Power grid operation task processing method, device, equipment, medium and system

Abstract

The invention provides a power grid operation task processing method, device, equipment, medium and system. A power grid operation task is obtained; performing semantic analysis on the power grid operation task by adopting a pre-training language model to obtain power grid operation task feature information; comparing the power grid operation task feature information with a preset power grid operation task rule to obtain a task comparison result; and if the task comparison result shows that the power grid operation task feature information does not meet the preset power grid operation task requirement, the optimization processing mode of the power grid operation task is completed according to the pre-training language model, automatic generation and checking of the operation task are realized, and the checking efficiency of the power grid operation task is improved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method, device, equipment, medium and system for processing power grid operation tasks. Background Art

[0002] In power grid dispatching and industrial operations, operational tasks are becoming increasingly complex and critical. The efficiency and accuracy of these tasks are crucial to the stability and security of power grid systems. Any operational errors or misaligned sequences can cause equipment damage, operational delays, or even serious safety incidents, placing higher demands on the accuracy and reliability of operational tasks.

[0003] Currently, the writing and review of operational tasks is primarily done manually. Based on experience and standards, operators gradually develop task steps and arrange them in a chronological order. When the task volume is large, manual review becomes a critical step in ensuring the logical correctness and security of the task.

[0004] However, the above method is highly dependent on the operator's experience and technical level, which reduces the efficiency of task review and makes it difficult to cope with high requirements in complex scenarios. Summary of the Invention

[0005] The present application provides a method, device, equipment, medium and system for processing power grid operation tasks, which are used to solve the technical problem of low efficiency in power grid operation task review in the prior art.

[0006] In a first aspect, the present application provides a method for processing a power grid operation task, comprising:

[0007] Acquire a power grid operation task, where the power grid operation task is a natural language task generated based on power grid scheduling and industrial operations;

[0008] Using a pre-trained language model to perform semantic analysis on the power grid operation task to obtain power grid operation task feature information, the pre-trained language model is trained based on power grid operation rules;

[0009] Comparing the grid operation task characteristic information with the preset grid operation task rules to obtain a task comparison result;

[0010] If the task comparison result indicates that the grid operation task characteristic information does not meet the preset grid operation task requirements, the grid operation task optimization processing is completed according to the pre-trained language model.

[0011] Optionally, the using a pre-trained language model to perform semantic parsing on the power grid operation task to obtain power grid operation task feature information includes:

[0012] Using a pre-trained language model to perform semantic parsing on the power grid operation task to obtain contextual text information of the power grid operation task;

[0013] Determining, based on the context text information, a feature vector corresponding to the context text information, the feature vector including device information, time information, and operation information;

[0014] According to the characteristic vector, characteristic information of the power grid operation task is obtained.

[0015] Optionally, comparing the grid operation task characteristic information with preset grid operation task rules to obtain a task comparison result includes:

[0016] Determining operation step characteristic information, device logic characteristic information, and time logic characteristic information based on the power grid operation task characteristic information;

[0017] Comparing the operation step characteristic information with the operation step sequence rules in the preset power grid operation task rules to obtain an operation step comparison result;

[0018] Comparing the device logic feature information with the device logic operation rules in the preset power grid operation task rules to obtain a device logic comparison result;

[0019] Comparing the device logic feature information with the time logic rules in the preset power grid operation task rules to obtain a time logic comparison result;

[0020] Obtaining a task comparison result according to the operation step comparison result, the device logic comparison result, and the time logic comparison result;

[0021] The preset grid operation task rules are obtained based on standard operating procedures, safety specifications and logical rules in grid dispatching and industrial operations.

[0022] Optionally, if the task comparison result indicates that the grid operation task characteristic information does not meet preset grid operation task requirements, optimizing the grid operation task according to the pre-trained language model includes:

[0023] If the task comparison result indicates that the grid operation task characteristic information does not meet the preset grid operation task requirements, determining, based on the task comparison result, a step to be optimized that does not meet the preset grid operation task requirements;

[0024] Determining the characteristic information to be optimized of the step to be optimized according to the step to be optimized and the characteristic information of the power grid operation task;

[0025] The feature information to be optimized is deployed to the pre-trained language model to complete the optimization processing of the power grid operation task.

[0026] Optionally, deploying the feature information to be optimized to the pre-trained language model to complete the optimization process of the power grid operation task includes:

[0027] Deploying the feature information to be optimized to the pre-trained language model to determine an optimization plan for the power grid operation task;

[0028] Determining priority information of each of the feature information to be optimized according to the power grid operation task optimization plan;

[0029] According to the priority information, a target power grid operation task optimization scheme in the power grid operation task optimization scheme is determined to complete the optimization processing of the power grid operation task.

[0030] Optionally, after determining the grid operation task optimization solution, the method further includes:

[0031] Presenting the power grid operation task optimization plan and the characteristic information to be optimized to staff in a visual manner;

[0032] In response to the staff's selection operation of the power grid operation task optimization scheme, a target power grid operation task optimization scheme is determined to complete the optimization processing of the power grid operation task.

[0033] Optionally, the method further includes:

[0034] Determining, according to the power grid operation task, device nodes and topological connection relationships in the power grid operation task;

[0035] Based on a graph search algorithm and pattern recognition technology, it is determined whether the device nodes and the topological connection relationship meet the preset power grid operation task requirements, and a task comparison result is obtained.

[0036] If the task comparison result indicates that the device node and the topological connection relationship do not meet the preset power grid operation task requirements, the optimization processing of the power grid operation task is completed according to the pre-trained language model.

[0037] In a second aspect, the present application provides a power grid operation task processing device, comprising:

[0038] A power grid operation task acquisition module, configured to acquire power grid operation tasks, wherein the power grid operation tasks are natural language tasks generated based on power grid scheduling and industrial operations;

[0039] A power grid operation task characteristic information obtaining module is used to perform semantic analysis on the power grid operation task using a pre-trained language model to obtain power grid operation task characteristic information, wherein the pre-trained language model is trained based on power grid operation rules;

[0040] A task comparison result obtaining module is used to compare the grid operation task characteristic information with the preset grid operation task rules to obtain a task comparison result;

[0041] The optimization processing module is used to complete the optimization processing of the power grid operation task according to the pre-trained language model if the task comparison result indicates that the power grid operation task characteristic information does not meet the preset power grid operation task requirements.

[0042] In a third aspect, the present application provides an electronic device, comprising: a processor, and a memory communicatively connected to the processor;

[0043] The memory stores computer-executable instructions;

[0044] The processor executes the computer-executable instructions stored in the memory to implement the method of the embodiment of the present application.

[0045] In a fourth aspect, the present application provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the method of the embodiment of the present application.

[0046] In a fifth aspect, the present application provides a power grid operation task processing system, comprising a computer program, which implements the method described in any one of the first aspects when executed by a processor.

[0047] The power grid operation task processing method, device, equipment, medium and system provided in the present application obtain power grid operation tasks; use a pre-trained language model to perform semantic analysis on the power grid operation tasks to obtain power grid operation task feature information; compare the power grid operation task feature information with preset power grid operation task rules to obtain a task comparison result; if the task comparison result indicates that the power grid operation task feature information does not meet the preset power grid operation task requirements, then according to the pre-trained language model, the power grid operation task is optimized. The processing method realizes the automatic generation and verification of the operation tasks and improves the review efficiency of the power grid operation tasks. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0049] Figure 1The overall architecture diagram of the power grid operation task processing system provided for this application;

[0050] Figure 2 A flowchart of a first embodiment of a method for processing power grid operation tasks provided by this application;

[0051] Figure 3 A flowchart of a second embodiment of the method for processing power grid operation tasks provided in this application;

[0052] Figure 4 A flowchart of a third embodiment of the method for processing power grid operation tasks provided in this application;

[0053] Figure 5 A flowchart of a fourth embodiment of the method for processing power grid operation tasks provided by this application;

[0054] Figure 6 A flowchart of a fifth embodiment of the method for processing power grid operation tasks provided in this application;

[0055] Figure 7 A flowchart of a sixth embodiment of the method for processing power grid operation tasks provided in this application;

[0056] Figure 8 A flowchart of a seventh embodiment of the method for processing power grid operation tasks provided in this application;

[0057] Figure 9 A schematic diagram of the structure of the power grid operation task processing device provided in this application;

[0058] Figure 10 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0059] The above drawings illustrate specific embodiments of the present application, which will be described in more detail below. These drawings and the textual description are not intended to limit the scope of the present application in any way, but rather to illustrate the concepts of the present application to those skilled in the art by reference to specific embodiments. DETAILED DESCRIPTION

[0060] Exemplary embodiments will be described in detail herein, with examples illustrated in the accompanying drawings. In the following description, when referring to the drawings, identical numerals in different figures represent identical or similar elements, unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.

[0061] Existing grid operation task management relies primarily on manual authoring and review, leading to issues such as misinterpretation, delayed rule verification, high risk of misoperation, and inefficient optimization and adjustment. Because grid dispatch tasks are typically described in natural language, manual analysis is prone to ambiguity and struggles to accurately extract key equipment, operational procedures, and timing information. This makes dispatch tasks susceptible to human error, impacting the safety and reliability of grid operations.

[0062] To address the above issues, this solution combines large models, rule engines, graph search algorithms, and pattern recognition technology to build an intelligent power grid operation task parsing, verification, and optimization method. It uses pre-trained language models to parse scheduling task texts, rule engines, and topology analysis to verify whether the tasks comply with power grid operating procedures, safety specifications, and topological logic to ensure that there will be no misoperations or equipment status errors. It also uses large models to automatically generate optimization plans and screen the optimal adjustment plans, effectively reducing manual intervention, improving the intelligence and safety of scheduling tasks, reducing the risk of misoperation, and improving power grid scheduling efficiency.

[0063] The following specific embodiments describe in detail the technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0064] Figure 1 This is the overall architecture diagram of the power grid operation task processing system provided in this application. Figure 1 As shown, the power grid operation task processing system 10 includes a task input layer 101 , a task parsing layer 102 , a task rule comparison layer 103 , a topology analysis and pattern recognition layer 104 , a task optimization layer 105 and a user interaction and visualization layer 106 .

[0065] Among them, the task input layer 101 is responsible for receiving scheduling tasks, and the tasks can be manually input by staff or automatically imported from the scheduling system.

[0066] The task parsing layer 102 uses a pre-trained language model to parse the task text, extract key information such as equipment, operation steps, time, etc., and convert it into structured data.

[0067] The task rule comparison layer 103 uses a rule engine to verify the task: check whether the operation sequence is correct, confirm whether the device logic is reasonable, verify whether the time arrangement conflicts, and combine all the comparison results to draw a conclusion on the feasibility of the task.

[0068] The topology analysis and pattern recognition layer 104 uses a graph search algorithm to check the grid topology to ensure that the equipment connection relationship meets safety requirements, identify the grid equipment nodes and connection relationships in the task, and detect whether there are hidden dangers of misoperation (such as opening the isolation switch under load).

[0069] The task optimization layer 105 is responsible for task error detection and optimization, identifying substandard task steps and generating optimization suggestions. Optimization prioritization ensures that the most urgent task issues are prioritized. Intelligent optimization combines large-scale models (GPT / BERT) to adjust tasks and ensure optimal adjustment solutions.

[0070] The user interaction and visualization layer 106 displays the optimization plan through a visual interface, allowing staff to select the optimal adjustment plan, intuitively presenting task problems and optimization suggestions, allowing staff to manually confirm or adjust the optimization plan, and after confirming the optimization plan, perform the final adjustment.

[0071] After the analysis at all the above levels, the final task is executed and output, and the optimized task is output to ensure compliance with the grid dispatching standards, ensure the safety of task execution, and avoid misoperation.

[0072] The power grid operation task processing system combines large models, rule engines, and graph search to achieve a complete closed loop of intelligent analysis, automatic verification, optimization and adjustment, and visual interaction, ensuring the intelligence of the entire process of power grid dispatching tasks from input to final execution, improving the safety, compliance, and efficiency of task execution, effectively reducing the risk of human operational errors, and improving the intelligence and automation level of power grid dispatching tasks.

[0073] Figure 2 This is a flow chart of the first embodiment of the method for processing power grid operation tasks provided by this application. Figure 2 As shown, the method includes:

[0074] S201: Obtain power grid operation tasks.

[0075] Grid operation tasks are specific operational steps generated based on grid dispatch and industrial operations, such as substation equipment switching, line maintenance, and power outages and restorations. These tasks are typically described in natural language and include information such as equipment names, schedules, and operational instructions. Natural language tasks are tasks described in Chinese or English, rather than structured or programming languages.

[0076] For example, in actual applications, power grid workers need to perform a series of scheduling tasks, such as a 110kV line maintenance task. The task is usually described by text, that is, "A 110kV line is planned to be maintained. First, the 110kV circuit breaker A1 at a certain station must be disconnected, and then the 110kV disconnector G1 at a certain station must be opened. The operation time is 10:30-12:30." In an embodiment of the present application, the power grid operation task is first obtained and then passed to the large model as input for processing at a later stage.

[0077] S202: Use a pre-trained language model to perform semantic analysis on the power grid operation task to obtain feature information of the power grid operation task.

[0078] The pre-trained language model is a natural language processing model trained on large-scale datasets, such as BERT or GPT. This model has been fine-tuned using grid operation rules and historical task data, enabling it to possess specialized grid semantic parsing capabilities. Semantic parsing involves structured processing of natural language tasks to extract key elements, such as device names, operation steps, and time requirements. Grid operation task feature information refers to the structured data after semantic parsing, for example, device name: 110kV circuit breaker A1; operation instruction: open; time requirement: 10:30-12:30.

[0079] For example, the BERT model is used to parse the input task text and extract the key elements of the task. The formula is:

[0080] H=Transformer(E(x1,x2…x3))

[0081] Here, E(x1, x2…x3) represents the word embedding of the input text, and H represents the context information calculated by the Transformer. In a specific power grid task application, the BERT model analyzed the key features of the "110kV line planned maintenance" task: equipment: 110kV circuit breaker A1, 110kV disconnector G1; operation steps: disconnect A1 → open G1; task time: 10:30-12:30. This information is then used to match and verify task rules.

[0082] S203: Compare the grid operation task characteristic information with the preset grid operation task rules to obtain a task comparison result.

[0083] Preset grid operation task rules refer to standard rules based on grid dispatch and safety regulations. Examples include the following: operating sequence rules: circuit breakers must be operated before disconnectors; equipment logic rules: devices of different voltage levels cannot be connected incorrectly; and scheduling rules: ensuring that tasks do not conflict with other maintenance tasks. Task comparison results verify whether a task complies with these rules.

[0084] For example, the comparison is performed using a rule engine, which mainly includes: (1) Operation step sequence verification and comparison. The rule is "the circuit breaker must be disconnected first, and then the disconnector is pulled." However, if the actual operation is "pull G1 → disconnect A1", an error is detected and the following is returned: "Operation error! The circuit breaker A1 should be disconnected first, and then the disconnector G1 should be pulled." (2) Equipment logic operation verification. For example, the rule is that the "closing" operation cannot be performed on equipment that has been shut down. However, if the actual situation is that the input task is "closing the repaired equipment G1", the prompt "Logic error! Equipment G1 is currently under maintenance and cannot be closed" will be returned. (3) Time logic verification. For example, the rule is that tasks within the same time period cannot conflict. However, if it is found that there is another maintenance task in the "10:30-12:30" time period, the prompt "Time conflict! Please adjust the task time or confirm with the dispatch center" will be returned.

[0085] S204: If the task comparison result indicates that the grid operation task characteristic information does not meet the preset grid operation task requirements, then the grid operation task optimization process is completed according to the pre-trained language model.

[0086] Task optimization involves generating error correction suggestions based on the large model, adjusting the order, logic, or timing of tasks to meet grid operating standards. For example, adjusting the order involves reordering operational steps to meet specifications; correcting logical errors involves prompting staff to modify unreasonable operational instructions; and optimizing timelines involves recommending more appropriate execution times to avoid conflicts.

[0087] For example, based on the task comparison results, an optimization plan is automatically generated: (1) Adjust the operation sequence and find the wrong operation: "Pull G1 → Disconnect A1"; Error correction plan: "It is recommended to modify it to: Disconnect A1 first, then pull G1." (2) Correct the logical error and find the wrong operation: "Close the repaired device G1"; Error correction plan: "Device G1 is in maintenance status and cannot be closed. Please confirm whether to release the maintenance status." (3) Optimize the time arrangement and find time conflict; Error correction plan: "It is recommended to adjust the execution time to 13:00-15:00 to avoid task conflict."

[0088] The grid operation task processing method proposed in this application integrates a large model with a rule engine to achieve intelligent analysis, automatic verification, and optimization and adjustment of grid operation tasks. A pre-trained language model is used to perform semantic analysis of natural language tasks, extract key features, and then a rule engine is used to compare them against preset grid operation standards to detect errors in operation sequence, device logic, and timing. This optimizes the task execution process, effectively reduces the risk of operational errors, and improves the security and intelligence level of grid dispatch.

[0089] Figure 3 This is a flow chart of the second embodiment of the method for processing power grid operation tasks provided by this application. Figure 3 As shown, in Figure 2 Based on the embodiment, a pre-trained language model is used to perform semantic analysis on the power grid operation task to obtain the power grid operation task feature information, including:

[0090] S301: Use a pre-trained language model to perform semantic analysis on the power grid operation task to obtain contextual text information of the power grid operation task.

[0091] Contextual text information refers to the contextual information of the grid operation task text, including the preceding and following related operation descriptions. For example, “After disconnecting the 110kV circuit breaker A1, the 110kV disconnector G1 should be opened,” where the previous step will affect the understanding of the subsequent steps.

[0092] In actual applications, scheduling tasks usually consist of multi-step instructions, and multiple devices and operations are designed. For example, "To plan to repair the 110kVA line, you must first disconnect the 110kV circuit breaker A1 at station A, and then open the 110kV disconnector G1 at station A. The operation time is 10:30-12:30."

[0093] Specifically, the text is parsed using the BERT or GPT pre-trained model: (1) Tokenization: The task text is split into words or phrases, such as [Planned Maintenance], [110kV], [A Line], [Disconnect], [110kV Circuit Breaker A1], and then the context vector is calculated. The Transformer mechanism is used to calculate the context relationship of each word. Finally, the complete context information is extracted for feature vector construction in the subsequent steps.

[0094] S302: Determine a feature vector corresponding to the context text information according to the context text information.

[0095] Among them, the feature vector is obtained by converting text information into mathematical representation, which can enable the computer to identify the key elements of the task, including device information, time information and operation information.

[0096] For example, based on the context information extracted in the previous step, the feature vector of the task is further constructed to convert the natural language into structured data for subsequent comparison. The feature vector construction process includes device information extraction, operation information extraction and time information extraction. The feature vector can be expressed as V i = [device information, operation information, time information], and then convert natural language tasks into computable vector data, so that it can be used for rule comparison and error detection.

[0097] S303: Obtain grid operation task characteristic information according to the characteristic vector.

[0098] Among them, the grid operation task characteristic information can be used for subsequent analysis such as task rule comparison and error detection.

[0099] Specifically, in the steps above, the grid operation task text has been broken down into multiple key points. For example, the device is 110kV circuit breaker A1, the operation is open, and the time is 10:30. To ensure that all information is clear and complete, each key point can be organized into task feature information according to specific rules. This ensures that the dispatcher can directly understand the content of the task.

[0100] For example, if the current operation task is "110kVA line maintenance, you need to first disconnect the 110kV circuit breaker A1, and then open the 110kV disconnector G1, the operation time is 10:30-12:30." Through the previous analysis, the key information of the task can be extracted, and then the task can be understood more intuitively, and problems can be discovered quickly. If there is a problem with the task, such as an error in the operation sequence, the staff can be notified immediately to make modifications to avoid accidents during execution. This not only reduces human errors, but also makes the entire scheduling process more intelligent and efficient.

[0101] The power grid operation task processing method proposed in the embodiment of the present application can accurately identify key information such as equipment, operation and time in the task, making the task description clearer and more structured, facilitating the system to perform rule comparison, error detection and intelligent optimization, reducing human understanding bias, and improving the accuracy and automation of task analysis, thereby enhancing the intelligence and safety of power grid dispatching operations.

[0102] Figure 4 This is a flow chart of the third embodiment of the method for processing power grid operation tasks provided by this application. Figure 4 As shown, in Figure 2 Based on the embodiment, the grid operation task characteristic information is compared with the preset grid operation task rules to obtain the task comparison results, including:

[0103] S401. Determine operation step characteristic information, equipment logic characteristic information, and time logic characteristic information according to power grid operation task characteristic information.

[0104] Operational step feature information refers to the order of all operations within a task, such as disconnecting the circuit breaker first and then opening the disconnector. Device logic feature information refers to the relationships between devices, such as whether a device is shut down and whether closing the switch is permitted. Time logic feature information indicates whether the task's timing is reasonable, such as whether there are any conflicts or if the task's timing exceeds the permitted range. This information is subsequently compared to ensure that the task complies with grid operating standards.

[0105] S402: Compare the operation step feature information with the operation step sequence rules in the preset power grid operation task rules to obtain an operation step comparison result.

[0106] The preset grid operation task rules are based on standard operating procedures, safety regulations, and logic rules used in grid dispatching and industrial operations. The operation step sequence rule means that equipment operations must be performed in a specific safety order.

[0107] S403: Compare the device logic feature information with the device logic operation rules in the preset power grid operation task rules to obtain a device logic comparison result.

[0108] Among them, the equipment logic operation rules can ensure that the equipment operation in the task will not violate the operating logic of the power grid equipment. For example, the device cannot be closed when it is not shut down, the equipment under maintenance cannot perform switching operations, and interrelated equipment cannot have contradictory operations.

[0109] S404: Compare the device logic feature information with the time logic rules in the preset power grid operation task rules to obtain a time logic comparison result.

[0110] Among them, the time logic rule is to ensure that the task time is arranged reasonably. For example, the task time cannot conflict with other tasks, the operation must be completed within the allowed time range, and there must be no contradiction in the order of task times (such as restoring power first and then cutting off power).

[0111] S405 , obtaining a task comparison result based on the operation step comparison result, the device logic comparison result, and the time logic comparison result.

[0112] In this step, the issues identified in the previous steps are comprehensively reviewed to determine whether the grid operation task can be executed. For example, a worker submits a task such as "Disconnect 110kV circuit breaker A1 at 10:30, then open 110kV disconnector G1 at 12:30." After inspection, it is found that the step sequence and device logic are correct, but the timing is incorrect. In this case, the worker can reschedule the task, for example, to 13:00, and the task will pass review.

[0113] The grid operation task processing method proposed in the embodiment of the present application comprehensively checks the rationality and safety of grid operation tasks through operation step verification, equipment logic verification and time schedule comparison, which can effectively reduce operational errors, avoid task conflicts, and improve the safety and execution efficiency of grid dispatching, thereby realizing more intelligent and precise grid task management.

[0114] Figure 5 This is a flow chart of the fourth embodiment of the method for processing power grid operation tasks provided by this application. Figure 5 As shown, in Figure 2 Based on the embodiment, if the task comparison result indicates that the grid operation task characteristic information does not meet the preset grid operation task requirements, the grid operation task optimization processing is completed according to the pre-trained language model, including:

[0115] S501. If the task comparison result indicates that the grid operation task characteristic information does not meet the preset grid operation task requirement, determine the steps to be optimized that do not meet the preset grid operation task requirement based on the task comparison result.

[0116] Among them, the steps to be optimized refer to the parts of the task that do not meet the standards and the specific steps that need to be adjusted, such as incorrect operation sequence, conflicting time arrangements, unreasonable equipment operation, etc.

[0117] For example, in a power grid dispatch task, a worker submitted the following task: "Open 110kV disconnector G1 at 10:30 AM, disconnect 110kV circuit breaker A1 at 12:30 PM." The comparison result showed that the operation sequence was incorrect (circuit breaker A1 should be opened first, followed by disconnector G1), while the timing was correct. The final result indicated that the task failed the rule check, and the step to be optimized required adjusting the disconnection sequence. The problem was that A1 should be opened first, followed by G1.

[0118] S502: Determine the characteristic information to be optimized of the step to be optimized according to the step to be optimized and the characteristic information of the power grid operation task.

[0119] Among them, the feature information to be optimized is the key factor that causes the task to fail to meet the standards, such as incorrect operating steps, incorrect equipment logic and time conflicts.

[0120] Specifically, for the step to be optimized identified in the previous step (disconnection sequence error), the corresponding feature information to be optimized can be extracted: the equipment features are 110kV circuit breaker A1 and 110kV disconnector G1; the error type is incorrect operation sequence (opening G1 before disconnecting A1); and the optimization direction is to adjust the sequence so that A1 comes before G1. The purpose of this step is to clarify the specific optimization target and provide a basis for subsequent automatic optimization.

[0121] S503: Deploy the feature information to be optimized to the pre-trained language model to complete the optimization processing of the power grid operation task.

[0122] Among them, optimization processing refers to modifying the power grid operation task according to the solution generated by the pre-trained language model. Specifically, the wrong task is input into the pre-trained language model, and the optimization solution is generated in combination with the standard rules, and then the power grid operation task is modified and optimized according to the optimization solution. For example, the original task is "open the 110kV disconnector G1 at 10:30 and disconnect the 110kV circuit breaker A1 at 12:30", and the optimization solution output by the pre-trained language model is "It is recommended to adjust the operation sequence: first disconnect the 110kV circuit breaker A1 (12:30), and then open the 110kV disconnector G1 (10:30)". Finally, the adjustment suggestion is that according to the power grid operation specifications, the circuit breaker should be disconnected first, and then the disconnector should be opened to ensure safe operation.

[0123] The power grid operation task processing method proposed in the embodiment of the present application realizes the intelligent optimization of power grid operation tasks by automatically identifying task errors, extracting optimization features, generating optimization plans and executing adjustments, reducing the workload of manual modification, improving the efficiency and accuracy of task adjustment, effectively reducing the risk of misoperation in power grid dispatching, and making task execution safer, compliant and intelligent.

[0124] Figure 6 This is a flow chart of the fifth embodiment of the method for processing power grid operation tasks provided by this application. Figure 6 As shown, in Figure 5 Based on the embodiment, the feature information to be optimized is deployed to the pre-trained language model to complete the optimization processing of the power grid operation task, which also includes:

[0125] S601: Deploy the feature information to be optimized to the pre-trained language model to determine the optimization plan for the power grid operation task.

[0126] For example, a dispatcher submits the following task: "Open 110kV disconnector G1 at 10:30, disconnect 110kV circuit breaker A1 at 12:30, and close 220kV circuit breaker B2 at 11:00." Therefore, the optimization options include: incorrect operation sequence (high priority): disconnect A1 first, then disconnect G1, otherwise there is a safety risk; equipment status conflict (highest priority): 220kV circuit breaker B2 is currently under maintenance and cannot be closed; and scheduling conflict (medium priority): the equipment is still in other operation processes at 11:00, which may affect scheduling. Therefore, the final priority information includes: the highest priority (must be optimized immediately) is that the 220kV circuit breaker B2 is not allowed to be closed (involving the equipment status and directly affecting the safety of the power grid system), the high priority (needs to be optimized) is that the disconnection sequence of 110kV circuit breakers A1 and G1 is wrong (affecting operational safety), and the medium priority (can be optimized) is the 11:00 time scheduling conflict (can be adjusted, but will not immediately affect equipment safety).

[0127] S602: Determine priority information of each feature information to be optimized according to the power grid operation task optimization plan.

[0128] Among them, priority information refers to determining which issues are the most critical among multiple errors or multiple optimization points and must be handled first. For example, the priority can be determined based on the level of security risk, or based on the degree of impact on task execution, or based on the urgency of operation time.

[0129] S603: Determine a target power grid operation task optimization scheme in the power grid operation task optimization scheme according to the priority information to complete the optimization process of the power grid operation task.

[0130] The target grid operation task optimization plan involves prioritizing the optimization and adjustment plans that need to be executed first, based on priority, to ensure that the most critical errors are corrected first. In this step, optimization processing involves automatically executing adjustments or providing optimization suggestions based on the target grid operation task optimization plan to ensure that the task ultimately meets grid operation standards.

[0131] For example, based on the task information identified by S601, the "most critical optimization task" is selected as the target optimization plan, that is, the "closing 220kV circuit breaker B2 at 11:00" operation is deleted, and the staff is prompted; the "disconnection order of 110kV circuit breakers A1 and G1" is adjusted; the time conflict problem is not handled immediately (the staff can adjust it manually).

[0132] Therefore, the optimized solution automatically deletes the "Close 220kV circuit breaker B2" operation from the task and notifies the operator that "220kV circuit breaker B2 is currently under maintenance and cannot be closed. This operation has been removed." The task sequence is then adjusted. The original task was to open G1 at 10:30 and disconnect A1 at 12:30 (incorrect), but after optimization, it becomes disconnect A1 at 10:30 and open G1 at 12:30 (correct). Finally, optional optimization suggestions are provided. Regarding task time conflicts, the power grid system does not automatically adjust, but instead prompts the operator, "The 11:00 task time may conflict with other operations. It is recommended to adjust the execution time." This ultimately optimizes the power grid operation tasks, making them safer and more reasonable.

[0133] The grid operation task processing method proposed in the embodiment of the present application ensures that the adjustment of grid operation tasks is more intelligent and efficient by optimizing priority judgment, target optimization scheme screening and optimized execution, avoids low-priority issues from interfering with core operations, and thus improves the safety, rationality and execution efficiency of grid dispatching tasks.

[0134] Figure 7 This is a flow chart of the sixth embodiment of the method for processing power grid operation tasks provided by this application. Figure 7 As shown, in Figure 6 Based on the embodiment, after determining the grid operation task optimization plan, the method further includes:

[0135] S701. Display the power grid operation task optimization plan and the feature information to be optimized to the staff in a visual manner.

[0136] Among them, the visualization method refers to presenting the optimization plan and error points to the staff in an intuitive way such as a graphical interface, table or flow chart to help the staff understand the task optimization suggestions.

[0137] For example, suppose a worker submitted the following task: "Open the 110kV disconnector G1 at 10:30, disconnect the 110kV circuit breaker A1 at 12:30, and close the 220kV circuit breaker B2 at 11:00". After the above S501-S603 analysis, the power grid system found error 1 (high risk): closing the 220kV circuit breaker B2 at 11:00 (the equipment is still under maintenance and cannot be closed), error 2 (medium): opening G1 at 10:30 → disconnecting A1 at 12:30 (the order is wrong, A1 should be disconnected first), error 3 (low priority): task time conflict (adjustment recommended). The power grid system then displays the optimization plan in a visual way, for example, a table showing the optimization suggestions:

[0138]

[0139] Therefore, staff can visually see on the table which operations have problems, which areas need to be optimized, and how tasks are adjusted after optimization.

[0140] S702 : In response to the staff's selection of the power grid operation task optimization solution, determine a target power grid operation task optimization solution to complete the optimization process of the power grid operation task.

[0141] The target grid operation task optimization plan refers to the optimization plan that the staff finally confirms and decides to adopt. For example, different optimization plans are provided in the S701 visual interface, and the staff can manually select the appropriate optimization plan.

[0142] For example, if the staff member chooses to remove only the high-risk errors, further optimization steps would include removing the 11:00 AM closing of the 220kV circuit breaker B2 from the task, retaining the original operation sequence (G1 opened first, A1 disconnected later), and not adjusting the task time (although there was a conflict, the staff member decided not to modify it). After optimization, the final task becomes "Open 110kV disconnector G1 at 10:30 and disconnect 110kV circuit breaker A1 at 12:30." Finally, the staff member is notified that "Task optimization is complete, the high-risk errors have been corrected, and the rest of the task remains unchanged."

[0143] The power grid operation task processing method proposed in the embodiment of the present application improves the transparency and flexibility of power grid operation task adjustment through visual optimization schemes, staff autonomous selection and final optimization execution, allows staff to independently select the most appropriate optimization scheme, avoids system forced modification, improves the controllability and flexibility of scheduling, enhances the intelligence of task adjustment and human-computer collaboration capabilities, and improves scheduling efficiency and the reliability of task execution.

[0144] Figure 8 This is a flow chart of the seventh embodiment of the method for processing power grid operation tasks provided by this application. Figure 8 As shown, in Figure 2 Based on the embodiment, the method further includes:

[0145] S801. Determine, according to a power grid operation task, device nodes and topological connection relationships in the power grid operation task.

[0146] Device nodes refer to key equipment in the power grid, such as substations, lines, circuit breakers, disconnectors, and busbars. Each node represents a physical piece of grid equipment. Topological connections refer to the electrical connections between devices. For example, circuit breaker A1 is connected to transformer T1, and busbar B1 is connected to 110kV line L1 through disconnector G1.

[0147] For example, suppose the task is "110kV line L1 power outage for maintenance, which requires disconnecting circuit breaker A1 first and then opening disconnector G1." In this step, it is necessary to first analyze the device nodes and topological relationships and construct a power grid topology graph. The device nodes are circuit breaker A1, disconnector G1, line L1, and busbar B1, and the connection relationship is busbar B1 - circuit breaker A1 - disconnector G1 - line L1. The purpose of this step is to convert the power grid task into a computable graph structure to provide data support for subsequent topology verification.

[0148] S802: Based on the graph search algorithm and pattern recognition technology, determine whether the device nodes and topological connection relationship meet the preset power grid operation task requirements and obtain the task comparison result.

[0149] Graph search algorithms are used to traverse the grid topology and verify whether tasks adhere to grid safety logic. For example, they check whether equipment is still operational and verify whether the equipment start-up and shutdown sequences are appropriate. Pattern recognition technology uses historical data and standard patterns to match the topology of tasks to determine whether operational specifications are met. For example, anti-misoperation detection can be used to determine whether errors such as "opening an isolating switch under load" have occurred. Grid safety verification verifies that tasks will not cause dangerous conditions such as short circuits or ring network operation.

[0150] For example, through the graph search algorithm, the critical path in the task is found. For example, the rule requires that the circuit breaker A1 must be disconnected first, and then the disconnector G1 is opened. The disconnector G1 cannot be operated with load (that is, the circuit breaker A1 must be disconnected first). Then, the task matching standard mode is entered. If the match is successful, the task meets the standard. If the match fails, an error prompt is returned. Finally, the task comparison result is determined. For example, if the comparison result indicates that the task is correct, it indicates that the topological relationship is correct and the equipment operation sequence meets the requirements. If the comparison result indicates that the task is wrong, it indicates that the risk of load operation has been detected. It is recommended to disconnect the circuit breaker A1 first and then operate the disconnector G1.

[0151] S803: If the task comparison result indicates that the device nodes and topological connection relationship do not meet the preset grid operation task requirements, then the grid operation task optimization process is completed according to the pre-trained language model.

[0152] In this step, the task optimization process can be: (1) task error analysis, the error is that the disconnector G1 cannot be opened when the circuit breaker A1 is closed, then the optimization direction is to adjust the order, first disconnect A1, and then operate to open G1; (2) the pre-trained language model generates an optimization plan, the original task is to open G1 at 10:30 → disconnect A1 at 12:30, the optimization plan is to disconnect A1 at 10:30 → open G1 at 12:30, and finally, the optimization prompt is to recommend adjusting the operation order, first disconnect the circuit breaker A1, and then open the disconnector G1 to prevent misoperation.

[0153] The grid operation task processing method proposed in the embodiment of the present application uses a graph search algorithm and pattern recognition technology, combined with the equipment topology structure, to intelligently verify and optimize the grid operation tasks, ensuring that the equipment connection relationship and operation sequence of the task meet the grid safety standards, effectively reducing the risk of misoperation, avoiding dangerous situations such as opening the disconnector under load, and improving the safety, accuracy and intelligence level of the grid dispatching tasks.

[0154] Figure 9 This is a schematic diagram of the structure of the power grid operation task processing device provided in this application. Figure 9 As shown, the power grid operation task processing device 90 includes a power grid operation task acquisition module 901, a power grid operation task characteristic information acquisition module 902, a task comparison result acquisition module 903 and an optimization processing module 904, wherein,

[0155] A power grid operation task acquisition module 901 is used to acquire power grid operation tasks, where the power grid operation tasks are natural language tasks generated based on power grid scheduling and industrial operations;

[0156] A power grid operation task characteristic information obtaining module 902 is configured to perform semantic analysis on the power grid operation task using a pre-trained language model to obtain power grid operation task characteristic information. The pre-trained language model is trained based on power grid operation rules.

[0157] The task comparison result obtaining module 903 is used to compare the grid operation task characteristic information with the preset grid operation task rules to obtain the task comparison result;

[0158] The optimization processing module 904 is configured to complete the optimization processing of the power grid operation task according to the pre-trained language model if the task comparison result indicates that the characteristic information of the power grid operation task does not meet the preset power grid operation task requirements.

[0159] Furthermore, the grid operation task characteristic information obtaining module 902 further includes:

[0160] Use a pre-trained language model to perform semantic analysis on power grid operation tasks and obtain contextual text information of power grid operation tasks;

[0161] Determine, based on the context text information, a feature vector corresponding to the context text information, the feature vector including device information, time information, and operation information;

[0162] According to the characteristic vector, the characteristic information of the power grid operation task is obtained.

[0163] Furthermore, the task comparison result obtaining module 903 further includes:

[0164] Determine operation step characteristic information, equipment logic characteristic information, and time logic characteristic information based on power grid operation task characteristic information;

[0165] Comparing the operation step feature information with the operation step sequence rules in the preset power grid operation task rules to obtain the operation step comparison results;

[0166] Compare the device logic feature information with the device logic operation rules in the preset power grid operation task rules to obtain the device logic comparison result;

[0167] Compare the device logic feature information with the time logic rules in the preset power grid operation task rules to obtain the time logic comparison results;

[0168] Obtain task comparison results based on the operation step comparison results, device logic comparison results, and time logic comparison results;

[0169] The preset grid operation task rules are based on standard operating procedures, safety specifications and logical rules in grid dispatching and industrial operations.

[0170] Furthermore, the optimization processing module 904 further includes:

[0171] If the task comparison result indicates that the grid operation task characteristic information does not meet the preset grid operation task requirements, then, based on the task comparison result, determining the steps to be optimized that do not meet the preset grid operation task requirements;

[0172] Determining the characteristic information to be optimized of the step to be optimized according to the characteristic information of the step to be optimized and the power grid operation task;

[0173] The feature information to be optimized is deployed to the pre-trained language model to complete the optimization processing of the power grid operation task.

[0174] Furthermore, the optimization processing module 904 further includes:

[0175] Deploy the feature information to be optimized to the pre-trained language model to determine the optimization plan for the power grid operation task;

[0176] According to the power grid operation task optimization plan, determine the priority information of each feature information to be optimized;

[0177] According to the priority information, a target power grid operation task optimization scheme in the power grid operation task optimization scheme is determined to complete the optimization processing of the power grid operation task.

[0178] Furthermore, the optimization processing module 904 further includes:

[0179] Visually display the power grid operation task optimization plan and the characteristics to be optimized to the staff;

[0180] In response to the staff's selection operation of the power grid operation task optimization plan, a target power grid operation task optimization plan is determined to complete the optimization processing of the power grid operation task.

[0181] Furthermore, the optimization processing module 904 further includes:

[0182] According to the power grid operation task, determine the device nodes and topological connection relationship in the power grid operation task;

[0183] Based on graph search algorithms and pattern recognition technology, determine whether the device nodes and topological connection relationships meet the preset power grid operation task requirements and obtain task comparison results.

[0184] If the task comparison result indicates that the device nodes and topological connection relationships do not meet the preset grid operation task requirements, the grid operation task optimization processing is completed based on the pre-trained language model.

[0185] Figure 10 This is a schematic diagram of the structure of the electronic device provided in the embodiment of the present application. Figure 10 As shown, the electronic device 100 includes:

[0186] The electronic device 100 may include one or more processors 1001 , one or more computer-readable storage media memories 1002 , and a communication component 1003 . The processor 1001 , the memory 1002 , and the communication component 1003 are connected via a bus 1004 .

[0187] In a specific implementation process, at least one processor 1001 executes the computer-executable instructions stored in the memory 1002 , so that the at least one processor 1001 performs the above-mentioned power grid operation task processing method.

[0188] The specific implementation process of the processor 1001 can be found in the above method embodiment. Its implementation principle and technical effects are similar and will not be repeated here in this embodiment.

[0189] In the above Figure 10In the illustrated embodiment, it should be understood that the processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASICs), etc. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in the present invention may be directly executed by a hardware processor or by a combination of hardware and software modules in the processor.

[0190] The memory may include a high-speed memory (Random Access Memory, RAM), and may also include a non-volatile memory (NVM), such as at least one disk memory.

[0191] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus. Buses can be classified as address buses, data buses, and control buses. For ease of illustration, the buses in the drawings of this application are not limited to just one bus or just one type of bus.

[0192] The specific implementation of the above operations can be found in the previous embodiments and will not be repeated here.

[0193] Those skilled in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be accomplished by instructions, or by controlling related hardware through instructions. The instructions may be stored in a computer-readable storage medium and loaded and executed by a processor.

[0194] To this end, an embodiment of the present application provides a computer-readable storage medium, which stores a plurality of instructions, and the instructions can be loaded by a processor to execute the steps in any power grid operation task processing method provided in the embodiment of the present application.

[0195] The storage medium may include a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0196] Since the instructions stored in the storage medium can execute the steps in any power grid operation task processing method provided in the embodiments of the present application, the beneficial effects that can be achieved by any power grid operation task processing method provided in the embodiments of the present application can be achieved. Please refer to the previous embodiments for details and will not be repeated here.

[0197] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present application that follow the general principles of the present application and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered as exemplary only, and the true scope and spirit of the present application are indicated by the following claims.

[0198] It should be noted that for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that this application is not limited by the order of the actions described, because according to this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in this specification are all optional embodiments, and the actions and modules involved are not necessarily required by this application.

[0199] It should be further noted that, although the various steps in the flowchart are shown in sequence as indicated by the arrows, these steps are not necessarily performed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps may be performed in other orders. Moreover, at least a portion of the steps in the flowchart may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily performed at the same time, but may be performed at different times. The execution order of these sub-steps or stages is not necessarily to be performed in sequence, but may be performed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0200] It should be understood that the above-described device embodiments are merely illustrative, and the device of the present application may also be implemented in other ways. For example, the division of units / modules in the above-described embodiments is merely a logical functional division, and actual implementations may employ other division methods. For example, multiple units, modules, or components may be combined or integrated into another system, or some features may be omitted or not implemented.

[0201] In addition, unless otherwise specified, the functional units / modules in the various embodiments of the present application may be integrated into a single unit / module, each unit / module may exist physically separately, or two or more units / modules may be integrated together. The aforementioned integrated units / modules may be implemented in the form of hardware or software program modules.

[0202] If the integrated unit / module is implemented in hardware, the hardware may be digital circuits, analog circuits, etc. The physical implementation of the hardware structure includes, but is not limited to, transistors, memristors, etc. Unless otherwise specified, the processor may be any appropriate hardware processor, such as a CPU, GPU, FPGA, DSP, and ASIC. Unless otherwise specified, the storage unit may be any appropriate magnetic storage medium or magneto-optical storage medium, such as resistive random access memory (RRAM), dynamic random access memory (DRAM), static random access memory (SRAM), enhanced dynamic random access memory (EDRAM), high-bandwidth memory (HBM), hybrid memory cube (HMC), etc.

[0203] If the integrated unit / module is implemented in the form of a software program module and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes a number of instructions for enabling a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned memory includes various media that can store program codes, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk.

[0204] In the above embodiments, the description of each embodiment has its own emphasis. For parts not described in detail in a particular embodiment, please refer to the relevant description of other embodiments. The technical features of the above embodiments can be combined in any way. To keep the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0205] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present application that follow the general principles of the present application and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered as exemplary only, and the true scope and spirit of the present application are indicated by the following claims.

[0206] It should be understood that the present application is not limited to the exact structure described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A method for processing power grid operation tasks, characterized in that: include: Acquire a power grid operation task, where the power grid operation task is a natural language task generated based on power grid scheduling and industrial operations; Using a pre-trained language model to perform semantic analysis on the power grid operation task to obtain power grid operation task feature information, the pre-trained language model is trained based on power grid operation rules; Comparing the grid operation task characteristic information with the preset grid operation task rules to obtain a task comparison result; If the task comparison result indicates that the grid operation task characteristic information does not meet the preset grid operation task requirements, the grid operation task optimization processing is completed according to the pre-trained language model.

2. The method for processing power grid operation tasks according to claim 1, characterized in that: The using of the pre-trained language model to perform semantic parsing on the power grid operation task to obtain power grid operation task feature information includes: Using a pre-trained language model to perform semantic parsing on the power grid operation task to obtain contextual text information of the power grid operation task; Determining, based on the context text information, a feature vector corresponding to the context text information, the feature vector including device information, time information, and operation information; According to the characteristic vector, characteristic information of the power grid operation task is obtained.

3. The method for processing power grid operation tasks according to claim 1, characterized in that: Comparing the grid operation task characteristic information with the preset grid operation task rules to obtain a task comparison result, including: Determining operation step characteristic information, device logic characteristic information, and time logic characteristic information based on the power grid operation task characteristic information; Comparing the operation step characteristic information with the operation step sequence rules in the preset power grid operation task rules to obtain an operation step comparison result; Comparing the device logic feature information with the device logic operation rules in the preset power grid operation task rules to obtain a device logic comparison result; Comparing the device logic feature information with the time logic rules in the preset power grid operation task rules to obtain a time logic comparison result; Obtaining a task comparison result according to the operation step comparison result, the device logic comparison result, and the time logic comparison result; The preset grid operation task rules are obtained based on standard operating procedures, safety specifications and logical rules in grid dispatching and industrial operations.

4. The method for processing power grid operation tasks according to claim 1, characterized in that: If the task comparison result indicates that the grid operation task characteristic information does not meet the preset grid operation task requirements, then optimizing the grid operation task according to the pre-trained language model includes: If the task comparison result indicates that the grid operation task characteristic information does not meet the preset grid operation task requirements, determining, based on the task comparison result, a step to be optimized that does not meet the preset grid operation task requirements; Determining the characteristic information to be optimized of the step to be optimized according to the step to be optimized and the characteristic information of the power grid operation task; The feature information to be optimized is deployed to the pre-trained language model to complete the optimization processing of the power grid operation task.

5. The method for processing power grid operation tasks according to claim 4, characterized in that: The step of deploying the feature information to be optimized to the pre-trained language model to complete the optimization process of the power grid operation task includes: Deploying the feature information to be optimized to the pre-trained language model to determine an optimization plan for the power grid operation task; Determining priority information of each of the feature information to be optimized according to the power grid operation task optimization plan; According to the priority information, a target power grid operation task optimization scheme in the power grid operation task optimization scheme is determined to complete the optimization processing of the power grid operation task.

6. The method for processing power grid operation tasks according to claim 5, characterized in that: After determining the grid operation task optimization solution, the method further includes: Presenting the power grid operation task optimization plan and the characteristic information to be optimized to staff in a visual manner; In response to the staff's selection operation of the power grid operation task optimization scheme, a target power grid operation task optimization scheme is determined to complete the optimization processing of the power grid operation task.

7. The method for processing power grid operation tasks according to claim 1 or 2, characterized in that: The method further comprises: Determining, according to the power grid operation task, device nodes and topological connection relationships in the power grid operation task; Based on a graph search algorithm and pattern recognition technology, determining whether the device nodes and the topological connection relationship meet the preset power grid operation task requirements, and obtaining a task comparison result; If the task comparison result indicates that the device node and the topological connection relationship do not meet the preset power grid operation task requirements, the optimization processing of the power grid operation task is completed according to the pre-trained language model.

8. A power grid operation task processing device, characterized in that: include: A power grid operation task acquisition module, configured to acquire power grid operation tasks, wherein the power grid operation tasks are natural language tasks generated based on power grid scheduling and industrial operations; A power grid operation task characteristic information obtaining module is used to perform semantic analysis on the power grid operation task using a pre-trained language model to obtain power grid operation task characteristic information, wherein the pre-trained language model is trained based on power grid operation rules; A task comparison result obtaining module is used to compare the grid operation task characteristic information with the preset grid operation task rules to obtain a task comparison result; The optimization processing module is used to complete the optimization processing of the power grid operation task according to the pre-trained language model if the task comparison result indicates that the power grid operation task characteristic information does not meet the preset power grid operation task requirements.

9. An electronic device, characterized in that: include: a processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 7 when executed by a processor.

11. A power grid operation task processing system, characterized in that: The invention comprises a computer program, which implements the method according to any one of claims 1 to 7 when the computer program is executed by a processor.

Images