Invalid work order identification method and device, storage medium and electronic device
By combining the rule identification module and the model identification module in the work order identification system, the problem of difficulty in identifying invalid work orders in the prior art is solved, and the fault diagnosis efficiency is improved and after-sales cost is reduced.
Patent Information
- Application Number
- CN202411387094.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-30
- Publication Date
- 2025-02-11
AI Technical Summary
There is a lack of effective methods in the prior art to identify and filter invalid work orders, resulting in low fault diagnosis efficiency and high after-sales cost.
By receiving the text content of the target work order, the rule recognition module is used to identify and classify invalid work orders based on the keyword matching algorithm and the model recognition module based on the trained work order recognition model.
Effectively identify and filter invalid work orders, improve the quality of fault description and fault diagnosis efficiency, and reduce after-sales costs.
Smart Images
Figure CN119415629A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of data processing technology, and in particular to a method, device, storage medium and electronic device for identifying invalid work orders. Background Art
[0002] At present, the work orders received from users for reporting equipment failures include a large number of invalid work orders. In the field, low-quality work orders, i.e., work orders that do not contain valid fault information, are usually defined as invalid work orders. When users report machine failures, the quality of the fault description affects the effect of fault diagnosis, which in turn indirectly affects the efficiency of after-sales problem solving and after-sales costs. In order to improve the effect of fault diagnosis, it is necessary to identify invalid work orders for filtering, thereby reducing the proportion of invalid work orders.
[0003] Therefore, in the related art, there is a problem of how to identify invalid work orders.
[0004] Regarding the problem of how to identify invalid work orders in related technologies, no effective solution has been proposed yet. Summary of the invention
[0005] The embodiments of the present application provide a method, device, storage medium and electronic device for identifying an invalid work order, so as to at least solve the problem of how to identify an invalid work order in the related art.
[0006] According to an embodiment of the embodiments of the present application, a method for identifying an invalid work order is provided, comprising: receiving a target work order submitted by a target object, inputting the text content of the target work order into a rule recognition module, and obtaining a first recognition result output by the rule recognition module, wherein the rule recognition module identifies the work order based on a keyword matching algorithm; when it is determined that the first recognition result indicates that the target work order is an invalid work order, obtaining a first work order type output by the rule recognition module based on the target work order, wherein the first work order type is used to indicate an invalid work order type; when it is determined that the first recognition result does not indicate that the target work order is an invalid work order, inputting the text content of the target work order into a model recognition module, and obtaining a second recognition result output by the model recognition module, wherein the model recognition module identifies the work order based on a trained work order recognition model; when it is determined that the second recognition result indicates that the target work order is an invalid work order, obtaining a second work order type output by the model recognition module based on the target work order, wherein the second work order type is used to indicate an invalid work order type.
[0007] In an exemplary embodiment, the first recognition result and the first work order type output by the rule recognition module are obtained in the following manner: determining an recognition rule table, wherein the recognition rule table is used to store the correspondence between invalid work order types and keywords; performing string matching on the text content of the target work order, and when it is determined that the string in the text content includes any keyword in the recognition rule table, determining that the first recognition result indicates that the target work order is an invalid work order; determining the target invalid work order type corresponding to the any keyword from the recognition rule table, and determining the target invalid work order type as the first work order type.
[0008] In an exemplary embodiment, before performing string matching on the text content of the target work order, the method further includes: determining text cleaning rules, wherein the text cleaning rules include at least: specific word filtering rules, repeated text filtering rules, similar word replacement rules, and erroneous text correction rules; and performing text cleaning on the text content of the target work order based on the text cleaning rules.
[0009] In an exemplary embodiment, the second recognition result and the second work order type output by the model recognition module are obtained in the following manner: the text content of the target work order is encoded to obtain a text feature vector; the text feature vector is input into the target work order recognition model to obtain the second recognition result and the second work order type output by the work order recognition model, wherein the work order recognition model is trained with the text content of the marked work order as input and whether the work order is an invalid work order and the type of invalid work order as output.
[0010] In an exemplary embodiment, the text content of the marked work order is obtained in the following manner: obtaining the historical work orders submitted by the target object and the processing results of the historical work orders; determining invalid historical work orders from the historical work orders based on the processing results; marking the invalid historical work orders as invalid work orders, classifying the invalid historical work orders, and marking the invalid work order type of the invalid historical work orders based on the classification results corresponding to the invalid historical work orders, to obtain the text content of the marked work orders.
[0011] In an exemplary embodiment, the method further includes: performing statistics on the recognition results of the target work orders according to the rule recognition module and the model recognition module to obtain statistical results, wherein the statistical results include the ratio of invalid work orders to all work orders, and the ratio of each type of invalid work orders to all invalid work orders; when it is determined that the statistical results meet preset conditions, issuing an early warning reminder to the target object.
[0012] In an exemplary embodiment, the embodiment of the present application also provides an invalid work order identification system, including: a data processing module, used to obtain a target work order submitted by a target object, perform string matching on the text content of the target work order, and count the work order identification results; a rule identification module, used to identify whether the target work order is an invalid work order and the type of invalid work order based on a keyword matching algorithm; a model identification module, used to identify whether the target work order is an invalid work order and the type of invalid work order based on a trained work order identification model, wherein the work order identification model is trained with the text content of annotated work orders as input and whether the work order is an invalid work order and the type of invalid work order as output.
[0013] According to another aspect of an embodiment of the present application, there is also provided an apparatus for identifying an invalid work order, including a work order receiving module, configured to receive a target work order submitted by a target object, input the text content of the target work order into a rule identification module, and obtain a first identification result output by the rule identification module, wherein the rule identification module identifies the work order based on a keyword matching algorithm; a first obtaining module, configured to obtain a first work order type output by the rule identification module based on the target work order when it is determined that the first identification result indicates that the target work order is an invalid work order, wherein the first work order type is used to indicate an invalid work order type; a second obtaining module, configured to input the text content of the target work order into a model identification module when it is determined that the first identification result does not indicate that the target work order is an invalid work order, and obtain a second identification result output by the model identification module, wherein the model identification module identifies the work order based on a trained work order identification model; and a third obtaining module, configured to obtain a second work order type output by the model identification module based on the target work order when it is determined that the second identification result indicates that the target work order is an invalid work order, wherein the second work order type is used to indicate an invalid work order type.
[0014] According to another aspect of the embodiments of the present application, a computer-readable storage medium is provided, in which a computer program is stored, wherein the computer program is configured to execute the above-mentioned method for identifying invalid work orders when running.
[0015] According to another aspect of an embodiment of the present application, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the method for identifying invalid work orders through the computer program.
[0016] According to another aspect of the embodiments of the present application, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in any of the above method embodiments are implemented.
[0017] In an embodiment of the present application, a first recognition result is obtained by inputting a target work order submitted by a target object into a rule recognition module. When the first recognition result indicates that the target work order is an invalid work order, a first work order type output by the rule recognition module based on the target work order is obtained. When it is determined that the first recognition result does not indicate that the target work order is an invalid work order, the text content of the target work order is input into a model recognition module to obtain a second recognition result output by the model recognition module. When it is determined that the second recognition result indicates that the target work order is an invalid work order, a second work order type output by the model recognition module based on the target work order is obtained. The above-mentioned technical solution is adopted to solve the problem of how to identify invalid work orders, and then by identifying invalid work orders and invalid work order types, the effect of improving the fault description quality of the work order and improving the fault diagnosis efficiency is achieved. BRIEF DESCRIPTION OF THE DRAWINGS
[0018] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.
[0019] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.
[0020] Figure 1 It is a hardware environment diagram of a method for identifying an invalid work order according to an embodiment of the present application;
[0021] Figure 2 is a flow chart of a method for identifying an invalid work order according to an embodiment of the present application;
[0022] Figure 3 is a schematic diagram of a method for identifying an invalid work order according to an embodiment of the present application;
[0023] Figure 4 It is a structural block diagram of a device for identifying invalid work orders according to an embodiment of the present application. DETAILED DESCRIPTION
[0024] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.
[0025] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application 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 interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.
[0026] According to one aspect of an embodiment of the present application, a method for identifying an invalid work order is provided. Optionally, in this embodiment, the above-mentioned method for identifying an invalid work order can be applied to Figure 1 In the hardware environment composed of the terminal device 102 and the server 104 shown in FIG. Figure 1 As shown, the server 104 is connected to the terminal device 102 via a network, and can be used to provide services (such as application services, etc.) for the terminal or a client installed on the terminal. A database can be set on the server or independently of the server to provide data storage services for the server 104. Cloud computing and / or edge computing services can be configured on the server or independently of the server to provide data computing services for the server 104.
[0027] The network may include but is not limited to at least one of the following: wired network, wireless network. The wired network may include but is not limited to at least one of the following: wide area network, metropolitan area network, local area network, and the wireless network may include but is not limited to at least one of the following: WIFI (Wireless Fidelity), Bluetooth. The terminal device 102 may be but is not limited to a PC, a mobile phone, a tablet computer, a smart air conditioner, a smart range hood, a smart refrigerator, a smart oven, a smart stove, a smart washing machine, a smart water heater, a smart washing device, a smart dishwasher, a smart projection device, a smart TV, a smart clothes drying rack, a smart curtain, a smart audio and video, a smart socket, a smart speaker, a smart fresh air device, a smart kitchen and bathroom device, a smart bathroom device, a smart sweeping robot, a smart window cleaning robot, a smart mopping robot, a smart air purification device, a smart steamer, a smart microwave oven, a smart kitchen treasure, a smart purifier, a smart water dispenser, a smart door lock, etc.
[0028] In this embodiment, a method for identifying an invalid work order is provided, which is applied to the above terminal device. Figure 2 : is a flowchart of a method for identifying an invalid work order according to an embodiment of the present application, and the process includes the following steps:
[0029] Step S202, receiving a target work order submitted by a target object, inputting the text content of the target work order into a rule recognition module, and obtaining a first recognition result output by the rule recognition module, wherein the rule recognition module recognizes the work order based on a keyword matching algorithm;
[0030] Optionally, in the above step S202, the keyword matching algorithm is implemented based on a pre-built keyword dictionary. First, all keywords are converted into a hash table, and then the matching operation of the work order type and the keyword is completed in almost constant time through the hash collision principle, which greatly improves the matching speed.
[0031] Step S204, when it is determined that the first recognition result indicates that the target work order is an invalid work order, obtaining a first work order type output by the rule recognition module based on the target work order, wherein the first work order type is used to indicate an invalid work order type;
[0032] Optionally, in the above step S204, the first recognition result output by the rule recognition module indicates that the target work order is an invalid work order, which means that the rule recognition module matches the keyword corresponding to the invalid work order in the rule table based on the keyword matching algorithm.
[0033] Step S206, when it is determined that the first recognition result does not indicate that the target work order is an invalid work order, input the text content of the target work order into a model recognition module to obtain a second recognition result output by the model recognition module, wherein the model recognition module recognizes the work order based on the trained work order recognition model;
[0034] Optionally, in the above step S204, if the first identification result output by the rule identification module does not indicate that the target work order is an invalid work order, it means that the rule identification module did not match the keyword corresponding to the invalid work order in the rule table based on the keyword matching algorithm, but it cannot be determined that the target work order is a valid work order, and further identification is required by the model identification module.
[0035] Step S208, when it is determined that the second recognition result indicates that the target work order is an invalid work order, obtain a second work order type output by the model recognition module based on the target work order, wherein the second work order type is used to indicate an invalid work order type.
[0036] Through the above steps, the target work order submitted by the target object is input into the rule recognition module to obtain a first recognition result. When the first recognition result indicates that the target work order is an invalid work order, the first work order type output by the rule recognition module based on the target work order is obtained. When it is determined that the first recognition result does not indicate that the target work order is an invalid work order, the text content of the target work order is input into the model recognition module to obtain a second recognition result output by the model recognition module. When it is determined that the second recognition result indicates that the target work order is an invalid work order, the second work order type output by the model recognition module based on the target work order is obtained. The above technical solution is adopted to solve the problem of how to identify invalid work orders, and then by identifying invalid work orders and invalid work order types, the effect of improving the fault description quality of the work order and improving the fault diagnosis efficiency is achieved.
[0037] In an exemplary embodiment, the first recognition result and the first work order type output by the rule recognition module can be obtained in the following manner, specifically including: determining an recognition rule table, wherein the recognition rule table is used to store the correspondence between invalid work order types and keywords; performing string matching on the text content of the target work order, and when it is determined that the string in the text content includes any keyword in the recognition rule table, determining that the first recognition result indicates that the target work order is an invalid work order; determining the target invalid work order type corresponding to the any keyword from the recognition rule table, and determining the target invalid work order type as the first work order type.
[0038] Optionally, in the above embodiment, the corresponding relationship between some rules and invalid work order types may be defined in the rule table, for example, when no content is detected, the work order type is determined to be an invalid work order described as empty.
[0039] Optionally, an example of an identification rule table in the above embodiment is given below, as shown in Table 1:
[0040] Table 1
[0041] Invalid ticket type Pattern Non-fault Machine is normal Service type classification error Unable to install The fault description is not clear Not working Other faults Other faults Description is empty No text detected
[0042] Different rules are used to determine the invalid work order type. For example, if the text contains normal machine text, the corresponding invalid work order type is matched as non-fault. If no text is detected, the corresponding invalid work order type is matched as description empty. Through the above recognition rule table, some easily identifiable and common invalid work orders can be quickly identified without calling the recognition model, which improves the recognition efficiency of invalid work orders.
[0043] In an exemplary embodiment, before executing the above steps to perform string matching on the text content of the target work order, the method also includes: determining text cleaning rules, wherein the text cleaning rules include at least: specific word filtering rules, repeated text filtering rules, similar word replacement rules, and erroneous text correction rules; and performing text cleaning on the text content of the target work order based on the text cleaning rules.
[0044] Optionally, in the above embodiment, the text content of the work order submitted by the user also includes personal information, submission channel and other information. Such information does not need to be analyzed, so it needs to be filtered. The text content of the work order submitted by the user may also include repeated content with similar descriptions or the same description. For this part of the content, it is necessary to perform deduplication processing or replace similar words. The text content of the work order submitted by the user may also contain typos, grammatical errors, etc., and the erroneous content needs to be identified and corrected.
[0045] By preprocessing the text content of the work order, the accuracy and efficiency of rule matching can be improved, thereby improving the recognition efficiency of the work order.
[0046] In an exemplary embodiment, the second recognition result and the second work order type output by the model recognition module can be obtained in the following manner, specifically including: encoding the text content of the target work order to obtain a text feature vector; inputting the text feature vector into the target work order recognition model to obtain the second recognition result and the second work order type output by the work order recognition model, wherein the work order recognition model is trained by taking the text content of the marked work order as input and whether the work order is an invalid work order and the type of invalid work order as output.
[0047] Optionally, in the above embodiment, the text content of the above marked work order indicates whether the work order is invalid. If the work order is an invalid work order, the invalid work order type is further marked.
[0048] In an exemplary embodiment, the text content of the work order marked in the above steps can be obtained in the following manner, specifically including: obtaining the historical work order submitted by the target object and the processing result of the historical work order; determining invalid historical work orders from the historical work orders based on the processing result; marking the invalid historical work order as an invalid work order, classifying the invalid historical work order, and marking the invalid work order type of the invalid historical work order based on the classification result corresponding to the invalid historical work order, to obtain the text content of the marked work order.
[0049] Optionally, in the above embodiment, the historical work orders that have been processed can directly determine whether the work order is valid and the type of invalid work order based on the processing results, so there is no need to additionally annotate training data, thereby improving the training efficiency of the work order recognition model.
[0050] In an exemplary embodiment, the method further includes: performing statistics on the recognition results of the target work orders according to the rule recognition module and the model recognition module to obtain statistical results, wherein the statistical results include the ratio of invalid work orders to all work orders, and the ratio of each type of invalid work orders to all invalid work orders; when it is determined that the statistical results meet preset conditions, issuing an early warning reminder to the target object.
[0051] Optionally, in the above embodiment, the statistical results may also include monitoring of indicators such as the changing trend of the invalid work order rate, the channels of invalid work orders, and the reasons for invalid work orders, which may be adjusted according to actual application requirements. When it is determined that the statistical results meet the preset conditions, an early warning reminder is given to the target object. For example, when it is determined that the ratio of invalid work orders to all work orders is greater than a preset value, an early warning reminder is given to the target object. When the ratio of a certain type of invalid work orders to all invalid work orders is greater than a preset value, an early warning reminder is given to the target object. When any of the above indicators is monitored to be abnormal, an early warning reminder may be given to the target object, so that the target object can take corresponding operational measures to reduce the proportion of invalid work orders.
[0052] In order to better understand the process of the above-mentioned method for identifying invalid work orders, the implementation method flow of the above-mentioned identification of invalid work orders is described below in combination with an optional embodiment, but it is not used to limit the technical solution of the embodiment of the present application.
[0053] In this embodiment, a method for identifying an invalid work order is provided. Figure 3 is a schematic diagram of a method for identifying an invalid work order according to an embodiment of the present application, such as Figure 3 As shown, the data processing module receives the work order submitted by the user, extracts the text content of the work order, cleans the text content to obtain the cleaned text content, and then the data processing module obtains the manually marked invalid work order data and submits it together with the text content to the NLP (Natural Language Processing) model. The rule module of the NLP model (equivalent to the rule module) identifies the work order according to the invalid rules and the dictionary tree. The large model module of the NLP model (equivalent to the model recognition model) performs feature encoding on the text and then performs valid / invalid binary classification recognition. Then, in the case of invalidity, invalid type classification is performed to output the invalid work order type.
[0054] Through the above embodiments, an invalid work order identification and classification system is constructed, which can efficiently and accurately realize the identification and classification of invalid work orders, so as to help equipment operators improve the quality of user fault descriptions through operations, thereby improving fault diagnosis effects.
[0055] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods of each embodiment of the present application.
[0056] Figure 4 is a structural block diagram of an invalid work order identification device according to an embodiment of the present application; Figure 4 As shown, including:
[0057] The work order receiving module 42 is used to receive a target work order submitted by a target object, input the text content of the target work order into a rule recognition module, and obtain a first recognition result output by the rule recognition module, wherein the rule recognition module recognizes the work order based on a keyword matching algorithm;
[0058] A first obtaining module 44 is used to obtain a first work order type output by the rule identification module based on the target work order when it is determined that the first identification result indicates that the target work order is an invalid work order, wherein the first work order type is used to indicate an invalid work order type;
[0059] A second obtaining module 46 is used for inputting the text content of the target work order into a model recognition module to obtain a second recognition result output by the model recognition module when it is determined that the first recognition result does not indicate that the target work order is an invalid work order, wherein the model recognition module recognizes the work order based on the trained work order recognition model;
[0060] The third obtaining module 48 is used to obtain the second work order type output by the model identification module based on the target work order when it is determined that the second identification result indicates that the target work order is an invalid work order, wherein the second work order type is used to indicate an invalid work order type.
[0061] Through the above-mentioned device, a first recognition result is obtained by inputting the target work order submitted by the target object into the rule recognition module. When the first recognition result indicates that the target work order is an invalid work order, a first work order type output by the rule recognition module based on the target work order is obtained. When it is determined that the first recognition result does not indicate that the target work order is an invalid work order, the text content of the target work order is input into the model recognition module to obtain a second recognition result output by the model recognition module. When it is determined that the second recognition result indicates that the target work order is an invalid work order, a second work order type output by the model recognition module based on the target work order is obtained. The above-mentioned technical solution is adopted to solve the problem of how to identify invalid work orders, and then by identifying invalid work orders and invalid work order types, the effect of improving the fault description quality of the work order and improving the fault diagnosis efficiency is achieved.
[0062] In an exemplary embodiment, the above-mentioned first obtaining module 44 is also used to: determine an identification rule table, wherein the identification rule table is used to store the correspondence between invalid work order types and keywords; perform string matching on the text content of the target work order, and when it is determined that the string in the text content includes any keyword in the identification rule table, determine that the first identification result indicates that the target work order is an invalid work order; determine the target invalid work order type corresponding to the any keyword from the identification rule table, and determine the target invalid work order type as the first work order type.
[0063] In an exemplary embodiment, the work order receiving module 42 is further used to: determine text cleaning rules, wherein the text cleaning rules include at least: specific word filtering rules, repeated text filtering rules, similar word replacement rules, and erroneous text correction rules; and perform text cleaning on the text content of the target work order based on the text cleaning rules.
[0064] In an exemplary embodiment, the third obtaining module 48 is also used to: encode the text content of the target work order to obtain a text feature vector; input the text feature vector into the target work order recognition model to obtain the second recognition result and the second work order type output by the work order recognition model, wherein the work order recognition model is trained with the text content of the marked work order as input and whether the work order is an invalid work order and the type of invalid work order as output.
[0065] In an exemplary embodiment, the third obtaining module 48 is also used to: obtain the historical work orders submitted by the target object and the processing results of the historical work orders; determine invalid historical work orders from the historical work orders based on the processing results; mark the invalid historical work orders as invalid work orders, classify the invalid historical work orders, and mark the invalid work order type of the invalid historical work orders based on the classification results corresponding to the invalid historical work orders, and obtain the text content of the marked work orders.
[0066] In an exemplary embodiment, the device also includes: an early warning reminder module, which is used to perform statistics on the recognition results of the target work order according to the rule recognition module and the model recognition module to obtain statistical results, wherein the statistical results include the ratio of invalid work orders to all work orders, and the ratio of each type of invalid work orders to all invalid work orders; when it is determined that the statistical results meet the preset conditions, a early warning reminder is issued to the target object.
[0067] An embodiment of the present application further provides a storage medium, which includes a stored program, wherein the program executes any of the above methods when it is run.
[0068] Optionally, in this embodiment, the storage medium may be configured to store program codes for executing the following steps:
[0069] S1, receiving a target work order submitted by a target object, inputting the text content of the target work order into a rule recognition module, and obtaining a first recognition result output by the rule recognition module, wherein the rule recognition module recognizes the work order based on a keyword matching algorithm;
[0070] S2, when it is determined that the first recognition result indicates that the target work order is an invalid work order, obtaining a first work order type output by the rule recognition module based on the target work order, wherein the first work order type is used to indicate an invalid work order type;
[0071] S3, when it is determined that the first recognition result does not indicate that the target work order is an invalid work order, inputting the text content of the target work order into a model recognition module to obtain a second recognition result output by the model recognition module, wherein the model recognition module recognizes the work order based on a trained work order recognition model;
[0072] S4. When it is determined that the second recognition result indicates that the target work order is an invalid work order, obtain a second work order type output by the model recognition module based on the target work order, wherein the second work order type is used to indicate an invalid work order type.
[0073] An embodiment of the present application further provides an electronic device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.
[0074] Optionally, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.
[0075] Optionally, in this embodiment, the processor may be configured to perform the following steps through a computer program:
[0076] S1, receiving a target work order submitted by a target object, inputting the text content of the target work order into a rule recognition module, and obtaining a first recognition result output by the rule recognition module, wherein the rule recognition module recognizes the work order based on a keyword matching algorithm;
[0077] S2, when it is determined that the first recognition result indicates that the target work order is an invalid work order, obtaining a first work order type output by the rule recognition module based on the target work order, wherein the first work order type is used to indicate an invalid work order type;
[0078] S3, when it is determined that the first recognition result does not indicate that the target work order is an invalid work order, inputting the text content of the target work order into a model recognition module to obtain a second recognition result output by the model recognition module, wherein the model recognition module recognizes the work order based on a trained work order recognition model;
[0079] S4. When it is determined that the second recognition result indicates that the target work order is an invalid work order, obtain a second work order type output by the model recognition module based on the target work order, wherein the second work order type is used to indicate an invalid work order type.
[0080] Optionally, in this embodiment, the above-mentioned storage medium may include but is not limited to: a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and other media that can store program codes.
[0081] An embodiment of the present application further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the steps in any one of the above method embodiments are implemented.
[0082] An embodiment of the present application further provides another computer program product, including a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in any of the above method embodiments are implemented.
[0083] The embodiments of the present application also provide a computer program, which includes computer instructions, which are stored in a computer-readable storage medium; a processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the steps in any one of the above method embodiments.
[0084] Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments and optional implementation modes, and this embodiment will not be described in detail here.
[0085] Obviously, those skilled in the art should understand that the above modules or steps of the present application can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, and optionally, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order from that herein, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present application is not limited to any specific combination of hardware and software.
[0086] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.
Claims
1. A method for identifying an invalid work order, characterized in that: include: Receiving a target work order submitted by a target object, inputting text content of the target work order into a rule recognition module, and obtaining a first recognition result output by the rule recognition module, wherein the rule recognition module recognizes the work order based on a keyword matching algorithm; In the case where it is determined that the first recognition result indicates that the target work order is an invalid work order, obtaining a first work order type output by the rule recognition module based on the target work order, where the first work order type is used to indicate an invalid work order type; In the case where it is determined that the first recognition result does not indicate that the target work order is an invalid work order, inputting the text content of the target work order into a model recognition module to obtain a second recognition result output by the model recognition module, wherein the model recognition module recognizes the work order based on a trained work order recognition model; When it is determined that the second recognition result indicates that the target work order is an invalid work order, a second work order type output by the model recognition module based on the target work order is obtained, wherein the second work order type is used to indicate an invalid work order type.
2. The method for identifying an invalid work order according to claim 1, characterized in that: The first recognition result and the first work order type output by the rule recognition module are obtained in the following manner: Determine an identification rule table, wherein the identification rule table is used to store the correspondence between invalid work order types and keywords; Performing string matching on the text content of the target work order, and determining that the first recognition result indicates that the target work order is an invalid work order when it is determined that the string in the text content includes any keyword in the recognition rule table; Determine a target invalid work order type corresponding to the arbitrary keyword from the identification rule table, and determine the target invalid work order type as a first work order type.
3. The method for identifying an invalid work order according to claim 2, characterized in that: Before performing string matching on the text content of the target work order, the method further includes: Determine text cleaning rules, wherein the text cleaning rules at least include: specific word filtering rules, repeated text filtering rules, similar word replacement rules, and erroneous text correction rules; The text content of the target work order is cleaned based on the text cleaning rule.
4. The method for identifying an invalid work order according to claim 1, characterized in that: The second recognition result and the second work order type output by the model recognition module are obtained in the following manner: Encoding the text content of the target work order to obtain a text feature vector; The text feature vector is input into the target work order recognition model to obtain the second recognition result and the second work order type output by the work order recognition model, wherein the work order recognition model is trained by taking the text content of the marked work order as input and whether the work order is an invalid work order and the type of invalid work order as output.
5. The method for identifying an invalid work order according to claim 4, characterized in that: Get the text content of the marked work order in the following way: Obtaining historical work orders submitted by the target object and processing results of the historical work orders; Determine invalid historical work orders from the historical work orders based on the processing result; The invalid historical work order is marked as an invalid work order, the invalid historical work order is classified, and the invalid work order type of the invalid historical work order is marked based on the classification result corresponding to the invalid historical work order, so as to obtain the text content of the marked work order.
6. The method for identifying an invalid work order according to claim 1, characterized in that: The method further includes: performing statistics on the recognition results of the target work orders according to the rule recognition module and the model recognition module to obtain statistical results, wherein the statistical results include the ratio of invalid work orders to all work orders, and the ratio of each type of invalid work orders to all invalid work orders; When it is determined that the statistical result meets the preset conditions, an early warning reminder is issued to the target object.
7. A system for identifying invalid work orders, characterized in that: include: A data processing module is used to obtain a target work order submitted by a target object, perform string matching on the text content of the target work order, and count the work order recognition results; A rule identification module, used to identify whether the target work order is an invalid work order and the type of invalid work order based on a keyword matching algorithm; A model recognition module is used to identify whether the target work order is an invalid work order and the type of invalid work order based on a trained work order recognition model, wherein the work order recognition model is trained with the text content of the marked work order as input and whether the work order is an invalid work order and the type of invalid work order as output.
8. A device for identifying invalid work orders, characterized in that: include: A work order receiving module, used for receiving a target work order submitted by a target object, inputting the text content of the target work order into a rule recognition module, and obtaining a first recognition result output by the rule recognition module, wherein the rule recognition module recognizes the work order based on a keyword matching algorithm; A first obtaining module, configured to obtain a first work order type output by the rule identification module based on the target work order when it is determined that the first identification result indicates that the target work order is an invalid work order, wherein the first work order type is used to indicate an invalid work order type; A second obtaining module is used for inputting the text content of the target work order into a model recognition module to obtain a second recognition result output by the model recognition module when it is determined that the first recognition result does not indicate that the target work order is an invalid work order, wherein the model recognition module recognizes the work order based on the trained work order recognition model; The third obtaining module is used to obtain the second work order type output by the model identification module based on the target work order when it is determined that the second identification result indicates that the target work order is an invalid work order, wherein the second work order type is used to indicate an invalid work order type.
9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein the program executes the method described in any one of claims 1 to 7 when executed.
10. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to execute the method according to any one of claims 1 to 7 through the computer program.