Operation and maintenance work order intelligent matching dispatching method and device based on data portrait

Abstract

The invention discloses an operation and maintenance work order intelligent matching dispatching method and device based on data portraits. The method comprises the steps that basic information data and historical work order data of engineers are collected; the work orders are clustered to obtain clustering results of all kinds of work orders, and the clustering results comprise all serial numbers and cluster information of each kind of work orders; respectively clustering each log word vector in each type of work order to determine a personnel capability label required by each type of work order and a weight of the personnel capability label so as to obtain a personnel capability label set X; personnel portraying is carried out on each engineer based on the personnel ability label set X, and an ability label and a corresponding score of each engineer are obtained; when a new work order arrives, the category to which the new work order belongs is judged according to the obtained cluster information of each type of work order so as to determine the ability label set M of the personnel required by the new work order, comprehensive scoring is performed on each candidate engineer based on the label set M, and finally dispatching is performed based on comprehensive score ranking, so that the dispatching efficiency and accuracy are effectively improved.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a method and device for intelligently matching and dispatching operation and maintenance work orders based on data profiling. Background Art

[0002] In the power engineering operation and maintenance management system, personnel profiling is usually used to realize intelligent dispatching of work orders. It analyzes and processes a large amount of data, abstracts the data into specific labels, and uses these labels to concretize the personnel images. Then, intelligent matching of work order tasks is carried out according to various personnel portraits to realize automatic arrangement and optimization of dispatching work.

[0003] However, the personnel portrait method used in the current traditional dispatching method is mostly based on the capabilities of engineering personnel as the analysis benchmark, which is not closely integrated with the actual business needs, resulting in the inability to directly correspond to the personnel portrait during actual dispatching, and the inability to achieve rapid dispatching; in addition, due to the dynamic changes in the market environment, personnel capabilities, and project experience, the traditional portrait method does not have continuous scalability, resulting in the problem of low dispatching accuracy; in addition, the power engineering operation and maintenance management system has a large amount of unstructured data, rich information, and a variety of data sources. The personnel portrait method based on traditional artificial intelligence algorithms does not fully consider the product information in the company's product system, the historical work order data and historical log data in the work order system, the demand order data in the demand collection system, and the training course data in the training system, resulting in the personnel label not covering all information elements, the subject label is often lost, and there are problems with the integrity and precision of the label system, so that the subsequent dispatching cannot be quickly and effectively matched. Therefore, the current power engineering operation and maintenance work order dispatching method needs to be further optimized. Summary of the invention

[0004] In order to address the deficiencies in the prior art, the present invention provides a method and device for intelligent matching and dispatching of operation and maintenance work orders based on data portraits, which fully considers and utilizes historical data, effectively derives the set of personnel capability labels required for the power engineering operation and maintenance system, and takes into account the complex characteristics of engineering personnel, adapts to engineering personnel with different backgrounds, accurately derives the capability labels and scores of engineering personnel, comprehensively depicts the portraits of engineering personnel, improves the accuracy, practicality and intelligence of the portraits, provides more reasonable data support for subsequent dispatching decisions, and effectively improves the overall efficiency and accuracy of intelligent matching and dispatching of operation and maintenance work orders.

[0005] The present invention adopts the following technical solution.

[0006] In a first aspect, the present invention provides a method for intelligently matching and dispatching operation and maintenance work orders based on data profiling, the method comprising the following steps:

[0007] S1. Collect basic information data of engineering personnel and historical work order data, and perform pre-processing;

[0008] S2. Based on the pre-processed historical work order data, cluster the work orders to obtain clustering results of various types of work orders, including all numbers and cluster information of each type of work order;

[0009] S3. Cluster the log word vectors in each type of work order to determine the personnel capability labels and their weights required for each type of work order, thereby obtaining the personnel capability label set X.

[0010] S4, based on the personnel capability label set X, a personnel profile is performed for each engineering personnel to obtain the capability label and corresponding score of each engineering personnel;

[0011] S5. When a new work order arrives, the category of the new work order is determined according to the cluster information of various work orders obtained in step S2 to determine the capability label set M of the personnel required for the new work order, and each candidate engineering personnel is comprehensively scored based on the label set M, and finally the work is assigned based on the comprehensive score ranking.

[0012] Optionally, the method further comprises the following steps:

[0013] S6. When the engineer completes the new work order task, return to step S4 to achieve real-time update of the engineer portrait.

[0014] Optionally, in step S1, the basic information data of the engineering personnel includes: personal information, educational background, years of work experience, years of work experience in the company, job grade, job responsibilities and requirements, skills, skills certificates, work performance, training courses, training time, training content, completion certificate, professional qualification certificate, current location information of the engineering personnel and / or future schedule arrangements;

[0015] The historical work order data includes the task content of the work order, the creator of the work order, the work order status, the work order type, the work order priority, the contract list, the work order time, precautions, relevant contacts, preparation work, log information, customer feedback, data archive, product model on the work order, production year and month, version information and / or years of field use.

[0016] Optionally, in step S1, the preprocessing includes:

[0017] Step 101, clean the collected data: delete spaces, line breaks, exclamation marks and special characters in the text data, and remove duplicate, erroneous, incomplete and redundant data;

[0018] Step 102: Standardize the cleaned data to form a complete and usable data set.

[0019] Optionally, in step S2, the step of clustering the work orders includes:

[0020] Step 201: extracting a dictionary of power engineering operation and maintenance from the content recorded in the preprocessed historical work order data, and segmenting each work order based on the dictionary to obtain a text of the work order after segmentation;

[0021] Step 203: convert the work order words in the word segmentation text of each work order into word vectors one by one;

[0022] Step 204: sum the word vectors involved in each work order to obtain a work order vector corresponding to each work order;

[0023] Step 205: cluster the work order vectors, determine the target cluster to which each work order belongs, and obtain the types of all work orders.

[0024] Optionally, in step S3, the step of obtaining the personnel capability tag set X includes:

[0025] Step 301: extract all logs contained in each type of work order according to all numbers of each type of work order obtained in step S2;

[0026] Step 302: Segment all logs in each type of work order, and remove date words and repeated words;

[0027] Step 303: convert the log word segments in each type of work order into log word vectors one by one, and count the frequency of occurrence and total word frequency of each word in each type of work order;

[0028] Step 304: cluster all log word vectors in each type of work order, and summarize the similar words of each type of log word to determine the personnel capability labels required for each type of work order;

[0029] Step 305: Based on the clustering result of step 304, the frequencies of similar words in each type of log words are summed up to obtain the frequency of personnel ability labels, and the weight corresponding to each personnel ability label is obtained according to the proportion of each label frequency in the total word frequency;

[0030] Step 306: Aggregate and remove duplicates of the personnel capability labels obtained from all types of work orders to obtain a personnel capability label set X.

[0031] Optionally, in step S4, the step of creating a personnel profile for each engineering personnel based on the personnel capability tag set X includes:

[0032] Step 401: Calculate basic information of each engineer based on the pre-processed basic information data of the engineers to form an initial information database corresponding to each of the engineers;

[0033] Step 402: perform word segmentation operations on the initial information base of each engineer to obtain the corresponding word segmentation information base;

[0034] Step 403: cluster the word segmentation information base of each engineering staff respectively with the staff capability tag set X as the centroid;

[0035] Step 404: Based on the clustering result of step 403, the frequency of the engineering personnel having each corresponding capability is obtained, that is, if the frequency is greater than 0, it proves that the engineering personnel has this capability label;

[0036] Step 405: The proportion of the frequency of each engineering personnel under the same capability label in the total frequency of all personnel is used as the score of each corresponding engineering personnel having the capability label.

[0037] Optionally, in step S5, the step of comprehensively scoring each candidate engineer includes:

[0038] According to the capability tag set M of the personnel required for the new work order, all engineers with free time are traversed to select the candidate set N with the capability tag set M, and the comprehensive capability score of each person in the candidate set N under the new work order is calculated by the following formula:

[0039]

[0040] Where score(n) is the score of the nth candidate in the candidate set N; m i is the weight corresponding to the i-th capability label in the capability label set M, x i n is the score of the nth candidate with the ith ability label.

[0041] Optionally, the algorithm used for clustering in the method is: density-based DBSCAN clustering algorithm.

[0042] In a second aspect, the present invention provides an intelligent matching and dispatching device for operation and maintenance work orders based on data profiling, and executes the steps of any method described in the first aspect of the present invention, the device comprising:

[0043] The data collection module is used to collect basic information data of engineering personnel and historical work order data, and perform pre-processing;

[0044] A first clustering module is used to cluster the work orders based on the preprocessed historical work order data to obtain clustering results of various types of work orders, including all numbers and cluster information of each type of work order;

[0045] The second clustering module is used to cluster the log word vectors in each type of work order to determine the personnel capability labels and their weights required for each type of work order, thereby obtaining the personnel capability label set X;

[0046] A personnel portrait module is used to perform personnel portraits on each engineering staff based on the personnel capability label set X, and obtain the capability label and corresponding score of each engineering staff;

[0047] The scoring and dispatching module is used to determine the category of a new work order based on the cluster information of various work orders obtained by the second clustering module when a new work order arrives, so as to determine the capability label set M of the personnel required for the new work order, and to comprehensively score each candidate engineering personnel based on the label set M, and finally dispatch the work based on the comprehensive score ranking.

[0048] Optionally, the device further comprises:

[0049] The portrait updating module is used to update the information of the engineer after completing the new work order task into the basic information data of the engineer, and combine the personnel capability tag set X to re-profile the engineer.

[0050] In a third aspect, the present invention provides a terminal, including a processor and a storage medium;

[0051] The storage medium is used to store instructions;

[0052] The processor is used to operate according to the instructions to execute the steps of any one of the methods described in the first aspect of the present invention.

[0053] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any one of the methods described in the first aspect of the present invention.

[0054] The beneficial effects of the present invention are as follows:

[0055] 1. The present invention fully considers and utilizes the basic information data and historical work order data of engineering personnel. Different from the traditional method of only making portraits based on basic information of personnel, the present invention is based on the classification of historical work orders. By mining an effective historical information database, multi-level clustering can form the personnel capability labels required for various types of work orders, and after summarizing, a set of personnel capability labels is obtained to ensure the integrity of the labels and cover all existing work order tasks. At the same time, the complex characteristics of engineering personnel are taken into account, and the historical log data, training data, etc. of the personnel are mined, and clustering is performed to obtain the capability labels and scores of engineering personnel, comprehensively depict the portrait of engineering personnel, and improve the accuracy, practicality and intelligence of the portrait. When dispatching a new work order, the engineering management personnel can quickly obtain the capabilities and weights that the engineering personnel who execute the work order should have, and conduct a comprehensive score based on the portraits of each engineering personnel, so as to provide more reasonable data support for subsequent dispatching decisions, and effectively improve the overall efficiency and accuracy of intelligent matching and dispatching of operation and maintenance work orders.

[0056] 2. The present invention generates personnel capability label sets by means of multi-level clustering, which can effectively avoid the subjective influence of manually defined label sets, realize the regular updating of personnel capability label sets, ensure the integrity and real-time performance of personnel capability label sets, and analyze the work order tasks and historical log data as entry points. Through work order clustering, the capability label sets of required personnel can be automatically identified, thereby providing fast and accurate decision-making for work dispatch. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 It is a flow chart of the intelligent matching and dispatching method of operation and maintenance work orders based on data profiling in the present invention;

[0058] Figure 2 A schematic diagram of the process of generating the personnel capability tag set described in the present invention;

[0059] Figure 3 A schematic diagram of the process of generating the engineering personnel portrait described in the present invention;

[0060] Figure 4 A schematic diagram of the process of scoring and assigning work to each engineering personnel in the present invention;

[0061] Figure 5 This is a structural principle block diagram of the intelligent matching and dispatching device for operation and maintenance work orders based on data profiling in the present invention. DETAILED DESCRIPTION

[0062] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. The embodiments described in the present invention are only part of the embodiments of the present invention, not all of the embodiments. Based on the spirit of the present invention, other embodiments obtained by ordinary technicians in this field without creative work are all within the scope of protection of the present invention.

[0063] Embodiment 1:

[0064] Reference Figure 1 The embodiment of the present invention provides a method for intelligently matching and dispatching operation and maintenance work orders based on data profiling, which specifically includes the following steps:

[0065] S1. Collect basic information data of engineering personnel and historical work order data, and perform pre-processing;

[0066] Specifically, the basic information data collected by this embodiment includes:

[0067] (a) Basic information of engineers in the human resources system, including but not limited to personal information, educational background, years of work experience, years of work experience in the company, job grade, job responsibilities and requirements, skills, skills certificates, work performance, and information on the current location of the engineer, future schedule, etc.;

[0068] (b) Relevant data in the training system, including but not limited to information such as training courses, training time, training content, completion certificates, and professional qualification certificates.

[0069] In this embodiment, the historical work order data collection includes:

[0070] The historical work order data in the work order system, including but not limited to task content, work order creator, work order status, work order type, work order priority, contract list, work order time, precautions, relevant contacts, preparation work, log information, customer feedback, and data archiving; as well as product data in the company's product system, including but not limited to product model, year and month of manufacture, version information, years of field use, and other data.

[0071] Collect all the above information to get the original data set.

[0072] In this embodiment, the collected raw data is preprocessed in the following steps:

[0073] Step 101, clean the collected data: delete spaces, line breaks, exclamation marks and special characters in the text data, and remove duplicate, erroneous, incomplete and redundant data;

[0074] Step 102: Standardize the cleaned data (such as unifying the date and time format, improving data quality and achieving cascading and merging of multi-source data) to form a complete and usable data set.

[0075] S2. Based on the pre-processed historical work order data, cluster the work orders to obtain clustering results of various types of work orders, including all numbers and cluster information of each type of work order;

[0076] Reference Figure 2 In the embodiment of the present invention, the work orders are taken as the analysis objects, and the steps of clustering each work order include:

[0077] Step 201: extracting a dictionary of power engineering operation and maintenance from the content recorded in the preprocessed historical work order data, and segmenting each work order based on the dictionary to obtain a text of the work order after segmentation;

[0078] Step 203: convert the work order words in the word segmentation text of each work order into word vectors one by one;

[0079] Step 204: sum the word vectors involved in each work order to obtain a work order vector corresponding to each work order;

[0080] Step 205: cluster the work order vectors, determine the target cluster to which each work order belongs, and obtain the types of all work orders.

[0081] As an embodiment of the present invention, the specific implementation process of step S2 includes: for all historical work orders and related product information, first use jieba to perform initial word segmentation, then manually check the initial results, and form a professional dictionary in the field of power engineering operation and maintenance after deduplication, and perform final word segmentation based on the dictionary to obtain the text of the work order after word segmentation; according to the obtained word segmentation text, use the word2vec tool to train to obtain a word embedding tool in the field of power engineering operation and maintenance, and then based on the tool, convert the obtained work order word segmentation text into a work word vector, and add the work word vectors involved in each work order to obtain a work order vector; finally, use the density-based DBSCAN clustering algorithm to cluster the obtained work order vectors to obtain all numbers and cluster information of the same type of work orders.

[0082] S3. Cluster the log word vectors in each type of work order to determine the personnel capability labels and their weights required for each type of work order, thereby obtaining the personnel capability label set X.

[0083] Reference Figure 2 In the embodiment of the present invention, the step of obtaining the personnel capability tag set X includes:

[0084] Step 301: extract all logs contained in each type of work order according to all numbers of each type of work order obtained in step S2;

[0085] Step 302: Segment all logs in each type of work order, and remove date words and repeated words;

[0086] Step 303: convert the log word segments in each type of work order into log word vectors one by one, and count the frequency of occurrence and total word frequency of each word in each type of work order;

[0087] Step 304: cluster all log word vectors in each type of work order, and summarize the similar words of each type of log word to determine the personnel capability labels required for each type of work order;

[0088] Step 305: Based on the clustering result of step 304, the frequencies of similar words in each type of log words are summed up to obtain the frequency of personnel ability labels, and the weight corresponding to each personnel ability label is obtained according to the proportion of each label frequency in the total word frequency;

[0089] Step 306: Aggregate and remove duplicates of the personnel capability labels obtained from all types of work orders to obtain a personnel capability label set X.

[0090] As an embodiment of the present invention, the specific implementation process of step S3 includes: based on all the numbers of this type of work order, all the logs contained in this type of work order are found, the log data is also segmented using jieba, and after removing date-related words, modal particles, conjunctions and repeated words, it is converted into a log word vector using word2vec, and the frequency and total frequency of each word are counted, and then the DBSCAN clustering algorithm is used again to cluster the log word vector, summarize similar words, and determine the personnel capability labels required for this type of work order. At the same time, based on the clustering results, the frequencies of similar words are added to obtain the personnel capability label frequencies, and the personnel capability label weights are obtained according to the proportion of each label frequency in the total frequency; finally, the personnel capability labels obtained from all types of work orders are summarized and deduplicated to obtain a personnel capability label set X including the weight W of each personnel capability label.

[0091] S4, based on the personnel capability label set X, a personnel profile is performed for each engineering personnel to obtain the capability label and corresponding score of each engineering personnel;

[0092] Reference Figure 3 In this embodiment, personnel are used as the analysis object, where the total number of engineering personnel is Z, and the steps of creating a personnel profile for each engineering personnel include:

[0093] Step 401: Calculate basic information of each engineer based on the pre-processed basic information data of the engineers to form an initial information database corresponding to each of the engineers;

[0094] Step 402: perform word segmentation operations on the initial information base of each engineer to obtain the corresponding word segmentation information base;

[0095] Step 403: cluster the word segmentation information base of each engineering staff respectively with the staff capability tag set X as the centroid;

[0096] Step 404: Based on the clustering result of step 403, the frequency of the engineering personnel having each corresponding capability is obtained, that is, if the frequency is greater than 0, it proves that the engineering personnel has this capability label;

[0097] Step 405: The proportion of the frequency of each engineering personnel under the same capability label in the total frequency of all personnel is used as the score of each corresponding engineering personnel having the capability label.

[0098] As an embodiment of the present invention, the specific implementation process of step S4 includes: first, summarizing the basic information, historical work orders, user feedback, log content and training records of the engineering personnel to form an initial information database, performing word segmentation operation through jieba to form a word segmentation information database, and then clustering the word segmentation information database using the personnel capability label set X obtained in step S3 as the centroid of the cluster, and obtaining the frequency of the personnel under this capability based on the clustering results. If the frequency is greater than 0, it proves that the personnel has this capability label. Finally, the proportion of the frequency of each personnel under the same capability label in the total frequency of all personnel is the final score x of the capability.

[0099] S5. When a new work order arrives, the category of the new work order is determined according to the cluster information of various work orders obtained in step S2 to determine the capability label set M of the personnel required for the new work order, and each candidate engineering personnel is comprehensively scored based on the label set M, and finally the work is assigned based on the comprehensive score ranking.

[0100] Reference Figure 4 In this embodiment, the process of scoring and assigning work to each engineering personnel includes: first, the new work order is segmented and converted into word vectors, and the DBSCAN clustering algorithm is used to calculate which type of work order the word vector of the new work order belongs to according to the cluster information of each type of work order obtained in step S2. For example, if the type F to which the new work order belongs is calculated, the required personnel capability label set corresponding to the F type work order is used as the capability label set M of the personnel required for the new work order; then, according to the capability label set M of the personnel required for the new work order, all engineering personnel with free time are traversed, and the candidate personnel set N with the capability label set M is screened out, and the comprehensive capability score of each person in the candidate personnel set N under the new work order is calculated by formula (1); finally, the work is assigned based on the score ranking.

[0101]

[0102] Where score(n) is the score of the nth candidate in the candidate set N; m i is the weight corresponding to the i-th capability label in the capability label set M, x i n is the score of the nth candidate with the ith ability label.

[0103] As an embodiment of the present invention, the method of the present invention further comprises the following steps:

[0104] S6. When the engineer completes the new work order task, return to step S4 to achieve real-time update of the engineer portrait, thereby ensuring the speed and accuracy of subsequent work dispatch.

[0105] It should be noted that those skilled in the art can use K-means clustering algorithm, agglomerative hierarchical clustering and / or clustering algorithm based on mixed Gaussian model in clustering at each level in the above steps. However, in order to obtain better technical effects, the embodiment of the present invention adopts hierarchical clustering of each step of the density-based DBSCAN clustering algorithm.

[0106] The beneficial effects of the present invention are as follows:

[0107] 1. The present invention fully considers and utilizes the basic information data and historical work order data of engineering personnel. Different from the traditional method of only making portraits based on basic information of personnel, the present invention is based on the classification of historical work orders. By mining an effective historical information database, multi-level clustering can form the personnel capability labels required for various types of work orders, and after summarizing, a set of personnel capability labels is obtained to ensure the integrity of the labels and cover all existing work order tasks. At the same time, the complex characteristics of engineering personnel are taken into account, and the historical log data, training data, etc. of the personnel are mined, and clustering is performed to obtain the capability labels and scores of engineering personnel, comprehensively depict the portrait of engineering personnel, and improve the accuracy, practicality and intelligence of the portrait. When dispatching a new work order, the engineering management personnel can quickly obtain the capabilities and weights that the engineering personnel who execute the work order should have, and conduct a comprehensive score based on the portraits of each engineering personnel, so as to provide more reasonable data support for subsequent dispatching decisions, and effectively improve the overall efficiency and accuracy of intelligent matching and dispatching of operation and maintenance work orders.

[0108] 2. The present invention generates personnel capability label sets by means of multi-level clustering, which can effectively avoid the subjective influence of manually defined label sets, realize the regular updating of personnel capability label sets, ensure the integrity and real-time performance of personnel capability label sets, and analyze the work order tasks and historical log data as entry points. Through work order clustering, the capability label sets of required personnel can be automatically identified, thereby providing fast and accurate decision-making for work dispatch.

[0109] Embodiment 2:

[0110] like Figure 5 As shown, the present invention provides an intelligent matching and dispatching device for operation and maintenance work orders based on data profiling, the device is used to implement the steps of the method in the above embodiment 1, and the device specifically includes:

[0111] The data collection module is used to collect basic information data of engineering personnel and historical work order data, and perform pre-processing;

[0112] A first clustering module is used to cluster the work orders based on the preprocessed historical work order data to obtain clustering results of various types of work orders, including all numbers and cluster information of each type of work order;

[0113] The second clustering module is used to cluster the log word vectors in each type of work order to determine the personnel capability labels and their weights required for each type of work order, thereby obtaining the personnel capability label set X;

[0114] A personnel portrait module is used to perform personnel portraits on each engineering staff based on the personnel capability label set X, and obtain the capability label and corresponding score of each engineering staff;

[0115] The scoring and dispatching module is used to determine the category of a new work order based on the cluster information of various work orders obtained in the second clustering module when a new work order arrives, so as to determine the capability label set M of the personnel required for the new work order, and to comprehensively score each candidate engineering personnel based on the label set M, and finally dispatch the work based on the comprehensive score ranking.

[0116] Furthermore, the device in this embodiment also includes:

[0117] The portrait updating module is used to update the information of the engineer after completing the new work order task into the basic information data of the engineer, and combine the personnel capability tag set X to re-profile the engineer.

[0118] The intelligent matching and dispatching device for operation and maintenance work orders based on data portraits provided in the embodiment of the present invention and the intelligent matching and dispatching method for operation and maintenance work orders based on data portraits provided in Example 1 are based on the same technical concept, and can produce the beneficial effects as described in Example 1. For the contents not described in detail in this embodiment, please refer to Example 1.

[0119] Embodiment three:

[0120] An embodiment of the present invention provides a terminal, including a processor and a storage medium;

[0121] The storage medium is used to store instructions;

[0122] The processor is used to operate according to the instruction to execute the steps of the method according to any one of the first embodiments.

[0123] Embodiment 4:

[0124] An embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, the steps of any method described in Embodiment 1 are implemented.

[0125] The present disclosure may be a system, a method and / or a computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for causing a processor to implement various aspects of the present disclosure.

[0126] A computer-readable storage medium may be a tangible device that can hold and store instructions used by an instruction execution device. A computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples of computer-readable storage media (a non-exhaustive list) include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, such as a punch card or a raised structure in a groove on which instructions are stored, and any suitable combination of the foregoing. As used herein, a computer-readable storage medium is not to be interpreted as a transient signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., a light pulse through a fiber optic cable), or an electrical signal transmitted through a wire.

[0127] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical fiber transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing / processing device.

[0128] The computer program instructions for performing the operation of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages, such as Smalltalk, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. Computer-readable program instructions may be executed completely on a user's computer, partially on a user's computer, as an independent software package, partially on a user's computer, partially on a remote computer, or completely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., using an Internet service provider to connect via the Internet). In some embodiments, an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), may be customized by utilizing the state information of the computer-readable program instructions, and the electronic circuit may execute the computer-readable program instructions, thereby realizing various aspects of the present disclosure.

[0129] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents, and any modifications or equivalent replacements that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A method for intelligent matching and dispatching of operation and maintenance work orders based on data profiling, characterized in that: The method comprises the following steps: S1. Collect basic information data of engineering personnel and historical work order data, and perform pre-processing; S2. Based on the pre-processed historical work order data, cluster the work orders to obtain clustering results of various types of work orders, including all numbers and cluster information of each type of work order; S3. Cluster the log word vectors in each type of work order to determine the personnel capability labels and their weights required for each type of work order, thereby obtaining the personnel capability label set X. S4, based on the personnel capability label set X, a personnel profile is performed for each engineering personnel to obtain the capability label and corresponding score of each engineering personnel; S5. When a new work order arrives, the category of the new work order is determined according to the cluster information of various work orders obtained in step S2 to determine the capability label set M of the personnel required for the new work order, and each candidate engineering personnel is comprehensively scored based on the label set M, and finally the work is assigned based on the comprehensive score ranking.

2. The intelligent matching and dispatching method for operation and maintenance work orders based on data profiling according to claim 1 is characterized in that: The method further comprises the following steps: S6. When the engineer completes the new work order task, return to step S4 to achieve real-time update of the engineer portrait.

3. The intelligent matching and dispatching method for operation and maintenance work orders based on data profiling according to claim 1 is characterized in that: In step S1, the basic information data of the engineering personnel includes: personal information, educational background, years of work experience, years of work experience in the company, job grade, job responsibilities and requirements, skills, skills certificates, work performance, training courses, training time, training content, completion certificate, professional qualification certificate, current location information of the engineering personnel and / or future schedule; The historical work order data includes the task content of the work order, the creator of the work order, the work order status, the work order type, the work order priority, the contract list, the work order time, precautions, relevant contacts, preparation work, log information, customer feedback, data archive, product model on the work order, production year and month, version information and / or years of field use.

4. The method for intelligent matching and dispatching of operation and maintenance work orders based on data profiling according to claim 3 is characterized in that: In step S1, the preprocessing includes: Step 101, clean the collected data: delete spaces, line breaks, exclamation marks and special characters in the text data, and remove duplicate, erroneous, incomplete and redundant data; Step 102: Standardize the cleaned data to form a complete and usable data set.

5. The method for intelligent matching and dispatching of operation and maintenance work orders based on data profiling according to claim 1 is characterized in that: In step S2, the step of clustering the work orders includes: Step 201: extracting a dictionary of power engineering operation and maintenance from the content recorded in the preprocessed historical work order data, and segmenting each work order based on the dictionary to obtain a text of the work order after segmentation; Step 203: convert the work order words in the word segmentation text of each work order into word vectors one by one; Step 204: sum the word vectors involved in each work order to obtain a work order vector corresponding to each work order; Step 205: cluster the work order vectors, determine the target cluster to which each work order belongs, and obtain the types of all work orders.

6. The intelligent matching and dispatching method for operation and maintenance work orders based on data profiling according to claim 1 is characterized in that: In step S3, the step of obtaining the personnel capability tag set X includes: Step 301: extract all logs contained in each type of work order according to all numbers of each type of work order obtained in step S2; Step 302: Segment all logs in each type of work order, and remove date words and repeated words; Step 303: convert the log word segments in each type of work order into log word vectors one by one, and count the frequency of occurrence and total word frequency of each word in each type of work order; Step 304: cluster all log word vectors in each type of work order, and summarize the similar words of each type of log word to determine the personnel capability labels required for each type of work order; Step 305: Based on the clustering result of step 304, the frequencies of similar words in each type of log words are summed up to obtain the frequency of personnel ability labels, and the weight corresponding to each personnel ability label is obtained according to the proportion of each label frequency in the total word frequency; Step 306: Aggregate and remove duplicates of the personnel capability labels obtained from all types of work orders to obtain a personnel capability label set X.

7. The method for intelligent matching and dispatching of operation and maintenance work orders based on data profiling according to claim 1 or 6, characterized in that: In step S4, the steps of creating a personnel profile for each engineering personnel based on the personnel capability label set X include: Step 401: Calculate basic information of each engineer based on the pre-processed basic information data of the engineers to form an initial information database corresponding to each of the engineers; Step 402: perform word segmentation operations on the initial information base of each engineer to obtain the corresponding word segmentation information base; Step 403: cluster the word segmentation information base of each engineering staff respectively with the staff capability tag set X as the centroid; Step 404: Based on the clustering result of step 403, the frequency of the engineering personnel having each corresponding capability is obtained, that is, if the frequency is greater than 0, it proves that the engineering personnel has this capability label; Step 405: The proportion of the frequency of each engineering personnel under the same capability label in the total frequency of all personnel is used as the score of each corresponding engineering personnel having the capability label.

8. The method for intelligent matching and dispatching of operation and maintenance work orders based on data profiling according to claim 7 is characterized in that: In step S5, the step of comprehensively scoring each candidate engineer includes: According to the capability tag set M of the personnel required for the new work order, all engineers with free time are traversed to select the candidate set N with the capability tag set M, and the comprehensive capability score of each person in the candidate set N under the new work order is calculated by the following formula: Where score(n) is the score of the nth candidate in the candidate set N; m i is the weight corresponding to the i-th capability label in the capability label set M, x i n is the score of the nth candidate with the ith ability label.

9. The intelligent matching and dispatching method for operation and maintenance work orders based on data profiling according to claim 1 is characterized in that: The algorithm used for clustering in the method is: density-based DBSCAN clustering algorithm.

10. A device for intelligently matching and dispatching maintenance work orders based on data profiling, running the method for intelligently matching and dispatching maintenance work orders based on data profiling as claimed in any one of claims 1 to 8, characterized in that: The device includes: The data collection module is used to collect basic information data of engineering personnel and historical work order data, and perform pre-processing; A first clustering module is used to cluster the work orders based on the preprocessed historical work order data to obtain clustering results of various types of work orders, including all numbers and cluster information of each type of work order; The second clustering module is used to cluster the log word vectors in each type of work order to determine the personnel capability labels and their weights required for each type of work order, thereby obtaining the personnel capability label set X; A personnel portrait module is used to perform personnel portraits on each engineering staff based on the personnel capability label set X, and obtain the capability label and corresponding score of each engineering staff; The scoring and dispatching module is used to determine the category of a new work order based on the cluster information of various work orders obtained by the second clustering module when a new work order arrives, so as to determine the capability label set M of the personnel required for the new work order, and to comprehensively score each candidate engineering personnel based on the label set M, and finally dispatch the work based on the comprehensive score ranking.

11. The intelligent matching and dispatching device for operation and maintenance work orders based on data profiling according to claim 10, characterized in that: The device also includes: The portrait updating module is used to update the information of the engineer after completing the new work order task into the basic information data of the engineer, and combine the personnel capability tag set X to re-profile the engineer.

12. A terminal comprising a processor and a storage medium; characterized in that: The storage medium is used to store instructions; The processor is configured to operate according to the instructions to execute the steps of the method according to any one of claims 1-9.

13. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method according to any one of claims 1 to 9 are implemented.

Images