Fault work order scheduling method, system and device based on multi-dimensional data model

Abstract

This invention discloses a fault work order scheduling method, system, and apparatus based on a multidimensional data model. The method includes: acquiring user fault work orders and maintenance personnel's operation and maintenance data; obtaining work order description data through information extraction; performing matching mining and prediction based on historical operation and maintenance databases and work order description data to obtain an initial spare parts list; generating a corresponding spare parts list through spare parts optimization; obtaining the spare parts retrieval time, spare parts coverage score, and skill matching degree of maintenance personnel for fault work orders based on the spare parts list and operation and maintenance data, thereby obtaining an initial operation and maintenance list for fault work orders; obtaining the optimal retrieval point for the required spare parts based on the initial operation and maintenance list and the location data of maintenance personnel; obtaining the commuting time of maintenance personnel in the initial operation and maintenance list based on the optimal retrieval point and location data, thereby obtaining the scheduling result of the fault work orders. This invention achieves efficient and accurate scheduling of fault work orders based on multidimensional data.

Description

Technical Field

[0001] This invention relates to the field of work order scheduling technology, specifically to a fault work order scheduling method, system, and device based on a multidimensional data model. Background Technology

[0002] Proper scheduling of fault work orders helps improve customer satisfaction and service efficiency. Improper allocation of fault work orders can negatively impact processing efficiency, jeopardize customer satisfaction, damage the image of operations and maintenance (O&M), and lead to low O&M efficiency. Therefore, reasonable and effective scheduling of fault work orders is essential.

[0003] Traditional fault ticket scheduling methods focus on a single data dimension, such as distance, while ignoring other variables affecting operational efficiency, such as working hours and spare parts requirements. This makes them unsuitable for dynamic and complex scenarios. Furthermore, they fail to integrate the required spare parts into the overall analysis, leading to situations where maintenance personnel do not carry the necessary spare parts. In addition, one-dimensional data analysis is insufficient for a comprehensive understanding of both maintenance personnel and fault tickets, resulting in inadequate matching between them. This increases the time maintenance personnel spend handling faults, leading to inefficiency and negatively impacting user satisfaction. Traditional methods relying on manual scheduling by dispatchers, allocating fault tickets according to fixed rules, suffer from slow response times, resource mismatches, and a lack of information transparency. Summary of the Invention

[0004] This invention addresses the shortcomings of existing fault work order scheduling methods, such as single data dimension and low processing efficiency, by providing a fault work order scheduling method, system, and device based on a multi-dimensional data model.

[0005] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0006] A fault work order scheduling method based on a multidimensional data model includes the following steps: Obtain user fault work orders and maintenance data of maintenance personnel, extract information from fault work orders to obtain work order description data; build a historical maintenance database to perform matching, mining and prediction based on work order description data to obtain an initial spare parts list. The initial spare parts list is optimized by using operation and maintenance data to generate a spare parts list corresponding to the fault work order. The spare parts list includes spare parts type, corresponding probability data, spare parts location and spare parts quantity. Based on the spare parts list and maintenance data, the spare parts retrieval time and spare parts coverage score of maintenance personnel are obtained. The skill matching degree of maintenance personnel for fault work orders is obtained through the historical maintenance database. Based on the spare parts retrieval time, spare parts coverage score and skill matching degree, the initial maintenance list of fault work orders is obtained. By using the initial maintenance list and the location data of maintenance personnel, the optimal pick-up point for the required spare parts in the spare parts list is obtained. Based on the optimal pick-up point, the location data of maintenance personnel, and the location data of fault work orders, the commuting time of maintenance personnel in the initial maintenance list is obtained, and then the scheduling result of the fault work orders is obtained.

[0007] As one possible implementation method, the step of extracting information from fault work orders to obtain work order description data includes the following steps: Extract the text information from the fault work order and perform noise reduction processing to obtain the fault text information; Based on historical work order description data, a work order dictionary is constructed. Based on the work order dictionary, the fault text information is standardized and converted to obtain standard fault information. Through information extraction, the fault performance data, fault location data, and equipment type data of the fault work order are obtained. Vector transformation is performed based on the work order dictionary and standard fault information to obtain historical work order vectors and standard fault vectors. Then, similar work order data of faulty work orders are obtained through vector retrieval. By analyzing fault performance data and similar work order data, user spare parts data for faulty work orders are obtained. Combined with fault performance data, fault location data, and equipment type data, work order description data is generated.

[0008] As one possible implementation, the construction of a historical maintenance database, used for matching, mining, and prediction based on work order description data, to obtain an initial spare parts list, includes the following steps: Based on the maintenance data of maintenance personnel and historical work order description data, a historical maintenance database is constructed. The maintenance data includes penalty cost data, spare parts related data, historical maintenance data, and location data. A spare parts pre-training model is constructed, and the model is trained based on a historical operation and maintenance database to obtain a spare parts prediction model; the spare parts prediction model is as follows:

[0009] Based on the spare parts prediction model and the work order description data of the fault work orders, spare parts prediction is performed. By combining the spare parts prediction results with equipment type data, the spare parts types corresponding to the fault work orders and their corresponding probability data are obtained. By extracting the quantity of spare parts corresponding to the spare parts type from the user spare parts data, and forming an initial spare parts list corresponding to the fault work order based on the spare parts type, the corresponding probability data and the spare parts quantity. in, Indicates the first Spare parts were used in one of the fault work orders. The probability, Indicates the first A vector formed from the work order description data of each fault work order. , Indicates spare parts The corresponding model parameters, Indicates the first Did the fault work order use spare parts? , Indicates the first One spare part, It represents probability.

[0010] As one possible implementation method, optimizing the initial spare parts list using maintenance data to generate a spare parts list corresponding to the fault work order includes the following steps: Based on the penalty cost data and spare parts related data in the operation and maintenance data, and combined with the spare parts types and corresponding probability data in the initial spare parts list, a spare parts optimization function is constructed to optimize the spare parts types in the initial spare parts list corresponding to the fault work order. The spare parts optimization function is as follows:

[0011] Based on the results of spare parts optimization and the types of spare parts and corresponding probability data in the initial spare parts list, spare parts are selected to obtain the spare parts list corresponding to the fault work order. in, This indicates that maintenance personnel carry spare parts. The cost of carrying Indicate whether maintenance personnel carry spare parts. , This indicates that the maintenance personnel did not bring spare parts. Data on the cost of punishment, This indicates that spare parts were used in the fault work order. The probability, Indicates spare parts Spatial capacity data, This indicates the total capacity of the maintenance personnel. This indicates that maintenance personnel are concerned about spare parts. Available inventory Indicates the quantity of spare parts.

[0012] As one possible implementation method, the initial maintenance list is obtained through the following steps: The spare parts list is used to obtain the types of spare parts required for the fault work order and the corresponding spare parts location data. The operation and maintenance area is set. Based on the spare parts location data and the location data of the operation and maintenance personnel, the retrieval distance and time of all operation and maintenance personnel within the operation and maintenance area are obtained. Combined with the current task and interval operation time of the operation and maintenance personnel, the spare parts retrieval time is obtained. Based on the spare parts data and spare parts list of the maintenance personnel, and combined with the spare parts retrieval time of the maintenance personnel, the current spare parts coverage of the maintenance personnel is evaluated to obtain a spare parts coverage score. Based on the historical maintenance data and fault performance data of the maintenance personnel and fault work orders, the skill matching degree of the maintenance personnel for the current fault is calculated. The spare parts retrieval time, spare parts coverage score, and skill matching degree are normalized respectively. Based on the normalized spare parts retrieval time, spare parts coverage score, and skill matching degree, the corresponding comprehensive score of the current maintenance personnel is obtained. The initial maintenance list of fault work orders is obtained by sorting the comprehensive scores.

[0013] As one possible implementation method, the spare parts coverage score is:

[0014] The skill matching degree is:

[0015] in, Indicates maintenance personnel Spare parts coverage score Indicates maintenance personnel Carry spare parts Quantity, Indicate the required spare parts Quantity, Indicates the quantity of different types of spare parts. Indicates spare parts The number of inventory points, Indicates inventory point Medium spare parts Available quantity, This represents the time decay coefficient, and its value is determined based on the urgency level of the maintenance personnel. Indicates maintenance personnel Head to inventory point Spare parts pickup time, Indicates skill matching degree. Indicates maintenance personnel Successfully handled the fault Number of times, Indicates maintenance personnel Troubleshooting Total number of times Indicates the matching weight. Indicates maintenance personnel Skill rating.

[0016] As one possible implementation method, the scheduling result of the fault work order is obtained through the following steps: Obtain the inventory location of the required spare parts from the spare parts list. Based on the location information of the maintenance personnel, the inventory location of the required spare parts, and the fault location data, calculate the optimal retrieval point for the required spare parts. The optimal retrieval point is defined as follows:

[0017] Based on the optimal pickup point, spare parts list, location data of maintenance personnel, and fault location data, the commute time of maintenance personnel in the initial maintenance list to the current fault location is obtained. The commuting times of the maintenance personnel in the initial maintenance list are sorted, and fault work orders are assigned according to the sorting results to obtain the scheduling results of the fault work orders. in, Indicates spare parts The best pickup point Indicates the location of maintenance personnel and the pickup point. The distance between them Indicates the pickup point Distance from the fault location This indicates the distance between the location of the maintenance personnel and the location of the fault. Indicates spare parts The number of inventory points.

[0018] A fault work order scheduling system based on a multidimensional data model includes: The spare parts prediction module obtains user fault work orders and maintenance data from maintenance personnel, extracts information from fault work orders to obtain work order description data, and builds a historical maintenance database to perform matching, mining, and prediction based on the work order description data to obtain an initial spare parts list. The spare parts optimization module optimizes the initial spare parts list using operation and maintenance data, and generates a spare parts list corresponding to the fault work order. The spare parts list includes spare parts type, corresponding probability data, spare parts location and spare parts quantity. The maintenance matching module obtains the spare parts retrieval time and spare parts coverage score of maintenance personnel based on the spare parts list and maintenance data. It also obtains the skill matching degree of maintenance personnel for fault work orders through the historical maintenance database. Based on the spare parts retrieval time, spare parts coverage score and skill matching degree, it obtains the initial maintenance list of fault work orders. The work order scheduling module obtains the optimal pickup point for the required spare parts from the spare parts list by using the initial maintenance list and the location data of maintenance personnel. Based on the optimal pickup point, the location data of maintenance personnel, and the location data of the fault work order, it obtains the commuting time of maintenance personnel in the initial maintenance list, and then obtains the scheduling result of the fault work order.

[0019] A computer-readable storage medium storing a computer program that, when executed by a processor, implements the method described in any one of the following ways: Obtain user fault work orders and maintenance data of maintenance personnel, extract information from fault work orders to obtain work order description data; build a historical maintenance database to perform matching, mining and prediction based on work order description data to obtain an initial spare parts list. The initial spare parts list is optimized by using operation and maintenance data to generate a spare parts list corresponding to the fault work order. The spare parts list includes spare parts type, corresponding probability data, spare parts location and spare parts quantity. Based on the spare parts list and maintenance data, the spare parts retrieval time and spare parts coverage score of maintenance personnel are obtained. The skill matching degree of maintenance personnel for fault work orders is obtained through the historical maintenance database. Based on the spare parts retrieval time, spare parts coverage score and skill matching degree, the initial maintenance list of fault work orders is obtained. By using the initial maintenance list and the location data of maintenance personnel, the optimal pick-up point for the required spare parts in the spare parts list is obtained. Based on the optimal pick-up point, the location data of maintenance personnel, and the location data of fault work orders, the commuting time of maintenance personnel in the initial maintenance list is obtained, and then the scheduling result of the fault work orders is obtained.

[0020] A fault work order scheduling device based on a multidimensional data model includes a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, it implements the method described in any one of the following ways: Obtain user fault work orders and maintenance data of maintenance personnel, extract information from fault work orders to obtain work order description data; build a historical maintenance database to perform matching, mining and prediction based on work order description data to obtain an initial spare parts list. The initial spare parts list is optimized by using operation and maintenance data to generate a spare parts list corresponding to the fault work order. The spare parts list includes spare parts type, corresponding probability data, spare parts location and spare parts quantity. Based on the spare parts list and maintenance data, the spare parts retrieval time and spare parts coverage score of maintenance personnel are obtained. The skill matching degree of maintenance personnel for fault work orders is obtained through the historical maintenance database. Based on the spare parts retrieval time, spare parts coverage score and skill matching degree, the initial maintenance list of fault work orders is obtained. By using the initial maintenance list and the location data of maintenance personnel, the optimal pick-up point for the required spare parts in the spare parts list is obtained. Based on the optimal pick-up point, the location data of maintenance personnel, and the location data of fault work orders, the commuting time of maintenance personnel in the initial maintenance list is obtained, and then the scheduling result of the fault work orders is obtained.

[0021] This invention, by adopting the above technical solutions, has significant technical effects: The method of this invention, based on the operation and maintenance data of maintenance personnel and the work order description data of fault work orders, predicts the spare parts list required for each fault work order. Based on the spare parts list and the operation and maintenance data of the maintenance personnel, it obtains the personnel's pickup time and analyzes the skill matching degree between the maintenance personnel and the fault work order to obtain an initial maintenance list. It then calculates the optimal pickup point for the spare parts and obtains the commuting time of the maintenance personnel in the initial maintenance list, thereby obtaining the corresponding scheduling result for the fault work order. This application, by constructing a model, analyzes multi-dimensional data of maintenance personnel and fault work orders, and performs collaborative analysis from multiple aspects such as pickup, skill matching degree, and commuting time to achieve effective scheduling of fault work orders, solving the technical problems of untimely and mismatched scheduling in existing systems, and thus improving customer satisfaction. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 This is a schematic flowchart of the method of the present invention; Figure 2 This is a schematic diagram of the modules of the system of the present invention. Detailed Implementation

[0024] The present invention will be further described in detail below with reference to the embodiments. The following embodiments are explanations of the present invention, but the present invention is not limited to the following embodiments.

[0025] Example 1: A fault work order scheduling method based on a multidimensional data model, such as Figure 1 As shown, it includes the following steps: S100: Obtain user fault work orders and maintenance data of maintenance personnel, extract information from fault work orders to obtain work order description data; build a historical maintenance database to perform matching mining and prediction based on work order description data to obtain an initial spare parts list. S200: Optimize the initial spare parts list using maintenance data to generate a spare parts list corresponding to the fault work order. The spare parts list includes spare parts type, corresponding probability data, spare parts location and spare parts quantity. S300. Based on the spare parts list and maintenance data, obtain the spare parts retrieval time and spare parts coverage score of the maintenance personnel. Obtain the skill matching degree of the maintenance personnel for the fault work order through the historical maintenance database. Based on the spare parts retrieval time, spare parts coverage score and skill matching degree, obtain the initial maintenance list of the fault work order. S400: Using the initial maintenance list and the location data of maintenance personnel, obtain the optimal pick-up point for the spare parts required in the spare parts list. Based on the optimal pick-up point, the location data of maintenance personnel, and the location data of the fault work order, obtain the commuting time of the maintenance personnel in the initial maintenance list, and then obtain the scheduling result of the fault work order.

[0026] The method described in this application forms multidimensional data based on the operation and maintenance data of operation and maintenance personnel and the work order description data of fault work orders. Through matching mining and prediction, an initial spare parts list corresponding to the fault work order is obtained. Through spare parts optimization, a multidimensional data model is constructed to optimize operation and maintenance scheduling from multiple dimensions based on the spare parts list, operation and maintenance data, and work order description data, resulting in an initial operation and maintenance list. By obtaining the optimal pick-up point for spare parts and combining the location data of operation and maintenance personnel and the location data of fault work orders, the commuting time of the operation and maintenance personnel in the initial operation and maintenance list is obtained. Then, the scheduling result of the fault work order is obtained based on the commuting time.

[0027] S100. Obtain user fault work orders and maintenance data of maintenance personnel, and extract information from the fault work orders to obtain work order description data; construct a historical maintenance database for matching, mining, and prediction based on the work order description data to obtain an initial spare parts list; this embodiment provides a maintenance work order submission platform, through which users submit text information of encountered fault work orders. By further extracting information from the text information, the work order description data of the fault work orders is obtained, and then the initial spare parts list is obtained through matching, mining, and prediction, including the following steps: Step 1001: Extract the text information submitted by the user on the maintenance work order submission platform and perform noise reduction processing to obtain the fault text information. In this embodiment, the noise in the text information mainly refers to text content that affects the accuracy of information extraction, is irrelevant to the fault content, or is redundant, such as the user's colloquial expressions, emotional words, fault-irrelevant information, typos, and redundant modifiers. The noise reduction processing in this embodiment includes one or more of the following: text clarity, useless information filtering, normalization, and key information extraction. Step 1002: Collect historical work order description data and match it with industry standard terminology. Construct a work order dictionary through the correspondence, and perform standard conversion on the fault text information to obtain standard fault information. Then, extract the fault performance data, fault location data, and equipment type data of the fault work order through data extraction. Step 1003: Perform vector transformation on the work order dictionary and standard fault information to obtain historical work order vectors and standard fault vectors. Use the standard fault vectors to perform vector retrieval on the historical work order vectors to obtain similar work order data to the fault work orders in the historical work order description data. Step 1004: Analyze the fault performance data and combine it with similar work order data to obtain the user spare parts data of the fault work order. Combine the fault performance data, fault location data and equipment type data to form the work order description data. Step S1005: Based on the operation and maintenance data of the operation and maintenance personnel and the historical work order description data, construct a historical operation and maintenance database, in which the operation and maintenance data includes penalty cost data, spare parts related data, historical maintenance data and location data; Step S1006: In this embodiment, the prediction of spare parts is modeled as a classification problem. A pre-trained spare parts model is constructed, and the model is trained based on the historical operation and maintenance database to obtain a spare parts prediction model. The spare parts prediction model is as follows:

[0028] Step S1007: Based on the spare parts prediction model and the work order description data of the fault work order, perform spare parts prediction. Further limit the spare parts prediction results by equipment type, such as equipment model, to obtain the spare parts types and corresponding probability data corresponding to the fault work order, as shown below:

[0029] Step S1008: Extract the quantity of spare parts corresponding to the spare parts type through the user spare parts data, and form an initial spare parts list corresponding to the fault work order based on the spare parts type, the corresponding probability data and the spare parts quantity. in, Indicates the first Spare parts were used in one of the fault work orders. The probability, Indicates the first A vector formed from the work order description data of each fault work order. , Indicates spare parts The corresponding model parameters, Indicates the first Did the fault work order use spare parts? , This indicates that spare parts were used in the fault work order. The probability, A vector representing the work order description data of a fault work order. Indicates the first One spare part, Indicates the quantity of spare parts. It represents probability.

[0030] S200. Optimize the initial spare parts list using maintenance data to generate a spare parts list corresponding to the fault work order. The spare parts list includes spare parts type, corresponding probability data, spare parts location, and spare parts quantity. Since maintenance personnel may not have the required parts with them if the fault work order is not carried, it will lead to a second on-site visit and decreased customer satisfaction. Furthermore, the cost of carrying spare parts must be considered. Therefore, this embodiment constructs a spare parts optimization function to optimize the initial spare parts list obtained in step S100, including the following steps: Step S2001: Obtain the penalty cost data from the maintenance data of the maintenance personnel. The penalty cost data is used to represent the penalty cost if a fault work order actually requires a certain part, but the maintenance personnel do not carry the part. Spare part related data includes the carrying cost of a certain part for the maintenance personnel, the space capacity data of the spare parts, and the total volume of spare parts carried by the maintenance personnel. Step S2002: Construct a spare parts optimization function. Based on penalty cost data and spare parts related data, combined with the spare parts types and corresponding probability data in the initial spare parts list, optimize the initial spare parts list. The spare parts optimization function is as follows:

[0031] Step S2003: Based on the results of spare parts optimization, select spare parts from the types of spare parts and their corresponding probability data in the initial spare parts list to obtain the spare parts list corresponding to the fault work order. in, This indicates that maintenance personnel carry spare parts. The cost of carrying Indicate whether maintenance personnel carry spare parts. , This indicates that the maintenance personnel did not bring spare parts. Data on the cost of punishment, This indicates that spare parts were used in the fault work order. The probability, Indicates spare parts Spatial capacity data, This indicates the total capacity of the maintenance personnel. This indicates the available inventory for current maintenance personnel. Indicates the quantity of spare parts.

[0032] S300. Based on the spare parts list and maintenance data, obtain the spare parts retrieval time and spare parts coverage score of the maintenance personnel. Obtain the skill matching degree of the maintenance personnel for the fault work orders through the historical maintenance database. Based on the spare parts retrieval time, spare parts coverage score, and skill matching degree, obtain the initial maintenance list of fault work orders. To conduct multi-dimensional analysis of maintenance work orders, this embodiment considers both the spare parts retrieval time and the maintenance personnel's familiarity with the fault work orders. Through comprehensive consideration of multiple aspects, the initial maintenance list of fault work orders is formed, including the following steps: Step S3001: Obtain the corresponding spare part location data through the spare part types in the spare parts list. In order to ensure the scheduling and processing time of the work order, the operation and maintenance area range is set in this embodiment. According to the spare part location data and the location data of the operation and maintenance personnel, the retrieval distance time of all operation and maintenance personnel within the operation and maintenance area is obtained. The interval distance time represents the time required for the operation and maintenance personnel to travel from the current location to the spare part location. Step S3002: Determine if the maintenance personnel currently have a task. If so, calculate the spare part retrieval time based on the current task's completion time, interval distance time, and retrieval operation time. The retrieval operation time represents the time required for the maintenance personnel to arrive at the spare part and leave after retrieval. The spare part retrieval time is:

[0033] Step 3003: Based on the spare parts-related data and spare parts list of the maintenance personnel, and combined with the spare parts retrieval time of the maintenance personnel, evaluate the current spare parts coverage of the maintenance personnel to obtain a spare parts coverage score. The spare parts coverage score is used to measure the ease with which the maintenance personnel obtain the spare parts from the spare parts list. The spare parts-related data represents the spare parts already carried by the maintenance personnel. The spare parts coverage score is:

[0034] Step 3004: To better serve users, in this embodiment, to assign more suitable maintenance personnel to fault work orders as much as possible, the skill matching degree of the maintenance personnel for the current fault is calculated based on the maintenance personnel's historical maintenance data and the fault performance data of the fault work orders. The skill matching degree is:

[0035] Step 3005: In order to conduct a comprehensive analysis of maintenance personnel, the spare parts retrieval time, spare parts coverage score and skill matching degree are normalized respectively. Based on the normalized spare parts retrieval time, spare parts coverage score and skill matching degree, the corresponding comprehensive score of the current maintenance personnel is obtained. In this embodiment, the comprehensive score is sorted to obtain the initial maintenance list of fault work orders. in, Indicates maintenance personnel For spare parts Spare parts pickup time, Indicates spare parts Pickup distance time, Indicates spare parts The pickup operation time, Indicates maintenance personnel The end time of the current task. Indicates maintenance personnel Spare parts coverage score Indicates maintenance personnel Carry spare parts Quantity, Indicate the required spare parts Quantity, Indicates the quantity of different types of spare parts. Indicates spare parts The number of inventory points, Indicates inventory point Medium spare parts Available quantity, This represents the time decay coefficient, and its value is determined based on the urgency level of the maintenance personnel. Indicates maintenance personnel Head to inventory point Spare parts pickup time, Indicates skill matching degree. Indicates maintenance personnel Successfully handled the fault Number of times, Indicates maintenance personnel Troubleshooting Total number of times Indicates the matching weight. Indicates maintenance personnel Skill rating.

[0036] S400. Using the initial maintenance list and the location data of maintenance personnel, obtain the optimal pickup point for the spare parts required in the spare parts list. Based on the optimal pickup point, the location data of maintenance personnel, and the location data of the fault work order, obtain the commuting time of the maintenance personnel in the initial maintenance list, and then obtain the scheduling result of the fault work order. In this embodiment, assign the optimal pickup point of the spare parts in the spare parts list to each maintenance personnel in the initial maintenance list, and then calculate the commuting time required for each maintenance personnel to reach the location of the fault work order. Further selection is made based on the commuting time to obtain the scheduling result of the fault work order, including the following steps: S4001: Obtain the inventory location of all required spare parts in the spare parts list. Based on the location information of maintenance personnel, the inventory location of required spare parts, and the fault location data of fault work orders, calculate the optimal retrieval point for the required spare parts. The optimal retrieval point is defined as follows:

[0037] Step S4002: Based on the optimal pick-up point, spare parts list, location data of maintenance personnel, and fault location data, obtain the commute time for all maintenance personnel in the initial maintenance list to reach the fault location. The commute time is represented as follows:

[0038] Step S4003: Sort the commuting times of the maintenance personnel in the initial maintenance list, assign fault work orders to the maintenance personnel according to the sorting results, and obtain the scheduling results of the fault work orders; in, Indicates spare parts The best pickup point Indicates the location of maintenance personnel and the pickup point. The distance between them Indicates the pickup point Distance from the fault location This indicates the distance between the location of the maintenance personnel and the location of the fault. Indicates spare parts The number of inventory points, Indicates maintenance personnel Commuting time, This indicates the time between the location of the maintenance personnel and the optimal pick-up point for the first spare part. Indicates spare parts Spare parts The time between the best pickup points Indicates spare parts The time between the optimal pickup point and the location of the fault.

[0039] In this embodiment, the commuting time required by maintenance personnel is sorted, and maintenance personnel with shorter commuting time are selected to handle the fault work order based on the sorting results, thus completing the scheduling of the fault work order.

[0040] Example 2: A fault work order scheduling system based on a multidimensional data model, such as Figure 2 As shown, it includes: The spare parts prediction module 100 acquires the user's fault work orders and the operation and maintenance data of the operation and maintenance personnel, extracts information from the fault work orders to obtain work order description data, and builds a historical operation and maintenance database to perform matching mining and prediction in combination with the work order description data to obtain an initial spare parts list. The spare parts optimization module 200 optimizes the initial spare parts list using operation and maintenance data, and generates a spare parts list corresponding to the fault work order. The spare parts list includes spare parts type, corresponding probability data, spare parts location and spare parts quantity. The maintenance matching module 300 obtains the spare parts retrieval time and spare parts coverage score of maintenance personnel based on the spare parts list and maintenance data. It also obtains the skill matching degree of maintenance personnel for fault work orders through the historical maintenance database. Based on the spare parts retrieval time, spare parts coverage score and skill matching degree, it obtains the initial maintenance list of fault work orders. The work order scheduling module 400 obtains the optimal pick-up point for the required spare parts in the spare parts list through the initial maintenance list and the location data of maintenance personnel. Based on the optimal pick-up point, the location data of maintenance personnel, and the location data of the fault work order, it obtains the commuting time of maintenance personnel in the initial maintenance list, and then obtains the scheduling result of the fault work order.

[0041] Various changes and modifications made without departing from the spirit and scope of this invention, and all equivalent technical solutions, also fall within the scope of this invention.

[0042] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0043] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, apparatus, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0044] This invention is described with reference to flowchart illustrations and / or block diagrams of the method, terminal device (system), and computer program product according to the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0045] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing terminal device to operate in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0046] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal equipment, causing a series of operational steps to be performed on the computer or other programmable terminal equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable terminal equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0047] It should be noted that: The phrase "an embodiment" or "an embodiment" used in this specification means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the invention. Therefore, the phrase "an embodiment" or "an embodiment" appearing in various places throughout the specification does not necessarily refer to the same embodiment.

[0048] Furthermore, it should be noted that the shapes and names of the parts and components described in the specific embodiments described in this specification may differ. All equivalent or simple variations made to the structure, features, and principles described in this patent concept are included within the protection scope of this patent. Those skilled in the art to which this invention pertains may make various modifications or additions to the described specific embodiments or use similar methods to replace them, as long as they do not depart from the structure of this invention or exceed the scope defined in these claims, they should all fall within the protection scope of this invention.

Claims

1. A fault work order scheduling method based on a multidimensional data model, characterized in that, Includes the following steps: Obtain user fault work orders and maintenance data of maintenance personnel, extract information from fault work orders to obtain work order description data; build a historical maintenance database to perform matching, mining and prediction based on work order description data to obtain an initial spare parts list. The initial spare parts list is optimized by using operation and maintenance data to generate a spare parts list corresponding to the fault work order. The spare parts list includes spare parts type, corresponding probability data, spare parts location and spare parts quantity. Based on the spare parts list and maintenance data, the spare parts retrieval time and spare parts coverage score of maintenance personnel are obtained. The skill matching degree of maintenance personnel for fault work orders is obtained through the historical maintenance database. Based on the spare parts retrieval time, spare parts coverage score and skill matching degree, the initial maintenance list of fault work orders is obtained. By using the initial maintenance list and the location data of maintenance personnel, the optimal pick-up point for the required spare parts in the spare parts list is obtained. Based on the optimal pick-up point, the location data of maintenance personnel, and the location data of fault work orders, the commuting time of maintenance personnel in the initial maintenance list is obtained, and then the scheduling result of the fault work orders is obtained.

2. The fault work order scheduling method based on a multi-dimensional data model according to claim 1, characterized in that, The process of extracting information from fault work orders to obtain work order description data includes the following steps: Extract the text information from the fault work order and perform noise reduction processing to obtain the fault text information; Based on historical work order description data, a work order dictionary is constructed. Based on the work order dictionary, the fault text information is standardized and converted to obtain standard fault information. Through information extraction, the fault performance data, fault location data, and equipment type data of the fault work order are obtained. Vector transformation is performed based on the work order dictionary and standard fault information to obtain historical work order vectors and standard fault vectors. Then, similar work order data of faulty work orders are obtained through vector retrieval. By analyzing fault performance data and similar work order data, user spare parts data for faulty work orders are obtained. Combined with fault performance data, fault location data, and equipment type data, work order description data is generated.

3. The fault work order scheduling method based on a multi-dimensional data model according to claim 1, characterized in that, The construction of the historical operation and maintenance database, used to perform matching, mining, and prediction based on work order description data, to obtain an initial spare parts list, includes the following steps: Based on the maintenance data of maintenance personnel and historical work order description data, a historical maintenance database is constructed. The maintenance data includes penalty cost data, spare parts related data, historical maintenance data, and location data. A spare parts pre-training model is constructed, and the model is trained based on a historical operation and maintenance database to obtain a spare parts prediction model; the spare parts prediction model is as follows: Based on the spare parts prediction model and the work order description data of the fault work orders, spare parts prediction is performed. By combining the spare parts prediction results with equipment type data, the spare parts types corresponding to the fault work orders and their corresponding probability data are obtained. By extracting the quantity of spare parts corresponding to the spare parts type from the user spare parts data, and forming an initial spare parts list corresponding to the fault work order based on the spare parts type, the corresponding probability data and the spare parts quantity. in, Indicates the first Spare parts were used in one of the fault work orders. The probability, Indicates the first A vector formed from the work order description data of each fault work order. , Indicates spare parts The corresponding model parameters, Indicates the first Did the fault work order use spare parts? , Indicates the first One spare part, It represents probability.

4. The fault work order scheduling method based on a multi-dimensional data model according to claim 1, characterized in that, The process of optimizing the initial spare parts list using maintenance data to generate a spare parts list corresponding to the fault work order includes the following steps: Based on the penalty cost data and spare parts related data in the operation and maintenance data, and combined with the spare parts types and corresponding probability data in the initial spare parts list, a spare parts optimization function is constructed to optimize the spare parts types in the initial spare parts list corresponding to the fault work order. The spare parts optimization function is as follows: Based on the results of spare parts optimization and the types of spare parts and corresponding probability data in the initial spare parts list, spare parts are selected to obtain the spare parts list corresponding to the fault work order. in, This indicates that maintenance personnel carry spare parts. The cost of carrying Indicate whether maintenance personnel carry spare parts. , This indicates that the maintenance personnel did not bring spare parts. Data on the cost of punishment, This indicates that spare parts were used in the fault work order. The probability, Indicates spare parts Spatial capacity data, This indicates the total capacity of the maintenance personnel. This indicates that maintenance personnel are concerned about spare parts. Available inventory Indicates the quantity of spare parts.

5. The fault work order scheduling method based on a multidimensional data model according to claim 1, characterized in that, The initial maintenance list is obtained through the following steps: The spare parts list is used to obtain the types of spare parts required for the fault work order and the corresponding spare parts location data. The operation and maintenance area is set. Based on the spare parts location data and the location data of the operation and maintenance personnel, the retrieval distance and time of all operation and maintenance personnel within the operation and maintenance area are obtained. Combined with the current task and interval operation time of the operation and maintenance personnel, the spare parts retrieval time is obtained. Based on the spare parts data and spare parts list of the maintenance personnel, and combined with the spare parts retrieval time of the maintenance personnel, the current spare parts coverage of the maintenance personnel is evaluated to obtain a spare parts coverage score. Based on the historical maintenance data and fault performance data of the maintenance personnel and fault work orders, the skill matching degree of the maintenance personnel for the current fault is calculated. The spare parts retrieval time, spare parts coverage score, and skill matching degree are normalized respectively. Based on the normalized spare parts retrieval time, spare parts coverage score, and skill matching degree, the corresponding comprehensive score of the current maintenance personnel is obtained. The initial maintenance list of fault work orders is obtained by sorting the comprehensive scores.

6. The fault work order scheduling method based on a multidimensional data model according to claim 1, characterized in that, The spare parts coverage score is: The skill matching degree is: in, Indicates maintenance personnel Spare parts coverage score Indicates maintenance personnel Carry spare parts Quantity, Indicate the required spare parts Quantity, Indicates the quantity of different types of spare parts. Indicates spare parts The number of inventory points, Indicates inventory point Medium spare parts Available quantity, This represents the time decay coefficient, and its value is determined based on the urgency level of the maintenance personnel. Indicates maintenance personnel Head to inventory point Spare parts pickup time, Indicates skill matching degree. Indicates maintenance personnel Successfully handled the fault Number of times, Indicates maintenance personnel Troubleshooting Total number of times Indicates the matching weight. Indicates maintenance personnel Skill rating.

7. The fault work order scheduling method based on a multidimensional data model according to claim 1, characterized in that, The scheduling result of the fault work order is obtained through the following steps: Obtain the inventory location of the required spare parts from the spare parts list. Based on the location information of the maintenance personnel, the inventory location of the required spare parts, and the fault location data, calculate the optimal retrieval point for the required spare parts. The optimal retrieval point is defined as follows: Based on the optimal pickup point, spare parts list, location data of maintenance personnel, and fault location data, the commute time of maintenance personnel in the initial maintenance list to the current fault location is obtained. The commuting times of the maintenance personnel in the initial maintenance list are sorted, and fault work orders are assigned according to the sorting results to obtain the scheduling results of the fault work orders. in, Indicates spare parts The best pickup point Indicates the location of maintenance personnel and the pickup point. The distance between them Indicates the pickup point Distance from the fault location This indicates the distance between the location of the maintenance personnel and the location of the fault. Indicates spare parts The number of inventory points.

8. A fault work order scheduling system based on a multidimensional data model, characterized in that, include: The spare parts prediction module obtains user fault work orders and maintenance data from maintenance personnel, extracts information from fault work orders to obtain work order description data, and builds a historical maintenance database to perform matching, mining, and prediction based on the work order description data to obtain an initial spare parts list. The spare parts optimization module optimizes the initial spare parts list using operation and maintenance data, and generates a spare parts list corresponding to the fault work order. The spare parts list includes spare parts type, corresponding probability data, spare parts location and spare parts quantity. The maintenance matching module obtains the spare parts retrieval time and spare parts coverage score of maintenance personnel based on the spare parts list and maintenance data. It also obtains the skill matching degree of maintenance personnel for fault work orders through the historical maintenance database. Based on the spare parts retrieval time, spare parts coverage score and skill matching degree, it obtains the initial maintenance list of fault work orders. The work order scheduling module obtains the optimal pickup point for the required spare parts from the spare parts list by using the initial maintenance list and the location data of maintenance personnel. Based on the optimal pickup point, the location data of maintenance personnel, and the location data of the fault work order, it obtains the commuting time of maintenance personnel in the initial maintenance list, and then obtains the scheduling result of the fault work order.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1 to 7.

10. A fault work order scheduling device based on a multidimensional data model, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the method as described in any one of claims 1 to 7.

Images