Centralized control system event processing rule standardization matching method and system

Abstract

The invention relates to the technical field of power system automation, in particular to a centralized control system event processing rule standardization matching method and system, and the method comprises the steps: obtaining event alarm information, and generating an event feature value based on the event alarm information; obtaining a plurality of event processing rules matched with the event characteristic value based on an expert knowledge base, and performing sorting recommendation on each event processing rule according to a recommendation index of each event processing rule; constructing an event handling scene based on the event handling rule, wherein the event handling scene comprises a visual event handling action process; based on the event handling scene, executing a corresponding event handling action process; each handling action in the event handling action process is used for triggering and executing a corresponding specific action event and automatically recording a handling process event. According to the invention, through standardized matching and automatic processing, the standardization and efficiency of transformer substation event processing are effectively improved.

Description

Technical Field

[0001] This invention relates to the field of power system automation technology, specifically to a standardized matching method and system for event-based handling rules in a centralized control system. Background Technology

[0002] With the continuous advancement of smart grid construction, the types and quantities of primary and secondary equipment connected to substation centralized control systems are growing exponentially. The real-time alarm information generated by the system has jumped from "hourly" to "second-level" or even "millisecond-level." These alarm messages are characterized by event-driven, fragmented, and highly semantically dense information. They include critical events such as protection actions, monitoring and control anomalies, and communication interruptions, as well as a large number of repetitive, jittery, or cascading redundant signals. Traditional handling methods rely on operators' experience to identify each alarm individually, manually formulate, and execute handling measures, which has the following prominent drawbacks: 1. High dependence on manual intervention: Operators need to perform semantic analysis, causal reasoning, and risk rating of multi-source heterogeneous alarms within a very short time. Differences in experience directly lead to misjudgments, missed judgments, or delays in handling, especially during night shifts or shift handover periods when the risk is higher. 2. Inconsistent handling rules: Existing operating procedures are mostly textual and itemized descriptions, lacking calculable and quantifiable execution templates. The same event may trigger drastically different handling procedures in different shifts and different substations, resulting in a lack of standards and difficulties in tracing responsibility. 3. Lengthy information processing chain: Manual recording, telephone reporting, OMS reporting, and defect order circulation are fragmented, requiring repeated data entry and format conversion, resulting in excessively long average processing time and low overall efficiency. 4. Insufficient intelligent support: Early automation attempts mostly focused on simple threshold comparisons or regular expression matching, failing to extract deep semantics from multi-dimensional features such as alarm text, time-series waveforms, and topological structures; the expert knowledge base is primarily based on static rules, lacking dynamic update mechanisms based on cases, graphs, or reinforcement learning, leading to simplistic recommendation results and uninterpretable confidence levels; and actions still rely on manual triggering of each action on the SCADA / OMS interface, making it difficult to form a closed loop of "perception-decision-execution-feedback."

[0003] Existing technologies have attempted to optimize incident handling processes through automation, but the following bottlenecks still exist: Insufficient feature extraction dimensions: The accuracy of entity recognition and event relationship extraction in unstructured alarm text is low, making it difficult to accurately identify key event features. For example, it cannot effectively distinguish between signals with similar semantics such as "protection action" and "protection device malfunction" but with completely different handling paths.

[0004] The knowledge base matching is coarse-grained: the matching mechanism of the expert knowledge base is not intelligent enough, and it cannot dynamically generate multiple sets of handling rules and provide recommendation indices. For example, the rules are mostly described by "keyword + equipment type" tuples, lacking contextual modeling of power grid topology, operating mode, meteorological environment, etc., resulting in insufficient executability of the recommended solutions.

[0005] Lack of Standards in Disposal Scenario Orchestration: The construction of disposal scenarios and the triggering of actions lack standardized and automated support, making it difficult to achieve efficient management of the entire process. For example, it is impossible to achieve automatic orchestration, version management, and effect evaluation of disposal scripts across heterogeneous systems. Summary of the Invention

[0006] The purpose of this invention is to provide a standardized matching method and system for event-based handling rules in a centralized control system in order to solve at least one of the above-mentioned technical problems. This method and system can deeply integrate natural language processing, knowledge graph and process orchestration technologies to improve the reliability of substation operation, reduce human error, and meet the urgent need for an "unmanned operation + centralized monitoring" mode.

[0007] The present invention achieves the above objectives through the following technical solutions: A standardized matching method for event-based handling rules in a centralized control system includes: Acquire event-based alarm information and generate event feature values ​​based on the event-based alarm information; Based on the expert knowledge base, multiple event handling rules matching the event feature values ​​are obtained, and the event handling rules are ranked and recommended according to the recommendation index of each event handling rule. An event handling scenario is constructed based on the event handling rules, and the event handling scenario includes a visualized event handling action flow; Based on the event handling scenario, the corresponding event handling action flow is executed; each handling action in the event handling action flow is used to trigger the execution of the corresponding specific action event, and the handling process event is automatically recorded.

[0008] Furthermore, generating event feature values ​​based on the event-based alarm information includes: The event-based alarm information is segmented and part-of-speech tagging is performed. Keywords are identified based on part-of-speech tagging results, and feature values ​​are extracted from these keywords. The feature values ​​are mapped to a predefined standardized feature library to generate event feature values ​​in a structured data format.

[0009] Furthermore, the expert knowledge base includes: historical event handling rules, equipment operation specifications, and an expert experience database; The expert knowledge base is dynamically updated based on automatically recorded events during the handling process.

[0010] Furthermore, the recommendation index of the event handling rules is calculated based on the applicability of the event handling rules, historical success rate, and expert scores. The rules for handling each incident are ranked and recommended based on their recommendation indices, including: The top three event handling rules based on the recommendation index are recommended in descending order of scores, or all event handling rules with recommendation indices higher than the recommendation threshold are recommended in descending order of scores.

[0011] Furthermore, each node corresponding to the event handling action flow is equipped with a node status indicator for displaying progress.

[0012] Furthermore, the node status identifier includes: "Not Started", "In Progress", and "Completed".

[0013] Furthermore, the event handling scenario also includes: a handling button for human interaction; Operators can execute corresponding actions by clicking the appropriate action button.

[0014] Furthermore, the processing buttons include function buttons for triggering monitoring log recording, defect information reporting, telephone dialing, and SMS sending.

[0015] A standardized matching system for event-based handling rules in a centralized control system, comprising: The alarm information processing module is used to acquire event-based alarm information and generate event feature values ​​based on the event-based alarm information. The rule matching module is used to obtain multiple event handling rules that match the event feature values ​​based on the expert knowledge base, and to rank and recommend each event handling rule according to the recommendation index of each event handling rule; The scenario building module is used to build event handling scenarios based on the event handling rules, and the event handling scenarios include a visualized event handling action flow; The handling execution module is used to execute the corresponding event handling action flow based on the event handling scenario; each handling action in the event handling action flow is used to trigger the execution of the corresponding specific action event and automatically record the handling process events.

[0016] An electronic device includes a processor, a memory, and a computer program stored in the memory and running on the processor, wherein when the computer program is executed by the processor, it implements the standardized matching method for event-based handling rules of a centralized control system as described above.

[0017] The beneficial effects of this invention are as follows: This invention automates the semantic parsing and rule matching of alarm information through deep integration of natural language processing and knowledge graphs. The semantic fit calculation model combines historical success rate and expert ratings into a three-dimensional recommendation index, improving the efficiency of optimal rule identification and significantly reducing manual screening costs.

[0018] This invention constructs a visual, node-based process engine that transforms complex rules into executable, standardized action sequences. Through status indicators and dynamic progress feedback mechanisms, it enhances the transparency of the process, ensures consistency across shifts, and reduces the rate of errors.

[0019] This invention integrates a one-click handling button and achieves automated management of event handling through direct connection technology to the background service. This includes status identification, event recording, progress display, and one-click triggering, significantly reducing manual workload and improving handling efficiency.

[0020] This invention features a customized expert knowledge base tailored to the characteristics of substation equipment. It integrates the IEC 61850 standard communication protocol with the D5000 platform data specifications, enabling seamless integration with existing centralized control systems. Based on real-time recording of events during the handling process and a dynamic knowledge graph update mechanism, it forms a "handling-feedback-optimization" closed loop, ensuring the accuracy of rule matching and enhancing adaptability to complex scenarios.

[0021] This invention, through the integration and innovation of multiple technologies, constructs a complete technical system from intelligent sensing to automatic execution, breaks through the efficiency bottleneck of traditional manual handling mode, and provides a standardized and intelligent centralized control and handling solution for the construction of new power systems, with significant economic benefits and social value. Attached Figure Description

[0022] Figure 1 This is a schematic diagram of a standardized matching method for event-based handling rules in a centralized control system according to one embodiment of the present invention; Figure 2 This is a schematic diagram of the standardized matching method for event-based handling rules in a centralized control system according to another embodiment of the present invention; Figure 3 This is a schematic diagram of the standardized matching system structure for event-based handling rules in a centralized control system according to one embodiment of the present invention. Detailed Implementation

[0023] The invention will now be discussed with reference to exemplary embodiments. It should be understood that the described embodiments are merely intended to enable those skilled in the art to better understand and thus implement the invention, and are not intended to imply any limitation on the scope of the invention.

[0024] As used herein, the term "comprising" and its variations are to be interpreted as open-ended terms meaning "including but not limited to". The term "based on" is to be interpreted as "at least partially based on". The terms "one embodiment" and "an embodiment" are to be interpreted as "at least one embodiment".

[0025] Example 1 Figure 1 This is a schematic diagram of a standardized matching method for event-based handling rules in a centralized control system according to one embodiment of the present invention. Figure 1 As shown, according to one embodiment of the present invention, a standardized matching method for event-based handling rules in a centralized control system includes the following steps: Step S102: Obtain event-based alarm information and generate event feature values ​​based on the event-based alarm information; Step S104: Based on the expert knowledge base, obtain multiple event handling rules that match the event feature values, and rank and recommend each event handling rule according to the recommendation index of each event handling rule; Step S106: Construct an event handling scenario based on the event handling rules. The event handling scenario includes a visualized event handling action flow. Step S108: Based on the event handling scenario, execute the corresponding event handling action flow; each handling action in the event handling action flow is used to trigger the execution of the corresponding specific action event, and the handling process event is automatically recorded.

[0026] In this implementation, the centralized control system first captures event-based alarm information such as "transformer oil temperature too high" in real time through the I-zone interface. It then uses an NLP engine to perform word segmentation, part-of-speech tagging, and keyword extraction. Next, it maps "transformer / oil temperature / too high" into structured event feature values ​​<equipment type=01, alarm type=OT_HIGH> according to a pre-set standardized feature library. Subsequently, the rule engine intelligently matches the event feature value with a dynamic expert knowledge base containing historical rules, equipment specifications, and expert experience. It automatically generates multiple event handling rules and calculates the recommendation index in real time based on applicability, historical success rate, and expert scores. The top three rules are then pushed to the operators in descending order of scores. Operators select the event handling rules with the highest recommendation index to construct a visualized event handling scenario: The event handling scenario presents a node-based action sequence in the form of a flowchart. Each node is bound to a specification description, required parameters, and a three-color status light indicating "not started / in progress / completed". Operators can click on the node button to trigger specific action events such as writing monitoring logs, reporting defects, automatic dialing, or SMS notifications. The action execution results and process data are written back in real time and used to incrementally update the knowledge base, forming a closed-loop optimization and significantly improving the standardization and efficiency of substation event handling.

[0027] This invention achieves standardized and streamlined execution and closed-loop optimization of incident handling actions through structured feature extraction, dynamic matching and recommendation from an expert knowledge base, and construction of a visualized handling scenario, significantly improving the standardization and efficiency of substation incident handling.

[0028] According to one embodiment of the present invention, in step S102, generating event feature values ​​based on event-based alarm information includes: Event-based alarm information is segmented into words and tagged with parts of speech. Keyword identification is based on part-of-speech tagging results, and feature values ​​are extracted from the keywords. The feature values ​​are mapped to a predefined standardized feature library to generate event feature values ​​in a structured data format.

[0029] In this implementation, the received event-based alarm text, such as "transformer oil temperature too high," is first segmented into words to obtain the sequence "transformer / n, oil temperature / n, too high / a." Then, part-of-speech tags are used to filter out effective words such as nouns and adjectives, and a domain dictionary is used to identify keywords such as "transformer," "oil temperature," and "too high" as potential business entities and attributes. Next, these keywords are converted into raw feature values ​​of "equipment type = transformer, alarm type = oil temperature too high" using a keyword-feature mapping table. Finally, the raw feature values ​​are input into a predefined standardized feature library, where synonym merging, numerical range normalization, and encoding mapping are performed, outputting a unified structured event feature value.<DEV_TYPE=01, ALARM_CODE=OT_HIGH> This process ensures that regardless of the differences in the alarm text, the system can obtain a unique and computable feature vector, providing consistent and high-precision input for subsequent rule matching and scene construction.

[0030] This invention transforms event-based alarm information with different expressions into unique, structured feature vectors through word segmentation, part-of-speech tagging, keyword extraction, and standardized feature mapping, providing consistent and high-precision input for subsequent rule matching and scene construction.

[0031] According to one embodiment of the present invention, the expert knowledge base in step S104 includes: historical event handling rules, equipment operation specifications, and expert experience base; The expert knowledge base is dynamically updated based on automatically recorded events in the handling process.

[0032] In this implementation, the expert knowledge base consists of three complementary data sources: a historical event handling rule base, which stores the complete chain of alarm-rule-result; an equipment operation specification base, which solidifies manufacturer technical conditions and industry safety thresholds; and an expert experience base, which includes unstructured experience from senior operators. Each time the system completes an event loop, it logs the handling process events, including "action sequence, time consumption, success rate, and manual correction opinions." When the success rate of a rule falls below a threshold within a preset time window, or when new expert correction opinions appear, an update condition is triggered. At this time, the update engine automatically recalculates the recommendation index of the rule, splits / merges action nodes when necessary, and synchronously writes them to the corresponding three-layer sub-bases, ensuring that the knowledge base evolves in real time with on-site practice, continuously improving subsequent matching accuracy and handling efficiency.

[0033] The expert knowledge base of this invention integrates three data sources: historical event handling rules, equipment operation specifications, and expert experience. It also dynamically updates the rule recommendation index and action nodes in real time based on the events during the handling process, continuously optimizing the accuracy of the knowledge base and effectively improving the accuracy of subsequent rule matching and the efficiency of event handling.

[0034] According to one embodiment of the present invention, the recommendation index of the event handling rules in step S104 is calculated based on the applicability of the event handling rules, historical success rate and expert scores. The rules for handling each incident are ranked and recommended based on their recommendation indices, including: The top three event handling rules are recommended in descending order of score, or all event handling rules with a recommendation index higher than the recommendation threshold are recommended in descending order of score.

[0035] In this embodiment, in step S104, a recommendation index is calculated in real time for each candidate event handling rule. The recommendation index is derived from multiple weighted factors: the semantic fit between the event handling rule and the current event feature value (applicability weight 0.4), the successful handling ratio of the event handling rule in similar historical events (historical success rate weight 0.4), and the confidence score given by senior operators or algorithm experts (expert score weight 0.2). After calculation, the rules are sorted in descending order of score and a configurable recommendation strategy is adopted: if "simplified mode" is enabled, only the top three rules with the highest scores are pushed to operators; if "comprehensive mode" is enabled, all rules with scores higher than the preset recommendation threshold (e.g., 80 points) are pushed. Both modes support online threshold adjustment to ensure that information overload is avoided while not missing potential best solutions with high scores but slightly lower rankings, thereby ensuring recommendation quality while taking into account human-computer interaction efficiency.

[0036] This invention calculates a recommendation index by weighting applicability, historical success rate, and expert ratings. It combines two configurable recommendation modes, namely simplified and comprehensive, and dynamically adjusts the threshold to improve human-computer interaction efficiency while ensuring recommendation quality and avoiding information overload and the omission of potential best solutions.

[0037] According to one embodiment of the present invention, each node of an event handling action flow is provided with a node status indicator for displaying progress.

[0038] Preferably, the node status identifier includes: "Not Started", "In Progress", and "Completed".

[0039] Preferably, the event handling scenario further includes: a handling button for human interaction; Operators can execute corresponding actions by clicking the appropriate action button.

[0040] Preferably, the action buttons include function buttons for triggering monitoring log recording, defect information reporting, telephone dialing, and SMS sending.

[0041] In this implementation, the incident handling scenario provides operators with a visual, interactive, closed-loop operation interface: node-based action flows are automatically generated based on the current incident handling rules. Each node is bound to a three-color status indicator ("Not Started - In Progress - Completed"), providing real-time feedback on execution progress to prevent omissions. Clickable handling buttons are configured next to each node, with button functions directly connected to the backend service—clicking the "Monitoring Log" button instantly writes timestamped operational data; clicking the "Defect Reporting" button automatically pops up a pre-filled defect form; clicking the "Phone Dialing" or "SMS Sending" button invokes the softswitch / SMS gateway to complete one-click outbound calls or group messages, all without requiring manual system switching. To prevent accidental operation, the buttons are only available when the node status is "Not Started" or "In Progress," and are automatically grayed out and the result is written back after the status changes to "Completed," ensuring both the rigor of the process and significantly shortening incident handling time.

[0042] This invention provides real-time feedback on execution progress through a visualized node-based action flow and three-color status indicators. It combines one-click triggering of monitoring log recording, defect reporting, automatic dialing / SMS notification and other function buttons, and automatically disables completed node buttons to prevent accidental operation. It eliminates the need for manual system switching, significantly shortens event handling time and improves process standardization and operational rigor.

[0043] Example 2 Figure 2 This is a schematic diagram of a standardized matching method for event-based handling rules in a centralized control system, according to another embodiment of the present invention. Figure 2 As shown, according to one embodiment of the present invention, a standardized matching method for event-based handling rules in a centralized control system includes the following steps: Step S201: Acquisition of event-based alarm information and extraction of event feature values; Event-based alarm information is acquired in real time from the centralized control system of Substation Zone I. This information is then processed using semantic analysis techniques, including word segmentation, part-of-speech tagging, keyword extraction, and feature value mapping, to extract the feature value events of the event-based alarm information. Specifically, this includes: Step 1, Data Acquisition: Obtain event-based alarm information in real time from the substation's Zone I centralized control system, such as "transformer oil temperature too high" and "circuit breaker tripped".

[0044] Step two, semantic analysis: taking "transformer oil temperature too high" as an example, (1) Perform word segmentation on event-based alarm information, such as “transformer / oil temperature / too high”.

[0045] (2) Perform part-of-speech tagging and identify keywords (such as "transformer" and "oil temperature").

[0046] (3) Extract feature value events, such as "Equipment type: Transformer" and "Alarm type: Oil temperature too high".

[0047] (4) Event feature value mapping: The extracted feature values ​​are mapped to a predefined standardized feature library to generate structured data, which is convenient for subsequent matching.

[0048] Step S202: Intelligent matching and rule generation; The extracted event feature values ​​are intelligently matched with an expert knowledge base, which includes historical event handling rules, equipment operation specifications, and expert experience. Based on the matching results, multiple event handling rules are automatically generated, and a recommendation index is assigned to each rule. The recommendation index is calculated based on the rule's applicability, historical success rate, and expert ratings. Specifically, this includes: Step 1: Accessing the Expert Knowledge Base: This step involves accessing the expert knowledge base, which includes historical event handling rules, equipment operation specifications, and expert experience. For example, for the "transformer oil temperature too high" event, the knowledge base might contain rules such as "check the cooling system" and "reduce the load."

[0049] Step two, intelligent matching: The extracted event feature values ​​are matched with rules in the expert knowledge base. For example, rules related to the event "transformer oil temperature too high" are matched.

[0050] Step 3: Event handling rule generation and recommendation index calculation: Automatically generate multiple event handling rules, for example: (1) Rule 1: Check the cooling system, recommendation index 90; (2) Rule 2: Reduce transformer load, recommended index 85; (3) Rule 3: Notify maintenance personnel, recommendation index 80.

[0051] The recommendation index is calculated based on the applicability of the rules, historical success rate, and expert ratings.

[0052] Step S203: Event handling scenario construction and action generation; Based on the handling rules with the highest recommendation index, an incident handling scenario is constructed for operational personnel. The incident handling scenario includes a visual display of the handling process, standardized descriptions of handling actions, and automated triggering of specific action events. Standardized handling actions are generated for each node of the handling process, and specific action events can be triggered. Specifically, this includes: Step 1, Event Scenario Construction: Select the event handling rule with the highest recommendation index (such as rule 1: check the cooling system) to construct the event handling scenario.

[0053] Incident handling scenarios include a visual representation of the process, such as a flowchart showing "Check the cooling system → Confirm the status of the cooling system → Record the inspection results".

[0054] Step 2, Action Generation: Generate standardized handling actions for each process node, for example: (1) Node 1: Check the cooling system and generate the action "Check the cooling system operating status"; (2) Node 2: Confirm the status of the cooling system and generate the action "Record Cooling System Parameters"; (3) Node 3: Record the inspection results and generate the action "Fill in the inspection report".

[0055] Step 3, Action Event Triggering: Supports automated triggering of specific action events, such as automatically generating monitoring logs, triggering the defect reporting system, etc.

[0056] Step S204: Incident handling and process management; Incident handling is conducted based on the constructed incident handling scenarios. The handling process and nodes are marked with handling status indicators (such as "Not Started," "In Progress," and "Completed"), which automatically records incidents during the handling process and displays the handling progress in real time. Operators can trigger operations such as monitoring log recording, defect reporting, making phone calls, and sending SMS messages with a single click, thereby reducing the workload of manual information collection, reporting, and data entry, and improving handling efficiency. Specifically, this includes: Step 1: Execution of the handling process: Operators carry out incident handling work according to the handling scenario. The process nodes are equipped with status indicators (such as "Not Started", "In Progress", "Completed"), and the handling progress is displayed in real time.

[0057] Step 2, Automatic Recording and Feedback: (1) Automatically record events during the handling process, such as "cooling system check completed, parameters normal".

[0058] (2) Operators can trigger related operations with a single click by clicking on the action, for example: Clicking "View Cooling System Operating Status" triggers monitoring log recording; Click "Fill in Inspection Report" to trigger the defect reporting system; Clicking "Notify maintenance personnel" will trigger a phone call or text message.

[0059] Step 3, Feedback on handling results: After the handling is completed, the system automatically generates a handling report and updates the expert knowledge base to provide a reference for subsequent event handling.

[0060] This embodiment proposes a standardized matching method for event-based handling rules in a centralized control system, achieving intelligent handling of alarm events through a four-layer architecture. First, based on real-time collection of event-based alarm information such as "transformer oil temperature too high" by the substation's Zone I centralized control system, deep processing is performed using semantic analysis technology: a word segmentation algorithm is used to decompose the alarm text into semantic units such as "transformer / oil temperature / too high," and part-of-speech tagging is used to identify core equipment parameters such as "transformer" and "oil temperature," thereby extracting structured feature values ​​such as "equipment type: transformer" and "alarm type: oil temperature too high," and mapping them to a predefined feature library. Second, an expert knowledge base system is constructed, integrating historical handling rules, equipment operation specifications, and expert experience to form a knowledge graph. When a feature value matches the "transformer oil temperature too high" event, the system automatically retrieves candidate rules such as "check the cooling system" and "reduce the load." A recommendation index is generated by comprehensively evaluating the rule's applicability, historical handling success rate, and expert scores (e.g., rule 1: check the cooling system, recommendation index 90). The third step involves constructing a handling scenario based on the highest recommendation index rule, generating a visualized handling path that includes the process of "checking the cooling system → confirming the status → recording the results." Each node corresponds to a standardized handling action (e.g., node 1 generates the action of "checking the cooling system's operating status"), and supports automated triggering of monitoring log recording, defect reporting, and other operations. The fourth step is to achieve full-cycle control through the handling process management system, setting "not started / in progress / completed" status indicators. Operators can click on the handling action to complete monitoring log recording, SMS notification, and other operations with one click. After the handling is completed, the system automatically generates a report and updates the knowledge base.

[0061] This invention achieves a dual improvement in the efficiency and accuracy of alarm handling through the deep integration of semantic analysis technology and an expert knowledge base. In practical applications, the handling time for "transformer oil overheating" events has been reduced from 30 minutes in the traditional mode to 10 minutes, significantly improving efficiency. A recommendation index-based quantitative evaluation mechanism ensures that core handling rules with a historical success rate of over 90% are prioritized, significantly reducing the risk of human error. The system's built-in standardized handling action templates reduce the number of steps required by operators, while automatically recorded handling process data provides continuous optimization data for the knowledge base, forming a closed-loop management system of "handling-feedback-improvement." This invention is particularly suitable for scenarios requiring high-frequency, standardized handling, such as power control stations and intelligent operation and maintenance, effectively solving problems such as delayed response, non-standardized operation, and strong reliance on experience inherent in traditional manual handling methods.

[0062] Example 3 Figure 3 This is a schematic diagram of the standardized matching system structure for event-based handling rules in a centralized control system, according to one embodiment of the present invention. Figure 3 As shown, according to one embodiment of the present invention, a standardized matching system for event-based handling rules in a centralized control system includes: The alarm information processing module is used to acquire event-based alarm information and generate event feature values ​​based on the event-based alarm information; The rule matching module is used to obtain multiple event handling rules that match the event feature values ​​based on the expert knowledge base, and to rank and recommend each event handling rule according to the recommendation index of each event handling rule. The scenario building module is used to build event handling scenarios based on event handling rules. The event handling scenarios include a visualized event handling action flow. The event handling execution module is used to execute the corresponding event handling action flow based on the event handling scenario; each handling action in the event handling action flow is used to trigger the execution of the corresponding specific action event, and the handling process events are automatically recorded.

[0063] This embodiment proposes a standardized matching system for event-based handling rules in a centralized control system. The alarm information processing module captures text alarms from the centralized control system of substation zone I in real time through a standard interface. It first segments the alarms into words, tags them with part-of-speech tags, and maps them to a standardized feature library, outputting structured event feature values. The rule matching module sends these feature values ​​into an expert knowledge base composed of historical rules, equipment specifications, and expert experience. Using a weighted algorithm (e.g., 40% applicability, 40% historical success rate, and 20% expert score), it instantly generates multiple event handling rules and pushes them in descending order of recommendation index. The scenario construction module then generates a visual event handling scenario based on the highest-scoring rule. The scenario is presented as a node flowchart, with each node carrying a three-color status indicator: "Not Started - In Progress - Completed". The handling execution module drives this process. Operators can trigger the writing of monitoring logs, defect reporting, telephone dialing, or SMS sending with one click by clicking the handling button next to the node. The system synchronously records the events in the handling process and writes them back to the knowledge base, realizing closed-loop updates and efficient and standardized event handling.

[0064] This invention is not only applicable to substations but can also be extended to other power system scenarios, such as distribution networks and power plants. By continuously accumulating case studies and expert experience, and dynamically updating the expert knowledge base, matching accuracy is improved. This invention achieves standardized matching of event-based handling rules in centralized control systems, featuring high efficiency, standardization, and intelligence, and can be widely applied in the field of power system automation.

[0065] According to one embodiment of the present invention, an electronic device includes a processor, a memory, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, it implements the standardized matching method for event-based handling rules of any centralized control system of the present invention.

[0066] According to one embodiment of the present invention, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, it implements the standardized matching method for event-based handling rules of any centralized control system of the present invention.

[0067] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and media described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0068] The above description is merely a preferred embodiment of this application and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of the invention involved in this application is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the inventive concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features with similar functions disclosed in this application.

[0069] It should be understood that the sequence number of each step in the invention and embodiments of the present invention does not absolutely imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

Claims

1. A standardized matching method for event-based handling rules in a centralized control system, characterized in that, include: Acquire event-based alarm information and generate event feature values ​​based on the event-based alarm information; Based on the expert knowledge base, multiple event handling rules matching the event feature values ​​are obtained, and the event handling rules are ranked and recommended according to the recommendation index of each event handling rule. An event handling scenario is constructed based on the event handling rules, and the event handling scenario includes a visualized event handling action flow; Based on the event handling scenario, the corresponding event handling action flow is executed; each handling action in the event handling action flow is used to trigger the execution of the corresponding specific action event, and the handling process event is automatically recorded.

2. The standardized matching method for event-based handling rules in a centralized control system according to claim 1, characterized in that, Based on the event-based alarm information, event feature values ​​are generated, including: The event-based alarm information is segmented and part-of-speech tagging is performed. Keywords are identified based on part-of-speech tagging results, and feature values ​​are extracted from these keywords. The feature values ​​are mapped to a predefined standardized feature library to generate event feature values ​​in a structured data format.

3. The standardized matching method for event-based handling rules in a centralized control system according to claim 1, characterized in that, The expert knowledge base includes: historical event handling rules, equipment operation specifications, and expert experience database; The expert knowledge base is dynamically updated based on automatically recorded events during the handling process.

4. The standardized matching method for event-based handling rules in a centralized control system according to claim 1, characterized in that: The recommendation index for the event handling rules is calculated based on the applicability of the event handling rules, historical success rate, and expert scores. The rules for handling each incident are ranked and recommended based on their recommendation indices, including: The top three event handling rules based on the recommendation index are recommended in descending order of scores, or all event handling rules with recommendation indices higher than the recommendation threshold are recommended in descending order of scores.

5. The standardized matching method for event-based handling rules in a centralized control system according to claim 1, characterized in that: Each node in the event handling process is equipped with a node status indicator to display progress.

6. The standardized matching method for event-based handling rules in a centralized control system according to claim 5, characterized in that, The node status identifiers include: "Not Started", "In Progress", and "Completed".

7. The standardized matching method for event-based handling rules in a centralized control system according to claim 5, characterized in that: The event handling scenario also includes: a handling button for human interaction; Operators can execute corresponding actions by clicking the appropriate action button.

8. The standardized matching method for event-based handling rules in a centralized control system according to claim 7, characterized in that: The action buttons include function buttons for triggering monitoring log recording, defect information reporting, telephone dialing, and SMS sending.

9. A standardized matching system for event-based handling rules in a centralized control system, characterized in that, include: The alarm information processing module is used to acquire event-based alarm information and generate event feature values ​​based on the event-based alarm information. The rule matching module is used to obtain multiple event handling rules that match the event feature values ​​based on the expert knowledge base, and to rank and recommend each event handling rule according to the recommendation index of each event handling rule; The scenario building module is used to build event handling scenarios based on the event handling rules, and the event handling scenarios include a visualized event handling action flow; The handling execution module is used to execute the corresponding event handling action flow based on the event handling scenario; each handling action in the event handling action flow is used to trigger the execution of the corresponding specific action event and automatically record the handling process events.

10. An electronic device, characterized in that, It includes a processor, a memory, and a computer program stored in the memory and running on the processor, wherein when the computer program is executed by the processor, it implements the standardized matching method for event-based handling rules of a centralized control system as described in any one of claims 1-8.

Images