Big data driven cross-regional maintenance personnel collaborative scheduling repair system

Abstract

The application relates to the technical field of maintenance scheduling, and relates to a big-data-driven cross-region maintenance personnel cooperative scheduling and repair system. The system comprises a task analysis module, a task portrait module, an efficiency portrait module, a cooperative scheduling module, a target assignment module and a synchronous updating module. Multi-region heterogeneous repair data is standardized and analyzed to obtain a structured maintenance task list and generate a task feature portrait. The dynamic state, historical efficiency and skill qualification data of maintenance personnel are collected to construct a dynamic efficiency portrait of the personnel. Through cross-region cooperative scheduling decision, executability simulation and efficiency calculation, a target matching assignment list is generated. The target matching assignment list is sent to the work terminal of the schedulable maintenance personnel, and the real-time maintenance state of the multi-region is synchronously updated. The application can improve the efficiency of the big-data-driven cross-region maintenance personnel cooperative scheduling and repair.

Description

Technical Field

[0001] This invention relates to the field of maintenance scheduling technology, and in particular to a big data-driven cross-regional collaborative scheduling and repair reporting system for maintenance personnel. Background Technology

[0002] In cross-regional maintenance scenarios, heterogeneous repair data formats are complex and lack a unified standardized parsing mechanism. This makes it difficult to effectively integrate repair information from different regions and quickly convert it into structured task data that can be directly used for scheduling, thus affecting the rapid response of maintenance tasks. At the same time, existing technologies do not accurately characterize the features of maintenance tasks and fail to fully quantify key dimensions such as task complexity, time sensitivity, and required skills and qualifications, resulting in a lack of scientific basis for matching tasks with personnel.

[0003] The existing dispatching methods fail to fully integrate the dynamic status, historical work efficiency, and skill qualification data of maintenance personnel, making it difficult to form an accurate dynamic performance profile of personnel. When coordinating dispatching across regions, there is a lack of a global optimization decision-making mechanism, which easily leads to problems such as poor adaptability of dispatching plans to actual scenarios and uneven efficiency. Furthermore, the lack of sufficient feasibility verification of the plans results in high dispatching costs and low overall execution efficiency. Therefore, how to improve the efficiency of cross-regional collaborative dispatching and repair reporting of maintenance personnel has become an urgent problem to be solved. Summary of the Invention

[0004] To achieve the above objectives, the present invention provides a big data-driven cross-regional collaborative scheduling and repair reporting system for maintenance personnel, characterized in that the system includes a task parsing module, a task profiling module, an efficiency profiling module, a collaborative scheduling module, a target assignment module, and a synchronization update module, wherein: The task parsing module is used to standardize and parse heterogeneous repair data from multiple regions to obtain structured repair task orders from the multiple regions. The task profiling module is used to process the structured maintenance task sheet into a profile and determine the maintenance task feature profiles for the multi-regional areas. The performance profiling module is used to collect dynamic status data, historical work performance data, and skill qualification data of dispatchable maintenance personnel in the multiple areas in real time, and topologically depict them as dynamic performance profiles of personnel in the multiple areas. The collaborative scheduling module is used to make cross-regional collaborative scheduling decisions by combining the maintenance task feature profile with the personnel dynamic performance profile, so as to obtain the multi-regional collaborative scheduling scheme. The target assignment module is used to perform executability simulation on the collaborative scheduling scheme and calculate the efficiency value of the simulation results to obtain the target matching assignment list of the multi-region. The synchronization update module is used to send the target matching assignment list to the work terminals of the dispatchable maintenance personnel and to synchronously update the real-time maintenance status of the multiple areas.

[0005] In a preferred embodiment, when the task parsing module performs standardized parsing of heterogeneous repair request data from multiple regions to obtain structured repair task orders for those regions, it is specifically used for: Receive heterogeneous repair data from multiple regions, including text description data, voice data, and image data; By identifying the device identification information and fault phenomenon description in the text description data, the text task information of the multi-region is obtained; The voice data is labeled to obtain the location and time information of the multiple regions; By fusing the device model identifier and fault status visual features in the image data, the visual feature information of the multi-region is obtained; The text task information, location information, time information, and visual feature information are formatted and integrated to obtain the multi-region structured maintenance task sheet.

[0006] In a preferred embodiment, when the task profiling module performs profiling processing on the structured maintenance task order to determine the maintenance task feature profiles for the multi-regional areas, it is specifically used for: The key data fields in the structured maintenance task sheet are parsed, including equipment type identifier, fault description text, and urgency level code; The key data fields are divided into task modes to obtain the maintenance task results for the multiple regions. Based on the fault description text and the urgency level code, the complexity and time sensitivity of different tasks in the maintenance task results are quantified to obtain the task complexity coefficient and time sensitivity coefficient of the multi-region. The necessary skills and estimated working hours for the maintenance task are mapped by associating the equipment type identifier and the fault description text. A multi-dimensional feature vector is constructed from the maintenance task results, the task complexity coefficient, the time sensitivity coefficient, the skill qualifications, and the estimated working hours to obtain a multi-region maintenance task feature profile.

[0007] In a preferred embodiment, when the performance profiling module performs real-time collection of dynamic status data, historical operational performance data, and skill qualification data of dispatchable maintenance personnel in the multiple areas, it is specifically used for: The system receives real-time location information and equipment online status from dispatchable maintenance personnel in the multiple regions, forming dynamic status data of the dispatchable maintenance personnel. Based on the historical task record database of the multi-regional area, the task completion rate, average response time and customer satisfaction evaluation of the dispatchable maintenance personnel are determined and integrated into the historical work efficiency data of the dispatchable maintenance personnel. By querying the personnel qualification database of the multiple regions, the certified skill categories, skill level certificate information and operable equipment list of the dispatchable maintenance personnel are determined, and the skill qualification data of the dispatchable maintenance personnel is obtained.

[0008] In a preferred embodiment, when the performance profiling module performs topological mapping to create dynamic performance profiles of personnel in the multi-region area, it is specifically used for: The basic performance vector of the schedulable maintenance personnel is obtained by extracting performance features from the dynamic state data. Dynamic reachability analysis is performed on the historical operational efficiency data to obtain the dynamic reachability vector of the dispatchable maintenance personnel; Multi-level skill mapping is performed on the skill qualification data to obtain the skill adaptation vector of the dispatchable maintenance personnel; The basic performance vector, the dynamic reachability vector, and the skill adaptation vector are vectorized and associated, and the associated results are reduced in dimension and aggregated to obtain the personal dynamic performance vector of the schedulable maintenance personnel. The individual dynamic performance vector is reconstructed in dimensions to obtain the dynamic performance profile of the personnel in the multi-region.

[0009] In a preferred embodiment, when the collaborative scheduling module performs cross-regional collaborative scheduling decision-making by combining the maintenance task feature profile with the personnel dynamic performance profile to obtain the multi-regional collaborative scheduling scheme, it is specifically used for: Using the maintenance task feature profile as the matching dimension, multiple rounds of bidirectional matching are performed with the personnel dynamic performance profile to obtain the initial cross-regional task-person matching pairs in the multi-regional area. Based on the dynamic performance profile of the personnel, the initial cross-regional task-person matching pair is subjected to spatiotemporal constraint verification and performance balance verification to obtain the target feasible matching pair of the multi-regional task-person matching pair. With the optimization objectives of maximizing the overall scheduling efficiency of the multi-region and minimizing the cross-region scheduling cost, the feasible matching pairs of the objectives are globally serialized to obtain the optimized scheduling sequence of the multi-region. The optimized scheduling sequence is structured and encapsulated to obtain the multi-regional collaborative scheduling scheme.

[0010] In a preferred embodiment, when the target assignment module performs an executability simulation of the cooperative scheduling scheme and calculates the performance value of the simulation results to obtain the target matching assignment list for the multi-regional area, it is specifically used for: Configure the simulation execution environment for the multi-region according to the aforementioned collaborative scheduling scheme; In the simulated execution environment, based on the personnel dynamic performance profile, the trajectory simulation of the dispatchable maintenance personnel moving from their current location to the corresponding task location in the maintenance task feature profile is performed to obtain the benchmark simulated trajectory of the multi-region; Multiple perturbation simulations are performed on key nodes in the baseline simulation trajectory to obtain the multi-region perturbation simulation trajectory cluster; By summing the baseline simulated trajectory and the cluster of disturbance simulated trajectories, multi-scenario simulation data of the cooperative scheduling scheme is obtained.

[0011] In a preferred embodiment, when the target assignment module performs performance evaluation of the simulation results to obtain the target matching assignment list for the multi-region area, it is specifically used for: The key indicators of the baseline simulation trajectory are quantified to obtain the basic performance evaluation values ​​of the multi-region; The stability index of the simulated disturbance trajectory cluster is evaluated to obtain the robustness evaluation value of the multi-region scheme. The basic performance evaluation value and the scheme robustness evaluation value are weighted by data to obtain the performance value of the multi-region; The performance value is mapped to the multi-scenario simulation data, and the fused result is reconstructed into a task-oriented structure to obtain the target matching assignment list for the multi-region.

[0012] In a preferred embodiment, the performance value is calculated using the following formula: ; In the formula, The performance value is... The efficiency adjustment coefficient for the baseline simulated trajectory is given. The basic performance evaluation value is... The robust stability coefficient of the simulated perturbation trajectory cluster is given by [reference to a specific parameter]. The robustness evaluation value of the case is given.

[0013] In a preferred embodiment, when the synchronization update module sends the target matching assignment list to the work terminals of the schedulable maintenance personnel and synchronously updates the real-time maintenance status of the multiple areas, it is specifically used for: The target matching assignment list is pushed to the work terminal of the dispatchable maintenance personnel, and the task start confirmation record of the work terminal is confirmed. Based on the task start confirmation record, the task status in the target matching assignment list is updated from pending assignment to started, so as to establish a dynamic execution association between task identifiers and personnel identifiers in the multi-region area; Based on the dynamic execution association, the system continuously receives the on-the-go location information and task completion confirmation information from the work terminal; Based on the location information along the route and the task completion confirmation information, the real-time maintenance status of the multiple areas is updated synchronously.

[0014] Compared with the prior art, the present invention has the following beneficial effects: 1. This invention standardizes and integrates heterogeneous repair data from multiple regions through a task parsing module, accurately extracting key information from text, voice, and images to form a structured repair task sheet. The task profiling module then quantifies core dimensions such as task complexity and time sensitivity to construct a comprehensive repair task feature profile. Simultaneously, relying on an efficiency profiling module, it collects real-time data on the dynamic status, historical work efficiency, and skill qualifications of repair personnel, topologically depicting precise dynamic efficiency profiles of personnel. This enables efficient extraction of core information about tasks and personnel, providing accurate data support for scheduling decisions and improving the relevance of task assignment.

[0015] 2. This invention generates a cross-regional scheduling scheme that balances efficiency and cost through multi-round matching and global optimization by the collaborative scheduling module. Then, through multi-scenario simulation and performance value calculation by the target assignment module, the feasibility and stability of the scheme are ensured. The synchronous update module issues the assignment list in real time and dynamically updates the maintenance status, ensuring that the cross-regional collaborative scheduling is controllable throughout the process. This effectively improves the accuracy and response efficiency of maintenance personnel scheduling, strengthens the synergy and reliability of multi-regional maintenance services, and enhances the overall quality of maintenance services. Attached Figure Description

[0016] Figure 1 This is a system architecture diagram of a big data-driven cross-regional collaborative scheduling and repair reporting system provided in an embodiment of the present invention; The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0017] 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 belong to some, but not all, embodiments of the present invention. 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.

[0018] The terminology used in the embodiments of this invention is for the purpose of describing particular embodiments only and is not intended to limit the invention. The singular forms “said” and “the” as used in the embodiments of this invention and the appended claims are also intended to include the plural forms, and “multiple” generally includes at least two unless the context clearly indicates otherwise.

[0019] Depending on the context, the word "if" or "if" as used here can be interpreted as "when," "when," "in response to determination," or "in response to detection." Similarly, depending on the context, the phrase "if determination" or "if detection (of the stated condition or event)" can be interpreted as "when determination," "in response to determination," "when detection (of the stated condition or event)," or "in response to detection (of the stated condition or event)."

[0020] Furthermore, the timing of the steps in the following method embodiments is merely an example and not a strict limitation.

[0021] In practice, the server-side equipment deployed in a big data-driven cross-regional collaborative dispatch and repair system for maintenance personnel may consist of one or more devices. This system can be implemented as a business instance, a virtual machine, or hardware devices. For example, it can be implemented as a business instance deployed on one or more devices in a cloud node. Simply put, it can be understood as software deployed on a cloud node, providing big data-driven cross-regional collaborative dispatch and repair services to various user terminals. Alternatively, it can be implemented as a virtual machine deployed on one or more devices in a cloud node, with application software installed to manage various user terminals. Or, it can also be implemented as a server composed of numerous identical or different types of hardware devices, with one or more devices configured to provide big data-driven cross-regional collaborative dispatch and repair services to various user terminals.

[0022] In terms of implementation, the big data-driven cross-regional collaborative dispatch and repair system for maintenance personnel and the user terminal are mutually compatible. That is, if the big data-driven cross-regional collaborative dispatch and repair system for maintenance personnel is implemented as an application installed on a cloud service platform, then the user terminal is implemented as a client that establishes a communication connection with the application; or if the big data-driven cross-regional collaborative dispatch and repair system for maintenance personnel is implemented as a website, then the user terminal is implemented as a webpage; or if the big data-driven cross-regional collaborative dispatch and repair system for maintenance personnel is implemented as a cloud service platform, then the user terminal is implemented as a mini-program in an instant messaging application.

[0023] like Figure 1 The figure shown is a system architecture diagram of a big data-driven cross-regional maintenance personnel collaborative scheduling and repair reporting system provided in an embodiment of the present invention.

[0024] The big data-driven cross-regional collaborative dispatch and repair system 100 described in this invention can be located on a cloud server. In terms of implementation, it can be implemented as one or more service devices, as an application installed in the cloud (e.g., a mobile service operator's server, server cluster, etc.), or as a website. Depending on the functions implemented, the big data-driven cross-regional collaborative dispatch and repair system 100 may include a task parsing module 101, a task profiling module 102, a performance profiling module 103, a collaborative dispatching module 104, a target assignment module 105, and a synchronization update module 106. The modules described in this invention can also be called units, referring to a series of computer program segments that can be executed by the processor of an electronic device and perform a fixed function, stored in the memory of the electronic device.

[0025] In this embodiment of the invention, in the big data-driven cross-regional collaborative scheduling and repair system for maintenance personnel, each of the above modules can be implemented independently and can call other modules. Here, "calling" can be understood as a module connecting to multiple modules of another type and providing corresponding services to those connected modules. In the big data-driven cross-regional collaborative scheduling and repair system provided by this embodiment of the invention, the applicable scope of the big data-driven cross-regional collaborative scheduling and repair system architecture can be adjusted by adding modules and directly calling them without modifying the program code, achieving cluster-based horizontal expansion to quickly and flexibly expand the big data-driven cross-regional collaborative scheduling and repair system. In practical applications, the above modules can be set in the same device or different devices, or they can be set in virtual devices, such as service instances in a cloud server.

[0026] The following describes the components and specific workflow of a big data-driven cross-regional collaborative dispatch and repair system for maintenance personnel, using specific examples: The task parsing module 101 is used to standardize and parse heterogeneous repair data from multiple regions to obtain structured repair task orders from the multiple regions. In this embodiment of the invention, when the task parsing module performs standardized parsing of heterogeneous repair request data from multiple regions to obtain structured repair task orders for the multiple regions, it is specifically used for: Receive heterogeneous repair data from multiple regions, including text description data, voice data, and image data; By identifying the device identification information and fault phenomenon description in the text description data, the text task information of the multi-region is obtained; The voice data is labeled to obtain the location and time information of the multiple regions; By fusing the device model identifier and fault status visual features in the image data, the visual feature information of the multi-region is obtained; The text task information, location information, time information, and visual feature information are formatted and integrated to obtain the multi-region structured maintenance task sheet.

[0027] The system receives repair data through a preset multi-region data receiving port. This port supports UTF-8 character encoding transmission of text description data, WAV or MP3 format reception of voice data, and JPG or PNG pixel format transmission of image data. Each region's repair data carries a unique 6-digit region identifier code. The system accurately distinguishes repair data from different regions by recognizing this identifier code, ensuring that all text description data, voice data, and image data from multiple regions can be completely and error-free recorded by the system.

[0028] The system has a built-in database of device identification information containing unique identification codes and device names for various devices, as well as a keyword database of fault phenomena covering common fault type terms and fault manifestation description terms. By comparing the strings in the text description data with the content of the device identification information database word by word, the corresponding device identification information is extracted. At the same time, the content in the text description data that matches the fault phenomenon keyword database is retrieved to completely extract the fault phenomenon description. Then, these two parts of information are organized according to a fixed format of "device identification information - fault phenomenon description" to form multi-region text task information.

[0029] The system first employs speech-to-text technology, accurately converting speech data into text content by recognizing the correspondence between syllables, intonation, and text characters in the speech data. Subsequently, it calls upon the built-in location information keyword database and time information keyword database. The location information keyword database contains geographically related terms such as city, district, street, and neighborhood, while the time information keyword database contains time-related terms such as year, month, day, hour, and minute. The system retrieves content in the converted text that matches the two keyword databases, extracts the location information and time information respectively, completes the information labeling of the speech data, and obtains location information and time information for multiple regions.

[0030] The system first preprocesses the image data, converting the color image into an 8-bit grayscale image to unify the color mode. Then, it uses a mean filtering algorithm to scan the grayscale image to remove noise interference caused by abnormal fluctuations in pixels. Next, it uses image recognition technology to scan the text areas in the image and compares them one by one with a preset equipment model identification database. This database contains the model text styles and character combinations of various equipment to extract the equipment model identification. At the same time, the preprocessed image is compared with a preset fault state visual feature template library. This template library contains features such as the shape of the damaged parts, color change areas, and abnormal component morphology corresponding to different faults to identify the visual features of the fault state. Finally, the equipment model identification and the fault state visual features are associated and integrated to form multi-region visual feature information.

[0031] The system has a pre-set structured maintenance task sheet template, which includes four fixed columns: text task information, location information, time information, and visual feature information. The text task information column should be filled in the format of "Equipment Identifier: XXX, Fault Phenomenon: XXX". The location information column should be filled in the format of "Province-City-District-Street-Specific Address". The time information column should be filled in the format of "Year-Month-Day Hour:Minute". The visual feature information column should be filled in the format of "Equipment Model: XXX, Fault Visual Feature: XXX". The system will fill in the text task information, location information, time information, and visual feature information obtained from multiple regions into the corresponding columns of the template. After the information is filled in, the system will verify that each column has valid information. Once the information is confirmed to be correct, a multi-region structured maintenance task sheet will be generated.

[0032] The beneficial effects are that, through a standardized and reproducible implementation process, the system can comprehensively and accurately extract key information from heterogeneous repair data from multiple regions, ensuring that information such as equipment identification, fault description, location, time, equipment model, and visual characteristics of the fault is complete and error-free. Furthermore, it integrates these information into a structured maintenance task sheet in a unified format, providing a standardized and high-quality data foundation for subsequent profiling of maintenance tasks and effectively ensuring the efficient advancement of cross-regional maintenance scheduling.

[0033] The task profiling module 102 is used to perform profiling processing on the structured maintenance task order to determine the maintenance task feature profile of the multi-region. In this embodiment of the invention, when the task profiling module performs profiling processing on the structured maintenance task order to determine the maintenance task feature profiles for the multi-regional areas, it is specifically used for: The key data fields in the structured maintenance task sheet are parsed, including equipment type identifier, fault description text, and urgency level code; The key data fields are divided into task modes to obtain the maintenance task results for the multiple regions. Based on the fault description text and the urgency level code, the complexity and time sensitivity of different tasks in the maintenance task results are quantified to obtain the task complexity coefficient and time sensitivity coefficient of the multi-region. The necessary skills and estimated working hours for the maintenance task are mapped by associating the equipment type identifier and the fault description text. A multi-dimensional feature vector is constructed from the maintenance task results, the task complexity coefficient, the time sensitivity coefficient, the skill qualifications, and the estimated working hours to obtain a multi-region maintenance task feature profile.

[0034] The system pre-sets fixed field indexes for structured maintenance task sheets. The "Equipment Type" column corresponds to the equipment type identifier, which consists of 8 digits, with the first 4 digits being the equipment category code and the last 4 digits being the equipment subcategory code. The "Fault Details" column corresponds to the fault description text, and the "Priority" column corresponds to the urgency level code, which consists of 1-3 digits, with 1 digit representing the highest urgency level and 3 digits representing the lowest. By locating these fixed field indexes, the complete information within the corresponding column can be directly extracted to obtain the three key data fields: equipment type identifier, fault description text, and urgency level code.

[0035] The system has a built-in task mode classification rule base, which contains fixed combination patterns of equipment type identifiers and urgency codes. Each combination pattern corresponds to a unique task mode name. At the same time, the rule base has a preset core keyword classification table for fault description text. The system first combines the extracted equipment type identifiers and urgency codes with the combination patterns in the rule base, and then combines the classification of the core keywords in the fault description text to determine the unique task mode corresponding to each task. Tasks with the same task mode are grouped together to form multi-region maintenance task results.

[0036] The system establishes a fault complexity vocabulary classification library, categorizing common words in fault description texts into 5 levels based on their impact scope and repair difficulty. Level 1 words correspond to 1 point, Level 2 to 2 points, Level 3 to 3 points, Level 4 to 4 points, and Level 5 to 5 points. The total score of all words in the fault description text is calculated. Simultaneously, an urgency coding score standard is set: 1 digit corresponds to 3 points, 2 digits to 2 points, and 3 digits to 1 point. The total vocabulary score is added to the urgency coding score, and then divided by 6 to obtain a specific value between 0 and 1, which is the task complexity coefficient. The time sensitivity coefficient is determined based on a fixed correspondence set according to the urgency coding: 1 digit corresponds to 0.9, 2 digits to 0.6, and 3 digits to 0.3. This correspondence directly determines the time sensitivity coefficient of each task, ultimately yielding the task complexity coefficient and time sensitivity coefficient for multiple regions.

[0037] The system constructs an equipment-skill-working-hour association database. The database stores a one-to-one correspondence between all equipment type identifiers and required skill qualifications, as well as standard working hour intervals corresponding to different fault description texts. Each standard working hour interval is divided into three specific duration levels: basic, intermediate, and advanced, based on the differences in fault details. The system uses the extracted equipment type identifier as the primary search condition to match the corresponding required skill qualification name and code in the database. Then, it uses the fault manifestation details in the fault description text as the secondary search condition to select the specific duration matched from the corresponding standard working hour interval as the estimated working hour, thereby associating and mapping the skill qualifications and estimated working hours necessary for the maintenance task result.

[0038] The system assigns dedicated vector dimensions to maintenance task results, task complexity coefficient, time sensitivity coefficient, skill qualification, and estimated working hours. The maintenance task result is filled into the dimension with its corresponding 3-digit pattern code, the skill qualification is filled into the dimension with its corresponding 4-digit qualification code, and the task complexity coefficient, time sensitivity coefficient, and estimated working hours are directly filled into the corresponding dimension with specific values. The values ​​of the five dimensions are integrated in a fixed order of "maintenance task result pattern code - task complexity coefficient - time sensitivity coefficient - skill qualification code - estimated working hours" to form an ordered multi-dimensional feature vector. This multi-dimensional feature vector is the feature profile of maintenance tasks in multiple regions.

[0039] The beneficial effects are that, through a standardized and reproducible process of parsing, partitioning, quantifying, mapping, and vector construction, the core features of maintenance tasks are comprehensively extracted and transformed into standardized maintenance task feature profiles. This ensures that the profiles accurately reflect the key attributes of the tasks, providing high-quality and reliable data support for the accurate matching and efficient scheduling of maintenance personnel across regions, and effectively improving the accuracy of matching maintenance tasks with personnel.

[0040] The performance profiling module 103 is used to collect dynamic status data, historical work performance data and skill qualification data of dispatchable maintenance personnel in the multi-area in real time, and topologically depict them as dynamic performance profiles of personnel in the multi-area. In this embodiment of the invention, when the performance profiling module performs real-time collection of dynamic status data, historical work performance data, and skill qualification data of dispatchable maintenance personnel in the multiple areas, it is specifically used for: The system receives real-time location information and equipment online status from dispatchable maintenance personnel in the multiple regions, forming dynamic status data of the dispatchable maintenance personnel. Based on the historical task record database of the multi-regional area, the task completion rate, average response time and customer satisfaction evaluation of the dispatchable maintenance personnel are determined and integrated into the historical work efficiency data of the dispatchable maintenance personnel. By querying the personnel qualification database of the multiple regions, the certified skill categories, skill level certificate information and operable equipment list of the dispatchable maintenance personnel are determined, and the skill qualification data of the dispatchable maintenance personnel is obtained.

[0041] When the performance profiling module performs topological mapping to create dynamic performance profiles of personnel in the multi-region area, it is specifically used for: The basic performance vector of the schedulable maintenance personnel is obtained by extracting performance features from the dynamic state data. Dynamic reachability analysis is performed on the historical operational efficiency data to obtain the dynamic reachability vector of the dispatchable maintenance personnel; Multi-level skill mapping is performed on the skill qualification data to obtain the skill adaptation vector of the dispatchable maintenance personnel; The basic performance vector, the dynamic reachability vector, and the skill adaptation vector are vectorized and associated, and the associated results are reduced in dimension and aggregated to obtain the personal dynamic performance vector of the schedulable maintenance personnel. The individual dynamic performance vector is reconstructed in dimensions to obtain the dynamic performance profile of the personnel in the multi-region.

[0042] The system uses the GPS positioning module built into the work terminal of the dispatchable maintenance personnel to obtain latitude and longitude coordinates in real time as the current location information. At the same time, it uses the heartbeat packets between the work terminal and the system server to determine the online status of the equipment. The heartbeat packets are sent every 30 seconds. If they are not received for 3 consecutive times, the equipment is judged to be offline. If they are received successfully, the equipment is judged to be online. The real-time location information and the determined online status of the equipment are integrated to form the dynamic status data of the dispatchable maintenance personnel.

[0043] The system accesses a multi-regional historical task record database, which stores task assignment records, task start times, task completion times, and customer ratings for all dispatchable maintenance personnel over the past 12 months. It calculates the total number of assigned tasks and the actual number of tasks completed for each maintenance personnel, dividing the actual number of completed tasks by the total number of assigned tasks to obtain the task completion rate. It also calculates the total time from receiving a task to arriving at the site for each maintenance personnel across all tasks, dividing this time by the total number of tasks to obtain the average response time. Finally, it aggregates customer ratings for each maintenance personnel, taking the arithmetic mean of all ratings as the customer satisfaction evaluation. The task completion rate, average response time, and customer satisfaction evaluation are then integrated in a fixed format of "completion rate - response time - satisfaction" to form historical operational efficiency data for dispatchable maintenance personnel.

[0044] The system calls upon a multi-regional personnel qualification database. This database uses the unique identification code of maintenance personnel as an index and stores the certification skill category, skill level certificate information, and list of operable equipment. By inputting the identification code of the dispatchable maintenance personnel, the system retrieves the corresponding entry in the database, extracts the complete certification skill category, skill level certificate information, and list of operable equipment, and obtains the skill qualification data of the dispatchable maintenance personnel.

[0045] The system verifies the validity of the current location information in the dynamic status data. If the positioning error is no more than 10 meters, it is marked as a valid location and recorded as 1; otherwise, it is recorded as 0. The online status of the equipment is calculated based on the cumulative online time of the day. The cumulative online time is ≥4 hours and recorded as 1, 3-4 hours as 0.7, 2-3 hours as 0.4, and less than 2 hours as 0.1. The valid positioning mark value and the online time conversion value are used as the core performance characteristics. They are combined in the order of "positioning validity - online time conversion value" to obtain the basic performance vector of dispatchable maintenance personnel.

[0046] The system sets classification standards for the average response time in historical operation efficiency data: ≤30 minutes is recorded as 0.9, 30-60 minutes as 0.6, 61-90 minutes as 0.3, and more than 90 minutes as 0.1; task completion rate ≥90% is recorded as 1, 80%-89% as 0.8, 70%-79% as 0.6, and below 70% as 0.3; customer satisfaction rating ≥4.5 is recorded as 1, 4-4.4 as 0.8, 3.5-3.9 as 0.6, and below 3.5 as 0.3. Based on these standards, the three data items are converted into corresponding values ​​and combined in the order of "response time converted value - completion rate converted value - satisfaction value" to obtain the dynamic reachability vector of dispatchable maintenance personnel.

[0047] The system categorizes certified skills in the skill qualification data into three levels: core skills, common skills, and basic skills. Core skills correspond to the equipment maintenance areas where maintenance personnel primarily work, and are denoted as 1. Common skills correspond to auxiliary areas where they are proficient in operation, and are denoted as 0.7. Basic skills correspond to areas where they possess basic operational capabilities, and are denoted as 0.4. Skill level certificates are divided into 5 levels, with level 5 being the highest and denoted as 1, level 4 as 0.8, level 3 as 0.6, level 2 as 0.4, and level 1 as 0.2. The list of operable equipment is divided by the proportion of equipment quantity: ≥10 types are denoted as 1, 5-9 types as 0.7, 3-4 types as 0.4, and less than 3 types as 0.2. The converted values ​​of the three levels are combined in the order of "skill category level - certificate level - proportion of equipment quantity" to obtain the skill adaptation vector for dispatchable maintenance personnel.

[0048] The system concatenates the basic performance vector, dynamic reachability vector, and skill adaptation vector in sequence to form a combined vector. Then, it takes a weighted average of each corresponding dimension in the combined vector. The weight of each of the three vectors is set to 1 / 3, that is, the value of each dimension is equal to (the value of the corresponding dimension of the basic performance vector + the value of the corresponding dimension of the dynamic reachability vector + the value of the corresponding dimension of the skill adaptation vector) ÷ 3, and retains 3 decimal places. In this way, vectorization association and dimensionality reduction aggregation are completed to obtain the personal dynamic performance vector of the dispatchable maintenance personnel.

[0049] The system pre-defines a fixed structure for the dynamic performance profile of personnel, including three core modules: basic performance dimension, dynamic accessibility dimension, and skill adaptation dimension. Each module corresponds to a value in the individual's dynamic performance vector. The basic performance dimension indicates the effectiveness of positioning and online time, the dynamic accessibility dimension indicates response efficiency, task completion quality, and customer satisfaction, and the skill adaptation dimension indicates skill mastery level, certificate level, and equipment operation range. The values ​​of the individual's dynamic performance vector are filled into the corresponding modules, and specific explanations for each value are added to form a structured, multi-regional dynamic performance profile of personnel.

[0050] The beneficial effects are that, through a clear and reproducible process of collection, extraction, analysis, association, and reconstruction, the dynamic status, historical work efficiency, and skill qualification data of maintenance personnel are comprehensively integrated and accurately transformed into standardized dynamic performance profiles of personnel. This ensures that the profiles can comprehensively and truthfully reflect the overall capabilities and real-time status of maintenance personnel, providing reliable data for the accurate matching and efficient scheduling of subsequent cross-regional maintenance tasks and personnel, and guaranteeing the scientific and rational nature of scheduling decisions.

[0051] The collaborative scheduling module 104 is used to make cross-regional collaborative scheduling decisions by combining the maintenance task feature profile with the personnel dynamic performance profile to obtain the multi-regional collaborative scheduling scheme. In this embodiment of the invention, when the collaborative scheduling module performs cross-regional collaborative scheduling decision-making by combining the maintenance task feature profile with the personnel dynamic performance profile to obtain the multi-regional collaborative scheduling scheme, it is specifically used for: Using the maintenance task feature profile as the matching dimension, multiple rounds of bidirectional matching are performed with the personnel dynamic performance profile to obtain the initial cross-regional task-person matching pairs in the multi-regional area. Based on the dynamic performance profile of the personnel, the initial cross-regional task-person matching pair is subjected to spatiotemporal constraint verification and performance balance verification to obtain the target feasible matching pair of the multi-regional task-person matching pair. With the optimization objectives of maximizing the overall scheduling efficiency of the multi-region and minimizing the cross-region scheduling cost, the feasible matching pairs of the objectives are globally serialized to obtain the optimized scheduling sequence of the multi-region. The optimized scheduling sequence is structured and encapsulated to obtain the multi-regional collaborative scheduling scheme.

[0052] The system uses skill qualifications, task complexity coefficient, time sensitivity coefficient, and estimated working hours from the maintenance task feature profile as core matching dimensions. Simultaneously, it extracts key indicators corresponding to the skill adaptation vector, dynamic reachability vector, and basic performance vector from the personnel dynamic performance profile. A three-round bidirectional matching rule is set. The first round focuses on the matching degree between skill qualifications and the skill adaptation vector; a matching degree ≥ 80% proceeds to the next round. The second round focuses on the time sensitivity coefficient and the response time conversion value in the dynamic reachability vector; a response time conversion value ≥ 0.6 passes. The third round focuses on the task complexity coefficient and the skill level conversion value in the skill adaptation vector; a skill level conversion value ≥ 0.5 indicates a successful match. After three rounds of screening, tasks that simultaneously meet all three rules are matched one-to-one with personnel, forming initial cross-regional task-person matching pairs across multiple regions.

[0053] The system performs spatiotemporal constraint verification based on the current location information and dynamic reachability vector in the personnel dynamic performance profile. Spatially, it calculates the travel time from the personnel's current location to the task location. This time is less than or equal to the maximum allowable travel time corresponding to the urgency of the task, where 1-digit urgency code corresponds to ≤60 minutes, 2-digit urgency code corresponds to ≤90 minutes, and 3-digit urgency code corresponds to ≤120 minutes. Temporally, it ensures that the sum of the personnel's idle time after completing the currently assigned task and the estimated working time of the current task is less than or equal to the task's required completion time limit, where 1-digit urgency code requires ≤240 minutes, 2-digit urgency code corresponds to ≤480 minutes, and 3-digit urgency code corresponds to ≤960 minutes. The performance balance verification uses the task completion rate in the personnel's historical work performance data as a benchmark to ensure that the total number of tasks undertaken by each personnel after matching is ≤3, and the ratio of the sum of the task complexity coefficients of all matched pairs to the total score of the personnel's skill adaptation vector is between 0.8 and 1.2. The initial matched pairs that pass the dual verification are the target feasible matched pairs for multiple regions.

[0054] The system clarifies the calculation method for overall scheduling efficiency. The efficiency value of each feasible matching pair is the task complexity coefficient × the completion rate conversion value in the personnel dynamic reachability vector × 100. The sum of the efficiency values ​​of all matching pairs is the overall scheduling efficiency. Cross-regional scheduling cost is determined by the regional identifier code. The cost is 50 units when the regional identifier codes of the task and personnel are consistent, and 200 units when they are inconsistent. The sum of the costs of all matching pairs is the total scheduling cost. The optimization objective is to maximize overall scheduling efficiency and minimize total scheduling cost. The feasible matching pairs are sorted in order of overall scheduling efficiency from high to low and total scheduling cost from low to high. Matching pairs are selected sequentially to ensure that each task and personnel is selected only once, until all tasks are assigned, forming an optimized scheduling sequence of multiple regions arranged in the order of assignment.

[0055] The system pre-sets a structured template for collaborative scheduling schemes. The template includes 11 fixed fields: scheduling sequence number, unique task identifier, unique personnel identifier, task location, personnel current location, skill matching basis, estimated departure time, estimated completion time, cross-region identifier, scheduling efficiency value, and scheduling cost. The scheduling sequence number is generated in the format of "XD-6-digit region code-8-digit date-3-digit serial number". The estimated departure time is calculated based on the personnel's current task completion time and travel time, accurate to the minute. The cross-region identifier is marked "yes" or "no" according to whether the task and personnel region identifier codes are consistent. Each piece of information in the optimized scheduling sequence is filled into the template fields one by one. After the system verifies that all fields are complete, a standardized multi-region collaborative scheduling scheme is generated.

[0056] The beneficial effects are that through multiple rounds of precise two-way matching, dual verification and screening, and global optimization sorting, combined with a structured encapsulation process, the collaborative scheduling scheme ensures that it not only meets the core adaptation requirements of tasks and personnel, but also takes into account the rationality of time and space, the balance of efficiency and cost control. The resulting scheme is standardized and highly executable, providing a clear and reliable execution basis for the efficient allocation of cross-regional maintenance resources, and effectively improving the overall efficiency and resource utilization of cross-regional scheduling.

[0057] The target assignment module 105 is used to perform an executability simulation of the collaborative scheduling scheme and calculate the efficiency value of the simulation results to obtain the target matching assignment list of the multi-region. In this embodiment of the invention, when the target assignment module performs an executability simulation of the collaborative scheduling scheme and calculates the performance value of the simulation results to obtain the target matching assignment list for the multi-regional area, it is specifically used for: Configure the simulation execution environment for the multi-region according to the aforementioned collaborative scheduling scheme; In the simulated execution environment, based on the personnel dynamic performance profile, the trajectory simulation of the dispatchable maintenance personnel moving from their current location to the corresponding task location in the maintenance task feature profile is performed to obtain the benchmark simulated trajectory of the multi-region; Multiple perturbation simulations are performed on key nodes in the baseline simulation trajectory to obtain the multi-region perturbation simulation trajectory cluster; By summing the baseline simulated trajectory and the cluster of disturbance simulated trajectories, multi-scenario simulation data of the cooperative scheduling scheme is obtained.

[0058] When the target assignment module performs performance evaluation on the simulation results to obtain the target matching assignment list for the multi-region, it is specifically used for: The key indicators of the baseline simulation trajectory are quantified to obtain the basic performance evaluation values ​​of the multi-region; The stability index of the simulated disturbance trajectory cluster is evaluated to obtain the robustness evaluation value of the multi-region scheme. The basic performance evaluation value and the scheme robustness evaluation value are weighted by data to obtain the performance value of the multi-region; The performance value is mapped to the multi-scenario simulation data, and the fused result is reconstructed into a task-oriented structure to obtain the target matching assignment list for the multi-region.

[0059] The formula for calculating the performance value is as follows: ; In the formula, The performance value is... The efficiency adjustment coefficient for the baseline simulated trajectory is given. The basic performance evaluation value is... The robust stability coefficient of the simulated perturbation trajectory cluster is given by [reference to a specific parameter]. The robustness evaluation value of the case is given.

[0060] The system is based on the task location, current personnel location, and cross-regional road information in the collaborative scheduling scheme. It imports multi-regional electronic map data, including details such as road networks, traffic light locations, and speed limit signs. It sets traffic congestion coefficients according to weekdays / rest days, peak hours, and off-peak hours, with a peak coefficient of 1.5 and an off-peak coefficient of 1.0. At the same time, it records data such as online status and historical movement speed from the personnel dynamic performance profile, and constructs a multi-regional simulation execution environment consistent with the actual scenario to ensure the authenticity and accuracy of the simulation process.

[0061] In the simulated execution environment, the current location latitude and longitude of the personnel dynamic performance profile is extracted to six decimal places. Combined with the specific coordinates of the task location in the maintenance task feature profile, the road network data in the environment is called to plan the optimal driving route, prioritizing main roads and avoiding congested sections. At a time node of 5 minutes, the latitude and longitude of the personnel at that node, the cumulative driving time, and the remaining driving distance are recorded to form continuous and complete trajectory data. This trajectory data is the benchmark simulation trajectory for multiple areas.

[0062] First, identify the key nodes in the baseline simulation trajectory, including the starting node, the three main intersection nodes along the route, and the destination node, for a total of five fixed key nodes. For each key node, set three disturbance types: traffic congestion coefficient fluctuation ±0.3 on the original basis, temporary road control requiring detour of 1-3 kilometers, and personnel departure delay of 5-15 minutes. Each disturbance type is simulated independently five times. Each simulation generates a complete trajectory according to the recording standard of the baseline trajectory. The trajectories generated by all disturbance simulations are summarized to form a multi-regional disturbance simulation trajectory cluster.

[0063] According to the classification rule of "task identifier - personnel identifier - trajectory type", the baseline simulation trajectory is labeled as "baseline type" and each of the disturbance simulation trajectory clusters is labeled as "disturbance type + sequence number". Each trajectory retains complete node time, coordinates, time consumption and other information. All trajectory data under the same task identifier are stored together to form multi-scenario simulation data of multi-region collaborative scheduling schemes that include the baseline scenario and multiple disturbance scenarios.

[0064] Key performance indicators (KPIs) include total trajectory time, route matching accuracy, and node on-time rate. Total trajectory time is the cumulative travel time after the simulation ends, compared with the estimated travel time in the collaborative scheduling scheme. ≤90% of the estimated time earns 30 points, 90%-100% earns 25 points, 100%-110% earns 20 points, and over 110% earns 10 points. Route matching accuracy is the percentage of road overlap between the baseline trajectory and the optimal route in the environment. ≥90% earns 25 points, 80%- 89% earns 20 points, 70%-79% earns 15 points, and below 70% earns 5 points; the node on-time rate is the proportion of the number of key nodes arriving on schedule to the total number of key nodes, 100% earns 45 points, 90%-99% earns 35 points, 80%-89% earns 25 points, and below 80% earns 15 points. The sum of the three scores is the basic performance evaluation value for the multi-region, which is also the basic performance evaluation value in the performance value calculation formula, with a maximum score of 100 points.

[0065] The stability indicators are set as the total trajectory time fluctuation range and the critical node arrival time fluctuation range. The total trajectory time fluctuation range is calculated as the difference between the total time of each trajectory in the disturbed trajectory cluster and the total time of the reference trajectory. The absolute value of the maximum difference is taken: ≤10 minutes, 50 points; 11-20 minutes, 40 points; 21-30 minutes, 30 points; and more than 30 minutes, 10 points. The critical node arrival time fluctuation range is calculated as the maximum difference between the arrival time of each critical node of each disturbed trajectory and the corresponding node of the reference trajectory: ≤5 minutes, 50 points; 6-10 minutes, 40 points; 11-15 minutes, 30 points; and more than 15 minutes, 10 points. The sum of the two scores is the multi-region scheme robustness evaluation value. This scheme robustness evaluation value is also the scheme robustness evaluation value in the effectiveness value calculation formula, with a full score of 100 points.

[0066] The efficiency adjustment coefficient of the baseline simulated trajectory is determined based on the statistical analysis of the system's historical cross-regional scheduling data. The system extracts the simulated execution data of all collaborative scheduling schemes in the past 12 months, calculates the correlation between the efficiency performance of the baseline simulated trajectory and the actual scheduling execution effect, and statistically determines the weight of the influence of the baseline efficiency on the overall scheduling effectiveness. Finally, the specific value of the coefficient is determined to be 0.6, which is the efficiency adjustment coefficient of the baseline simulated trajectory in the efficiency value calculation formula.

[0067] The robust stability coefficient of the disturbance simulation trajectory cluster is also determined based on the statistical analysis of the system's historical cross-regional scheduling data. The system analyzes the correlation data between the stability performance of the disturbance simulation trajectory in the past 12 months and the effectiveness of responding to emergencies during actual scheduling. The influence weight of trajectory stability on the overall scheduling effectiveness is statistically derived, and the specific value of the coefficient is finally determined to be 0.4. The sum of this coefficient and the efficiency adjustment coefficient of the baseline simulation trajectory is 1 to ensure the rationality of the weighted calculation. This coefficient is the robust stability coefficient of the disturbance simulation trajectory cluster in the efficiency value calculation formula.

[0068] The relevance of the performance value calculation formula lies in its precise support of the core functions of the target assignment module in simulating the feasibility of collaborative scheduling schemes and calculating performance. It weights and sums the quantified basic performance evaluation value and the scheme robustness evaluation value through corresponding coefficients, comprehensively considering the execution performance of the collaborative scheduling scheme in the baseline scenario and its stability performance in the disturbance scenario. This avoids the one-sidedness caused by a single-dimensional evaluation. The calculated performance value can comprehensively and objectively reflect the actual adaptability and execution reliability of the collaborative scheduling scheme. It provides a precise and unified evaluation basis for subsequently mapping the performance value to multi-scenario simulation data and reconstructing it into a task-oriented manner to obtain a target matching assignment list for multiple regions, ensuring the scientific nature and executability of the target matching assignment list.

[0069] Multiply the basic performance evaluation value by 0.6, then multiply the robustness evaluation value of the scheme by 0.4, add the two products together, and keep two decimal places. The resulting value is the performance value of the multi-region.

[0070] The performance values ​​are matched one-to-one with the multi-scenario simulation data according to the task identifier. The task-person matching relationship corresponding to the simulation data with a performance value ≥ 80 is selected. The task is sorted by urgency, with the first digit code having priority, the second digit code having priority, and the third digit code having priority. Only the matching relationship with the highest performance value is retained for each task. The results are compiled into a standardized list containing task identifier, personnel identifier, recommended trajectory, performance value, and estimated completion time. This list is the target matching and assignment list for multiple regions.

[0071] The beneficial effects are that, through standardized simulation environment configuration, trajectory simulation, indicator quantification and data fusion process, combined with scientific efficiency value calculation method, the feasibility and stability of collaborative scheduling scheme are fully verified, efficient and reliable task-person matching relationship is accurately selected, and the resulting target matching assignment list is standardized and highly implementable, effectively reducing the risk in the scheduling execution process and improving the accuracy of cross-regional maintenance task assignment and overall execution efficiency.

[0072] The synchronization update module 106 is used to send the target matching assignment list to the work terminal of the dispatchable maintenance personnel and to synchronously update the real-time maintenance status of the multiple areas.

[0073] In this embodiment of the invention, when the synchronization update module sends the target matching assignment list to the work terminals of the schedulable maintenance personnel and synchronously updates the real-time maintenance status of the multiple areas, it is specifically used for: The target matching assignment list is pushed to the work terminal of the dispatchable maintenance personnel, and the task start confirmation record of the work terminal is confirmed. Based on the task start confirmation record, the task status in the target matching assignment list is updated from pending assignment to started, so as to establish a dynamic execution association between task identifiers and personnel identifiers in the multi-region area; Based on the dynamic execution association, the system continuously receives the on-the-go location information and task completion confirmation information from the work terminal; Based on the location information along the route and the task completion confirmation information, the real-time maintenance status of the multiple areas is updated synchronously.

[0074] The system pre-stores a unique 10-digit device code for each dispatchable maintenance worker's work terminal. The target matching assignment list establishes an association mapping according to "task identifier - personnel identifier - device code" and pushes it to the work terminal through a dedicated maintenance scheduling application. The list contains complete information such as task identifier, task location, skill requirements, estimated working hours, and efficiency value. After the terminal receives the information, a confirmation pop-up window appears. After the maintenance worker clicks the "Confirm Start" button, the system immediately receives feedback information with a timestamp accurate to the second, personnel identifier, and task identifier. This feedback information is the task start confirmation record of the work terminal.

[0075] The system retrieves the task status field of the corresponding task identifier in the target matching assignment list. The initial value of this field is "pending assignment". After receiving the task departure confirmation record, the field is automatically updated to "departed". At the same time, a dynamic execution association table is generated. The table contains core information such as task identifier, personnel identifier, equipment code, departure confirmation timestamp, and status update time. Through this table, a one-to-one correspondence between tasks and executors in multiple regions is established to ensure that the task execution trajectory is traceable.

[0076] Based on the personnel identifier and equipment code in the dynamic execution association table, the system establishes a continuous communication connection with the work terminal. The work terminal automatically collects and uploads latitude and longitude coordinates every 5 minutes through its built-in GPS module as location information along the way. When the maintenance personnel complete the maintenance work, they need to enter a brief description of the task completion status in the terminal's dedicated application and click the "Confirm Completion" button. The terminal then uploads information including task identifier, personnel identifier, completion timestamp, and a brief description of completion status as task completion confirmation information. The system continuously receives and stores the two types of information according to the dynamic execution association table.

[0077] The system has preset rules for updating the real-time maintenance status. When it receives on-the-go location information, it updates the real-time status of the corresponding task to "on the way" and calculates the estimated arrival time based on the distance between the current location and the task location and the historical movement speed, which is then displayed synchronously on the system status panel. When it receives task completion confirmation information, it updates the real-time status to "completed" and records the completion timestamp and a brief description of the completion status. If it fails to receive on-the-go location information for three consecutive times and does not receive any abnormal feedback, the status is updated to "confirmation required" and a terminal reminder is triggered. Based on the above different situations, the system synchronously updates the real-time maintenance status of all related tasks in multiple areas to ensure that the status data is consistent with the actual execution progress.

[0078] The beneficial effects are that targeted push notifications, status linkage updates, continuous information collection, and standardized status management processes ensure accurate delivery of target matching assignment lists and real-time synchronization of task execution status. This enables visualized control of the entire process of maintenance tasks in multiple regions from start to finish, improves the overall control efficiency of cross-regional dispatch, and ensures the timeliness and accuracy of information synchronization between maintenance personnel and dispatch centers, thereby optimizing service response and process control quality.

[0079] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0080] This application embodiment can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence is the theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0081] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A big data-driven cross-regional collaborative dispatch and repair system for maintenance personnel, characterized in that: The system includes a task parsing module, a task profiling module, a performance profiling module, a collaborative scheduling module, a target assignment module, and a synchronization update module, wherein: The task parsing module is used to standardize and parse heterogeneous repair data from multiple regions to obtain structured repair task orders from the multiple regions. The task profiling module is used to process the structured maintenance task sheet into a profile and determine the maintenance task feature profiles for the multi-regional areas. The performance profiling module is used to collect dynamic status data, historical work performance data, and skill qualification data of dispatchable maintenance personnel in the multiple areas in real time, and topologically depict them as dynamic performance profiles of personnel in the multiple areas. The collaborative scheduling module is used to make cross-regional collaborative scheduling decisions by combining the maintenance task feature profile with the personnel dynamic performance profile, so as to obtain the multi-regional collaborative scheduling scheme. The target assignment module is used to perform executability simulation on the collaborative scheduling scheme and calculate the efficiency value of the simulation results to obtain the target matching assignment list of the multi-region. The synchronization update module is used to send the target matching assignment list to the work terminals of the dispatchable maintenance personnel and to synchronously update the real-time maintenance status of the multiple areas.

2. The big data-driven cross-regional collaborative dispatch and repair system for maintenance personnel as described in claim 1, characterized in that, When the task parsing module performs standardized parsing of heterogeneous repair request data from multiple regions to obtain structured repair task orders for those regions, it is specifically used for: Receive heterogeneous repair data from multiple regions, including text description data, voice data, and image data; By identifying the device identification information and fault phenomenon description in the text description data, the text task information of the multi-region is obtained; The voice data is labeled to obtain the location and time information of the multiple regions; By fusing the device model identifier and fault status visual features in the image data, the visual feature information of the multi-region is obtained; The text task information, location information, time information, and visual feature information are formatted and integrated to obtain the multi-region structured maintenance task sheet.

3. The big data-driven cross-regional collaborative dispatch and repair system for maintenance personnel as described in claim 1, characterized in that, When the task profiling module performs profiling processing on the structured maintenance task order to determine the maintenance task feature profiles for the multi-regional areas, it is specifically used for: The key data fields in the structured maintenance task sheet are parsed, including equipment type identifier, fault description text, and urgency level code; The key data fields are divided into task modes to obtain the maintenance task results for the multiple regions. Based on the fault description text and the urgency level code, the complexity and time sensitivity of different tasks in the maintenance task results are quantified to obtain the task complexity coefficient and time sensitivity coefficient of the multi-region. The necessary skills and estimated working hours for the maintenance task are mapped by associating the equipment type identifier and the fault description text. A multi-dimensional feature vector is constructed from the maintenance task results, the task complexity coefficient, the time sensitivity coefficient, the skill qualifications, and the estimated working hours to obtain a multi-region maintenance task feature profile.

4. The big data-driven cross-regional collaborative dispatch and repair system for maintenance personnel as described in claim 1, characterized in that, When the performance profiling module performs real-time collection of dynamic status data, historical work performance data, and skill qualification data of dispatchable maintenance personnel in the multiple areas, it is specifically used for: The system receives real-time location information and equipment online status from dispatchable maintenance personnel in the multiple regions, forming dynamic status data of the dispatchable maintenance personnel. Based on the historical task record database of the multi-regional area, the task completion rate, average response time and customer satisfaction evaluation of the dispatchable maintenance personnel are determined and integrated into the historical work efficiency data of the dispatchable maintenance personnel. By querying the personnel qualification database of the multiple regions, the certified skill categories, skill level certificate information and operable equipment list of the dispatchable maintenance personnel are determined, and the skill qualification data of the dispatchable maintenance personnel is obtained.

5. The big data-driven cross-regional collaborative dispatch and repair system for maintenance personnel as described in claim 4, characterized in that, When the performance profiling module performs topological mapping to create dynamic performance profiles of personnel in the multi-region area, it is specifically used for: The basic performance vector of the schedulable maintenance personnel is obtained by extracting performance features from the dynamic state data. Dynamic reachability analysis is performed on the historical operational efficiency data to obtain the dynamic reachability vector of the dispatchable maintenance personnel; Multi-level skill mapping is performed on the skill qualification data to obtain the skill adaptation vector of the dispatchable maintenance personnel; The basic performance vector, the dynamic reachability vector, and the skill adaptation vector are vectorized and associated, and the associated results are reduced in dimension and aggregated to obtain the personal dynamic performance vector of the schedulable maintenance personnel. The individual dynamic performance vector is reconstructed in dimensions to obtain the dynamic performance profile of the personnel in the multi-region.

6. The big data-driven cross-regional collaborative dispatch and repair system for maintenance personnel as described in claim 1, characterized in that, When the collaborative scheduling module performs cross-regional collaborative scheduling decision-making by combining the maintenance task feature profile with the personnel dynamic performance profile to obtain the multi-regional collaborative scheduling scheme, it is specifically used for: Using the maintenance task feature profile as the matching dimension, multiple rounds of bidirectional matching are performed with the personnel dynamic performance profile to obtain the initial cross-regional task-person matching pairs in the multi-regional area. Based on the dynamic performance profile of the personnel, the initial cross-regional task-person matching pair is subjected to spatiotemporal constraint verification and performance balance verification to obtain the target feasible matching pair of the multi-regional task-person matching pair. With the optimization objectives of maximizing the overall scheduling efficiency of the multi-region and minimizing the cross-region scheduling cost, the feasible matching pairs of the objectives are globally serialized to obtain the optimized scheduling sequence of the multi-region. The optimized scheduling sequence is structured and encapsulated to obtain the multi-regional collaborative scheduling scheme.

7. The big data-driven cross-regional collaborative dispatch and repair system for maintenance personnel as described in claim 1, characterized in that, When the target assignment module performs an executability simulation of the collaborative scheduling scheme and calculates the performance value of the simulation results to obtain the target matching assignment list for the multi-regional area, it is specifically used for: Configure the simulation execution environment for the multi-region according to the aforementioned collaborative scheduling scheme; In the simulated execution environment, based on the personnel dynamic performance profile, the trajectory simulation of the dispatchable maintenance personnel moving from their current location to the corresponding task location in the maintenance task feature profile is performed to obtain the benchmark simulated trajectory of the multi-region; Multiple perturbation simulations are performed on key nodes in the baseline simulation trajectory to obtain the multi-region perturbation simulation trajectory cluster; By summing the baseline simulated trajectory and the cluster of disturbance simulated trajectories, multi-scenario simulation data of the cooperative scheduling scheme is obtained.

8. The big data-driven cross-regional collaborative dispatch and repair system for maintenance personnel as described in claim 7, characterized in that, When the target assignment module performs performance evaluation on the simulation results to obtain the target matching assignment list for the multi-region, it is specifically used for: The key indicators of the baseline simulation trajectory are quantified to obtain the basic performance evaluation values ​​of the multi-region; The stability index of the simulated disturbance trajectory cluster is evaluated to obtain the robustness evaluation value of the multi-region scheme. The basic performance evaluation value and the scheme robustness evaluation value are weighted by data to obtain the performance value of the multi-region; The performance value is mapped to the multi-scenario simulation data, and the fused result is reconstructed into a task-oriented structure to obtain the target matching assignment list for the multi-region.

9. The big data-driven cross-regional collaborative dispatch and repair system for maintenance personnel as described in claim 8, characterized in that, The formula for calculating the performance value is as follows: ； In the formula, The performance value is... The efficiency adjustment coefficient for the baseline simulated trajectory is given. The basic performance evaluation value is... The robust stability coefficient of the simulated perturbation trajectory cluster is given by [reference to a specific parameter]. The robustness evaluation value of the case is given.

10. The big data-driven cross-regional collaborative dispatch and repair system for maintenance personnel as described in claim 1, characterized in that, When the synchronization update module sends the target matching assignment list to the work terminals of the schedulable maintenance personnel and synchronously updates the real-time maintenance status of the multiple areas, it is specifically used for: The target matching assignment list is pushed to the work terminal of the dispatchable maintenance personnel, and the task start confirmation record of the work terminal is confirmed. Based on the task start confirmation record, the task status in the target matching assignment list is updated from pending assignment to started, so as to establish a dynamic execution association between task identifiers and personnel identifiers in the multi-region area; Based on the dynamic execution association, the system continuously receives the on-the-go location information and task completion confirmation information from the work terminal; Based on the location information along the route and the task completion confirmation information, the real-time maintenance status of the multiple areas is updated synchronously.

Images