing tools (such as the NumPy library) to perform vectorized calculations to ensure that the fuzzy numbers in each local feature cluster are consistent and accurate, and finally the triangular fuzzy numbers corresponding to the local fuzzy sub-features of each operation and maintenance case in each local feature cluster are obtained.

[0066] Preferably, a Gaussian expansion transformation is performed on the triangular fuzzy number corresponding to the local fuzzy sub-feature of each operation and maintenance case in each local feature cluster to obtain a Gaussian fuzzy number corresponding to the local fuzzy sub-feature of each operation and maintenance case in each local feature cluster.

[0067] In the embodiment of the present invention, the Gaussian function is used to perform Gaussian expansion transformation calculation on the triangular fuzzy number corresponding to each local fuzzy sub-feature of each operation and maintenance case in each local feature cluster previously obtained by quantitative calculation by adopting the definition of Gaussian fuzzy number. In the specific implementation, the parameters of the triangular fuzzy number are first determined, and then the mathematical model of Gaussian distribution is used to perform numerical calculation to obtain the corresponding Gaussian fuzzy number. This process can be numerically solved and converted by writing a custom function and combining it with the Gaussian distribution function in the SciPy library, for example , is the mean, As the standard deviation, it is ensured that the fuzzy sub-features in each local feature cluster have high accuracy and consistency in the Gaussian fuzzy number generation process, and finally the Gaussian fuzzy number corresponding to the local fuzzy sub-features of each operation and maintenance case in each local feature cluster is obtained.

[0068] Furthermore, the calculation formula for the local fuzzy feature representation of the case described in step S234 is specifically: ; In the formula, is the local fuzzy sub-feature in the local fuzzy feature mapping matrix The local fuzzy feature performance score of the operation and maintenance case, is the input variable of the local fuzzy sub-feature, is the integral variable parameter of the local fuzzy sub-feature input variable, is the lower limit of the integration of the local fuzzy sub-characteristic input variable, is the upper limit of the integration of the local fuzzy sub-characteristic input variables, Input variables for local fuzzy sub-features in the local fuzzy feature map matrix The probability of occurrence, is the weight coefficient of the occurrence probability, Input variables for local fuzzy sub-features in the local fuzzy feature map matrix The response time, is the weight coefficient of response time, Input variables for local fuzzy sub-features in the local fuzzy feature map matrix The success rate of case problem solving, is the weight coefficient of the success rate of case problem solving, is the local fuzzy sub-feature attenuation factor, is the fuzzy mean of the operation and maintenance cases of the local fuzzy sub-feature input variables, It is the correction coefficient of the local fuzzy feature performance score of the operation and maintenance case.

[0069] The present invention obtains a case local fuzzy feature performance calculation formula by using a specific mathematical model and after verification, which is used to perform fuzzy sub-feature evaluation calculation on the corresponding real-time operation and maintenance case of electric power information and communication business. The case local fuzzy feature performance calculation formula can integrate information from multiple dimensions by weighting different fuzzy sub-features (such as occurrence probability, response time and resolution success rate) to form a comprehensive evaluation of the operation and maintenance case. This method can ensure that the influence of multiple factors is taken into account when making decisions. By introducing weight coefficients, the contribution of features to the score can be adjusted according to the importance in actual operation and maintenance, thereby enhancing the flexibility and adaptability of the calculation formula. In addition, through the application of fuzzy feature mapping matrices, the calculation formula allows for better performance in handling uncertainty and ambiguity. Many operation and maintenance data have incomplete or fuzzy features. This fuzzy logic method provides an effective evaluation framework. In addition, by introducing the Gaussian attenuation factor and the use of the fuzzy mean, the distance factor can be introduced into the feature calculation, so that the score focuses more on data points closer to the mean and reduces the influence of outliers. In summary, the formula fully considers the local fuzzy sub-features in the local fuzzy feature mapping matrix. Local fuzzy feature performance score of operation and maintenance cases , the input variable of the local fuzzy sub-feature , integral variable parameter of local fuzzy sub-characteristic input variable , the integral lower limit of the local fuzzy sub-characteristic input variable , the integral upper limit of the local fuzzy sub-characteristic input variable , local fuzzy sub-feature input variables in the local fuzzy feature mapping matrix The probability of occurrence , the weight coefficient of the probability of occurrence , local fuzzy sub-feature input variables in the local fuzzy feature mapping matrix Response time , the weight coefficient of response time , local fuzzy sub-feature input variables in the local fuzzy feature mapping matrix Case problem solving success rate , weight coefficient of case problem solving success rate , local fuzzy sub-feature attenuation factor , the fuzzy mean of the operation and maintenance case of the local fuzzy sub-feature input variable , the correction coefficient of the local fuzzy feature performance score of the operation and maintenance case , according to the local fuzzy feature mapping matrix local fuzzy sub-features Local fuzzy feature performance score of operation and maintenance cases The correlation between the above parameters constitutes a functional relationship This formula can realize the fuzzy sub-feature evaluation calculation process of the corresponding real-time operation and maintenance case of power information and communication business. At the same time, the correction coefficient of the local fuzzy feature performance score of the operation and maintenance case is The introduction of can be adjusted according to the error conditions that occur during the calculation process, thereby improving the accuracy and applicability of the calculation formula for the local fuzzy feature representation of the case.

[0070] Further, step S25 includes the following steps: Step S251: performing local fuzzy feature normalization processing on the local fuzzy features of the real-time operation and maintenance cases of the electric power information and communication services and the local fuzzy features corresponding to each historical operation and maintenance case of the electric power information and communication services, so as to obtain the local fuzzy features of the real-time operation and maintenance cases and the local fuzzy features of each historical operation and maintenance case under the same dimensional scale; In an embodiment of the present invention, the local fuzzy features of the corresponding real-time operation and maintenance cases of electric power information and communication services and the local fuzzy features corresponding to each historical operation and maintenance case of electric power information and communication services are normalized by using the Z-score normalization or Min-Max normalization method to ensure that all local fuzzy features are compared under the same dimensional scale, so that their numerical ranges are consistent and the influence of different dimensions is eliminated, and finally the local fuzzy features of the real-time operation and maintenance cases and the local fuzzy features of each historical operation and maintenance case under the same dimensional scale are obtained.

[0071] Step S252: integrating the local fuzzy features of each historical operation and maintenance case to obtain a local fuzzy feature library of historical operation and maintenance cases; In an embodiment of the present invention, local fuzzy features of each historical operation and maintenance case obtained after normalization are integrated, and the normalized local fuzzy features are classified by a cluster analysis method (such as K-means or hierarchical clustering), and the historical operation and maintenance cases are divided into different groups according to a set number of clusters by selecting a suitable distance metric (such as Euclidean distance or Manhattan distance). The integrated features of each group represent a similar set of operation and maintenance cases, thereby forming a local fuzzy feature library of historical operation and maintenance cases. The feature library is used to store the central feature value of each case group and its corresponding case identification, and finally a local fuzzy feature library of historical operation and maintenance cases is obtained.

[0072] Step S253: performing local fuzzy hash mapping processing on the local fuzzy features of the real-time operation and maintenance cases and the local fuzzy feature library of the historical operation and maintenance cases respectively, so as to obtain the local fuzzy hash value of the real-time operation and maintenance cases and the local fuzzy hash table of the historical operation and maintenance cases; In an embodiment of the present invention, a local sensitive hashing (LSH) algorithm is used to map hash values ​​of the corresponding local fuzzy features of real-time operation and maintenance cases and each local fuzzy feature in the local fuzzy feature library of historical operation and maintenance cases, so as to select an appropriate hash function (such as SimHash or MinHash) and generate corresponding hash values ​​according to the local fuzzy features, thereby preprocessing the local fuzzy features of the real-time operation and maintenance cases and the historical cases, and mapping each local fuzzy feature to a low-dimensional hash specific value through the hash function, and finally obtaining the local fuzzy hash value of the real-time operation and maintenance case and the local fuzzy hash table of the historical operation and maintenance case.

[0073] Step S254: Based on the local fuzzy hash table of historical operation and maintenance cases, similarity reasoning analysis is performed on the local fuzzy hash values ​​of the real-time operation and maintenance cases to obtain historical similar operation and maintenance cases corresponding to the real-time operation and maintenance cases of the electric power information and communication business.

[0074] In an embodiment of the present invention, a local fuzzy hash table of historical operation and maintenance cases obtained by combining with previous mapping is used to perform similarity inference matching analysis on the local fuzzy hash values ​​of the corresponding real-time operation and maintenance cases, so as to use corresponding matching strategies including proximity search based on hash values, and use the hash table and the local fuzzy hash values ​​of the real-time operation and maintenance cases for fast retrieval, and search the hash table for historical operation and maintenance cases with the same hash value according to the local fuzzy hash values ​​of the real-time operation and maintenance cases, so as to obtain a set of possibly similar historical operation and maintenance cases. At the same time, similarity calculations are performed on the local fuzzy features of these candidate cases (such as cosine similarity or Jaccard similarity), and qualified historical operation and maintenance cases are screened out according to the set similarity threshold, so as to output a list of historical operation and maintenance cases similar to the real-time operation and maintenance cases, and finally obtain historical similar operation and maintenance cases corresponding to the real-time operation and maintenance cases of the electric power communication business.

[0075] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0076] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A method for analyzing power information and communication business operation and maintenance data, characterized in that: The following steps are involved: Step S1: low-power real-time collection of operation and maintenance data of the power communication service process between the power equipment and the communication infrastructure to obtain real-time monitoring data of power communication service operation and maintenance; Conduct case analysis on the real-time monitoring data of power telecommunication business operation and maintenance to obtain real-time operation and maintenance cases of power telecommunication business; Step S2: Perform local fuzzy feature analysis on the real-time operation and maintenance cases of electric power information and communication services to obtain local fuzzy features of the real-time operation and maintenance cases of electric power information and communication services; obtain historical operation and maintenance cases of electric power information and communication services, and perform local similarity reasoning analysis on the historical operation and maintenance cases of electric power information and communication services based on the local fuzzy features of the real-time operation and maintenance cases of electric power information and communication services to obtain historical similar operation and maintenance cases corresponding to the real-time operation and maintenance cases of electric power information and communication services; Step S3: Performing operation and maintenance decision mining and analysis on historical similar operation and maintenance cases corresponding to the real-time operation and maintenance cases of electric power information and communication services, and obtaining a support plan for historical similar operation and maintenance decisions of electric power information and communication services; Step S4: Perform business operation and maintenance feedback optimization processing on the corresponding real-time operation and maintenance cases of electric power communication services according to the historical similar operation and maintenance decision support scheme of electric power communication services to obtain the operation and maintenance feedback optimization management results of electric power communication services.

2. The method for analyzing power information and communication business operation and maintenance data according to claim 1, characterized in that: Step S1 includes the following steps: Step S11: Deploy various operation and maintenance sensors between the power equipment and the information and communication infrastructure, wherein the operation and maintenance sensors include current sensors, temperature sensors, and vibration sensors, and use low-power wide area network technology to construct an operation and maintenance monitoring network for the various operation and maintenance sensors deployed between the power equipment and the information and communication infrastructure, so as to generate an operation and maintenance monitoring network for power information and communication services; Step S12: using the power information and communication service operation and maintenance monitoring network to collect operation and maintenance data of the power information and communication service process between the power equipment and the information and communication infrastructure in real time with low power consumption, so as to obtain real-time monitoring data of power information and communication service operation and maintenance; Step S13: performing quantitative analysis of operation and maintenance indicators on the real-time monitoring data of the power information and communication service operation and maintenance to obtain a parameter set of power information and communication service operation and maintenance performance indicators; Step S14: Based on the power information and communication service operation and maintenance performance indicator parameter set, statistical analysis is performed on the power information and communication service process corresponding to the power equipment and the information and communication infrastructure to obtain the power information and communication service process operation and maintenance description characteristics; Step S15: Perform communication and information service operation and maintenance case analysis based on the power communication and information service process operation and maintenance description characteristics to obtain real-time operation and maintenance cases for the power communication and information service.

3. The method for analyzing power information and communication business operation and maintenance data according to claim 2, characterized in that: Step S13 includes the following steps: Step S131: converting the real-time monitoring data of the power information and communication business operation and maintenance into a time series data stream to obtain a time series data stream of the power information and communication business operation and maintenance monitoring; Step S132: Performing power information and communication operation and maintenance state variable analysis on the power information and communication business operation and maintenance monitoring time series data stream to obtain power information and communication business operation and maintenance state variables, wherein the power information and communication business operation and maintenance state variables include power information and communication operation and maintenance current fluctuation rate, power information and communication operation and maintenance fault duration, and power information and communication operation response time; Step S133: performing quantitative analysis on the availability of power communication and information service operation and maintenance for the corresponding power communication and information service process according to the power communication and information service operation and maintenance current fluctuation rate, and obtaining the power communication and information service operation and maintenance equipment availability index parameter; Step S134: quantitatively analyzing the efficiency of power communication and information service operation and maintenance and the failure rate of power communication and information service operation and maintenance on the corresponding power communication and information service process according to the duration of the power communication and information service operation and maintenance failure and the power communication and information service operation and maintenance response time, so as to obtain the power communication and information service operation and maintenance efficiency index parameter and the power communication and information service operation and maintenance failure rate index parameter; Step S135: Merge the performance indicator parameters of the electric power information and communication business operation and maintenance equipment availability indicator parameters, the electric power information and communication business operation and maintenance maintenance efficiency indicator parameters, and the electric power information and communication business operation and maintenance failure occurrence rate indicator parameters to obtain the electric power information and communication business operation and maintenance performance indicator parameter set.

4. The method for analyzing power information and communication business operation and maintenance data according to claim 1, characterized in that: Step S2 includes the following steps: Step S21: dividing the real-time operation and maintenance cases of electric power information and communication services into operation and maintenance attribute classes to obtain the real-time operation and maintenance case attribute data of electric power information and communication services; Step S22: performing operation and maintenance local feature clustering analysis on the corresponding real-time operation and maintenance cases of electric power information and communication services based on the attribute data of the real-time operation and maintenance cases of electric power information and communication services, and obtaining the local feature clustering results of the real-time operation and maintenance cases; Step S23: Based on the local feature clustering results of the real-time operation and maintenance cases, the local fuzzy feature analysis of the corresponding real-time operation and maintenance cases of the electric power information and communication services is performed to obtain the local fuzzy features of the real-time operation and maintenance cases of the electric power information and communication services; Step S24: obtaining historical operation and maintenance cases of electric power information and communication services, and performing consistent local fuzzy feature analysis on the historical operation and maintenance cases of electric power information and communication services to obtain local fuzzy features corresponding to each historical operation and maintenance case of electric power information and communication services; Step S25: Based on the local fuzzy features of the real-time operation and maintenance cases of the electric power information and communication services, the local fuzzy features corresponding to the historical operation and maintenance cases of the electric power information and communication services are subjected to real-time case local similarity reasoning analysis to obtain historical similar operation and maintenance cases corresponding to the real-time operation and maintenance cases of the electric power information and communication services.

5. The method for analyzing power information and communication business operation and maintenance data according to claim 4 is characterized in that: Step S23 includes the following steps: Step S231: performing fuzzy feature space membership mapping conversion on each operation and maintenance case local feature clustering cluster in the local feature clustering result of the real-time operation and maintenance case to obtain the local fuzzy feature mapping space of each real-time operation and maintenance case; Step S232: performing fuzzy feature association analysis on each local fuzzy sub-feature of each operation and maintenance case in the local fuzzy feature mapping space of each real-time operation and maintenance case, so as to obtain a potential association relationship between different local fuzzy sub-features in each local fuzzy feature mapping space; Step S233: constructing a feature matrix connection for each operation and maintenance case local fuzzy sub-feature in the local fuzzy feature mapping space corresponding to the real-time operation and maintenance case based on the potential correlation between different local fuzzy sub-features in each local fuzzy feature mapping space, so as to generate a local fuzzy feature mapping matrix for the real-time operation and maintenance case; Step S234: Based on each local fuzzy sub-feature of the operation and maintenance case in the local fuzzy feature mapping matrix of the real-time operation and maintenance case, a fuzzy sub-feature evaluation calculation is performed on the corresponding real-time operation and maintenance case of the electric power information and communication business using the local fuzzy feature performance calculation formula to obtain the local fuzzy feature performance score of the operation and maintenance case corresponding to each local fuzzy sub-feature in the local fuzzy feature mapping matrix; Step S235: Perform local fuzzy feature screening and output according to the local fuzzy feature performance score of the operation and maintenance case corresponding to each local fuzzy sub-feature in the local fuzzy feature mapping matrix to obtain the local fuzzy features of the real-time operation and maintenance case of the electric power information and communication business.

6. The method for analyzing power information and communication business operation and maintenance data according to claim 5, characterized in that: Step S231 includes the following steps: Perform outlier feature elimination processing on each local feature clustering cluster of operation and maintenance cases in the local feature clustering result of real-time operation and maintenance cases to obtain local outlier optimized feature clustering clusters of each real-time operation and maintenance case; Perform local fuzzy feature matching calculation on each local sub-feature of the operation and maintenance case in the local outlier optimization feature clustering cluster of each real-time operation and maintenance case, and obtain each local fuzzy sub-feature of the operation and maintenance case corresponding to the local feature clustering cluster of each real-time operation and maintenance case; Perform triangular and Gaussian fuzzy number statistical analysis on each local fuzzy sub-feature of each operation and maintenance case corresponding to each local feature clustering cluster of each real-time operation and maintenance case, and obtain the triangular fuzzy number and Gaussian fuzzy number corresponding to each local fuzzy sub-feature of each operation and maintenance case in each local feature clustering cluster; Based on the triangular fuzzy number and Gaussian fuzzy number corresponding to each local fuzzy sub-feature of each operation and maintenance case in each local feature clustering cluster, the feature fuzzy membership quantization calculation is performed on each corresponding local fuzzy sub-feature of the operation and maintenance case to obtain the feature fuzzy membership corresponding to each local fuzzy sub-feature of the operation and maintenance case in each local feature clustering cluster; Based on the feature fuzzy membership corresponding to each local fuzzy sub-feature of each operation and maintenance case in each local feature clustering cluster, the fuzzy feature space membership mapping conversion is performed on the corresponding local fuzzy sub-feature of each operation and maintenance case to obtain the local fuzzy feature mapping space of each real-time operation and maintenance case.

7. The method for analyzing power information and communication business operation and maintenance data according to claim 6, characterized in that: The process of removing outlier features from each local feature clustering cluster of operation and maintenance cases in the local feature clustering result of real-time operation and maintenance cases comprises the following steps: Perform local feature mean and variance statistical calculations on each operation and maintenance case local feature clustering cluster in the real-time operation and maintenance case local feature clustering results to obtain the local feature mean and local feature variance corresponding to each operation and maintenance case local feature clustering cluster; The outlier feature discrimination threshold is calculated based on the local feature mean and local feature variance corresponding to each operation and maintenance case local feature cluster, and the local outlier feature discrimination threshold corresponding to each operation and maintenance case local feature cluster is obtained; According to the local outlier feature discrimination threshold corresponding to each operation and maintenance case local feature clustering cluster, the corresponding operation and maintenance case local sub-features in each operation and maintenance case local feature clustering cluster are identified and judged. If the corresponding operation and maintenance case local sub-feature is greater than or equal to the local outlier feature discrimination threshold, the corresponding operation and maintenance case local sub-feature in the operation and maintenance case local feature clustering cluster is marked as an outlier feature; if the corresponding operation and maintenance case local sub-feature is less than the local outlier feature discrimination threshold, the corresponding operation and maintenance case local sub-feature in the operation and maintenance case local feature clustering cluster is marked as a non-outlier feature; The local sub-features of the operation and maintenance cases corresponding to the outlier features in the local feature clustering clusters of each operation and maintenance case are eliminated and optimized to obtain the local outlier optimized feature clustering clusters of each real-time operation and maintenance case.

8. The method for analyzing power information and communication business operation and maintenance data according to claim 6, characterized in that: The triangular and Gaussian fuzzy number statistical analysis of each local fuzzy sub-feature of each operation and maintenance case corresponding to the local feature cluster of each real-time operation and maintenance case includes the following steps: Performing feature initial value statistical analysis on each local fuzzy sub-feature of each operation and maintenance case corresponding to each local feature clustering cluster of each real-time operation and maintenance case, and obtaining each local fuzzy sub-feature initial value corresponding to each local feature clustering cluster of each real-time operation and maintenance case; Based on the initial value of each local fuzzy sub-feature corresponding to each local feature cluster of each real-time operation and maintenance case, the fuzzy spatial distribution characteristics of the corresponding local fuzzy sub-feature of the operation and maintenance case are analyzed to obtain the fuzzy spatial distribution shape and fuzzy spatial distribution interval corresponding to each local fuzzy sub-feature in each local feature cluster; Based on the fuzzy spatial distribution shape and fuzzy spatial distribution interval corresponding to each local fuzzy sub-feature in each local feature cluster, the triangular fuzzy number statistical analysis is performed on the corresponding local fuzzy sub-features of the operation and maintenance cases, and the triangular fuzzy number corresponding to each local fuzzy sub-feature of the operation and maintenance cases in each local feature cluster is obtained; The triangular fuzzy number corresponding to the local fuzzy sub-feature of each operation and maintenance case in each local feature clustering cluster is calculated by Gaussian expansion transformation to obtain the Gaussian fuzzy number corresponding to the local fuzzy sub-feature of each operation and maintenance case in each local feature clustering cluster.

9. The method for analyzing power information and communication service operation and maintenance data according to claim 5, characterized in that: The calculation formula for the local fuzzy feature expression of the case described in step S234 is specifically: ； In the formula, is the local fuzzy sub-feature in the local fuzzy feature mapping matrix The local fuzzy feature performance score of the operation and maintenance case, is the input variable of the local fuzzy sub-feature, is the integral variable parameter of the local fuzzy sub-feature input variable, is the lower limit of the integration of the local fuzzy sub-characteristic input variable, is the upper limit of the integration of the local fuzzy sub-characteristic input variables, Input variables for local fuzzy sub-features in the local fuzzy feature map matrix The probability of occurrence, is the weight coefficient of the occurrence probability, Input variables for local fuzzy sub-features in the local fuzzy feature map matrix The response time, is the weight coefficient of response time, Input variables for local fuzzy sub-features in the local fuzzy feature map matrix The success rate of case problem solving, is the weight coefficient of the success rate of case problem solving, is the local fuzzy sub-feature attenuation factor, is the fuzzy mean of the operation and maintenance cases of the local fuzzy sub-feature input variables, It is the correction coefficient of the local fuzzy feature performance score of the operation and maintenance case.

10. The method for analyzing power information and communication service operation and maintenance data according to claim 4, characterized in that: Step S25 includes the following steps: Step S251: performing local fuzzy feature normalization processing on the local fuzzy features of the real-time operation and maintenance cases of the electric power information and communication services and the local fuzzy features corresponding to each historical operation and maintenance case of the electric power information and communication services, so as to obtain the local fuzzy features of the real-time operation and maintenance cases and the local fuzzy features of each historical operation and maintenance case under the same dimensional scale; Step S252: integrating the local fuzzy features of each historical operation and maintenance case to obtain a local fuzzy feature library of historical operation and maintenance cases; Step S253: performing local fuzzy hash mapping processing on the local fuzzy features of the real-time operation and maintenance cases and the local fuzzy feature library of the historical operation and maintenance cases respectively, so as to obtain the local fuzzy hash value of the real-time operation and maintenance cases and the local fuzzy hash table of the historical operation and maintenance cases; Step S254: Based on the local fuzzy hash table of historical operation and maintenance cases, similarity reasoning analysis is performed on the local fuzzy hash values ​​of the real-time operation and maintenance cases to obtain historical similar operation and maintenance cases corresponding to the real-time operation and maintenance cases of the electric power information and communication business.

Images