Work order allocation method and device based on machine learning algorithm, equipment and medium

Through the work order allocation method based on machine learning algorithms, the work order tasks and staff information are automatically processed, which improves the efficiency and accuracy of work order allocation, and solves the problem of inefficiency of traditional manual allocation methods.

CN118982186APending Publication Date: 2024-11-19BEIJING YOUTEJIE INFORMATION TECH
View PDF 0 Cites 2 Cited by

Patent Information

Application Number
CN202411047768.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-01
Publication Date
2024-11-19

AI Technical Summary

Technical Problem

Traditional work order allocation methods rely on manual experience and workloads, are inefficient and error-prone, and are difficult to meet the growing data volume and business complexity needs of enterprises.

Method used

The work order allocation method based on machine learning algorithm is adopted to obtain and parse work order task information, obtain staff information in real time, perform feature extraction, and input features into a pre-built machine learning model to automatically allocate work orders.

Benefits of technology

The efficiency, adaptability and accuracy of work order allocation are improved, and the problem of inefficient manual allocation is solved.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118982186A_ABST
    Figure CN118982186A_ABST
Patent Text Reader

Abstract

The invention discloses a work order distribution method and device based on a machine learning algorithm, equipment and a medium. The method comprises the steps of obtaining a current work order allocation task, and performing analysis processing on the current work order allocation task to obtain current work order description information; acquiring current worker information in real time; performing feature extraction on the current work order description information and the current worker information through a preset feature extraction method to obtain current work order description information features and current worker information features; inputting the current work order description information features and the current worker information features into a pre-constructed work order allocation machine learning algorithm model to obtain a current work order allocation result corresponding to the current work order allocation task; and feeding back the current work order distribution result to the user. The problems that the work order is manually distributed mainly according to the experience and workload of workers in a work order distribution mode, the efficiency is low, and errors are prone to occurring are solved, and the efficiency, the adaptability and the accuracy of work order distribution are improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a work order allocation method, device, equipment and medium based on a machine learning algorithm. Background Art

[0002] With the development of information technology, there is more and more work order data in enterprises, and the management and allocation of work orders are also crucial.

[0003] In the process of implementing the present invention, the inventors found that the prior art has the following defects: At present, the traditional work order allocation method mainly relies on manual work, which is inefficient and prone to errors. With the increase in data volume and the increase in business complexity, traditional methods are difficult to meet the needs of enterprise work order allocation. Summary of the invention

[0004] The present invention provides a work order allocation method, device, equipment and medium based on a machine learning algorithm to improve the efficiency, adaptability and accuracy of work order allocation.

[0005] According to one aspect of the present invention, a work order allocation method based on a machine learning algorithm is provided, which includes:

[0006] Obtaining the current work order assignment task, and parsing the current work order assignment task to obtain the current work order description information corresponding to the current work order assignment task;

[0007] Get current staff information in real time;

[0008] By using a preset feature extraction method, feature extraction is performed on the current work order description information and the current staff information respectively to obtain the current work order description information feature and the current staff information feature;

[0009] Inputting the current work order description information features and the current staff information features into a pre-built work order allocation machine learning algorithm model to obtain a current work order allocation result corresponding to the current work order allocation task;

[0010] The current work order allocation result is fed back to the user to complete the allocation task of the current work order.

[0011] According to another aspect of the present invention, a work order allocation device based on a machine learning algorithm is provided, comprising:

[0012] A current work order description information determination module is used to obtain the current work order assignment task, and parse the current work order assignment task to obtain the current work order description information corresponding to the current work order assignment task;

[0013] Current staff information acquisition module, used to obtain current staff information in real time;

[0014] The current work order description information feature and the current staff information feature determination module are used to extract features of the current work order description information and the current staff information respectively through a preset feature extraction method to obtain the current work order description information feature and the current staff information feature;

[0015] A current work order allocation result determination module, used to input the current work order description information features and the current staff information features into a pre-built work order allocation machine learning algorithm model to obtain a current work order allocation result corresponding to the current work order allocation task;

[0016] The current work order allocation result feedback module is used to feed back the current work order allocation result to the user to complete the allocation task of the current work order.

[0017] According to another aspect of the present invention, there is provided an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the work order allocation method based on a machine learning algorithm as described in any embodiment of the present invention is implemented.

[0018] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the work order allocation method based on a machine learning algorithm described in any embodiment of the present invention when executed.

[0019] The technical solution of the embodiment of the present invention obtains the current work order assignment task and parses the current work order assignment task to obtain the current work order description information corresponding to the current work order assignment task; obtains the current staff information in real time; extracts the features of the current work order description information and the current staff information respectively through a preset feature extraction method to obtain the features of the current work order description information and the features of the current staff information; inputs the features of the current work order description information and the features of the current staff information into a pre-built work order assignment machine learning algorithm model to obtain the current work order assignment result corresponding to the current work order assignment task; and feeds back the current work order assignment result to the user to complete the current work order assignment task. The problem that the work order assignment method mainly manually assigns work orders based on the experience and workload of the staff is inefficient and prone to errors is solved, and the efficiency, adaptability and accuracy of work order assignment are improved.

[0020] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in 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 creative work.

[0022] Figure 1 is a flow chart of a work order allocation method based on a machine learning algorithm provided according to Embodiment 1 of the present invention;

[0023] Figure 2 is a flowchart of another work order allocation method based on a machine learning algorithm provided according to Embodiment 2 of the present invention;

[0024] Figure 3 It is a structural schematic diagram of a work order allocation device based on a machine learning algorithm provided according to Embodiment 3 of the present invention;

[0025] Figure 4 It is a schematic diagram of the structure of an electronic device provided according to Embodiment 4 of the present invention. DETAILED DESCRIPTION

[0026] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0027] It should be noted that the terms "target", "current", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0028] Embodiment 1

[0029] Figure 1 A flowchart of a work order allocation method based on a machine learning algorithm is provided in Example 1 of the present invention. This embodiment is applicable to the situation of allocating work order allocation tasks. The method can be executed by a work order allocation device based on a machine learning algorithm, and the work order allocation device based on a machine learning algorithm can be implemented in the form of hardware and / or software.

[0030] Correspondingly, such as Figure 1 As shown, the method includes:

[0031] S110: Acquire the current work order assignment task, and parse and process the current work order assignment task to obtain current work order description information corresponding to the current work order assignment task.

[0032] The current work order allocation task may be a task that needs to be allocated to the current work order, and the current work order description information may be obtained by parsing the current work order allocation task.

[0033] In this embodiment, one or more current work order allocation tasks may be acquired, and current work order description information corresponding to each current work order allocation task may be acquired, so as to perform work order allocation processing.

[0034] Specifically, the current work order description information may include the current work order type, the current work order description details, the current work order processing time, the current work order priority, and the current work order submission time.

[0035] S120. Obtain current staff information in real time.

[0036] The current staff information may be information describing the current staff from different aspects. Specifically, the current staff information may include current staff skills, current work experience and current workload time.

[0037] S130. Perform feature extraction on the current work order description information and the current staff information respectively through a preset feature extraction method to obtain features of the current work order description information and features of the current staff information.

[0038] The current work order description information feature may be a description feature obtained by extracting features from the current work order description information. The current staff member information feature may be a description feature obtained by extracting features from the current staff member information.

[0039] Exemplarily, when the work order allocation system based on the machine learning algorithm is turned on, it is assumed that three current work order allocation tasks can be received, and the current work order allocation tasks are parsed respectively to obtain the current work order description information.

[0040] In detail, the current work order description information 1: The current work order type is network failure; the current work order description details are unable to connect to the Internet; the current work order processing time is 2 hours; the current work order priority is high; the current work order submission time is 8:00 on June 1, 2024.

[0041] Current work order description information 2: The current work order type is a software issue; the current work order description details are software startup crash; the current work order processing time is 3 hours; the current work order priority is medium; the current work order submission time is 9:00 on June 1, 2024.

[0042] Current work order description information 3: The current work order type is hardware failure; the current work order description details are that the printer cannot print; the current work order processing time is 1 hour; the current work order priority is low; the current work order submission time is 10:00 on June 1, 2024.

[0043] In addition, assume that there are 3 staff members. Specifically, current staff member information 1: current staff member skills are network fault handling and hardware maintenance; current work experience is 5 years; current workload time is 3 hours. Current staff member information 2: current staff member skills are software development and software maintenance; current work experience is 3 years; current workload time is 5 hours. Current staff member information 3: current staff member skills are hardware maintenance and network fault handling; current work experience is 2 years; current workload time is 2 hours.

[0044] Furthermore, feature extraction may be performed on the current work order description information and the current staff information respectively to obtain features of the current work order description information and features of the current staff information.

[0045] Specifically, the preset feature extraction method is used to perform feature extraction on the current work order description information to obtain the current work order description information features, including: performing numerical assignment feature extraction on the current work order type and the current work order priority respectively through the numerical assignment feature extraction method in the feature extraction method to obtain the current work order type feature and the current work order priority feature; performing vectorized feature extraction on the current work order description details through the TF-IDF vectorization method in the feature extraction method to obtain the current work order description details vectorized feature; performing numerical feature extraction on the current work order processing time through the numerical feature extraction method in the feature extraction method to obtain the current work order processing time feature; performing timestamp feature extraction processing on the current work order submission time through the timestamp feature extraction method in the feature extraction method to obtain the current work order submission time feature; wherein the current work order description information features include: current work order type feature, current work order priority feature, current work order description details vectorized feature, current work order processing time feature and current work order submission time feature.

[0046] In this embodiment, different feature extraction methods may be used to extract features from different current work order description information to obtain corresponding features.

[0047] In this embodiment, Table 1 is a detailed description of the characteristics of the current work order description information.

[0048] Table 1

[0049]

[0050] Continuing with the previous example, since the current work order type of the current work order description information 1 is a network failure, the current work order type of the current work order description information 2 is a software problem, and the current work order type of the current work order description information 3 is a hardware failure, the current work order type feature can be obtained through the numerical assignment feature extraction method. Specifically, the current work order type feature corresponding to the current work order type of network failure is 1; the current work order type feature corresponding to the current work order type of software problem is 2; and the current work order type feature corresponding to the current work order type of hardware failure is 3.

[0051] Since the current work order priority of the current work order description information 1 is high, the current work order priority of the current work order description information 2 is medium, and the current work order priority of the current work order description information 3 is low, the current work order priority feature can be obtained by the numerical assignment feature extraction method. Specifically, the current work order priority feature corresponding to the high current work order priority is 3; the current work order priority feature corresponding to the medium current work order priority is 2; and the current work order priority feature corresponding to the low current work order priority is 1.

[0052] Since the current work order description details of the current work order description information 1 are unable to connect to the Internet; the current work order description details of the current work order description information 2 are software startup crashes; and the current work order description details of the current work order description information 3 are printers that cannot print. The TF-IDF vectorization method can be used to extract vectorized features of the current work order description details to obtain the vectorized features of the current work order description details. Specifically, corresponding to the current work order description details, the vectorized features of the current work order description details that can be obtained are [0.2, 0.8], [0.4, 0.6], and [0.1, 0.9] respectively.

[0053] Furthermore, a numerical feature extraction method can be used to extract numerical features of the current work order processing time to obtain the current work order processing time features. Specifically, the obtained current work order processing time features are 2, 3, and 1, respectively.

[0054] Correspondingly, the timestamp feature extraction method can be used to perform timestamp feature extraction on the current work order submission time to obtain the current work order submission time feature. It can be obtained that the current work order submission time is 8:00 on June 1, 2024, and the corresponding current work order submission time feature is 1590998400; the current work order submission time is 9:00 on June 1, 2024, and the corresponding current work order submission time feature is 1591002000; the current work order submission time is 10:00 on June 1, 2024, and the corresponding current work order submission time feature is 1591005600.

[0055] Specifically, the preset feature extraction method is used to extract features of the current staff information to obtain current staff information features; the TF-IDF vectorization method in the feature extraction method is used to extract vectorized features of the current employee skills to obtain current employee skill vectorized features; the numerical feature extraction method in the feature extraction method is used to extract numerical features of the current work experience and the current workload time to obtain current work experience features and current workload time features; wherein the current staff information features include: current employee skill vectorized features, current work experience features and current workload time features.

[0056] In this embodiment, different feature extraction methods may be used to extract features from different pieces of current staff information to obtain corresponding features.

[0057] In this embodiment, Table 2 is a detailed description of the current staff information features.

[0058] Table 2

[0059]

[0060] In this embodiment, the TF-IDF vectorization method in the feature extraction method is used to perform vectorized feature extraction on the current employee skills to obtain the vectorized features of the current employee skills. The vectorized features of the current employee skills corresponding to network fault handling and hardware maintenance can be obtained as [1, 0, 1]; the vectorized features of the current employee skills corresponding to software development and software maintenance can be obtained as [0, 1, 0]; the vectorized features of the current employee skills corresponding to hardware maintenance and network fault handling can be obtained as [1, 0, 1].

[0061] Furthermore, a numerical feature extraction method can be used to extract numerical features of the current work experience and the current workload time, respectively, to obtain current work experience features and current workload time features.

[0062] S140. Input the current work order description information features and the current staff information features into a pre-built work order allocation machine learning algorithm model to obtain a current work order allocation result corresponding to the current work order allocation task.

[0063] Optionally, the current work order description information features and the current staff information features are input into a pre-built work order allocation machine learning algorithm model to obtain a current work order allocation result corresponding to the current work order allocation task, including: performing data cleaning on the current work order description information features and the current staff information features, and performing numerical feature standardization processing on the cleaned current work order priority features, current work order processing time features, current work order submission time features, current work experience features and current workload time features to obtain current standard work order description information features and current standard staff information features; inputting the current standard work order description information features and the current standard staff information features into a pre-built work order allocation machine learning algorithm model to obtain a current work order allocation result corresponding to the current work order allocation task.

[0064] Continuing with the previous example, the current staff information features in Table 1 are cleaned, and the cleaned current work order priority features, current work order processing time features and current work order submission time features are numerically standardized to obtain the current standard work order description information features. The detailed current standard work order description information features are shown in Table 3 below.

[0065] Table 3

[0066]

[0067] Furthermore, the current staff information characteristics in Table 2 are cleaned, and the current work experience characteristics and current workload time characteristics after cleaning are numerically standardized to obtain the current standard staff information characteristics. The detailed current standard staff information characteristics are shown in the following Table 4.

[0068] Table 4

[0069]

[0070] Correspondingly, the current standard work order description information features and the current standard staff information features can be input into the work order allocation machine learning algorithm model to obtain the current work order allocation result corresponding to the current work order allocation task.

[0071] S150: Feedback the current work order allocation result to the user to complete the allocation task of the current work order.

[0072] Continuing with the previous example, assuming that the current work order allocation result can be obtained as the current staff member information 1 according to the current work order description information 1 in the current work order allocation result, it can be fed back to the user.

[0073] The technical solution of the embodiment of the present invention obtains the current work order assignment task and parses the current work order assignment task to obtain the current work order description information corresponding to the current work order assignment task; obtains the current staff information in real time; extracts the features of the current work order description information and the current staff information respectively through a preset feature extraction method to obtain the features of the current work order description information and the features of the current staff information; inputs the features of the current work order description information and the features of the current staff information into a pre-built work order assignment machine learning algorithm model to obtain the current work order assignment result corresponding to the current work order assignment task; and feeds back the current work order assignment result to the user to complete the current work order assignment task. The problem that the work order assignment method mainly manually assigns work orders based on the experience and workload of the staff is inefficient and prone to errors is solved, and the efficiency, adaptability and accuracy of work order assignment are improved.

[0074] Embodiment 2

[0075] Figure 2 A flowchart of another work order allocation method based on a machine learning algorithm is provided for Embodiment 2 of the present invention. This embodiment is optimized based on the above embodiments. In this embodiment, before obtaining the current work order allocation task and parsing the current work order allocation task to obtain the current work order description information corresponding to the current work order allocation task, it also includes training the work order allocation machine learning algorithm model.

[0076] Correspondingly, such as Figure 2 As shown, the method includes:

[0077] S210. Obtain multiple groups of historical work order description information and historical staff information.

[0078] In this embodiment, it can be known that the historical work order description information may include the historical work order type, historical work order description details, historical work order processing time, historical work order priority, and historical work order submission time.

[0079] Similarly, it can be known that historical staff information can include historical employee skills, historical work experience and historical workload time.

[0080] S220. By using the feature extraction method, feature extraction is performed on each historical work order description information and each historical staff member information to obtain features of each historical work order description information and features of each historical staff member information.

[0081] In this embodiment, the historical work order description information features that can be obtained include historical work order type features, historical work order description details quantization features, historical work order processing time features, historical work order priority features and historical work order submission time features.

[0082] Furthermore, historical staff information features may be obtained including historical staff skill quantization features, historical work experience features, and historical workload time features.

[0083] S230, respectively clean the data of each historical work order description information feature and each historical staff member information feature, and perform numerical feature standardization processing on the cleaned historical work order description information feature and each historical staff member information feature to obtain each historical standard work order description information feature and each historical standard staff member information feature.

[0084] In this embodiment, the above-mentioned historical work order type characteristics, historical work order description details quantization characteristics, historical work order processing time characteristics, historical work order priority characteristics, historical work order submission time characteristics, historical employee skill quantization characteristics, historical work experience characteristics and historical workload time characteristics can be cleaned respectively, and the cleaned historical work order processing time characteristics, historical work order priority characteristics, historical work order submission time characteristics, historical work experience characteristics and historical workload time characteristics can be subjected to numerical feature standardization processing to obtain each historical standard work order description information characteristic and each historical standard staff member information characteristic.

[0085] S240. According to a preset sample division ratio, the description information characteristics of each historical standard work order and the information characteristics of each historical standard staff member are divided and processed to obtain a historical training sample set and a historical test sample set.

[0086] Among them, both the historical training sample set and the historical test sample set include the description information features of each historical standard work order and the information features of each historical standard staff member.

[0087] The sample division ratio may be a preset ratio for dividing the sample of each of the historical standard work order description information features and each of the historical standard staff information features. The historical training sample set and the historical test sample set may be obtained by the sample division ratio.

[0088] Specifically, the historical training sample set may be a sample set used to train the work order allocation machine learning algorithm model, and the historical test sample set may be a sample set used to verify the performance of the work order allocation machine learning algorithm model.

[0089] S250. Perform model training on the pre-built initial work order allocation machine learning algorithm model through the historical training sample set, and perform model evaluation on the trained initial work order allocation machine learning algorithm model through the historical test sample set to train the work order allocation machine learning algorithm model.

[0090] Specifically, the method of performing model evaluation on the trained initial work order allocation machine learning algorithm model through a historical test sample set to train the work order allocation machine learning algorithm model includes: performing model evaluation on the trained initial work order allocation machine learning algorithm model through a historical test sample set to respectively calculate the model work order allocation result calculation probability; wherein the model work order allocation result calculation probability includes: the model work order allocation result accuracy, the model work order allocation result precision and the model work order allocation result recall rate; if the model work order allocation result accuracy meets the requirements of a preset accuracy threshold, and the model work order allocation result accuracy meets the requirements of a preset accuracy threshold, and the model work order allocation result recall meets the requirements of a preset recall threshold, then it is determined that the work order allocation machine learning algorithm model is trained.

[0091] In this embodiment, it is necessary to use a historical test sample set to perform model evaluation on the trained initial work order allocation machine learning algorithm model. The model evaluation process can be performed by calculating the accuracy of the model work order allocation result, the precision of the model work order allocation result and the recall rate of the model work order allocation result, and then further comparing them with the accuracy threshold, precision threshold and recall threshold respectively. If the requirements of each threshold are met, it means that the work order allocation machine learning algorithm model has been trained.

[0092] On the contrary, if any one of them does not meet the threshold requirement, it is necessary to optimize the model parameters of the work order allocation machine learning algorithm model, or obtain a new sample set to retrain the work order allocation machine learning algorithm model.

[0093] S260: Acquire the current work order assignment task, and parse and process the current work order assignment task to obtain current work order description information corresponding to the current work order assignment task.

[0094] S270. Obtain current staff information in real time.

[0095] S280. Perform feature extraction on the current work order description information and the current staff information respectively through a preset feature extraction method to obtain features of the current work order description information and features of the current staff information.

[0096] S290. Input the current work order description information features and the current staff information features into a pre-built work order allocation machine learning algorithm model to obtain a current work order allocation result corresponding to the current work order allocation task.

[0097] S2100. Feedback the current work order allocation result to the user to complete the allocation task of the current work order.

[0098] The technical solution of the embodiment of the present invention is to obtain multiple groups of historical work order description information and historical staff information; perform feature extraction on each historical work order description information and each historical staff information respectively through the feature extraction method to obtain the features of each historical work order description information and each historical staff information; perform data cleaning on each historical work order description information feature and each historical staff information feature respectively, and perform numerical feature standardization processing on the cleaned historical work order description information features and each historical staff information features to obtain each historical standard work order description information feature and each historical standard staff information feature; divide and process each historical standard work order description information feature and each historical standard staff information feature according to a preset sample division ratio to obtain a historical training sample set and a historical test sample set; use the historical training sample set to allocate machine learning to a pre-constructed initial work order. The algorithm model is trained, and the model evaluation is performed on the trained initial work order allocation machine learning algorithm model through the historical test sample set to train the work order allocation machine learning algorithm model; the current work order allocation task is obtained, and the current work order allocation task is parsed and processed to obtain the current work order description information corresponding to the current work order allocation task; the current staff information is obtained in real time; the current work order description information and the current staff information are respectively extracted by a preset feature extraction method to obtain the current work order description information feature and the current staff information feature; the current work order description information feature and the current staff information feature are input into the pre-built work order allocation machine learning algorithm model to obtain the current work order allocation result corresponding to the current work order allocation task; the current work order allocation result is fed back to the user to complete the current work order allocation task. A more accurate work order allocation machine learning algorithm model can be trained, which can better allocate work orders and improve the efficiency, adaptability and accuracy of work order allocation.

[0099] Embodiment 3

[0100] Figure 3 The schematic diagram of the structure of a work order distribution device based on a machine learning algorithm provided in the third embodiment of the present invention. The work order distribution device based on a machine learning algorithm provided in this embodiment can be implemented by software and / or hardware, and can be configured in a terminal device or a server to implement a work order distribution method based on a machine learning algorithm in the embodiment of the present invention. Figure 3 As shown, the device includes: a current work order description information determination module 310, a current staff information acquisition module 320, a current work order description information feature and current staff information feature determination module 330, a current work order allocation result determination module 340 and a current work order allocation result feedback module 350.

[0101] The current work order description information determination module 310 is used to obtain the current work order assignment task, and parse the current work order assignment task to obtain the current work order description information corresponding to the current work order assignment task;

[0102] The current staff information acquisition module 320 is used to acquire the current staff information in real time;

[0103] The current work order description information feature and current staff information feature determination module 330 is used to extract features from the current work order description information and the current staff information respectively through a preset feature extraction method to obtain the current work order description information feature and the current staff information feature;

[0104] The current work order allocation result determination module 340 is used to input the current work order description information characteristics and the current staff information characteristics into a pre-built work order allocation machine learning algorithm model to obtain the current work order allocation result corresponding to the current work order allocation task;

[0105] The current work order assignment result feedback module 350 is used to feed back the current work order assignment result to the user to complete the assignment task of the current work order.

[0106] The technical solution of the embodiment of the present invention obtains the current work order assignment task and parses the current work order assignment task to obtain the current work order description information corresponding to the current work order assignment task; obtains the current staff information in real time; extracts the features of the current work order description information and the current staff information respectively through a preset feature extraction method to obtain the features of the current work order description information and the features of the current staff information; inputs the features of the current work order description information and the features of the current staff information into a pre-built work order assignment machine learning algorithm model to obtain the current work order assignment result corresponding to the current work order assignment task; and feeds back the current work order assignment result to the user to complete the current work order assignment task. The problem that the work order assignment method mainly manually assigns work orders based on the experience and workload of the staff is inefficient and prone to errors is solved, and the efficiency, adaptability and accuracy of work order assignment are improved.

[0107] Based on the above embodiments, the current work order description information includes: current work order type, current work order description details, current work order processing time, current work order priority and current work order submission time; wherein, the current staff information includes: current employee skills, current work experience and current workload time.

[0108] On the basis of the above embodiments, the current work order description information feature and current staff information feature determination module 330 can be specifically used for: performing numerical assignment feature extraction on the current work order type and the current work order priority respectively through the numerical assignment feature extraction method in the feature extraction method to obtain the current work order type feature and the current work order priority feature; performing vectorized feature extraction on the current work order description details through the TF-IDF vectorization method in the feature extraction method to obtain the current work order description details vectorized feature; performing numerical feature extraction on the current work order processing time through the numerical feature extraction method in the feature extraction method to obtain the current work order processing time feature; performing timestamp feature extraction processing on the current work order submission time through the timestamp feature extraction method in the feature extraction method to obtain the current work order submission time feature; wherein, the current work order description information features include: current work order type feature, current work order priority feature, current work order description details vectorized feature, current work order processing time feature and current work order submission time feature.

[0109] On the basis of the above embodiments, the current work order description information feature and current staff information feature determination module 330 can be specifically used for: performing vectorized feature extraction on the current employee skills through the TF-IDF vectorization method in the feature extraction method to obtain the current employee skill vectorized feature; performing numerical feature extraction on the current work experience and the current workload time through the numerical feature extraction method in the feature extraction method to obtain the current work experience feature and the current workload time feature; wherein the current staff information features include: the current employee skill vectorized feature, the current work experience feature and the current workload time feature.

[0110] Based on the above embodiments, the current work order assignment result determination module 340 can be specifically used to: perform data cleaning on the current work order description information characteristics and the current staff information characteristics, and perform numerical feature standardization processing on the cleaned current work order priority characteristics, current work order processing time characteristics, current work order submission time characteristics, current work experience characteristics and current workload time characteristics, to obtain current standard work order description information characteristics and current standard staff information characteristics; input the current standard work order description information characteristics and the current standard staff information characteristics into a pre-built work order assignment machine learning algorithm model to obtain the current work order assignment result corresponding to the current work order assignment task.

[0111] On the basis of the above embodiments, it also includes a work order allocation machine learning algorithm model determination module, which can be specifically used for: obtaining multiple groups of historical work order description information and historical staff information before obtaining the current work order allocation task and parsing the current work order allocation task to obtain the current work order description information corresponding to the current work order allocation task; extracting features of each historical work order description information and each historical staff information through the feature extraction method to obtain features of each historical work order description information and features of each historical staff information; cleaning each historical work order description information feature and each historical staff information feature, and extracting the cleaned features of each historical work order description information and each historical staff information feature. Performing standardization processing on numerical features to obtain descriptive information features of each historical standard work order and information features of each historical standard staff member; dividing and processing each historical standard work order descriptive information feature and each historical standard staff member information feature according to a preset sample division ratio to obtain a historical training sample set and a historical test sample set; wherein both the historical training sample set and the historical test sample set include each historical standard work order descriptive information feature and each historical standard staff member information feature; performing model training on a pre-built initial work order allocation machine learning algorithm model through the historical training sample set, and performing model evaluation on the trained initial work order allocation machine learning algorithm model through the historical test sample set to train a work order allocation machine learning algorithm model.

[0112] On the basis of the above embodiments, the work order allocation machine learning algorithm model determination module can also be specifically used to: perform model evaluation on the trained initial work order allocation machine learning algorithm model through a historical test sample set to calculate the model work order allocation result calculation probability respectively; wherein the model work order allocation result calculation probability includes: the model work order allocation result accuracy, the model work order allocation result precision and the model work order allocation result recall rate; if the model work order allocation result accuracy meets the requirements of the preset accuracy threshold, and the model work order allocation result accuracy meets the requirements of the preset accuracy threshold, and the model work order allocation result recall rate meets the requirements of the preset recall threshold, then it is determined that the work order allocation machine learning algorithm model is trained.

[0113] The work order allocation device based on machine learning algorithm provided in the embodiment of the present invention can execute the work order allocation method based on machine learning algorithm provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0114] Embodiment 4

[0115] Figure 4A schematic diagram of the structure of an electronic device 10 that can be used to implement the fourth embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0116] like Figure 4 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0117] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0118] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The processor 11 executes the various methods and processes described above, such as a work order allocation method based on a machine learning algorithm.

[0119] In some embodiments, the work order allocation method based on the machine learning algorithm may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the work order allocation method based on the machine learning algorithm described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute the work order allocation method based on the machine learning algorithm in any other appropriate manner (e.g., by means of firmware).

[0120] The method includes: obtaining a current work order assignment task, and parsing the current work order assignment task to obtain current work order description information corresponding to the current work order assignment task; obtaining current staff information in real time; extracting features of the current work order description information and the current staff information respectively through a preset feature extraction method to obtain current work order description information features and current staff information features; inputting the current work order description information features and the current staff information features into a pre-built work order assignment machine learning algorithm model to obtain a current work order assignment result corresponding to the current work order assignment task; and feeding back the current work order assignment result to a user to complete the current work order assignment task.

[0121] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0122] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0123] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, 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), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0124] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0125] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0126] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0127] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0128] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

[0129] Embodiment 5

[0130] Embodiment 5 of the present invention also provides a computer-readable storage medium, wherein the computer-readable instructions are used to execute a work order assignment method based on a machine learning algorithm when executed by a computer processor, the method comprising: obtaining a current work order assignment task, and parsing the current work order assignment task to obtain current work order description information corresponding to the current work order assignment task; obtaining current staff information in real time; performing feature extraction on the current work order description information and the current staff information respectively through a preset feature extraction method to obtain current work order description information features and current staff information features; inputting the current work order description information features and the current staff information features into a pre-built work order assignment machine learning algorithm model to obtain a current work order assignment result corresponding to the current work order assignment task; and feeding back the current work order assignment result to a user to complete the current work order assignment task.

[0131] Of course, the computer-readable storage medium provided in an embodiment of the present invention has computer executable instructions that are not limited to the method operations described above, and can also execute related operations in the work order allocation method based on machine learning algorithm provided in any embodiment of the present invention.

[0132] Through the above description of the implementation methods, the technicians in the relevant field can clearly understand that the present invention can be implemented by means of software and necessary general hardware, and of course it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, a read-only memory (ROM), a random access memory (RAM), a flash memory (FLASH), a hard disk or an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0133] It is worth noting that in the above-mentioned embodiment of the work order allocation device based on machine learning algorithm, the various units and modules included are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0134] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A work order allocation method based on machine learning algorithm, It is characterized in that include: Obtaining the current work order assignment task, and parsing the current work order assignment task to obtain the current work order description information corresponding to the current work order assignment task; Get current staff information in real time; By using a preset feature extraction method, feature extraction is performed on the current work order description information and the current staff information respectively to obtain the current work order description information feature and the current staff information feature; Inputting the current work order description information features and the current staff information features into a pre-built work order allocation machine learning algorithm model to obtain a current work order allocation result corresponding to the current work order allocation task; The current work order allocation result is fed back to the user to complete the allocation task of the current work order.

2. The method according to claim 1, It is characterized in that The current work order description information includes: the current work order type, the current work order description details, the current work order processing time, the current work order priority and the current work order submission time; The current staff information includes: current staff skills, current work experience and current workload time.

3. The method according to claim 2, It is characterized in that The feature extraction of the current work order description information is performed by a preset feature extraction method to obtain the features of the current work order description information, including: By using the numerical value assignment feature extraction method in the feature extraction method, numerical value assignment feature extraction is performed on the current work order type and the current work order priority respectively to obtain the current work order type feature and the current work order priority feature; Performing vectorized feature extraction on the current work order description details by using the TF-IDF vectorization method in the feature extraction method to obtain vectorized features of the current work order description details; By using the numerical feature extraction method in the feature extraction method, the numerical feature extraction of the current work order processing time is performed to obtain the current work order processing time feature; By using the timestamp feature extraction method in the feature extraction method, the timestamp feature extraction process is performed on the current work order submission time to obtain the current work order submission time feature; Among them, the current work order description information features include: current work order type features, current work order priority features, current work order description details vectorization features, current work order processing time features and current work order submission time features.

4. The method according to claim 3, It is characterized in that The feature extraction method is used to extract features of the current staff information to obtain features of the current staff information; Performing vectorized feature extraction on the current employee skills by using the TF-IDF vectorization method in the feature extraction method to obtain vectorized features of the current employee skills; By using the numerical feature extraction method in the feature extraction method, numerical feature extraction is performed on the current work experience and the current workload time respectively, so as to obtain the current work experience feature and the current workload time feature; The current staff information features include: current staff skill quantization features, current work experience features and current workload time features.

5. The method according to claim 4, It is characterized in that The inputting of the current work order description information features and the current staff information features into a pre-built work order allocation machine learning algorithm model to obtain a current work order allocation result corresponding to the current work order allocation task includes: Data cleaning is performed on the current work order description information characteristics and the current staff information characteristics respectively, and numerical feature standardization is performed on the cleaned current work order priority characteristics, current work order processing time characteristics, current work order submission time characteristics, current work experience characteristics and current workload time characteristics respectively, to obtain current standard work order description information characteristics and current standard staff information characteristics; The current standard work order description information features and the current standard staff information features are input into a pre-built work order allocation machine learning algorithm model to obtain a current work order allocation result corresponding to the current work order allocation task.

6. The method according to claim 5, It is characterized in that Before obtaining the current work order assignment task and parsing the current work order assignment task to obtain the current work order description information corresponding to the current work order assignment task, the method further includes: Get multiple sets of historical work order description information and historical staff information; By using the feature extraction method, feature extraction is performed on each historical work order description information and each historical staff member information respectively to obtain features of each historical work order description information and features of each historical staff member information; Data cleaning is performed on each historical work order description information feature and each historical staff member information feature respectively, and numerical feature standardization is performed on each cleaned historical work order description information feature and each historical staff member information feature to obtain each historical standard work order description information feature and each historical standard staff member information feature; According to the preset sample division ratio, the description information characteristics of each historical standard work order and the information characteristics of each historical standard staff member are divided and processed to obtain a historical training sample set and a historical test sample set; Among them, the historical training sample set and the historical test sample set both include the description information features of each historical standard work order and the information features of each historical standard staff member; The pre-built initial work order allocation machine learning algorithm model is trained through the historical training sample set, and the trained initial work order allocation machine learning algorithm model is evaluated through the historical test sample set to train the work order allocation machine learning algorithm model.

7. The method according to claim 6, It is characterized in that The method of evaluating the trained initial work order allocation machine learning algorithm model by using the historical test sample set to train the work order allocation machine learning algorithm model includes: The trained initial work order allocation machine learning algorithm model is evaluated through the historical test sample set to calculate the probability of the model work order allocation result; The calculation probability of the model work order allocation result includes: the accuracy rate of the model work order allocation result, the precision rate of the model work order allocation result and the recall rate of the model work order allocation result; If the accuracy of the model work order allocation result meets the requirements of the preset accuracy threshold, and the recall rate of the model work order allocation result meets the requirements of the preset recall threshold, it is determined that the work order allocation machine learning algorithm model is trained.

8. A work order distribution device based on machine learning algorithm, It is characterized in that include: A current work order description information determination module is used to obtain the current work order assignment task, and parse the current work order assignment task to obtain the current work order description information corresponding to the current work order assignment task; Current staff information acquisition module, used to obtain current staff information in real time; The current work order description information feature and the current staff information feature determination module are used to extract features of the current work order description information and the current staff information respectively through a preset feature extraction method to obtain the current work order description information feature and the current staff information feature; A current work order allocation result determination module, used to input the current work order description information features and the current staff information features into a pre-built work order allocation machine learning algorithm model to obtain a current work order allocation result corresponding to the current work order allocation task; The current work order allocation result feedback module is used to feed back the current work order allocation result to the user to complete the allocation task of the current work order.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, It is characterized in that When the processor executes the computer program, the work order allocation method based on the machine learning algorithm as described in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, It is characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the work order allocation method based on a machine learning algorithm as described in any one of claims 1-7 when executed.

Citation Information

Cited By

  • Power grid information scheduling disposal work order circulation guiding method and system

    CN121660327A

  • Water supply work order automatic dispatching method

    CN122472436A