Work order distribution method and system, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a work order distribution method and system. The method comprises the following steps: acquiring work order detailed information of a target work order; dividing the target work order into a target grid region in a plurality of grid regions according to the work order detailed information, and taking average installation and maintenance time information of the target grid region as estimated installation and maintenance time information of the target work order; determining estimated commuting time information of the target work order; and according to the pre-estimated installation and maintenance time information, the pre-estimated commuting time information and customer reservation time information of the target work order, distributing the target work order to installation and maintenance workers in the target grid area or the cooperation area. According to the embodiment of the invention, through a more flexible and accurate work order division and distribution mechanism, the problems of work order time overlapping and non-uniform human resource distribution are effectively solved, the timeliness and the overall efficiency of installation and maintenance work are remarkably improved, and the customer satisfaction and the operation effect of an enterprise are further improved.

Description

Technical Field

[0001] The present invention relates to the field of information processing technology, and in particular to a work order distribution method, a work order distribution system, an electronic device and a computer-readable storage medium. Background Art

[0002] Currently, the distribution mode of installation and maintenance work orders usually adopts the method of "one installation and maintenance worker is responsible for one grid area", that is, the installation and maintenance work orders in a grid area can only be distributed to the installation and maintenance workers in the grid area for processing. This method has several technical problems and challenges in practice:

[0003] 1. Work order time overlap problem: Installation and maintenance staff need to handle multiple work orders in a designated grid area, which often leads to work order time overlap. For example, the installation and maintenance task of the previous order is overdue due to various reasons (such as equipment failure, construction complexity exceeding expectations, etc.). This delay will directly affect the execution time of the next order. This situation will cause the next customer to wait for a long time, which will cause dissatisfaction and complaints. This conflict in time management not only affects customer satisfaction, but may also bring negative brand impact and economic losses to the company.

[0004] 2. Uneven distribution of human resources: Allocating installation and maintenance workers by grid area can easily lead to excessive workload for installation and maintenance workers in some grid areas, while installation and maintenance workers in other grid areas are relatively idle. Specifically, in some grid areas, the installation and maintenance tasks are heavy, and installation and maintenance workers often need to work overtime to complete all work orders, while in other grid areas, the number of work orders is small, and the working time of installation and maintenance workers is not fully utilized. This unbalanced distribution of human resources not only causes overwork of some employees, but also limits the production efficiency of the overall installation and maintenance team, making it difficult to achieve the optimal allocation of human resources.

[0005] In short, the current mode of distributing installation and maintenance work orders not only affects the timeliness of installation and maintenance work and customer satisfaction, but also has a negative impact on the overall efficiency of the installation and maintenance team and the company's operating results. Summary of the invention

[0006] In view of the above problems, embodiments of the present invention are proposed to provide a work order allocation method, a work order allocation system, an electronic device and a computer-readable storage medium that overcome the above problems or at least partially solve the above problems.

[0007] In order to solve the above problems, an embodiment of the present invention discloses a method for allocating work orders, the method comprising: obtaining detailed work order information of a target work order; dividing the target work order into a target grid area among multiple grid areas according to the work order detailed information, and using the average installation and maintenance time information of the target grid area as the estimated installation and maintenance time information of the target work order; determining the estimated commuting time information of the target work order; and allocating the target work order to the installation and maintenance staff in the target grid area or the collaborative area according to the estimated installation and maintenance time information, the estimated commuting time information and the customer appointment time information of the target work order.

[0008] Optionally, the target work order is assigned to the installation and maintenance staff in the target grid area or the collaborative area based on the estimated installation and maintenance time information, the estimated commuting time information and the customer appointment time information of the target work order, including: adding the estimated installation and maintenance time information and the estimated commuting time information to obtain an estimated on-site time information; comparing the estimated on-site time information with the customer appointment time information to obtain a comparison result; if the comparison result indicates that the estimated on-site time information is less than or equal to the customer appointment time information, the target work order is assigned to the installation and maintenance staff in the target grid area; if the comparison result indicates that the estimated on-site time information is greater than the customer appointment time information, the target work order is assigned to the installation and maintenance staff in the collaborative area.

[0009] Optionally, determining the estimated commuting time information of the target work order includes: searching a commuting record database to see whether there is a commuting record from the destination of a previous work order of the target work order to the destination of the target work order; if the commuting record exists in the commuting record database, using the commuting time information corresponding to the commuting record as the estimated commuting time information; if the commuting record does not exist in the commuting record database, using a path planning algorithm in a geographic vector map to calculate the estimated commuting time information.

[0010] Optionally, the use of a path planning algorithm in a geographic vector map to calculate the estimated commuting time information includes: treating the geographic vector map as a weighted undirected graph, the weighted undirected graph comprising a set of vertices and a set of arcs, the vertices representing intersections and buildings, and the arcs representing distances between vertices; using a dynamically adaptive Metropolis acceptance criterion and utilizing an ant colony algorithm to calculate the estimated commuting time information.

[0011] Optionally, before obtaining the work order details of the target work order, the method further includes: obtaining work order history data within the target geographical area; and clustering the work order destinations in the work order history data using an unsupervised learning algorithm to obtain a plurality of the grid areas.

[0012] Optionally, the use of an unsupervised learning algorithm to cluster the work order destinations in the work order history data to obtain a plurality of the grid areas includes: initializing the neighborhood radius and density threshold of the unsupervised learning algorithm; dividing the coordinate points corresponding to each of the work order destinations into core points, boundary points or noise points according to the neighborhood radius and the density threshold; taking each of the core points as the center point of each of the grid areas, classifying the boundary points within the neighborhood radius of each of the center points into the grid area where the center point is located, and excluding the noise points to generate a plurality of the grid areas.

[0013] Optionally, after allocating the target work order to the installation and maintenance staff in the target grid area or the collaborative area based on the estimated installation and maintenance time information, the estimated commuting time information and the customer appointment time information of the target work order, the method also includes: setting multiple grid areas into multiple collaborative areas; predicting the total work order volume of each collaborative area in the next cycle; if the total work order volume of the next cycle of a target collaborative area among the multiple collaborative areas is less than the total work order volume of the current cycle, screening out at least one grid area from the target collaborative area, and dividing the screened grid area into other collaborative areas; if the total work order volume of the next cycle of the target collaborative area is greater than or equal to the total work order volume of the current cycle, adding a new grid area to the target collaborative area.

[0014] An embodiment of the present invention also discloses a work order distribution system, which includes: a work order information acquisition module, which is used to obtain detailed work order information of a target work order; a work order grid division module, which is used to divide the target work order into a target grid area among multiple grid areas according to the work order detailed information, and use the average installation and maintenance time information of the target grid area as the estimated installation and maintenance time information of the target work order; a commuting time estimation module, which is used to determine the estimated commuting time information of the target work order; and a target work order distribution module, which is used to distribute the target work order to the installation and maintenance staff in the target grid area or the collaborative area according to the estimated installation and maintenance time information, the estimated commuting time information and the customer appointment time information of the target work order.

[0015] Optionally, the target work order allocation module includes: an estimated on-site time information calculation module, used to add the estimated installation and maintenance time information and the estimated commuting time information to obtain the estimated on-site time information; a time information comparison module, used to compare the estimated on-site time information with the customer appointment time information to obtain a comparison result; a work order allocation module, used to allocate the target work order to the installation and maintenance staff in the target grid area if the comparison result indicates that the estimated on-site time information is less than or equal to the customer appointment time information; if the comparison result indicates that the estimated on-site time information is greater than the customer appointment time information, then allocate the target work order to the installation and maintenance staff in the collaborative area.

[0016] Optionally, the commuting time estimation module includes: a database search module, used to search the commuting record database for a commuting record from the destination of the previous work order of the target work order to the destination of the target work order; a commuting time determination module, used to use the commuting time information corresponding to the commuting record as the estimated commuting time information if the commuting record exists in the commuting record database; and a commuting time calculation module, used to use a path planning algorithm in a geographic vector map to calculate the estimated commuting time information if the commuting record does not exist in the commuting record database.

[0017] Optionally, the commuting time calculation module includes: a weighted undirected graph determination module, used to treat the geographic vector map as a weighted undirected graph, the weighted undirected graph containing a set of vertices and a set of arcs, the vertices representing intersections and buildings, and the arcs representing distances between vertices; an ant colony algorithm calculation module, used to use a dynamically adaptive Metropolis acceptance criterion and an ant colony algorithm to calculate the estimated commuting time information.

[0018] Optionally, the system also includes: a work order history data acquisition module, used to obtain the work order history data within the target geographical area before the work order information acquisition module obtains the work order details of the target work order; a grid area clustering module, used to cluster the work order destinations in the work order history data using an unsupervised learning algorithm to obtain a plurality of grid areas.

[0019] Optionally, the grid area clustering module includes: a parameter initialization module, used to initialize the neighborhood radius and density threshold of the unsupervised learning algorithm; a point division module, used to divide the coordinate points corresponding to each work order destination into core points, boundary points or noise points according to the neighborhood radius and the density threshold; a grid area drawing module, used to take each core point as the center point of each grid area, classify the boundary points within the neighborhood radius of each center point into the grid area where the center point is located, and exclude the noise points to generate multiple grid areas.

[0020] Optionally, the system also includes: a collaborative area setting module, which is used to set multiple grid areas into multiple collaborative areas after the target work order allocation module allocates the target work order to the installation and maintenance personnel in the target grid area or the collaborative area according to the estimated installation and maintenance time information, the estimated commuting time information and the customer appointment time information of the target work order; a work order quantity prediction module, which is used to predict the total work order quantity of each collaborative area in the next cycle; a collaborative area adjustment module, which is used to filter out at least one of the grid areas from the target collaborative area if the total work order quantity of the next cycle of the target collaborative area among the multiple collaborative areas is less than the total work order quantity of the current cycle, and divide the filtered grid area into other collaborative areas; if the total work order quantity of the next cycle of the target collaborative area is greater than or equal to the total work order quantity of the current cycle, then add a new grid area to the target collaborative area.

[0021] An embodiment of the present invention further discloses an electronic device, comprising: one or more processors; and one or more machine-readable media storing instructions thereon, which, when executed by the one or more processors, enables the electronic device to execute a work order allocation method as described above.

[0022] An embodiment of the present invention further discloses a computer-readable storage medium, wherein a computer program stored in the storage medium enables a processor to execute the work order allocation method as described above.

[0023] The embodiments of the present invention include the following advantages:

[0024] An embodiment of the present invention provides a work order allocation scheme, which obtains work order details of a target work order, and then divides the target work order into a target grid area among multiple grid areas according to the work order details, and uses the average installation and maintenance time information of the target grid area as the estimated installation and maintenance time information of the target work order. At the same time, the estimated commuting time information of the target work order is determined. According to the estimated installation and maintenance time information, the estimated commuting time information, and the customer appointment time information of the target work order, the target work order is allocated to the installation and maintenance staff in the target grid area or the collaborative area.

[0025] By acquiring detailed information of the target work order and reasonably dividing and estimating it, the embodiment of the present invention can more accurately calculate the estimated installation and maintenance time information and estimated commuting time information of each target work order, allowing for more flexible arrangement of installation and maintenance tasks, and reducing the problem of customers waiting too long for the next order due to the timeout of the previous order. Through better time management and task allocation, the waiting time of customers is effectively shortened, thereby improving customer satisfaction and reducing complaints and negative brand impacts caused by delays. It is no longer limited to the mode that one installation and maintenance staff is responsible for one grid area, but according to the detailed information of the target work order and the average installation and maintenance time information of each grid area, the target work order is reasonably allocated to the installation and maintenance staff in the target grid area or the collaborative area. The flexible allocation mechanism effectively solves the problem that some grid areas have heavy installation and maintenance tasks, while other grid areas have fewer installation and maintenance tasks, and realizes the balanced allocation of human resources. By more reasonably utilizing the working time of the installation and maintenance staff, the overall production efficiency is improved. By accurately calculating the estimated installation and maintenance time information and the estimated commuting time information of the target work order, the work tasks of the installation and maintenance staff can be better arranged to ensure that the installation and maintenance work is processed in time within the customer's appointment time. It not only improves the timeliness of installation and maintenance work, but also improves service quality and further increases customer satisfaction. It enables installation and maintenance staff to complete tasks more efficiently and reduces the problem of overwork or idleness of some employees due to uneven workload. By reasonably allocating target work orders and optimizing resource utilization, the overall efficiency of the installation and maintenance team has been significantly improved, and the company's operating results have also been improved.

[0026] To sum up, compared with the traditional installation and maintenance dispatching model, the embodiments of the present invention not only effectively solve the problems of work order time overlap and uneven distribution of human resources through a more flexible and accurate work order division and allocation mechanism, but also significantly improve the timeliness and overall efficiency of installation and maintenance work, thereby improving customer satisfaction and the company's operating results. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 It is a flowchart of the steps of a method for allocating a work order according to an embodiment of the present invention;

[0028] Figure 2 is a schematic diagram of a weighted undirected graph according to an embodiment of the present invention;

[0029] Figure 3 is a schematic diagram of adaptively adjusting a collaboration zone according to an embodiment of the present invention;

[0030] Figure 4 is a schematic diagram of a work order quantity prediction model based on deep learning according to an embodiment of the present invention;

[0031] Figure 5It is a structural block diagram of a work order distribution system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0032] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0033] A work order allocation scheme proposed in an embodiment of the present invention obtains detailed information of a target work order, reasonably divides the target work order into target grid areas among multiple grid areas, and flexibly allocates the target work order to the installation and maintenance staff in the target grid area or the collaborative area according to the average installation and maintenance time information and estimated commuting time information of each grid area, combined with the customer's appointment time. This scheme optimizes the work order allocation process, effectively reduces the problem of work order time overlap, avoids overload or idleness of installation and maintenance staff, realizes balanced allocation of human resources, and significantly improves the timeliness and overall efficiency of installation and maintenance work, thereby improving customer satisfaction and the operational effect of the enterprise.

[0034] Reference Figure 1 , showing a flowchart of a method for allocating a work order in an embodiment of the present invention. The embodiment of the present invention is described by taking a work order specifically being an installation and maintenance work order as an example. The method for allocating a work order can be applied to a work order allocation system (referred to as the system for short). The method for allocating a work order can specifically include the following steps:

[0035] Step 101, obtaining detailed work order information of the target work order.

[0036] In an embodiment of the present invention, the work order details include, but are not limited to, the customer's name, address, contact information, work order type, specific installation and maintenance requirements, appointment time, and related fault descriptions or requirements provided by the customer. In order to ensure the accuracy and efficiency of the target work order allocation, the acquisition of the work order details can be as comprehensive and accurate as possible.

[0037] For example, suppose a customer, Mr. Zhang, has a problem with his home broadband network and applies for repair service through the customer service hotline. At this point, the system will generate a new work order, and the work order details will record Mr. Zhang's address (such as a certain unit in a certain building in a certain community), contact number, broadband fault description (such as frequent network disconnections, which may be a line problem), and the time when Mr. Zhang is convenient for on-site repair (such as Tuesday from 10 am to 12 pm). In addition, if the customer provides further troubleshooting information, such as he has tried to restart the router but the problem has not been solved, this information will also be recorded in the work order.

[0038] In the process of obtaining this information, the system can automatically extract the customer's historical maintenance records and equipment information by connecting with the customer service system and database. For example, Mr. Zhang's account information shows that the broadband model used in his home is a certain brand of fiber optic access equipment. Such detailed information helps the installation and maintenance staff to make corresponding preparations before going to the customer's home.

[0039] Through this step, the system ensures that all relevant information of the target work order is accurately recorded, providing a reliable data basis for the subsequent division and allocation of work orders. The successful implementation of this step not only helps to improve the efficiency of work order processing, but also reduces rework and customer complaints caused by incomplete or erroneous information, thereby improving customer satisfaction.

[0040] Step 102 , divide the target work order into a target grid area among the multiple grid areas according to the work order detailed information, and use the average installation and maintenance time information of the target grid area as the estimated installation and maintenance time information of the target work order.

[0041] In an embodiment of the present invention, after obtaining the work order details of the target work order, it is necessary to divide the target work order into a target grid area among multiple grid areas according to the work order details, and determine the average installation and maintenance time information of the target network area. The division of the target grid area is to optimize the allocation of installation and maintenance resources so that the installation and maintenance work in each grid area can be carried out more efficiently.

[0042] For example, suppose a city is divided into multiple grid areas, and each grid area has a certain number of installation and maintenance staff responsible for it. Based on Mr. Zhang's address information (a certain unit in a certain building in a certain community), the system will assign his work order to a specific grid area. There may be 5 installation and maintenance personnel in this grid area who are responsible for handling all customer work orders, including Mr. Zhang's. In order to ensure the rationality of work order allocation, the system will combine the historical installation and maintenance data in the grid area to calculate the average installation and maintenance time information for the grid area. For example, based on the data from the past month, the average installation and maintenance time in this specific grid area is 45 minutes.

[0043] After determining the target grid area and its average installation and maintenance time information, the system uses this information as the estimated installation and maintenance time information for Mr. Zhang's work order. The implementation of this step helps to improve the accuracy of work order allocation, allowing installation and maintenance personnel to better arrange their work time and avoid time waste and work backlogs caused by improper work order allocation.

[0044] Through this method, the system can not only optimize the utilization of installation and maintenance resources, but also improve overall work efficiency and customer satisfaction. For example, if Mr. Zhang's work order is reasonably assigned to a suitable grid area, the installation and maintenance personnel can prepare in advance based on the estimated installation and maintenance time information to ensure that the maintenance task is completed efficiently within the appointment time, thereby improving service quality and customer experience.

[0045] Step 103, determining the estimated commuting time information of the target work order.

[0046] In the embodiment of the present invention, the estimated commuting time information refers to the time required for the installation and maintenance staff to reach the target customer location from the current location or the destination of the previous work order. This time information is of great significance for reasonably arranging installation and maintenance tasks and improving work efficiency.

[0047] For example, suppose Mr. Zhang's work order has been assigned to a certain grid area, and the maintenance worker Xiao Li who is currently in charge of the grid area is currently performing maintenance work at another customer's home. The system needs to calculate the commuting time required for Xiao Li to reach Mr. Zhang's home from his current location. To ensure the accuracy of the calculation, the system can use the Global Positioning System (GPS) and the traffic information system to obtain Xiao Li's current location and current traffic conditions in real time.

[0048] Assume that Xiao Li is currently doing maintenance in another community. The system knows his current location through GPS positioning and obtains real-time traffic conditions through the traffic information system. Based on factors such as current traffic flow, road congestion, and distance, the system calculates that the estimated commuting time for Xiao Li to reach Mr. Zhang's home from his current location is 20 minutes. This time information will serve as an important reference for arranging Xiao Li's next maintenance task.

[0049] By determining the estimated commuting time information, the system can arrange the work order and time of the installation and maintenance personnel more reasonably. For example, suppose Mr. Zhang's scheduled door-to-door maintenance time is from 10 am to 12 pm, and Xiao Li can arrive at Mr. Zhang's home before 10 o'clock after processing the current work order, then the system can arrange Xiao Li to go to Mr. Zhang's home immediately after completing the current work order, so as to ensure that the installation and maintenance task is completed within the appointment time. If the estimated commuting time is too long, the system can consider assigning the work order to other installation and maintenance personnel who are closer to improve overall work efficiency.

[0050] Through this method, the system can effectively reduce the idle time and unnecessary waiting time of installation and maintenance personnel, ensuring that installation and maintenance tasks can be completed in a timely and efficient manner. This not only improves the overall efficiency of installation and maintenance work, but also significantly improves customer satisfaction and reduces complaints and dissatisfaction caused by long waiting times.

[0051] Step 104, assigning the target work order to the installation and maintenance staff in the target grid area or the collaborative area according to the estimated installation and maintenance time information, the estimated commuting time information and the customer appointment time information of the target work order.

[0052] In an embodiment of the present invention, after determining the estimated installation and maintenance time information and the estimated commuting time information of the target work order, the system needs to comprehensively consider this information and the customer's appointment time information, and reasonably allocate the target work order to the installation and maintenance staff in the target grid area or the collaborative area. This step is to ensure the rationality and efficiency of work order allocation, and improve the overall installation and maintenance efficiency and customer satisfaction.

[0053] For example, suppose the system has obtained Mr. Zhang's work order details and assigned them to a grid area, determining the estimated installation and maintenance time to be 45 minutes and the commuting time to be 20 minutes. Mr. Zhang's scheduled door-to-door maintenance time is from 10 a.m. to 12 p.m. At this point, the system needs to select the appropriate installation and maintenance staff based on this information.

[0054] The system will first check the current work status and schedule of the installation and maintenance staff in the target grid area. If Xiao Li can rush to Mr. Zhang's home before 10 o'clock after processing the current work order and complete the installation and maintenance task within 45 minutes, the system can assign Mr. Zhang's work order to Xiao Li. If Xiao Li's current work status does not allow the task to be completed within the appointment time, the system will further check the status of other installation and maintenance personnel in the collaborative area.

[0055] Collaboration areas refer to adjacent grid areas or other similar network areas. Installation and maintenance personnel can collaborate across regions to process work orders. Assume that Xiao Wang is an installation and maintenance personnel in an adjacent grid area. His current work order is expected to be completed at 9:30 am, and his commute time to Mr. Zhang's home is 15 minutes. Then the system can consider assigning Mr. Zhang's work order to Xiao Wang. In this way, Xiao Wang can arrive at Mr. Zhang's home before 10 o'clock and complete the installation and maintenance task within 45 minutes, ensuring the timeliness of the service.

[0056] Through this method, the system can make full use of installation and maintenance resources and avoid inefficiencies caused by insufficient or overloaded human resources in a single grid area. At the same time, through a flexible collaborative area mechanism, the system can optimize resource allocation over a larger range to ensure that each work order can be efficiently processed within the appropriate time.

[0057] An embodiment of the present invention provides a work order allocation scheme, which obtains work order details of a target work order, and then divides the target work order into a target grid area among multiple grid areas according to the work order details, and uses the average installation and maintenance time information of the target grid area as the estimated installation and maintenance time information of the target work order. At the same time, the estimated commuting time information of the target work order is determined. According to the estimated installation and maintenance time information, the estimated commuting time information, and the customer appointment time information of the target work order, the target work order is allocated to the installation and maintenance staff in the target grid area or the collaborative area.

[0058] By acquiring detailed information of the target work order and reasonably dividing and estimating it, the embodiment of the present invention can more accurately calculate the estimated installation and maintenance time information and estimated commuting time information of each target work order, allowing for more flexible arrangement of installation and maintenance tasks, and reducing the problem of customers waiting too long for the next order due to the timeout of the previous order. Through better time management and task allocation, the waiting time of customers is effectively shortened, thereby improving customer satisfaction and reducing complaints and negative brand impacts caused by delays. It is no longer limited to the mode that one installation and maintenance staff is responsible for one grid area, but according to the detailed information of the target work order and the average installation and maintenance time information of each grid area, the target work order is reasonably allocated to the installation and maintenance staff in the target grid area or the collaborative area. The flexible allocation mechanism effectively solves the problem that some grid areas have heavy installation and maintenance tasks, while other grid areas have fewer installation and maintenance tasks, and realizes the balanced allocation of human resources. By more reasonably utilizing the working time of the installation and maintenance staff, the overall production efficiency is improved. By accurately calculating the estimated installation and maintenance time information and the estimated commuting time information of the target work order, the work tasks of the installation and maintenance staff can be better arranged to ensure that the installation and maintenance work is processed in time within the customer's appointment time. It not only improves the timeliness of installation and maintenance work, but also improves service quality and further increases customer satisfaction. It enables installation and maintenance staff to complete tasks more efficiently and reduces the problem of overwork or idleness of some employees due to uneven workload. By reasonably allocating target work orders and optimizing resource utilization, the overall efficiency of the installation and maintenance team has been significantly improved, and the company's operating results have also been improved.

[0059] To sum up, compared with the traditional installation and maintenance dispatching model, the embodiments of the present invention not only effectively solve the problems of work order time overlap and uneven distribution of human resources through a more flexible and accurate work order division and allocation mechanism, but also significantly improve the timeliness and overall efficiency of installation and maintenance work, thereby improving customer satisfaction and the company's operating results.

[0060] In an exemplary embodiment of the present invention, an implementation method of assigning a target work order to an installation and maintenance staff in a target grid area or a collaborative area based on the estimated installation and maintenance time information, the estimated commuting time information and the customer appointment time information of the target work order is as follows: the estimated installation and maintenance time information and the estimated commuting time information are added to obtain the estimated on-site time information; the estimated on-site time information is compared with the customer appointment time information to obtain a comparison result; if the comparison result indicates that the estimated on-site time information is less than or equal to the customer appointment time information, the target work order is assigned to the installation and maintenance staff in the target grid area; if the comparison result indicates that the estimated on-site time information is greater than the customer appointment time information, the target work order is assigned to the installation and maintenance staff in the collaborative area.

[0061] In the process of work order allocation, considering the actual installation and maintenance time, commuting time and the customer's appointment time, resource allocation can be optimized and customer satisfaction can be improved. In actual application, the estimated door-to-door time information refers to the total time required for the installation and maintenance personnel to reach the target customer's location from the start of the current task. Specifically, the estimated door-to-door time information is equal to the sum of the estimated installation and maintenance time information and the estimated commuting time information. Assuming that the estimated installation and maintenance time of Mr. Zhang's work order is 45 minutes and the estimated commuting time is 20 minutes, then the estimated door-to-door time information is 45 minutes + 20 minutes = 65 minutes. Compare the estimated door-to-door time information with the customer's appointment time information to obtain a comparison result. The customer's appointment time information refers to the time interval that the customer wants the installation and maintenance personnel to provide door-to-door service. For example, Mr. Zhang's appointment time is from 10 am to 12 pm. At this time, the system will check the current time and the estimated door-to-door time to determine whether it is within the appointment time range. Based on the comparison result, the system decides to assign the work order to the installation and maintenance personnel in the target grid area or the collaboration area. If the estimated door-to-door time information is less than or equal to the customer's appointment time information, that is, the installation and maintenance personnel can complete the task within the appointment time, then the system assigns the work order to the installation and maintenance personnel in the target grid area. For example, the current time is 9 am, Xiao Li needs 65 minutes to complete the task, he can arrive at Mr. Zhang's house at 10:05 am and complete the task within the appointment time. If the estimated door-to-door time information is greater than the customer's appointment time information, that is, the installation and maintenance personnel cannot complete the task within the appointment time, then the system assigns the work order to the installation and maintenance personnel in the collaborative area. For example, the current time is 9 am, and Xiao Li needs 2 hours to complete the task, which will exceed the deadline of 12 am scheduled by Mr. Zhang. Therefore, the system will check the installation and maintenance personnel in the adjacent grid areas and look for installation and maintenance personnel who can complete the task within the appointment time. Assuming Xiao Wang is in the adjacent area, his commuting time is 15 minutes, and the installation and maintenance time is 45 minutes, a total of 60 minutes, and he can complete the task within the appointment time, then the system assigns the work order to Xiao Wang.

[0062] The embodiment of the present invention effectively optimizes the work order allocation process by accurately calculating and comparing the estimated door-to-door time information and the customer appointment time information. It ensures that the installation and maintenance tasks can be completed efficiently within the customer appointment time, improves customer satisfaction, and reduces complaints caused by installation and maintenance delays. In addition, it also makes full use of installation and maintenance resources, avoids the problem of overload or idle installation and maintenance personnel in certain areas, and improves the work efficiency of the overall installation and maintenance team and the operating effect of the enterprise.

[0063] In an exemplary embodiment of the present invention, an implementation method for determining the estimated commuting time information of a target work order is to search in a commuting record database whether there is a commuting record from the destination of the previous work order of the target work order to the destination of the target work order; if there is a commuting record in the commuting record database, the commuting time information corresponding to the commuting record is used as the estimated commuting time information; if there is no commuting record in the commuting record database, the estimated commuting time information is calculated using a path planning algorithm in a geographic vector map. In actual application, the system searches in the commuting record database whether there is a commuting record from the destination of the previous work order of the target work order to the destination of the target work order. The commuting record database stores a large amount of historical commuting data, including commuting time between different locations. These data can help the system quickly obtain the estimated commuting time, reduce calculation time, and improve efficiency. For example, suppose that the previous work unit of the maintenance personnel Xiao Li was in Community A, and now he needs to go to Community B to process a new work order. The system searches the commuting record database for historical commuting records from Community A to Community B. If this record exists in the database and the recorded commuting time is 20 minutes, the system will directly use 20 minutes as Xiao Li's estimated commuting time information. If there is no commuting record from the previous work order destination to the target work order destination in the commuting record database, the system will use the path planning algorithm in the geographic vector map to calculate the estimated commuting time information. The geographic vector map contains detailed road information, traffic rules, and real-time traffic conditions. The path planning algorithm can calculate the best driving path and estimated time required for the maintenance personnel based on this information. For example, if there is no historical commuting record from community A to community B in the database, the system will calculate the estimated commuting time for the path through the path planning algorithm. The algorithm will take into account the current traffic conditions, road congestion, and traffic rules, and finally calculate a reasonable estimated commuting time, assuming it is 25 minutes. This real-time calculation method ensures that the system can still provide accurate commuting time information in the absence of historical data.

[0064] The embodiment of the present invention combines historical data and real-time calculation to ensure the accuracy and reliability of commuting time information. By searching the commuting record database, the system can quickly obtain historical commuting time information, greatly reducing calculation time and improving the efficiency of work order allocation. In the absence of historical data, the path planning algorithm can provide real-time commuting time prediction to ensure that the processing of each work order can be supported in a timely manner.

[0065] In an exemplary embodiment of the present invention, an implementation method of using a path planning algorithm to calculate estimated commuting time information in a geographic vector map is to use the geographic vector map as a weighted undirected graph, the weighted undirected graph includes a set of vertices and a set of arcs, the vertices represent intersections, buildings, etc., and the arcs represent the distance between the vertices; using a dynamically adaptive Metropolis acceptance criterion, the estimated commuting time information is calculated using an ant colony algorithm. In the actual application process, the geographic vector map is represented as a weighted undirected graph. The weighted undirected graph includes two basic elements: a set of vertices and a set of arcs. The vertices represent key nodes in the map, such as intersections, buildings, etc. The arcs represent the paths between the vertices, and each arc has a weight, which represents the distance or commuting time between the two vertices. The weight can be adjusted according to factors such as the length of the actual road and traffic conditions. For example, in a geographic vector map of a city, a certain intersection L and another intersection P can be used as vertices, and the road between intersection L and intersection P can be used as an arc, and the weight of the arc can represent the actual distance from intersection L to intersection P or the estimated commuting time. The dynamic adaptive Metropolis acceptance criterion is an acceptance criterion used in optimization algorithms. This criterion dynamically balances exploration and exploitation in the search process by adjusting the acceptance probability. In path planning, this criterion can help the ant colony algorithm to more effectively jump out of the local optimum and find the global optimal solution when searching for the best path. Specifically, when the ant colony algorithm chooses between multiple paths, the dynamic adaptive Metropolis acceptance criterion adjusts the probability of accepting a new path based on the quality of the current path and the number of iterations. If the new path is better, it is accepted with a higher probability; if the new path is worse, it is accepted with a lower probability, but it is not completely excluded. This dynamic adjustment helps the algorithm to conduct extensive exploration in the early stage and fine optimization in the later stage. Ant Colony Optimization (ACO) is an optimization algorithm based on swarm intelligence that imitates the behavior of ants marking paths with pheromones when looking for food. The algorithm performs well in path planning and is suitable for solving complex shortest path problems. In practical applications, each "ant" represents a possible path choice. In each iteration, the ant selects the vertex for the next step based on the pheromone concentration on the path and the weight of the path (distance or time). As the number of iterations increases, the pheromone concentration on excellent paths will gradually increase, thereby attracting more ants to choose these paths. Combined with the dynamically adaptive Metropolis acceptance criterion, the algorithm can explore the entire graph more effectively and avoid falling into local optimality. For example, from vertex L to vertex P, the ant colony algorithm simulates the movement of multiple ants in a geographic vector map. Each ant will select the vertices and paths it passes through, and mark the pheromone according to the path length and commuting time. After multiple iterations, the algorithm will gradually converge to the optimal path and obtain the estimated commuting time information from vertex L to vertex P.

[0066] The embodiment of the present invention combines a weighted undirected graph and an ant colony algorithm to efficiently calculate the optimal path and commuting time between multiple locations, and is particularly suitable for large-scale and complex urban road networks. The use of a dynamically adaptive Metropolis acceptance criterion enables the algorithm to dynamically adjust during the search process, balance global search and local optimization, avoid falling into local optimality, and ensure that the global optimal path is found. By utilizing detailed road information and traffic conditions in geographic vector maps, the algorithm can provide more accurate commuting time predictions and improve the accuracy and reliability of work order assignments. The representation of a weighted undirected graph allows the algorithm to flexibly adapt to geographical environments of different sizes and complexities, and is suitable for a variety of practical application scenarios. Through accurate commuting time predictions, installation and maintenance personnel can arrive at customer sites more punctually, reduce customer waiting time, improve customer satisfaction, and reduce complaint rates.

[0067] In an exemplary embodiment of the present invention, before obtaining the detailed information of the work order of the target work order, an implementation method is to obtain the work order history data in the target geographical area; and cluster the work order destinations in the work order history data using an unsupervised learning algorithm to obtain multiple grid areas. In the actual application process, it is necessary to collect and organize the work order history data in the target geographical area. These data usually include the specific location of the work order (such as the customer address or the building location), the work order type (such as installation, maintenance, repair, etc.), the work order completion time, the installation and maintenance personnel information and other related business data. These data are the basis for subsequent clustering analysis, and the integrity and accuracy of the data directly affect the quality of the clustering results. For example, in a certain urban area, all the installation and maintenance work order data in the past year can be used as historical data, which contains information such as the specific address, processing time and type of each work order. Next, the work order destinations in the work order history data are clustered using an unsupervised learning algorithm. Unsupervised learning algorithm (ULA for short) is a type of machine learning algorithm that does not require pre-labeled data sets, and groups and classifies data by discovering patterns and structures in the data. Commonly used unsupervised learning algorithms include K-means clustering and hierarchical clustering. In this process, the geographical location of each work order can be used as the main feature of cluster analysis. These location data are input into the clustering algorithm, and the algorithm will cluster the work orders into several grid areas based on the similarity of the geographical locations. The work orders in each grid area are relatively concentrated in geographical location, which is conducive to the subsequent dispatching and management of installation and maintenance personnel. For example, using the K-means clustering algorithm, the work order data in the urban area is analyzed, and finally several grid areas are obtained. The work orders in each grid area are relatively concentrated in geographical location, thus forming a reasonable service area.

[0068] For example: suppose that the historical data of installation and maintenance work orders of a telecommunications company in a city area includes 1,000 work order records, which cover all installation and maintenance tasks in the past year. Through data preprocessing, the geographical location of each work order is extracted, and these location data are input into the K-means clustering algorithm. After multiple iterations and calculations, the algorithm finally clusters these work orders into 10 grid areas. The work orders in each grid area are relatively close in geographical location. For example, grid area 1 contains 100 work orders in the city center, grid area 2 contains 150 work orders in the northern suburbs, and so on. In this way, telecommunications companies can better manage and allocate installation and maintenance personnel to ensure that the installation and maintenance tasks in each grid area can be handled in a timely manner.

[0069] The grid areas formed by clustering in the embodiments of the present invention make the dispatching and management of installation and maintenance personnel more efficient, avoid waste of resources and excessive load, and improve overall work efficiency. The work orders in the grid area after clustering analysis are relatively concentrated in geographical location, which helps installation and maintenance personnel to quickly respond to customer needs, shorten response time, and improve customer satisfaction. Reasonable grid area division can reduce the commuting time and cost of installation and maintenance personnel, improve the completion efficiency of installation and maintenance tasks, and reduce the operating costs of enterprises. Through regular updates and re-clustering, the grid area division can be dynamically adjusted according to actual business needs and changes in geographical areas to ensure the flexibility and adaptability of installation and maintenance services. Using unsupervised learning algorithms to cluster historical work order data enables enterprises to make more scientific decisions based on data analysis and improve the accuracy and effectiveness of decisions.

[0070] In an exemplary embodiment of the present invention, an implementation method of clustering the work order destinations in the work order history data using an unsupervised learning algorithm to obtain multiple grid areas is to initialize the neighborhood radius and density threshold of the unsupervised learning algorithm; according to the neighborhood radius and density threshold, the coordinate points corresponding to each work order destination are divided into core points, boundary points or noise points; each core point is taken as the center point of each grid area, and the boundary points within the neighborhood radius of each center point are classified into the grid area where the center point is located, and the noise points are excluded to generate multiple grid areas. In the actual application process, two key parameters of the unsupervised learning algorithm are initialized: the neighborhood radius r and the density threshold (MinPts). The neighborhood radius r defines the neighborhood range of each point, that is, other points within this range are considered to be adjacent to the point. The density threshold (MinPts) refers to the number of points that must be included in the neighborhood radius to determine whether a point is a core point. For example, in an urban area, assume that the neighborhood radius is set to 500 meters and the density threshold is set to 5 points. If a work order destination has at least 5 other work order destinations within 500 meters, then this point can be considered a core point. According to the set neighborhood radius and density threshold, the coordinate points of each work order destination are classified. Specifically:

[0071] Core point: A point that contains at least the density threshold number of points within its neighborhood radius.

[0072] Border points: The number of points contained within their neighborhood radius is less than the density threshold, but is within the neighborhood of the core point.

[0073] Noise point: a point that is neither a core point nor a boundary point, that is, the number of points in its neighborhood is less than the density threshold and is not in the neighborhood of any core point.

[0074] For example, if there are 8 other work order destinations within 500 meters of a work order destination A, then A is considered a core point. If another work order destination B has only 3 points within 500 meters, but one of these 3 points is core point A, then B is considered a boundary point. If a work order destination C has only 2 points within 500 meters and neither of these two points is a core point, then C is considered a noise point.

[0075] After the core points are determined, each core point is used as the center point, and the boundary points within its neighborhood radius are classified into the grid area where the core point is located. This process will exclude all noise points, thereby generating multiple grid areas. For example, core point A and all boundary points within its neighborhood range together form a grid area, and the center point of this grid area is A. In this way, several grid areas can be formed in the entire geographical area, and the work order destinations in each area are relatively concentrated in terms of geographical location.

[0076] The embodiment of the present invention can more efficiently allocate installation and maintenance personnel, avoid resource waste and excessive load, and improve overall work efficiency by reasonably clustering the work order destinations and grouping geographically close work orders into one grid area. The work orders with similar geographical locations are concentrated in one grid area, which helps installation and maintenance personnel to quickly respond to and process work orders, shorten response time, and improve customer satisfaction. Reasonable grid area division can reduce the commuting time and cost of installation and maintenance personnel, improve the efficiency of completing installation and maintenance tasks, and reduce the operating costs of the enterprise. By identifying and eliminating noise points, it is ensured that the work order data in each grid area is more accurate and reliable, which helps to improve the accuracy of work order allocation and management.

[0077] In an exemplary embodiment of the present invention, after allocating the target work order to the installation and maintenance staff in the target grid area or the collaborative area based on the estimated installation and maintenance time information, the estimated commuting time information and the customer appointment time information of the target work order, an implementation method is to set multiple grid areas into multiple collaborative areas; predict the total work order volume of each collaborative area in the next cycle; if the total work order volume of the target collaborative area in the next cycle among the multiple collaborative areas is less than the total work order volume of the current cycle, filter out at least one grid area from the target collaborative area, and divide the filtered grid area into other collaborative areas; if the total work order volume of the target collaborative area in the next cycle is greater than or equal to the total work order volume of the current cycle, add a new grid area to the target collaborative area.

[0078] In the actual application process, the multiple grid areas previously obtained by clustering are further integrated and set into several collaborative areas. A collaborative area is a larger area composed of multiple adjacent or geographically close grid areas. This setting helps to better coordinate and manage installation and maintenance personnel and ensure that resources are optimally allocated over a larger range. For example, assuming that there are 20 grid areas in a city, these grid areas can be divided into 5 collaborative areas based on geographical location and work order volume, and each collaborative area contains 4 grid areas. This integration method can improve the flexibility of resource scheduling. Next, the total work order volume of each collaborative area in the next cycle (such as a week or a month) is predicted using a prediction algorithm. The prediction algorithm can be based on a comprehensive analysis of historical data, seasonal factors, market activities and other factors to derive the work order demand of each collaborative area in the future cycle. For example, by analyzing the work order data of the past six months and combining the information of marketing activities, the expected work order volume of a collaborative area in the next month can be predicted. This prediction can help enterprises make resource scheduling and arrangements in advance. Based on the prediction results, multiple collaborative areas are dynamically adjusted:

[0079] If the forecast shows that the total number of work orders in the next cycle of the target collaboration area is less than the total number of work orders in the current cycle, at least one grid area is selected from the target collaboration area and divided into other collaboration areas. This can balance the workload of each collaboration area and avoid idle resources.

[0080] If the forecast shows that the total work order volume of the next cycle in the target collaboration area is greater than or equal to the total work order volume of the current cycle, a new grid area needs to be added to the target collaboration area to cope with the increased workload.

[0081] For example, if the estimated work order volume of collaboration area A in the next month is 200, and the work order volume of the current month is 300, then a grid area in collaboration area A can be divided into the adjacent collaboration area B to reduce the burden of A. Conversely, if the estimated work order volume of collaboration area C is 400, and the work order volume of the current month is 350, then a new grid area needs to be added to C to ensure that the increased work orders can be processed in a timely manner.

[0082] The embodiments of the present invention can ensure the rational allocation of installation and maintenance personnel and resources, avoid resource waste and excessive load, and improve overall work efficiency by dynamically adjusting grid areas and collaborative areas. Through prediction and adjustment, changes in the number of work orders can be responded to in advance to ensure that the work orders in each area can be processed in a timely manner, thereby improving customer satisfaction. Reasonable resource scheduling and flexible adjustment mechanisms can reduce operating costs caused by fluctuations in the number of work orders and improve the economic benefits of the enterprise. Through dynamic adjustment, a quick response can be made when the number of work orders suddenly increases, avoiding service delays and customer complaints due to insufficient resources. By setting up a dynamic adjustment mechanism for collaborative areas and grid areas, enterprises can flexibly respond to market changes and business needs and improve work efficiency and adaptability.

[0083] Based on the above description of an embodiment of a method for allocating a work order, a method for dispatching work orders based on a map and cross-grid collaboration is introduced below. The method for dispatching work orders may specifically include the following steps:

[0084] Step S1: Based on the work order type, work order task, installation and maintenance destination address and longitude and latitude, an unsupervised learning algorithm is used to perform clustering processing to obtain multiple grid areas, and the average installation and maintenance time of each grid area is determined.

[0085] Step S2: When a new work order arrives, the grid area to which the new work order belongs is divided according to the field information of step S1, and the average installation and maintenance time of the grid area to which it belongs is the estimated installation and maintenance time of the new work order.

[0086] Step S3: For a new work order, if the commuting record from the previous work order destination to the current work order destination exists in the database, the historically recorded path and estimated commuting time are directly output; if the commuting record does not exist in the database, the estimated commuting time from the previous work order destination to the current work order destination is obtained by parsing the map data and using a path planning algorithm on a real geographic vector map.

[0087] Step S4: Combine the estimated installation and maintenance time of step S2 with the estimated commuting time of step S3. If the sum of the two is less than or equal to the customer's appointment time, the new work order will still be sent to the installation and maintenance staff corresponding to the grid area. If the sum of the two is greater than the customer's appointment time, the new work order will be sent to the collaboration area for order grabbing collaboration.

[0088] Step S5: Based on historical management experience, multiple grid areas are initialized and set to collaboration area 1-collaboration area n, and predictions are made for each collaboration area. When it is predicted that the total work order volume of a certain assistance area next month is similar to, equal to, or greater than the total work order volume of this month, a new grid area needs to be added to the assistance area. When it is predicted that the total work order volume of a certain assistance area next month is less than the total work order volume of this month, a grid area needs to be selected from the assistance area and divided into other collaboration areas to form a new collaboration area.

[0089] In an embodiment of the present invention, in the above step S1, taking the geographical area of ​​a business service as an example, first, the installation and maintenance work orders in the business service are classified according to the work order tasks, such as gigabit broadband, smart home services, interactive network television (Internet Protocol Television, IPTV for short) and other categories, and then on the basis of the work order task division, further fine division is performed according to the new installation / repair work order type, such as gigabit broadband (new installation), gigabit broadband (repair), smart home service (new installation), smart home service (repair), IPTV (new installation), IPTV (repair) and other categories.

[0090] In an embodiment of the present invention, in the above step S1, the parameters of the unsupervised learning algorithm include the radius r and the density threshold MinPts. For a given data set of longitude and latitude of the destination addresses of each installation and maintenance work order in the service map area, with latitude as the horizontal coordinate and longitude as the vertical coordinate, each installation and maintenance work order is converted into corresponding coordinate points on the coordinate system to represent it.

[0091] In the embodiment of the present invention, in the above step S1, an unsupervised algorithm clustering operation is performed on each of the above categories within the geographical area of ​​the service, and the specific operation is as follows:

[0092] ① Initialization parameters:

[0093] r: Set a neighborhood radius. You will need to draw a circle with r as radius to determine the neighborhood range.

[0094] MinPts: Set the density threshold, that is, the minimum number of points in the neighborhood of a circle with a point as the center and r as the radius;

[0095] ②Find all the core points:

[0096] For each point in the data set, draw a circle with each point as the center and r as the radius. If the number of points in the circle is greater than or equal to MinPts, the corresponding point is marked as a core point;

[0097] ③Find the boundary points:

[0098] For the points in the data set, draw a circle with each of them as the center and r as the radius. If the number of points in the circle is less than MinPts but within the circular range defined by the core points above, these points are marked as boundary points;

[0099] ④Create a grid area:

[0100] Traverse all points in the data set and mark them as core points or boundary points according to the above rules. If some points do not meet the rules of core points or boundary points, they will be marked as noise points. Each core point is used as the center of its own grid area, and the boundary points in its neighborhood are included in its own grid area to form multiple grid areas and exclude noise points.

[0101] ⑤The algorithm ends:

[0102] When all points in the data set have been processed, the algorithm ends and returns the results of the above clustering processing.

[0103] In the embodiment of the present invention, in the above step S2, the problem that the time required for the same installation and maintenance task may be different due to different locations, such as urban villages, standard communities, etc., can be overcome.

[0104] In an embodiment of the present invention, in the above step S3, since the staff in the grid area are very familiar with some paths in their own grid area and know how to take some small roads, which are difficult for the system to calculate, the actual traffic paths and actual times of occurrence of the previous installation and maintenance staff are recorded.

[0105] In an embodiment of the present invention, in the above step S3, since the installation and maintenance staff are familiar with and understand some paths in the grid area they are responsible for, such as some shortcuts and small roads, but it is difficult for the system to calculate such paths, it is necessary to record the historical data of the installation and maintenance staff in previous decoration tasks, and the historical data includes the actual traffic path and the actual time of occurrence.

[0106] Reference Figure 2 , showing a schematic diagram of a weighted undirected graph in an embodiment of the present invention. The letters F, G, H, ..., P, Q represent vertices respectively, and the lines between the vertices represent arcs. The box where the vertex is located represents the grid area where the vertex is located. The actual traffic road can be regarded as a weighted undirected graph. For a given weighted undirected graph (V, {E}), where V is a set of all vertices (vertices can represent intersections, buildings, etc.), the distance between vertices is just like the actual distance length E, which is a set of arcs (arcs can represent roads, etc.).

[0107] If we need to go from vertex F to vertex K in the graph, the dynamic adaptive Metropolis acceptance criterion is used in the search process of each individual in the ant colony algorithm, that is, the algorithm can accept inferior solutions with a greater probability in the early stage of the search, and the algorithm can accept inferior solutions with a smaller probability in the later stage of the search;

[0108] Reference Figure 3 , showing a schematic diagram of adaptively adjusting the collaboration area in an embodiment of the present invention. Figure 3In the example, area 1 includes collaboration area 1, collaboration area 2, collaboration area 3, and collaboration area 4. Moreover, each collaboration area of ​​area 1 includes grid 1, grid 2, ..., grid 16. Specifically, collaboration area 1 includes grid 1, grid 2, grid 3, and grid 4. Collaboration area 2 includes grid 9, grid 10, grid 11, and grid 12. After adaptive adjustment, collaboration area 1 includes grid 1, grid 2, grid 3, grid 4, and grid 10. Collaboration area 2 includes grid 9, grid 11, and grid 12.

[0109] In the above step S5, the threshold of abnormal work orders is set according to actual needs. When the system detects that the number of abnormal work orders in collaboration area 1 this month exceeds the threshold, and the work hour efficiency of the installation and maintenance staff in each grid in collaboration area 1 is as high as 95 or above, it means that the installation and maintenance manpower in the collaboration area is overloaded and the number of work orders this month is too large. The system builds a time series prediction model based on deep learning, and performs time series prediction on the work orders of each grid in the assistance area in the next month. If it is predicted that the total number of work orders in the assistance area next month is similar, equal to or greater than the total number of work orders this month, it is necessary to add a grid to the assistance area 1;

[0110] Similarly, the system continues to count the remaining collaboration areas 2-collaboration areas n according to the above steps. When it is detected that the working time efficiency in a collaboration area is low, the number of work orders is small, and there is an excess of installation and maintenance manpower, the system selects grids from the collaboration area and divides them into the remaining collaboration areas to form a new collaboration area.

[0111] Reference Figure 4 , shows a schematic diagram of a work order quantity prediction model based on deep learning in an embodiment of the present invention. The prediction model is mainly composed of an input layer, a long short-term memory network (LSTM) layer and a fully connected layer.

[0112] The input item of the input layer is the number of historical work orders x in the forecast month t 、x t-1 、x t-2 ,……,x t-p+1 , where t represents the previous month of the forecast month, p represents the limit number of input items, and x represents the number of work orders. For example, if you need to predict the number of work orders in collaboration zone 1 in April 2024, the input items are the historical work order numbers of collaboration zone 1 corresponding to March, February, and January 2024, and December, November, and October 2023.

[0113] The LSTM layer is mainly composed of several LSTMs. LSTM is a time recursive neural network that is suitable for processing and predicting important events with relatively long intervals and delays in time series. LSTM will selectively retain historical information and selectively learn the input information of the current moment. After the information is integrated, it is passed to the next moment as a hidden state, which can effectively avoid the gradient disappearance problem. The input historical work order number is extracted through the LSTM cycle to extract abstract feature state information. For example, if the input item uses the historical work order number of the first 50 months of the predicted month, each LSTM layer also corresponds to 50 LSTM module units.

[0114] The fully connected layer reads the above feature status information and generates output to predict the number of installation and maintenance work orders in the collaboration area next month.

[0115] In an embodiment of the present invention, in the above step S5, based on the map location technology, longitude and latitude are used to calculate the average location of all work order addresses this month within the respective grid areas of collaboration area R and collaboration area S, and the destination text description of each work order is converted into the longitude and latitude location on the actual map. The longitude and latitude data of each work order are used to calculate the average longitude and latitude location of all work orders in the corresponding collaboration area or grid area, and the two grid areas with similar overall average positions in the above two collaboration areas are checked as the grid areas selected to be divided into the remaining collaboration areas, and the operation of adaptively adjusting the scope of the assistance area is performed.

[0116] It should be noted that, for the sake of simplicity, the method embodiments are described as a series of action combinations, but those skilled in the art should be aware that the embodiments of the present invention are not limited by the order of the actions described, because according to the embodiments of the present invention, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of the present invention.

[0117] Reference Figure 5 , shows a structural block diagram of a work order distribution system according to an embodiment of the present invention. The work order distribution system may specifically include the following modules.

[0118] The work order information acquisition module 51 is used to obtain detailed work order information of the target work order;

[0119] A work order grid division module 52 is used to divide the target work order into a target grid area among a plurality of grid areas according to the work order detailed information, and use the average installation and maintenance time information of the target grid area as the estimated installation and maintenance time information of the target work order;

[0120] A commuting time estimation module 53, used to determine the estimated commuting time information of the target work order;

[0121] The target work order allocation module 54 is used to allocate the target work order to the installation and maintenance personnel in the target grid area or the collaborative area according to the estimated installation and maintenance time information, the estimated commuting time information and the customer appointment time information of the target work order.

[0122] In an exemplary embodiment of the present invention, the target work order allocation module 54 includes:

[0123] An estimated door-to-door time information calculation module, used to add the estimated installation and maintenance time information and the estimated commuting time information to obtain the estimated door-to-door time information;

[0124] A time information comparison module, used to compare the estimated door-to-door time information with the customer appointment time information to obtain a comparison result;

[0125] A work order allocation module is used to allocate the target work order to the installation and maintenance staff in the target grid area if the comparison result indicates that the estimated on-site time information is less than or equal to the customer appointment time information; if the comparison result indicates that the estimated on-site time information is greater than the customer appointment time information, the target work order is allocated to the installation and maintenance staff in the collaborative area.

[0126] In an exemplary embodiment of the present invention, the commuting time estimation module 53 includes:

[0127] A database search module, used for searching in a commuting record database whether there is a commuting record from the destination of a previous work order of the target work order to the destination of the target work order;

[0128] a commuting time determination module, configured to use the commuting time information corresponding to the commuting record as the estimated commuting time information if the commuting record exists in the commuting record database;

[0129] A commuting time calculation module is used to calculate the estimated commuting time information using a path planning algorithm in a geographic vector map if the commuting record does not exist in the commuting record database.

[0130] In an exemplary embodiment of the present invention, the commuting time calculation module includes:

[0131] A weighted undirected graph determination module, used to treat the geographic vector map as a weighted undirected graph, wherein the weighted undirected graph includes a set of vertices and a set of arcs, wherein the vertices represent intersections and buildings, and the arcs represent distances between vertices;

[0132] The ant colony algorithm calculation module is used to use the dynamically adaptive Metropolis acceptance criterion and the ant colony algorithm to calculate the estimated commuting time information.

[0133] In an exemplary embodiment of the present invention, the system further comprises:

[0134] A work order history data acquisition module, used to acquire work order history data in a target geographical area before the work order information acquisition module 51 acquires the work order detailed information of the target work order;

[0135] The grid area clustering module is used to cluster the work order destinations in the work order history data using an unsupervised learning algorithm to obtain a plurality of the grid areas.

[0136] In an exemplary embodiment of the present invention, the grid area clustering module includes:

[0137] A parameter initialization module, used to initialize the neighborhood radius and density threshold of the unsupervised learning algorithm;

[0138] A point division module, used for dividing the coordinate point corresponding to each work order destination into a core point, a boundary point or a noise point according to the neighborhood radius and the density threshold;

[0139] The grid area drawing module is used to take each core point as the center point of each grid area, classify the boundary points within the neighborhood radius of each center point into the grid area where the center point is located, and exclude the noise points to generate multiple grid areas.

[0140] In an exemplary embodiment of the present invention, the system further comprises:

[0141] A collaboration area setting module, configured to set a plurality of the grid areas into a plurality of the collaboration areas after the target work order assignment module 54 assigns the target work order to the installation and maintenance personnel in the target grid area or the collaboration area according to the estimated installation and maintenance time information, the estimated commuting time information and the customer appointment time information of the target work order;

[0142] A work order quantity prediction module, used to predict the total work order quantity of each collaboration area in the next cycle;

[0143] A collaboration area adjustment module is used to select at least one of the grid areas from the target collaboration area and divide the selected grid areas into other collaboration areas if the total work order volume of the next cycle of the target collaboration area among the multiple collaboration areas is less than the total work order volume of the current cycle; if the total work order volume of the next cycle of the target collaboration area is greater than or equal to the total work order volume of the current cycle, add a new grid area to the target collaboration area.

[0144] As for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0145] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0146] It will be appreciated by those skilled in the art that the embodiments of the present invention may be provided as methods, devices, or computer program products. Therefore, the embodiments of the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the embodiments of the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0147] The embodiments of the present invention are described with reference to the flowcharts and / or block diagrams of the methods, terminal devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0148] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing terminal device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0149] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device so that a series of operating steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable terminal device to implement the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0150] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present invention.

[0151] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or terminal device including the elements.

[0152] The above is a detailed introduction to a work order allocation method and a work order allocation system provided by the present invention. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for general technical personnel in this field, according to the idea of ​​the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A method for allocating a work order, characterized in that: The method comprises: Get the work order details of the target work order; Dividing the target work order into a target grid area among a plurality of grid areas according to the work order detailed information, and using the average installation and maintenance time information of the target grid area as the estimated installation and maintenance time information of the target work order; Determine estimated commuting time information for the target work order; According to the estimated installation and maintenance time information, the estimated commuting time information and the customer appointment time information of the target work order, the target work order is allocated to the installation and maintenance staff in the target grid area or the collaborative area.

2. The method according to claim 1, characterized in that The allocating the target work order to the installation and maintenance staff in the target grid area or the collaborative area according to the estimated installation and maintenance time information, the estimated commuting time information, and the customer appointment time information of the target work order includes: Adding the estimated installation and maintenance time information and the estimated commuting time information to obtain the estimated door-to-door time information; Comparing the estimated door-to-door time information with the customer appointment time information to obtain a comparison result; If the comparison result indicates that the estimated on-site visit time information is less than or equal to the customer appointment time information, the target work order is assigned to the installation and maintenance staff in the target grid area; If the comparison result indicates that the estimated on-site visit time information is greater than the customer appointment time information, the target work order is assigned to the installation and maintenance staff in the collaboration area.

3. The method according to claim 1, characterized in that The determining of the estimated commuting time information of the target work order includes: Searching in a commuting record database whether there is a commuting record from the destination of a previous work order of the target work order to the destination of the target work order; If the commuting record exists in the commuting record database, the commuting time information corresponding to the commuting record is used as the estimated commuting time information; If the commuting record does not exist in the commuting record database, a path planning algorithm is used in the geographic vector map to calculate the estimated commuting time information.

4. The method according to claim 3, characterized in that: The calculating the estimated commuting time information by using a path planning algorithm in a geographic vector map includes: The geographic vector map is used as a weighted undirected graph, wherein the weighted undirected graph includes a set of vertices and a set of arcs, wherein the vertices represent intersections and buildings, and the arcs represent distances between vertices; The estimated commuting time information is calculated using a dynamically adaptive Metropolis acceptance criterion and an ant colony algorithm.

5. The method according to claim 1, characterized in that Before obtaining the work order details of the target work order, the method further includes: Obtain historical data on work orders within the target geographic area; An unsupervised learning algorithm is used to cluster the work order destinations in the work order history data to obtain a plurality of the grid areas.

6. The method according to claim 5, characterized in that The method of clustering the work order destinations in the work order history data using an unsupervised learning algorithm to obtain a plurality of grid areas includes: Initializing the neighborhood radius and density threshold of the unsupervised learning algorithm; According to the neighborhood radius and the density threshold, the coordinate point corresponding to each work order destination is divided into a core point, a boundary point or a noise point; Each core point is taken as the center point of each grid area, the boundary points within the neighborhood radius of each center point are classified into the grid area where the center point is located, and the noise points are excluded to generate multiple grid areas.

7. The method according to claim 1, characterized in that After allocating the target work order to the installation and maintenance staff in the target grid area or the collaborative area according to the estimated installation and maintenance time information, the estimated commuting time information, and the customer appointment time information of the target work order, the method further includes: Arrange a plurality of the grid areas into a plurality of the collaboration areas; Predicting the total number of work orders in the next cycle for each of the collaboration areas; If the total work order volume of the next cycle of the target collaborative area among the multiple collaborative areas is less than the total work order volume of the current cycle, at least one of the grid areas is selected from the target collaborative area, and the selected grid area is divided into other collaborative areas; If the total work order volume of the next cycle of the target collaboration area is greater than or equal to the total work order volume of the current cycle, then the new grid area is added to the target collaboration area.

8. A work order distribution system, characterized in that: The system comprises: The work order information acquisition module is used to obtain detailed work order information of the target work order; A work order grid division module, used to divide the target work order into a target grid area among multiple grid areas according to the work order detailed information, and use the average installation and maintenance time information of the target grid area as the estimated installation and maintenance time information of the target work order; A commuting time estimation module, used to determine the estimated commuting time information of the target work order; The target work order allocation module is used to allocate the target work order to the installation and maintenance personnel in the target grid area or the collaborative area according to the estimated installation and maintenance time information, the estimated commuting time information and the customer appointment time information of the target work order.

9. An electronic device, characterized in that: include: one or more processors; and One or more machine-readable media having instructions stored thereon, when executed by the one or more processors, enable the electronic device to execute the work order allocation method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer program stored therein enables the processor to execute the work order allocation method as described in any one of claims 1 to 7.

Images