Intelligent dispatching method, equipment, medium and product based on maintenance personnel portrait
By building user portraits and training intelligent order assignment matching models, the inaccuracy and mis-submission problems of traditional order assignment methods are solved, and more efficient equipment fault repair order assignment is achieved, and the order assignment accuracy and efficiency are improved.
Patent Information
- Application Number
- CN202110586563.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-05-27
- Publication Date
- 2024-11-29
- Estimated Expiration
- 2041-05-27
AI Technical Summary
The traditional order dispatch method relies on manual experience, which leads to inaccurate order dispatch, prone to misleading and misleading, and the ability to comprehensively consider the skills and fault history of maintenance personnel, resulting in increased maintenance difficulty.
By extracting maintenance personnel and equipment failure information from the online maintenance management system, building user portraits, and using preset algorithms to train intelligent order assignment matching models, output the most suitable maintenance personnel information, and realize intelligent order assignment.
It improves the accuracy and efficiency of order assignments, reduces the situation of invalid order assignments, can target the problem of maintenance personnel and equipment failures, and reduces the dependence on manual order assignments.
Smart Images

Figure CN113191509B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of equipment maintenance, and in particular to an intelligent dispatching method, equipment, medium and product based on maintenance personnel portraits. Background Art
[0002] At present, maintenance work usually involves multiple professions. For example, rail transit operation and maintenance work involves different professions such as locomotive, engineering, electrical and vehicle. The maintenance work items of each profession are diverse and highly professional, and the demand for effectiveness and accuracy is increasing. At the same time, the existing traditional dispatching method usually adopts manual dispatching, and the dispatching efficiency depends on the personal experience of the dispatcher. When complex problems arise, it is difficult for the dispatcher to find and comprehensively consider the fault history and inspection records of the facilities and equipment in a timely and accurate manner, which increases the difficulty of maintenance.
[0003] Therefore, the following problems arise in the dispatching of work orders during the traditional equipment maintenance process: 1. Dispatching is based on the business experience of the dispatcher, which is not universal. It requires a high level of professionalism from the dispatcher, and is prone to mis-dispatching or incorrect dispatching, resulting in invalid dispatches. 2. Traditional dispatching cannot comprehensively consider the maintenance personnel's work skills, proficiency, location and other attributes, making it difficult to optimally match maintenance personnel with work orders. 3. Traditional dispatching only has fault codes, does not understand the faults of different equipment, and cannot comprehensively consider historical maintenance records to conduct targeted dispatching. Summary of the invention
[0004] In order to overcome the shortcomings of the prior art, the purpose of the present invention is to provide an intelligent dispatching method based on maintenance personnel portraits, which can solve the problems of inaccurate dispatching, easy mis-dispatching and erroneous dispatching, and low dispatching efficiency caused by manual dispatching in the process of existing equipment fault handling.
[0005] The second purpose of the present invention is to provide an electronic device that can solve the problems of inaccurate dispatching, easy mis-dispatching and erroneous dispatching, and low dispatching efficiency caused by manual dispatching during the existing equipment fault handling process.
[0006] The third object of the present invention is to provide a computer-readable storage medium, which can solve the problems of inaccurate dispatching, easy mis-dispatching and erroneous dispatching, and low dispatching efficiency caused by manual dispatching in the process of existing equipment failure handling.
[0007] The fourth object of the present invention is to provide a computer program product that can solve the problems of inaccurate dispatching, easy mis-dispatching and erroneous dispatching, and low dispatching efficiency caused by manual dispatching in the process of existing equipment failure handling.
[0008] One of the purposes of the present invention is achieved by the following technical solution:
[0009] Intelligent dispatching method based on maintenance personnel portraits,
[0010] Data extraction, extracting maintenance personnel information and equipment failure information associated with a number of processed equipment failures from the online maintenance management system, wherein the maintenance personnel information includes skill information and distribution information, and the equipment failure information includes historical work order data and failure data;
[0011] Construct a user portrait, quantify the distribution information according to preset statistical analysis rules, and cluster the skill information corresponding to each maintenance personnel using a preset algorithm to obtain user portrait data containing behavior labels and skill labels corresponding to each maintenance personnel and equipment fault information;
[0012] Model training: input all the user portrait data and the corresponding equipment fault information into a preset matching model for training to obtain an intelligent dispatch matching model, and deploy the intelligent dispatch matching model in the intelligent dispatch system;
[0013] Intelligent dispatching inputs the acquired fault information of the equipment to be repaired into the intelligent dispatching matching model, and the intelligent dispatching matching model outputs the corresponding maintenance personnel information.
[0014] Furthermore, the distribution information includes the number of maintenance times today, location information and idle information, the skill information includes work information data, performance data and maintenance data, and the construction of the user portrait is specifically: using the mean, standard deviation and kurtosis as statistics to quantify the distribution information, and obtain a behavior label for representing the behavior distribution characteristics of a single maintenance personnel, and using clustering algorithm, classification algorithm and association analysis method in turn to cluster the skill information to obtain a skill label corresponding to each maintenance personnel.
[0015] Furthermore, before constructing the user portrait, data preprocessing is also included, in which incomplete information in the maintenance personnel information is completed, useless information in the maintenance personnel information is eliminated, abnormal data in the maintenance personnel information is corrected, and all the processed maintenance personnel information is solidified and stored.
[0016] Furthermore, the model training is specifically as follows: the user portrait data and the corresponding equipment fault information are divided into a training set, a verification set and a test set according to a preset ratio, the training set is used to train the preset matching model, the verification set is used to evaluate the trained preset matching model for verification and obtain the verification result, the test set is used to predict the trained preset matching model to obtain the matching accuracy, when the verification result reaches the preset verification threshold and the matching accuracy reaches the preset matching accuracy threshold, the trained preset matching model is used as the intelligent dispatching matching model.
[0017] Furthermore, the dividing of the user portrait data and the corresponding equipment fault information into a training set, a validation set and a test set according to a preset ratio is specifically as follows: first, basic information, maintenance information and fault information corresponding to the faulty equipment are extracted from the historical work order data and fault data in the equipment fault information, the basic information, maintenance information and fault information are used as work order extraction information, and the user portrait data and the corresponding work order extraction information are divided into a training set, a validation set and a test set according to a preset ratio.
[0018] Furthermore, the basic information includes the device ID, device type and service life, the maintenance information includes the number of historical failures and failure frequencies, and the failure information includes the failure code, failure level and failure urgency.
[0019] The second object of the present invention is achieved by adopting the following technical solution:
[0020] An electronic device, comprising: a processor;
[0021] A memory; and a program, wherein the program is stored in the memory and is configured to be executed by a processor, and the program includes a method for executing the intelligent dispatching method based on maintenance personnel portraits described in the present application.
[0022] The third object of the present invention is achieved by adopting the following technical solutions:
[0023] A computer-readable storage medium having a computer program stored thereon, wherein the computer program is executed by a processor to implement the intelligent dispatching method based on maintenance personnel portraits described in the present application.
[0024] The fourth object of the present invention is achieved by the following technical solutions:
[0025] A computer program product includes a computer program, characterized in that when the computer program is executed by a processor, it implements the intelligent dispatching method based on maintenance personnel portraits described in the present application.
[0026] Compared with the prior art, the beneficial effect of the present invention is that the intelligent dispatching method based on maintenance personnel portraits in the present application is used for intelligent maintenance dispatching of equipment to be repaired by constructing user portraits and training an intelligent dispatching matching model in which users can only dispatch orders. The entire process does not require human intervention, and can avoid dependence on dispatching personnel, effectively reduce the occurrence of invalid dispatching, and improve the accuracy and efficiency of dispatching during the overall equipment failure repair process.
[0027] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention and implement it according to the contents of the specification, the following is a detailed description of the preferred embodiments of the present invention in conjunction with the accompanying drawings. The specific implementation of the present invention is given in detail by the following embodiments and their accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS
[0028] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:
[0029] Figure 1 It is a flow chart of the intelligent dispatching method based on maintenance personnel portrait of the present invention. DETAILED DESCRIPTION
[0030] The present invention is further described below in conjunction with the accompanying drawings and specific implementation methods. It should be noted that, under the premise of no conflict, the various embodiments or technical features described below can be arbitrarily combined to form a new embodiment.
[0031] like Figure 1 As shown, the intelligent dispatching method based on maintenance personnel portrait in this embodiment includes the following steps:
[0032] Data extraction, extracting maintenance personnel information and equipment failure information associated with a number of processed equipment failures from the online maintenance management system, the maintenance personnel information includes skill information and distribution information, and the equipment failure information includes historical work order data and failure data. In this embodiment, the distribution information includes the number of maintenance times today, location information, and idle information, and the skill information includes work information data, performance data, and maintenance data.
[0033] Data preprocessing: completing incomplete information in maintenance personnel information, removing useless information in maintenance personnel information, correcting abnormal data in maintenance personnel information, and solidifying and storing all processed maintenance personnel information.
[0034] Construct a user profile, quantify the distribution information according to preset statistical analysis rules, and cluster the skill information corresponding to each maintenance personnel using a preset algorithm to obtain user profile data containing behavior labels and skill labels corresponding to each maintenance personnel and equipment failure information. Specifically, use the mean, standard deviation, and kurtosis as statistics to quantify the distribution information, obtain a behavior label used to represent the characteristics of the behavior distribution of a single maintenance personnel, and use clustering algorithms, classification algorithms, and association analysis methods to cluster the skill information in turn to obtain a skill label corresponding to each maintenance personnel.
[0035] Model training, input all the user portrait data and the corresponding equipment failure information into the preset matching model for training, obtain the intelligent dispatch matching model, and deploy the intelligent dispatch matching model in the intelligent dispatch system. Specifically: divide the user portrait data and the corresponding equipment failure information into a training set, a verification set and a test set according to a preset ratio, the training set is used to train the preset matching model, the verification set is used to evaluate the trained preset matching model for verification and obtain the verification result, the test set is used to predict the trained preset matching model and obtain the matching accuracy. When the verification result reaches the preset verification threshold and the matching accuracy reaches the preset matching accuracy threshold, the trained preset matching model is used as the intelligent dispatch matching model. In this embodiment, the user portrait data and the corresponding equipment fault information are divided into a training set, a validation set, and a test set according to a preset ratio. Specifically, the basic information, maintenance information, and fault information corresponding to the faulty equipment are first extracted from the historical work order data and fault data in the equipment fault information, and the basic information, maintenance information, and fault information are used as work order extraction information. The user portrait data and the corresponding work order extraction information are divided into a training set, a validation set, and a test set according to a preset ratio. The basic information includes equipment ID, equipment type, and service life, the maintenance information includes the number of historical faults and fault frequency, and the fault information includes fault code, fault level, and fault urgency.
[0036] Intelligent dispatching inputs the acquired fault information of the equipment to be repaired into the intelligent dispatching matching model, and the intelligent dispatching matching model outputs the corresponding maintenance personnel information.
[0037] The present invention also provides an electronic device, comprising: a processor;
[0038] A memory; and a program, wherein the program is stored in the memory and is configured to be executed by a processor, and the program includes a method for executing the intelligent dispatching method based on maintenance personnel portraits described in the present application.
[0039] The present invention also provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program is executed by a processor to implement the intelligent dispatching method based on maintenance personnel portraits described in the present application.
[0040] The present invention also provides a computer program product, including a computer program, characterized in that when the computer program is executed by a processor, it implements the intelligent dispatching method based on maintenance personnel portraits described in the present application.
[0041] The intelligent dispatching method based on maintenance personnel portrait in the present application is used for intelligent maintenance dispatching of equipment to be repaired by constructing user portraits and training an intelligent dispatching matching model that can only dispatch orders to users. The entire process does not require human intervention, which can avoid dependence on dispatching personnel, effectively reduce the occurrence of invalid dispatching, and improve the accuracy and efficiency of dispatching during the overall equipment fault repair process. The matching model is constructed using the user portrait data and work order data of the maintenance personnel, which can dig out the best matching relationship between the fault and the maintenance personnel, comprehensively consider the intrinsic connection between the fault and the maintenance personnel, and consider the historical maintenance records of the faulty equipment, so as to carry out targeted dispatching.
[0042] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in any form. Any ordinary technician in the industry can smoothly implement the present invention as shown in the drawings and above. However, any equivalent changes, modifications and evolutions made by technicians familiar with the profession without departing from the scope of the technical solution of the present invention using the technical content disclosed above are all equivalent embodiments of the present invention. At the same time, any equivalent changes, modifications and evolutions made to the above embodiments based on the essential technology of the present invention are still within the protection scope of the technical solution of the present invention.
Claims
1. An intelligent dispatching method based on maintenance personnel portraits, characterized by: Data extraction, extracting maintenance personnel information and equipment failure information associated with a number of processed equipment failures from the online maintenance management system, wherein the maintenance personnel information includes skill information and distribution information, and the equipment failure information includes historical work order data and failure data; Constructing a user portrait, quantifying the distribution information according to preset statistical analysis rules, and clustering the skill information corresponding to each maintenance personnel using a preset algorithm, to obtain user portrait data containing behavior labels and skill labels corresponding to each maintenance personnel and equipment fault information; the distribution information includes the number of maintenance times today, location information, and idle information, and the skill information includes work information data, performance data, and maintenance data. The construction of the user portrait specifically includes: using the mean, standard deviation, and kurtosis as statistics to quantify the distribution information, to obtain a behavior label used to represent the distribution characteristics of the behavior of a single maintenance personnel, and using a clustering algorithm, a classification algorithm, and an association analysis method in turn to cluster the skill information to obtain a skill label corresponding to each maintenance personnel; Model training: input all the user portrait data and the corresponding equipment fault information into a preset matching model for training to obtain an intelligent dispatch matching model, and deploy the intelligent dispatch matching model in the intelligent dispatch system; The model training is specifically as follows: firstly extracting basic information, maintenance information and fault information corresponding to the faulty equipment from the historical work order data and fault data in the equipment fault information, taking the basic information, maintenance information and fault information as work order extraction information, and dividing the user portrait data and the corresponding work order extraction information into a training set, a verification set and a test set according to a preset ratio, wherein the basic information includes equipment ID, equipment type and service life, the maintenance information includes the number of historical faults and the fault frequency, and the fault information includes the fault code, fault level and fault urgency; the training set is used to train the preset matching model, the verification set is used to verify the trained preset matching model and obtain the verification result, the test set is used to predict the trained preset matching model and obtain the matching accuracy, and when the verification result reaches the preset verification threshold and the matching accuracy reaches the preset matching accuracy threshold, the trained preset matching model is used as the intelligent dispatching matching model; Intelligent dispatching inputs the acquired fault information of the equipment to be repaired into the intelligent dispatching matching model, and the intelligent dispatching matching model outputs the corresponding maintenance personnel information.
2. The intelligent dispatching method based on maintenance personnel portrait according to claim 1, characterized in that: Before constructing the user portrait, data preprocessing is also included, which includes completing incomplete information in the maintenance personnel information, eliminating useless information in the maintenance personnel information, correcting abnormal data in the maintenance personnel information, and solidifying and storing all the processed maintenance personnel information.
3. An electronic device, characterized in that include: processor; Memory; And a program, wherein the program is stored in the memory and is configured to be executed by a processor, and the program includes a method for executing the intelligent dispatching method based on maintenance personnel portraits as described in any one of claims 1-2.
4. A computer-readable storage medium having a computer program stored thereon, characterized in that: The computer program is executed by the processor to implement the intelligent dispatching method based on maintenance personnel portraits as described in any one of claims 1-2.
5. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, it implements the intelligent dispatching method based on maintenance personnel portraits as described in any one of claims 1-2.
Citation Information
Patent Citations
Order processing method and system
CN110245791A
