Operation and maintenance event management method and device, equipment and storage medium

Abstract

The invention discloses an operation and maintenance event management method and device, equipment and a storage medium, and relates to the technical field of application operation and maintenance. The method is used for managing a corresponding operation and maintenance state in a whole operation and maintenance process after operation and maintenance operation is performed on an operation and maintenance event, and one specific embodiment of the method comprises the following steps: in response to a reported operation and maintenance event monitored by a monitoring operation, performing classification operation on the operation and maintenance event to obtain a classification result; and according to the classification result, performing distribution operation on the operation and maintenance event, and receiving a processing result returned after the operation and maintenance end corresponding to the distribution operation performs processing operation on the operation and maintenance event.

Description

TECHNICAL FIELD

[0001] The present application relates to the application operation and maintenance technical field, and particularly relates to an operation and maintenance event management method and device, equipment and a storage medium. BACKGROUND

[0002] A customer relationship management (CRM) application system generally faces enterprise customers, and the enterprise customers are directly managed by service personnel. Before online application deployment, test environment and pre-release environment verification work is performed; however, due to the particularity of the production environment of the application and increasingly complex business requirements, various problems inevitably occur during online operation of the application. Therefore, operation and maintenance events cause operation and maintenance personnel to consume a lot of energy to maintain and process.

[0003] At present, common operation and maintenance event feedback channels and processing methods are as follows: different operation and maintenance groups are established based on enterprise instant messaging tools for various business logics of the application, and the operation and maintenance groups are used for interface processing. However, the following problems exist: (1) there are too many operation and maintenance groups, and management is disorganized; and (2) instant problem follow-up is not systematic. SUMMARY

[0004] Embodiments of the present application provide an operation and maintenance event management method, device, equipment and storage medium.

[0005] In a first aspect, embodiments of the present application provide an operation and maintenance event management method for managing the corresponding operation and maintenance state in the whole operation and maintenance process after operation and maintenance operation on the operation and maintenance event. The method comprises: in response to the reporting operation and maintenance event being listened to by a listening operation, performing a classification operation on the operation and maintenance event to obtain a classification result; and performing an allocation operation on the operation and maintenance event according to the classification result, and receiving a processing result returned after the operation and maintenance event is processed by an operation and maintenance terminal corresponding to the allocation operation.

[0006] In some embodiments, the classification operation on the operation and maintenance event to obtain the classification result comprises: processing the operation and maintenance event to obtain a first operation and maintenance feature; and performing a classification operation on the first operation and maintenance feature according to a target classification model to obtain a classification result corresponding to the operation and maintenance feature, wherein the target classification model is obtained based on a decision tree.

[0007] In some embodiments, the method further comprises: obtaining an operation and maintenance sample event and a classification label corresponding to the operation and maintenance sample event; processing the operation and maintenance sample event to obtain a second operation and maintenance feature; inputting the second operation and maintenance feature into a decision tree to obtain a classification result; and training the decision tree according to the classification result and the classification label to obtain a target classification model.

[0008] In some embodiments, the method further comprises: obtaining an operation and maintenance attribute of the operation and maintenance sample event; determining information entropy of the operation and maintenance sample event according to the operation and maintenance attribute of the operation and maintenance sample event; and generating the decision tree according to the information entropy of the operation and maintenance sample event.

[0009] In some embodiments, the operation and maintenance sample event is processed to obtain the second operation and maintenance feature, including: processing the operation and maintenance sample event by using a natural language processing algorithm to obtain the second operation and maintenance feature.

[0010] In some embodiments, the operation and maintenance operation further comprises an evaluation operation, and the method further comprises: receiving an evaluation result returned after the evaluation operation on the processing result.

[0011] In a second aspect, embodiments of the present application provide an operation and maintenance event management device for managing an operation and maintenance state corresponding to an operation and maintenance event in a full operation and maintenance process after an operation and maintenance operation on the operation and maintenance event, the device comprising: a listening module configured to listen to the operation and maintenance event; a classification module configured to perform a classification operation on the operation and maintenance event according to a classification result obtained by the listening module; an allocation module configured to perform an allocation operation on the operation and maintenance event according to the classification result; and a processing module configured to receive a processing result returned after a processing operation on the operation and maintenance event by an operation and maintenance terminal corresponding to the allocation operation.

[0012] In some embodiments, the classification module is configured to: process the operation and maintenance event to obtain a first operation and maintenance feature; and perform a classification operation on the first operation and maintenance feature according to a target classification model to obtain a classification result corresponding to the operation and maintenance feature, wherein the target classification model is obtained based on the decision tree.

[0013] In some embodiments, the device further comprises: an obtaining module configured to obtain an operation and maintenance sample event and a classification label corresponding to the operation and maintenance sample event; a obtaining module configured to process the operation and maintenance sample event to obtain a second operation and maintenance feature; an input module configured to input the second operation and maintenance feature into the decision tree to obtain the classification result; and a training module configured to train the decision tree according to the classification result and the classification label to obtain the target classification model.

[0014] In some embodiments, the device further comprises: an obtaining module configured to obtain an operation and maintenance attribute of the operation and maintenance sample event; a determining module configured to determine information entropy of the operation and maintenance sample event according to the operation and maintenance attribute of the operation and maintenance sample event; and a generating module configured to generate the decision tree according to the information entropy of the operation and maintenance sample event.

[0015] In some embodiments, the obtaining module is configured to process the operation and maintenance sample event by using a natural language processing algorithm to obtain the second operation and maintenance feature.

[0016] In some embodiments, the operation further includes: an evaluation operation; and the device further includes: an evaluation module configured to receive an evaluation result returned after the evaluation operation on the processing result.

[0017] In a third aspect, embodiments of the present application provide an electronic device, comprising at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method described in the first aspect.

[0018] In a fourth aspect, embodiments of the present application provide a non-transitory computer-readable storage medium storing computer instructions, and the computer instructions are used to enable a computer to perform the method described in the first aspect.

[0019] In a fifth aspect, embodiments of the present application provide a computer program product comprising a computer program, and the computer program, when executed by a processor, implements the method described in the first aspect.

[0020] The method, device, equipment and storage medium provided by the embodiments of the present application can classify the operation event when the operation event is reported by the listening operation, obtain a classification result, then distribute the operation event according to the classification result, and receive a processing result returned by the operation event after the operation event is processed by the operation end corresponding to the distribution operation, so that the operation event in the whole operation process can be operated according to the listening operation, the classification operation, the distribution operation and the processing operation, and the operation state of the operation event in the whole operation process can be managed after the operation, so that the operation event can be quickly responded, the whole life cycle management can be realized, the operation service can be improved, the operation event has rules to follow, and data support is provided for subsequent operation analysis. BRIEF DESCRIPTION OF DRAWINGS

[0021] Other characteristics, objects and advantages of the present application will become more apparent from the following detailed description of the non-restrictive embodiments, made with reference to the attached drawings:

[0022] Figure 1 is an exemplary system architecture diagram to which the present application can be applied;

[0023] Figure 2 is a flowchart of one embodiment of the operation event management method according to the present application;

[0024] Figure 3 is a flowchart of one embodiment of the operation event management method according to the present application;

[0025] Figure 4 is a schematic diagram of a target classification model;

[0026] Figure 5 is a structural schematic diagram of an embodiment of an operation and maintenance event management platform according to the present application;

[0027] Figure 6 is a structural schematic diagram of an embodiment of an operation and maintenance event management method according to the present application;

[0028] Figure 7 is a structural schematic diagram of an embodiment of an operation and maintenance event management device according to the present application;

[0029] Figure 8 is a structural schematic diagram of an embodiment of an operation and maintenance event management device according to the present application. DETAILED DESCRIPTION

[0030] The present application will be further described below in conjunction with the accompanying drawings and embodiments. It can be understood that the specific embodiments described herein are only used to explain the related application, and not to limit the application. In addition, it should be noted that, for the sake of description, only the parts related to the application are shown in the drawings.

[0031] It should be noted that the embodiments in the present application and the features in the embodiments can be combined with each other without conflict. The present application will be described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.

[0032] Figure 1 An exemplary system architecture 100 to which embodiments of the operation and maintenance event management method and device of the present application can be applied is shown.

[0033] As shown in Figure 1 , the system architecture 100 can include clients 101 and 102, an operation and maintenance end 103, a network 104 and an operation and maintenance event management platform 105. The network 104 is used to provide a communication link medium between the clients 101 and 102 and the operation and maintenance event management platform 105, and between the operation and maintenance event management platform 105 and the operation and maintenance end 103. The network 104 can include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0034] Service personnel can use the clients 101 and 102 to interact with the operation and maintenance event management platform 105 through the network 104, such as reporting operation and maintenance events, etc.

[0035] The operation and maintenance event management platform 105 can manage the whole operation and maintenance process of operation and maintenance events. For example, when the operation and maintenance event management platform 105 listens to an operation and maintenance event, it can perform a classification operation on the operation and maintenance event to obtain a classification result; according to the classification result, it can perform an allocation operation on the operation and maintenance event, and receive a processing result returned by the operation and maintenance end 103 after performing a processing operation on the operation and maintenance event corresponding to the allocation operation.

[0036] It should be noted that the operation and maintenance event management platform 105 can be hardware or software. When the operation and maintenance event management platform 105 is hardware, it can be implemented as a distributed server cluster composed of multiple servers, or as a single server. When the operation and maintenance event management platform 105 is software, it can be implemented as multiple software or software modules (for example, to provide distributed services), or as a single software or software module. No specific limitation is made herein.

[0037] The operation and maintenance terminal 103 can be hardware or software. When the operation and maintenance terminal 103 is hardware, the terminal can be an electronic product that interacts with a user through one or more ways such as a keyboard, a touchpad, a touch screen, a remote control, voice interaction, or a handwriting device, for example, a PC (Personal Computer), a mobile phone, a smart phone, a PDA (Personal Digital Assistant), a wearable device, a PPC (Pocket PC), a tablet computer, a smart car machine, a smart television, a smart speaker, a tablet computer, a laptop computer, and a desktop computer, etc. When the operation and maintenance terminal 103 is software, it can be installed in the above electronic devices. It can be implemented as multiple software or software modules, or as a single software or software module. No specific limitation is made herein.

[0038] It should be noted that the operation and maintenance event management method provided by the embodiments of the present application is generally executed by the operation and maintenance event management platform 105, and accordingly, the operation and maintenance event management apparatus is generally provided in the operation and maintenance event management platform 105.

[0039] It should be understood that Figure 1 The number of terminals, networks, and servers in

[0040] As Figure 2 , a flowchart 200 of one embodiment of the operation and maintenance event management method according to the present application is shown, which can include the following steps:

[0041] Step 201: In response to the reported operation and maintenance event being listened to by the listening operation, performing a classification operation on the operation and maintenance event to obtain a classification result.

[0042] In the present embodiment, the execution subject of the operation and maintenance event management method (for example Figure 1The client 101 and 102 shown) can listen to the service personnel reported operation and maintenance events through the listening operation, and classify the reported operation and maintenance events to obtain the classification result. Here, the above-mentioned listening operation can be a listener installed in the above-mentioned execution subject, and if the listener listens to the service personnel reported operation and maintenance events, the operation and maintenance state of the operation and maintenance event is updated to the initial state. Here, the service personnel is the personnel who performs operation and maintenance docking with the customer using the Customer Relationship Management (CRM) system, for example, a salesperson, which is used to collect, feedback, summarize, report, and other operations of operation and maintenance events. The CRM system includes the fields of clues, business opportunities, contracts, customers, visits, and risk control. The CRM system manages the process promotion between sales and customers. The operation and maintenance event can be any application maintenance related event generated during the customer's use of the CRM system.

[0043] In this embodiment, according to the full operation and maintenance process of the operation and maintenance event, the operation and maintenance event is processed according to the operation and maintenance operation corresponding to each operation and maintenance stage in the full operation and maintenance process, and the processed operation and maintenance state is recorded, thereby realizing the management of the full operation and maintenance process of the operation and maintenance event.

[0044] In one example, the full operation and maintenance process can be a complete operation and maintenance process from the service personnel reporting the operation and maintenance event to the customer feeding back the processing situation of the operation and maintenance event.

[0045] In this embodiment, the full operation and maintenance process is divided into multiple operation and maintenance stages, each operation and maintenance stage corresponds to a corresponding operation and maintenance operation, and after processing the operation and maintenance event based on the operation and maintenance operation, the operation and maintenance result and operation and maintenance state are recorded, thereby enabling the customer to trace the full operation and maintenance process of the operation and maintenance event of interest, and improving the timeliness of operation and maintenance.

[0046] In one example, the corresponding operation and maintenance stage of the operation and maintenance event reported by the customer can be set based on the business logic to which the operation and maintenance event belongs.

[0047] For example, the business logic is to evaluate the processing result of the operation and maintenance event after processing the operation and maintenance event.

[0048] In one example, the operation and maintenance stage in the full operation and maintenance process can include a listening stage, a classification stage, an allocation stage, a processing stage, etc. Correspondingly, the listening stage corresponds to the listening operation, the classification stage corresponds to the classification operation, the allocation stage corresponds to the allocation operation, and the processing stage corresponds to the processing operation. Here, the operation and maintenance operation can include operations corresponding to the above-mentioned operation and maintenance stages, such as listening operation, classification operation, allocation operation, and processing operation.

[0049] In the embodiment, in order to better provide operation and maintenance services for customers, other operation and maintenance operations and the above operation and maintenance operations can be adopted to complete the management of the full operation and maintenance process of the operation and maintenance event; therefore, the other operation and maintenance operations can also be included in the protection scope of the present application, and will not be described here.

[0050] In one example, after the operation and maintenance event is reported, the operation and maintenance event management method further includes: displaying the operation and maintenance event through a display device.

[0051] Correspondingly, in the example, displaying the operation and maintenance event through the display device includes:

[0052] The service personnel reports the operation and maintenance event to the execution subject through an input device, and displays the operation and maintenance event on the display device.

[0053] The input device can be an input device connected to the display device, such as a keyboard, a handwriting board, etc.; or the input device can be on the display device, such as a button on the display device; or the input device is an input module on the display device, such as an input module on a touch screen.

[0054] In one example, the classification operation on the operation and maintenance event to obtain a classification result can include:

[0055] The operation and maintenance event reported by the service personnel is classified according to a preset category. Alternatively, the operation and maintenance event reported by the service personnel is classified through a preset classification model. Alternatively, the operation and maintenance event reported by the service personnel is classified based on a preset category to obtain a first classification result, and then the operation and maintenance event is classified again through a preset classification model to obtain a second classification result; then, according to the first classification result and the second classification result, a final classification result of the operation and maintenance event is determined.

[0056] Here, the preset category can include a category obtained by classifying other operation and maintenance events by the user before reporting the operation and maintenance event.

[0057] Correspondingly, in the example, by performing similarity matching between the operation and maintenance event corresponding to the preset category and the operation and maintenance event, the category corresponding to the operation and maintenance event with the highest similarity can be taken as the category of the operation and maintenance event.

[0058] Here, according to the first classification result and the second classification result, the final classification result of the operation and maintenance event can include:

[0059] When the similarity deviation between the first classification result and the second classification result meets a preset classification threshold, the first classification result or the second classification result is taken as the final classification result.

[0060] In this embodiment, after classifying the operation and maintenance event reported by the service personnel, the operation and maintenance state corresponding to the reported operation and maintenance event is updated to classified.

[0061] In step 202, according to the classification result, the operation and maintenance event is assigned, and the processing result returned by the operation and maintenance terminal after processing the operation and maintenance event is received.

[0062] In this embodiment, the above execution subject can assign the operation and maintenance event according to the classification result, and assign the operation and maintenance event corresponding to the classification result to the corresponding operation and maintenance terminal; and receive the processing result returned by the operation and maintenance terminal after processing the operation and maintenance event corresponding to the classification result.

[0063] In one example, according to the classification result, the operation and maintenance event is assigned, which can include:

[0064] According to the classification result, the corresponding operation and maintenance personnel is assigned; or, the operation and maintenance event is automatically claimed by the operation and maintenance personnel; or, according to the classification result, the operation and maintenance event is assigned to the operation and maintenance personnel corresponding to the classification result.

[0065] Here, the classification result can include various operation and maintenance attributes for describing various operation and maintenance attributes, including operation and maintenance personnel attributes, field attributes, operation and maintenance time attributes, operation and maintenance mode attributes, etc.

[0066] In this embodiment, various operation and maintenance attributes are used to more accurately classify operation and maintenance events. In this embodiment, operation and maintenance attributes that can improve classification accuracy are all included in the protection scope of the present application.

[0067] In this embodiment, after the operation and maintenance event is assigned, the operation and maintenance state of the operation and maintenance event is updated to assigned.

[0068] It should be noted that the above processing result can be a processing result generated by the operation and maintenance personnel of the operation and maintenance terminal on the operation and maintenance terminal; or, a processing result generated by the operation and maintenance personnel on the above execution subject on the operation and maintenance event corresponding to the classification result.

[0069] In one example, the operation and maintenance personnel can complete the operation and maintenance of the operation and maintenance event through online or offline operation and maintenance services to obtain the operation and maintenance result corresponding to the operation and maintenance event. Among them, online can be to complete the processing of the operation and maintenance event through remote guidance of the operation and maintenance terminal.

[0070] Here, the operation and maintenance terminal can be a device for the operation and maintenance personnel to process the operation and maintenance event, and the operation and maintenance terminal can be connected to the operation and maintenance event management platform through a network; or, the operation and maintenance terminal can be a device on the operation and maintenance event management platform for the operation and maintenance personnel to perform operation and maintenance operations.

[0071] Correspondingly, in this example, the customer can be assisted by the display device of the above-mentioned execution subject to complete the processing of the operation and maintenance event.

[0072] Here, the operation and maintenance personnel can be personnel processing operation and maintenance events, for example, the operation and maintenance personnel maintains the problems existing in the process of using the CRM system by the customer.

[0073] In this embodiment, after obtaining the processing result by processing the operation and maintenance event, the operation and maintenance state of the operation and maintenance event is updated to be processed.

[0074] The operation and maintenance event management method provided in this embodiment classifies the operation and maintenance event when the listening operation listens to the reported operation and maintenance event, obtains a classification result, then, according to the classification result, performs an allocation operation on the operation and maintenance event, and receives a processing result returned after the operation and maintenance terminal processes the operation and maintenance event according to the allocation operation, so that the operation and maintenance operation such as the listening operation, the classification operation, the allocation operation and the processing operation can be performed on the operation and maintenance event in the whole operation and maintenance process, and the operation and maintenance state of the operation and maintenance event in the whole operation and maintenance process can be managed after the operation and maintenance operation, so that the operation and maintenance event can be quickly responded, the whole life cycle management can be realized, the operation and maintenance service is improved, and the operation and maintenance event is managed according to rules, providing data support for subsequent operation and maintenance analysis.

[0075] In some optional implementation manners of this embodiment, the operation and maintenance operation further includes an evaluation operation.

[0076] The operation and maintenance event management method further includes receiving an evaluation result returned after the evaluation operation on the processing result.

[0077] After the operation and maintenance event is processed by the processing operation, the processing result of the operation and maintenance event can be evaluated, for example, the evaluation result is directly fed back by the customer or fed back by the customer through the service personnel.

[0078] In one example, the customer performs an evaluation operation on the processing result of the operation and maintenance event, and returns an evaluation result corresponding to the evaluation operation to the above-mentioned execution subject.

[0079] Correspondingly, in this example, the customer fills in the evaluation operation on the processing result of the operation and maintenance event through the service personnel on the display device of the above-mentioned execution subject.

[0080] In this implementation manner, after the evaluation operation on the processing result corresponding to the operation and maintenance event, the operation and maintenance state is updated and recorded to be evaluated.

[0081] In this implementation manner, each operation and maintenance stage in the whole operation and maintenance process has a time sequence, for example, the classification stage is a stage after the listening stage, and the classification stage is a stage after the processing stage.

[0082] In the implementation, each operation stage in the whole operation and maintenance process of the operation and maintenance event is fully considered from the monitoring operation to the evaluation operation, so that the whole operation and maintenance process of each operation and maintenance event can be tracked.

[0083] It should be noted that each operation stage involved in the whole operation and maintenance process is not limited to the operation stages described above, and the operation stages described above can be freely combined into the whole operation and maintenance process of a certain operation and maintenance event.

[0084] In the implementation, various operation and maintenance operations are performed according to the business logic of the operation and maintenance event to manage the operation and maintenance state of each operation and maintenance stage of the operation and maintenance event in the whole operation and maintenance process.

[0085] As shown in Figure 3 , a flowchart 300 of one embodiment of an operation and maintenance event management method according to the present application can include the following steps:

[0086] Step 301, in response to the monitoring operation monitoring the reported operation and maintenance event, processing the operation and maintenance event to obtain first operation and maintenance features; performing a classification operation on the first operation and maintenance features according to a target classification model to obtain a classification result corresponding to the first operation and maintenance features, wherein the target classification model is obtained based on a decision tree.

[0087] In this embodiment, the execution subject of the operation and maintenance event management method (for example, the client 101 and 102 shown in Figure 1 ) can extract the features of the operation and maintenance event to obtain the first operation and maintenance features after the monitoring operation monitors the reported operation and maintenance event; then, input the first operation and maintenance features into the target classification model to obtain the classification result.

[0088] In one example, processing the operation and maintenance event to obtain the first operation and maintenance features can include: processing the operation and maintenance event using a natural language processing algorithm to obtain the first operation and maintenance features.

[0089] Correspondingly, in this example, the operation and maintenance event can be analyzed by NLP to obtain an NLP analysis result; then, the NLP analysis result is feature extracted to obtain the first operation and maintenance features.

[0090] For example, the NLP analysis result is feature extracted using an NLP feature extraction network to obtain the first operation and maintenance features.

[0091] In one example, in Figure 4 , the operation and maintenance event is feature extracted by the NLP feature extraction network; then, the decision tree is used as the target classification model or the decision tree is trained to obtain the target classification model.

[0092] Herein, the above-mentioned monitoring operation can be a monitor installed in the above-mentioned execution subject, and if the service personnel reports a maintenance event through the monitor, the maintenance state of the maintenance event is updated to the initial state. Herein, the service personnel is a personnel who interfaces with a customer using a Customer Relationship Management (CRM) system for maintenance, and the service personnel is used for collecting, feeding back, summarizing, reporting, and the like operation maintenance events. The maintenance event can be any event related to application maintenance generated in the process of the customer using the CRM system.

[0093] In this embodiment, according to the full maintenance process of the maintenance event, the maintenance event is processed according to the maintenance operation corresponding to each maintenance stage in the full maintenance process, and the processed maintenance state is recorded, so as to realize the management of the full maintenance process of the maintenance event.

[0094] In one example, the full maintenance process can be a complete maintenance process from the service personnel reporting a maintenance event to the customer feeding back the processing situation of the maintenance event.

[0095] In this embodiment, the full maintenance process is divided into multiple maintenance stages, each maintenance stage corresponds to a corresponding maintenance operation, and after processing the maintenance event based on the maintenance operation, the maintenance result and the maintenance state are recorded, so that the customer can trace the full maintenance process of the maintenance event that he cares about, and improve the timeliness of maintenance.

[0096] In one example, the maintenance stage in the full maintenance process can include a monitoring stage, a classification stage, an allocation stage, a processing stage, and the like; correspondingly, the monitoring stage corresponds to the monitoring operation, the classification stage corresponds to the classification operation, the allocation stage corresponds to the allocation operation, and the processing stage corresponds to the processing operation.

[0097] In this embodiment, in order to better provide maintenance services for customers, other maintenance operations and the above-mentioned maintenance operations can be used together to complete the management of the full maintenance process of the maintenance event; therefore, other maintenance operations can also be included in the protection scope of the present application, which will not be repeated here.

[0098] In one example, the decision tree can be used as the target classification model; or, the decision tree is trained, and the trained decision tree is used as the target classification model.

[0099] Step 302, according to the classification result, the maintenance event is subjected to an allocation operation, and the processing result returned by the maintenance terminal after the processing operation of the maintenance event corresponding to the allocation operation is received.

[0100] In the embodiment, the execution subject can perform an allocation operation on the operation and maintenance event according to the classification result, and allocate the operation and maintenance event corresponding to the classification result to a corresponding operation and maintenance terminal; and receive a processing result returned by the operation and maintenance terminal after the operation and maintenance terminal performs a processing operation on the operation and maintenance event corresponding to the classification result.

[0101] In one example, the allocation operation on the operation and maintenance event according to the classification result can include:

[0102] According to the classification result, a corresponding operation and maintenance personnel or an operation and maintenance terminal corresponding to the operation and maintenance personnel is assigned; or, the operation and maintenance event is automatically claimed by the operation and maintenance personnel; or, according to the classification result, the operation and maintenance event is allocated to a corresponding operation and maintenance group, and then according to a preset strategy, for example, the operation and maintenance event is polled to the operation and maintenance personnel in the operation and maintenance group.

[0103] Here, the classification result can include various operation and maintenance attributes for description, and the various operation and maintenance attributes include operation and maintenance personnel attributes, field attributes, operation and maintenance time attributes, operation and maintenance mode attributes, and the like.

[0104] In the embodiment, after the allocation operation on the operation and maintenance event, the operation and maintenance state of the operation and maintenance event is updated to allocated.

[0105] It should be noted that the processing result can be a processing result generated by an operation and maintenance personnel of the operation and maintenance terminal on the operation and maintenance terminal; or, a processing result generated by the operation and maintenance personnel on the execution subject after the operation and maintenance personnel performs a processing operation on the operation and maintenance event corresponding to the classification result.

[0106] In one example, the operation and maintenance personnel can complete the operation and maintenance of the operation and maintenance event through online or offline operation and maintenance services to obtain an operation and maintenance result corresponding to the operation and maintenance event. The online can be a remote guidance to complete the processing of the operation and maintenance event.

[0107] Correspondingly, in this example, the display device of the execution subject can remotely assist the customer to complete the processing of the operation and maintenance event.

[0108] Here, the operation and maintenance personnel can be a person who processes the operation and maintenance event, for example, the operation and maintenance personnel maintains the problems existing in the process of using the CRM system by the customer.

[0109] In the embodiment, after the processing of the operation and maintenance event to obtain the processing result, the operation and maintenance state of the operation and maintenance event is updated to processed.

[0110] In some optional implementation manners of the embodiment, the operation and maintenance event management method further includes:

[0111] Obtaining an operation and maintenance sample event and a classification label corresponding to the operation and maintenance sample event;

[0112] Processing the operation and maintenance sample events to obtain the second operation and maintenance feature;

[0113] Input the second operation and maintenance feature into the decision tree to obtain the classification result;

[0114] According to the classification results and classification labels, the decision tree is trained to obtain the target classification model.

[0115] In this implementation, the operation and maintenance sample events can be processed to obtain the second operation and maintenance features; then the second operation and maintenance features are input into the decision tree to obtain the classification results; then the decision tree is trained based on the classification results and classification labels to obtain the target classification model.

[0116] In one example, the target classification model is determined based on the following steps:

[0117] The first step is to obtain corpus, which may include operation and maintenance sample events and their corresponding classification labels.

[0118] In this implementation, the operation and maintenance sample event is a sample used to train the target classification model.

[0119] The second step is corpus preprocessing, for example, filtering out malicious operation and maintenance sample events.

[0120] The third step is to extract the second operation and maintenance features of the operation and maintenance sample events through the NLP feature extraction network.

[0121] In one example, Figure 4 In the example, the NLP feature extraction network can be trained based on the second operation and maintenance features and the corresponding feature labels.

[0122] In the fourth step, the second operation and maintenance feature is input into the decision tree to obtain the classification result of the operation and maintenance sample event.

[0123] In the fifth step, the decision tree is trained using the classification labels in the first step and the classification results in the fourth step to obtain the target classification model.

[0124] It should be noted that the target classification model used for classification of operation and maintenance events can be obtained by training a decision tree.

[0125] In this implementation, the operation and maintenance events can be classified based on the target classification model obtained by decision tree training.

[0126] In some optional implementations of this embodiment, the operation and maintenance event management method further includes:

[0127] Get the operation and maintenance attributes of the operation and maintenance sample events;

[0128] Determine the information entropy of the operation and maintenance sample events based on their operation and maintenance attributes;

[0129] According to the information entropy of the operation and maintenance sample event, a decision tree is generated.

[0130] In the implementation manner, the execution subject can determine the information entropy of the operation and maintenance sample event according to the operation and maintenance attribute of the operation and maintenance sample event, and then generate the decision tree based on the information entropy of the operation and maintenance sample event.

[0131] Here, the operation and maintenance attribute of the operation and maintenance sample event can include an operation and maintenance personnel attribute, a domain attribute, an operation and maintenance time attribute, an operation and maintenance mode attribute, and the like.

[0132] In one example, determining the information entropy of the operation and maintenance sample event according to the operation and maintenance attribute of the operation and maintenance sample event can include:

[0133] In the operation and maintenance sample event, there are k operation and maintenance attributes, i is one of them, p refers to the probability that the i operation and maintenance attribute is a certain classification result, and the information entropy that the classification result of the operation and maintenance sample event is a certain classification result is obtained by summing up each operation and maintenance attribute in the k operation and maintenance attributes and the corresponding probability.

[0134] In the implementation manner, the method further includes selecting an operation and maintenance attribute whose probability meets a preset probability threshold from a plurality of operation and maintenance attributes, so that the influence of an operation and maintenance attribute with a lower probability on the classification result can be filtered out, and the accuracy of the classification is higher.

[0135] In one example, the probability threshold can be set based on the accuracy of the classification result or based on the satisfaction of a customer in the evaluation result.

[0136] For example, when the evaluation result is that the operation and maintenance personnel is unprofessional, it can be that the classification result of the target classification model is inaccurate, resulting in that the operation and maintenance personnel allocated does not match, and resulting in that the operation and maintenance effect is not good. At this time, the probability threshold can be increased to allocate a more matched operation and maintenance personnel.

[0137] In Figure 4 , the decision tree can be determined based on the following steps:

[0138] First, the operation and maintenance attribute of the operation and maintenance sample event is obtained.

[0139] Second, the probability that the operation and maintenance attribute of the operation and maintenance sample event is a certain classification result is obtained.

[0140] Third, according to a preset probability threshold, an operation and maintenance attribute that exceeds the preset probability threshold is selected (i.e., the optimal attribute is selected).

[0141] Fourth, the information entropy is determined according to the probability that the operation and maintenance attribute that exceeds the preset probability threshold is a certain classification result.

[0142] In the fifth step, the decision tree is generated according to the information entropy.

[0143] It should be noted that the target classification model can also be obtained based on the decision tree. For example, the decision tree is directly taken as the target classification model.

[0144] In some optional implementations of the embodiment, processing the operation and maintenance sample event to obtain the second operation and maintenance feature can include: processing the operation and maintenance sample event by using a natural language processing algorithm to obtain the second operation and maintenance feature.

[0145] In the implementation, the operation and maintenance sample event is analyzed and processed by using a natural language processing (NLP) algorithm to obtain an NLP analysis result; and then, the NLP analysis result is subjected to feature extraction to obtain the second operation and maintenance feature.

[0146] In one example, the NLP analysis result is subjected to feature extraction by using a neural network to obtain the second operation and maintenance feature.

[0147] Here, in Figure 4 , the neural network can be an NLP feature extraction network.

[0148] In the implementation, the NLP analysis result can be subjected to feature extraction by using a trained NLP feature extraction network to obtain the second operation and maintenance feature, thereby improving the accuracy of the second operation and maintenance feature and further improving the accuracy of the target classification model.

[0149] As Figures 5-6 shown in FIG. 1, an embodiment of a method for operation and maintenance event management according to the present application is shown, which can be applied to a listening operation and maintenance event management platform for managing corresponding operation and maintenance states in a full operation and maintenance process after operation and maintenance operations are performed on operation and maintenance events.

[0150] In the embodiment, the operation and maintenance event management platform includes: Figure 5 a problem feedback access layer, which is mainly an entrance for service personnel to feed back operation and maintenance events, including two end feedback modes of a PC (personal computer) end and a mobile end.

[0151] a business processing layer, which is used to classify operation and maintenance events fed back by service personnel. When feeding back, the service personnel can first perform a first classification on the operation and maintenance events, for example, fill in a problem classification table; and then, on this basis, perform a second classification on the operation and maintenance events by using a target classification model to obtain a classification result of the operation and maintenance events.

[0152]

[0153] ​It should be noted that the classification result of the operation and maintenance event can be determined based on the similarity deviation between the first classification and the second classification.

[0154] In one example, when the similarity deviation between the first classification and the second classification meets a preset classification threshold, the result of the first classification or the second classification is taken as the final classification result.

[0155] A custom configuration layer is configured to configure relevant information, including configuration definition of operation and maintenance personnel corresponding to each module in the CRM system, operation and maintenance state preset, rule preset of operation and maintenance event flow, and the like.

[0156] An operation and maintenance engine layer is configured to provide training data support for a target classification model. The layer is also configured to summarize evaluation results of customers for processing results, and to perform risk control identification and rewards and punishments on malicious operation and maintenance events. The layer is also configured to provide support for intelligent sorting of classified operation and maintenance events. The layer can also limit the permission settings of relevant personnel associated with the operation and maintenance event management platform, for example, service personnel have the permission to view and evaluate the operation and maintenance events they report, and operation and maintenance personnel have the permission to view and handle operation and maintenance events.

[0157] An external service layer is configured to control the detailed level of the operation and maintenance events reported by service personnel according to the permission, and the management personnel of the operation and maintenance event management platform can display all reported operation and maintenance events, especially the current real-time operation and maintenance events for management and export of corresponding dimension reports, and the like.

[0158] In one example, the operation and maintenance event management method can include: Figure 6 In one example, the operation and maintenance event management method can include:

[0159] In one example, the operation and maintenance event management method can include:

[0160] First, before the operation and maintenance event management platform is running, the service personnel and operation and maintenance personnel of each application in the CRM are defined.

[0161] Second, the operation and maintenance event listener EventListener is used to listen to the reporting of operation and maintenance events for data aggregation.

[0162] Thirdly, the operation and maintenance event reported in the second step is classified by an operation and maintenance event classifier EventClassifier, and a classification result is obtained.

[0163] The operation and maintenance event reported by the service personnel is classified according to the preset category. Alternatively, the operation and maintenance event reported by the service personnel is classified by a preset classification model. Alternatively, the operation and maintenance event reported by the service personnel is classified based on the preset category to obtain a first classification result, and then the operation and maintenance event is classified again by a preset classification model to obtain a second classification result. Then, according to the first classification result and the second classification result, a final classification result of the operation and maintenance event is determined.

[0164] Here, the preset category can include a category obtained by classifying other operation and maintenance events by the user before reporting the operation and maintenance event.

[0165] Correspondingly, in this example, by performing similarity matching between the operation and maintenance event corresponding to the preset category and the operation and maintenance event, the category corresponding to the operation and maintenance event with the highest similarity can be taken as the category of the operation and maintenance event.

[0166] Here, according to the first classification result and the second classification result, the final classification result of the operation and maintenance event can include:

[0167] When the similarity deviation between the first classification result and the second classification result meets a preset classification threshold, the first classification result or the second classification result is taken as the final classification result.

[0168] Fourthly, after classifying the operation and maintenance event, the classified operation and maintenance event is put into an operation and maintenance event feedback pool. The operation and maintenance states of the operation and maintenance events in the feedback pool are all unspecified.

[0169] In this embodiment, the operation and maintenance event feedback pool can be used to cache the classified operation and maintenance events.

[0170] In this embodiment, the operation and maintenance events in the operation and maintenance event feedback pool can be distributed to corresponding operation and maintenance personnel in the following three ways:

[0171] (1) The operation and maintenance event is distributed to the corresponding operation and maintenance personnel according to the classification result of the operation and maintenance event by the manager; (2) The operation and maintenance personnel independently claims from the operation and maintenance event feedback pool; (3) The operation and maintenance event is first distributed to the corresponding operation and maintenance group based on the classification result; then, the operation and maintenance event is distributed within the operation and maintenance group based on a preset strategy, for example, polling designation, etc. The operation and maintenance state of the operation and maintenance event after being assigned is specified.

[0172] In the fifth step, the classified operation and maintenance events are executed by an operation and maintenance event processor EventProcessor, and a processing result returned by an operation and maintenance terminal after a processing operation corresponding to the distribution operation is received.

[0173] In the sixth step, an operation and maintenance event post-processor EventPostProcessor is used. After the processing result of the operation and maintenance event is obtained, an entry is provided for a service personnel to evaluate the timeliness and accuracy of the operation and maintenance personnel in processing the operation and maintenance event, so as to be fed back to the operation and maintenance group.

[0174] In the seventh step, after the second step, the third step, the fourth step, the fifth step or the sixth step is executed, an operation and maintenance event changer EventChanger is used to update and record the operation and maintenance state.

[0175] In the embodiment, the operation and maintenance states involved in the whole operation and maintenance process can include initial state, unclassified, classified, unassigned, assigned, rejected, closed, to be evaluated, evaluated, and the like.

[0176] In the embodiment, the CRM operation and maintenance events are executed according to the corresponding operation and maintenance operation in each operation and maintenance stage in the whole operation and maintenance process, and the operation and maintenance state of the operation and maintenance event in the whole operation and maintenance process is managed after the operation and maintenance operation, so that the operation and maintenance event can be quickly responded, the whole life cycle management can be realized, the operation and maintenance service is improved, the operation and maintenance event is provided with rules, and data support is provided for subsequent operation and maintenance analysis.

[0177] Further referring to Figure 7 , as an implementation of the method shown in the above figures, the application discloses an embodiment of an operation and maintenance event management device, which corresponds to the method embodiment shown in Figure 2 , and the device can be applied to various electronic devices.

[0178] As shown in Figure 7 , the embodiment of the application provides an operation and maintenance event management device 700 for managing the operation and maintenance state in the whole operation and maintenance process after an operation and maintenance operation on the operation and maintenance event, and the device 700 comprises a listening module 701, a classification module 702, a distribution module 703 and a processing module 704. The listening module 701 is used for listening to the operation and maintenance event; the classification module 702 is used for performing a classification operation on the operation and maintenance event according to the reported operation and maintenance event listened to by the listening operation, to obtain a classification result; the distribution module 703 is used for performing a distribution operation on the operation and maintenance event according to the classification result; and the processing module 704 is used for receiving a processing result returned by an operation and maintenance terminal after a processing operation on the operation and maintenance event.

[0179] In the embodiment, the specific processing of the listening module 701, the classification module 702, the distribution module 703 and the processing module 704 in the operation and maintenance event management apparatus 700 and the technical effects brought by the specific processing can be referred to the listening module 701, the classification module 702, the distribution module 703 and the processing module 704 respectively. Figure 2 Steps 201-202 in the corresponding embodiment.

[0180] In some embodiments, the classification module 702 is configured to: process the operation and maintenance event to obtain first operation and maintenance features; and perform a classification operation on the first operation and maintenance features according to a target classification model to obtain a classification result corresponding to the operation and maintenance features, wherein the target classification model is obtained based on a decision tree.

[0181] In some embodiments, the apparatus further includes: an obtaining module configured to obtain operation and maintenance sample events and classification labels corresponding to the operation and maintenance sample events; a obtaining module configured to process the operation and maintenance sample events to obtain second operation and maintenance features; an input module configured to input the second operation and maintenance features into the decision tree to obtain the classification result; and a training module configured to train the decision tree according to the classification result and the classification labels to obtain the target classification model.

[0182] In some embodiments, the apparatus further includes: an obtaining module configured to obtain operation and maintenance attributes of the operation and maintenance sample events; a determining module configured to determine information entropy of the operation and maintenance sample events according to the operation and maintenance attributes of the operation and maintenance sample events; and a generating module configured to generate the decision tree according to the information entropy of the operation and maintenance sample events.

[0183] In some embodiments, the obtaining module is configured to process the operation and maintenance sample events by using a natural language processing algorithm to obtain the second operation and maintenance features.

[0184] In some embodiments, the operation and maintenance operation further includes an evaluation operation, and the apparatus further includes an evaluation module configured to receive an evaluation result returned after the evaluation operation on the processing result.

[0185] As shown in Figure 8 is a block diagram of an electronic device that implements a method for operation and maintenance event management according to embodiments of the present application. The electronic device is intended to represent various forms of digital computers, such as laptops, desktops, tablets, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown here, their connections and relationships, and their functions, are meant to be examples only, and are not intended to limit the implementations of the present application described and / or claimed in this document.

[0186] As shown in Figure 8As shown, the electronic device includes one or more processors 801, a memory 802, and interfaces for connecting the various components, including high-speed interfaces and low-speed interfaces. The various components are interconnected by different buses, and can be mounted on a common main board or otherwise installed as desired. The processor can process instructions executed within the electronic device, including instructions stored in the memory or graphical information stored on the memory to display a GUI on an external input / output device, such as a display device coupled to the interface. In other embodiments, multiple processors and / or buses can be used with multiple memories and multiple memory, if desired. Likewise, multiple electronic devices can be connected, each device providing part of the necessary operations (e.g., as a server array, a set of blade servers, or a multi-processor system). Figure 8 The processor 801 is taken as an example in the embodiment.

[0187] The memory 802 is a non-transitory computer readable storage medium provided by the present application. The memory stores instructions executable by at least one processor, so that the at least one processor executes the operation and maintenance event management method provided by the present application. The non-transitory computer readable storage medium of the present application stores computer instructions for causing a computer to execute the operation and maintenance event management method provided by the present application.

[0188] The memory 802 is a non-transitory computer readable storage medium, which can be used to store non-transitory software programs, non-transitory computer executable programs and modules, such as program instructions / modules of the operation and maintenance event management method in the embodiment of the present application (for example, the listening module 701, the classification module 702, the allocation module 703 and the processing module 704). The processor 801 executes various functional applications and data processing of the server by running the non-transitory software programs, instructions and modules stored in the memory 802, that is, implements the operation and maintenance event management method in the above method embodiment.

[0189] The memory 802 can include a program storage area and a data storage area, wherein the program storage area can store an operating system and application programs required by at least one function; the data storage area can store data created according to the use of the blockchain-based information processing electronic device, etc. In addition, the memory 802 can include a high-speed random access memory, and can also include a non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state memory device. In some embodiments, the memory 802 can optionally include a memory remotely arranged with respect to the processor 801, which can be connected to the blockchain-based information processing electronic device through a network. Examples of the above network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0190] The electronic device of the operation and maintenance event management method can further include an input device 803 and an output device 804. The processor 801, the memory 802, the input device 803, and the output device 804 can be connected through a bus or other means, Figure 8 The connection through the bus is taken as an example.

[0191] The input device 803 can receive inputted digital or character information, and generate key signal input related to user settings and function control of the blockchain-based information processing electronic device, such as a touch screen, a keypad, a mouse, a trackpad, a touchpad, a pointing stick, one or more mouse buttons, a trackball, a joystick, and the like. The output device 804 can include a display device, an auxiliary lighting device (e.g., an LED), and a tactile feedback device (e.g., a vibration motor), and the like. The display device can include, but is not limited to, a liquid crystal display (LCD), a light-emitting diode (LED) display, and a plasma display. In some embodiments, the display device can be a touch screen.

[0192] Various embodiments of the systems and techniques described here can be realized in digital electronic circuitry, integrated circuitry, specially designed ASICs (application specific integrated circuits), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0193] These computer programs (also known as programs, software, software applications or code) include machine instructions for a programmable processor, and can be implemented in a high-level procedural and / or object-oriented programming language, and / or in assembly / machine language. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, apparatus and / or device (e.g., magnetic discs, optical disks, memory, Programmable Logic Devices (PLDs)) used to provide machine instructions and / or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal used to provide machine instructions and / or data to a programmable processor.

[0194] To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0195] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0196] The computing system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other.

[0197] It should be understood that various forms of flow shown above can be used, re-ordered, added to, or deleted from without departing from the spirit of the technology disclosed in this application. For example, the steps recited in this application can be executed in parallel, executed in sequence, or executed in a different order, as long as the desired results of the technology disclosed in this application are achieved, and this application is not limited herein.

[0198] The specific embodiments described above have been disclosed by way of example only. Persons skilled in the art will appreciate that numerous modifications, substitutions, combinations, sub-combinations, and alternatives can be made to the specific embodiments disclosed herein without departing from the spirit and scope of the disclosure. Any modifications, equivalent substitutions, improvements, combinations, sub-combinations and alternatives not described above are included within the scope of the disclosure.

Claims

1. A method for managing an operation and maintenance event, for managing the corresponding operation and maintenance status in the entire operation and maintenance process after an operation and maintenance operation is performed on an operation and maintenance event, comprising: In response to monitoring the reported operation and maintenance events through the monitoring operation, a classification operation is performed on the operation and maintenance events to obtain a classification result; According to the classification result, an allocation operation is performed on the operation and maintenance event, and a processing result returned by the operation and maintenance end corresponding to the allocation operation after the operation and maintenance event is processed is received.

2. The method according to claim 1, wherein The classifying operation of the operation and maintenance event to obtain the classification result includes: Processing the operation and maintenance event to obtain a first operation and maintenance feature; A classification operation is performed on the first operation and maintenance feature according to a target classification model to obtain a classification result corresponding to the operation and maintenance feature, wherein the target classification model is obtained based on a decision tree.

3. The method according to claim 2, wherein: The method further comprises: Obtain operation and maintenance sample events and their corresponding classification labels; Processing the operation and maintenance sample event to obtain a second operation and maintenance feature; Inputting the second operation and maintenance feature into a decision tree to obtain a classification result; According to the classification results and the classification labels, a decision tree is trained to obtain a target classification model.

4. The method according to claim 2 or 3, wherein: The method further comprises: Get the operation and maintenance attributes of the operation and maintenance sample events; Determining the information entropy of the operation and maintenance sample event based on the operation and maintenance attributes of the operation and maintenance sample event; Generate a decision tree based on the information entropy of operation and maintenance sample events.

5. The method according to claim 3, wherein The processing of the operation and maintenance sample event to obtain a second operation and maintenance feature includes: The operation and maintenance sample event is processed using a natural language processing algorithm to obtain a second operation and maintenance feature.

6. The method according to claim 1, wherein: The operation and maintenance operations also include: evaluation operations; The method further includes: receiving an evaluation result returned after performing an evaluation operation on the processing result.

7. An operation and maintenance event management device, used to manage the corresponding operation and maintenance status in the entire operation and maintenance process after the operation and maintenance operation is performed on the operation and maintenance event, comprising: Monitoring module, used to monitor operation and maintenance events; A classification module is configured to classify the operation and maintenance events reported by the monitoring operation to obtain a classification result; An allocation module, configured to perform allocation operations on the operation and maintenance events according to the classification results; The processing module is used to receive the processing result returned by the operation and maintenance end corresponding to the allocation operation after processing the operation and maintenance event.

8. The device according to claim 7, wherein The classification module is used to: Processing the operation and maintenance event to obtain a first operation and maintenance feature; A classification operation is performed on the first operation and maintenance feature according to a target classification model to obtain a classification result corresponding to the operation and maintenance feature, wherein the target classification model is obtained based on a decision tree.

9. The device according to claim 8, wherein The device further comprises: An acquisition module is used to obtain operation and maintenance sample events and the classification labels corresponding to the operation and maintenance sample events; An obtaining module, configured to process the operation and maintenance sample event to obtain a second operation and maintenance feature; An input module, configured to input the second operation and maintenance feature into a decision tree to obtain a classification result; The training module is used to train the decision tree according to the classification results and the classification labels to obtain a target classification model.

10. The device according to claim 8 or 9, wherein The device further comprises: The acquisition module is used to obtain the operation and maintenance attributes of the operation and maintenance sample events; A determination module, configured to determine the information entropy of the operation and maintenance sample event based on the operation and maintenance attributes of the operation and maintenance sample event; The generation module is used to generate a decision tree based on the information entropy of operation and maintenance sample events.

11. The device according to claim 9, wherein The module is used to: The operation and maintenance sample event is processed using a natural language processing algorithm to obtain a second operation and maintenance feature.

12. The device according to claim 7, wherein: The operation and maintenance operations also include: evaluation operations; The device further includes: an evaluation module, configured to receive an evaluation result returned after an evaluation operation is performed on the operation and maintenance result.

13. An electronic device comprising: one or more processors; a storage device having one or more programs stored thereon; When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 6.

14. A non-transitory computer-readable storage medium storing computer instructions, having a computer program stored thereon, wherein: When the program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

15. A computer program product comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements the method according to any one of claims 1 to 6.

Images