Work order processing method and device, equipment and storage medium

Abstract

The invention relates to a work order processing method and device, equipment and a storage medium. The method comprises the steps of collecting a to-be-processed work order; extracting to-be-processed work order information from the to-be-processed work order; the work order information to be processed is analyzed through a pre-trained work order analysis model, a work order processing result is generated, and the work order processing result comprises the fault type and / or the solving method. According to the method, the to-be-processed work order information in the to-be-processed work order is extracted, the to-be-processed work order information is analyzed, and the work order processing result containing the fault type and / or the solution method is determined, so that automatic analysis and processing of the work order are realized, a traditional manual processing mode is replaced, the labor cost is reduced, and meanwhile, the work order processing speed is increased.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of work order processing, and particularly relates to a work order processing method, device, equipment and storage medium. BACKGROUND

[0002] In daily life and work, as a tool for feeding back problems and demands to obtain technical support, work orders play a crucial role in the research and development, production and actual application stages. However, in the existing work order processing process, the processing of work orders mainly depends on manual operation. After a user submits a work order, relevant staff need to view and process these work orders one by one, which not only requires a large amount of labor cost, but also causes delay in the processing process, especially when facing some urgent or important work orders. If the staff do not process them in time, it may cause unnecessary losses to the user. Therefore, how to improve the work order processing speed is a technical problem to be solved. SUMMARY

[0003] In order to solve the above technical problems, the present disclosure provides a work order processing method, device, equipment and storage medium.

[0004] The first aspect of the embodiment of the present disclosure provides a work order processing method, which comprises:

[0005] collecting work orders to be processed;

[0006] extracting work order information to be processed from the work orders to be processed;

[0007] analyzing the work order information to be processed by using a pre-trained work order analysis model to generate a work order processing result, wherein the work order processing result comprises a fault type and / or a solution method.

[0008] The second aspect of the embodiment of the present disclosure provides a work order processing device, which comprises:

[0009] a work order collection module configured to collect work orders to be processed;

[0010] an information extraction module configured to extract work order information to be processed from the work orders to be processed;

[0011] an analysis module configured to analyze the work order information to be processed by using a pre-trained work order analysis model to generate a work order processing result, wherein the work order processing result comprises a fault type and / or a solution method.

[0012] The third aspect of the embodiment of the present disclosure provides a computer device comprising a memory and a processor, and a computer program, wherein the memory stores the computer program, and when the computer program is executed by the processor, the work order processing method of the first aspect is implemented.

[0013] A fourth aspect of the embodiments of the present disclosure provides a computer-readable storage medium, and the computer-readable storage medium stores a computer program. When the computer program is executed by a processor, the computer program implements the work order processing method of the first aspect.

[0014] Compared with the prior art, the technical solutions provided by the embodiments of the present disclosure have the following advantages:

[0015] In the work order processing method, device, equipment and storage medium provided by the embodiments of the present disclosure, the work order to be processed is collected, the work order information to be processed is extracted from the work order to be processed, the work order information to be processed is analyzed by the pre-trained work order analysis model, and the work order processing result is generated. The work order processing result includes the fault type and / or the solution method. The work order information to be processed in the work order to be processed can be extracted and analyzed, the work order processing result containing the fault type and / or the solution method is determined, the automatic workflow from work order collection, data extraction to work order processing is realized, the traditional manual processing mode is replaced, the labor cost is reduced, the work order processing speed is improved, and errors caused by manual processing are effectively avoided. BRIEF DESCRIPTION OF DRAWINGS

[0016] The accompanying drawings, which are incorporated into and form part of the specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the disclosure.

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure or the prior art, the accompanying drawings needed to be used in the embodiments or prior art description will be briefly introduced. Obviously, for those skilled in the art, other drawings can also be obtained from these drawings without creative labor.

[0018] Figure 1 is a flowchart of a work order processing method provided by the embodiments of the present disclosure;

[0019] Figure 2 is a flowchart of a method for extracting work order information to be processed provided by the embodiments of the present disclosure;

[0020] Figure 3 is a flowchart of a method for training a work order analysis model provided by the embodiments of the present disclosure;

[0021] Figure 4 is a flowchart of a method for optimizing a work order analysis model provided by the embodiments of the present disclosure;

[0022] Figure 5 is a structural schematic diagram of a work order processing device provided by the embodiments of the present disclosure;

[0023] Figure 6This is a schematic diagram of the structure of a computer device provided in an embodiment of this disclosure. Detailed Implementation

[0024] To better understand the above-mentioned objectives, features, and advantages of this disclosure, the solutions disclosed herein will be further described below. It should be noted that, unless otherwise specified, the embodiments and features described herein can be combined with each other.

[0025] Numerous specific details are set forth in the following description in order to provide a full understanding of this disclosure, but this disclosure may also be implemented in other ways different from those described herein; obviously, the embodiments in the specification are only some, and not all, of the embodiments of this disclosure.

[0026] It should be understood that the steps described in the method embodiments of this disclosure may be performed in different orders and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit the steps shown. The scope of this disclosure is not limited in this respect.

[0027] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0028] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0029] As described in the background section, existing work order processing workflows often involve staff reviewing and processing each work order individually. This can lead to delays and extended response times, impacting production efficiency and customer satisfaction. Manual intervention and tedious manual operations can also increase processing errors and labor intensity. Furthermore, work orders from different departments or teams may not flow smoothly in terms of data and workflow, resulting in inconsistencies and reduced processing efficiency.

[0030] In view of this, this disclosure provides a work order processing method. Figure 1This is a flowchart of a work order processing method provided in an embodiment of this disclosure, which can be executed by a work order processing device. Figure 1 As shown, the work order processing method provided in this embodiment includes the following steps:

[0031] S101. Collect pending work orders.

[0032] In this embodiment of the disclosure, the work order processing device can continuously monitor and collect pending work orders from different sources through preset interfaces, such as application programming interfaces (APIs) and web forms. It assigns a unique identifier to each received pending work order, and stores the unique identifier, the pending work order, and other related information such as source information. For example, these pending work orders can be filled out and uploaded by staff of various departments or product users according to preset work order templates when they encounter problems, or they can be automatically generated and reported by the device when it detects abnormal situations. There is no limitation here.

[0033] In one exemplary embodiment of the present disclosure, when a work order processing device collects multiple work orders to be processed at the same time, it can sort the work orders to be processed according to their urgency, so that the work orders to be processed can be processed sequentially based on the sorting.

[0034] S102. Extract the information of the pending work orders from the pending work orders.

[0035] In this embodiment of the disclosure, the work order processing device can extract the work order information from the work orders after collecting them, based on preset information extraction rules. Specifically, the work order processing device can use Natural Language Processing (NLP) technology to identify information such as text, numbers, and dates in the work orders to be processed, and perform operations such as keyword detection, semantic analysis, entity recognition, and topic modeling on the identified text information to determine the key text information, and identify the key text information, numbers, and dates as the work order information to be processed.

[0036] In one exemplary embodiment of the present disclosure, the work order processing device can convert the work order information to be processed into a format suitable for subsequent processing and analysis after extracting the work order information to be processed, such as converting key text information into numerical data and performing feature encoding.

[0037] S103. Analyze the work order information to be processed using a pre-trained work order analysis model to generate work order processing results, which include fault type and / or solution.

[0038] The work order analysis model in this embodiment can be understood as a model with fault prediction and classification capabilities. Specifically, it can be a machine learning model using machine learning algorithms such as decision tree, support vector machine or random forest, or a deep learning model, without limitation.

[0039] In this embodiment of the disclosure, after extracting the work order information to be processed, the work order processing device can input the work order information to be processed into a pre-trained work order analysis model. The work order analysis model performs deep analysis and pattern matching on the work order information to be processed, generates and outputs the work order processing result including the fault type and / or solution. Then, based on the source information of the work order to be processed that has been recorded in advance, the work order processing result is returned to the corresponding personnel or equipment through a preset interface (such as email, SMS, system notification, etc.).

[0040] This embodiment of the disclosure collects pending work orders, extracts pending work order information from them, analyzes the pending work order information using a pre-trained work order analysis model, and generates work order processing results. The work order processing results include fault types and / or solutions. It can extract pending work order information from pending work orders, analyze the pending work order information, and determine work order processing results containing fault types and / or solutions. This realizes an automated workflow from work order collection and data extraction to work order processing, replacing the traditional manual processing method, reducing labor costs, increasing work order processing speed, and effectively avoiding errors caused by manual processing.

[0041] Figure 2 This is a flowchart of a method for extracting work order information to be processed according to an embodiment of this disclosure, such as... Figure 2 As shown, based on the above embodiments, the work order information to be processed can be extracted by the following method, wherein the work order information to be processed includes fault information and / or log information.

[0042] S201. Extract fault information from the work order to be processed based on preset keywords. The fault information includes at least one of fault description information, fault occurrence time, and fault vehicle identification.

[0043] In this embodiment of the disclosure, the work order processing device can perform keyword matching on the information contained in the work order to be processed based on preset keywords related to fault description information, fault occurrence time, and fault vehicle identification, to obtain fault information including at least one of fault description information, fault occurrence time, and fault vehicle identification.

[0044] S202. When the fault information includes the fault occurrence time and the fault vehicle identifier, search the preset database for the log information of the vehicle corresponding to the fault vehicle identifier at the fault occurrence time.

[0045] The preset database in this embodiment can be understood as a database used to store log information generated by the vehicle during operation.

[0046] In this embodiment of the disclosure, after extracting the fault information from the work order to be processed, the work order processing device can, when the fault information includes the fault occurrence time and the fault vehicle identifier, search for the log information of the vehicle corresponding to the fault vehicle identifier in a preset database at the time of the fault occurrence based on the fault vehicle identifier, and determine the extracted fault information and / or log information as the work order information to be processed.

[0047] In one exemplary embodiment of this disclosure, the work order processing device can first search for the log information of the vehicle corresponding to the faulty vehicle identifier in a preset database based on the faulty vehicle identifier, and then extract the log information recorded within a preset time period before and after the fault occurred from the log information of the vehicle corresponding to the faulty vehicle identifier.

[0048] This embodiment of the disclosure extracts fault information from work orders to be processed based on preset keywords. The fault information includes at least one of fault description information, fault occurrence time, and fault vehicle identification. When the fault information includes fault occurrence time and fault vehicle identification, the log information of the vehicle corresponding to the fault vehicle identification at the time of fault occurrence is searched in a preset database based on the fault vehicle identification. Keywords can be set according to needs, thereby improving the accuracy of extracting information from work orders to be processed. At the same time, the automatic acquisition of fault log information is realized, which facilitates the subsequent determination of work order processing results based on fault log information and improves the accuracy of work order processing.

[0049] In some embodiments of this disclosure, S103 includes: extracting and filtering features from the work order information to be processed to obtain the features of the work order to be processed; analyzing the features of the work order to be processed through a work order analysis model to generate the work order processing result.

[0050] Specifically, after extracting the work order information from the work orders to be processed, the work order processing device can convert the work order information into feature vectors, and then perform feature filtering on the feature vectors. Specifically, redundant features or features that are not related to the fault type and solution can be removed by statistical methods, and features that have an important impact on the prediction of fault type and solution can be retained. These features are then identified as work order features to be processed. The filtered work order features are then input into a pre-trained work order analysis model, which analyzes the work order features to be processed and generates work order processing results.

[0051] Optionally, the work order processing device can perform data cleaning on the work order information to be processed before converting it into feature vectors. Specifically, this may include removing duplicate data, handling missing values, and handling outliers. Then, feature extraction and feature filtering are performed on the cleaned work order information to be processed. The filtered work order features are then input into the work order analysis model to obtain the work order processing results. This can further improve the speed and accuracy of work order processing, thereby enhancing user satisfaction.

[0052] Figure 3 This is a flowchart of a method for training a work order analysis model provided in an embodiment of this disclosure, such as... Figure 3 As shown, based on the above embodiments, the work order analysis model can be trained using the following method.

[0053] S301. Extract historical work order information and historical processing results from the pre-acquired historical work orders.

[0054] In this embodiment of the disclosure, historical work orders can be understood as work orders that have been processed. In addition to historical work order information, historical work orders also include historical processing results of historical work orders. The historical processing results are confirmed and accurate processing results. For example, historical work orders may be those that were manually analyzed and processed by staff before the work order processing system was enabled, and the processing results were written into the work order.

[0055] In this embodiment of the disclosure, the work order processing device can extract historical work order information and historical processing results from a large number of pre-acquired historical work orders. The method for extracting historical work order information is the same as that for extracting work order information to be processed. Historical processing results can be extracted from preset locations in historical work orders or by detecting keywords related to the processing results.

[0056] S302. Extract and filter features from historical work order information to obtain historical work order features.

[0057] In this embodiment of the disclosure, the work order processing device can extract historical work order information and historical processing results from historical work orders, and then perform feature extraction and feature filtering on the historical work order information to obtain historical work order features.

[0058] In one exemplary embodiment of this disclosure, after extracting historical work order information and historical processing results from historical work orders, the work order processing device first performs data cleaning on the historical work order information and historical processing results, and then performs feature extraction and feature filtering on the cleaned historical work order information to obtain historical work order features. The cleaning method is the same as the method used to clean the work order information to be processed.

[0059] S303. For each historical work order feature, determine the training label of the historical work order feature based on the historical processing results associated with the historical work order feature, classify each historical work order feature according to the training label, and construct a training dataset based on the classification results.

[0060] The training dataset in this embodiment may include historical work order features and their corresponding training labels, wherein the training labels are used to represent different fault types or solutions and can be set according to business needs.

[0061] In this embodiment of the disclosure, the work order processing device can determine the historical processing results associated with each historical work order feature, then obtain pre-set training labels, determine the fault type training labels and solution training labels corresponding to the historical processing results associated with each historical work order feature, classify each historical work order feature according to the training labels, group historical work order features with the same fault type training labels and solution training labels into a group, add the corresponding fault type training labels and solution training labels, and then construct a training dataset based on the classification results.

[0062] S304. Train the pre-built work order analysis model based on the training dataset to obtain the pre-trained work order analysis model.

[0063] In this embodiment of the disclosure, the work order processing device can train a pre-built work order analysis model after the training dataset is constructed. Specifically, the architecture and parameters of the work order analysis model can be initialized according to a pre-selected machine learning algorithm. The historical work order features in the training dataset are input into the work order analysis model, and the output results of the work order analysis model are compared with the training labels. The loss value is calculated based on a preset loss function, and the parameters of the work order analysis model are updated based on the loss value using a model optimization method, such as stochastic gradient descent, to obtain a pre-trained work order analysis model.

[0064] In one exemplary embodiment of this disclosure, the work order processing device can update the parameters of the work order analysis model based on a preset loss function, so that the loss value of the work order analysis model is less than or equal to a preset loss threshold. After the model is initially trained, at least one of the accuracy, recall, and precision of the trained work order analysis model is further evaluated, and the parameters of the trained work order analysis model are adjusted according to the evaluation results until the trained work order analysis model meets the preset evaluation conditions. Specifically, a pre-constructed test dataset can be used to test the work order analysis model. At least one of the accuracy, recall, and precision of the work order analysis model is calculated based on the model output results and the test labels in the test dataset. The calculation results are compared with the preset evaluation threshold to determine whether the work order analysis model meets the preset evaluation conditions. If it does, the work order analysis model is determined to be trained successfully; otherwise, the parameters of the trained work order analysis model are adjusted according to the evaluation results until the trained work order analysis model meets the preset evaluation conditions. The method for constructing the test dataset can be the same as that for the training dataset, and will not be described in detail here.

[0065] This embodiment of the disclosure extracts historical work order information and historical processing results from pre-acquired historical work orders, performs feature extraction and feature filtering on the historical work order information to obtain historical work order features. For each historical work order feature, a training label is determined based on the historical processing results associated with the historical work order feature. Each historical work order feature is then classified according to the training label. A training dataset is constructed based on the classification results. The pre-constructed work order analysis model is trained based on the training dataset to obtain a pre-trained work order analysis model. This can improve the accuracy of model prediction and replace the traditional manual processing method to achieve automatic processing of work orders.

[0066] Figure 4 This is a flowchart of a method for optimizing a work order analysis model provided in an embodiment of this disclosure, such as... Figure 4 As shown, based on the above embodiments, the work order analysis model can be optimized using the following methods.

[0067] S401. Collect user feedback on the results of work order processing.

[0068] In this embodiment of the disclosure, after the work order analysis model is trained, the work order processing device uses the trained work order analysis model to analyze the work order information extracted from the work order to be processed, determines the work order processing result of the work order to be processed, and returns the work order processing result to the corresponding personnel or equipment. The corresponding personnel or equipment can repair the fault according to the work order processing result, and package the repair result into feedback information for reporting. The work order processing device will collect the feedback information reported by these users.

[0069] In one exemplary embodiment of this disclosure, the work order processing device can associate the feedback information collected from the user regarding the work order processing result with the original work order to be processed.

[0070] S402. When the feedback information is of the target feedback type, send the work order to be processed to the work order processing platform and obtain the corrected work order processing result from the work order processing platform. The target feedback type is used to indicate that the work order processing result needs to be corrected.

[0071] The target feedback type in this embodiment is used to characterize that the fault has not been successfully repaired and the work order processing result needs to be corrected.

[0072] In this embodiment, after collecting user feedback on work order processing results, the work order processing device can determine the feedback type. If the feedback is the target feedback type, it sends the corresponding pending work order to the work order processing platform. This allows relevant staff to receive the pending work order through the work order processing platform, analyze and process it, determine the corrected work order processing result, and upload the corrected result back to the platform. After detecting that the corrected result has been updated on the platform, the work order processing device obtains the corrected result and feeds it back to the user or device that reported the pending work order.

[0073] S403. Based on the work order information to be processed and the corrected work order processing results, the work order analysis model is incrementally learned to obtain the optimized work order analysis model.

[0074] In this embodiment of the disclosure, after obtaining the corrected work order processing result, the work order processing device can use the corrected work order processing result and the work order information extracted from the corresponding work order to be processed as incremental data, input them into the work order analysis model for training, and fine-tune the model parameters based on the existing work order analysis model to obtain an optimized work order analysis model.

[0075] This embodiment of the disclosure collects user feedback on work order processing results. When the feedback is of the target feedback type, it sends a work order to be processed to the work order processing platform and obtains the corrected work order processing result from the platform. The target feedback type is used to characterize the work order processing result that needs to be corrected. Based on the work order information to be processed and the corrected work order processing result, the work order analysis model is incrementally learned to obtain an optimized work order analysis model. When the fault cannot be repaired based on the automatically determined work order processing result, the model can provide feedback to the staff and obtain the corrected work order processing result, and integrate the new work order processing result into the model, so that the model can continuously optimize itself and improve the accuracy of predictive analysis of work orders.

[0076] Figure 5 This is a schematic diagram of the structure of a work order processing device provided in an embodiment of this disclosure, as shown below. Figure 5 As shown, the work order processing device 500 includes: a work order collection module 510, an information extraction module 520, and an analysis module 530. The work order collection module 510 is used to collect work orders to be processed; the information extraction module 520 is used to extract work order information from the work orders to be processed; and the analysis module 530 is used to analyze the work order information to be processed using a pre-trained work order analysis model to generate work order processing results, wherein the work order processing results include fault types and / or solutions.

[0077] Optionally, the work order information to be processed includes fault information and / or log information. The information extraction module 520 includes: a first extraction unit, used to extract fault information from the work order to be processed based on preset keywords, wherein the fault information includes at least one of fault description information, fault occurrence time, and fault vehicle identifier; and a first acquisition unit, used to search for the log information of the vehicle corresponding to the fault vehicle identifier at the fault occurrence time in a preset database based on the fault vehicle identifier when the fault information includes the fault occurrence time and the fault vehicle identifier.

[0078] Optionally, the analysis module 530 includes: a second extraction unit, used to extract and filter features from the work order information to be processed, and obtain the features of the work order to be processed; and a model analysis unit, used to analyze the features of the work order to be processed through the work order analysis model, and generate the work order processing result.

[0079] Optionally, the work order processing device 500 further includes a model training module, which includes: a third extraction unit for extracting historical work order information and historical processing results from pre-acquired historical work orders; a fourth extraction unit for performing feature extraction and feature filtering on the historical work order information to obtain historical work order features; a construction unit for determining the training label of each historical work order feature based on the historical processing results associated with the historical work order feature, classifying each historical work order feature according to the training label, and constructing a training dataset based on the classification results; and a training unit for training a pre-constructed work order analysis model based on the training dataset to obtain the pre-trained work order analysis model.

[0080] Optionally, the training unit is specifically used to evaluate at least one of the accuracy, recall, and precision of the trained work order analysis model, and adjust the parameters of the trained work order analysis model according to the evaluation results until the trained work order analysis model meets the preset evaluation conditions.

[0081] Optionally, the work order processing device 500 further includes a model optimization module, which includes: a collection unit for collecting user feedback information on the work order processing result; and a second acquisition unit for sending the work order to be processed to the work order processing platform when the feedback information is a target feedback type, and acquiring the corrected work order processing result from the work order processing platform, wherein the target feedback type is used to characterize the work order processing result that needs to be corrected.

[0082] Optionally, the model optimization module further includes: an optimization unit, used to perform incremental learning on the work order analysis model based on the work order information to be processed and the corrected work order processing result, to obtain an optimized work order analysis model.

[0083] The work order processing device provided in this embodiment can execute the method described in any of the above embodiments. Its execution method and beneficial effects are similar, and will not be repeated here.

[0084] Figure 6 This is a schematic diagram of the structure of a computer device provided in an embodiment of this disclosure.

[0085] like Figure 6 As shown, the computer device may include a processor 610 and a memory 620 storing computer program instructions.

[0086] Specifically, the processor 610 may include a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of this application.

[0087] Memory 620 may include a large-capacity storage for information or instructions. For example, and not limitingly, memory 620 may include a hard disk drive (HDD), a floppy disk drive, flash memory, optical disk, magneto-optical disk, magnetic tape, or a Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, memory 620 may include removable or non-removable (or fixed) media. Where appropriate, memory 620 may be internal or external to the integrated gateway device. In a particular embodiment, memory 620 is a non-volatile solid-state memory. In a particular embodiment, memory 620 includes read-only memory (ROM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (Electrically Programmable ROM, EPROM), an electrically erasable programmable PROM (EEPROM), an electrically alterable ROM (EAROM), or flash memory, or a combination of two or more of these.

[0088] The processor 610 reads and executes computer program instructions stored in the memory 620 to perform the steps of the work order processing method provided in the embodiments of this disclosure.

[0089] In one example, the computer device may also include a transceiver 630 and a bus 640. Wherein, as... Figure 6 As shown, the processor 610, memory 620 and transceiver 630 are connected via bus 640 and communicate with each other.

[0090] Bus 640 may include hardware, software, or both. For example, and not limitingly, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industrial Standard Architecture (ISA) bus, an Infinite Bandwidth Interconnect, a Low Pin Count (LPC) bus, a memory bus, a MicroChannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local Bus (VLB) bus, or other suitable buses, or a combination of two or more of these. Where appropriate, bus 640 may include one or more buses. Although specific buses are described and illustrated in the embodiments of this application, this application considers any suitable bus or interconnection.

[0091] This disclosure also provides a computer-readable storage medium that can store a computer program. When the computer program is executed by a processor, the processor enables the processor to implement the work order processing method provided in this disclosure.

[0092] The aforementioned storage medium may, for example, include a memory 620 containing computer program instructions, which can be executed by the processor 610 of the work order processing device to complete the work order processing method provided in this embodiment. Optionally, the storage medium may be a non-transitory computer-readable storage medium, such as a ROM, random access memory (RAM), compact disc ROM (CD-ROM), magnetic tape, floppy disk, and optical data storage device. The aforementioned computer program may be written in any combination of one or more programming languages ​​to perform the operations of this embodiment. The programming languages ​​include object-oriented programming languages ​​such as Java and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code may be executed entirely on the user's computing device, partially on the user's device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0093] The above description is merely a specific embodiment of this disclosure, enabling those skilled in the art to understand or implement it. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this disclosure. Therefore, this disclosure is not to be limited to the embodiments described herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A work order processing method, characterized in that, The method includes: Collect pending work orders; Extract the work order information from the work orders to be processed; The work order information to be processed is analyzed by a pre-trained work order analysis model to generate work order processing results, which include fault type and / or solution.

2. The method according to claim 1, characterized in that, The pending work order information includes fault information and / or log information. Extracting the pending work order information from the pending work orders includes: Fault information is extracted from the work order to be processed based on preset keywords. The fault information includes at least one of fault description information, fault occurrence time, and fault vehicle identification. When the fault information includes the fault occurrence time and the fault vehicle identifier, the log information of the vehicle corresponding to the fault vehicle identifier at the fault occurrence time is searched in a preset database based on the fault vehicle identifier.

3. The method according to claim 1, characterized in that, The step of analyzing the work order information to be processed using a pre-trained work order analysis model to generate work order processing results includes: The features of the work orders to be processed are obtained by performing feature extraction and feature filtering on the work order information to be processed; The work order analysis model is used to analyze the characteristics of the work order to be processed, and the work order processing result is generated.

4. The method according to claim 1, characterized in that, The work order analysis model was trained based on the following steps: Extract historical work order information and historical processing results from pre-acquired historical work orders; Feature extraction and feature filtering are performed on the historical work order information to obtain historical work order features; For each historical work order feature, a training label for the historical work order feature is determined based on the historical processing results associated with the historical work order feature, and each historical work order feature is classified according to the training label. A training dataset is constructed based on the classification results. The pre-built work order analysis model is trained based on the training dataset to obtain the pre-trained work order analysis model.

5. The method according to claim 4, characterized in that, The training of the pre-built work order analysis model based on the training dataset includes: The accuracy, recall, and precision of the trained work order analysis model are evaluated, and the parameters of the trained work order analysis model are adjusted according to the evaluation results until the trained work order analysis model meets the preset evaluation conditions.

6. The method according to claim 1, characterized in that, After analyzing the work order information to be processed using a pre-trained work order analysis model and generating work order processing results, the method further includes: Collect user feedback on the processing results of the work orders; When the feedback information is of the target feedback type, the work order to be processed is sent to the work order processing platform, and the corrected work order processing result is obtained from the work order processing platform. The target feedback type is used to indicate that the work order processing result needs to be corrected.

7. The method according to claim 6, characterized in that, After obtaining the corrected work order processing result from the work order processing platform, the method further includes: Based on the work order information to be processed and the corrected work order processing results, the work order analysis model is incrementally learned to obtain an optimized work order analysis model.

8. A work order processing device, characterized in that, include: The work order collection module is used to collect work orders that need to be processed. The information extraction module is used to extract the information of the work order to be processed from the work order to be processed; The analysis module is used to analyze the work order information to be processed through a pre-trained work order analysis model and generate work order processing results, which include fault type and / or solution.

9. A computer device, characterized in that, include: Memory; processor; And a computer program; wherein the computer program is stored in the memory and configured to be executed by the processor to implement the method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The storage medium stores a computer program that, when executed by a processor, implements the method as described in any one of claims 1-7.

Images