Operation and maintenance management method and device, electronic equipment and storage medium

Abstract

The invention relates to an operation and maintenance management method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring operation and maintenance data; performing anomaly detection on the operation and maintenance data by using the multi-task prediction model to obtain a health assessment result; wherein the multi-task prediction model comprises an expert network and a prediction network; the expert network comprises at least one shared expert network and a plurality of private expert networks; the shared expert network is used for performing feature extraction and fusion processing on the operation and maintenance data to obtain a global feature vector; the private expert network is used for performing feature processing on operation and maintenance data corresponding to a specific scene and / or a specific task to obtain a local feature vector; the prediction network is used for detecting a target feature vector obtained by fusing the global feature vector and the local feature vector to obtain a health assessment result; performing evaluation analysis on the operation and maintenance quality based on the operation and maintenance data to obtain a target operation and maintenance evaluation result; and determining a target comprehensive result according to the health assessment result and the target operation and maintenance assessment result.

Description

Technical Field

[0001] The present application relates to the field of operation and maintenance management technology, and in particular to an operation and maintenance management method, device, electronic device and storage medium. Background Art

[0002] In modern operation and maintenance management, with the development of big data technology, the types and amount of operation and maintenance data have increased dramatically, and business has become more complex and diversified. How to effectively collect, analyze and utilize this data has become a challenge.

[0003] Existing operation and maintenance management methods mostly use static indicators, expert experience or preset rules for analysis and evaluation. They are unable to timely capture new problems and changing trends in operation and maintenance work, and it is difficult to achieve status analysis and integrated evaluation of operation and maintenance data of different tasks and / or different dimensions. There is a lag in problem discovery and it cannot meet the needs of real-time and accuracy.

[0004] Therefore, how to ensure the real-time and accuracy of operation and maintenance monitoring and evaluation analysis is an urgent problem to be solved. Summary of the Invention

[0005] Based on this, it is necessary to provide an operation and maintenance management method, device, distribution box and storage medium to address the above technical problems.

[0006] In a first aspect, the present application provides an operation and maintenance management method, the method comprising: Acquiring operation and maintenance data in the power system; wherein the operation and maintenance data includes at least one of network dimension data, work specification dimension data, and power dimension data; A multi-task prediction model is used to perform anomaly detection on the operation and maintenance data to obtain a health assessment result; wherein the multi-task prediction model includes an expert network and a prediction network; the expert network includes at least one shared expert network and multiple private expert networks; the shared expert network is used to perform feature extraction and fusion processing on the operation and maintenance data to obtain a global feature vector; the private expert network is used to perform feature processing on the operation and maintenance data corresponding to a specific scenario and / or a specific task to obtain a local feature vector; the prediction network is used to detect a target feature vector obtained by fusion of the global feature vector and the local feature vector to obtain the health assessment result; Evaluate and analyze the operation and maintenance quality based on the operation and maintenance data to obtain a target operation and maintenance evaluation result; Determine a target comprehensive result based on the health assessment result and the target operation and maintenance assessment result.

[0007] In one embodiment, obtaining operation and maintenance data in the power system includes: Acquiring original operation and maintenance data in the power system; Performing data cleaning on the original operation and maintenance data using an interpolation method, an average value filling method, and / or a deletion method to obtain first data; performing outlier identification on the first data to obtain second data; Perform data standardization processing on the second data to obtain the operation and maintenance data.

[0008] In one embodiment, the evaluating and analyzing the operation and maintenance quality based on the operation and maintenance data to obtain a target operation and maintenance evaluation result includes: Assigning an initial weight to the operation and maintenance data of each dimension based on preset rules; Determine the importance score of the operation and maintenance data in each dimension based on the operation and maintenance goals in the current scenario; According to the importance score, updating the initial weight of the operation and maintenance data to obtain a real-time weight; The target operation and maintenance evaluation result is obtained according to the evaluation score of the operation and maintenance data of each dimension and the corresponding real-time weight.

[0009] In one embodiment, the method further comprises: Obtain real-time operation and maintenance assessment results within a predetermined time window; Calculating a weight optimization factor based on the real-time operation and maintenance evaluation results; Determine the evaluation deviation based on the comparison of the real-time operation and maintenance evaluation result with the weight optimization factor; Updating the real-time weight according to the evaluation deviation and the weight optimization factor to obtain an updated real-time weight; The target operation and maintenance evaluation result is recalculated based on the evaluation score of the operation and maintenance data in each dimension and the corresponding updated real-time weight.

[0010] In one embodiment, the calculation expression of the weight optimization factor is as follows: ; in, Indicate the starting time of the predetermined time window; Indicate the end time of the predetermined time window; Indicates the real-time weight corresponding to the k-th dimension; Indicates the real-time operation and maintenance evaluation result of the operation and maintenance data of the kth dimension at time t.

[0011] In one embodiment, the multi-task detection model also includes a gating network; wherein the gating network is used to obtain the weight coefficient corresponding to each feature vector based on the global feature vector and / or the local feature vector; the expert network connects multiple gating networks; and the gating network is connected to the prediction network in a one-to-one correspondence.

[0012] In one embodiment, the method further comprises: In response to a request to view the operation and maintenance evaluation interface, display the operation and maintenance evaluation interface; wherein the operation and maintenance evaluation interface is used to display detailed information of the operation and maintenance data in the power system; the operation and maintenance evaluation interface includes an operation and maintenance evaluation option; When a trigger operation for the operation and maintenance evaluation option is received, the target comprehensive result is output on the operation and maintenance evaluation interface in at least one of a chart form and a report form, and / or the target comprehensive result is sent to a third-party terminal.

[0013] In a second aspect, the present application further provides an operation and maintenance management device, the device comprising: An acquisition module, configured to acquire operation and maintenance data in the power system; wherein the operation and maintenance data includes at least one of network dimension data, work specification dimension data, and power dimension data; A health assessment module is configured to use a multi-task prediction model to perform anomaly detection on the operation and maintenance data to obtain a health assessment result; wherein the multi-task prediction model includes an expert network and a prediction network; the expert network includes at least one shared expert network and multiple private expert networks; the shared expert network is configured to perform feature extraction and fusion processing on the operation and maintenance data to obtain a global feature vector; the private expert network is configured to perform feature processing on the operation and maintenance data corresponding to a specific scenario and / or specific task to obtain a local feature vector; the prediction network is configured to detect a target feature vector obtained by fusion of the global feature vector and the local feature vector to obtain the health assessment result; A quality assessment module is used to evaluate and analyze the operation and maintenance quality based on the operation and maintenance data to obtain a target operation and maintenance assessment result; The determination module is used to determine the target comprehensive result based on the health assessment result and the target operation and maintenance assessment result.

[0014] In a third aspect, the present application also provides an electronic device comprising a processor and a memory for storing a computer program for the processor; wherein the processor is configured to: when executing the computer program, implement the steps of the method execution described in any embodiment of the present application.

[0015] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method execution described in any embodiment of the present application.

[0016] The aforementioned O&M management method, on the one hand, enables comprehensive monitoring of the power system's operating status through the integrated collection of multiple types of O&M data, reducing the risk of misjudgment caused by single-dimensional / static indicator judgments and enhancing the ability to identify potential faults or abnormal behavior. On the other hand, shared expert networks can extract common features across tasks / scenarios, improving the model's generalization and stability. Multiple private expert networks, processed in parallel, enable detailed modeling for specific scenarios / tasks, enabling integrated evaluation of O&M data from different tasks / dimensions, improving anomaly detection accuracy, and meeting real-time requirements. Furthermore, a target comprehensive outcome is determined based on the health assessment results and the target O&M assessment results. This not only focuses on the operating status of the power system's physical equipment and virtual network / power transmission status, but also incorporates factors such as personnel operating procedures, process execution, and response timeliness, forming a comprehensive assessment perspective that further enhances the accuracy and reliability of O&M assessment management. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 is a flowchart of an operation and maintenance management method according to an exemplary embodiment; Figure 2 is a flowchart of an operation and maintenance management method according to an exemplary embodiment; Figure 3 is a structural block diagram of an operation and maintenance management device according to an exemplary embodiment; Figure 4 It is a diagram showing the internal structure of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0019] The terms "first", "second" and "third" in the embodiments of the present application are only used for descriptive purposes and are not to be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first", "second" and "third" may explicitly or implicitly include at least one of the features. In the description of the present application, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, method, product or device comprising a series of steps or units is not limited to the listed steps or units, but may optionally also include steps or units that are not listed, or may optionally also include other steps or units inherent to these processes, methods, products or devices.

[0020] References to "embodiments" herein mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0021] In some embodiments, the operation and maintenance management method provided in the embodiments of the present application can be applied to electronic devices or cloud servers. Among them, the electronic device can be any mobile terminal or fixed terminal. The terminal can be a device that provides voice and / or data connectivity to the user. Exemplarily, the terminal can be an Internet of Things terminal, such as a sensor device, a mobile phone or a so-called "cellular" phone and a computer with an Internet of Things terminal, for example, it can be a fixed, portable, pocket-sized, handheld, or computer-built-in device. The cloud server can be any virtualized computing resource or a physical server cluster. The server can be a platform that provides on-demand, scalable computing, storage, network, and application services to users.

[0022] In some embodiments, as Figure 1 As shown, an operation and maintenance management method is provided, the method comprising the following steps: S101, obtaining operation and maintenance data in the power system; wherein the operation and maintenance data includes at least one of network dimension data, work specification dimension data and power dimension data.

[0023] In an embodiment of the present application, network dimension data may include but is not limited to resource consumption, failure rate, load rate, communication bandwidth utilization, network delay, packet loss rate, router load, network connectivity, service classification data (such as service address, service port, service request method, etc.) and abnormal judgment data (request response time, number of request responses, total number of requests, etc.) of hardware / system / software / network connection resources. At least one of them.

[0024] In an embodiment of the present application, work specification data may include but is not limited to at least one of operation / inspection record data, operation execution compliance data, safety specification compliance data, and work order processing efficiency data.

[0025] In an embodiment of the present application, the power dimension data may include but is not limited to at least one of electrical dimension data (current / voltage), power, frequency, harmonic content, switch status, electrical equipment health status data and relay protection data.

[0026] In one embodiment, the information operation and maintenance platform in the electronic device / cloud server can collect and store operation and maintenance data in real time during the operation of the power system through electronic transformers, sensors (temperature / humidity sensors) and / or network traffic mirroring devices.

[0027] S102, using a multi-task prediction model to perform anomaly detection on the operation and maintenance data to obtain a health assessment result; wherein, the multi-task prediction model includes an expert network and a prediction network; the expert network includes at least one shared expert network and multiple private expert networks; the shared expert network is used to perform feature extraction and fusion processing on the operation and maintenance data to obtain a global feature vector; the private expert network is used to perform feature processing on the operation and maintenance data corresponding to a specific scenario and / or a specific task to obtain a local feature vector; the prediction network is used to detect a target feature vector obtained by fusion of the global feature vector and the local feature vector to obtain the health assessment result.

[0028] In an embodiment of the present application, the multi-task prediction model may include but is not limited to at least one of a multi-gate mixture of experts (MMoE), a progressive layered extraction (PLE) model, and a multi-task deep learning (MDL) framework.

[0029] In this embodiment of the present application, the expert network refers to a specialized subnetwork that extracts task-related high-level features through deep convolution, attention mechanisms, and other techniques. It typically comprises multiple parallel structures. By isolating the feature spaces of different tasks, the expert network can avoid negative transfer (for example, where improved performance on one task leads to decreased performance on a second task).

[0030] In the embodiment of the present application, the prediction network is used to integrate the output of the expert network to generate the final prediction result; the input of the prediction network is usually a fusion representation of multiple expert feature vectors.

[0031] In some embodiments, the power system may have different power-consuming devices and peak power consumption during different time periods. This may result in different network communication loads and throughput. For example, in the hot summer, regions often use more cooling equipment, resulting in peak power consumption and a higher load on the power system. In contrast, in the spring, temperatures are mild, and power consumption is low compared to the summer, resulting in different scenarios. Alternatively, due to the wide variety of distribution and consumer equipment in the power system, their usage rules and health conditions may also vary, resulting in different scenarios.

[0032] In some embodiments, specific tasks may include but are not limited to at least one of tasks focusing on power load anomalies, tasks focusing on equipment status anomalies, tasks focusing on network communication anomalies, tasks focusing on network load anomalies, and tasks focusing on electrical safety anomalies.

[0033] Exemplarily, the expert network includes one shared expert network and three private expert networks; the shared expert network may include one or more fully connected networks arranged in parallel to perform feature extraction and feature fusion on the operation and maintenance data to obtain a global feature vector; the first private expert network receives the operation and maintenance data corresponding to the task of focusing on abnormal distribution equipment, and outputs a first local feature vector; the second private expert network receives the operation and maintenance data corresponding to the task of focusing on abnormal electrical safety, and outputs a second local feature vector; the third private expert network receives the operation and maintenance data corresponding to the task of focusing on abnormal network communication, and outputs a third local feature vector; the prediction network fuses the global feature vector with the local feature vector, and performs multi-task prediction to obtain the health assessment result of the power system.

[0034] In some embodiments, the multi-task detection model also includes a gating network; wherein the gating network is used to obtain the weight coefficient corresponding to each feature vector based on the global feature vector and / or the local feature vector; the expert network connects multiple gating networks; and the gating network is connected to the prediction network in a one-to-one correspondence.

[0035] In the embodiment of the present application, a gating network is a neural network structure; the gating network is used to dynamically adjust the contribution of different expert networks or feature channels.

[0036] In one embodiment, the gating network can assign differentiated weights to different expert networks based on the characteristics of the operation and maintenance data or task requirements; and by adjusting the weights of shared experts and private experts, the competition between tasks can be alleviated.

[0037] In some embodiments, the gating network generates a set of normalized weights through nonlinear transformation, multiplies the weights with the output of the corresponding expert network and then sums them to generate fusion features.

[0038] S103: Evaluate and analyze the operation and maintenance quality based on the operation and maintenance data to obtain a target operation and maintenance evaluation result.

[0039] In one embodiment, the operation and maintenance data can be divided into multiple dimensions of data; the electronic device can establish a linear weighted model, use the operation and maintenance data to evaluate and analyze the operation and maintenance quality, and obtain a target operation and maintenance evaluation result.

[0040] For example, the linear weighted model is expressed as follows: ; in, Indicates the weight corresponding to the i-th dimension; Indicates the standardized score corresponding to the i-th dimension.

[0041] For example, a normalized score is calculated as follows: For positive dimensions (such as inspection completion rate): ; For negative dimensions (such as the proportion of power outage duration): ; in, Indicates the minimum value of the i-th dimension in the operation and maintenance data, representing the "worst performance" boundary; Indicates the maximum value of the i-th dimension in the operation and maintenance data, representing the "optimal performance" boundary.

[0042] S104: Determine a target comprehensive result based on the health assessment result and the target operation and maintenance assessment result.

[0043] In one embodiment, the electronic device can use the weight superposition method to fuse the health assessment results and the target operation and maintenance assessment results to obtain the target comprehensive result of the power system; it can also determine the target comprehensive result based on the comparison of the health assessment results and the target operation and maintenance assessment results with the key threshold. For example, if the health assessment result is less than the health critical value (60), the target comprehensive result can be determined as the health assessment result, highlighting the risks in the equipment / operation process that need to be paid special attention.

[0044] In one embodiment, the electronic device can evaluate and score the service providers providing operation and maintenance services for the power system based on the target comprehensive results, so as to facilitate the subsequent selection of the service providers.

[0045] The aforementioned O&M management method, on the one hand, enables comprehensive monitoring of the power system's operating status through the integrated collection of multiple types of O&M data, reducing the risk of misjudgment caused by single-dimensional / static indicator judgments and enhancing the ability to identify potential faults or abnormal behavior. On the other hand, shared expert networks can extract common features across tasks / scenarios, improving the model's generalization and stability. Multiple private expert networks, processed in parallel, enable detailed modeling for specific scenarios / tasks, enabling integrated evaluation of O&M data from different tasks / dimensions, improving anomaly detection accuracy, and meeting real-time requirements. Furthermore, a target comprehensive outcome is determined based on the health assessment results and the target O&M assessment results. This not only focuses on the operating status of the power system's physical equipment and virtual network / power transmission status, but also incorporates factors such as personnel operating procedures, process execution, and response timeliness, forming a comprehensive assessment perspective that further enhances the accuracy and reliability of O&M assessment management.

[0046] In one embodiment, obtaining operation and maintenance data in the power system includes: Acquiring original operation and maintenance data in the power system; Performing data cleaning on the original operation and maintenance data using an interpolation method, an average value filling method, and / or a deletion method to obtain first data; performing outlier identification on the first data to obtain second data; Perform data standardization processing on the second data to obtain the operation and maintenance data.

[0047] In some embodiments, electronic devices can obtain operational data, such as voltage, current, power, device temperature, and switch status, from intelligent electronic devices such as transformers, circuit breakers, and instrument transformers. Data can also be extracted from power automation systems such as SCADA (Supervisory Control and Data Acquisition), EMS (Energy Management System), and DMS (Distribution Management System). SCADA focuses on real-time data acquisition and monitoring, providing real-time equipment operating status. EMS is used for grid dispatching and power generation control, and includes data such as power flow and load for overall grid operation. DMS focuses on the distribution network, providing data such as distribution transformer monitoring and feeder automation. Operation and maintenance business data can be obtained from production management systems (PMS) and operation and maintenance work order systems, including inspection records (inspection time, inspection personnel, and problems found), fault reporting and handling records (fault occurrence time, fault type, and repair time), and equipment records (equipment model, commissioning date, and manufacturer information). This data is used as raw operation and maintenance data.

[0048] In one embodiment, the electronic device can use interpolation to process missing values ​​for original operation and maintenance data with strong time series, use average value filling to process missing values ​​for original operation and maintenance data with relatively uniform data distribution, and directly delete missing values ​​for original operation and maintenance data with weak context association to obtain first data.

[0049] In one embodiment, the electronic device can identify abnormal values ​​based on power business rules, for example, by comparing each piece of operation and maintenance data with an electrical quantity threshold or equipment status threshold, and marking data that exceeds the threshold range as an abnormal value; or, the electronic device can identify abnormal values ​​in the operation and maintenance data that conforms to the normal distribution based on statistical methods. For example, by using the mean-standard deviation method ( Principle), calculate the mean and standard deviation of operation and maintenance data of the same dimension, identify and mark data outside the predetermined range as outliers; eliminate, smooth, replace, or reduce the weight of outliers to obtain the second data.

[0050] In some embodiments, the electronic device may normalize the dimensional directions of operation and maintenance data of multiple dimensions, dividing them into positive dimensions and negative dimensions; and use Min-Max scaling or Z-Score normalization to normalize the second data to obtain operation and maintenance data.

[0051] In the embodiment of the present application, by performing data cleaning and outlier identification on the original operation and maintenance data, invalid interference data can be eliminated, real fault signals can be retained, and data quality and credibility can be improved; it can also adapt to the input requirements of subsequent evaluation models and enhance model performance and stability.

[0052] In some embodiments, as Figure 2 As shown, the operation and maintenance quality is evaluated and analyzed based on the operation and maintenance data to obtain the target operation and maintenance evaluation result, including: S1031, assigning an initial weight to the operation and maintenance data of each dimension based on a preset rule; S1032: Determine the importance score of the operation and maintenance data in each dimension based on the operation and maintenance goals in the current scenario; S1033: updating the initial weight of the operation and maintenance data according to the importance score to obtain a real-time weight; S1034: Obtain the target operation and maintenance evaluation result according to the evaluation score of the operation and maintenance data of each dimension and the corresponding real-time weight.

[0053] In one embodiment, the electronic device may calculate an evaluation score for the operation and maintenance data of each dimension based on a machine learning model (such as a decision tree, a neural network, a gradient model, etc.).

[0054] In some embodiments, the electronic device can set the weight corresponding to each dimension of operation and maintenance data to the same value. Alternatively, the weights can be unevenly distributed based on the importance of each dimension in power system operation. For example, a lower weight can be assigned to operation and maintenance data related to network latency, while a higher weight can be assigned to operation and maintenance data related to work order processing efficiency. Alternatively, the contribution of each dimension feature in the machine learning model to the model's prediction results (evaluation score) can be determined based on the SHAP value (SHapley Additive exPlanations), and initial weights can be assigned based on the contribution.

[0055] In one embodiment, the electronic device can be based on the operation and maintenance goals in the current scenario. For example, the failure rate of the power system in the current quarter has increased significantly, and the operation and maintenance goal is to reduce the failure rate. In this case, the importance scores of operation and maintenance data in dimensions such as fault response time and equipment health status can be determined to be higher; or, the current scenario is the peak power consumption period, and the operation and maintenance goal is to ensure continuous and safe power consumption. In this case, the importance scores of operation and maintenance data in electrical dimensions such as load balancing and voltage stability can be determined to be higher; based on the importance scores, the initial weights (or current weights) of the operation and maintenance data are updated, and the weights of dimensions with higher importance scores are increased, and the weights of dimensions with lower importance scores are decreased, to obtain updated real-time weights; based on the evaluation scores (such as standardized scores) and real-time weights of the operation and maintenance data of each dimension, the target operation and maintenance evaluation results are determined.

[0056] In the embodiment of the present application, the real-time weight of each dimension is dynamically adjusted according to the changes in the operation and maintenance objectives in the current scenario, ensuring that the target operation and maintenance evaluation results are in line with actual needs, improving the accuracy and strategic guidance significance of the target operation and maintenance evaluation results, and meeting the evaluation needs of different scenarios; it also enhances the interpretability and transparency of the evaluation results, making it easier to locate the root cause of the problem.

[0057] In some embodiments, the method further comprises: Obtain real-time operation and maintenance assessment results within a predetermined time window; Calculating a weight optimization factor based on the real-time operation and maintenance evaluation results; Determine the evaluation deviation based on the comparison of the real-time operation and maintenance evaluation result with the weight optimization factor; Updating the real-time weight according to the evaluation deviation and the weight optimization factor to obtain an updated real-time weight; The target operation and maintenance evaluation result is recalculated based on the evaluation score of the operation and maintenance data in each dimension and the corresponding updated real-time weight.

[0058] In one embodiment, the electronic device determines a first real-time operation and maintenance evaluation result based on the operation and maintenance data at the first moment within a predetermined time window; determines a second real-time operation and maintenance evaluation result based on the operation and maintenance data at the second moment within the predetermined time window; and so on, until the real-time operation and maintenance evaluation result at the end moment of the predetermined time window is determined; calculates a weight optimization factor based on the real-time operation and maintenance evaluation result of the predetermined time window; compares the real-time operation and maintenance evaluation result at the current moment with the weight optimization factor, calculates the difference between the two, and obtains an evaluation deviation; and updates the real-time weight based on the evaluation deviation and the weight optimization factor.

[0059] In some embodiments, the calculation expression of the weight optimization factor is as follows: ; in, Indicate the starting time of the predetermined time window; Indicate the end time of the predetermined time window; Indicates the real-time weight corresponding to the k-th dimension; Indicates the real-time operation and maintenance evaluation result of the operation and maintenance data of the kth dimension at time t.

[0060] In some embodiments, the update expression of the real-time weight is as follows: ; in, Indicates the learning rate, representing the step size of weight update, with a value range of 0~1; Indicates the real-time weight of the k-th dimension at time t; Indicates the real-time weight of the kth dimension at time t+1; s indicates the weight optimization factor.

[0061] In the embodiments of the present application, during the operation and maintenance of the power system, equipment status, environmental conditions (such as seasonal changes leading to load differences), etc. will change over time. By obtaining real-time evaluation results within a predetermined time window, the characteristics of recent operation and maintenance data can be captured (such as the changes in the impact of indicators such as transformer oil temperature and load rate on operation and maintenance quality during high temperatures in summer). Calculating weight optimization factors and updating weights allows the evaluation model to dynamically adapt to the current scenario. Furthermore, by comparing real-time evaluation results with weight optimization factors to determine deviations, and then updating weights based on the deviations, the model can be gradually corrected. For example, newly commissioned equipment may have different operating patterns from older equipment, making initial evaluations prone to misjudgment. Dynamically updating weights allows the model to learn the characteristics of new equipment operation and maintenance data, improving the accuracy of evaluations for new scenarios and new equipment.

[0062] In some embodiments, the method further comprises: In response to a request to view the operation and maintenance evaluation interface, display the operation and maintenance evaluation interface; wherein the operation and maintenance evaluation interface is used to display detailed information of the operation and maintenance data in the power system; the operation and maintenance evaluation interface includes an operation and maintenance evaluation option; When a trigger operation for the operation and maintenance evaluation option is received, the target comprehensive result is output on the operation and maintenance evaluation interface in at least one of a chart form and a report form, and / or the target comprehensive result is sent to a third-party terminal.

[0063] In some embodiments, the target comprehensive results and corresponding detailed information (such as statistical charts, classification tables, etc.) can be output in text or voice form on the display component of the electronic device; or, they can be sent to a third-party terminal and output on the third-party terminal.

[0064] In the embodiment of the present application, by outputting the target comprehensive results, the operation and maintenance status of the power system can be intuitively determined, which makes it easier for operators to select service providers or locate power system problems based on the operation and maintenance status, and make corresponding adjustments or processing to the power system.

[0065] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0066] Based on the same inventive concept, the embodiments of the present application also provide an operation and maintenance management device for implementing the above-mentioned operation and maintenance management method. The implementation solution provided by this device is similar to the implementation solution described in the above-mentioned method. Therefore, the specific limitations of one or more operation and maintenance management device embodiments provided below can be referred to the limitations of the operation and maintenance management method above, and will not be repeated here.

[0067] In one embodiment, Figure 3 As shown, an operation and maintenance management device is provided, the device comprising: An acquisition module 10 is configured to acquire operation and maintenance data in the power system; wherein the operation and maintenance data includes at least one of network dimension data, work specification dimension data, and power dimension data; The health assessment module 20 is configured to use a multi-task prediction model to perform anomaly detection on the operation and maintenance data to obtain a health assessment result; wherein the multi-task prediction model includes an expert network and a prediction network; the expert network includes at least one shared expert network and multiple private expert networks; the shared expert network is configured to perform feature extraction and fusion processing on the operation and maintenance data to obtain a global feature vector; the private expert network is configured to perform feature processing on the operation and maintenance data corresponding to a specific scenario and / or a specific task to obtain a local feature vector; the prediction network is configured to detect a target feature vector obtained by fusion of the global feature vector and the local feature vector to obtain the health assessment result; A quality assessment module 30 is configured to assess and analyze the operation and maintenance quality based on the operation and maintenance data to obtain a target operation and maintenance assessment result; The determination module 40 is used to determine a target comprehensive result based on the health assessment result and the target operation and maintenance assessment result.

[0068] In one embodiment, the acquisition module 10 is configured to perform the following steps: Acquiring original operation and maintenance data in the power system; Performing data cleaning on the original operation and maintenance data using an interpolation method, an average value filling method, and / or a deletion method to obtain first data; performing outlier identification on the first data to obtain second data; Perform data standardization processing on the second data to obtain the operation and maintenance data.

[0069] In one embodiment, the quality assessment module 30 is configured to perform the following steps: Assigning an initial weight to the operation and maintenance data of each dimension based on preset rules; Determine the importance score of the operation and maintenance data in each dimension based on the operation and maintenance goals in the current scenario; According to the importance score, updating the initial weight of the operation and maintenance data to obtain a real-time weight; The target operation and maintenance evaluation result is obtained according to the evaluation score of the operation and maintenance data of each dimension and the corresponding real-time weight.

[0070] In one embodiment, the apparatus further comprises: The acquisition module 10 is used to obtain real-time operation and maintenance evaluation results within a predetermined time window; A calculation module, configured to calculate a weight optimization factor based on the real-time operation and maintenance evaluation result; A comparison module, configured to compare the real-time operation and maintenance evaluation result with the weight optimization factor to determine an evaluation deviation; An updating module, configured to update the real-time weight according to the evaluation deviation and the weight optimization factor to obtain an updated real-time weight; The determination module 40 is configured to recalculate the target operation and maintenance evaluation result based on the evaluation score of the operation and maintenance data of each dimension and the corresponding updated real-time weight.

[0071] In one embodiment, the calculation expression of the weight optimization factor is as follows: ; in, Indicate the starting time of the predetermined time window; Indicate the end time of the predetermined time window; Indicates the real-time weight corresponding to the k-th dimension; Indicates the real-time operation and maintenance evaluation result of the operation and maintenance data of the kth dimension at time t.

[0072] In one embodiment, the multi-task detection model also includes a gating network; wherein the gating network is used to obtain the weight coefficient corresponding to each feature vector based on the global feature vector and / or the local feature vector; the expert network connects multiple gating networks; and the gating network is connected to the prediction network in a one-to-one correspondence.

[0073] In one embodiment, the apparatus further comprises: A display module, configured to display the operation and maintenance evaluation interface in response to a viewing request for the operation and maintenance evaluation interface; wherein the operation and maintenance evaluation interface is configured to display detailed information of the operation and maintenance data in the power system; and the operation and maintenance evaluation interface includes an operation and maintenance evaluation option; The display module is used to output the target comprehensive result in at least one of a chart form and a report form on the operation and maintenance evaluation interface when a trigger operation for the operation and maintenance evaluation option is received, and / or send the target comprehensive result to a third-party terminal.

[0074] Each module in the above-mentioned operation and maintenance management device can be implemented in whole or in part through software, hardware and their combination. The above-mentioned modules can be embedded in or independent of the processor of the electronic device in the form of hardware, or can be stored in the memory of the electronic device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0075] In one embodiment, an electronic device is provided, whose internal structure diagram can be as follows: Figure 4 As shown. The electronic device includes a processor, memory, a communication interface, a display unit, and an input device connected via a method bus. The processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating method and a computer program. The internal memory provides an environment for the operation of the operating method and computer program in the non-volatile storage medium. The communication interface of the electronic device is used to communicate with an external terminal via wired or wireless communication. The wireless communication method can be achieved through Wi-Fi, a mobile cellular network, NFC (near field communication), or other technologies. When executed by the processor, the computer program implements an image processing method. The display screen of the electronic device can be a liquid crystal display or an electronic ink display screen. The input device of the electronic device can be a touch layer covering the display screen, or keys, a trackball, or a touchpad provided on the electronic device housing, or an external keyboard, touchpad, or mouse.

[0076] Those skilled in the art will understand that Figure 4The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the electronic device to which the solution of the present application is applied. The specific electronic device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0077] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0078] In one embodiment, a computer program product is provided, comprising a computer program, which implements the steps performed by a processor of an electronic device when the computer program is executed by a processor.

[0079] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0080] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the above-mentioned embodiments. In particular, any reference to memory, database, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The databases involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the various embodiments provided herein may be, but are not limited to, general-purpose processors, central processing units (CPUs), graphics processing units (GPUs), digital signal processors (DSPs), compilable logic units, and the like.

[0081] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0082] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. An operation and maintenance management method, characterized in that: The method comprises: Acquiring operation and maintenance data in the power system; wherein the operation and maintenance data includes at least one of network dimension data, work specification dimension data, and power dimension data; A multi-task prediction model is used to perform anomaly detection on the operation and maintenance data to obtain a health assessment result; wherein the multi-task prediction model includes an expert network and a prediction network; the expert network includes at least one shared expert network and multiple private expert networks; the shared expert network is used to perform feature extraction and fusion processing on the operation and maintenance data to obtain a global feature vector; the private expert network is used to perform feature processing on the operation and maintenance data corresponding to a specific scenario and / or a specific task to obtain a local feature vector; the prediction network is used to detect a target feature vector obtained by fusion of the global feature vector and the local feature vector to obtain the health assessment result; Evaluate and analyze the operation and maintenance quality based on the operation and maintenance data to obtain a target operation and maintenance evaluation result; Determine a target comprehensive result based on the health assessment result and the target operation and maintenance assessment result.

2. The method according to claim 1, characterized in that The obtaining of operation and maintenance data in the power system includes: Acquiring original operation and maintenance data in the power system; Performing data cleaning on the original operation and maintenance data using an interpolation method, an average value filling method, and / or a deletion method to obtain first data; performing outlier identification on the first data to obtain second data; Perform data standardization processing on the second data to obtain the operation and maintenance data.

3. The method according to any one of claims 1 or 2, characterized in that The evaluating and analyzing the operation and maintenance quality based on the operation and maintenance data to obtain a target operation and maintenance evaluation result includes: Assigning an initial weight to the operation and maintenance data of each dimension based on preset rules; Determine the importance score of the operation and maintenance data in each dimension based on the operation and maintenance goals in the current scenario; According to the importance score, updating the initial weight of the operation and maintenance data to obtain a real-time weight; The target operation and maintenance evaluation result is obtained according to the evaluation score of the operation and maintenance data of each dimension and the corresponding real-time weight.

4. The method according to claim 3, characterized in that The method further comprises: Obtain real-time operation and maintenance assessment results within a predetermined time window; Calculating a weight optimization factor based on the real-time operation and maintenance evaluation results; Determine the evaluation deviation based on the comparison of the real-time operation and maintenance evaluation result with the weight optimization factor; Updating the real-time weight according to the evaluation deviation and the weight optimization factor to obtain an updated real-time weight; The target operation and maintenance evaluation result is recalculated based on the evaluation score of the operation and maintenance data in each dimension and the corresponding updated real-time weight.

5. The method according to claim 4, characterized in that The calculation expression of the weight optimization factor is as follows: ； in, Indicate the starting time of the predetermined time window; Indicate the end time of the predetermined time window; Indicates the real-time weight corresponding to the k-th dimension; Indicates the real-time operation and maintenance evaluation result of the operation and maintenance data of the kth dimension at time t.

6. The method according to any one of claims 1 or 2, characterized in that The multi-task detection model also includes a gating network; wherein the gating network is used to obtain the weight coefficient corresponding to each feature vector based on the global feature vector and / or the local feature vector; the expert network connects multiple gating networks; and the gating network is connected to the prediction network in a one-to-one correspondence.

7. The method according to claim 1, characterized in that The method further comprises: In response to a request to view the operation and maintenance evaluation interface, display the operation and maintenance evaluation interface; wherein the operation and maintenance evaluation interface is used to display detailed information of the operation and maintenance data in the power system; the operation and maintenance evaluation interface includes an operation and maintenance evaluation option; When a trigger operation for the operation and maintenance evaluation option is received, the target comprehensive result is output on the operation and maintenance evaluation interface in at least one of a chart form and a report form, and / or the target comprehensive result is sent to a third-party terminal.

8. An operation and maintenance management device, characterized in that: The device comprises: An acquisition module, configured to acquire operation and maintenance data in the power system; wherein the operation and maintenance data includes at least one of network dimension data, work specification dimension data, and power dimension data; A health assessment module is configured to use a multi-task prediction model to perform anomaly detection on the operation and maintenance data to obtain a health assessment result; wherein the multi-task prediction model includes an expert network and a prediction network; the expert network includes at least one shared expert network and multiple private expert networks; the shared expert network is configured to perform feature extraction and fusion processing on the operation and maintenance data to obtain a global feature vector; the private expert network is configured to perform feature processing on the operation and maintenance data corresponding to a specific scenario and / or specific task to obtain a local feature vector; the prediction network is configured to detect a target feature vector obtained by fusion of the global feature vector and the local feature vector to obtain the health assessment result; A quality assessment module is used to evaluate and analyze the operation and maintenance quality based on the operation and maintenance data to obtain a target operation and maintenance assessment result; The determination module is used to determine the target comprehensive result based on the health assessment result and the target operation and maintenance assessment result.

9. An electronic device, characterized in that: The method comprises a processor and a memory for storing a computer program of the processor; wherein the processor is configured to implement the method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images