Power grid emergency command information processing method and device, computer equipment, readable storage medium and program product

Abstract

The invention relates to a power grid emergency command information processing method and device, computer equipment, a computer readable storage medium and a computer program product, relates to the technical field of data processing, and can improve the emergency command processing efficiency. The method comprises the following steps: acquiring emergency data from a plurality of power grid service information systems; fusing the emergency data according to the service processing logic of the plurality of power grid service information systems to obtain comprehensive emergency situation information of the current emergency event; performing risk prediction analysis on the comprehensive emergency situation information by using a preset machine learning model to obtain a risk prediction result of the current emergency event; the risk prediction result comprises an affected area, a user influence range and a power grid equipment damage condition; determining a target emergency strategy from preset emergency strategies based on the comprehensive emergency situation information and the risk prediction result; and displaying the emergency special report including the comprehensive emergency situation information, the risk prediction result and the target emergency strategy.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, and in particular to a power grid emergency command information processing method and device, computer equipment, computer readable storage medium and computer program product. BACKGROUND

[0002] The current power grid emergency command technology has attempted to integrate multi-service system data and automatically collect.

[0003] However, in practical applications, these technical solutions still have significant limitations. Since the emergency-related data is stored in multiple heterogeneous information systems, and part of the key information still relies heavily on manual layer-by-layer reporting, the information obtained by the emergency command center often has the problems of delay, inaccuracy and even mutual contradiction, thereby making the efficiency low when relying on emergency data for emergency command. SUMMARY

[0004] Therefore, it is necessary to provide a power grid emergency command information processing method, device, computer equipment, computer readable storage medium and computer program product to solve the above technical problems.

[0005] In a first aspect, the present application provides a power grid emergency command information processing method, comprising:

[0006] obtaining emergency data from multiple power grid service information systems;

[0007] According to the business processing logic of the multiple power grid service information systems, the emergency data is fused to obtain comprehensive emergency situation information of the current emergency event;

[0008] Using a preset machine learning model, the comprehensive emergency situation information is analyzed to obtain a risk prediction result of the current emergency event; the risk prediction result includes a disaster area, a user influence range and a power grid equipment damage situation;

[0009] Based on the comprehensive emergency situation information and the risk prediction result, a target emergency strategy is determined from a preset emergency strategy;

[0010] An emergency special report including the comprehensive emergency situation information, the risk prediction result and the target emergency strategy is displayed.

[0011] In one embodiment, the preset emergency strategy includes a resource allocation strategy; and determining the target emergency strategy from the preset emergency strategy based on the comprehensive emergency situation information and the risk prediction result comprises:

[0012] Based on the risk prediction result, the risk levels of different disaster areas in the current emergency event are determined;

[0013] According to the comprehensive emergency situation information and the risk level, a resource allocation strategy matched with different disaster areas is determined;

[0014] The matched resource allocation strategy is determined as the target emergency strategy.

[0015] In one of the embodiments, after the emergency special report including the comprehensive emergency situation information, the risk prediction result and the target emergency strategy is displayed, the method further includes:

[0016] The emergency special report is fed back to a user through a preset reminding mode, and the emergency special report is saved to a database;

[0017] According to the saved emergency special report, an emergency disposal efficiency when the target emergency strategy in the emergency special report is processed according to the risk prediction result is determined;

[0018] Based on the emergency disposal efficiency, the preset emergency strategy is updated to obtain an updated preset emergency strategy.

[0019] In one of the embodiments, the risk prediction analysis on the comprehensive emergency situation information by using the preset machine learning model to obtain the risk prediction result of the current emergency event includes:

[0020] A risk prediction model trained according to historical comprehensive emergency situation information including a risk label is obtained;

[0021] According to the emergency situation information, the risk prediction model determines a development trend of the current emergency event; the development trend includes a development path, a development intensity and a development impact range change of the current emergency event in a preset time period;

[0022] Based on the development trend, the risk prediction result is determined.

[0023] In one of the embodiments, the emergency data is fused according to the business processing logic of the plurality of power grid business information systems to obtain the comprehensive emergency situation information of the current emergency event, including:

[0024] According to the business processing logic of the emergency data, a topological relationship between power grid devices is determined; the topological relationship is used to indicate other power grid devices associated with a current power grid device damaged;

[0025] According to the business processing logic of the emergency data, a corresponding relationship between the power grid device and a user is determined;

[0026] Based on the topological relationship and the corresponding relationship, the various emergency data are integrated to determine the comprehensive emergency situation information of the current emergency event.

[0027] In one embodiment, obtaining emergency data from multiple power grid business information systems includes:

[0028] Acquiring the emergency data determined by the data requirement template from the plurality of power grid business information systems through a preset standardized interface, and standardizing the emergency data to obtain standardized emergency data;

[0029] The standardized emergency data is classified and marked, and the processed emergency data is saved in a database.

[0030] In a second aspect, the present application further provides a power grid emergency command information processing device, comprising:

[0031] Emergency data acquisition module, used to obtain emergency data from multiple power grid business information systems;

[0032] A comprehensive emergency situation information determination module, configured to fuse the emergency data according to the business processing logic of the plurality of power grid business information systems to obtain comprehensive emergency situation information of the current emergency event;

[0033] A risk prediction result determination module is used to use a preset machine learning model to perform risk prediction analysis on the comprehensive emergency situation information to obtain a risk prediction result of the current emergency event; the risk prediction result includes the affected area, the user impact range, and the damage to the power grid equipment;

[0034] A target emergency strategy determination module is used to determine a target emergency strategy from preset emergency strategies based on the comprehensive emergency situation information and the risk prediction result;

[0035] The emergency report display module is used to display the emergency report including the comprehensive emergency situation information, the risk prediction results, and the target emergency strategy.

[0036] In a third aspect, the present application further provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the capacity configuration method of the hydrogen production system as described in any one of the above items are implemented.

[0037] 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 capacity configuration method for a hydrogen production system as described in any one of the above items.

[0038] In a fifth aspect, the present application also provides a computer program product comprising a computer program which, when executed by a processor, implements the steps of the capacity configuration method of the hydrogen production system according to any one of the above.

[0039] The power grid emergency command information processing method and device, computer device, computer readable storage medium, and computer program product described above obtain emergency data from multiple power grid business information systems; fuse the emergency data according to the business processing logic of the multiple power grid business information systems to obtain comprehensive emergency situation information of a current emergency event; perform risk prediction analysis on the comprehensive emergency situation information by using a preset machine learning model to obtain a risk prediction result of the current emergency event; the risk prediction result includes a disaster area, a user influence range, and a power grid equipment damage situation; based on the comprehensive emergency situation information and the risk prediction result, a target emergency strategy is determined from preset emergency strategies; and an emergency special report including the comprehensive emergency situation information, the risk prediction result, and the target emergency strategy is displayed. By obtaining emergency data from multiple power grid business information systems and deeply fusing the data according to business processing logic, comprehensive and unified comprehensive emergency situation information can be formed, thereby improving the accuracy and comprehensiveness of the perception of the current emergency event situation. Further, the machine learning model is used to perform risk prediction analysis on the comprehensive emergency situation information, which realizes forward-looking prediction of the event development trend and potential impact, and provides a more accurate decision basis for emergency command. The target emergency strategy is determined based on the comprehensive emergency situation information and the risk prediction result, and key information is integrated and displayed, thereby improving the efficiency of emergency command decision-making. BRIEF DESCRIPTION OF DRAWINGS

[0040] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related art, the drawings needed to be used in the description of the embodiments of the present application or the related art will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other related drawings can also be obtained without creative labor.

[0041] Figure 1 A flowchart of the power grid emergency command information processing method in one embodiment;

[0042] Figure 2 A flowchart of the power grid emergency command information processing method in another embodiment;

[0043] Figure 3 A block diagram of the structure of the power grid emergency command information processing device in one embodiment;

[0044] Figure 4 An internal structure diagram of the computer device in one embodiment. DETAILED DESCRIPTION

[0045] 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.

[0046] In one embodiment, Figure 1 As shown, a method for capacity configuration of a hydrogen production system is provided. This embodiment uses the method applied to a terminal as an example for illustration. It is understandable that the method can also be applied to a server, or to a system including a terminal and a server, and implemented through interaction between the terminal and the server. In this embodiment, the method includes the following steps:

[0047] Step S102: Acquire emergency data from multiple power grid business information systems.

[0048] The power grid business information system can be a collection of information systems that support various aspects of daily power grid operations, such as the production management system responsible for equipment management, the power grid dispatch automation system responsible for real-time monitoring, and the marketing management system responsible for user services. Emergency data can be various types of information directly or indirectly related to the current emergency event obtained from the power grid business information system.

[0049] For example, the terminal can start the data acquisition process according to a preset data requirement list or a trigger signal of an emergency event, and actively initiate a data request to one or more target power grid business information systems to collect the data required to process the current emergency event.

[0050] Specifically, the system requests real-time line tripping lists, substation pressure loss information, and flow data of key sections from the power grid dispatching automation system; requests asset ledgers, historical defect reports, and related power grid geographic wiring diagram information of the transmission, transformation, and distribution equipment in the affected area from the production management system; requests information on power outage users associated with the outage lines from the marketing management system; and requests information on the real-time location, personnel composition, and emergency supplies (such as generators and repair materials) carried by the emergency repair team from the production safety supervision system to ensure the timeliness and accuracy of resource information.

[0051] Optionally, obtain monitoring videos of transmission, transformation, and distribution equipment, road administration videos, and smart safety monitoring videos from each power grid business information system to provide more on-site real-time video information for emergency command, supporting auxiliary decision-making and dispatching command.

[0052] Alternatively, the terminal may periodically query the database of the power grid business information system to obtain updated data in a polling manner. Alternatively, the terminal may also receive event alerts proactively pushed by the business system in real time by subscribing to a message queue.

[0053] Specifically, data collection for each power grid business information system can be automated and collected in real time using smart sensors and IoT technology. In one embodiment, in the event of a natural disaster, sensors installed in various substations, transmission lines, and distribution rooms can monitor parameters such as temperature, humidity, wind speed, and flooding in real time, and automatically transmit these data to multiple business management information systems, significantly reducing the time and errors associated with manual statistics.

[0054] Alternatively, terminals can use a streaming data processing framework (such as Apache Kafka) to stream data collected in real time, ensuring analysis and response in the shortest possible time. Streaming data processing frameworks offer high throughput and low latency, enabling the processing of massive amounts of data. This enables real-time collection and processing of emergency data, significantly improving its timeliness.

[0055] Step S104 , according to the business processing logic of multiple power grid business information systems, the emergency data are integrated to obtain comprehensive emergency situation information of the current emergency event.

[0056] Among them, the business processing logic is the digital embodiment of the inherent relationship between power grid operation rules and data, and is used to define the data in different power grid business information systems that are interrelated and influence each other in power grid operation.

[0057] In an optional embodiment, the service processing logic can be embodied as a set of association rules based on data attributes. The terminal establishes associations by analyzing and matching the attributes of different emergency data (such as timestamps, geographic coordinates, functional areas, keywords, etc.). For example, a logical rule can be defined as: all event data with timestamps within a preset threshold (such as 3 minutes) and geographic coordinates belonging to the same grid area are grouped into a group of related events. In one embodiment, based on this rule, the terminal can automatically associate a device failure alarm with a nearby user repair call record, even if there is no direct device affiliation between the two.

[0058] In another optional embodiment, the business processing logic can also be based on a statistically significant strong correlation model. This model, by studying massive amounts of historical data, discovers potential correlations between different events. For example, the model may discover that a certain type of weather warning and a line tripping fault in a specific area have historically shown a very high probability of coexistence. Therefore, when receiving similar data, it prioritizes integrating them and determining that a causal relationship may exist.

[0059] Step S106: Use a preset machine learning model to perform risk prediction analysis on the comprehensive emergency situation information to obtain a risk prediction result for the current emergency event.

[0060] Machine learning models can be built by studying historical emergency event data, revealing the complex mapping between current trends and future risks. The model's ultimate risk prediction output is a structured set of predictions about potential losses and impacts, indicating the likely impacted areas, the scale of affected users, and the estimated damage to critical grid equipment.

[0061] Exemplarily, the preset machine learning model can be a similar event matching model. When the terminal performs this step, it first extracts the comprehensive emergency situation information of the current emergency event and converts it into a standardized feature vector (for example, including dimensions such as disaster type, intensity level, and initial characteristics of the affected area). The terminal then uses this feature vector to perform high-speed searches and similarity calculations within a historical emergency event case library. This case library stores complete situation information of actual historical emergency events and their final, verified actual loss results. The model's goal is to find and match the historical case most similar to the current event. Finally, the terminal derives a risk prediction for the current emergency event by performing a statistically weighted average, aggregation, or probability distribution calculation on the actual loss results of these most similar historical cases (for example, the actual list of damaged equipment, the scope of the power outage, and the number of users in that year). This prediction then displays the probability of equipment damage in different areas in the form of a risk heat map.

[0062] Step S108: Based on the comprehensive emergency situation information and risk prediction results, a target emergency strategy is determined from the preset emergency strategies.

[0063] Among them, the preset emergency strategy can be a pre-digitized and structured knowledge base, which stores emergency plans or action lists for different disaster types, different emergency levels, and different business scenarios.

[0064] For example, the terminal can employ a scoring and ranking-based model. In this case, each pre-defined emergency response strategy is associated with a multi-dimensional evaluation function. Using the current comprehensive emergency situation information and risk prediction results, the terminal can assess the suitability of all strategies in the library. The strategy with the highest score (i.e., the strategy deemed most suitable for the current complex scenario by the model) is selected as the target emergency response strategy. Alternatively, the terminal can rapidly simulate the potential consequences of applying different emergency response strategies based on a high-level organizational strategy (e.g., minimizing economic losses) and select the emergency response strategy whose simulated results best align with the current dominant strategy as the final output.

[0065] In step S110, an emergency report including comprehensive emergency situation information, risk prediction results, and target emergency strategies is displayed.

[0066] For example, an emergency report can be presented through an interactive map interface based on a geographic information system (GIS), such as an emergency map or emergency sandbox. Specific visualizations include, but are not limited to, dynamic charts, dashboards, heat maps, and other visualizations. These visually present complex data to command personnel, greatly improving readability and comprehension. In this interface, the map serves as the core canvas, while the report's comprehensive emergency situation information, risk prediction results, and targeted emergency response strategies are overlaid on the map as distinct visualization layers.

[0067] In some embodiments, comprehensive emergency situation information can be displayed as dynamic icons on a map (such as flashing fault equipment symbols, line tripping information, and substation voltage loss), highlighted areas (such as polygons of the power outage impact range), and real-time data panels (such as rolling updates of the number of affected users in the entire network, lost load, etc.). For example, during the emergency command process, commanders can intuitively view various types of comprehensive emergency situation information in the form of a sandbox, including power outage and restoration conditions in the affected area, resource allocation progress, weather changes, and equipment status, so as to better grasp the overall situation and make scientific decisions.

[0068] The risk prediction results can be rendered into a semi-transparent risk thermal layer, using different shades of color to visually indicate the probability of different areas experiencing equipment damage or line tripping in the future.

[0069] The targeted emergency response strategy can be displayed as a task list or flowchart fixed to the side. Each action item can highlight its corresponding geographic target on the map, realizing the linkage between command and space. For example, during a flood disaster caused by a heavy rainstorm, a sand table displayed the water levels in each affected area, the location of affected power facilities, and the distribution of emergency repair teams. The command center rationally allocated resources based on the targeted emergency response strategy and displayed the repair team's movements on the sand table, restoring power supply in a relatively short period of time.

[0070] Optionally, the terminal breaks down the emergency report into multiple independent information blocks, which commanders can freely combine based on their responsibilities and preferences. For example, if the user is the commander-in-chief, the main interface can be displayed as a macro GIS map, supplemented with key performance indicator (KPI) statistics (such as total loss load). If the user is the deputy commander in charge of material dispatch, a real-time data chart showing the inventory and demand of emergency resources in various regions and a path indicating the resource deployment path can be used.

[0071] Optionally, the terminal can automatically compile the emergency report into a formatted electronic document with clear sections and charts for easy archiving, printing, and distribution via instant messaging tools. Specifically, during a disaster rescue operation, the on-site team displays the emergency report on an action sandbox. The command center quickly adjusts resource allocation and task scheduling based on the real-time updated task status and progress of the emergency report, generates a new emergency report, and guides the on-site team to adopt new solutions through real-time communication tools, ultimately successfully completing the emergency repair task. This enables real-time communication and information sharing between the on-site team and the command center, ensuring the orderly conduct of on-site response work.

[0072] In this embodiment, by acquiring emergency data from multiple power grid business information systems and deeply integrating them according to business processing logic, a comprehensive and unified integrated emergency situation information can be formed, thereby improving the accuracy and comprehensiveness of the perception of the current emergency event status. Furthermore, a machine learning model is used to perform risk prediction analysis on the integrated emergency situation information, achieving a forward-looking prediction of the development trend and potential impact of the event, and providing a more accurate decision-making basis for emergency command. By determining the target emergency strategy based on the integrated emergency situation information and risk prediction results, and integrating and displaying key information, the efficiency of emergency command decision-making is improved.

[0073] In an exemplary embodiment, the preset emergency strategy includes a resource allocation strategy; based on the comprehensive emergency situation information and risk prediction results, a target emergency strategy is determined from the preset emergency strategy, including:

[0074] Based on the risk prediction results, the risk levels of different disaster-stricken areas in the current emergency event are determined; based on the comprehensive emergency situation information and risk levels, the resource allocation strategies that match different disaster-stricken areas are determined; the matched resource allocation strategies are determined as the target emergency strategies.

[0075] The resource allocation strategy can be a deployment plan that specifies the type and quantity of emergency resources (such as repair teams, emergency generators, spare parts, etc.) that should be dispatched to specific locations under certain circumstances. The risk level can be a quantitative or graded assessment of the severity of future losses that different disaster-stricken areas may suffer based on risk prediction results (for example, high, medium, and low).

[0076] Specifically, the terminal first receives the generated risk prediction results, which can be a geographic information map containing the future probability of damage to power grid equipment. Based on a pre-set threshold rule table, the map is automatically partitioned and ranked. For example, a rule might be defined as follows: any geographic area with a predicted probability of severe equipment damage greater than 70% is marked as high risk; areas with a probability between 30% and 70% are marked as medium risk; and areas with a probability below 30% are marked as low risk. For example, if the comprehensive emergency situation information for a high-risk area indicates that it contains a hospital (a critical user), the terminal will match it with a resource package called Class A - Power Supply for Critical Users. This policy specifically states: immediately dispatch a Class A repair team (10 people, capable of live-line work) and two 500-kilowatt emergency generators to the area, with the highest response priority. For an area marked as medium-risk, if the situation information shows that it is an ordinary residential area, the terminal may match a resource package called Class B - Conventional Repair. Its strategy is to plan to dispatch a Class B emergency repair team (5 people) to be in place within 4 hours, with a response priority of conventional.

[0077] Finally, the terminal will summarize the specific resource allocation strategies matched to all affected areas, forming a comprehensive and detailed emergency resource dispatch summary. This summary is ultimately determined as the target emergency strategy for this incident and presented to the command personnel.

[0078] In a specific embodiment, during a large-scale power outage, the optimal target emergency strategy is determined from a preset emergency plan based on the needs of the affected area indicated by the risk level and the inventory of emergency supplies. For example, generators, lighting equipment, and repair teams are quickly dispatched to the most severely affected areas to restore power supply as soon as possible.

[0079] In this embodiment, the introduction of risk levels achieves precise and differentiated resource allocation, allowing commanders to quickly grasp the current disaster situation through a visual interface, including which areas have the most serious power outages and which equipment needs priority repair, ensuring that emergency resources can be prioritized in the most critical areas. Secondly, standardized resource templates replace fuzzy judgments based on personal experience, greatly improving the scientific nature and standardization of resource allocation and improving the efficiency of emergency response and resource scheduling.

[0080] In an exemplary embodiment, after presenting the emergency report including comprehensive emergency situation information, risk prediction results, and target emergency strategies, the following is also included:

[0081] The emergency report is fed back to the user through a preset reminder method and is saved in the database; based on the saved emergency report, the emergency response effectiveness of the target emergency strategy in the emergency report when processing the corresponding risk prediction results is determined; based on the emergency response effectiveness, the preset emergency strategy is updated to obtain an updated preset emergency strategy.

[0082] Emergency response effectiveness serves as an objective evaluation metric, measuring the effectiveness of implemented target emergency response strategies in addressing specific risk predictions. This effectiveness metric enables the system to self-learn and iterate, dynamically updating its knowledge base of pre-set emergency response strategies and enabling continuous optimization.

[0083] Specifically, based on the preset communication configuration, the emergency report or its summary information will be sent to one or more designated commander user terminals through methods such as short message service, secure instant messaging protocol or application programming interface (API) push; at the same time, the terminal will serialize the complete emergency report data object including timestamp, comprehensive emergency situation information, risk prediction results and adopted target emergency strategy, and store it persistently in the system's relational database or time series database as an independent event record.

[0084] After the emergency response is complete, the terminal automatically retrieves the archived emergency report and obtains the actual response data from relevant business systems (such as marketing and production management systems). The terminal then uses a reinforcement learning-based policy selection model to calculate the effectiveness of the emergency response and, based on this calculated effectiveness, updates the policy library. If the effectiveness of a target emergency strategy falls below a preset baseline threshold, the terminal automatically marks the strategy for optimization and alerts the system administrator, who then proactively updates the strategy. Alternatively, in a more selective implementation, the terminal can use the effectiveness of the emergency response as a reward signal within the reinforcement learning framework to fine-tune the internal parameters of the policy selection model, thereby increasing the probability of selecting a high-performance strategy in similar scenarios in the future. For example, by analyzing the experience of past typhoon emergency responses, the system has improved the resource allocation process and information transmission mechanism, enhancing overall emergency response capabilities.

[0085] In this embodiment, by regularly reviewing and analyzing historical data, problems existing in past emergency response are identified, and emergency plans are optimized based on the analysis results, forming a traceable data-driven model. This ensures that the system's emergency strategy knowledge base can dynamically and continuously adapt to changes in the power grid environment, thereby continuously improving the power grid's efficiency in handling emergencies.

[0086] In an exemplary embodiment, a preset machine learning model is used to perform risk prediction analysis on the comprehensive emergency situation information to obtain the risk prediction result of the current emergency event, including:

[0087] A risk prediction model is obtained by training based on historical comprehensive emergency situation information including risk labels; the risk prediction model determines the development trend of the current emergency event based on the emergency situation information; the development trend includes the development path, development intensity and development impact range changes of the current emergency event within a preset time period; based on the development trend, a risk prediction result is determined.

[0088] The risk prediction model is a computational model trained using supervised learning methods. Specifically, its training dataset consists of a large number of historical comprehensive emergency situation information samples, each of which has been manually or semi-automatically annotated with a risk label. This label is a true record of the actual disaster losses ultimately incurred by the historical event.

[0089] Specifically, a pre-trained risk prediction model, such as one based on a long short-term memory (LSTM) network or a spatiotemporal graph convolutional network, is loaded. When a prediction is needed, the terminal uses comprehensive emergency situation information for the current event as input to the model. After receiving this input, the model's primary task is to output a forecast of the event's development trend over a preset time period. This development trend is a composite data structure that can include a development path: for example, for a typhoon disaster, the model outputs a predicted trajectory consisting of a series of future longitude and latitude coordinates; development intensity: a time series predicting changes in key intensity indicators of the event at various future time points; and development impact range changes: a series predicting the dynamic changes in the future impact range over time.

[0090] After determining the dynamic development trend, the terminal performs the second phase of calculations, determining the final risk prediction based on this trend. Specifically, the terminal overlays the predicted development path and impact range changes onto a geographic map of power grid equipment, thereby screening all grid equipment that will be affected by the event trajectory. Subsequently, based on the predicted development intensity, the terminal calculates the specific damage status (such as the probability of collapse or damage) for each affected device based on its vulnerability (such as tower type and construction year). This is further correlated with marketing data to summarize the precise user impact range.

[0091] In one specific embodiment, by determining comprehensive emergency situation information for a transmission line (such as the affected area and number of users), a risk prediction model can be used to accurately predict potential problems that may arise on a transmission line under severe weather conditions. This allows for proactive maintenance and inspections, reducing the probability of accidents. For example, during a winter cold snap, real-time monitoring of equipment icing and meteorological data can be used to assess the safety and stability of power equipment operations based on risk prediction results, enabling preemptive deicing measures to be initiated to avoid power outages caused by ice accumulation.

[0092] In this embodiment, through the above steps, emergency command can be more proactive and flexible, and resource deployment and defense strategies can be adjusted in advance and dynamically according to the predicted path and intensity changes, thereby achieving more accurate and efficient risk avoidance.

[0093] In an exemplary embodiment, emergency data is integrated according to the business processing logic of multiple power grid business information systems to obtain comprehensive emergency situation information of the current emergency event, including:

[0094] According to the business processing logic of emergency data, the topological relationship between power grid equipment is determined; the topological relationship is used to indicate other power grid equipment associated with the current damaged power grid equipment; according to the business processing logic of emergency data, the corresponding relationship between power grid equipment and users is determined; based on the topological relationship and corresponding relationship, the various emergency data are integrated to determine the comprehensive emergency situation information of the current emergency event.

[0095] Among them, the topological relationship can be a data model that describes how the various devices in the power grid (such as substations, lines, switches, etc.) are physically connected and electrically interconnected; the corresponding relationship between power grid equipment and users can be a data model that binds the terminal power supply equipment with the electricity customers.

[0096] Specifically, according to the business processing logic, for any upstream power grid device determined from the emergency data (for example, a malfunctioning switch), its directly downstream associated device is determined by retrieving all its superior device or power supply connection point field value matching the unique identifier of the upstream device in the power grid device asset data. Further, the above-mentioned direct association rule is recursively executed. That is, for each newly determined directly downstream associated device, the rule needs to be repeatedly applied until all terminal devices (for example, distribution transformers) on the path branch without downstream connection are traced back. By sequentially executing the above-mentioned rule, one or more complete topology relationship paths composed of a series of devices can be determined from an initial fault device.

[0097] Specifically, according to the business processing logic, for any terminal power supply device determined in the above-mentioned topology relationship tracing process, all its corresponding users can be determined by retrieving all user records whose user field value matches the unique identifier of the terminal device in the market power business information system data, to determine the relationship between the power grid device and the user.

[0098] In this embodiment, by analyzing the business logic of the power grid business information system, the emergency data from different sources are fused, solving the technical problem that the prior art is difficult to realize rapid extraction and integration in the case of data island, and providing a real and reliable data basis for subsequent risk prediction, resource allocation and other steps.

[0099] In an exemplary embodiment, the emergency data from multiple power grid business information systems is obtained, including:

[0100] The emergency data determined by the data requirement template is obtained from the multiple power grid business information systems through a preset standardized interface, and the emergency data is standardized to obtain standardized emergency data; the standardized emergency data is classified and labeled, and the processed emergency data is saved to the database.

[0101] Specifically, the terminal communicates with each power grid business information system through a preset standardized interface. The interface can be a set of RESTful API based on Hypertext Transfer Protocol (HTTP), in which a uniform request / response format, authentication method and error code are predefined.

[0102] Before initiating a data request, the terminal will first load a corresponding data requirement template based on the type of the current emergency event. The template is a structured file (such as JSON or XML format), which clearly lists the data item names, data source systems, and acquisition frequency parameters required for this emergency. The terminal generates specific API requests based on this template to ensure that only necessary data is obtained. After obtaining the original emergency data from different systems through the interface, the terminal performs standardized processing on it. This processing includes but is not limited to: format conversion, converting all data into the system's internal standard JSON object format; code mapping, converting the internal business codes of different business systems (for example, multiple alarm codes indicating line tripping) into standard codes in the system master data by referring to the preset mapping table.

[0103] After data standardization, the terminal can classify and tag it, adding metadata. For example, each piece of data can be tagged with the source system, data category (such as real-time telemetry), update frequency, and content description. Finally, the standardized emergency data, which has undergone all the above processing steps and is in a unified format and rich in metadata, is stored in a dedicated data staging repository or data lake for subsequent data fusion steps.

[0104] In this embodiment, a set of standardized data access and processing procedures are established through the above steps, which greatly improves the interoperability, scalability and data governance level of the system.

[0105] In an exemplary embodiment, existing emergency command technology mainly addresses challenges through four methods. Method one aims to open up the emergency data chain by establishing a data center to aggregate data from various disciplines such as production, scheduling, market, and safety supervision, so as to achieve business integration of data damaged by disasters such as line tripping, voltage loss, and user impact. Method two is committed to realizing automatic data collection. By building an emergency map function, data from various systems are integrated on a single platform and statistical analysis is automatically performed to solve the problem of untimely and inaccurate data. Method three focuses on the timely control and execution of command, providing different functions such as decision support, on-site disposal control, and power outage monitoring to the management level, team level, and supervisory level to optimize resource allocation. Method four attempts to support the entire decision-making process and provide a basis for resource allocation and risk prevention and control by developing emergency guarantee and risk intelligent analysis functions.

[0106] However, despite these efforts, existing technologies still have significant shortcomings. First, the data chain is not fully connected, and emergency damage data is scattered across multiple independent systems such as scheduling, marketing, and production. The data silo problem is serious and cannot provide effective data support for command decision-making. Second, automatic data collection has not been achieved, and the system still generally uses manual reporting to collect information. This method cannot meet the high-frequency reporting requirements of massive emergency information, nor can it guarantee the timeliness, accuracy, and completeness of the information. Third, the construction functions of emergency command scenarios are incomplete. The existing system focuses more on information reporting and cannot meet the real needs of management, team, and supervisory levels in actual command decision-making and on-site disposal work. Finally, the system lacks in-depth applications such as emergency resource allocation information and multi-dimensional risk analysis, and cannot meet the needs of efficient information transmission between the command center and the work site.

[0107] Based on the above problems, this application arises at the historic moment and provides a method for processing power grid emergency command information, such as Figure 2 As shown, the method includes:

[0108] Step S201, based on the preset data requirement template, collects, processes and stores standardized emergency data from multiple power grid business information systems through standardized interfaces. The terminal will first automatically load and parse a preset data requirement template corresponding to the type of initial event (such as equipment failure, external force damage, etc.). Subsequently, the terminal initiates data acquisition requests to multiple power grid business information systems such as the internal production management system, scheduling automation system, marketing customer management system, and production safety supervision system through a standardized API interface based on the data items specified in the template. All collected heterogeneous raw data undergoes a rigorous preprocessing process, including format conversion, unit unification, and coding mapping, to form high-quality standardized emergency data. After being attached with metadata tags such as source and timestamp, it is stored in an emergency-specific database to provide a clean and regular data foundation for subsequent analysis and processing.

[0109] Step S202, through the fusion of multiple emergency data, the fault topology is traced back to determine the scope of affected equipment and users, thereby forming comprehensive emergency situation information. After the data is acquired, the terminal immediately starts data fusion processing on the massive amount of standardized data. At this time, the terminal starts from the initial fault point (for example, a tripped switch device) according to the business processing logic, recursively traces downward, and calculates and determines in real time all downstream equipment sets directly or indirectly affected by the fault. Using the equipment list composed of this downstream equipment set, all users powered by these devices are matched and classified according to user categories. Finally, the terminal integrates the initial emergency data, the determined equipment topology path, and the determined user impact list to form a comprehensive emergency situation information.

[0110] Step S203, based on the comprehensive emergency situation information, uses the risk prediction model to deduce future development trends and generate risk prediction results. After forming the preliminary situation information, the terminal will immediately input it into the preset risk prediction model. The model has been trained by learning various historical emergency events and their disaster loss results (with risk labels). The core task of the model is to output a prediction of the development trend of the event within a preset time period in the future. This trend can be a prediction of the expansion path of the fault impact range, or a prediction of the intensity change of certain key parameters in the system (such as the overload risk of other lines). After obtaining this dynamic trend prediction, the terminal will further deduce specific risk prediction results based on this trend.

[0111] Step S204, based on the risk prediction results, automatically match the optimal target emergency strategy from the preset emergency strategies. For example, based on the internal decision-making rules, the risk level of the area where the critical line predicted to have the risk of cascading tripping is located is automatically assessed as high. Subsequently, the terminal uses high risk and prevention of cascading failures as indexes to match an optimal resource allocation strategy or operation instruction set in the preset emergency strategy library. This matched strategy is finally determined as the current target emergency strategy, and its specific content may be: immediately execute risk avoidance operations and adjust the grid operation mode to reduce the target line load; at the same time, dispatch an emergency repair team to the area near the line to stand by in case of an emergency.

[0112] In step S205, an emergency report including comprehensive emergency situation information, risk prediction results, and target emergency strategies is displayed; the comprehensive emergency situation information can be displayed as dynamic icons on the map (such as flashing fault equipment symbols, line tripping information, and substation voltage loss), highlighted areas (such as polygons of the power outage impact range), and real-time data panels (such as rolling updates of the number of affected users in the entire network, loss load, etc.). For example, during the emergency command process, commanders can intuitively view various types of comprehensive emergency situation information in the form of a sandbox, including power outage and restoration status in the affected area, resource allocation progress, weather changes, and equipment status, so as to better grasp the overall situation and make scientific decisions.

[0113] The risk prediction results can be rendered into a semi-transparent risk thermal layer, using different shades of color to visually indicate the probability of different areas experiencing equipment damage or line tripping in the future.

[0114] The target emergency strategy can be displayed as a task list or flowchart fixed on the side, and each action item can highlight the corresponding geographical target on the map to realize the linkage of instructions and space. For example, in a large-scale rainstorm-induced flood disaster, the sand table displays the water level of each affected area, the location of affected power facilities, and the distribution of repair teams. According to the target emergency strategy, the command center reasonably allocates resources and displays the action direction of the repair team on the sand table to restore power supply in a short time.

[0115] In step S206, the relevant data of the current emergency event is archived, the emergency disposal efficiency of the target emergency strategy with respect to the current emergency event is evaluated, and the preset emergency strategy is updated based on the emergency disposal efficiency. Exemplarily, the terminal archives the whole process data of the event, including the final disposal result (for example, whether the cascading failure is successfully avoided). The system compares the obtained real disposal result with the preset evaluation model to calculate the emergency disposal efficiency score of the risk avoidance operation strategy. Based on the efficiency score, the terminal automatically updates its emergency strategy library, for example, adjusts the load rate threshold for triggering the strategy, or optimizes the execution priority of the strategy, so that it can more accurately and effectively deal with similar risks in the future.

[0116] In this embodiment, the information island problem is fundamentally solved by standardized data acquisition and deep fusion based on power grid topology, forming a comprehensive and accurate unified situation view, which provides a solid and reliable data cornerstone for all subsequent analysis. Based on this accurate situation, the method uses machine learning models to predict the dynamic development trend of the event, changes the command mode from passive "after-response" to active "pre-anticipation", gives the command decision unprecedented foresight and initiative, and makes it possible to avoid risks in advance. Further, this accurate grasp of the current situation and scientific prediction of future risks support the automatic and rapid generation of emergency strategies, and scientific decision-making driven by data replaces the traditional mode relying on personal experience, greatly improving the efficiency and success rate of emergency disposal. Most importantly, the invention introduces the quantitative evaluation of emergency disposal efficiency and the self-updating mechanism of the strategy library, builds an intelligent closed-loop system that can learn and evolve from actual combat, and ensures the continuous and iterative improvement of emergency command capabilities to cope with the increasingly complex challenges of power grid security.

[0117] It should be understood that although each step in the flowchart involved in the above-described embodiments is shown in sequence according to the direction of the arrow, these steps are not necessarily executed in the order indicated by the arrow. Unless otherwise specified herein, there is no strict order limitation for the execution of these steps, and these steps can be executed in other orders. Moreover, at least some of the steps in the flowchart involved in the above-described embodiments can include multiple steps or multiple stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily sequential, but can be alternately or alternately executed with at least part of other steps or steps or stages in other steps. It can be understood that the steps in different embodiments can be freely combined as needed, and various non-contradictory schemes formed by the combination are within the scope of protection of the present application.

[0118] Based on the same inventive concept, the embodiments of the present application also provide a power grid emergency command information processing device for implementing the above-mentioned power grid emergency command information processing method. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme described in the above method, so the specific limitations in one or more power grid emergency command information processing device embodiments provided below can refer to the limitations of the power grid emergency command information processing method in the above text, which will not be repeated here.

[0119] In one exemplary embodiment, as shown in Figure 3 A power grid emergency command information processing device is provided, comprising: an emergency data acquisition module 310, a comprehensive emergency situation information determination module 320, a risk prediction result determination module 330, a target emergency strategy determination module 340, and an emergency special report display module 350, wherein:

[0120] The emergency data acquisition module 310 is configured to acquire emergency data from a plurality of power grid business information systems;

[0121] The comprehensive emergency situation information determination module 320 is configured to fuse the emergency data according to the business processing logic of the plurality of power grid business information systems to obtain comprehensive emergency situation information of a current emergency event;

[0122] The risk prediction result determination module 330 is configured to use a preset machine learning model to perform risk prediction analysis on the comprehensive emergency situation information to obtain a risk prediction result of the current emergency event; the risk prediction result includes a disaster-affected area, a user influence range, and a power grid equipment damage situation;

[0123] The target emergency strategy determination module 340 is configured to determine a target emergency strategy from a preset emergency strategy based on the comprehensive emergency situation information and the risk prediction result.

[0124] The emergency report display module 350 is used to display the emergency report including the comprehensive emergency situation information, the risk prediction results, and the target emergency strategy.

[0125] In one embodiment, the preset emergency strategy includes a resource allocation strategy, and the target emergency strategy determination module 340 is further used to determine the risk levels of different disaster-stricken areas in the current emergency event based on the risk prediction results; determine the resource allocation strategies that match different disaster-stricken areas based on the comprehensive emergency situation information and the risk levels; and determine the matched resource allocation strategies as the target emergency strategy.

[0126] In one embodiment, the target emergency strategy determination module 340 is also used to feed back the emergency report to the user through a preset reminder method, and save the emergency report to the database; based on the saved emergency report, determine the emergency response effectiveness of the target emergency strategy in the emergency report when processing the corresponding risk prediction result; based on the emergency response effectiveness, update the preset emergency strategy to obtain an updated preset emergency strategy.

[0127] In one embodiment, the risk prediction result determination module 330 is also used to obtain a risk prediction model trained based on historical comprehensive emergency situation information including risk labels; the risk prediction model determines the development trend of the current emergency event based on the emergency situation information; the development trend includes the development path, development intensity and development impact range changes of the current emergency event within a preset time period; based on the development trend, the risk prediction result is determined.

[0128] In one embodiment, the comprehensive emergency situation information determination module 320 is also used to determine the topological relationship between power grid devices based on the business processing logic of the emergency data; the topological relationship is used to indicate other power grid devices associated with the current damaged power grid device; according to the business processing logic of the emergency data, the corresponding relationship between the power grid device and the user is determined; based on the topological relationship and the corresponding relationship, each of the emergency data is integrated to determine the comprehensive emergency situation information of the current emergency event.

[0129] In one embodiment, the emergency data acquisition module 310 is also used to obtain the emergency data determined by the data requirement template from the multiple power grid business information systems through a preset standardized interface, and standardize the emergency data to obtain standardized emergency data; classify and mark the standardized emergency data, and save the processed emergency data to a database.

[0130] Each module in the aforementioned power grid emergency command information processing device can be implemented in whole or in part through software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in hardware form, or can be stored in a computer device memory in software form, so that the processor can call and execute the corresponding operations of each module.

[0131] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 4 As shown. The computer device includes a processor, memory, an input / output interface, a communication interface, a display unit, and an input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals via wired or wireless means, and the wireless means can be implemented via Wi-Fi, a mobile cellular network, near-field communication (NFC), or other technologies. When executed by the processor, the computer program implements a method for processing power grid emergency command information. The display unit of the computer device is used to form a visually visible image and can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device casing, or an external keyboard, touchpad or mouse.

[0132] Those skilled in the art will understand that Figure 4 The 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 computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0133] In one embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps in the above method embodiments when executing the computer program.

[0134] In an embodiment, a computer readable storage medium is provided, having stored thereon a computer program, which, when executed by a processor, implements the steps of any of the above method embodiments.

[0135] In an embodiment, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the steps of any of the above method embodiments.

[0136] It should be noted that the user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties, and the collection, use and processing of related data need to comply with relevant regulations.

[0137] It should be noted that the user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties, and the collection, use and processing of related data need to comply with relevant regulations.

[0138] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when executed, can include the processes of the above-mentioned embodiment methods. Any reference to memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. The non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. The volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration but not limitation, the RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The database involved in the embodiments provided in the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a block chain, etc., without being limited thereto. The processor involved in the embodiments provided in the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., without being limited thereto.

[0139] The technical features of the above embodiments can be combined in any manner. To make the description concise, all possible combinations of the technical features in the above embodiments are not described, but as long as the combinations of the technical features do not exist contradictions, they should be considered as the scope of the present application.

[0140] 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. A method for processing power grid emergency command information, characterized in that: The method comprises: Obtain emergency data from multiple power grid business information systems; According to the business processing logic of the multiple power grid business information systems, the emergency data are integrated to obtain comprehensive emergency situation information of the current emergency event; Using a preset machine learning model, a risk prediction analysis is performed on the comprehensive emergency situation information to obtain a risk prediction result of the current emergency event; the risk prediction result includes the affected area, the user impact range, and the damage to the power grid equipment; Determining a target emergency strategy from preset emergency strategies based on the comprehensive emergency situation information and the risk prediction result; An emergency report including the comprehensive emergency situation information, the risk prediction results, and the target emergency strategy will be displayed.

2. The method according to claim 1, characterized in that The preset emergency strategy includes a resource allocation strategy; the target emergency strategy is determined from the preset emergency strategy based on the comprehensive emergency situation information and the risk prediction result, including: Determining the risk levels of different disaster-stricken areas in the current emergency event based on the risk prediction results; Determining resource allocation strategies matching different disaster-stricken areas based on the comprehensive emergency situation information and the risk level; The matched resource allocation strategy is determined as the target emergency strategy.

3. The method according to claim 1, characterized in that After presenting the emergency report including the comprehensive emergency situation information, the risk prediction results, and the target emergency strategy, the following is also included: Feedback the emergency report to the user through a preset reminder method, and save the emergency report to the database; Determining, based on the saved emergency report, the emergency response effectiveness of the target emergency strategy in the emergency report when processing the corresponding risk prediction result; Based on the emergency response effectiveness, the preset emergency strategy is updated to obtain an updated preset emergency strategy.

4. The method according to claim 1, wherein The risk prediction analysis of the comprehensive emergency situation information using a preset machine learning model to obtain a risk prediction result of the current emergency event includes: Obtaining a risk prediction model trained based on historical comprehensive emergency situation information including risk labels; The risk prediction model determines the development trend of the current emergency event based on the emergency situation information; the development trend includes the development path, development intensity, and development impact range changes of the current emergency event within a preset time period; Based on the development trend, the risk prediction result is determined.

5. The method according to claim 1, wherein The emergency data is integrated according to the business processing logic of the multiple power grid business information systems to obtain comprehensive emergency situation information of the current emergency event, including: Determining a topological relationship between power grid devices according to the business processing logic of the emergency data; the topological relationship is used to indicate other power grid devices associated with the current damaged power grid device; Determining a correspondence between the power grid equipment and the user according to the business processing logic of the emergency data; Based on the topological relationship and the corresponding relationship, the various emergency data are integrated to determine the comprehensive emergency situation information of the current emergency event.

6. The method according to any one of claims 1 to 5, characterized in that Acquiring emergency data from multiple power grid business information systems includes: Acquiring the emergency data determined by the data requirement template from the plurality of power grid business information systems through a preset standardized interface, and standardizing the emergency data to obtain standardized emergency data; The standardized emergency data is classified and marked, and the processed emergency data is saved in a database.

7. A power grid emergency command information processing device, characterized in that: The device comprises: Emergency data acquisition module, used to obtain emergency data from multiple power grid business information systems; A comprehensive emergency situation information determination module, configured to fuse the emergency data according to the business processing logic of the plurality of power grid business information systems to obtain comprehensive emergency situation information of the current emergency event; A risk prediction result determination module is used to use a preset machine learning model to perform risk prediction analysis on the comprehensive emergency situation information to obtain a risk prediction result of the current emergency event; the risk prediction result includes the affected area, the user impact range, and the damage to the power grid equipment; A target emergency strategy determination module is used to determine a target emergency strategy from preset emergency strategies based on the comprehensive emergency situation information and the risk prediction result; The emergency report display module is used to display the emergency report including the comprehensive emergency situation information, the risk prediction results, and the target emergency strategy.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. 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 6 are implemented.

10. A computer program product comprising a computer program, 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 6 are implemented.

Images