An intelligent work order scheduling method, system, device and medium based on Xinchuang technology

Abstract

The application relates to the technical field of intelligent work order scheduling, and discloses an intelligent work order scheduling method, system, device and medium based on Xinchuang technology, which comprises the following steps: obtaining a target field equipment fault work order and a preset maintenance personnel first capability parameter for the target field; performing a second analysis operation on the target field equipment fault work order to obtain a second work order parameter; performing a third matching operation on the first capability parameter and the second work order parameter; performing work order scheduling according to the matching result of the third matching operation; obtaining the first capability parameter of the preset maintenance personnel through the first analysis operation, realizing accurate scheduling, matching according to the actual capability of the maintenance personnel, and avoiding maintenance delay or failure. The second analysis operation deeply analyzes the target field equipment fault work order to obtain the second work order parameter, thereby providing data support for subsequent matching. The third matching operation adopts a priority and ordinary matching strategy, flexibly selects according to the second work order parameter, and improves scheduling accuracy and efficiency.

Description

Technical Field

[0001] The present invention relates to the field of intelligent work order scheduling technology, and in particular to an intelligent work order scheduling method, system, equipment and medium based on information technology. Background Art

[0002] In the current field of equipment maintenance and troubleshooting, traditional work order scheduling methods rely primarily on manual experience. This approach is not only inefficient but also fails to ensure the optimal match between maintenance personnel and troubleshooting work orders. This is especially true in large enterprises or complex network environments, where faced with a large number and diverse range of equipment troubleshooting work orders, traditional methods expose further limitations: an inability to quickly respond to urgent work orders, uneven allocation of maintenance resources, and a mismatch between maintenance personnel's skills and the type of fault. These issues extend equipment maintenance cycles, increase enterprise operating costs, and potentially impact service quality.

[0003] Furthermore, while some highly automated work order management systems have emerged with the development of information technology, most lack the ability to deeply analyze maintenance personnel's capabilities and fault work order characteristics, preventing accurate matching and thus limiting their potential for improving work efficiency. In the field of xinchuang (innovation in information technology applications), leveraging advanced information technology to address these issues and achieve intelligent work order scheduling and management has become a key issue that needs to be addressed. Summary of the Invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides an intelligent work order scheduling method, system, equipment and medium based on the information technology, which can solve the problems of low efficiency and poor matching in traditional work order scheduling methods, and realize intelligent work order management and scheduling.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, the present invention provides an intelligent work order scheduling method based on ICT technology, comprising:

[0008] Obtain equipment failure work orders in the target area and the first capability parameters of preset maintenance personnel for the target area;

[0009] The first capability parameter of the preset maintenance personnel in the target field is obtained through a first analysis operation;

[0010] Performing a second analysis operation on the target field equipment failure work order to obtain second work order parameters;

[0011] performing a third matching operation on the first capability parameter and the second work order parameter;

[0012] Performing work order scheduling according to the matching result of the third matching operation;

[0013] The third matching operation includes a priority matching strategy and a normal matching strategy;

[0014] The matching strategy selection of the third matching operation is performed according to the second work order parameters.

[0015] As a preferred solution of the intelligent work order scheduling method based on the information technology of the present invention, the first analysis operation includes:

[0016] Obtaining the coordinate range of the target area and the relevant parameters of the preset maintenance personnel within the coordinate range;

[0017] The preset maintenance personnel related parameters include the maintenance personnel's remaining work order quantity, remaining work order processing time, skill level, expertise coefficient, historical work order records, maintenance personnel's location coordinates and service evaluation level;

[0018] A first capability parameter of the preset maintenance personnel is determined according to the preset maintenance personnel related parameters.

[0019] As a preferred solution of the intelligent work order scheduling method based on the information technology of the present invention, the second analysis operation includes:

[0020] Extract fault work order features from equipment fault work orders in the target field;

[0021] The fault work order features include fault features and work order features;

[0022] The fault characteristics include fault location, fault time, fault type and fault level;

[0023] The work order characteristics include the urgency of the work order and the maintenance resources required for the work order;

[0024] Establish second work order parameters based on fault work order characteristics.

[0025] As a preferred solution of the intelligent work order scheduling method based on the ICT technology described in the present invention, the matching strategy selection of the third matching operation is performed according to the second work order parameters, including:

[0026] The urgency of the work order includes the expedited level and the normal level;

[0027] If the urgency of the work order in the work order characteristics is expedited, the priority matching strategy is selected;

[0028] If the work order urgency in the work order characteristics is normal, the normal matching strategy is selected.

[0029] As a preferred solution of the intelligent work order scheduling method based on the information creation technology described in the present invention, the priority matching strategy includes:

[0030] Determining an urgency priority, wherein the urgency priority includes several different priorities;

[0031] Selecting a maintenance personnel with the highest skill level, the most matching expertise coefficient, and the shortest estimated arrival time based on the first capability parameter and the second work order parameter;

[0032] Dispatching work orders that meet the urgency level to the corresponding maintenance personnel, and determining whether there are any urgency-level work orders among the maintenance personnel's remaining work orders;

[0033] If it does not exist, the newly assigned expedited work order will be the one with the highest expedited priority;

[0034] If so, the priority of the newly assigned urgent work order will be compared with the urgent work orders in the remaining work orders of the maintenance personnel, and the pending work orders will be reordered according to the priority.

[0035] As a preferred solution of the intelligent work order scheduling method based on the ICT technology described in the present invention, wherein: the general matching strategy includes several layers of matching mechanisms;

[0036] Each matching mechanism in the plurality of matching mechanisms performs a matching operation on the first capability parameter and the second work order parameter;

[0037] Performing a matching operation on the first capability parameter and the second work order parameter based on the multiple layers of matching mechanisms in a preset order;

[0038] Work orders are distributed according to the matching operation results. Work orders of the common matching strategy are distributed in sequence.

[0039] As a preferred solution of the intelligent work order scheduling method based on the information technology described in the present invention, the several layers of matching mechanism include:

[0040] Remaining work order quantity matching mechanism, remaining work order processing time matching mechanism, skill level matching mechanism, expertise coefficient matching mechanism, historical work order record matching mechanism and service evaluation level matching mechanism.

[0041] In a second aspect, the present invention provides an intelligent work order scheduling system based on ICT technology, comprising:

[0042] A data acquisition module, used to obtain equipment failure work orders in the target field and the first capability parameters of preset maintenance personnel for the target field;

[0043] The first capability parameter of the preset maintenance personnel in the target field is obtained through a first analysis operation;

[0044] An analysis module, configured to perform a second analysis operation on the target field equipment failure work order to obtain second work order parameters;

[0045] a matching module, configured to perform a third matching operation on the first capability parameter and the second work order parameter;

[0046] A scheduling module, configured to schedule work orders according to the matching result of the third matching operation;

[0047] The third matching operation includes a priority matching strategy and a normal matching strategy;

[0048] The matching strategy selection of the third matching operation is performed according to the second work order parameters.

[0049] In a third aspect, the present invention provides an electronic device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the method described above when executing the computer program.

[0050] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of the method described above when the computer program is executed by a processor.

[0051] Compared with the existing technology, the present invention has the following beneficial effects: the present invention proposes an intelligent work order scheduling method based on ICT technology, which obtains work orders for equipment failures in a target domain and first capability parameters of preset maintenance personnel for the target domain; performs a second analysis operation on the work orders for equipment failures in the target domain to obtain second work order parameters; performs a third matching operation on the first capability parameters and the second work order parameters; and schedules the work orders based on the matching results of the third matching operation. First, by combining ICT technology, the present invention implements intelligent work order scheduling, improves maintenance efficiency, and reduces the subjectivity and uncertainty of manual scheduling. Second, by obtaining the first capability parameters of preset maintenance personnel through the first analysis operation, scheduling is more accurate and can be matched according to the actual capabilities of maintenance personnel, avoiding maintenance delays or failures caused by insufficient maintenance personnel capabilities. Furthermore, the second analysis operation conducts an in-depth analysis of the work orders for equipment failures in the target domain to obtain second work order parameters, providing detailed data support for subsequent matching operations. Finally, the third matching operation adopts a priority matching strategy and a normal matching strategy, flexibly selecting a matching strategy based on the second work order parameters, further improving the accuracy and efficiency of scheduling. In summary, the present invention has significant beneficial effects in intelligent work order scheduling. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0053] Figure 1 A method flow chart of an intelligent work order scheduling method based on trusted computing technology is provided for one embodiment of the present invention.

[0054] Figure 2 A schematic diagram of the structure of an integrated work order feature extraction model for an intelligent work order scheduling method based on trusted computing technology is provided as an embodiment of the present invention.

[0055] Figure 3 A general matching strategy matching flowchart of an intelligent work order scheduling method based on trusted computing technology is provided as an embodiment of the present invention.

[0056] Figure 4 An internal structure diagram of an electronic device for an intelligent work order scheduling method based on trusted computing technology provided as an embodiment of the present invention. DETAILED DESCRIPTION

[0057] To make the above-mentioned objects, features, and advantages of the present invention more clearly understood, the following detailed description of the specific embodiments of the present invention is given in conjunction with the accompanying drawings. It is obvious that the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in this field without creative work should fall within the scope of protection of the present invention.

[0058] Example 1, with reference to Figures 1 to 3 , which is the first embodiment of the present invention, provides an intelligent work order scheduling method based on Xinchuang technology, including:

[0059] Existing technologies present several challenges. For example, traditional work order scheduling methods often fail to respond to urgent work orders promptly, resulting in delays in resolving equipment failures and impacting production efficiency and service quality. Furthermore, the matching of maintenance personnel with fault work orders is not precise enough, which can lead to poor maintenance results due to insufficient maintenance personnel skills or uneven resource allocation.

[0060] The present invention provides a method that can effectively solve the above-mentioned problems. Next, we will combine multiple embodiments to explain in detail how to implement the intelligent work order scheduling method based on the information creation technology.

[0061] Figure 1 A flowchart of a method for intelligent work order scheduling based on Xinchuang technology is shown, including:

[0062] S101, obtaining a target field equipment failure work order and a first capability parameter of a preset maintenance personnel for the target field;

[0063] It's important to note that traditional work order scheduling often relies on manual judgment, which is not only inefficient but also difficult to optimally match maintenance personnel with troubleshooting work orders. Some automated work order scheduling systems exist, but most lack in-depth analysis of maintenance personnel's capabilities and troubleshooting work order characteristics, resulting in poor matching. This results in blindly implementing simple scheduling methods, often with unsatisfactory results.

[0064] It should also be noted that in today's highly developed information technology society, especially in the field of ICT (information technology application innovation), the demand for intelligence and automation is increasing. Traditional work order scheduling methods can no longer meet this demand. Therefore, this paper proposes an intelligent work order scheduling method based on ICT technology. This method aims to achieve precise matching through in-depth analysis of maintenance personnel's capability parameters and fault work order characteristics, thereby improving maintenance efficiency and service quality.

[0065] In some specific embodiments, by mapping the specific content of the work order to assign maintenance personnel, it is easy to cause some maintenance personnel to have too many or too few work orders, which cannot maximize the use of resources and affects the user experience. Therefore, after obtaining the target field device fault work order, the present application does not directly assign, but further obtains and analyzes the first ability parameter of the preset maintenance personnel in the target field.

[0066] It should be noted that in order to deal with the signal creation technology field, most of the information needs to be digitized, so as to realize real data processing and use it as a real technical means. Therefore, the first ability parameter obtained by the present application is used as a technical means for digitizing the ability of maintenance personnel.

[0067] In some specific embodiments, the first ability parameter can be evaluated by using historical maintenance data, skill certification level, professional training record, and past user evaluation and other multi-dimensional information. The acquisition and analysis of these information helps the system to more comprehensively understand the actual ability and expertise of each maintenance personnel, thereby providing more accurate data basis for subsequent matching operation. For example, historical maintenance data can reflect the experience and efficiency of the maintenance personnel in handling similar faults; skill certification level directly reflects the professional skill level of the maintenance personnel; professional training record shows whether the maintenance personnel has received the latest technology and knowledge training in the relevant field; and past user evaluation can reflect the service attitude and quality of the maintenance personnel from the user's perspective. By comprehensively considering these factors, the system can more accurately evaluate the first ability parameter of the maintenance personnel, and provide strong support for subsequent intelligent work order scheduling.

[0068] However, some of the above multi-dimensional information cannot truly display the first ability parameter, for example, when it is determined that a work order can be handled by A or B maintenance personnel, it is not possible to determine the specific personnel according to historical maintenance data, skill certification level, professional training record, and past user evaluation. In actual application process, this situation often occurs, and in this case, the maintenance personnel cannot be dispatched randomly according to the strategy in the prior art. Therefore, how to specifically determine the maintenance personnel according to the work order information is one of the problems solved by the present application.

[0069] In the embodiment of the present application, the first ability parameter of the preset maintenance personnel in the target field is obtained by a first analysis operation;

[0070] It should be noted that the first analysis operation here is to analyze the most suitable maintenance personnel for dispatch based on some existing parameters. The first analysis operation here can use machine learning algorithms, such as decision trees, random forests, or neural networks, to conduct in-depth analysis and modeling of the maintenance personnel's first ability parameters. These algorithms can extract key features from multi-dimensional information such as historical maintenance data, skill certification levels, professional training records, and past user reviews, and automatically learn the best matching rules between maintenance personnel and fault work orders. By training and optimizing these algorithms, the system can more accurately predict which maintenance personnel is most suitable for handling a specific fault work order, thereby improving the accuracy and efficiency of scheduling.

[0071] However, the modeling method places too high demands on the computing server, and without sufficient training samples, the established model is difficult to meet actual needs. Therefore, the present invention designs a new capability matrix expression strategy to display the first capability parameter through the capability matrix and lay the foundation for subsequent technical solutions.

[0072] In an embodiment of the present invention, the first analysis operation includes:

[0073] Obtaining the coordinate range of the target area and the relevant parameters of the preset maintenance personnel within the coordinate range;

[0074] The preset maintenance personnel-related parameters include the maintenance personnel's remaining work order quantity, remaining work order processing time, skill level, expertise coefficient, historical work order records, maintenance personnel's location coordinates, and service evaluation level;

[0075] The first capability parameter of the preset maintenance personnel is determined according to the relevant parameters of the preset maintenance personnel.

[0076] It should be noted that the coordinate range of the target area can be obtained by establishing a rectangular coordinate system. The present invention does not limit the specific location of the establishment of the coordinate system. Generally, any rectangular coordinate system that includes any position of the target area can be used.

[0077] Specifically, the specific steps of displaying the first capability parameter through the capability matrix may be as follows:

[0078] Quantify the parameters related to the preset maintenance personnel (excluding the coordinates of the maintenance personnel's location) one by one;

[0079] Arrange the quantified results of the preset maintenance personnel related parameters after quantification one by one in a fixed order;

[0080] Matrix the arranged quantization results;

[0081] Record the fixed order and matrix results, and use the matrix results as the capability matrix.

[0082] In some specific embodiments, the criteria for quantification are as follows:

[0083] The quantification standard for the remaining work orders is as follows: the work order quantity is expressed as a number, and the value range of the work order quantity is [0, 2*Gvd]. The larger the number, the more work orders there are. Gvd represents the ratio of the total work order quantity in the target area to the preset maintenance personnel in the target area, rounded to the nearest integer.

[0084] The quantitative standard for the remaining work order processing time is as follows: the processing time is expressed as a number, and the value range of the processing time is [0, the number of remaining work orders * Tmax]. The larger the number, the longer the remaining work order processing time. Tmax represents the maximum average time required for maintenance personnel to process a single work order in the target area, in minutes.

[0085] The quantitative standard for skill level is: divided according to the skill certification level, such as elementary, intermediate, advanced, etc., and assigned different numerical values. The larger the numerical value, the higher the skill level. In this invention, the skill certification level is divided into level one, level two, and level three, and the level one corresponds to a numerical value of 3, the level two corresponds to a numerical value of 2, and the level three corresponds to a numerical value of 1;

[0086] The quantitative standard for the expertise coefficient is as follows: a value is assigned based on the repair success rate of the maintenance personnel for a certain type of fault or equipment, and an expertise coefficient judgment threshold is set. If the assigned value of the repair success rate of the maintenance personnel for a certain type of fault or equipment is not greater than the expertise coefficient judgment threshold, it is marked as zero;

[0087] If the assigned value of the maintenance personnel's repair success rate for a certain type of fault or equipment is greater than the expertise coefficient judgment threshold, the assigned values ​​that meet the conditions are sorted by size and assigned values ​​from one to infinity in order of size. The larger the value, the stronger the expertise in that field.

[0088] The quantitative standard for historical work order records is to conduct a comprehensive evaluation based on indicators such as the maintenance personnel's historical success rate in handling work orders and average processing time, and assign corresponding values;

[0089] The quantitative standard for service evaluation levels is to categorize maintenance personnel's service ratings based on past user reviews, such as very satisfied, satisfied, average, and dissatisfied, and assign different numerical values ​​to each rating. A larger numerical value indicates a higher service rating. In this invention, the service evaluation levels include very satisfied, satisfied, average, and dissatisfied, and very satisfied, satisfied, average, and dissatisfied are assigned values ​​of 3, 2, 1, and 0, respectively.

[0090] For example, assume that the relevant parameters of a maintenance person are as follows:

[0091] Remaining work orders: 5;

[0092] Remaining ticket processing time: 120 minutes (based on an average ticket processing time of 30 minutes);

[0093] Skill level: Level 2 (corresponding value 2);

[0094] Expertise coefficient: For a certain type of fault, the success rate is 85%. The expertise coefficient threshold is set to 80%. Therefore, the maintenance worker's expertise coefficient for this fault type is assigned a value of 1 (assuming this is his only area of ​​expertise).

[0095] Historical work order records: success rate 90%, average processing time 30 minutes, comprehensive evaluation value 4;

[0096] Service evaluation level: Very satisfied (assigned value 3);

[0097] Furthermore, it is necessary to quantify the above-mentioned related parameters one by one. The quantification results are as follows:

[0098] Remaining work orders: 5;

[0099] Remaining work order processing time: 120;

[0100] Skill level: 2;

[0101] Expertise coefficient: For this particular fault type, the expertise coefficient is 1;

[0102] The expertise coefficients of other types are 0 (assuming there is only one area of ​​expertise), so the expertise coefficients can be represented as a vertical matrix [1;0;...;0], the specific length of which depends on the number of fault types considered.

[0103] Historical work order records: 4;

[0104] Service rating: 3;

[0105] Furthermore, a fixed order is determined to arrange these quantified results, such as: remaining work order volume, remaining work order processing time, skill level, expertise coefficient (as a separate vertical matrix), historical work order records, and service evaluation level.

[0106] Furthermore, these quantization results are converted into matrix form. Since the expertise coefficient is a vertical matrix, it can be treated as a column vector of the matrix, while other parameters are expanded row by row.

[0107] Assuming that only one type of fault is considered, the expertise coefficient is a simple 1 × 1 matrix. Ability moment = [5120 2 1 4 3];

[0108] If multiple fault types are considered, for example, there are three different fault types, and the expertise coefficients of the three fault types are: 85%, 90%, and 60% respectively. The expertise coefficient judgment threshold is set to 80%, so the corresponding expertise coefficients are 1, 2, and 0 respectively. The capability matrix becomes:

[0109]

[0110] The rows of the matrix represent the fault type, and the columns of the matrix represent the five parameters: remaining work order quantity, remaining work order processing time, skill level, expertise coefficient (as a separate vertical matrix), historical work order records, and service evaluation level.

[0111] In some specific implementations, the fixed order can be designed according to actual needs, and the arrangement in the front position of the matrix can be used as a key parameter, which is not limited in the present invention.

[0112] It should be noted that the fixed order within the current cycle is unchanged, and all subsequent related operations generated for this fixed order within the same cycle must be consistent with this fixed order. For example, the first capability parameters of different maintenance personnel in the same cycle are always represented by the capability matrix of the same type and the same fixed order.

[0113] It should be noted that the coordinates of the maintenance personnel's location play a role when the second work order parameters are subsequently obtained.

[0114] It's also important to note that obtaining work orders for equipment failures in the target area and the preset primary capability parameters of maintenance personnel for that area provide a critical data foundation for subsequent intelligent matching. By accurately capturing the specific content of the work orders and the actual capability parameters of maintenance personnel, we can more accurately understand the matching relationship between maintenance needs and personnel capabilities, thus providing strong support for intelligent scheduling decisions. Furthermore, acquiring this data helps optimize the entire work order processing process, improving maintenance efficiency and service quality, and reducing resource waste and time delays caused by improper matching.

[0115] S102, performing a second analysis operation on the target field equipment failure work order to obtain second work order parameters;

[0116] It should be noted that, based on the determination of the first capability parameter of the maintenance personnel, the fault work orders that occur are obtained in real time, and the most appropriate maintenance personnel are dispatched according to the specific content of the fault work orders.

[0117] It should be noted that after a fault work order is generated, it is necessary to obtain the main information therein, so it is necessary to perform feature extraction on the fault work order. Therefore, the present invention designs a second analysis operation for extracting features from the fault work order and mapping the feature to the previous capability matrix.

[0118] In an embodiment of the present invention, the second analysis operation includes:

[0119] Extract fault work order features from equipment fault work orders in the target field;

[0120] Fault work order features include fault features and work order features;

[0121] Fault characteristics include fault location, fault time, fault type, and fault level;

[0122] Work order characteristics include the urgency of the work order and the maintenance resources required for the work order;

[0123] Establish second work order parameters based on fault work order characteristics.

[0124] In some specific embodiments, the second analysis operation can be implemented using technologies such as natural language processing, deep learning, or data mining. These technologies can extract key information from fault work orders and automatically construct feature vectors related to the fault type and maintenance personnel's capabilities. By training and optimizing these technologies, the system can more quickly identify the key features of fault work orders, providing more accurate data support for subsequent intelligent matching. For example, the fault location can help the system determine which maintenance personnel are closest to the fault point, thereby reducing response time; the fault time can be used to assess the urgency of the fault, ensuring that high-priority work orders receive priority processing; the fault type and fault level can reflect the complexity and professionalism of the maintenance work, helping the system match maintenance personnel with the appropriate skills for specific faults. The urgency of the work order and the required maintenance resources further refine the maintenance requirements, allowing the system to more comprehensively consider various factors and achieve more accurate matching and scheduling. Through these technical means, the present invention can significantly improve the intelligent level of work order processing, optimize resource allocation, and enhance maintenance efficiency and service quality.

[0125] However, feature extraction based on natural language processing, deep learning or data mining related technologies can often only extract a certain feature separately, and it is necessary to design at least six different feature extraction methods, which greatly increases the complexity of the system and the fusion effect of features is not ideal. Therefore, the present invention proposes an integrated work order feature extraction model, such as Figure 2 As shown in the figure, a comprehensive and efficient extraction of fault work order features can be achieved.

[0126] Specifically, the entire fault ticket is considered as a unified semantic unit, and all features are extracted in one reasoning process. The detailed steps are as follows:

[0127] Phase 1: Preprocessing the input text, that is, preprocessing the fault ticket text in the fault ticket;

[0128] Preprocessing includes word segmentation (Chinese uses jieba or Harbin Institute of Technology LTP), removal of stop words, entity standardization (such as "water pump A3" → "water pump", "North Cooling Tower" → "N-CoolingTower");

[0129] Further, use a pre-trained language model (such as BERT, ERNIE, ChatGLM) to encode the text and get the vector representation of each word:

[0130]

[0131] wherein, is the embedding dimension.

[0132] Stage two: design a parallel decoder based on attention mechanism.

[0133] Define six decoding heads, each responsible for identifying a type of feature, and the structure is as follows: decoding head structure (take fault location as an example): input is , the attention weight is calculated as follows:

[0134]

[0135] Further, the weighted aggregation operation is as follows:

[0136]

[0137] Further, map to the target space and classification / regression operation as follows:

[0138] wherein, is a special learnable parameter matrix for the fault location task, used to generate attention weights, is a bias term, also specific to the fault location task, represents the importance weight of the i-th word to the "fault location" feature, which is obtained after softmax normalization, represents the global feature vector after attention weighting, representing the most relevant semantic information in the entire work order to "fault location", represents the final output result, for example, a string "South Plant Area Three Layers" or a category number.

[0139] wherein, MLP is a multi-layer perceptron (fully connected neural network), and its output form varies according to the task, as shown in the following table:

[0140]

[0141] Similarly, corresponding decoding heads are established for the other five types of features.

[0142] Stage three: establish a knowledge graph assisted correction mechanism;

[0143] The knowledge graph includes node types and edge relationships. The node types include devices, locations, resources, fault levels, etc. The edge relationships include device-location association, device-resource dependency, fault level-impact mapping, etc.

[0144] Furthermore, for the result output by each decoder , the prior knowledge in the domain knowledge graph is combined for verification and correction.

[0145] For example, if the decoder identifies "frequency converter overheating" but does not identify the fault level, it will be supplemented with "intermediate" according to the rule "overheating -> intermediate fault" in the domain knowledge graph.

[0146] If "East Plant" is identified as the fault location, but there is no such name in the domain knowledge graph, it will be automatically corrected to the standard name "E Zone".

[0147] Stage four: merge the feature results, and combine the results output by the six decoding heads into the final second work order parameter vector:

[0148] Among them, the fault location P, the fault time , the fault type , the fault level , the work order urgency , and the required maintenance resources .

[0149] It should be noted that in order to realize the calculation of the capability matrix corresponding to the first capability parameter, the second work order parameter vector needs to be quantized and matrixed.

[0150] Specifically, the quantization operation can be as follows:

[0151] The fault location and the location coordinates of the maintenance personnel are the same, and no quantization operation is performed. The distance between the fault location and the location coordinates of the maintenance personnel is calculated to obtain the distance between each maintenance personnel and the fault location.

[0152] The quantization method of fault type is the same as that of expertise;

[0153] The quantization method of fault time is similar to the remaining work order processing time, and the number of minutes from the current time to the fault start time is taken as the fault time quantization result.

[0154] The quantization method of fault level and work order urgency is the same,

[0155] They are all assigned corresponding values ​​according to the preset level classification standards. For example, the fault level and work order urgency can be divided into four levels: urgent, relatively urgent, general, and non-urgent, and are assigned values ​​of 4, 3, 2, and 1 respectively.

[0156] The quantification of the required maintenance resources is based on a comprehensive consideration of the resource types and quantities, and a comprehensive numerical value is assigned. For each resource type, if it exists, it is marked as 1, otherwise it is marked as 0.

[0157] The quantified failure time , Fault type , Fault Level , Work Order Urgency , required maintenance resources Create a matrix.

[0158] It should be noted that performing a second analysis on the equipment fault work orders in the target area and obtaining the second work order parameters ensures that the subsequent intelligent matching process has accurate and comprehensive data support. Through the refined extraction and quantification of fault work order features, a deeper understanding of the specific content of the maintenance needs can be achieved, thereby more accurately assessing the degree of match between maintenance personnel and fault work orders. This precise matching helps reduce resource mismatches and time waste caused by information asymmetry, further improving maintenance efficiency and service quality. In addition, the precise acquisition of the second work order parameters also makes it possible to continuously optimize the system. By continuously learning and adjusting the matching strategy, the system can gradually adapt to various complex scenarios and achieve more intelligent and efficient work order scheduling.

[0159] S103, performing a third matching operation on the first capability parameter and the second work order parameter;

[0160] It should be noted that the common matching strategy involves obtaining the first capability parameter and the second work order parameter. The strategy then determines the first capability parameter that best satisfies the second work order parameter. Based on the second work order parameter and the application's goals and constraints, a first capability parameter range is established that satisfies the second work order parameter. For example, a matrix corresponding to the second work order parameter is used to determine a first capability parameter (i.e., a capability matrix) that satisfies the second work order parameter.

[0161] That is, it is necessary to combine the objectives and design constraints of the present invention, and determine the value of each parameter in the capability matrix corresponding to the first capability parameter that meets the conditions based on the matrix form corresponding to the second work order parameter, so as to screen the maintenance personnel who meet the conditions and determine the final order dispatch.

[0162] In an embodiment of the present invention, the matching strategy selection of the third matching operation includes:

[0163] The urgency of the work order includes the expedited level and the normal level;

[0164] If the urgency of the work order in the work order characteristics is expedited, the priority matching strategy is selected;

[0165] If the work order urgency in the work order characteristics is normal, the normal matching strategy is selected.

[0166] In an embodiment of the present invention, the priority matching strategy includes:

[0167] Determine the priority of urgency, which includes several different priorities;

[0168] Selecting a maintenance personnel with the highest skill level, the most matching expertise coefficient, and the shortest estimated arrival time based on the first capability parameter and the second work order parameter;

[0169] Dispatching work orders that meet the urgency level to the corresponding maintenance personnel, and determining whether there are any urgency-level work orders among the maintenance personnel's remaining work orders;

[0170] If it does not exist, the newly assigned expedited work order will be the one with the highest expedited priority;

[0171] If so, the priority of the newly assigned urgent work order will be compared with the urgent work orders in the remaining work orders of the maintenance personnel, and the pending work orders will be re-sorted according to the priority.

[0172] Specifically, the operation steps of the priority matching strategy are as follows:

[0173] Step 1: Determine the priority of urgency and classify it according to the pre-set urgency levels. For example, it can be divided into four levels: "very high", "high", "medium" and "normal".

[0174] Determine the current work order level: Identify the urgency level of the current work order and mark it as the highest priority task.

[0175] Step 2: Select the best maintenance personnel

[0176] Based on the requirements of the second work order parameter, select the most suitable person to handle the work order from all available maintenance personnel. The specific steps are as follows:

[0177] ① Ensure that the skill level of the selected maintenance personnel meets or exceeds the fault level requirements. For example, if the fault level is intermediate (quantitative value 3), then at least a maintenance personnel with an intermediate skill level (quantitative value >= 2) is required.

[0178] ②. Expertise coefficient matching:

[0179] Based on the skill level, we further screen maintenance personnel with high expertise coefficients for specific fault types. For example, for faults such as inverter overheating, we select maintenance personnel with expertise coefficients greater than a certain threshold (e.g., >1).

[0180] ③ Shortest estimated arrival time:

[0181] Calculate the time it takes for each qualified maintenance personnel to arrive at the fault location. Taking into account factors such as distance and traffic conditions, select the maintenance personnel or personnel with the shortest estimated arrival time.

[0182] Step 3: Dispatching work orders and adjusting the order

[0183] Once the best candidate is identified, the next step is the actual process of assigning the ticket, which can be done as follows:

[0184] New expedited work orders that meet the above criteria will be dispatched to the selected maintenance personnel.

[0185] Determine whether there are other expedited work orders among the remaining work orders of the maintenance personnel.

[0186] If it does not exist, the newly assigned expedited work order automatically becomes its highest priority task.

[0187] If there are any, the newly assigned urgent work order will be compared with the urgent work orders in the maintenance personnel's remaining work order volume. The pending work orders will be re-ordered according to the priority to ensure that the most urgent tasks are handled first.

[0188] For example, suppose there is an urgent work order that needs to be processed immediately, with the following parameters:

[0189] Fault type: Inverter overheating (quantization value 1)

[0190] Fault level: Medium (quantitative value 3)

[0191] Work Order Urgency: Expedited (Quantitative Value 4)

[0192] The system performs the following actions:

[0193] ①The system marks this work order as the highest priority task.

[0194] ② Select maintenance personnel with intermediate skill level and above (quantitative value >= 2).

[0195] ③ On the basis of meeting the skill level, further screen maintenance personnel with a higher expertise coefficient (such as >1) for inverter overheating.

[0196] ④ Calculate the time required for each qualified maintenance personnel to arrive at the fault site, and select the one or several with the shortest time.

[0197] ⑤Dispatching work orders and adjusting the order:

[0198] Assume that maintenance worker A has five remaining work orders and is expected to complete all tasks in 120 minutes. His skill level is intermediate, his expertise coefficient for inverter maintenance is 1, his historical work order score is 4, and his service rating is 3. When the system assigns an urgent work order to maintenance worker A, it checks whether there are other expedited work orders among his current remaining work orders. If not, the new work order becomes his highest priority task. If so, the system compares the priorities of the existing expedited work orders and reorders the pending work orders.

[0199] In the embodiment of the present invention, the general matching strategy includes several layers of matching mechanisms;

[0200] Each matching mechanism in the plurality of matching mechanisms performs a matching operation on the first capability parameter and the second work order parameter;

[0201] Performing a matching operation on the first capability parameter and the second work order parameter based on a plurality of layers of matching mechanisms in a preset order;

[0202] Work orders are distributed according to the matching operation results. Work orders of the common matching strategy are distributed in sequence.

[0203] In an embodiment of the present invention, the multiple-layer matching mechanism includes:

[0204] Remaining work order quantity matching mechanism, remaining work order processing time matching mechanism, skill level matching mechanism, expertise coefficient matching mechanism, historical work order record matching mechanism and service evaluation level matching mechanism.

[0205] It should be noted that each layer of the matching mechanism can be simplified in the form of a matrix conversion of the second work order parameter to the first capability parameter range.

[0206] Specifically, the goal of the present invention is to select the optimal maintenance personnel. Constraints can be obtained based on the first capability parameter and the second work order parameter. The constraints can be as follows:

[0207] Skill matching is required: ensure that maintenance personnel have the ability to handle this type of fault.

[0208] Require ETA: For expedited work orders, priority is given to maintenance personnel who can arrive on site quickly.

[0209] It is necessary to ensure that maintenance personnel have enough free time to handle new tasks.

[0210] Take historical ticket records and service reviews as additional considerations.

[0211] In some specific embodiments, such as Figure 3 As shown, the specific steps of the common matching strategy (i.e., performing the first capability parameter inversion) include:

[0212] The specific method of determining the value of each parameter in the capability matrix corresponding to the first capability parameter that meets the conditions according to the matrix form corresponding to the second work order parameter can be as follows:

[0213] Set the minimum skill requirement based on the malfunction level. For example, if the malfunction level is medium (quantized value 3), the skill level should be at least medium (quantized value >= 2).

[0214] For specific fault types, set an expertise threshold. For example, if the expertise threshold for an inverter overheating fault is set to 80%, maintenance personnel with expertise above this threshold will be selected.

[0215] For expedited work orders, set a maximum allowable arrival time. This can be determined based on the fault location and the coordinates of the maintenance personnel. For example, it should not exceed 30 minutes.

[0216] Set a limit on the number of remaining tickets and the corresponding processing time limit. For example, the number of remaining tickets should not exceed 2, and the remaining processing time should not exceed 60 minutes.

[0217] Whenever possible, select maintenance personnel with high historical work order record scores (e.g. >3) and high service evaluation levels (e.g. >2).

[0218] From this, we can determine the scope of the capability matrix (i.e., the remaining work order quantity matching mechanism, the remaining work order processing time matching mechanism, the skill level matching mechanism, the expertise coefficient matching mechanism, the historical work order record matching mechanism, and the service evaluation level matching mechanism) such as:

[0219] Capacity matrix = [remaining work orders, remaining work order processing time, skill level, expertise coefficient (for specific faults), historical work order records, service evaluation level];

[0220] Value range = [[0,2],<60 minutes,[2,3],>1,>3,>2];

[0221] It should be noted that the above value range means that when selecting maintenance personnel, you should look for those who meet the following conditions:

[0222] The number of remaining work orders does not exceed 2;

[0223] The remaining work order processing time shall not exceed 60 minutes;

[0224] Skill level is intermediate or above;

[0225] Have a high expertise coefficient in specific fault areas;

[0226] The historical work order record scores and service evaluation levels are high.

[0227] In this way, the reasonable value range of each indicator in the first capability parameter can be accurately determined according to the specific second work order parameter requirements, so that maintenance personnel can be selected and dispatched efficiently and accurately.

[0228] This transforms the complex matching process into a simple matrix matching operation, achieving digital processing and highlighting the technological advantages of Xinchuang. By constructing such a capability matrix, the system can quickly screen out qualified maintenance personnel, greatly improving matching efficiency and accuracy.

[0229] S104, scheduling the work order according to the matching result of the third matching operation;

[0230] In an embodiment of the present invention, the third matching operation includes a priority matching strategy and a normal matching strategy;

[0231] In the embodiment of the present invention, the matching strategy selection of the third matching operation is performed according to the second work order parameters.

[0232] In summary, the present invention proposes an intelligent work order scheduling method based on ICT technology, which obtains work orders for equipment failures in a target area and first capability parameters of preset maintenance personnel for the target area; performs a second analysis operation on the work orders for equipment failures in the target area to obtain second work order parameters; performs a third matching operation on the first capability parameters and the second work order parameters; and schedules the work order based on the matching results of the third matching operation. First, by combining ICT technology, the present invention realizes intelligent work order scheduling, improves maintenance efficiency, and reduces the subjectivity and uncertainty of manual scheduling. Second, by obtaining the first capability parameters of the preset maintenance personnel through the first analysis operation, scheduling is more accurate and can be matched according to the actual capabilities of the maintenance personnel, avoiding maintenance delays or failures caused by insufficient maintenance personnel capabilities. Furthermore, the second analysis operation conducts an in-depth analysis of the work orders for equipment failures in the target area to obtain second work order parameters, providing detailed data support for subsequent matching operations. Finally, the third matching operation adopts a priority matching strategy and a normal matching strategy, flexibly selecting a matching strategy based on the second work order parameters, further improving the accuracy and efficiency of scheduling. In summary, the present invention has significant beneficial effects in intelligent work order scheduling.

[0233] Example 2: This embodiment also provides an intelligent work order scheduling system based on the Xinchuang technology, including:

[0234] A data acquisition module, used to obtain equipment failure work orders in the target field and the first capability parameters of preset maintenance personnel for the target field;

[0235] A first capability parameter of a preset maintenance personnel in a target area is obtained through a first analysis operation;

[0236] An analysis module, configured to perform a second analysis operation on the target field equipment failure work order to obtain second work order parameters;

[0237] a matching module, configured to perform a third matching operation on the first capability parameter and the second work order parameter;

[0238] A scheduling module, configured to schedule work orders according to the matching result of the third matching operation;

[0239] The third matching operation includes a priority matching strategy and a normal matching strategy;

[0240] The matching strategy selection of the third matching operation is performed according to the second work order parameters.

[0241] The above-mentioned unit modules can be embedded in or independent of the processor in the electronic device in the form of hardware, or can be stored in the memory of the electronic device in the form of software, so that the processor can call and execute the corresponding operations of the above-mentioned modules.

[0242] This embodiment also provides an electronic device, which may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 4 As shown. The electronic device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the electronic device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, an intelligent work order scheduling method based on information technology is implemented. The display screen of the electronic device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the electronic device can be a touch layer covering the display screen, or a button, trackball or touchpad provided on the housing of the electronic device, or an external keyboard, touchpad or mouse.

[0243] This embodiment further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the following steps are implemented:

[0244] Obtain equipment failure work orders in the target area and the first capability parameters of preset maintenance personnel for the target area;

[0245] A first capability parameter of a preset maintenance personnel in a target area is obtained through a first analysis operation;

[0246] Perform a second analysis operation on the target field equipment failure work order to obtain second work order parameters;

[0247] Performing a third matching operation on the first capability parameter and the second work order parameter;

[0248] Perform work order scheduling based on the matching result of the third matching operation;

[0249] The third matching operation includes a priority matching strategy and a normal matching strategy;

[0250] The matching strategy selection of the third matching operation is performed according to the second work order parameters.

[0251] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

[0252] 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 present invention.

[0253] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. An intelligent work order scheduling method based on ICT technology, characterized in that: include: Obtain equipment failure work orders in the target area and the first capability parameters of preset maintenance personnel for the target area; The first capability parameter of the preset maintenance personnel in the target field is obtained through a first analysis operation; Performing a second analysis operation on the target field equipment failure work order to obtain second work order parameters; performing a third matching operation on the first capability parameter and the second work order parameter; Performing work order scheduling according to the matching result of the third matching operation; The third matching operation includes a priority matching strategy and a normal matching strategy; The matching strategy selection of the third matching operation is performed according to the second work order parameter; The first analysis operation includes: Obtaining the coordinate range of the target area and the relevant parameters of the preset maintenance personnel within the coordinate range; The preset maintenance personnel related parameters include the maintenance personnel's remaining work order quantity, remaining work order processing time, skill level, expertise coefficient, historical work order records, maintenance personnel's location coordinates and service evaluation level; Determining a first capability parameter of a preset maintenance personnel according to the preset maintenance personnel related parameters; Quantify the preset maintenance personnel related parameters one by one after removing the coordinates of the maintenance personnel's location; Arrange the quantified results of the preset maintenance personnel related parameters after quantification one by one in a fixed order; Matrix the arranged quantization results; Record the fixed order and matrix results, and use the matrix results as the capability matrix; The quantitative standards are as follows: The quantification standard for the remaining work orders is as follows: the work order quantity is expressed as a number, and the value range of the work order quantity is [0, 2*Gvd]. The larger the number, the more work orders there are. Gvd represents the ratio of the total work order quantity in the target area to the preset maintenance personnel in the target area, rounded to the nearest integer. The quantitative standard for the remaining work order processing time is as follows: the processing time is expressed as a number, and the value range of the processing time is [0, the number of remaining work orders * Tmax]. The larger the number, the longer the remaining work order processing time. Tmax represents the maximum average time required for maintenance personnel to process a single work order in the target area, in minutes. The quantitative standard for skill levels is as follows: skill levels are divided according to skill certification levels and assigned different numerical values. The larger the numerical value, the higher the skill level. Skill levels are divided into level 1, level 2, and level 3 according to skill certification levels. Level 1 corresponds to a numerical value of 3, level 2 corresponds to a numerical value of 2, and level 3 corresponds to a numerical value of 1. The quantitative standard for the expertise coefficient is as follows: a value is assigned based on the repair success rate of the maintenance personnel for a certain type of fault or equipment, and an expertise coefficient judgment threshold is set. If the assigned value of the repair success rate of the maintenance personnel for a certain type of fault or equipment is not greater than the expertise coefficient judgment threshold, it is marked as zero; If the assigned value of the maintenance personnel's repair success rate for a certain type of fault or equipment is greater than the expertise coefficient judgment threshold, the assigned values ​​that meet the conditions are sorted by size and assigned values ​​from one to infinity in order of size. The larger the value, the stronger the expertise in that field. The quantitative standard for historical work order records is to conduct a comprehensive evaluation based on the maintenance personnel's historical success rate and average processing time indicators, and assign corresponding values; The quantitative standard for service evaluation level is as follows: based on past user evaluations of maintenance personnel's services, different numerical values ​​are assigned to each level. The larger the numerical value, the higher the service evaluation. The service evaluation level includes four levels: very satisfied, satisfied, average, and dissatisfied. Very satisfied, satisfied, average, and dissatisfied are assigned values ​​of 3, 2, 1, and 0 respectively. The second analysis operation includes: Extract fault work order features from equipment fault work orders in the target field; The fault work order features include fault features and work order features; The fault characteristics include fault location, fault time, fault type and fault level; The work order characteristics include the urgency of the work order and the maintenance resources required for the work order; Establishing second work order parameters based on fault work order characteristics; Treat the entire fault ticket as a unified semantic unit and extract all features in one reasoning process; Preprocess the trouble ticket text in the trouble ticket and encode it using a pre-trained language model to obtain a vector representation for each word. Design a parallel decoder based on the attention mechanism and define six decoding heads. Each decoding head is responsible for identifying a class of features, performing weighted aggregation operations, mapping them to the target space, and performing classification / regression operations. Establish a knowledge graph-assisted correction mechanism to verify and correct the output of each decoder by combining it with prior knowledge in the domain knowledge graph; Merge the feature results and combine the outputs of the six decoding heads into the final second work order parameter vector.

2. The intelligent work order scheduling method based on the information technology of claim 1 is characterized in that: The matching strategy selection of the third matching operation includes: The urgency of the work order includes the expedited level and the normal level; If the urgency of the work order in the work order characteristics is expedited, the priority matching strategy is selected; If the work order urgency in the work order characteristics is normal, the normal matching strategy is selected.

3. The intelligent work order scheduling method based on the information technology of claim 2 is characterized in that: The priority matching strategy includes: Determining an urgency priority, wherein the urgency priority includes several different priorities; Selecting a maintenance personnel with the highest skill level, the most matching expertise coefficient, and the shortest estimated arrival time based on the first capability parameter and the second work order parameter; Dispatching work orders that meet the urgency level to the corresponding maintenance personnel, and determining whether there are any urgency-level work orders among the maintenance personnel's remaining work orders; If it does not exist, the newly assigned expedited work order will be the one with the highest expedited priority; If so, the priority of the newly assigned urgent work order will be compared with the urgent work orders in the remaining work orders of the maintenance personnel, and the pending work orders will be re-sorted according to the priority.

4. The intelligent work order scheduling method based on the information technology as described in claim 3 is characterized in that: The general matching strategy includes several layers of matching mechanisms; Each matching mechanism in the plurality of matching mechanisms performs a matching operation on the first capability parameter and the second work order parameter; Performing a matching operation on the first capability parameter and the second work order parameter based on the multiple layers of matching mechanisms in a preset order; Work orders are distributed according to the matching operation results. Work orders of the common matching strategy are distributed in sequence.

5. The intelligent work order scheduling method based on the information technology of claim 4 is characterized in that: The several layers of matching mechanisms include: Remaining work order quantity matching mechanism, remaining work order processing time matching mechanism, skill level matching mechanism, expertise coefficient matching mechanism, historical work order record matching mechanism and service evaluation level matching mechanism.

6. An intelligent work order scheduling system based on ICT technology, applying the method according to any one of claims 1 to 5, characterized in that: include: A data acquisition module, used to obtain equipment failure work orders in the target field and the first capability parameters of preset maintenance personnel for the target field; The first capability parameter of the preset maintenance personnel in the target field is obtained through a first analysis operation; An analysis module, configured to perform a second analysis operation on the target field equipment failure work order to obtain second work order parameters; a matching module, configured to perform a third matching operation on the first capability parameter and the second work order parameter; A scheduling module, configured to schedule work orders according to the matching result of the third matching operation; The third matching operation includes a priority matching strategy and a normal matching strategy; The matching strategy selection of the third matching operation is performed according to the second work order parameter.

7. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of an intelligent work order scheduling method based on information technology as described in any one of claims 1 to 6 are implemented.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, the steps of an intelligent work order scheduling method based on information technology as described in any one of claims 1 to 6 are implemented.

Images