Dynamic management and intelligent dispatching method of power distribution network repair work order under extreme disaster

Abstract

The application provides a dynamic management and intelligent dispatching method for power distribution network repair work orders under extreme disasters, and relates to the field of power distribution network emergency management and information technology. The method comprises the following steps: obtaining extreme disaster monitoring data; when the extreme disaster monitoring level reaches the warning level, an audit request of a special repair strategy is pushed to the command end; after receiving the confirmation instruction of the command end, the method automatically switches to the extreme disaster emergency repair mode, constructs a multi-factor fusion model, extracts the social influence factor, fault disposal difficulty factor and team intelligent matching factor corresponding to the repair work order, and calculates the dynamic priority score of the work order; the method matches the best recommended repair team information for the repair work order and generates an intelligent dispatching suggestion sheet, which is pushed to the command end; the repair work order is pushed to the mobile terminal of the best recommended repair team, and the repair work order is received, applied for transfer, and grabbed, so as to realize automatic disaster sensing, intelligent analysis and decision-making, resource optimization and allocation, and precise and efficient dispatching.

Description

Technical Field

[0001] This invention relates to the field of distribution network emergency management and information technology, and in particular to a method for dynamic management and intelligent dispatch of distribution network repair work orders under extreme disasters. Background Technology

[0002] With global climate change and the increasing frequency of extreme weather events such as typhoons, the safe and stable operation of power distribution networks is seriously threatened. Extreme disasters often lead to a large number of densely packed fault points in the power distribution network within a short period of time, resulting in extreme shortages of emergency repair resources. Therefore, how to efficiently and scientifically dispatch emergency repair work orders to restore power supply as quickly as possible and maximize social benefits has become a core challenge for power emergency command.

[0003] Currently, the traditional emergency repair work order dispatch model mainly relies on the manual experience of dispatchers. Dispatchers need to comprehensively consider factors such as fault information, geographical location, and the workload of work teams, and assign tasks via telephone communication. This method has obvious drawbacks: First, in the early stages of a disaster when information is chaotic, manual decision-making is slow and prone to misjudgment and omissions; second, it is difficult to accurately prioritize a large number of work orders, which may lead to delays in power restoration for critical lifeline users such as hospitals and government agencies; third, the lack of consideration for matching the specific skills of work teams with the types of faults may result in repair teams arriving on site being unable to work due to insufficient capabilities or equipment, reducing repair efficiency; in addition, the existing work order management system has a low degree of automation and lacks linkage with meteorological disaster information, failing to form an intelligent closed loop from disaster perception to resource dispatch.

[0004] Therefore, it is necessary to provide a dynamic management and intelligent dispatching method for power distribution network emergency repair work orders under extreme disasters to solve the above-mentioned technical problems. Summary of the Invention

[0005] To address the aforementioned technical problems, this invention provides a dynamic management and intelligent dispatching method for power distribution network emergency repair work orders under extreme disasters. This method solves the problem that existing technologies cannot achieve automatic disaster detection, intelligent analysis and decision-making, optimized resource allocation, and accurate and efficient work order dispatching.

[0006] The present invention provides a method for dynamic management and intelligent dispatch of power distribution network emergency repair work orders under extreme disasters, the method comprising: Extreme disaster monitoring data is acquired in real time through a data interface. The extreme disaster monitoring level corresponding to the extreme disaster monitoring data is compared with the preset warning level. When the extreme disaster monitoring level reaches the preset warning level, the approval request for activating a special emergency repair strategy is pushed to the command terminal. Upon receiving the confirmation instruction from the command terminal, the system automatically switches to the extreme disaster emergency repair mode, constructs a multi-factor fusion model, and extracts social impact factors, fault handling difficulty factors, and team intelligent matching factors for repair work orders generated by distribution network faults, and calculates the dynamic priority score of the work order. Based on the dynamic priority score of the work order, the best recommended emergency repair team information is matched for the emergency repair work order. Based on the dynamic priority score of the work order and the best recommended emergency repair team information, an intelligent dispatch suggestion is generated and pushed to the command terminal for review. Based on the intelligent work order suggestion form reviewed by the command terminal, the emergency repair work order is simultaneously pushed to the mobile terminal of the corresponding best recommended emergency repair team. The best recommended emergency repair team receives, applies for transfer, and accepts the emergency repair work order through the mobile terminal, thus constructing a flexible work order dispatch mechanism.

[0007] Preferably, the step of acquiring extreme disaster monitoring data in real time through a data interface, comparing the extreme disaster monitoring level corresponding to the extreme disaster monitoring data with a preset warning level, and pushing an approval request to activate a special emergency repair strategy to the command terminal when the extreme disaster monitoring level reaches the preset warning level, specifically includes: The standardized message subscription interface published by the power grid resource business platform is invoked to obtain the extreme disaster monitoring data and the corresponding extreme disaster monitoring level in real time; A warning level rule engine is constructed to compare the extreme disaster monitoring level with the preset warning level. If the extreme disaster monitoring level reaches the preset warning level, it is determined that the activation conditions of the special emergency repair strategy are met, and the trigger signal of the special emergency repair strategy is output. Based on the trigger signal, the review request based on a highly interactive pop-up window is pushed to the command terminal via the WebSocket protocol. The review request includes the extreme disaster monitoring data and the scope of activation of the special emergency repair strategy. The command terminal then receives a confirmation instruction or a rejection instruction.

[0008] Preferably, the extraction process of the social impact factors includes: Collect user types within the power distribution network area, configure corresponding user weights according to the user priority of different user types, and simultaneously input the geographical coordinates of different user types to build a user type-user weight-geographic coordinate library; The fault point of the emergency repair work order is obtained, and the GIS geographic information service is invoked to delineate the fault impact range with the fault point as the center. Based on the user type-user weight-geographic coordinate library, extract the user type and corresponding number of users, user weight and geographic coordinates within the scope of the fault impact, and output a detailed dataset of users affected by the fault point. Based on the detailed user impact dataset of the aforementioned fault points, the social impact factor S is calculated using a weighted summation formula, as shown below: In the formula, This represents the user weight for the i-th user type; This represents the number of users of the i-th user type; n represents the total number of user types within the scope of the fault's impact. The social impact factor S is compared with a preset impact range. If the social impact factor S is within the preset impact range, the social impact factor S is determined to be valid and the social impact factor S is output. If the social impact factor S exceeds the preset impact range, the review process of the command terminal is triggered.

[0009] Preferably, the step of obtaining the fault point of the emergency repair work order and calling GIS geographic information services to delineate the fault impact range centered on the fault point specifically includes: Collect and standardize the names of administrative divisions at multiple levels, and establish a database of names of administrative divisions at multiple levels. Assign corresponding name weights to the names of administrative divisions at each level in the multi-level administrative division thesaurus, and construct an address database based on the multi-level administrative division thesaurus, wherein the administrative division names contained in the addresses in the address database are sorted from largest to smallest according to their name weights; Based on the address database, an administrative division name index is constructed using the Lucene search engine, and the file size of the administrative division name index is controlled to output an address retrieval model. Input the geographical coordinates of the fault point of the emergency repair work order into the address retrieval model to obtain the top 10 addresses with the highest matching degree, and calculate the matching degree difference ratio R of the top 3 addresses, as shown in the following formula: In the formula, This represents the highest matching value among the first three addresses; This represents the second highest match value among the first three addresses; Set the matching difference ratio threshold to ,like Then output directly. The corresponding address and the scope of the fault's impact; like If this occurs, the manual delineation process at the command terminal will be triggered.

[0010] Preferably, the extraction process of the fault handling difficulty factor includes: Obtain the text description of the fault phenomenon in the emergency repair work order, and use a pre-trained BERT natural language processing model to perform entity recognition and intent parsing on the text description of the fault phenomenon to extract fault phenomenon keywords. Obtain fault symptom keywords and fault repair times from historical emergency repair work orders. Compare the fault symptom keywords of the current emergency repair work order with those from the historical emergency repair work orders and calculate the similarity. Select the fault repair times of the historical emergency repair work orders with similarity scores higher than a similarity threshold and take the average to obtain a reference fault repair time. ; Construct a fault handling relationship mapping table, and the fault handling relationship mapping table contains the correspondence between fault phenomenon keywords and fault handling basic coefficient K and estimated additional time △T; Based on the fault handling relationship mapping table, the corresponding basic fault handling coefficient K and estimated additional time △T are matched for the fault phenomenon keywords of the emergency repair work order, and the standard handling time is calculated. and the aforementioned fault handling difficulty factor The corresponding formula is as follows: .

[0011] Preferably, the extraction process of the intelligent matching factor for the work group is as follows: A dynamic team capability profile is constructed for the emergency repair team, and the dynamic team capability profile includes skill tags, equipment tags, real-time load value, and location coordinates. Among them, the skill tag is the skill type, the equipment tag is the equipment type, and the real-time load value is the weighted value of the number of work orders that the emergency repair team has not yet completed and the difficulty of the work orders. Based on the fault handling difficulty factor, the fault handling difficulty level is determined. Based on the fault handling difficulty level and combined with the dynamic team capability profile, emergency repair teams with corresponding skill tags and equipment tags are selected. For emergency repair teams with corresponding skill and equipment tags, calculate the team-work order matching score M between the emergency repair team and the emergency repair work order, using the following formula: In the formula, 1 represents the adjustable matching weight; D represents the geographical distance between the location coordinates of the emergency repair team and the geographical coordinates of the fault point in the emergency repair work order; C represents the matching degree between the emergency repair team's skill tags, equipment tags and the fault handling requirements of the emergency repair work order; L represents the real-time load value of the emergency repair team. Select the highest work group-work order matching score As the intelligent matching factor for the work group, and the maximum work group-work order matching score The corresponding emergency repair team is the best recommended emergency repair team.

[0012] Preferably, the calculation process for the dynamic priority score of the work order includes: The min-max normalization algorithm is used to analyze the social impact factor S and the fault handling difficulty factor. Intelligent matching factors for work teams Normalization is performed, and the normalized social impact factor is output. Fault handling difficulty factor Intelligent matching factors for work teams ; Based on the priority requirements for power distribution network repair under extreme disasters, the normalized social impact factor is... Fault handling difficulty factor Intelligent matching factors for work teams Configure the corresponding priority weights ,and The dynamic priority score of the work order is calculated using a weighted summation formula. .

[0013] Preferably, the step of matching the emergency repair work order with the best recommended emergency repair team information based on the work order's dynamic priority score, generating an intelligent dispatch suggestion based on the work order's dynamic priority score and the best recommended emergency repair team information, and pushing it to the command terminal for review specifically includes: The emergency repair work orders are sorted from high to low according to their dynamic priority scores to generate a work order priority sorting list. Combined with the best recommended emergency repair team corresponding to each emergency repair work order, an intelligent dispatch suggestion form is generated. The intelligent work assignment suggestion is pushed to the command terminal for review, and the command terminal confirms, modifies or rejects the intelligent work assignment suggestion. If the command terminal confirms the intelligent dispatch suggestion, it outputs the confirmed intelligent dispatch suggestion; if the command terminal modifies the intelligent dispatch suggestion, it manually adjusts the priority order of the best recommended emergency repair team or work order and outputs the modified intelligent dispatch suggestion; if the command terminal rejects the intelligent dispatch suggestion, it recalculates the dynamic priority score of the work order and outputs the finally confirmed intelligent dispatch suggestion.

[0014] Preferably, based on the intelligent dispatch suggestion form reviewed by the command terminal, the emergency repair work order is simultaneously pushed to the mobile terminal of the corresponding best recommended emergency repair team. The best recommended emergency repair team receives, applies for transfer, and accepts the emergency repair work order through the mobile terminal, thus constructing a flexible work order dispatch mechanism, specifically including: Based on the intelligent dispatch suggestion form reviewed by the command terminal, the emergency repair work order is synchronously pushed to the mobile terminal of the corresponding best recommended emergency repair team through the MQTT message push service. The best recommended emergency repair team receives, applies for transfer, and accepts the emergency repair work order through the mobile terminal. If the recommended emergency repair team chooses to accept the operation, the execution of the emergency repair work order is confirmed; if the recommended emergency repair team chooses to apply for a transfer operation, the reason for the transfer is filled in and the work order is returned to the command terminal for reassignment; if the emergency repair work order is placed in the public order-grabbing pool, other emergency repair teams can choose to grab the work order and obtain the execution right of the emergency repair work order, thus constructing the flexible work order dispatch mechanism.

[0015] A dynamic management and intelligent dispatching system for power distribution network emergency repair work orders under extreme disasters, the system comprising: The strategy activation module is used to acquire extreme disaster monitoring data in real time through the data interface, compare the extreme disaster monitoring level corresponding to the extreme disaster monitoring data with the preset warning level, and push the approval request for activating the special emergency repair strategy to the command terminal when the extreme disaster monitoring level reaches the preset warning level. The priority calculation module is used to automatically switch to the extreme disaster emergency repair mode after receiving the confirmation instruction from the command terminal, construct a multi-factor fusion model, extract social impact factor, fault handling difficulty factor and team intelligent matching factor for repair work orders caused by distribution network faults, and calculate the dynamic priority score of the work order. The team matching module is used to match the best recommended emergency repair team information for the emergency repair work order based on the dynamic priority score of the work order, generate an intelligent dispatch suggestion form based on the dynamic priority score of the work order and the best recommended emergency repair team information, and push it to the command terminal for review. The work order dispatch module is used to push the emergency repair work order to the mobile terminal of the corresponding best recommended emergency repair team based on the intelligent work order suggestion form reviewed by the command terminal. The best recommended emergency repair team receives the emergency repair work order, applies for transfer, and accepts the work order through the mobile terminal, thus building a flexible work order dispatch mechanism.

[0016] Compared with related technologies, the dynamic management and intelligent dispatching method for power distribution network emergency repair work orders under extreme disasters provided by this invention has the following beneficial effects: This invention acquires extreme disaster monitoring data in real time through a data interface, compares the extreme disaster monitoring level corresponding to the extreme disaster monitoring data with a preset warning level, and pushes a request to activate a special emergency repair strategy to the command center when the extreme disaster monitoring level reaches the preset warning level. Upon receiving confirmation from the command center, it automatically switches to the extreme disaster emergency repair mode, constructs a multi-factor fusion model, and extracts social impact factors, fault handling difficulty factors, and intelligent team matching factors for repair work orders caused by distribution network faults, and calculates the dynamic priority score of the work order; based on the dynamic priority score of the work order, it determines the emergency repair strategy. Repair work orders are matched with the best recommended emergency repair teams. Based on the dynamic priority score of the work order and the information of the best recommended emergency repair teams, an intelligent dispatch suggestion is generated and pushed to the command center for review. Based on the intelligent dispatch suggestion approved by the command center, the repair work order is simultaneously pushed to the mobile terminal of the corresponding best recommended emergency repair team. The best recommended emergency repair team can receive, apply for transfer, and accept the repair work order through the mobile terminal, thus building a flexible work order dispatch mechanism. This enables automatic disaster detection, intelligent analysis and decision-making, optimized resource allocation, and accurate and efficient dispatch, significantly improving emergency repair efficiency.

[0017] This invention transforms data-driven intelligent decision-making from reliance on human experience into data-driven decision-making through a multi-factor fusion dynamic priority model, improving the scientific rigor and accuracy of work order sorting and dispatch. It automates the entire process from disaster perception to strategy activation and work order dispatch, significantly shortening emergency response time and ensuring rapid deployment of repair forces to the most critical areas. Through precise matching of team capability profiles and fault difficulty analysis, it achieves optimal integration of repair tasks and resource capabilities, avoiding resource misallocation and improving overall repair efficiency. By employing a two-way interactive mechanism involving command center confirmation and team order grabbing / transfer, it ensures system intelligence while providing flexibility in command and execution, enhancing system usability and personnel motivation. This constructs a complete "perception-decision-execution-feedback" business loop, enabling visualized and controllable management of the entire emergency repair process under extreme disasters. Attached Figure Description

[0018] Figure 1 A flowchart illustrating the dynamic management and intelligent dispatching method for power distribution network emergency repair work orders under extreme disasters, provided in an embodiment of the present invention; Figure 2 A system block diagram of a dynamic management and intelligent dispatching system for power distribution network emergency repair work orders under extreme disasters, provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0020] like Figure 1 The diagram shown is a flowchart of a method for dynamic management and intelligent dispatch of power distribution network emergency repair work orders under extreme disasters, provided in an embodiment of the present invention. Figure 1 The execution entity of the method shown can be a software and / or hardware device. The execution entity of this application can include, but is not limited to, at least one of the following: user equipment, network equipment, etc. User equipment can include, but is not limited to, computers, smartphones, personal digital assistants (PDAs), and the aforementioned electronic devices. Network equipment can include, but is not limited to, a single network server, a server group consisting of multiple network servers, or a cloud based on cloud computing consisting of a large number of computers or network servers. Cloud computing is a type of distributed computing, consisting of a super virtual computer composed of a group of loosely coupled computers. This embodiment does not limit this. Steps S1 to S4 are detailed as follows: S1. Real-time acquisition of extreme disaster monitoring data through data interface, comparison of the extreme disaster monitoring level corresponding to the extreme disaster monitoring data with the preset warning level, and when the extreme disaster monitoring level reaches the preset warning level, push the review request for activating special emergency repair strategy to the command terminal. S2, after receiving the confirmation instruction from the command terminal, automatically switch to the extreme disaster emergency repair mode, construct a multi-factor fusion model, extract social impact factor, fault handling difficulty factor and team intelligent matching factor for the repair work order caused by the distribution network fault, and calculate the dynamic priority score of the work order. S3. Based on the dynamic priority score of the work order, match the best recommended emergency repair team information for the emergency repair work order, generate an intelligent dispatch suggestion form based on the dynamic priority score of the work order and the best recommended emergency repair team information, and push it to the command terminal for review. S4. Based on the intelligent work order suggestion form reviewed by the command terminal, the emergency repair work order is simultaneously pushed to the mobile terminal of the corresponding best recommended emergency repair team. The best recommended emergency repair team receives, applies for transfer, and accepts the emergency repair work order through the mobile terminal, thus constructing a flexible work order dispatch mechanism.

[0021] First, extreme disaster monitoring data is collected in real time through standardized data interfaces, including core emergency information such as disaster type, intensity, and warning level. The data collection channels are linked with professional data platforms such as the power grid resource business platform to ensure the real-time nature and accuracy of extreme disaster monitoring data. Then, the collected extreme disaster monitoring levels are precisely compared with preset warning levels in the system. When the extreme disaster monitoring level reaches the preset warning level, a request to activate a special emergency repair strategy is pushed to the distribution network emergency repair command terminal for initial assessment by the designated commander, thus overcoming the lag problem of traditional manual disaster perception.

[0022] After receiving confirmation from the command center, the system automatically switches from the conventional distribution network management mode to the emergency repair mode for extreme disasters, simultaneously loading repair dispatch rules and calculation models adapted to extreme disasters. For all repair work orders generated due to distribution network faults caused by typhoons, a multi-factor fusion model is constructed. Three key factors are extracted from the core impact dimensions of the work orders: a social impact factor based on the scope, type, and number of users affected by the fault; a fault handling difficulty factor based on fault analysis and historical data; and a team intelligent matching factor combining team capabilities and work order requirements. Through multi-factor fusion calculations, the dynamic priority score of each repair work order is quantitatively calculated.

[0023] Based on the dynamic priority score of work orders, combined with the team capability profile and work order fault handling requirements, the system accurately matches each emergency repair work order with the best recommended emergency repair team. The matching process fully considers key factors such as the team's skills, equipment, real-time load, and geographical distance. The system integrates the dynamic priority score, basic fault information, and matching criteria for the best recommended emergency repair team for each emergency repair work order to generate a standardized intelligent dispatch suggestion form, which is then uniformly pushed to the command center for professional review and decision-making. This achieves intelligent generation of dispatch suggestions while retaining the manual review process at the command center, balancing intelligence and decision-making rigor.

[0024] After the command center completes the review, confirmation, or fine-tuning of the intelligent work order suggestion, it synchronizes the emergency repair work order to the mobile terminals of the best recommended emergency repair teams via a professional message push protocol, achieving real-time synchronization of work order information between the command center and the on-site operation team. On-site emergency repair teams can respond to work orders via their mobile terminals, supporting operations such as receiving work orders, requesting transfers when unable to handle the task, and grabbing work orders from the public order-grabbing pool. If a team requests a transfer, the work order will be returned to the command center for re-dispatch. The order-grabbing mechanism provides a flexible task allocation channel for non-urgent work orders, thus constructing a flexible work order dispatch mechanism with two-way interaction between the command center and the operation team. This solves the rigidity problem of the traditional work order dispatch model and improves the flexibility of emergency repair resource allocation and the response efficiency of on-site operations.

[0025] In the specific implementation process, extreme disaster monitoring data is acquired in real time through a data interface. The extreme disaster monitoring level corresponding to the extreme disaster monitoring data is compared with the preset warning level. When the extreme disaster monitoring level reaches the preset warning level, a request to activate a special emergency repair strategy is pushed to the command terminal. This specifically includes: The standardized message subscription interface published by the power grid resource business platform is invoked to obtain the extreme disaster monitoring data and the corresponding extreme disaster monitoring level in real time; A warning level rule engine is constructed to compare the extreme disaster monitoring level with the preset warning level. If the extreme disaster monitoring level reaches the preset warning level, it is determined that the activation conditions of the special emergency repair strategy are met, and the trigger signal of the special emergency repair strategy is output. Based on the trigger signal, the review request based on a highly interactive pop-up window is pushed to the command terminal via the WebSocket protocol. The review request includes the extreme disaster monitoring data and the scope of activation of the special emergency repair strategy. The command terminal then receives a confirmation instruction or a rejection instruction.

[0026] Based on the power grid digital platform and standardized communication protocols, automated integration of disaster monitoring, condition determination, and command interaction is achieved. First, data collection is completed using the standardized message subscription interface of the power grid resource business platform. This method ensures the real-time and standardized nature of extreme disaster monitoring data and corresponding monitoring levels, avoiding information errors caused by data heterogeneity. Second, the system has a built-in early warning level rule engine that automatically compares the real-time collected extreme disaster monitoring levels with preset early warning levels. The rule engine intelligently determines trigger conditions; if the extreme disaster monitoring level meets the criteria, it determines that the conditions for initiating a special emergency repair strategy are met, and outputs the corresponding strategy trigger signal, replacing the inefficient traditional manual determination mode. Finally, based on the strategy trigger signal, a highly interactive pop-up review request is pushed to the command center via the WebSocket protocol. The request fully includes the core data of extreme disaster monitoring and the scope of activation of the special emergency repair strategy, ensuring that the command center can make judgments based on complete information. Simultaneously, the command center can use this interactive channel to provide confirmation or rejection of commands, achieving two-way real-time communication between the system and the command center, ensuring the rigor and timeliness of strategy initiation judgment.

[0027] The extraction process of the social impact factors includes: Collect user types within the power distribution network area, configure corresponding user weights according to the user priority of different user types, and simultaneously input the geographical coordinates of different user types to build a user type-user weight-geographic coordinate library; The fault point of the emergency repair work order is obtained, and the GIS geographic information service is invoked to delineate the fault impact range with the fault point as the center. Based on the user type-user weight-geographic coordinate library, extract the user type and corresponding number of users, user weight and geographic coordinates within the scope of the fault impact, and output a detailed dataset of users affected by the fault point. Based on the detailed user impact dataset of the aforementioned fault points, the social impact factor S is calculated using a weighted summation formula, as shown below: In the formula, This represents the user weight for the i-th user type; This represents the number of users of the i-th user type; n represents the total number of user types within the scope of the fault's impact. The social impact factor S is compared with a preset impact range. If the social impact factor S is within the preset impact range, the social impact factor S is determined to be valid and the social impact factor S is output. If the social impact factor S exceeds the preset impact range, the review process of the command terminal is triggered.

[0028] First, we comprehensively collect data on all user types within the distribution network's power supply area. Based on the principle of prioritizing users who are lifelines for distribution network repair under extreme disasters, we assign corresponding differentiated user weights to different user types. At the same time, we accurately record the geographical coordinate information of various types of users and build a database that establishes a one-to-one correspondence between user types, user weights, and geographical coordinates.

[0029] Secondly, after obtaining the geolocation information of the fault point corresponding to the emergency repair work order, we call professional GIS geographic information services, take the fault point as the geographic core, and combine it with the power supply radius of the distribution network line to delineate the actual power supply impact range caused by the fault, clarify the geographic boundary of factor extraction, and ensure the relevance and accuracy of subsequent user information extraction.

[0030] Subsequently, detailed user data within the affected area of ​​the fault is extracted. Based on the existing user type-user weight-geographic coordinate database, all user types within the defined geographical area affected by the fault are automatically extracted. The actual number of each user type is simultaneously counted, and the corresponding user weights and geographic coordinate information are associated and matched to form a structured dataset of detailed user data affected by the fault point.

[0031] Based on a detailed dataset of users affected by fault points, a weighted summation method is used to quantify the social impact factor. The core approach combines the weights and quantities of each user type to achieve numerical conversion of the factor. Then, the calculated social impact factor is compared with a preset impact range. If the factor value falls within the preset range, it is deemed valid and officially output as the core input factor for dynamic work order priority calculation. If the factor value exceeds the preset range, a manual review process is immediately triggered at the command center. Professional personnel check for data collection and statistical errors, correct them, and recalculate the factor to ensure the accuracy and rationality of the social impact factor and the scientific nature of work order priority calculation.

[0032] The process of obtaining the fault point of the emergency repair work order, calling GIS geographic information services, and delineating the fault impact range centered on the fault point specifically includes: Collect and standardize the names of administrative divisions at multiple levels, and establish a database of names of administrative divisions at multiple levels. Assign corresponding name weights to the names of administrative divisions at each level in the multi-level administrative division thesaurus, and construct an address database based on the multi-level administrative division thesaurus, wherein the administrative division names contained in the addresses in the address database are sorted from largest to smallest according to their name weights; Based on the address database, an administrative division name index is constructed using the Lucene search engine, and the file size of the administrative division name index is controlled to output an address retrieval model. Input the geographical coordinates of the fault point of the emergency repair work order into the address retrieval model to obtain the top 10 addresses with the highest matching degree, and calculate the matching degree difference ratio R of the top 3 addresses, as shown in the following formula: In the formula, This represents the highest matching value among the first three addresses; This represents the second highest match value among the first three addresses; Set the matching difference ratio threshold to ,like Then output directly. The corresponding address and the scope of the fault's impact; like If this occurs, the manual delineation process at the command terminal will be triggered.

[0033] In practical applications, the names of administrative divisions at multiple levels, including provinces, cities, districts / counties, streets, and communities, are collected on a provincial basis. The collected names undergo standardization processes such as deduplication, error correction, and unified formatting to remove invalid and erroneous words. A structured multi-level administrative division name database is established to provide unified and standardized basic vocabulary support for subsequent address matching and ensure the consistency of address retrieval.

[0034] Differentiated name weights are assigned to administrative division names at different levels in the multi-level administrative division name database, and an address database is built. Generally, the names of administrative divisions within the jurisdiction of higher administrative levels and work groups have higher weights. The administrative division names contained in each address in the address database are sorted from high to low according to the name weight, so that address matching prioritizes core administrative division information and improves the accuracy of matching.

[0035] A lightweight Lucene address retrieval model was built, based on an ordered address database. An index of administrative division names was constructed using the Lucene search engine. At the same time, low-value information such as community names and house numbers, which are below the granularity of administrative divisions, was removed through thematic purification. The size of the index file was precisely controlled to avoid redundant data from affecting retrieval efficiency. Finally, an efficient and lightweight address retrieval model was output as the core tool for fault point address matching.

[0036] The geographical coordinates of the fault point in the emergency repair work order are input into the address retrieval model. The top 10 address results with the highest matching degree output by the model are obtained. The matching degree difference ratio of the top 3 addresses is calculated and compared with the system's preset matching degree difference ratio threshold. If the matching degree difference ratio is greater than the matching degree difference ratio threshold, the address matching result is determined to be unique and accurate, and the optimal matching address is directly output. The corresponding fault impact range is then delineated based on the power supply radius of the distribution network line. Otherwise, it indicates that there is ambiguity in the address matching. The system immediately triggers the manual delineation process at the command end, where professional dispatchers determine the fault impact range based on the actual power supply layout of the distribution network to ensure the accuracy of the range delineation.

[0037] The extraction process of the fault handling difficulty factor includes: Obtain the text description of the fault phenomenon in the emergency repair work order, and use a pre-trained BERT natural language processing model to perform entity recognition and intent parsing on the text description of the fault phenomenon to extract fault phenomenon keywords. Obtain fault symptom keywords and fault repair times from historical emergency repair work orders. Compare the fault symptom keywords of the current emergency repair work order with those from the historical emergency repair work orders and calculate the similarity. Select the fault repair times of the historical emergency repair work orders with similarity scores higher than a similarity threshold and take the average to obtain a reference fault repair time. ; Construct a fault handling relationship mapping table, and the fault handling relationship mapping table contains the correspondence between fault phenomenon keywords and fault handling basic coefficient K and estimated additional time △T; Based on the fault handling relationship mapping table, the corresponding basic fault handling coefficient K and estimated additional time △T are matched for the fault phenomenon keywords of the emergency repair work order, and the standard handling time is calculated. and the aforementioned fault handling difficulty factor The corresponding formula is as follows: .

[0038] First, the text description of the fault phenomenon reported on-site in the emergency repair work order is obtained. A pre-trained BERT natural language processing model is used to perform professional entity recognition and intent parsing on the unstructured text content. Through the semantic understanding ability of this model, invalid information is eliminated and fault phenomenon keywords that can represent the core features of the fault are accurately extracted, thereby realizing the transformation of unstructured fault text into structured feature information.

[0039] Then, the historical work order database for power distribution network emergency repairs is retrieved, and the fault phenomenon keywords and actual fault repair times corresponding to all historical emergency repair work orders in the database are extracted. The fault phenomenon keywords extracted from the current emergency repair work order are compared with the fault phenomenon keywords of the historical emergency repair work orders. Historical emergency repair work orders with similarity higher than the system's preset similarity threshold are selected, and their fault repair times are averaged to obtain the reference fault repair time for the current fault.

[0040] By integrating practical experience in power distribution network emergency repair with statistical analysis results of historical emergency repair work orders, a standardized fault handling relationship mapping table is built. The core of this table is to establish a one-to-one correspondence between fault phenomenon keywords and basic fault handling coefficients and estimated additional time. Among them, the basic fault handling coefficients are used to quantify the relative complexity of different faults, while the estimated additional time is configured with specific additional processing time for specific fault types, providing standardized quantitative parameters for the calculation of standard handling time.

[0041] Based on the fault symptoms keywords of the current emergency repair work order, precise matching is performed in the fault handling relationship mapping table to obtain the corresponding basic fault handling coefficients and estimated additional time. Combined with the system's preset benchmark fault handling time, the standard handling time for the fault is calculated. Then, through the conversion rules of time and factors, the standard handling time is converted into a fault handling difficulty factor. The factor value is inversely correlated with the actual difficulty of fault handling, realizing an intuitive quantification of fault handling difficulty. Thus, through data-driven and intelligent algorithms, the subjective error of manual judgment of fault difficulty is avoided, ensuring the scientificity and accuracy of the fault handling difficulty factor calculation.

[0042] The extraction process of the intelligent matching factor for the work group is as follows: A dynamic team capability profile is constructed for the emergency repair team, and the dynamic team capability profile includes skill tags, equipment tags, real-time load value, and location coordinates. Among them, the skill tag is the skill type, the equipment tag is the equipment type, and the real-time load value is the weighted value of the number of work orders that the emergency repair team has not yet completed and the difficulty of the work orders. Based on the fault handling difficulty factor, the fault handling difficulty level is determined. Based on the fault handling difficulty level and combined with the dynamic team capability profile, emergency repair teams with corresponding skill tags and equipment tags are selected. For emergency repair teams with corresponding skill and equipment tags, calculate the team-work order matching score M between the emergency repair team and the emergency repair work order, using the following formula: In the formula, 1 represents the adjustable matching weight; D represents the geographical distance between the location coordinates of the emergency repair team and the geographical coordinates of the fault point in the emergency repair work order; C represents the matching degree between the emergency repair team's skill tags, equipment tags and the fault handling requirements of the emergency repair work order; L represents the real-time load value of the emergency repair team. Select the highest work group-work order matching score As the intelligent matching factor for the work group, and the maximum work group-work order matching score The corresponding emergency repair team is the best recommended emergency repair team.

[0043] First, a comprehensive and dynamic capability profile is constructed for each emergency repair team. This profile is a digital representation of the team's capabilities, and it includes four core dimensions: skill tags, equipment tags, real-time load values, and location coordinates. Among them, skill tags indicate the types of distribution network emergency repair skills possessed by the emergency repair team, equipment tags specify the types of professional operation equipment equipped by the emergency repair team, real-time load values ​​are a comprehensive load index calculated by combining the number of incomplete work orders of the emergency repair team with the difficulty of handling each work order's faults, and location coordinates are the geographical information of the emergency repair team's permanent operating location. Moreover, the dynamic team capability profile will be dynamically updated according to the emergency repair team's skills, equipment, and operating status to ensure consistency with the actual capabilities on site.

[0044] Based on the extracted fault handling difficulty factors, the fault handling difficulty level of the current emergency repair work order is determined. Combined with this level, all emergency repair teams are accurately screened. Based on the dynamic team capability profile, emergency repair teams whose skill tags and equipment tags cannot match the fault handling skills and equipment requirements are eliminated. Only emergency repair teams with the corresponding operational capabilities are retained as candidate emergency repair teams, thus avoiding resource mismatch problems from the capability side.

[0045] For the selected candidate repair teams, a team-work order matching score is calculated. This score comprehensively considers three core elements: the geographical distance between the repair team and the fault location, the matching degree between the repair team's skills and equipment tags and the requirements of the repair work order, and the current real-time load value of the repair team. At the same time, adjustable matching weights are assigned to each element, which can be dynamically adjusted according to the needs of repair scenarios under extreme disasters, so as to adapt the matching calculation to the actual situation on site.

[0046] The maximum value is selected from the matching scores of all candidate emergency repair teams. This value is used as the team intelligent matching factor for this emergency repair work order. At the same time, the candidate emergency repair team corresponding to the maximum score is determined as the best recommended emergency repair team for the current emergency repair work order.

[0047] Through the above methods, data-driven intelligent and precise matching of emergency repair teams and emergency repair work orders is achieved. This fully combines the operational capabilities, real-time status, and geographical location of emergency repair teams, avoiding the experience-based resource allocation problems of traditional work dispatch. It not only provides effective resource matching factors for dynamic priority calculation of work orders, but also directly determines the best recommended emergency repair teams, providing team resource basis for the generation of subsequent intelligent work dispatch suggestions, thereby improving the overall efficiency of power distribution network emergency repair from the resource matching level.

[0048] The calculation process for the dynamic priority score of the work order includes: The min-max normalization algorithm is used to analyze the social impact factor S and the fault handling difficulty factor. Intelligent matching factors for work teams Normalization is performed, and the normalized social impact factor is output. Fault handling difficulty factor Intelligent matching factors for work teams ; Based on the priority requirements for power distribution network repair under extreme disasters, the normalized social impact factor is... Fault handling difficulty factor Intelligent matching factors for work teams Configure the corresponding priority weights ,and The dynamic priority score of the work order is calculated using a weighted summation formula. .

[0049] The process of matching the best recommended emergency repair team information for the emergency repair work order based on the dynamic priority score of the work order, generating an intelligent dispatch suggestion based on the dynamic priority score of the work order and the best recommended emergency repair team information, and pushing it to the command terminal for review, specifically includes: The emergency repair work orders are sorted from high to low according to their dynamic priority scores to generate a work order priority sorting list. Combined with the best recommended emergency repair team corresponding to each emergency repair work order, an intelligent dispatch suggestion form is generated. The intelligent work assignment suggestion is pushed to the command terminal for review, and the command terminal confirms, modifies or rejects the intelligent work assignment suggestion. If the command terminal confirms the intelligent dispatch suggestion, it outputs the confirmed intelligent dispatch suggestion; if the command terminal modifies the intelligent dispatch suggestion, it manually adjusts the priority order of the best recommended emergency repair team or work order and outputs the modified intelligent dispatch suggestion; if the command terminal rejects the intelligent dispatch suggestion, it recalculates the dynamic priority score of the work order and outputs the finally confirmed intelligent dispatch suggestion.

[0050] In practical applications, all pending emergency repair work orders are sorted in descending order from high to low based on their dynamic priority scores, forming a standardized work order priority ranking list. Simultaneously, each emergency repair work order is linked to the previously matched best recommended emergency repair team information. Combining basic work order fault information and core team matching criteria, a structured intelligent dispatch suggestion is generated and pushed to the distribution network emergency repair command terminal. The designated commander conducts a professional review based on the actual emergency repair scenario under extreme disaster conditions and resource allocation. The command terminal supports three operations for confirming, modifying, or rejecting the intelligent dispatch suggestion, retaining a human decision-making step, compensating for the limitations of pure algorithm scheduling, and aligning with a two-way interactive dispatch mechanism.

[0051] The system executes differentiated processing procedures based on different review results from the command center: If the command center directly confirms the intelligent dispatch suggestion, the system directly outputs the approved intelligent dispatch suggestion; if the command center needs to adjust it based on the actual situation on site, it can manually modify the best recommended emergency repair team corresponding to the work order, or readjust the work order priority order, and output the modified intelligent dispatch suggestion after completion; if the command center determines that the intelligent dispatch suggestion does not meet the on-site dispatch requirements and rejects it, the system will trigger a recalculation process of the work order's dynamic priority score, and generate an intelligent dispatch suggestion again based on the new calculation result, until the command center completes the final confirmation and outputs the approved intelligent dispatch suggestion.

[0052] The above approach achieves an organic combination of intelligent algorithms and human decision-making, leveraging the advantages of data-driven efficient sorting while ensuring the suitability of dispatch suggestions to the actual disaster relief efforts through professional review at the command center.

[0053] Based on the intelligent work order suggestion form reviewed by the command terminal, the emergency repair work order is simultaneously pushed to the mobile terminal of the corresponding best recommended emergency repair team. The best recommended emergency repair team receives, applies for transfer, and accepts the emergency repair work order through the mobile terminal, thus constructing a flexible work order dispatch mechanism, specifically including: Based on the intelligent dispatch suggestion form reviewed by the command terminal, the emergency repair work order is synchronously pushed to the mobile terminal of the corresponding best recommended emergency repair team through the MQTT message push service. The best recommended emergency repair team receives, applies for transfer, and accepts the emergency repair work order through the mobile terminal. If the recommended emergency repair team chooses to accept the operation, the execution of the emergency repair work order is confirmed; if the recommended emergency repair team chooses to apply for a transfer operation, the reason for the transfer is filled in and the work order is returned to the command terminal for reassignment; if the emergency repair work order is placed in the public order-grabbing pool, other emergency repair teams can choose to grab the work order and obtain the execution right of the emergency repair work order, thus constructing the flexible work order dispatch mechanism.

[0054] After the command center completes the final review of the intelligent work order suggestion, the system, relying on the MQTT professional message push service, accurately synchronizes the complete content of the emergency repair work order, including fault information, handling requirements, and priority, to the mobile terminals of the corresponding best recommended emergency repair teams. This push protocol is adapted to communication environments under extreme disasters, ensuring the real-time and stable transmission of work order information and ensuring that on-site teams receive dispatch instructions as soon as possible.

[0055] The system allows recommended emergency repair teams to perform three types of operations on emergency repair work orders via mobile terminals: receiving, requesting transfer, and accepting work orders. This breaks the limitations of the traditional rigid work assignment model and establishes a flexible work order dispatch mechanism. The system sets differentiated process rules for different operational behaviors of the recommended emergency repair teams: if the team confirms its ability to handle the situation and chooses the receive operation, the work order will be directly confirmed for execution, and the team will immediately enter the on-site repair phase; if the team is unable to execute the work order due to objective reasons such as skills, equipment, or real-time load, it can fill in specific reasons for transfer and submit them to the command center, which will then re-dispatch the work order based on on-site resource conditions.

[0056] For non-emergency repair work orders, the system will include them in a public order-grabbing pool, which will be made available to other repair teams with the corresponding fault handling capabilities. These teams can actively perform the order-grabbing operation through mobile terminals, and after successfully grabbing the order, they will obtain the right to execute the repair work order.

[0057] By standardizing message push, multi-dimensional team operation response, and differentiated follow-up processing rules, a flexible chemical work order dispatch mechanism with two-way interaction between the command end and the on-site operation end has been established. This effectively avoids the rigidity of traditional work dispatch, improves the flexibility of emergency repair resource allocation and on-site response efficiency under extreme disasters such as typhoons, and ensures the efficient implementation of emergency repair tasks.

[0058] like Figure 2 The diagram shown is a system block diagram of a dynamic management and intelligent dispatching system for power distribution network emergency repair work orders under extreme disasters, provided in an embodiment of the present invention. The system includes: The strategy activation module is used to acquire extreme disaster monitoring data in real time through the data interface, compare the extreme disaster monitoring level corresponding to the extreme disaster monitoring data with the preset warning level, and push the approval request for activating the special emergency repair strategy to the command terminal when the extreme disaster monitoring level reaches the preset warning level. The priority calculation module is used to automatically switch to the extreme disaster emergency repair mode after receiving the confirmation instruction from the command terminal, construct a multi-factor fusion model, extract social impact factor, fault handling difficulty factor and team intelligent matching factor for repair work orders caused by distribution network faults, and calculate the dynamic priority score of the work order. The team matching module is used to match the best recommended emergency repair team information for the emergency repair work order based on the dynamic priority score of the work order, generate an intelligent dispatch suggestion form based on the dynamic priority score of the work order and the best recommended emergency repair team information, and push it to the command terminal for review. The work order dispatch module is used to push the emergency repair work order to the mobile terminal of the corresponding best recommended emergency repair team based on the intelligent work order suggestion form reviewed by the command terminal. The best recommended emergency repair team receives the emergency repair work order, applies for transfer, and accepts the work order through the mobile terminal, thus building a flexible work order dispatch mechanism.

[0059] Figure 2 The apparatus of the illustrated embodiment can be used to perform corresponding actions. Figure 1 The steps in the method embodiments shown are implemented in a similar manner and have similar technical effects, and will not be repeated here.

[0060] An electronic device includes a memory and a processor, wherein the memory stores a computer program, and when the processor runs the computer program stored in the memory, the processor executes the steps of the dynamic management and intelligent dispatching method for power distribution network emergency repair work orders under extreme disasters as described in any of the above-mentioned methods.

[0061] like Figure 3 The diagram shown is a hardware structure schematic of an electronic device according to an embodiment of the present invention. The electronic device 30 includes: a processor 31, a memory 32, and a computer program; wherein... The memory 32 is used to store the computer program, and the memory may also be flash memory. The computer program is, for example, an application program or functional module that implements the above method.

[0062] Processor 31 is configured to execute the computer program stored in the memory to implement the various steps performed by the device in the above method. For details, please refer to the relevant descriptions in the preceding method embodiments.

[0063] Alternatively, the memory 32 can be either standalone or integrated with the processor 31.

[0064] When the memory 32 is a device independent of the processor 31, the device may further include: Bus 33 is used to connect the memory 32 and the processor 31.

[0065] A readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the dynamic management and intelligent dispatching method for power distribution network emergency repair work orders under extreme disasters as described above.

[0066] The readable storage medium can be a computer storage medium or a communication medium. A communication medium includes any medium that facilitates the transfer of computer programs from one location to another. A computer storage medium can be any available medium accessible to a general-purpose or special-purpose computer. For example, a readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application-Specific Integrated Circuit (ASIC). Alternatively, the ASIC can be located in a user equipment. Of course, the processor and the readable storage medium can also exist as discrete components in a communication device. The readable storage medium can be a read-only memory (ROM), random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc.

[0067] The present invention also provides a program product including executable instructions stored in a readable storage medium. At least one processor of the device can read the executable instructions from the readable storage medium, and the at least one processor executes the executable instructions to cause the device to implement the methods provided in the various embodiments described above.

[0068] In the embodiments of the above-described device, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly manifested as execution by a hardware processor, or execution by a combination of hardware and software modules within the processor.

[0069] Through the above embodiments, this invention provides a dynamic management and intelligent dispatching method for distribution network emergency repair work orders under extreme disasters. It acquires extreme disaster monitoring data in real time via a data interface, compares the extreme disaster monitoring level corresponding to the monitoring data with a preset warning level, and pushes a request to activate a special repair strategy to the command center when the extreme disaster monitoring level reaches the preset warning level. Upon receiving confirmation from the command center, it automatically switches to the extreme disaster emergency repair mode, constructs a multi-factor fusion model, and extracts social impact factors, fault handling difficulty factors, and intelligent team matching factors from repair work orders generated by distribution network faults, calculating the dynamic optimization of the work order. Priority score; based on the dynamic priority score of the work order, the best recommended emergency repair team information is matched for the emergency repair work order. Based on the dynamic priority score of the corresponding work order and the information of the best recommended emergency repair team, an intelligent dispatch suggestion order is generated and pushed to the command terminal for review. Based on the intelligent dispatch suggestion order reviewed by the command terminal, the emergency repair work order is simultaneously pushed to the mobile terminal of the corresponding best recommended emergency repair team. The best recommended emergency repair team receives the emergency repair work order, applies for transfer, and accepts the work order through the mobile terminal, thus building a flexible work order dispatch mechanism. This enables automatic disaster detection, intelligent analysis and decision-making, optimized resource allocation, and accurate and efficient dispatch, significantly improving emergency repair efficiency.

[0070] This invention transforms decision-making based on human experience into data-driven intelligent decision-making through a multi-factor fusion dynamic prioritization model, improving the scientific rigor and accuracy of sorting and assignment. It automates the entire process from disaster perception to strategy activation and work order assignment, significantly shortening emergency response time and ensuring rapid deployment of repair forces to the most critical areas. By precisely matching team capability profiles with fault difficulty analysis, it achieves optimal integration of repair tasks and resource capabilities, avoiding resource misallocation and improving overall repair efficiency. Through two-way interactive mechanisms such as command-end confirmation and team order grabbing / transfer, it ensures system intelligence while providing flexibility in command and execution, enhancing system usability and personnel motivation. This constructs a complete "perception-decision-execution-feedback" business loop, enabling visualized and controllable management of the entire emergency repair process under extreme disasters.

[0071] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for dynamic management and intelligent dispatch of power distribution network emergency repair work orders under extreme disasters, characterized in that, The method includes: Extreme disaster monitoring data is acquired in real time through a data interface. The extreme disaster monitoring level corresponding to the extreme disaster monitoring data is compared with the preset warning level. When the extreme disaster monitoring level reaches the preset warning level, the approval request for activating a special emergency repair strategy is pushed to the command terminal. Upon receiving the confirmation instruction from the command terminal, the system automatically switches to the extreme disaster emergency repair mode, constructs a multi-factor fusion model, and extracts social impact factors, fault handling difficulty factors, and team intelligent matching factors for repair work orders generated by distribution network faults, and calculates the dynamic priority score of the work order. Based on the dynamic priority score of the work order, the best recommended emergency repair team information is matched for the emergency repair work order. Based on the dynamic priority score of the work order and the best recommended emergency repair team information, an intelligent dispatch suggestion is generated and pushed to the command terminal for review. Based on the intelligent work order suggestion form reviewed by the command terminal, the emergency repair work order is simultaneously pushed to the mobile terminal of the corresponding best recommended emergency repair team. The best recommended emergency repair team receives, applies for transfer, and accepts the emergency repair work order through the mobile terminal, thus constructing a flexible work order dispatch mechanism.

2. The method for dynamic management and intelligent dispatch of power distribution network emergency repair work orders under extreme disasters as described in claim 1, characterized in that, The process involves acquiring extreme disaster monitoring data in real time via a data interface, comparing the extreme disaster monitoring level corresponding to the extreme disaster monitoring data with a preset warning level, and pushing a request to activate a special emergency repair strategy to the command center when the extreme disaster monitoring level reaches the preset warning level. Specifically, this includes: The standardized message subscription interface published by the power grid resource business platform is invoked to obtain the extreme disaster monitoring data and the corresponding extreme disaster monitoring level in real time; A warning level rule engine is constructed to compare the extreme disaster monitoring level with the preset warning level. If the extreme disaster monitoring level reaches the preset warning level, it is determined that the activation conditions of the special emergency repair strategy are met, and the trigger signal of the special emergency repair strategy is output. Based on the trigger signal, the review request based on a highly interactive pop-up window is pushed to the command terminal via the WebSocket protocol. The review request includes the extreme disaster monitoring data and the scope of activation of the special emergency repair strategy. The command terminal then receives a confirmation instruction or a rejection instruction.

3. The method for dynamic management and intelligent dispatch of power distribution network emergency repair work orders under extreme disasters as described in claim 1, characterized in that, The extraction process of the social impact factors includes: Collect user types within the power distribution network area, configure corresponding user weights according to the user priority of different user types, and simultaneously input the geographical coordinates of different user types to build a user type-user weight-geographic coordinate library; The fault point of the emergency repair work order is obtained, and the GIS geographic information service is invoked to delineate the fault impact range with the fault point as the center. Based on the user type-user weight-geographic coordinate library, extract the user type and corresponding number of users, user weight and geographic coordinates within the scope of the fault impact, and output a detailed dataset of users affected by the fault point. Based on the detailed user impact dataset of the aforementioned fault points, the social impact factor S is calculated using a weighted summation formula, as shown below: In the formula, This represents the user weight for the i-th user type; This represents the number of users of the i-th user type; n represents the total number of user types within the scope of the fault's impact. The social impact factor S is compared with a preset impact range. If the social impact factor S is within the preset impact range, the social impact factor S is determined to be valid and the social impact factor S is output. If the social impact factor S exceeds the preset impact range, the review process of the command terminal is triggered.

4. The method for dynamic management and intelligent dispatch of power distribution network emergency repair work orders under extreme disasters as described in claim 1, characterized in that, The process of obtaining the fault point of the emergency repair work order, calling GIS geographic information services, and delineating the fault impact range centered on the fault point specifically includes: Collect and standardize the names of administrative divisions at multiple levels, and establish a database of names of administrative divisions at multiple levels. Assign corresponding name weights to the names of administrative divisions at each level in the multi-level administrative division thesaurus, and construct an address database based on the multi-level administrative division thesaurus, wherein the administrative division names contained in the addresses in the address database are sorted from largest to smallest according to their name weights; Based on the address database, an administrative division name index is constructed using the Lucene search engine, and the file size of the administrative division name index is controlled to output an address retrieval model. Input the geographical coordinates of the fault point of the emergency repair work order into the address retrieval model to obtain the top 10 addresses with the highest matching degree, and calculate the matching degree difference ratio R of the top 3 addresses, as shown in the following formula: In the formula, This represents the highest matching value among the first three addresses; This represents the second highest match value among the first three addresses; Set the matching difference ratio threshold to ,like Then output directly. The corresponding address and the scope of the fault's impact; like If this occurs, the manual delineation process at the command terminal will be triggered.

5. The method for dynamic management and intelligent dispatch of power distribution network emergency repair work orders under extreme disasters as described in claim 1, characterized in that, The extraction process of the fault handling difficulty factor includes: Obtain the text description of the fault phenomenon in the emergency repair work order, and use a pre-trained BERT natural language processing model to perform entity recognition and intent parsing on the text description of the fault phenomenon to extract fault phenomenon keywords. Obtain fault symptom keywords and fault repair times from historical emergency repair work orders. Compare the fault symptom keywords of the current emergency repair work order with those from the historical emergency repair work orders and calculate the similarity. Select the fault repair times of the historical emergency repair work orders with similarity scores higher than a similarity threshold and take the average to obtain a reference fault repair time. ; Construct a fault handling relationship mapping table, and the fault handling relationship mapping table contains the correspondence between fault phenomenon keywords and fault handling basic coefficient K and estimated additional time △T; Based on the fault handling relationship mapping table, the corresponding basic fault handling coefficient K and estimated additional time △T are matched for the fault phenomenon keywords of the emergency repair work order, and the standard handling time is calculated. and the aforementioned fault handling difficulty factor The corresponding formula is as follows: 。 6. The method for dynamic management and intelligent dispatch of power distribution network emergency repair work orders under extreme disasters as described in claim 5, characterized in that, The extraction process of the intelligent matching factor for the work group is as follows: A dynamic team capability profile is constructed for the emergency repair team, and the dynamic team capability profile includes skill tags, equipment tags, real-time load value, and location coordinates. Among them, the skill tag is the skill type, the equipment tag is the equipment type, and the real-time load value is the weighted value of the number of work orders that the emergency repair team has not yet completed and the difficulty of the work orders. Based on the fault handling difficulty factor, the fault handling difficulty level is determined. Based on the fault handling difficulty level and combined with the dynamic team capability profile, emergency repair teams with corresponding skill tags and equipment tags are selected. For emergency repair teams with corresponding skill and equipment tags, calculate the team-work order matching score M between the emergency repair team and the emergency repair work order, using the following formula: In the formula, 1 represents the adjustable matching weight; D represents the geographical distance between the location coordinates of the emergency repair team and the geographical coordinates of the fault point in the emergency repair work order; C represents the matching degree between the emergency repair team's skill tags, equipment tags and the fault handling requirements of the emergency repair work order; L represents the real-time load value of the emergency repair team. Select the highest work group-work order matching score As the intelligent matching factor for the work group, and the maximum work group-work order matching score The corresponding emergency repair team is the best recommended emergency repair team.

7. The method for dynamic management and intelligent dispatch of power distribution network emergency repair work orders under extreme disasters as described in claim 1, characterized in that, The calculation process for the dynamic priority score of the work order includes: The min-max normalization algorithm is used to analyze the social impact factor S and the fault handling difficulty factor. Intelligent matching factors for work teams Normalization is performed, and the normalized social impact factor is output. Fault handling difficulty factor Intelligent matching factors for work teams ; Based on the priority requirements for power distribution network repair under extreme disasters, the normalized social impact factor is... Fault handling difficulty factor Intelligent matching factors for work teams Configure the corresponding priority weights ,and The dynamic priority score of the work order is calculated using a weighted summation formula. .

8. The method for dynamic management and intelligent dispatch of power distribution network emergency repair work orders under extreme disasters according to claim 1, characterized in that, The process of matching the best recommended emergency repair team information for the emergency repair work order based on the dynamic priority score of the work order, generating an intelligent dispatch suggestion based on the dynamic priority score of the work order and the best recommended emergency repair team information, and pushing it to the command terminal for review, specifically includes: The emergency repair work orders are sorted from high to low according to their dynamic priority scores to generate a work order priority sorting list. Combined with the best recommended emergency repair team corresponding to each emergency repair work order, an intelligent dispatch suggestion form is generated. The intelligent work assignment suggestion is pushed to the command terminal for review, and the command terminal confirms, modifies or rejects the intelligent work assignment suggestion. If the command terminal confirms the intelligent dispatch suggestion, it outputs the confirmed intelligent dispatch suggestion; if the command terminal modifies the intelligent dispatch suggestion, it manually adjusts the priority order of the best recommended emergency repair team or work order and outputs the modified intelligent dispatch suggestion; if the command terminal rejects the intelligent dispatch suggestion, it recalculates the dynamic priority score of the work order and outputs the finally confirmed intelligent dispatch suggestion.

9. The method for dynamic management and intelligent dispatch of power distribution network emergency repair work orders under extreme disasters according to claim 1, characterized in that, Based on the intelligent work order suggestion form reviewed by the command terminal, the emergency repair work order is simultaneously pushed to the mobile terminal of the corresponding best recommended emergency repair team. The best recommended emergency repair team receives, applies for transfer, and accepts the emergency repair work order through the mobile terminal, thus constructing a flexible work order dispatch mechanism, specifically including: Based on the intelligent dispatch suggestion form reviewed by the command terminal, the emergency repair work order is synchronously pushed to the mobile terminal of the corresponding best recommended emergency repair team through the MQTT message push service. The best recommended emergency repair team receives, applies for transfer, and accepts the emergency repair work order through the mobile terminal. If the recommended emergency repair team chooses to accept the operation, the execution of the emergency repair work order is confirmed; if the recommended emergency repair team chooses to apply for a transfer operation, the reason for the transfer is filled in and the work order is returned to the command terminal for reassignment; if the emergency repair work order is placed in the public order-grabbing pool, other emergency repair teams can choose to grab the work order and obtain the execution right of the emergency repair work order, thus constructing the flexible work order dispatch mechanism.

10. A dynamic management and intelligent dispatch system for distribution network emergency repair work orders under extreme disasters, applied to the dynamic management and intelligent dispatch method for distribution network emergency repair work orders under extreme disasters as described in any one of claims 1-9, characterized in that, The system includes: The strategy activation module is used to acquire extreme disaster monitoring data in real time through the data interface, compare the extreme disaster monitoring level corresponding to the extreme disaster monitoring data with the preset warning level, and push the approval request for activating the special emergency repair strategy to the command terminal when the extreme disaster monitoring level reaches the preset warning level. The priority calculation module is used to automatically switch to the extreme disaster emergency repair mode after receiving the confirmation instruction from the command terminal, construct a multi-factor fusion model, extract social impact factor, fault handling difficulty factor and team intelligent matching factor for repair work orders caused by distribution network faults, and calculate the dynamic priority score of the work order. The team matching module is used to match the best recommended emergency repair team information for the emergency repair work order based on the dynamic priority score of the work order, generate an intelligent dispatch suggestion form based on the dynamic priority score of the work order and the best recommended emergency repair team information, and push it to the command terminal for review. The work order dispatch module is used to push the emergency repair work order to the mobile terminal of the corresponding best recommended emergency repair team based on the intelligent work order suggestion form reviewed by the command terminal. The best recommended emergency repair team receives the emergency repair work order, applies for transfer, and accepts the work order through the mobile terminal, thus building a flexible work order dispatch mechanism.

Images