A distribution network operation ticket error prevention checking method and system

Abstract

The application discloses a kind of network operation ticket error-proof checking method and system, based on the risk prediction model set, not only the face operation item of current operation ticket is checked, for the operation ticket to be executed currently, it is also combined with current power grid real-time state, environmental parameter realizes operation risk prediction in future time window;Specifically including according to knowledge graph, in combination with the historical operation ticket, fault recording data and historical alarm data stored in history database construct risk prediction model;Receive current operation ticket, collect current power grid real-time state, environmental parameter, according to risk prediction model, check each item of current operation ticket.In addition, in the checking mode, it is combined with identity portrait to check leakage and make up for the lack, set personalized risk prompt content and mode for different operators, so that it is more in line with the cognitive habit of operator, reduce human error, while giving consideration to operation safety and operation experience.

Description

Technical Field

[0001] This invention relates to the field of distribution network operation ticket error prevention processing technology, specifically to a distribution network operation ticket error prevention verification method and system. Background Technology

[0002] Traditional operation ticket verification relies primarily on manual processes. After manual review and modification, the ticket is executed. This method is not only inefficient and time-consuming, but also lacks accuracy and standardization. It depends entirely on the knowledge and experience of the verification personnel and cannot guarantee comprehensive verification of all erroneous operations. While there are existing solutions involving automated operation ticket verification, they only perform logical verification based on the direct relationships between operation items or simply detect the impact of the current operation on the power grid. This relatively simple verification logic still leaves operational vulnerabilities, compromising operational safety and failing to predict operational risks.

[0003] Existing technologies include intelligent error correction methods for operation tickets based on natural language processing. These methods involve inputting an operation ticket to be corrected, extracting the operation tasks and item information from the ticket, and then feeding this information into an operation ticket error correction model for error checking. The error checking results are compared with the corresponding items on the user-uploaded operation ticket to determine whether the correction passes. The operation ticket error correction model is trained using a standard operation ticket corpus based on a Transformer model. Furthermore, methods extract all device type information and corresponding device status from the text of the operation ticket to be corrected, and verify the correctness of the operation process for each device type according to a pre-built operation ticket rule template. However, this method only verifies the operation ticket based on preset verification rules, resulting in incomplete verification logic and potential operational risks.

[0004] Furthermore, during the operation ticket verification process, although the operation ticket is verified, different operators may produce different operation results for the same operation ticket. There is no operation ticket verification method or system that can verify the operator's operation at the same time as verifying the operation ticket.

[0005] As mentioned above, the existing operation verification adopts a unified verification method to verify all operators. For skilled expert operators, the unified verification operation process is relatively redundant, which affects the operation efficiency and user experience. It cannot realize personalized verification methods. How to design a personalized verification method that improves operation accuracy and efficiency while taking into account operation safety is also a current challenge. Summary of the Invention

[0006] The purpose of this invention is to overcome the shortcomings of the prior art and propose a method and system for preventing errors in distribution network operation tickets. Based on a set risk prediction model, it not only verifies the operation items on the current operation ticket, but also combines the real-time status of the power grid and environmental parameters to predict the operation risk within the future time window, thereby improving operation safety. In addition, it also combines identity profiles to fill in gaps and provide operators with personalized verification methods, while taking into account both operation safety and operation experience.

[0007] To achieve the above objectives, in a first aspect, the present invention provides a method for preventing errors in distribution network operation tickets, comprising: A knowledge graph is constructed based on distribution network equipment, protection configuration, automation logic, and operating procedures. A risk prediction model is constructed based on the knowledge graph and combined with historical operation tickets, fault recording data and historical alarm data stored in the historical database. Receive the current operation ticket, collect the current real-time status of the power grid and environmental parameters, and verify the current operation ticket item by item according to the risk prediction model; If the verification reveals any operational risks, a risk warning and the basis for the judgment will be output, along with suggested modifications. If the verification passes, the operator will be notified to perform the operation according to the current operation ticket.

[0008] Optionally, the step of constructing a risk prediction model based on a knowledge graph, combined with historical operation tickets, fault recording data, and historical alarm data stored in a historical database, includes: First, randomly select a historical operation ticket from the historical database. Combine this historical operation ticket with the verification and modification records, extract the operation time corresponding to each operation item in the historical operation ticket, and analyze whether there is any abnormal or alarm data within a preset time window after the operation time of each operation item. If a relationship exists, the knowledge graph is used to analyze whether there is a correlation between the operation item and the abnormal or alarm data. If a correlation exists, a correlation mapping is established between the operation item and the abnormal or alarm data. If no correlation exists, the operation item and the abnormal or alarm data are marked as pending correlation mapping. If it does not exist, select the next historical operation ticket for analysis, and continue until all historical operation tickets have been traversed; All associated mappings established by traversing historical operation tickets are analyzed and processed to establish a set of associated mapping relationships. Based on the set of associated mapping relationships, combined with the corresponding operation items in the corresponding historical operation tickets, the power grid status and environmental parameters of the operation time corresponding to the operation items, a risk prediction model is constructed using a deep learning model or a graph neural network model.

[0009] Optionally, the analysis and processing of all associated mappings established by traversing historical operation tickets includes: If there are different exceptions or alarms corresponding to the same operation item and the number of associated mappings corresponding to the operation item exceeds the preset threshold, then modify the generation rule of the operation item in the operation ticket. If different operation items correspond to the same abnormal or alarm data, the associated mappings are merged; duplicate associated mappings are deduplicated.

[0010] Optionally, after the operator performs the operation according to the current operation ticket, the procedure further includes: If an anomaly or alarm occurs within a preset time window after the current operation ticket is completed, the correlation analysis process will be automatically triggered: If a relationship exists but is not present in the set of relationship mappings, then a new relationship mapping is created to supplement the set of relationship mappings. If no association exists, the operation item and the corresponding abnormal or alarm data are marked as pending association mappings. At the same time, the number of the same pending association mapping in the pending association mapping library is statistically analyzed. If the number of a certain pending association mapping exceeds the first threshold, it is determined as a new association mapping and added to the association mapping relationship set.

[0011] Optionally, the operator performs the operation according to the current operation ticket, including: Create identity profiles for each operator; Based on the identity profile, extract the association mapping related to the operator from all association mappings, and combine the operation duration in the operator's historical operation tickets to obtain the operator's operation style as an identity tag, and bind the identity tag to the identity profile; Risk warnings will be issued to the operator based on the identification tag.

[0012] Optionally, obtaining the operator's operating style as an identity tag includes: Extract historical operation tickets executed by operators, analyze the time interval between each operation item in the historical operation tickets, and extract operation items whose time interval is greater than the average operation time; And extract the operation items that were paused, reviewed, or repeatedly modified during the drafting of operation tickets or simulations; Find and statistically analyze the associated mappings involved by the operator in all associated mappings, and combine the extracted operation items and time intervals to obtain the operator's operation style.

[0013] Optionally, the risk warning method includes one or more of visual, auditory, or tactile methods, and operators can select and set the method according to their own habits to obtain a targeted risk warning method.

[0014] Secondly, the present invention also provides a distribution network operation ticket error prevention and verification system, including: a knowledge graph construction module, a risk prediction model construction module, a verification module and a display module; The knowledge graph construction module constructs a knowledge graph based on distribution network equipment, protection configuration, automation logic, and operating procedures, and sends it to the risk prediction model construction module. The risk prediction model building module receives the knowledge graph, combines it with historical operation tickets, fault recording data and historical alarm data stored in the historical database to build a risk prediction model and sends it to the verification module. The verification module receives the current operation ticket, collects the current real-time status of the power grid and environmental parameters, verifies the current operation ticket item by item according to the risk prediction model, and sends the verification results to the display module. The display module parses the verification results. If there are operational risks in the verification, it outputs risk warnings and the basis for judgment, and provides modification suggestions. If the verification passes, it notifies the operator to perform the operation according to the current operation ticket.

[0015] Optionally, the risk prediction model building module is configured as follows: First, randomly select a historical operation ticket from the historical database. Combine this historical operation ticket with the verification and modification records, extract the operation time corresponding to each operation item in the historical operation ticket, and analyze whether there is any abnormal or alarm data within a preset time window after the operation time of each operation item. If a relationship exists, the knowledge graph is used to analyze whether there is a correlation between the operation item and the abnormal or alarm data. If a correlation exists, a correlation mapping is established between the operation item and the abnormal or alarm data. If no correlation exists, the operation item and the abnormal or alarm data are marked as pending correlation mapping. If it does not exist, select the next historical operation ticket for analysis, and continue until all historical operation tickets have been traversed; All associated mappings established by traversing historical operation tickets are analyzed and processed to establish a set of associated mapping relationships. Based on the set of associated mapping relationships, combined with the corresponding operation items in the corresponding historical operation tickets, the power grid status and environmental parameters of the operation time corresponding to the operation items, a risk prediction model is constructed using a deep learning model or a graph neural network model.

[0016] Optionally, the false verification system further includes: an identity profile drawing module and a risk warning module; The identity profile drawing module creates an identity profile for each operator; it extracts the relevant association mappings of the operator from all association mappings according to the identity profile, and obtains the operator's operation style as an identity tag by combining the operation duration in the operator's historical operation tickets, and binds the identity tag to the identity profile. The risk warning module provides risk warnings to the operator based on the identity tag.

[0017] Compared with the prior art, the technical solution of the present invention has at least the following beneficial effects: The distribution network operation ticket error prevention verification method provided by this invention, based on a set risk prediction model, not only verifies the operation items on the current operation ticket, but also, for the operation ticket to be executed, combines the current real-time state of the power grid and environmental parameters to predict the operation risk within a future time window. That is, it outputs the probability of a specific risk occurring within a specific time window (such as 30 minutes) after executing the operation ticket or a certain operation. For example, it predicts whether the operation will change the short-circuit current level or power flow direction of the power grid, leading to protection mismatch (such as preemptive action of downstream protection), misjudgment of directional protection, or failure of the logic of the standby power supply automatic transfer device, etc., thereby improving the comprehensiveness of the verification and ensuring the safety of operation. In the verification method, an association mapping and a pending association mapping are set. Combined with the knowledge graph, the implicit logical relationships of verification are learned and verified. Anomalies or alarms caused by accidental factors can be eliminated, thereby improving the rigor and comprehensiveness of the verification logic. The verification process incorporates identity profiling to identify and address any gaps. Personalized risk warnings and methods are set for different operators to better align with their cognitive habits, reduce human error, and balance operational safety and user experience. Attached Figure Description

[0018] Figure 1 This is a schematic flowchart of a method for preventing errors in distribution network operation tickets according to an embodiment of the present invention; Figure 2 This is a schematic diagram illustrating the risk warning process for operators performing an operation method according to an embodiment of the present invention. Detailed Implementation

[0019] The following detailed description, in conjunction with the accompanying drawings and specific embodiments, provides a further detailed explanation of the distribution network operation ticket error prevention verification method and system proposed in this invention. The advantages and features of this invention will become clearer from the following description. It should be noted that the accompanying drawings are in a very simplified form and use non-precise proportions, used only to facilitate and clearly illustrate the embodiments of this invention. Please refer to the accompanying drawings to make the objectives, features, and advantages of this invention more apparent and understandable. It should be understood that the structures, proportions, sizes, etc., depicted in the accompanying drawings are only used to complement the content disclosed in the specification, for those skilled in the art to understand and read, and are not intended to limit the implementation conditions of this invention. Therefore, they have no substantial technical significance. Any modifications to the structure, changes in the proportional relationships, or adjustments to the size, without affecting the effects and objectives achieved by this invention, should still fall within the scope of the technical content disclosed in this invention.

[0020] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0021] This invention provides a method for preventing errors in the verification of distribution network operation tickets, such as... Figure 1 As shown, the method specifically includes the following steps: S1. Construct a knowledge graph based on distribution network equipment, protection configuration, automation logic, and operating procedures; S2. Based on the knowledge graph, and combined with historical operation tickets, fault recording data and historical alarm data stored in the historical database, a risk prediction model is constructed; S3. Receive the current operation ticket, collect the current real-time status of the power grid and environmental parameters, and verify the current operation ticket item by item according to the risk prediction model; S4. If the verification reveals any operational risks, output the risk warning and the basis for the judgment, and provide modification suggestions; if the verification passes, notify the operator to perform the operation according to the current operation ticket.

[0022] In some embodiments, the step of constructing a risk prediction model based on a knowledge graph, combined with historical operation tickets, fault recording data, and historical alarm data stored in a historical database, specifically includes: First, randomly select a historical operation ticket from the historical database. Combine this historical operation ticket with the verification and modification records, extract the operation time corresponding to each operation item in the historical operation ticket, and analyze whether there is any abnormal or alarm data within a preset time window after the operation time of each operation item. If a relationship exists, the knowledge graph is used to analyze whether there is a correlation between the operation item and the abnormal or alarm data. If a correlation exists, a correlation mapping is established between the operation item and the abnormal or alarm data. If no correlation exists, the operation item and the abnormal or alarm data are marked as pending correlation mapping. If it does not exist, select the next historical operation ticket for analysis, and continue until all historical operation tickets have been traversed; All associated mappings established by traversing historical operation tickets are analyzed and processed to establish a set of associated mapping relationships. Based on the set of associated mapping relationships, combined with the corresponding operation items in the corresponding historical operation tickets, the power grid status and environmental parameters of the operation time corresponding to the operation items, a risk prediction model is constructed using a deep learning model or a graph neural network model.

[0023] The power grid status data may include power flow, node voltage, branch power, etc., and environmental factors may include the temperature and humidity data at that time.

[0024] In some embodiments, the analysis and processing of all associated mappings established by traversing historical operation tickets specifically includes: if there are different abnormal or alarm data corresponding to the same operation item and the number of associated mappings corresponding to the operation item exceeds a preset threshold, then modify the generation rule of the operation item in the operation ticket; if there are different operation items corresponding to the same abnormal or alarm data, then merge the associated mappings; and deduplicate the same associated mappings.

[0025] In some embodiments, after the operator performs the operation according to the current operation ticket, the method further includes: if an abnormality or alarm occurs within a preset time window after the current operation ticket is completed, then the correlation analysis process is automatically triggered. If a relationship exists but is not present in the set of relationship mappings, then a new relationship mapping is created to supplement the set of relationship mappings. If no association exists, the operation item and the corresponding abnormal or alarm data are marked as pending association mappings. At the same time, the number of the same pending association mapping in the pending association mapping library is statistically analyzed. If the number of a certain pending association mapping exceeds the first threshold, it is determined as a new association mapping and added to the association mapping relationship set.

[0026] Specifically, the preset time window can be selected and set according to different operation items, or it can be set to a uniform fixed duration.

[0027] In some embodiments, such as Figure 2 As shown, the operator performs operations according to the current operation ticket, specifically including: S41. Create identity profiles for each operator; S42. Extract the association mapping related to the operator from all association mappings according to the identity profile, and obtain the operator's operation style as the identity tag by combining the operation duration in the operator's historical operation tickets, and bind the identity tag to the identity profile; S43. Provide risk warnings to the operator based on the identity tag.

[0028] In some embodiments, obtaining the operator's operating style as an identity tag specifically includes: Extract historical operation tickets executed by operators, analyze the time interval between each operation item in the historical operation tickets, and extract operation items whose time interval is greater than the average operation time; And extract the operation items that were paused, reviewed, or repeatedly modified during the drafting of operation tickets or simulations; Find and statistically analyze the associated mappings involved by the operator in all associated mappings, and combine the extracted operation items and time intervals to obtain the operator's operation style.

[0029] Specifically, the operating style may include, but is not limited to, "operational proficiency," "specialty," and "operational risk." For example, for operators with low operational proficiency, i.e., novice operators, their operating style can be set as novice, cautious, or without special skills, based on the fact that the time interval between each operation is greater than the average operation time and that they review or repeatedly modify multiple operation items during simulations. For skilled operators, their proficiency in a particular operation item can be determined by comparing the time interval between each operation item with the average operation time and their proficiency in the operation item during simulations, such as being proficient in "busbar switching" or "transformer operation."

[0030] Specifically, the operational style also includes "operational risk." For example, if an operator has too many associated mappings, then that operation item carries a high risk. A risk label can be set for that operation item, such as "Live unlocking risk." For the "operational risk" label, when the operator executes an operation ticket containing that operation item, corresponding key prompts and verifications are performed. For instance, after the operator completes the operation item, the status of the power grid nodes involved in that operation item is retrieved again for confirmation, and a risk prompt such as "Please confirm again" is output.

[0031] Specifically, based on the operator profile, the operation of the operator is analyzed. If the operator is found to have a certain type of "operational risk" label for a long time, the standard operating procedure for that operation or a video of an operator who is good at that operation will be pushed to the operator's terminal for learning, or operation suggestions will be given during the operation, such as "Choose to operate XXX first, then operate YYY. This can reduce the power-on time of the equipment and improve the operation efficiency. Do you want to try it?"

[0032] In some embodiments, the risk warning method includes one or more of visual, auditory, or tactile methods, and operators can select and set the method according to their own habits to obtain a targeted risk warning method.

[0033] Specifically, operators can select and set the appropriate risk warning method according to their own habits. Since operators have different preferences, such as some being sensitive to sound, some to sight, and some wanting to receive both visual and tactile cues, the verification system is set to provide visual, auditory, and tactile cues. Operators can combine and select the appropriate cues according to their needs to improve operational safety.

[0034] Based on the same inventive concept, this invention also provides a distribution network operation ticket error prevention and verification system, which specifically includes: a knowledge graph construction module, a risk prediction model construction module, a verification module, and a display module; The knowledge graph construction module constructs a knowledge graph based on distribution network equipment, protection configuration, automation logic, and operating procedures, and sends it to the risk prediction model construction module. The risk prediction model building module receives the knowledge graph, combines it with historical operation tickets, fault recording data and historical alarm data stored in the historical database to build a risk prediction model and sends it to the verification module. The verification module receives the current operation ticket, collects the current real-time status of the power grid and environmental parameters, verifies the current operation ticket item by item according to the risk prediction model, and sends the verification results to the display module. The display module parses the verification results. If there are operational risks in the verification, it outputs risk warnings and the basis for judgment, and provides modification suggestions. If the verification passes, it notifies the operator to perform the operation according to the current operation ticket.

[0035] In some embodiments, the risk prediction model building module is configured as follows: First, randomly select a historical operation ticket from the historical database. Combine this historical operation ticket with the verification and modification records, extract the operation time corresponding to each operation item in the historical operation ticket, and analyze whether there is any abnormal or alarm data within a preset time window after the operation time of each operation item. If a relationship exists, the knowledge graph is used to analyze whether there is a correlation between the operation item and the abnormal or alarm data. If a correlation exists, a correlation mapping is established between the operation item and the abnormal or alarm data. If no correlation exists, the operation item and the abnormal or alarm data are marked as pending correlation mapping. If it does not exist, select the next historical operation ticket for analysis, and continue until all historical operation tickets have been traversed; All associated mappings established by traversing historical operation tickets are analyzed and processed to establish a set of associated mapping relationships. Based on the set of associated mapping relationships, combined with the corresponding operation items in the corresponding historical operation tickets, the power grid status and environmental parameters of the operation time corresponding to the operation items, a risk prediction model is constructed using a deep learning model or a graph neural network model.

[0036] The power grid status data may include power flow, node voltage, branch power, etc., and environmental factors may include the temperature and humidity data at that time.

[0037] In some embodiments, the analysis and processing of all associated mappings established by traversing historical operation tickets specifically includes: if there are different abnormal or alarm data corresponding to the same operation item and the number of associated mappings corresponding to the operation item exceeds a preset threshold, then modify the generation rule of the operation item in the operation ticket; if there are different operation items corresponding to the same abnormal or alarm data, then merge the associated mappings; and deduplicate the same associated mappings.

[0038] In some embodiments, after the operator performs the operation according to the current operation ticket, the method further includes: if an abnormality or alarm occurs within a preset time window after the current operation ticket is completed, then the correlation analysis process is automatically triggered. If a relationship exists but is not present in the set of relationship mappings, then a new relationship mapping is created to supplement the set of relationship mappings. If no association exists, the operation item and the corresponding abnormal or alarm data are marked as pending association mappings. At the same time, the number of the same pending association mapping in the pending association mapping library is statistically analyzed. If the number of a certain pending association mapping exceeds the first threshold, it is determined as a new association mapping and added to the association mapping relationship set.

[0039] Specifically, the preset time window can be selected and set according to different operation items, or it can be set to a uniform fixed duration.

[0040] In some embodiments, the false verification system further includes an identity profile drawing module and a risk warning module; The identity profile drawing module creates an identity profile for each operator; it extracts the relevant association mappings of the operator from all association mappings according to the identity profile, and obtains the operator's operation style as an identity tag by combining the operation duration in the operator's historical operation tickets, and binds the identity tag to the identity profile. The risk warning module provides risk warnings to the operator based on the identity tag.

[0041] In some embodiments, obtaining the operator's operating style as an identity tag specifically includes: Extract historical operation tickets executed by operators, analyze the time interval between each operation item in the historical operation tickets, and extract operation items whose time interval is greater than the average operation time; And extract the operation items that were paused, reviewed, or repeatedly modified during the drafting of operation tickets or simulations; Find and statistically analyze the associated mappings involved by the operator in all associated mappings, and combine the extracted operation items and time intervals to obtain the operator's operation style.

[0042] Specifically, the operating style may include, but is not limited to, "operational proficiency," "specialty," and "operational risk." For example, for operators with low operational proficiency, i.e., novice operators, their operating style can be set as novice, cautious, or without special skills, based on the fact that the time interval between each operation is greater than the average operation time and that they review or repeatedly modify multiple operation items during simulations. For skilled operators, their proficiency in a particular operation item can be determined by comparing the time interval between each operation item with the average operation time and their proficiency in the operation item during simulations, such as being proficient in "busbar switching" or "transformer operation."

[0043] Specifically, the operational style also includes "operational risk." For example, if an operator has too many associated mappings, then that operation item carries a high risk. A risk label can be set for that operation item, such as "Live unlocking risk." For the "operational risk" label, when the operator executes an operation ticket containing that operation item, corresponding key prompts and verifications are performed. For instance, after the operator completes the operation item, the status of the power grid nodes involved in that operation item is retrieved again for confirmation, and a risk prompt such as "Please confirm again" is output.

[0044] Specifically, the verification system may also include a training module. The verification system analyzes the operator's actions based on the operator profile. If it detects that the operator consistently exhibits a certain type of "operational risk" label, it pushes the standard operating procedure for that operation or a video of an operator proficient in that operation to the operator's terminal for learning. Alternatively, it may provide operational suggestions during the operation, such as, "Choose to operate XXX first, then YYY. This can reduce the equipment's power-on time and improve operational efficiency. Would you consider trying this?"

[0045] In some embodiments, the verification system updates the identity profile periodically to improve the operational efficiency of the operator.

[0046] Based on the same inventive concept, embodiments of the present invention also provide an electronic device, which may include, but is not limited to: a processor and a memory; the memory for storing computer programs; and the processor for executing the method shown in any embodiment of the present invention by invoking the computer programs.

[0047] The processor can be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this invention. The processor can also be a combination that implements computational functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0048] The memory may be ROM (Read Only Memory) or other types of static storage devices capable of storing static information and instructions, RAM (Random Access Memory) or other types of dynamic storage devices capable of storing information and instructions, or EEPROM (Electrically Erasable Programmable Read Only Memory), CD-ROM (Compact Disc Read Only Memory) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited to these.

[0049] The memory stores application code (computer program) that executes the present invention, and its execution is controlled by a processor. The processor executes the application code stored in the memory to implement the content shown in the foregoing method embodiments.

[0050] This invention provides a computer-readable storage medium storing a computer program that, when run on a computer, enables the computer to execute the corresponding content in the aforementioned method embodiments.

[0051] It should be noted that the apparatus and methods disclosed in the embodiments herein can also be implemented in other ways. The apparatus embodiments described above are merely illustrative; for example, the flowcharts and block diagrams in the accompanying drawings show the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to various embodiments herein. In this regard, each block in a flowchart or block diagram may represent a module, program, or part of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram and / or flowchart, and combinations of blocks in block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system to perform the specified function or action, or can be implemented using a combination of dedicated hardware and computer instructions.

[0052] In addition, the functional modules in the various embodiments of this article can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0053] Although the present invention has been described in detail through the preferred embodiments above, it should be understood that the above description should not be considered as a limitation of the present invention. Various modifications and substitutions to the present invention will be apparent to those skilled in the art after reading the above description. Therefore, the scope of protection of the present invention should be defined by the appended claims.

Claims

1. A method for preventing errors in distribution network operation tickets, characterized in that, include: A knowledge graph is constructed based on distribution network equipment, protection configuration, automation logic, and operating procedures. A risk prediction model is constructed based on the knowledge graph and combined with historical operation tickets, fault recording data and historical alarm data stored in the historical database. Receive the current operation ticket, collect the current real-time status of the power grid and environmental parameters, and verify the current operation ticket item by item according to the risk prediction model; If the verification reveals any operational risks, output the risk warning and the basis for the judgment, and provide modification suggestions; If the verification passes, the operator will be notified to perform the operation according to the current operation ticket.

2. The method for preventing errors in distribution network operation tickets as described in claim 1, characterized in that, The risk prediction model is constructed based on a knowledge graph, combined with historical operation tickets, fault recording data, and historical alarm data stored in a historical database, including: First, randomly select a historical operation ticket from the historical database. Combine this historical operation ticket with the verification and modification records, extract the operation time corresponding to each operation item in the historical operation ticket, and analyze whether there is any abnormal or alarm data within a preset time window after the operation time of each operation item. If a relationship exists, the knowledge graph is used to analyze whether there is a correlation between the operation item and the abnormal or alarm data. If a correlation exists, a correlation mapping is established between the operation item and the abnormal or alarm data. If no correlation exists, the operation item and the abnormal or alarm data are marked as pending correlation mapping. If it does not exist, select the next historical operation ticket for analysis, and continue until all historical operation tickets have been traversed; All associated mappings established by traversing historical operation tickets are analyzed and processed to establish a set of associated mapping relationships. Based on the set of associated mapping relationships, combined with the corresponding operation items in the corresponding historical operation tickets, the power grid status and environmental parameters of the operation time corresponding to the operation items, a risk prediction model is constructed using a deep learning model or a graph neural network model.

3. The method for preventing errors in distribution network operation tickets as described in claim 2, characterized in that, The analysis and processing of all associated mappings established by traversing historical operation tickets includes: If there are different exceptions or alarms corresponding to the same operation item and the number of associated mappings corresponding to the operation item exceeds the preset threshold, then modify the generation rule of the operation item in the operation ticket. If different operation items correspond to the same abnormal or alarm data, the associated mappings are merged; duplicate associated mappings are deduplicated.

4. The method for preventing errors in distribution network operation tickets as described in claim 2, characterized in that, After the operator performs the operation according to the current operation ticket, it also includes: If an anomaly or alarm occurs within a preset time window after the current operation ticket is completed, the correlation analysis process will be automatically triggered: If a relationship exists but is not present in the set of relationship mappings, then a new relationship mapping is created to supplement the set of relationship mappings. If no association exists, the operation item and the corresponding abnormal or alarm data are marked as pending association mappings. At the same time, the number of the same pending association mapping in the pending association mapping library is statistically analyzed. If the number of a certain pending association mapping exceeds the first threshold, it is determined as a new association mapping and added to the association mapping relationship set.

5. The method for preventing errors in distribution network operation tickets as described in claim 2, characterized in that, The operator performs operations according to the current operation ticket, including: Create identity profiles for each operator; Based on the identity profile, extract the association mapping related to the operator from all association mappings, and combine the operation duration in the operator's historical operation tickets to obtain the operator's operation style as an identity tag, and bind the identity tag to the identity profile; Risk warnings will be issued to the operator based on the identification tag.

6. The method for preventing errors in distribution network operation tickets as described in claim 5, characterized in that, The step of obtaining the operator's operating style as an identity tag includes: Extract historical operation tickets executed by operators, analyze the time interval between each operation item in the historical operation tickets, and extract operation items whose time interval is greater than the average operation time; And extract the operation items that were paused, reviewed, or repeatedly modified during the drafting of operation tickets or simulations; Find and statistically analyze the associated mappings involved by the operator in all associated mappings, and combine the extracted operation items and time intervals to obtain the operator's operation style.

7. The method for preventing errors in distribution network operation tickets as described in claim 5, characterized in that, The risk warning methods include one or more of visual, auditory, or tactile methods. Operators can choose and set the method according to their own habits to obtain a targeted risk warning.

8. A distribution network operation ticket error prevention and verification system, characterized in that, include: The module includes a knowledge graph construction module, a risk prediction model construction module, a validation module, and a display module. The knowledge graph construction module constructs a knowledge graph based on distribution network equipment, protection configuration, automation logic, and operating procedures, and sends it to the risk prediction model construction module. The risk prediction model building module receives the knowledge graph, combines it with historical operation tickets, fault recording data and historical alarm data stored in the historical database to build a risk prediction model and sends it to the verification module. The verification module receives the current operation ticket, collects the current real-time status of the power grid and environmental parameters, verifies the current operation ticket item by item according to the risk prediction model, and sends the verification results to the display module. The display module parses the verification results. If there are operational risks in the verification, it outputs risk warnings and judgment criteria, and provides modification suggestions. If the verification passes, the operator will be notified to perform the operation according to the current operation ticket.

9. The distribution network operation ticket error prevention and verification system as described in claim 8, characterized in that, The risk prediction model construction module is configured as follows: First, randomly select a historical operation ticket from the historical database. Combine this historical operation ticket with the verification and modification records, extract the operation time corresponding to each operation item in the historical operation ticket, and analyze whether there is any abnormal or alarm data within a preset time window after the operation time of each operation item. If a relationship exists, the knowledge graph is used to analyze whether there is a correlation between the operation item and the abnormal or alarm data. If a correlation exists, a correlation mapping is established between the operation item and the abnormal or alarm data. If no correlation exists, the operation item and the abnormal or alarm data are marked as pending correlation mapping. If it does not exist, select the next historical operation ticket for analysis, and continue until all historical operation tickets have been traversed; All associated mappings established by traversing historical operation tickets are analyzed and processed to establish a set of associated mapping relationships. Based on the set of associated mapping relationships, combined with the corresponding operation items in the corresponding historical operation tickets, the power grid status and environmental parameters of the operation time corresponding to the operation items, a risk prediction model is constructed using a deep learning model or a graph neural network model.

10. The distribution network operation ticket error prevention and verification system as described in claim 8, characterized in that, The error prevention verification system also includes: an identity profile drawing module and a risk warning module; The identity profile drawing module creates an identity profile for each operator; it extracts the relevant association mappings of the operator from all association mappings according to the identity profile, and obtains the operator's operation style as an identity tag by combining the operation duration in the operator's historical operation tickets, and binds the identity tag to the identity profile. The risk warning module provides risk warnings to the operator based on the identity tag.

Images