Operation and maintenance data processing method and device

Abstract

The embodiment of the invention provides an operation and maintenance data processing method and device. The operation and maintenance data processing method comprises the steps of obtaining operation and maintenance data of a target operation and maintenance scene; performing fault analysis on the operation and maintenance data to obtain an operation and maintenance problem of the operation and maintenance data; according to the operation and maintenance problem, an initial problem atlas of the target operation and maintenance scene is updated, a target problem atlas of the target operation and maintenance scene is obtained, the initial problem atlas comprises at least one initial sub-graph, and the initial sub-graphs are constructed by taking the initial operation and maintenance problem as a root node and taking initial operation and maintenance data of the initial operation and maintenance problem as child nodes; the target problem map comprises at least one target operation and maintenance problem; and according to the target question map, generating a target reply result of the at least one target operation and maintenance question. By performing fault analysis on the operation and maintenance data, the operation and maintenance problems can be identified more comprehensively and accurately, the comprehensiveness and accuracy of operation and maintenance data processing are improved, the whole processing process is a highly automatic process, and the operation and maintenance data processing efficiency is improved.

Description

TECHNICAL FIELD

[0001] Embodiments of the present specification relate to the technical field of computer technology, and particularly relate to an operation and maintenance data processing method and device. BACKGROUND

[0002] With the rapid development of rail transit systems, the number and complexity of equipment are increasing, and the increase in train operation density and speed puts higher requirements on system safety and reliability. In order to ensure the efficient and stable operation of the rail transit system, it is necessary to effectively process a large amount of operation and maintenance data. By effectively processing operation and maintenance data, the health status of equipment can be monitored in real time, potential failure risks can be predicted, and a scientific maintenance plan can be provided. Therefore, operation and maintenance data processing is a key link to ensure the safe operation of the rail transit system.

[0003] Currently, operation and maintenance data processing of rail transit mainly relies on manual operation: the staff collects equipment status information through regular inspection, and manually records and organizes relevant data, and then analyzes and judges based on experience. However, manual inspection is inefficient, difficult to cover all equipment, and prone to missed or false detection, and cannot timely detect sudden problems, which may lead to the expansion of faults or even cause safety accidents. Moreover, manual analysis relies on personal experience and subjective judgment, and the results may be biased, and it is difficult to cope with complex and variable operation and maintenance scenarios. Therefore, an efficient and accurate automated operation and maintenance data processing scheme is urgently needed. SUMMARY

[0004] Therefore, the embodiments of the present specification provide an operation and maintenance data processing method. One or more embodiments of the present specification also relate to an operation and maintenance data processing device, a computing device, a computer-readable storage medium, and a computer program product to solve the technical defects in the prior art.

[0005] According to a first aspect of the embodiments of the present specification, an operation and maintenance data processing method is provided, comprising:

[0006] obtaining operation and maintenance data of a target operation and maintenance scenario;

[0007] performing fault analysis on the operation and maintenance data to obtain operation and maintenance problems of the operation and maintenance data;

[0008] updating an initial problem graph of the target operation and maintenance scenario according to the operation and maintenance problems, to obtain a target problem graph of the target operation and maintenance scenario, wherein the initial problem graph comprises at least one initial subgraph, the initial subgraph is constructed with an initial operation and maintenance problem as a root node and initial operation and maintenance data of the initial operation and maintenance problem as a child node, and the target problem graph comprises at least one target operation and maintenance problem;

[0009] According to the target problem graph, a target reply result of at least one target operation and maintenance problem is generated.

[0010] According to a second aspect of the embodiments of the present specification, an operation and maintenance data processing apparatus is provided, comprising:

[0011] An acquisition module is configured to acquire operation and maintenance data of a target operation and maintenance scene;

[0012] An analysis module is configured to perform fault analysis on the operation and maintenance data to obtain operation and maintenance problems of the operation and maintenance data.

[0013] An update module is configured to update an initial problem graph of the target operation and maintenance scene according to the operation and maintenance problems, to obtain a target problem graph of the target operation and maintenance scene, wherein the initial problem graph comprises at least one initial subgraph, the initial subgraph is constructed with an initial operation and maintenance problem as a root node and initial operation and maintenance data of the initial operation and maintenance problem as a child node, and the target problem graph comprises at least one target operation and maintenance problem.

[0014] A generation module is configured to generate a target reply result of at least one target operation and maintenance problem according to the target problem graph.

[0015] According to a third aspect of the embodiments of the present specification, a computing device is provided, comprising:

[0016] a memory and a processor;

[0017] The memory is used to store computer programs / instructions, and the processor is used to execute the computer programs / instructions, which realize the steps of the operation and maintenance data processing method described above when executed by the processor.

[0018] According to a fourth aspect of the embodiments of the present specification, a computer readable storage medium is provided, which stores computer programs / instructions, which realize the steps of the operation and maintenance data processing method described above when executed by the processor.

[0019] According to a fifth aspect of the embodiments of the present specification, a computer program product is provided, comprising computer programs / instructions, which realize the steps of the operation and maintenance data processing method described above when executed by the processor.

[0020] The operation and maintenance data processing method provided by one or more embodiments of the present specification comprises: obtaining operation and maintenance data of a target operation and maintenance scene; performing fault analysis on the operation and maintenance data to obtain operation and maintenance problems of the operation and maintenance data; updating an initial problem graph of the target operation and maintenance scene according to the operation and maintenance problems to obtain a target problem graph of the target operation and maintenance scene, wherein the initial problem graph comprises at least one initial subgraph, the initial subgraph is constructed with an initial operation and maintenance problem as a root node and initial operation and maintenance data of the initial operation and maintenance problem as a child node, and the target problem graph comprises at least one target operation and maintenance problem; and generating a target reply result of at least one target operation and maintenance problem according to the target problem graph. Through systematic collection and fault analysis on the operation and maintenance data in the target operation and maintenance scene, the operation and maintenance problems in the target operation and maintenance scene can be more comprehensively and accurately identified, the problems of missed detection or false detection are reduced, and the comprehensiveness and accuracy of operation and maintenance data processing are improved; the target problem graph obtained by updating the initial problem graph helps to organize and associate different operation and maintenance problems and operation and maintenance data, ensures the timeliness of the target problem graph, helps to better understand and cope with complex operation and maintenance environments, and at the same time, through the structured knowledge representation form of the target problem graph, similar operation and maintenance problems can be quickly searched, and the solving efficiency of operation and maintenance problems is greatly improved. Moreover, the entire operation and maintenance data processing process is a highly automated process, which not only improves the operation and maintenance data processing efficiency, but also reduces the dependence on human resources and reduces the labor cost. BRIEF DESCRIPTION OF DRAWINGS

[0021] Figure 1 FIG. 1 is an architecture diagram of an operation and maintenance data processing system provided by one embodiment of the present specification;

[0022] Figure 2 FIG. 2 is a flowchart of an operation and maintenance data processing method provided by one embodiment of the present specification;

[0023] Figure 3 FIG. 3 is a flowchart of a first target problem graph construction method provided by one embodiment of the present specification;

[0024] Figure 4 FIG. 4 is a flowchart of a second target problem graph construction method provided by one embodiment of the present specification;

[0025] Figure 5 FIG. 5 is a flowchart of a third target problem graph construction method provided by one embodiment of the present specification;

[0026] Figure 6 FIG. 6 is a processing process flowchart of an operation and maintenance data processing method provided by one embodiment of the present specification;

[0027] Figure 7 FIG. 7 is a structural schematic diagram of an operation and maintenance data processing device provided by one embodiment of the present specification;

[0028] Figure 8 This is a structural block diagram of a computing device provided by one embodiment of this specification. DETAILED DESCRIPTION

[0029] The following description sets forth many specific details to facilitate a thorough understanding of this specification. However, this specification can be implemented in many other ways than those described herein, and those skilled in the art can make similar generalizations without violating the scope of this specification. Therefore, this specification is not limited to the specific implementations disclosed below.

[0030] The terms used in one or more embodiments of this specification are for the purpose of describing specific embodiments only and are not intended to limit one or more embodiments of this specification. The singular forms of "a", "said" and "the" used in one or more embodiments of this specification and the appended claims are also intended to include plural forms, unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used in one or more embodiments of this specification refers to and includes any or all possible combinations of one or more associated listed items. The term "at least one" in one or more embodiments of this application refers to "one or more" and "a plurality" refers to "two or more". The term "including" is an open description and should be understood as "including but not limited to", and may include other content on the basis of the content already described.

[0031] It should be understood that although the terms first, second, etc. may be used to describe various information in one or more embodiments of this specification, such information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of one or more embodiments of this specification, the first may also be referred to as the second, and similarly, the second may also be referred to as the first. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0032] In addition, it should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in one or more embodiments of this specification are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0033] In one or more embodiments of the present specification, a large model refers to a deep learning model with a large number of model parameters, usually containing hundreds of millions, billions, tens of billions, hundreds of billions, or even tens of billions of model parameters. The large model can also be called a foundation model. Through large-scale unlabeled corpus pre-training, a pre-trained model with hundreds of millions of parameters is produced. This model can adapt to a wide range of downstream tasks and has good generalization ability. For example, large language models (LLM) and multi-modal pre-training models.

[0034] In practical applications, a large model only needs a small amount of sample data to fine-tune the pre-trained model and can be applied to different tasks. Large models can be widely used in natural language processing (NLP) and computer vision fields. Specifically, they can be applied to computer vision tasks such as visual question answering (VQA), image captioning (IC), image generation, and natural language processing tasks such as text-based sentiment classification, text summarization generation, and machine translation. The main application scenarios of large models include digital assistants, intelligent robots, search, online education, office software, e-commerce, intelligent design, etc.

[0035] First, the technical terms related to one or more embodiments of the present specification are explained.

[0036] Sensor technology: In rail transit operation and maintenance, sensors are used to collect various types of operating data of equipment in real time, such as temperature, vibration, pressure, etc. For example, by installing temperature sensors and vibration sensors on key components of trains (such as motors, bearings, etc.), the temperature and vibration state information of the equipment can be obtained in real time, providing a data basis for subsequent fault diagnosis.

[0037] Data acquisition and transmission technology: A large amount of equipment operating data collected needs to be transmitted to the data processing center in a timely and accurate manner. Currently, wired and wireless communication technologies are widely used in data transmission, such as optical fiber networks, 4G / 5G communication, etc., to ensure that data can be transmitted stably and quickly.

[0038] Data analysis and processing technology: Faced with massive amounts of equipment operating data, extracting valuable information to enable fault diagnosis and prediction is crucial. Data analysis technologies include traditional statistical analysis methods as well as emerging machine learning and deep learning algorithms. For example, machine learning algorithms can be used to study and analyze historical fault data and real-time monitoring data to build fault prediction models, predicting potential equipment failures in advance and providing a basis for operational and maintenance decisions.

[0039] An agent is a fundamental concept in the field of artificial intelligence, specifically referring to an entity that can autonomously perform tasks, perceive its environment, and make decisions based on environmental changes. Agents can operate in a variety of environments, including the physical and digital worlds, and can be implemented as software or hardware, or even a combination of both. Key characteristics of agents include: Autonomy: Agents are able to operate independently without direct human intervention and have the ability to control their internal state and behavior. Responsiveness: Agents are able to respond to changes in their environment, for example, by adjusting their actions based on sensor data to adapt to new situations. Sociality: Some agents are able to communicate and collaborate with other agents or humans to jointly complete tasks. This interaction can be achieved through messaging or other communication mechanisms. Goal-directedness: Agents are typically designed to pursue specific goals or complete specific tasks. Learning: Agents have the ability to learn from experience and continuously adjust their behavior to improve their performance in future tasks.

[0040] In this specification, an operation and maintenance data processing method is provided. This specification also involves an operation and maintenance data processing device, a computing device, a computer-readable storage medium and a computer program product, which are described in detail one by one in the following embodiments.

[0041] See also Figure 1 , Figure 1 The diagram shows an architecture diagram of an operation and maintenance data processing system provided by an embodiment of the present specification. The operation and maintenance data processing system may include a client 100 and a server 200;

[0042] The client 100 is used to send the operation and maintenance data of the target operation and maintenance scenario to the server 200;

[0043] The server 200 is used to perform fault analysis on the operation and maintenance data to obtain operation and maintenance problems of the operation and maintenance data; based on the operation and maintenance problems, the initial problem map of the target operation and maintenance scenario is updated to obtain a target problem map of the target operation and maintenance scenario, wherein the initial problem map includes at least one initial sub-graph, the initial sub-graph is constructed with the initial operation and maintenance problem as the root node and the initial operation and maintenance data of the initial operation and maintenance problem as the child nodes, and the target problem map includes at least one target operation and maintenance problem; based on the target problem map, a target response result for at least one target operation and maintenance problem is generated.

[0044] By applying the solution of the embodiments of this specification to systematically collect and analyze the operation and maintenance data in the target operation and maintenance scenario, the operation and maintenance problems in the target operation and maintenance scenario can be identified more comprehensively and accurately, the problems of missed detection or false detection can be reduced, and the comprehensiveness and accuracy of operation and maintenance data processing can be improved; by updating the initial problem map to obtain the target problem map, it is helpful to organize and associate different operation and maintenance problems and operation and maintenance data, and ensure the timeliness of the target problem map, which helps to better understand and deal with complex operation and maintenance environments. At the same time, through the structured knowledge representation form of the target problem map, similar operation and maintenance problems can be quickly retrieved, which greatly improves the efficiency of solving operation and maintenance problems. In addition, the entire operation and maintenance data processing process is a highly automated process, which not only improves the efficiency of operation and maintenance data processing, but also reduces dependence on human resources and reduces labor costs.

[0045] In an optional embodiment of this specification, the client 100 is further configured to send to the server 200 pending operation and maintenance issues of the target operation and maintenance scenario;

[0046] The server 200 is configured to select a matching operation and maintenance problem that matches the operation and maintenance problem to be processed from at least one target operation and maintenance problem included in the target problem map of the target operation and maintenance scenario; determine a matching answer result of the matching operation and maintenance problem as a response result of the operation and maintenance problem to be processed; and send the response result of the operation and maintenance problem to the client 100;

[0047] The client 100 is also used to receive the response results of the pending operation and maintenance issues sent by the server 200.

[0048] It should be noted that the target problem map of the target operation and maintenance scenario is obtained by updating the initial problem map of the target operation and maintenance scenario based on the operation and maintenance problem. The operation and maintenance problem is obtained based on fault analysis of the operation and maintenance data of the target operation and maintenance scenario. The initial problem map includes at least one initial sub-graph. The initial sub-graph is constructed with the initial operation and maintenance problem as the root node and the initial operation and maintenance data of the initial operation and maintenance problem as sub-nodes.

[0049] In actual application, the operation and maintenance data processing system can include the server 200 and a plurality of clients 100. The plurality of clients 100 can establish a communication connection through the server 200. In the operation and maintenance data processing scenario, the server 200 is used to provide operation and maintenance data processing services between the plurality of clients 100. The plurality of clients 100 can respectively act as a sending end or a receiving end to realize communication through the server 200. A user can interact with the server 200 through the client 100 to receive data sent by other clients 100 or send data to other clients 100, and the like. In the operation and maintenance data processing scenario, the user can publish a data stream to the server 200 through the client 100. The server 200 generates a reply result of a to-be-processed operation and maintenance problem according to the data stream, and pushes the reply result of the to-be-processed operation and maintenance problem to other clients that establish a communication connection. The client 100 and the server 200 establish a connection through a network. The network provides a medium for a communication link between the client 100 and the server 200. The network can include various connection types, such as a wired, wireless communication link, or a fiber optic cable, and the like. The data transmitted by the client 100 can need to be processed through encoding, transcoding, compression, and the like before being published to the server 200.

[0050] The client 100 can be a browser, an application (APP), or a web application such as a HyperText Markup Language 5 (H5) application, or a light application (also referred to as a mini-program, a lightweight application), or a cloud application, and the like. The client 100 can be developed based on a software development kit (SDK) of a corresponding service provided by the server 200, such as an Real Time Communication (RTC) SDK. The client 100 can be deployed in an electronic device and needs to depend on the device or some APP in the device to run, and the like. The electronic device can have a display screen and support information browsing, such as a personal mobile terminal such as a mobile phone, a tablet computer, a personal computer, and the like. Various other types of applications can also be configured in the electronic device, such as human-computer dialogue applications, model training applications, text processing applications, web browser applications, shopping applications, search applications, instant communication tools, mailbox clients, social platform software, and the like.

[0051] The service end 200 can include a server providing various services, for example, a server providing a communication service for multiple clients, for example, a server for background training supporting a model used on a client, for example, a server processing data sent by a client, and the like. It should be noted that the service end 200 can be implemented as a distributed server cluster composed of multiple servers, or as a single server. The server can also be a server of a distributed system, or a server combined with a blockchain. The server can also be a cloud server of a cloud service, a cloud database, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content distribution networks (CDN, Content Delivery Network), and big data and artificial intelligence platforms, and the like. Basic cloud computing services of artificial intelligence technology, or an intelligent cloud computing server or intelligent cloud host with artificial intelligence technology.

[0052] It should be noted that the operation and maintenance data processing method provided in the embodiments of the present specification is generally executed by the service end, but in other embodiments of the present specification, the client can also have similar functions as the service end, so as to execute the operation and maintenance data processing method provided in the embodiments of the present specification. In other embodiments, the operation and maintenance data processing method provided in the embodiments of the present specification can also be executed by the client and the service end together.

[0053] Referring to Figure 2 , Figure 2 A flowchart of an operation and maintenance data processing method provided by an embodiment of the present specification is shown, which specifically includes the following steps:

[0054] Step 202: Obtain operation and maintenance data of a target operation and maintenance scenario.

[0055] It should be noted that the target operation and maintenance scenario refers to a specific operation and maintenance management range or application environment defined in a specific field or industry in order to ensure the efficient, stable and safe operation of systems, devices, services or infrastructure. The target operation and maintenance scenario can be an operation and maintenance scenario in different fields. For example, the target operation and maintenance scenario can be a rail transit operation and maintenance scenario, a telecommunications network operation and maintenance scenario, an intelligent manufacturing operation and maintenance scenario, a smart city operation and maintenance scenario, and the like. The operation and maintenance data refers to various information collected from the target operation and maintenance scenario, including but not limited to device running status, system log, performance index, error report, and the like. The operation and maintenance data can be multi-modal operation and maintenance data, such as text data, visual data (such as images, videos), audio data, and the like.

[0056] For example, in rail transit operations and maintenance scenarios, operations and maintenance data can include equipment visual data, sensor monitoring data, signaling system data, operational data, and more. Equipment visual data is typically collected by cameras installed along the track, at stations, or on vehicles. It can be used to monitor the train's appearance (e.g., damage to wheels and car bodies), track conditions (for foreign objects, track deformation), and passenger flow on platforms and in train cars. Sensor monitoring data refers to data collected by various sensors. Sensors include, but are not limited to, the following: temperature sensors, used to monitor the internal and external ambient temperature of the train and the operating temperature of electrical equipment. Vibration sensors, used to detect the operating status of mechanical components during train operation and identify abnormal vibrations to provide early warning of potential failures. Pressure sensors, used to monitor key parameters such as brake system pressure and tire-rail contact pressure. Speed ​​sensors, used to record train speed in real time to ensure driving safety. Signaling system data refers to the operating status of the train control system, such as signal light status and automatic train protection system data, to ensure safe spacing between trains and correct travel direction. In intelligent manufacturing operations and maintenance scenarios, operations and maintenance data includes operational data from automated production lines, robots, CNC machine tools, and other equipment. In the smart city operation and maintenance scenario, operation and maintenance data includes urban traffic management data, public safety monitoring data, environmental monitoring data, etc.

[0057] In practical applications, there are multiple ways to obtain operation and maintenance data for the target operation and maintenance scenario, and the specific method to be selected depends on the actual situation. The embodiments of this specification do not impose any restrictions on this. In one possible implementation of this specification, the operation and maintenance data of the target operation and maintenance scenario can be read from other data acquisition devices or databases. In another possible implementation of this specification, the operation and maintenance data of the target operation and maintenance scenario can be collected in real time.

[0058] For example, taking the target operation and maintenance scenario as the rail transit operation and maintenance scenario, a drone equipped with high-definition camera equipment and related positioning and navigation systems can be used to monitor the rail transit scene through visual recognition technology to obtain visual data. During monitoring, the equipment, tracks, etc. in the rail transit scene can be inspected according to specific routes and time intervals through a preset flight path planning algorithm. The above process can be carried out by a visual monitoring agent (such as a drone agent). The drone agent is responsible for visual inspection of the equipment, tracks, etc. in the rail transit scene, taking various videos and photos during the drone flight to obtain real-time appearance status information of the rail transit facilities. Provide intuitive image data for subsequent fault analysis. In addition to the visual data collected by the drone agent, it can also receive sensor data and technical documents transmitted by monitoring equipment such as sensors.

[0059] Step 204: Perform fault analysis on the operation and maintenance data to obtain operation and maintenance problems of the operation and maintenance data.

[0060] It should be noted that fault analysis refers to a process of detailed checking of operation and maintenance data to identify abnormalities or problems therein. Operation and maintenance problems refer to problems determined from operation and maintenance data based on the fault analysis process. Operation and maintenance problems can affect the normal operation or performance of equipment. Fault analysis includes at least one of fault identification and fault prediction, and therefore, operation and maintenance problems include at least one of existing operation and maintenance problems and predicted operation and maintenance problems.

[0061] In actual applications, the manner of performing fault analysis on operation and maintenance data to obtain operation and maintenance problems of the operation and maintenance data is not limited in the embodiments of the present specification. In a possible implementation manner of the present specification, an operation and maintenance problem template and an operation and maintenance data template corresponding to the operation and maintenance problem template can be obtained, and an operation and maintenance problem template corresponding to an operation and maintenance data template matched with the operation and maintenance data is determined as the operation and maintenance problem of the operation and maintenance data. In another possible implementation manner of the present specification, a fault analysis model can be used to perform fault analysis on the operation and maintenance data to obtain operation and maintenance problems of the operation and maintenance data, wherein the fault analysis model refers to a deep learning model with fault identification and / or fault prediction capabilities, and the fault analysis model is, for example, a pre-trained large model.

[0062] In an optional embodiment of the present specification, the above-mentioned performing fault analysis on operation and maintenance data to obtain operation and maintenance problems of the operation and maintenance data can include the following steps:

[0063] performing fault identification on the operation and maintenance data to obtain operation and maintenance problems of the operation and maintenance data; and / or,

[0064] performing fault prediction on the operation and maintenance data to obtain operation and maintenance problems of the operation and maintenance data.

[0065] It should be noted that fault identification refers to the process of identifying existing fault problems in operation and maintenance data. Fault identification can be understood as a fault post-processing process. Fault prediction refers to the process of predicting possible future fault problems in operation and maintenance data. Fault prediction can be understood as a pre-warning process. Fault identification can help quickly determine existing fault problems and ensure the instant stability of the system. Fault prediction can help discover potential risks in advance and provide operation and maintenance teams with more preparation time, thereby reducing the probability of faults. For example, in the operation and maintenance scenario of rail transit, fault identification can be used to detect foreign object intrusion on the track or sudden failure of train equipment. Fault prediction can be used to predict problems such as track aging and equipment wear and tear, and to arrange maintenance plans in advance. The fault identification process can be based on image recognition algorithms, data mining algorithms, and machine learning models. For example, image recognition algorithms are used to identify videos and photos taken by unmanned aerial vehicle agents to determine the location or abnormal conditions of problems in the videos and photos. At the same time, machine learning models can be used to analyze operation and maintenance data in depth, mine potential relationships and rules between operation and maintenance data, and determine whether the equipment is in a normal state or whether there is a potential risk.

[0066] In actual applications, the implementation manners of “performing fault identification on operation and maintenance data to obtain operation and maintenance problems of the operation and maintenance data” and “performing fault prediction on operation and maintenance data to obtain operation and maintenance problems of the operation and maintenance data” can refer to the implementation manners of “performing fault analysis on operation and maintenance data to obtain operation and maintenance problems of the operation and maintenance data” described above, and the embodiments of the present specification will not be described herein again.

[0067] By using the scheme of the embodiments of the present specification, operation and maintenance problems of operation and maintenance data are determined through fault identification and / or fault prediction, which can more comprehensively and accurately identify operation and maintenance problems in a target operation and maintenance scenario, reduce missed or false detection problems, and improve the comprehensiveness and accuracy of operation and maintenance data processing.

[0068] In an optional embodiment of the present specification, when performing fault prediction on operation and maintenance data, the operation and maintenance data can be directly predicted. Further, to improve the accuracy of fault prediction, historical operation and maintenance data of a target operation and maintenance scenario and historical operation and maintenance problems of the historical operation and maintenance data can also be additionally considered. That is, the above-mentioned performing fault prediction on operation and maintenance data to obtain operation and maintenance problems of the operation and maintenance data can include the following steps:

[0069] Obtaining historical operation and maintenance data of a target operation and maintenance scenario and historical operation and maintenance problems of the historical operation and maintenance data;

[0070] Performing fault prediction on the operation and maintenance data according to the historical operation and maintenance data and the historical operation and maintenance problems to obtain operation and maintenance problems of the operation and maintenance data.

[0071] It should be noted that the historical operation and maintenance data refers to the operation and maintenance data collected from the target operation and maintenance scene in the past period of time. The historical operation and maintenance data can come from various log files, sensor outputs, etc. The historical operation and maintenance data includes but is not limited to sensor historical data, device historical running state data. By analyzing the historical operation and maintenance data, it can help to predict possible future operation and maintenance problems, find common failure modes or normal operation modes, and help to improve the accuracy of fault prediction. The historical operation and maintenance problem of the historical operation and maintenance data is the operation and maintenance problem determined based on the analysis of the historical operation and maintenance data. The historical operation and maintenance problem can be understood as historical fault record data. The historical operation and maintenance problem may have been solved or may not have been completely solved, but it can provide problem insights and help to understand which problems need more attention or improvement.

[0072] In actual application, there are various ways to obtain the historical operation and maintenance data of the target operation and maintenance scene and the historical operation and maintenance problem of the historical operation and maintenance data, which are selected according to actual conditions, and the embodiments of the present specification do not make any limitation on this. In a possible implementation manner of the present specification, the historical operation and maintenance data of the target operation and maintenance scene and the historical operation and maintenance problem of the historical operation and maintenance data can be received and sent by the operation and maintenance object through the client. In another possible implementation manner of the present specification, the historical operation and maintenance data of the target operation and maintenance scene and the historical operation and maintenance problem of the historical operation and maintenance data can be read from other data acquisition equipment or databases.

[0073] Further, there are various ways to perform fault prediction on the operation and maintenance data according to the historical operation and maintenance data and the historical operation and maintenance problem to obtain the operation and maintenance problem of the operation and maintenance data, which are selected according to actual conditions, and the embodiments of the present specification do not make any limitation on this. In a possible implementation manner of the present specification, the historical operation and maintenance data and the historical operation and maintenance problem can be used as fault prediction samples to generate the operation and maintenance problem of the operation and maintenance data by referring to the fault prediction samples through data analysis technology. In another possible implementation manner of the present specification, a fault prediction model (neural network model) can be trained by using the historical operation and maintenance data and the historical operation and maintenance problem, or a fault prediction model (mathematical model) can be constructed by using the historical operation and maintenance data, the historical operation and maintenance problem, and statistical, heuristic rules, and statistical machine models or light discriminant algorithm models, and the operation and maintenance data is input into the trained fault prediction model to obtain the operation and maintenance problem output by the fault prediction model.

[0074] By applying the scheme of the embodiments of the present specification, the operation and maintenance data (such as device running state data, sensor data) of the target operation and maintenance scene is monitored in real time, and the possible operation and maintenance problems are predicted, so as to provide a basis for formulating a maintenance plan, realize preventive maintenance, reduce unnecessary periodic calibration, maintenance and replacement operations, reduce maintenance cost and difficulty, and improve maintenance efficiency.

[0075] In an optional embodiment of the present specification, since the operation and maintenance data can be affected by various scene factors in the target operation and maintenance scene, such as sensor failure, high temperature, high humidity, strong electromagnetic interference, etc., resulting in distortion or abnormality of the operation and maintenance data, in order to ensure the accuracy of the operation and maintenance problem, the operation and maintenance data can be corrected before fault analysis, that is, before the above-mentioned fault analysis of the operation and maintenance data to obtain the operation and maintenance problem of the operation and maintenance data, the following steps can also be included:

[0076] Obtain scene information corresponding to the operation and maintenance data;

[0077] According to the scene information, the operation and maintenance data is verified to obtain a verification result;

[0078] In the case where it is determined based on the verification result that the operation and maintenance data does not meet the verification condition, the operation and maintenance data is modified to obtain modified operation and maintenance data, wherein the modified operation and maintenance data meets the verification condition;

[0079] The operation and maintenance data is analyzed for fault to obtain the operation and maintenance problem of the operation and maintenance data, which can include the following steps:

[0080] The modified operation and maintenance data is analyzed for fault to obtain the operation and maintenance problem of the operation and maintenance data.

[0081] It should be noted that the scene information refers to the background information when the operation and maintenance data is generated. The scene information includes but is not limited to the generation device state of the operation and maintenance data (such as sensor running state), generation environment information (such as temperature, humidity, electromagnetic interference, etc.). The sensor running state, such as whether it is working normally, whether its reading is reliable. The generation device state can be obtained through the self-diagnosis ability of the generation device, or through the comparative analysis of the historical operation and maintenance data and real-time operation and maintenance data of the generation device. The generation environment information can be obtained through environmental monitoring sensors, such as measuring the environmental temperature and humidity when the operation and maintenance data is generated through temperature and humidity sensors, and measuring the electromagnetic interference degree when the operation and maintenance data is generated through electromagnetic field intensity sensors.

[0082] The check result can reflect whether the operation and maintenance data is abnormal due to abnormal environment information or device state failure. The check condition is a standard or rule set in advance, which is used to determine whether to perform fault analysis on the operation and maintenance data. The check condition, such as normal operation and maintenance data generation environment and normal device state, is selected according to actual conditions, and the embodiments of the present specification do not make any limitation on this. In the case of determining that the operation and maintenance data meets the check condition based on the check result, it is indicated that the operation and maintenance data is not affected by various scene factors in the target operation and maintenance scene, and is the data that can accurately reflect the operation and maintenance problem. At this time, the operation and maintenance data can be analyzed for fault, and the operation and maintenance problem of the operation and maintenance data can be obtained. In the case of determining that the operation and maintenance data does not meet the check condition based on the check result, it is indicated that the operation and maintenance data is affected by various scene factors in the target operation and maintenance scene, and cannot accurately reflect the operation and maintenance problem. At this time, the operation and maintenance data can be modified until the modified operation and maintenance data meets the check condition.

[0083] In actual application, when the operation and maintenance data is checked according to the scene information, a sensor fault diagnosis algorithm, a multi-modal comparison model and the like can be used, wherein the sensor fault diagnosis algorithm is an algorithm for detecting and diagnosing the running state of the sensor itself, aiming to identify whether the sensor fails (such as drift, failure, excessive noise, etc.), and to judge the credibility of its readings. The multi-modal comparison model is an intelligent analysis model based on multi-source heterogeneous data (such as sensor data, visual data, log data, etc.), which can compare the consistency between different modal operation and maintenance data to obtain a check result.

[0084] Further, there are various ways to modify the operation and maintenance data to obtain the modified operation and maintenance data, which are selected according to actual conditions, and the embodiments of the present specification do not make any limitation on this. In the first possible implementation manner of the present specification, the operation and maintenance data can be modified by an environment adaptive algorithm to obtain the modified operation and maintenance data. The environment adaptive algorithm is an intelligent algorithm that can dynamically adjust the operation and maintenance data according to the environmental factors (such as temperature, humidity, electromagnetic interference, etc.) in the target operation and maintenance scene, and improve the accuracy and reliability of the operation and maintenance data. In the second possible implementation manner of the present specification, the operation and maintenance data can be modified by an intelligent correction algorithm, such as a multi-modal comparison model, to obtain the modified operation and maintenance data, so as to ensure the accuracy of the modified operation and maintenance data and provide a reliable data basis for subsequent fault analysis. In the third possible implementation manner of the present specification, a plurality of sensors can be deployed, the data of the plurality of sensors can be combined, and methods such as weighted average and Kalman filtering can be used to improve the accuracy and robustness of the overall system, or machine learning or deep learning algorithms can be used to analyze the error mode of the sensor data and perform real-time compensation, and a neural network can be used to predict and correct the drift caused by environmental factors such as temperature and humidity to improve the accuracy and reliability of the sensor data.

[0085] By applying the scheme of the embodiments of the present specification, for the problem that the precision and reliability of the operation and maintenance data such as sensors are affected in a complex target operation and maintenance scene, the operation and maintenance data can be monitored and corrected intelligently in real time, the accuracy of the collected operation and maintenance data is ensured, the misjudgment and missed judgment of the operation and maintenance problem caused by inaccurate or missing operation and maintenance data are effectively avoided, and the comprehensiveness, accuracy and reliability of the operation and maintenance data processing are improved.

[0086] Step 206: updating the initial problem graph of the target operation and maintenance scene according to the operation and maintenance problem, to obtain a target problem graph of the target operation and maintenance scene, wherein the initial problem graph includes at least one initial subgraph, the initial subgraph is constructed with an initial operation and maintenance problem as a root node and initial operation and maintenance data of the initial operation and maintenance problem as a child node, and the target problem graph includes at least one target operation and maintenance problem.

[0087] It should be noted that the initial problem graph refers to a structured graph constructed based on the initial operation and maintenance data and the initial operation and maintenance problem of the initial operation and maintenance data of the target operation and maintenance scene before the operation and maintenance data of the target operation and maintenance scene is obtained. The initial problem graph is composed of at least one initial subgraph, and each initial subgraph is constructed around a specific initial operation and maintenance problem, which can be used as a root node, and all initial operation and maintenance data related to the initial operation and maintenance problem can be used as a child node. When the initial problem graph includes multiple initial subgraphs, different initial subgraphs may have one or more shared child nodes, that is, the initial operation and maintenance data corresponding to the shared child node is related to the initial operation and maintenance problems in different initial subgraphs at the same time. For example, the initial problem graph includes an initial subgraph Figure 1 and an initial subgraph Figure 2 , the initial subgraph Figure 1 takes the initial operation and maintenance problem 1 as a root node, and takes the initial operation and maintenance data 1 and the initial operation and maintenance data 2 as child nodes, the initial subgraph Figure 2 takes the initial operation and maintenance problem 2 as a root node, and takes the initial operation and maintenance data 2 and the initial operation and maintenance data 3 as child nodes, then the initial operation and maintenance data 2 can be regarded as a shared child node of the initial subgraph Figure 1 and the initial subgraph Figure 2 , and the initial subgraph Figure 1 and the initial subgraph Figure 2 are connected through the shared child node.

[0088] The target problem graph is obtained by updating the initial problem graph according to newly acquired operation and maintenance data and operation and maintenance problems. The target problem graph includes operation and maintenance problems and / or operation and maintenance data of the operation and maintenance problems. Through the target problem graph, different operation and maintenance problems in the target operation and maintenance scene can be displayed in an intuitive manner, and a clear framework is provided for subsequent problem processing. The target operation and maintenance problem refers to the root node included in the target problem graph. The target operation and maintenance problem can include the initial operation and maintenance problem, or the operation and maintenance data of the operation and maintenance problem. The target operation and maintenance problem represents the operation and maintenance problem that needs to be focused on and solved in the current target operation and maintenance scene. In addition to the target operation and maintenance problem, the target problem graph also includes target operation and maintenance data of the target operation and maintenance problem. The target operation and maintenance data refers to all operation and maintenance data related to the target operation and maintenance problem. The target problem graph and the initial problem graph have the same structure.

[0089] In actual applications, there are various ways to update the initial problem graph of the target operation and maintenance scene according to the operation and maintenance problem to obtain the target problem graph of the target operation and maintenance scene. The specific selection is based on actual conditions, and the embodiments of the present specification do not make any limitation thereon. In one possible implementation manner of the present specification, a target subgraph with the operation and maintenance problem as the root node and the operation and maintenance data as the child node can be directly added in the initial problem graph to obtain the target problem graph. In another possible implementation manner of the present specification, the initial problem graph can include an initial operation and maintenance problem that is the same as or highly similar to the operation and maintenance problem, and an initial operation and maintenance data that is the same as or highly similar to the operation and maintenance data. Therefore, in order to avoid adding redundant operation and maintenance problems and operation and maintenance data in the initial problem graph, whether to add the operation and maintenance data and the operation and maintenance problem to the initial problem graph to obtain the target problem graph of the target operation and maintenance scene can be determined through a node merging condition.

[0090] In an optional embodiment of the present specification, the above updating the initial problem graph of the target operation and maintenance scene according to the operation and maintenance problem to obtain the target problem graph of the target operation and maintenance scene can include the following steps:

[0091] Comparing the operation and maintenance problem with the initial operation and maintenance problem to obtain a problem comparison result;

[0092] Updating the initial problem graph according to the problem comparison result to obtain the target problem graph of the target operation and maintenance scene.

[0093] It should be noted that the problem comparison result refers to a result obtained by comparing the difference between the operation and maintenance problem and the initial operation and maintenance problem. The problem comparison result is used to describe the similarity between the operation and maintenance problem and the initial operation and maintenance problem. The problem comparison result can be a problem similarity, such as 0.8, or a similarity level, such as very similar or relatively similar. The comparison between the operation and maintenance problem and the initial operation and maintenance problem can be achieved in a manner including but not limited to a comparison manner based on a cosine similarity and a comparison manner based on a Euclidean distance, and the embodiments of the present specification do not make any limitation on this.

[0094] By applying the scheme of the embodiments of the present specification, whether the operation and maintenance problem and the operation and maintenance data are to be added to the initial problem graph is determined based on the problem comparison result between the operation and maintenance problem and the initial operation and maintenance problem, so that the existing redundant problems and data in the initial problem graph can be avoided from being added to the initial problem graph, the operation and maintenance data processing pressure caused by the redundant data is effectively alleviated, the target problem graph is made more clear, and the problem solving efficiency based on the target problem graph is improved.

[0095] In actual application, when the initial problem graph is updated according to the problem comparison result to obtain the target problem graph of the target operation and maintenance scene, it can be determined whether the problem comparison result satisfies the node merging condition. In the case that the operation and maintenance problem satisfies the node merging condition based on the problem comparison result, it indicates that the initial operation and maintenance problem in the initial problem graph includes the same or highly similar initial operation and maintenance problem as the operation and maintenance problem, and the operation and maintenance problem does not need to be added to the initial problem graph. Only the child nodes of the initial operation and maintenance problem need to be perfected by using the operation and maintenance data of the operation and maintenance problem. In the process of perfecting the child nodes of the initial operation and maintenance problem by using the operation and maintenance data of the operation and maintenance problem, in one possible implementation manner of the present specification, the operation and maintenance data can be directly added to the initial problem graph as the child nodes of the initial operation and maintenance problem to obtain the target problem graph of the target operation and maintenance scene. In another possible implementation manner of the present specification, the initial operation and maintenance data of the initial operation and maintenance problem can also include the same or highly similar data as the operation and maintenance data of the operation and maintenance problem. Therefore, the operation and maintenance data that is different from the initial operation and maintenance data or has a low similarity can be screened out from the operation and maintenance data, and the screened operation and maintenance data can be added to the initial problem graph as the new child nodes of the initial operation and maintenance problem to obtain the target problem graph of the target operation and maintenance scene. In the case that the operation and maintenance problem does not satisfy the node merging condition based on the problem comparison result, it indicates that the initial operation and maintenance problem does not exist in the initial problem graph, and the operation and maintenance problem needs to be added to the initial problem graph as the root node of the new target subgraph. In the process of adding the new target subgraph to the initial problem graph, in one possible implementation manner of the present specification, all the operation and maintenance data of the operation and maintenance problem can be added to the initial problem graph as the root node of the operation and maintenance problem. In another possible implementation manner of the present specification, since the initial operation and maintenance data included in the initial problem graph can include the same or highly similar data as the operation and maintenance data of the operation and maintenance problem, the operation and maintenance data that is different from the initial operation and maintenance data or has a low similarity can be screened out from the operation and maintenance data, and the screened operation and maintenance data can be added to the initial problem graph as the child nodes of the operation and maintenance problem. Meanwhile, an edge is added between the operation and maintenance problem and the initial operation and maintenance data that is the same or highly similar to the operation and maintenance data of the operation and maintenance problem to obtain the target problem graph of the target operation and maintenance scene.

[0096] In one optional embodiment of the present specification, the above updating the initial problem graph according to the problem comparison result to obtain the target problem graph of the target operation and maintenance scene can include the following steps:

[0097] In the case that the operation and maintenance problem satisfies the node merging condition based on the problem comparison result, the operation and maintenance data is added to the initial problem graph as the child node of the initial operation and maintenance problem to obtain the target problem graph of the target operation and maintenance scene.

[0098] In a case where it is determined based on the problem comparison result that the operation and maintenance problem does not satisfy the node merging condition, a target subgraph is added in the initial problem graph to obtain a target problem graph of the target operation and maintenance scene, where the target subgraph is constructed with the operation and maintenance problem as a root node and the operation and maintenance data as a child node.

[0099] It should be noted that the node merging condition refers to a standard or rule for determining whether to merge the operation and maintenance problem with the initial operation and maintenance problem. The node merging condition is, for example, that the operation and maintenance problem and the initial operation and maintenance problem are the same or highly similar, the operation and maintenance data and the initial operation and maintenance data are the same or highly similar, or the processing suggestion and the initial processing suggestion are the same or highly similar. The node merging condition is specifically selected according to actual conditions, and the embodiments of the present specification do not make any limitation thereto. The highly similar refers to, for example, a similarity greater than a preset threshold or a similarity level greater than a preset level.

[0100] For example, in a case where it is determined based on the problem comparison result that the operation and maintenance problem satisfies the node merging condition, it can be determined that the operation and maintenance problem and the initial operation and maintenance problem are the same or highly similar, which indicates that the operation and maintenance problem and the initial operation and maintenance problem describe one fault problem, or a measure for solving one problem can also solve the other problem. Therefore, the operation and maintenance data can be added to the initial problem graph as a child node of the initial operation and maintenance problem to obtain a target problem graph of the target operation and maintenance scene. In a case where it is determined based on the problem comparison result that the operation and maintenance problem does not satisfy the node merging condition, it can be determined that the operation and maintenance problem and the initial operation and maintenance problem are not the same or have a low similarity, which indicates that the operation and maintenance problem and the initial operation and maintenance problem are two different fault problems, or a measure for solving one problem cannot solve the other problem. Therefore, the operation and maintenance problem and the operation and maintenance data of the operation and maintenance problem can be added to the initial problem graph to obtain a target problem graph.

[0101] By applying the scheme of the embodiments of the present specification, the initial problem graph is updated by determining whether to add the operation and maintenance problem and the operation and maintenance data to the initial problem graph according to the problem comparison result, which can avoid adding redundant problems already in the initial problem graph to the initial problem graph, and effectively alleviate the operation and maintenance data processing pressure caused by redundant data.

[0102] Referring to Figure 3 , Figure 3A flowchart of a first target problem graph construction method provided by an embodiment of the present specification is shown. The operation and maintenance data (such as pictures, videos, and sensor data) of a target operation and maintenance scene are obtained. The pictures, videos, and sensor data are analyzed for faults to obtain an operation and maintenance problem. It is determined whether the operation and maintenance problem meets a node merging condition. If yes, the pictures, videos, and sensor data are added to an initial problem graph as child nodes of an existing root node in the initial problem graph to obtain a target problem graph. If no, the operation and maintenance problem is added to the initial problem graph as a new root node, and the pictures, videos, and sensor data are added to the initial problem graph as child nodes of the new root node to obtain the target problem graph.

[0103] In actual applications, there are various ways to obtain a problem comparison result by comparing the operation and maintenance problem with the initial operation and maintenance problem. The specific selection is made according to actual conditions, and the embodiments of the present specification do not make any limitation thereon. In a possible implementation manner of the present specification, the operation and maintenance problem and the initial operation and maintenance problem can be directly compared to obtain the problem comparison result.

[0104] In another possible implementation manner of the present specification, since the operation and maintenance problem and the initial operation and maintenance problem can be long, in order to improve the comparison efficiency, the problem summary of the operation and maintenance problem and the initial problem summary of the initial operation and maintenance problem can be compared. That is, the above comparison of the operation and maintenance problem and the initial operation and maintenance problem to obtain the problem comparison result can include the following steps.

[0105] The operation and maintenance problem is summarized to obtain a problem summary, and the initial operation and maintenance problem is summarized to obtain an initial problem summary.

[0106] The problem summary and the initial problem summary are compared to obtain a problem comparison result.

[0107] It should be noted that summarization refers to a process of extracting key information from an operation and maintenance problem to generate a concise and accurate overview. Through summarization, the essence and key points of the operation and maintenance problem can be quickly understood. Summarization can be realized through an automatic tool or a summarization model. The problem summary refers to a result obtained by summarizing the operation and maintenance problem. The problem summary summarizes the essence and key points of the operation and maintenance problem. Summarization can also be referred to as summary extraction, and the problem summary can also be referred to as a problem summary.

[0108] By comparing the problem summary of the operation and maintenance problem with the initial problem summary of the initial operation and maintenance problem to obtain a problem comparison result, the data amount of comparison is reduced and the comparison efficiency is improved on the basis of ensuring the effectiveness and accuracy of the problem comparison result by applying the scheme of the embodiments of the present specification.

[0109] In an optional embodiment of the present specification, in addition to the comparison result of the problem, the initial problem graph can also be updated based on the comparison result of the data, that is, in the comparison, in addition to comparing the operation and maintenance problem and the initial operation and maintenance problem, the operation and maintenance data and the initial operation and maintenance data can also be compared. Before the initial problem graph is updated according to the comparison result of the problem to obtain the target problem graph of the target operation and maintenance scene, the following steps can also be included:

[0110] Comparing the operation and maintenance data and the initial operation and maintenance data to obtain a data comparison result;

[0111] Updating the initial problem graph according to the comparison result of the problem to obtain the target problem graph of the target operation and maintenance scene, including:

[0112] Updating the initial problem graph according to the comparison result of the problem and the data comparison result to obtain the target problem graph of the target operation and maintenance scene.

[0113] It should be noted that the data comparison result refers to a result obtained by comparing the differences between the operation and maintenance data and the initial operation and maintenance data. The data comparison result is used to describe the similarity between the operation and maintenance data and the initial operation and maintenance data. The data comparison result can be a data similarity, such as 0.8, or a similarity level, such as very similar or relatively similar. The way to compare the operation and maintenance data and the initial operation and maintenance data to obtain the data comparison result includes but is not limited to a comparison method based on cosine similarity and a comparison method based on Euclidean distance, which is not limited in the embodiments of the present specification.

[0114] In actual application, since the operation and maintenance data can be multi-modal data, the operation and maintenance data can be compared based on the modal of the operation and maintenance data to obtain the data comparison result. Taking an example in which the operation and maintenance data includes operation and maintenance text and operation and maintenance pictures and the initial operation and maintenance data includes initial operation and maintenance text and initial operation and maintenance pictures, the operation and maintenance text and the initial operation and maintenance text can be compared to obtain a text comparison result, the operation and maintenance pictures and the initial operation and maintenance pictures can be compared to obtain a picture comparison result, and the text comparison result and the picture comparison result can be weighted to obtain the data comparison result. When comparing the operation and maintenance pictures and the initial operation and maintenance pictures, a picture comparison model or a feature point matching method can be used for comparison, which is not limited in the embodiments of the present specification.

[0115] Further, according to the comparison result of the problem and the data comparison result, the initial problem graph can be updated by judging whether the comparison result of the problem and the data comparison result satisfy a node merging condition, and the initial problem graph is updated according to the judgment result. The process can refer to the implementation mode of the above-mentioned “updating the initial problem graph according to the comparison result of the problem to obtain the target problem graph of the target operation and maintenance scene”, and the embodiments of the present specification will not be described in detail.

[0116] By applying the scheme of the embodiments of the present specification, whether to add the operation and maintenance problem and the operation and maintenance data to the initial problem graph can be comprehensively evaluated based on the problem comparison result and the data comparison result, effectively relieving the operation and maintenance data processing pressure caused by redundant data, and making the target problem graph more clear and improving the subsequent problem solving efficiency based on the target problem graph.

[0117] In an optional embodiment of the present specification, in addition to the problem comparison result, the initial problem graph can also be updated based on the suggestion comparison result, that is, in the comparison, in addition to comparing the operation and maintenance problem and the initial operation and maintenance problem, the processing suggestion of the operation and maintenance problem and the initial processing suggestion of the initial operation and maintenance problem can also be compared. Before the initial problem graph is updated according to the problem comparison result to obtain the target problem graph of the target operation and maintenance scene, the following steps can also be included:

[0118] obtaining the processing suggestion of the operation and maintenance problem and the initial processing suggestion of the initial operation and maintenance problem;

[0119] comparing the processing suggestion and the initial processing suggestion to obtain a suggestion comparison result;

[0120] updating the initial problem graph according to the problem comparison result to obtain the target problem graph of the target operation and maintenance scene, comprising:

[0121] updating the initial problem graph according to the problem comparison result and the suggestion comparison result to obtain the target problem graph of the target operation and maintenance scene.

[0122] It should be noted that the processing suggestion of the operation and maintenance problem refers to a specific solution or recommended action step provided for the identified operation and maintenance problem. The processing suggestion aims to help the operation and maintenance team to quickly and effectively solve the problem, restore the normal operation state of the system, and prevent similar problems from occurring again in the future. The processing suggestion includes but is not limited to fault root cause, urgency, solution, preventive measures, and is selected according to actual conditions. The embodiments of the present specification do not make any limitation on this.

[0123] The suggestion comparison result refers to the result obtained by comparing the difference between the processing suggestion of the operation and maintenance problem and the initial processing suggestion of the initial operation and maintenance problem. The suggestion comparison result is used to describe the similarity between the processing suggestion and the initial processing suggestion. The suggestion comparison result can be a suggestion similarity, such as 0.8, or a similarity level, such as very similar, relatively similar. The way to compare the processing suggestion and the initial processing suggestion to obtain the suggestion comparison result includes but is not limited to a comparison method based on cosine similarity, a comparison method based on Euclidean distance, and the embodiments of the present specification do not make any limitation on this.

[0124] In actual applications, there are various manners to obtain the processing suggestion of the operation and maintenance problem, and the specific manner is selected according to actual conditions, and the embodiments of the present specification do not make any limitation on this. In a possible implementation manner of the present specification, the processing suggestion of the operation and maintenance problem can be searched from a professional knowledge base or an experience database. In another possible implementation manner of the present specification, the operation and maintenance problem can be input into a question and answer model to obtain the processing suggestion of the operation and maintenance problem, where the question and answer model can be a pre-trained large model, or a deep learning model trained based on sample processing suggestions and sample operation and maintenance problems corresponding to the sample processing suggestions. The implementation manner of "obtaining the initial processing suggestion of the initial operation and maintenance problem" is the same as that of "obtaining the processing suggestion of the operation and maintenance problem", and the embodiments of the present specification will not be repeated.

[0125] Exemplarily, the process of obtaining the processing suggestion of the operation and maintenance problem can be performed by an expert agent. The expert agent is internally built with rich professional knowledge and experience data in the target operation and maintenance scene, and can also call external technical documents for processing suggestion generation. The expert agent can analyze the operation and maintenance problem through a knowledge reasoning algorithm, search for relevant processing suggestions in the professional knowledge, experience data and technical documents, and provide professional guidance for other agents in problem processing, to ensure that the problem is reasonably and effectively solved.

[0126] Further, the implementation manner of "updating the initial problem graph according to the problem comparison result and the suggestion comparison result to obtain the target problem graph of the target operation and maintenance scene" can refer to the implementation manner of "updating the initial problem graph according to the problem comparison result to obtain the target problem graph of the target operation and maintenance scene" described above, and the embodiments of the present specification will not be repeated.

[0127] By applying the scheme of the embodiments of the present specification, based on the problem comparison result and the suggestion comparison result, it can be comprehensively evaluated whether the operation and maintenance problem and the operation and maintenance data are to be added to the initial problem graph, effectively alleviating the operation and maintenance data processing pressure brought by redundant data, and at the same time making the target problem graph more clear and improving the subsequent problem solving efficiency based on the target problem graph.

[0128] Referring to Figure 4 , Figure 4A flowchart of a second target problem graph construction method provided by one embodiment of the present specification is shown. The operation and maintenance data of a target operation and maintenance scene is obtained. Fault analysis is performed on the operation and maintenance data to obtain operation and maintenance problems (including problem text description and problem pictures) of the operation and maintenance data. The problem text description is abstracted to obtain a problem abstract of the operation and maintenance problem. The operation and maintenance problem is processed to generate a processing suggestion of the operation and maintenance problem. For an initial operation and maintenance problem in an initial problem graph and initial operation and maintenance data, a text comparison model is used to compare the problem abstract (compare the problem abstract with an initial problem abstract of the initial operation and maintenance problem), compare the processing suggestion (compare the processing suggestion with an initial processing suggestion of the initial operation and maintenance problem), and compare the problem text description (compare the problem text description of the operation and maintenance problem with an initial problem text description of the initial operation and maintenance problem) to obtain a text comparison result. An image comparison model is used to compare the problem pictures (compare the problem graph of the operation and maintenance problem with an initial operation and maintenance picture of the initial operation and maintenance problem) to obtain an image comparison result. The text comparison result and the image comparison result are weighted to obtain a weighted result. The initial problem graph of the target operation and maintenance scene is updated based on the weighted result to obtain a target problem graph.

[0129] Specifically, let P be a set of all nodes in the initial problem graph, and each node p i ∈P represents an initial operation and maintenance problem. Let N be the operation and maintenance data of the target operation and maintenance scene. Let S sum be a similarity function based on problem abstract comparison, S exp be a similarity function based on processing suggestion comparison, S data be a similarity function based on problem text description comparison, and S media be a similarity function based on problem picture comparison. The return values of these functions are all in the interval [0, 1], and the larger the value, the higher the similarity. Let θ be a similarity threshold value used to determine whether the operation and maintenance data of the target operation and maintenance scene can be attributed to an existing node in the initial problem graph. For each p i ∈P, the comprehensive similarity S total (p i ,N) is calculated by the following formula (1):

[0130] S total (p i ,N) = ω1×S sum (p i ,N) + ω2×S exp (p i ,N) + ω3×S data (p i ,N) + ω4×S media (p i ,N) (1)

[0131] Wherein, ω1, ω2, ω3, ω4 are the weights of each comparison, and ω1+ω2+ω3+ω4=1, the weight is set according to the importance of each comparison or default value. Then, the judgment classification is carried out:

[0132] If S total (p i ,N)≥θ, N is classified into p j .

[0133] If S total (p i ,N)<θ, a new graph node p new is created, and N is associated with p new P=P∪{p new}.

[0134] Referring to Figure 5 , Figure 5 , a flowchart of a third target problem graph construction method provided by an embodiment of the present specification is shown. The construction process of the target problem graph can be carried out by the cooperation of the data analysis intelligent agent, the assistant intelligent agent, the visual monitoring intelligent agent and the expert intelligent agent. The data analysis intelligent agent can determine the problem text description of the operation and maintenance problem, the assistant intelligent agent can determine the problem abstract of the operation and maintenance problem, the visual monitoring intelligent agent can determine the problem picture of the operation and maintenance problem, and the expert intelligent agent can determine the processing suggestion of the operation and maintenance problem. After the data analysis intelligent agent, the assistant intelligent agent, the visual monitoring intelligent agent and the expert intelligent agent cooperate to obtain these information, the target problem graph can be constructed with the problem text description, the problem abstract, the problem picture, the processing suggestion, the operation and maintenance problem and the operation and maintenance problem original text as nodes.

[0135] Step 208: According to the target problem graph, at least one target reply result of the target operation and maintenance problem is generated.

[0136] It should be noted that the target reply result refers to the specific solution or suggestion measure generated for each target operation and maintenance problem based on the target problem graph. Through the target reply result, the operation and maintenance personnel can effectively solve the problem and improve the system running condition.

[0137] In actual applications, there are various ways to generate the target reply result of the target operation and maintenance problem according to the target problem graph, which are selected according to actual conditions, and the embodiments of the present specification do not make any limitation on this. In a possible implementation manner of the present specification, target operation and maintenance data of the target operation and maintenance problem can be acquired from the target problem graph, and the target reply result of the target operation and maintenance problem is generated according to the target operation and maintenance problem and the target operation and maintenance data. In another possible implementation manner of the present specification, an associated operation and maintenance problem of the target operation and maintenance problem can be acquired from the target problem graph, wherein the associated operation and maintenance problem refers to an operation and maintenance problem in the target problem graph that shares a sub-node (shared operation and maintenance data) with the target operation and maintenance problem, and the target reply result of the target operation and maintenance problem is generated according to the associated operation and maintenance problem and the target operation and maintenance problem. The implementation manner of "generating the target reply result of the target operation and maintenance problem" can refer to the implementation manner of "acquiring the processing suggestion of the operation and maintenance problem" described above, and the embodiments of the present specification will not be described again.

[0138] By applying the scheme of the embodiments of the present specification, the operation and maintenance data in the target operation and maintenance scenario can be systematically collected and analyzed, the operation and maintenance problem in the target operation and maintenance scenario can be more comprehensively and accurately identified, the problem of missed detection or false detection can be reduced, and the comprehensiveness and accuracy of operation and maintenance data processing can be improved; the target problem graph obtained by updating the initial problem graph helps to organize and associate different operation and maintenance problems and operation and maintenance data, ensures the timeliness of the target problem graph, helps to better understand and cope with complex operation and maintenance environment, and at the same time, through the structured knowledge representation form of the target problem graph, similar operation and maintenance problems can be quickly searched, and the solving efficiency of the operation and maintenance problem is greatly improved. Moreover, the entire operation and maintenance data processing process is a highly automated process, which not only improves the operation and maintenance data processing efficiency, but also reduces the dependence on human resources and reduces the human cost.

[0139] In an optional embodiment of the present specification, operation and maintenance problem solving can be performed based on the target problem graph, that is, after the target reply result of at least one target operation and maintenance problem is generated according to the target problem graph, the following steps can be further included:

[0140] receiving a to-be-processed operation and maintenance problem sent by a client;

[0141] filtering a matching operation and maintenance problem matched with the to-be-processed operation and maintenance problem from the at least one target operation and maintenance problem;

[0142] determining a matching reply result of the matching operation and maintenance problem as a reply result of the to-be-processed operation and maintenance problem;

[0143] feeding back the reply result of the to-be-processed operation and maintenance problem to the client.

[0144] It should be noted that the to-be-handled operation and maintenance problem refers to a problem in a target operation and maintenance scenario submitted by a client. These problems can affect the normal operation, performance, or security of the system and need to be handled by appropriate measures. The target operation and maintenance problem refers to an operation and maintenance problem in the target operation and maintenance graph. Compared with the to-be-handled operation and maintenance problem, the target operation and maintenance problem is a historical operation and maintenance problem, and these target operation and maintenance problems have been analyzed and have known reply results. The matched operation and maintenance problem is a specific problem selected from the target operation and maintenance problem that matches the to-be-handled operation and maintenance problem. The matched operation and maintenance problem is the same as or highly similar to the to-be-handled operation and maintenance problem. The matched reply result refers to the reply result of the matched operation and maintenance problem, including but not limited to the root cause, mitigation measures, and solutions. The reply result of the to-be-handled operation and maintenance problem refers to the final solution or suggestion applicable to the to-be-handled operation and maintenance problem. This reply result aims to guide the client to solve the to-be-handled operation and maintenance problem.

[0145] In actual applications, the process of selecting a matched operation and maintenance problem that matches the to-be-handled operation and maintenance problem from at least one target operation and maintenance problem can be performed by a problem classification agent. After receiving the to-be-handled operation and maintenance problem sent by the client, the problem classification agent can perform semantic analysis on the to-be-handled operation and maintenance problem based on natural language understanding and text classification algorithms, extract keywords and key information, and then select a matched operation and maintenance problem that matches the to-be-handled operation and maintenance problem from at least one target operation and maintenance problem based on the extracted keywords and key information.

[0146] Exemplarily, taking the target operation and maintenance scenario as the rail transit operation and maintenance scenario and the to-be-handled operation and maintenance problem as “the train triggers emergency braking multiple times and cannot resume normal operation”, the matched operation and maintenance problem selected from at least one target operation and maintenance problem that matches the to-be-handled operation and maintenance problem is “the train triggers emergency braking due to false alarm of the track foreign object detection sensor when driving at high speed”, and the matched reply result of the matched operation and maintenance problem “immediately arrange the on-site maintenance team to check whether there are foreign objects on the track. If foreign objects are found, remove them and try to restart the train. Subsequently, calibrate the sensor and increase video monitoring to assist verification” is determined as the reply result of the to-be-handled operation and maintenance problem.

[0147] By applying the scheme of the embodiments of the present specification, by constructing a target problem graph, the matched operation and maintenance problem can be quickly found from the target problem graph after receiving the to-be-handled operation and maintenance problem, and the matched reply result previously generated for the matched operation and maintenance problem is taken as the reply result of the to-be-handled operation and maintenance problem, thereby improving the processing efficiency on the basis of ensuring the accuracy of the reply result.

[0148] In an optional embodiment of the present specification, after answering the pending operation and maintenance question, the target problem map may be updated using the pending operation and maintenance data of the pending operation and maintenance question. That is, after determining the matching answer result of the matching operation and maintenance question as the answer result of the pending operation and maintenance question, the following steps may be further included:

[0149] Obtain pending operation and maintenance data of pending operation and maintenance issues;

[0150] The operation and maintenance data to be processed is added to the target problem graph as a child node matching the operation and maintenance problem to obtain an updated target problem graph.

[0151] It should be noted that the pending operation and maintenance data refers to all the original data and information related to the pending operation and maintenance issues. These data are the basis for analyzing and solving the pending operation and maintenance issues. There are many ways to obtain the pending operation and maintenance data of the pending operation and maintenance issues, and the specific selection is based on the actual situation. The embodiments of this specification do not impose any restrictions on this. In one possible implementation of this specification, the pending operation and maintenance data of the pending operation and maintenance issues sent by the client can be received. In another possible implementation of this specification, the pending operation and maintenance data of the pending operation and maintenance issues can be read from other data acquisition devices or databases.

[0152] In actual applications, the implementation method of "adding the operation and maintenance data to be processed as a child node matching the operation and maintenance problem to the target problem graph to obtain an updated target problem graph" can refer to the above-mentioned "In one possible implementation method of this specification, all operation and maintenance data of the operation and maintenance problem can be added to the initial problem graph as the root node of the operation and maintenance problem. In another possible implementation method of this specification, since the initial operation and maintenance data included in the initial problem graph may include data that is identical or highly similar to the operation and maintenance data of the operation and maintenance problem, operation and maintenance data that is different from or has a lower similarity to the initial operation and maintenance data can be screened out from the operation and maintenance data, and these screened operation and maintenance data can be added to the initial problem graph as child nodes of the operation and maintenance problem. At the same time, edges are added between the operation and maintenance problem and the initial operation and maintenance data that is identical or highly similar to the operation and maintenance data of the operation and maintenance problem to obtain the target problem graph of the target operation and maintenance scenario." The implementation method of this specification will not be repeated.

[0153] By applying the solution of the embodiments of this specification, the target problem map is updated by utilizing the pending operation and maintenance problems received in real time, thereby improving the timeliness and comprehensiveness of the target problem map and further improving the efficiency of answering subsequent questions.

[0154] With the rapid development of information technology, intelligent operation and maintenance technology has gradually become a research hotspot and development direction in the field of rail transportation. Intelligent rail transportation operation and maintenance aims to use advanced sensor technology, data acquisition and transmission technology, data analysis and processing technology, etc. to achieve real-time monitoring, fault diagnosis and prediction of rail transportation equipment, thereby improving operation and maintenance efficiency and quality, reducing operation and maintenance costs, and ensuring the reliable operation of rail transportation systems. Figure 6 , taking the application of the operation and maintenance data processing method provided in this specification in the rail transit operation and maintenance scenario as an example, the operation and maintenance data processing method is further explained. Figure 6 A flowchart illustrating the processing process of an operation and maintenance data processing method provided by one embodiment of this specification is shown. The operation and maintenance data processing process can be performed collaboratively by multiple agents, including a visual monitoring agent, an intelligent correction agent, a data analysis agent, a fault prediction agent, an expert agent, an assistant agent, a graph construction agent, and a problem classification agent. The processing process of each agent is described below.

[0155] Visual monitoring agent: performs visual data monitoring on the target operation and maintenance scene to obtain visual data of the target operation and maintenance scene.

[0156] Intelligent correction agent: receives sensor data sent by sensors and other monitoring equipment, and determines the sensor data and visual data as operation and maintenance data; obtains scene information and technical documents corresponding to the operation and maintenance data; verifies the operation and maintenance data according to the scene information and technical documents to obtain verification results; if it is determined based on the verification results that the operation and maintenance data does not meet the verification conditions, modifies the operation and maintenance data to obtain modified operation and maintenance data, wherein the modified operation and maintenance data meets the verification conditions.

[0157] Data analysis agent: identifies faults in operation and maintenance data and obtains current problems of the operation and maintenance data.

[0158] Fault prediction agent: obtains historical operation and maintenance data of the target operation and maintenance scenario and historical operation and maintenance problems of the historical operation and maintenance data; based on the historical operation and maintenance data and historical operation and maintenance problems, it predicts faults on the operation and maintenance data and obtains the prediction problems of the operation and maintenance data.

[0159] Expert agent: Identify the current problem and the predicted problem as the operation and maintenance problem of the operation and maintenance data; obtain the initial operation and maintenance problem in the initial problem map, wherein the initial problem map includes at least one initial sub-graph, and the initial sub-graph is constructed with the initial operation and maintenance problem as the root node and the initial operation and maintenance data of the initial operation and maintenance problem as the child nodes. Based on the inventory system and technical documentation of the target operation and maintenance scenario, the operation and maintenance problem and the initial operation and maintenance problem are processed, and processing suggestions for the operation and maintenance problem and initial processing suggestions for the initial operation and maintenance problem are generated. When the expert agent processes the problem, it can also process the problem summary and initial problem summary generated by the assistant agent, and generate processing suggestions for the operation and maintenance problem and initial processing suggestions for the initial operation and maintenance problem. The expert agent can also directly answer the pending operation and maintenance problems sent by the operation and maintenance object, and generate response results for the pending operation and maintenance problems.

[0160] Assistant agent: extracts a summary of the operation and maintenance problem to obtain a problem summary, and extracts a summary of the initial operation and maintenance problem to obtain an initial problem summary.

[0161] Graph construction agent: compare the problem summary with the initial problem summary to obtain the problem comparison result; compare the operation and maintenance data with the initial operation and maintenance data to obtain the data comparison result; compare the processing suggestions with the initial processing suggestions to obtain the suggestion comparison result; when it is determined based on the problem comparison result, the data comparison result and the suggestion comparison result that the operation and maintenance problem meets the node merging condition, the operation and maintenance data is added as a child node of the initial operation and maintenance problem to the initial problem graph to obtain the target problem graph of the target operation and maintenance scenario; when it is determined based on the problem comparison result, the data comparison result and the suggestion comparison result that the operation and maintenance problem does not meet the node merging condition, the target subgraph is added to the initial problem graph to obtain the target problem graph of the target operation and maintenance scenario, wherein the target subgraph is constructed with the operation and maintenance problem as the root node and the operation and maintenance data as the child nodes, and the target problem graph includes multiple target operation and maintenance problems (such as problem 1, problem 2,..., problem n).

[0162] Problem classification agent: receives pending operation and maintenance problems sent by the operation and maintenance object; selects matching operation and maintenance problems that match the pending operation and maintenance problems from the target operation and maintenance problems included in the target problem map; determines the matching reply results of the matching operation and maintenance problems as the reply results of the pending operation and maintenance problems; and feeds back the reply results of the pending operation and maintenance problems to the operation and maintenance object.

[0163] In an optional embodiment of this specification, the assistant agent can also extract summaries of responses to pending operational issues, obtain summary responses, and provide feedback to the operational entity. Furthermore, the assistant agent can also, through an interactive interface with the operational entity, alert the entity to important issues and progress based on the recommended actions generated by the expert agent. Furthermore, the assistant agent can receive questions from relevant stakeholders and pass them on to the appropriate agent for resolution.

[0164] By applying the solution of the embodiments of this specification, in complex rail transit operation and maintenance scenarios, in order to address the problem that the accuracy and reliability of sensor data are affected by environmental factors (such as high temperature, high humidity, strong electromagnetic interference) and their own faults, a multi-agent system based on a problem map is constructed to achieve collaboration and information interaction between agents, real-time monitoring and intelligent correction of sensor collected data, rapid identification and correction of abnormal data, and ensure the accuracy of collected data, so as to effectively cope with complex environments and faults. The multi-agent system adopts distributed processing and collaborative computing, distributing massive amounts of data to each agent for parallel processing, and utilizing the local computing power and mutual cooperation mechanism of the agent to quickly analyze and process data, improve data processing efficiency, and comprehensively cover the entire data processing process from data collection, real-time monitoring, data verification, and intelligent correction to ensure data accuracy and reliability. When environmental factors or sensor failures cause abnormal operation and maintenance data, the intelligent correction agent can quickly identify and modify the operation and maintenance data through intelligent algorithms to ensure the accuracy of the operation and maintenance data, effectively avoid misjudgments and missed judgments caused by inaccurate or missing operation and maintenance data, thereby improving the reliability of the entire operation and maintenance system. The fault prediction agent can accurately predict potential subsequent faults in operation and maintenance data. Preventive maintenance strategies can be developed based on these predictions, allowing for pre-planned maintenance schedules and reducing unnecessary periodic calibration, maintenance, and replacement operations, thereby lowering maintenance costs. The graph construction agent intelligently filters, summarizes, categorizes, and hierarchically processes problem graphs when updating and constructing them. This reduces data redundancy, avoids unnecessary data analysis, and enables efficient data processing. This ensures the timeliness and accuracy of fault diagnosis and prediction, effectively managing the processing pressures brought on by massive amounts of sensor data. The problem graph can then be used as a foundation for the effective management and processing of various types of data.

[0165] Corresponding to the above-mentioned operation and maintenance data processing method embodiment, this specification also provides an operation and maintenance data processing device embodiment, Figure 7 FIG1 shows a schematic diagram of the structure of an operation and maintenance data processing device provided by an embodiment of this specification. Figure 7 As shown, the device includes:

[0166] An acquisition module 702 is configured to acquire operation and maintenance data of a target operation and maintenance scenario;

[0167] The analysis module 704 is configured to perform fault analysis on the operation and maintenance data to obtain an operation and maintenance problem of the operation and maintenance data.

[0168] The updating module 706 is configured to update an initial problem graph of the target operation and maintenance scene according to the operation and maintenance problem to obtain a target problem graph of the target operation and maintenance scene, wherein the initial problem graph includes at least one initial subgraph, the initial subgraph is constructed with an initial operation and maintenance problem as a root node and initial operation and maintenance data of the initial operation and maintenance problem as a child node, and the target problem graph includes at least one target operation and maintenance problem.

[0169] The generating module 708 is configured to generate a target reply result of at least one target operation and maintenance problem according to the target problem graph.

[0170] Optionally, the updating module 706 is further configured to compare the operation and maintenance problem with the initial operation and maintenance problem to obtain a problem comparison result, and update the initial problem graph according to the problem comparison result to obtain the target problem graph of the target operation and maintenance scene.

[0171] Optionally, the updating module 706 is further configured to, in a case where it is determined based on the problem comparison result that the operation and maintenance problem satisfies a node merging condition, add the operation and maintenance data as a child node of the initial operation and maintenance problem to the initial problem graph to obtain the target problem graph of the target operation and maintenance scene, and in a case where it is determined based on the problem comparison result that the operation and maintenance problem does not satisfy the node merging condition, add a target subgraph to the initial problem graph to obtain the target problem graph of the target operation and maintenance scene, wherein the target subgraph is constructed with the operation and maintenance problem as a root node and the operation and maintenance data as a child node.

[0172] Optionally, the updating module 706 is further configured to perform abstract extraction on the operation and maintenance problem to obtain a problem abstract, and perform abstract extraction on the initial operation and maintenance problem to obtain an initial problem abstract, and compare the problem abstract with the initial problem abstract to obtain the problem comparison result.

[0173] Optionally, the apparatus further includes a first comparison module configured to compare the operation and maintenance data with the initial operation and maintenance data to obtain a data comparison result, and the updating module 706 is further configured to update the initial problem graph according to the problem comparison result and the data comparison result to obtain the target problem graph of the target operation and maintenance scene.

[0174] Optionally, the apparatus further includes a second comparison module configured to obtain a processing suggestion of the operation and maintenance problem and an initial processing suggestion of the initial operation and maintenance problem, compare the processing suggestion with the initial processing suggestion to obtain a suggestion comparison result, and the updating module 706 is further configured to update the initial problem graph according to the problem comparison result and the suggestion comparison result to obtain the target problem graph of the target operation and maintenance scene.

[0175] Optionally, the analysis module 704 is further configured to perform fault identification on the operation and maintenance data to obtain operation and maintenance problems of the operation and maintenance data; and / or perform fault prediction on the operation and maintenance data to obtain operation and maintenance problems of the operation and maintenance data.

[0176] Optionally, the analysis module 704 is further configured to obtain historical operation and maintenance data of the target operation and maintenance scenario and historical operation and maintenance problems of the historical operation and maintenance data; perform fault prediction on the operation and maintenance data based on the historical operation and maintenance data and the historical operation and maintenance problems, and obtain the operation and maintenance problems of the operation and maintenance data.

[0177] Optionally, the device also includes: a verification module, configured to obtain scenario information corresponding to the operation and maintenance data; verifying the operation and maintenance data according to the scenario information to obtain a verification result; when it is determined based on the verification result that the operation and maintenance data does not meet the verification conditions, modifying the operation and maintenance data to obtain modified operation and maintenance data, wherein the modified operation and maintenance data meets the verification conditions; the analysis module 704 is further configured to perform fault analysis on the modified operation and maintenance data to obtain the operation and maintenance problems of the operation and maintenance data.

[0178] Optionally, the device also includes: a receiving module, configured to receive the pending operation and maintenance issues sent by the client; screen out matching operation and maintenance issues that match the pending operation and maintenance issues from at least one target operation and maintenance issue; determine the matching reply result of the matching operation and maintenance issue as the reply result of the pending operation and maintenance issue; and feed back the reply result of the pending operation and maintenance issue to the client.

[0179] Optionally, the device also includes: an adding module configured to obtain pending operation and maintenance data of pending operation and maintenance problems; add the pending operation and maintenance data as a sub-node matching the operation and maintenance problem to the target problem map to obtain an updated target problem map.

[0180] By applying the solution of the embodiments of this specification to systematically collect and analyze the operation and maintenance data in the target operation and maintenance scenario, the operation and maintenance problems in the target operation and maintenance scenario can be identified more comprehensively and accurately, the problems of missed detection or false detection can be reduced, and the comprehensiveness and accuracy of operation and maintenance data processing can be improved; by updating the initial problem map to obtain the target problem map, it is helpful to organize and associate different operation and maintenance problems and operation and maintenance data, and ensure the timeliness of the target problem map, which helps to better understand and deal with complex operation and maintenance environments. At the same time, through the structured knowledge representation form of the target problem map, similar operation and maintenance problems can be quickly retrieved, which greatly improves the efficiency of solving operation and maintenance problems. In addition, the entire operation and maintenance data processing process is a highly automated process, which not only improves the efficiency of operation and maintenance data processing, but also reduces dependence on human resources and reduces labor costs.

[0181] The above is a schematic diagram of an operation and maintenance data processing device according to this embodiment. It should be noted that the technical solution of this operation and maintenance data processing device and the technical solution of the above-mentioned operation and maintenance data processing method are based on the same concept. For details not described in detail in the technical solution of the operation and maintenance data processing device, please refer to the description of the technical solution of the above-mentioned operation and maintenance data processing method.

[0182] Figure 8 8. The structure of a computing device provided in one embodiment of the present specification is shown in FIG. Components of the computing device 800 include, but are not limited to, a memory 810 and a processor 820. The processor 820 is connected to the memory 810 via a bus 830, and a database 850 is used to store data.

[0183] The computing device 800 also includes an access device 840 that enables the computing device 800 to communicate via one or more networks 860. Examples of such networks include a public switched telephone network (PSTN), a local area network (LAN), a wide area network (WAN), a personal area network (PAN), or a combination of communication networks such as the Internet. The access device 840 may include one or more of any type of network interface (e.g., a network interface card (NIC)) whether wired or wireless, such as an IEEE 802.11 wireless local area network (WLAN) wireless interface, a world interoperability for microwave access (Wi-MAX) interface, an Ethernet interface, a universal serial bus (USB) interface, a cellular network interface, a Bluetooth interface, a near field communication (NFC) interface, and the like.

[0184] In one embodiment of the present specification, the above components of the computing device 800 and Figure 8 Other components not shown in the figure may also be connected to each other, for example, via a bus. Figure 8 The computing device structure block diagram shown is for illustrative purposes only and is not intended to limit the scope of this specification. Those skilled in the art may add or replace other components as needed.

[0185] Computing device 800 may be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (e.g., a tablet computer, personal digital assistant, laptop computer, notebook computer, netbook computer, etc.), a mobile phone (e.g., a smartphone), a wearable computing device (e.g., a smartwatch, smart glasses, etc.), or other types of mobile devices, or a stationary computing device such as a desktop computer or personal computer (PC). Computing device 800 may also be a mobile or stationary server.

[0186] The processor 820 is used to execute computer programs / instructions, which implement the steps of the above-mentioned operation and maintenance data processing method when executed by the processor.

[0187] The above is a schematic diagram of a computing device according to this embodiment. It should be noted that the technical solution of the computing device and the technical solution of the above-mentioned operation and maintenance data processing method are based on the same concept. For details not described in detail in the technical solution of the computing device, please refer to the description of the technical solution of the above-mentioned operation and maintenance data processing method.

[0188] An embodiment of the present specification further provides a computer-readable storage medium storing a computer program / instruction, which implements the steps of the above-mentioned operation and maintenance data processing method when executed by a processor.

[0189] The above is a schematic diagram of a computer-readable storage medium according to this embodiment. It should be noted that the technical solution of this storage medium and the technical solution of the aforementioned operation and maintenance data processing method are based on the same concept. For details not described in detail in the technical solution of the storage medium, please refer to the description of the technical solution of the aforementioned operation and maintenance data processing method.

[0190] An embodiment of the present specification further provides a computer program product, including a computer program / instruction, which implements the steps of the above-mentioned operation and maintenance data processing method when executed by a processor.

[0191] The above is a schematic diagram of a computer program product according to this embodiment. It should be noted that the technical solution of this computer program product and the technical solution of the aforementioned operation and maintenance data processing method are based on the same concept. For details not described in detail in the technical solution of the computer program product, please refer to the description of the technical solution of the aforementioned operation and maintenance data processing method.

[0192] The foregoing description of this specification describes specific embodiments. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different from that described in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order shown or the sequential order to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0193] The computer instructions include computer program code, which may be in source code form, object code form, executable file, or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal, and software distribution medium. It should be noted that the content contained in the computer-readable medium may be appropriately increased or decreased according to the requirements of patent practice. For example, in some regions, according to patent practice, computer-readable media does not include electric carrier signals and telecommunication signals.

[0194] It should be noted that for the aforementioned method embodiments, for the sake of simplicity of description, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the embodiments of this specification are not limited by the order of the actions described, because according to the embodiments of this specification, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in this specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the embodiments of this specification.

[0195] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0196] The preferred embodiments disclosed above are intended only to help illustrate this specification. The optional embodiments do not exhaustively describe all details, nor do they limit the invention to the specific embodiments described. Obviously, many modifications and variations can be made based on the content of the embodiments of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the embodiments of this specification, so that those skilled in the art can better understand and utilize this specification. This specification is limited only by the claims and their full scope and equivalents.

Claims

1. A method for processing operation and maintenance data, characterized in that: include: Obtain operation and maintenance data for the target operation and maintenance scenario; Performing fault analysis on the operation and maintenance data to obtain operation and maintenance problems of the operation and maintenance data; Based on the operation and maintenance problem, an initial problem graph of the target operation and maintenance scenario is updated to obtain a target problem graph of the target operation and maintenance scenario, wherein the initial problem graph includes at least one initial subgraph, the initial subgraph is constructed with the initial operation and maintenance problem as a root node and the initial operation and maintenance data of the initial operation and maintenance problem as child nodes, and the target problem graph includes at least one target operation and maintenance problem; A target answer result for the at least one target operation and maintenance problem is generated according to the target problem map.

2. The method according to claim 1, characterized in that The updating of the initial problem map of the target operation and maintenance scenario according to the operation and maintenance problem to obtain the target problem map of the target operation and maintenance scenario includes: Comparing the operation and maintenance problem with the initial operation and maintenance problem to obtain a problem comparison result; According to the problem comparison result, the initial problem map is updated to obtain the target problem map of the target operation and maintenance scenario.

3. The method according to claim 2, characterized in that The updating of the initial problem map according to the problem comparison result to obtain the target problem map of the target operation and maintenance scenario includes: If it is determined based on the problem comparison result that the operation and maintenance problem meets the node merging condition, the operation and maintenance data is added to the initial problem map as a child node of the initial operation and maintenance problem to obtain a target problem map of the target operation and maintenance scenario; When it is determined based on the problem comparison result that the operation and maintenance problem does not meet the node merging conditions, a target subgraph is added to the initial problem graph to obtain a target problem graph of the target operation and maintenance scenario, wherein the target subgraph is constructed with the operation and maintenance problem as the root node and the operation and maintenance data as the child nodes.

4. The method according to claim 2, characterized in that The comparing the operation and maintenance problem with the initial operation and maintenance problem to obtain a problem comparison result includes: Extracting a summary of the operation and maintenance problem to obtain a problem summary, and extracting a summary of the initial operation and maintenance problem to obtain an initial problem summary; The question summary and the initial question summary are compared to obtain the question comparison result.

5. The method according to claim 2, characterized in that Before updating the initial problem map according to the problem comparison result to obtain the target problem map of the target operation and maintenance scenario, the method further includes: Comparing the operation and maintenance data with the initial operation and maintenance data to obtain a data comparison result; The updating of the initial problem map according to the problem comparison result to obtain the target problem map of the target operation and maintenance scenario includes: The initial problem map is updated according to the problem comparison result and the data comparison result to obtain a target problem map for the target operation and maintenance scenario.

6. The method according to claim 2, characterized in that Before updating the initial problem map according to the problem comparison result to obtain the target problem map of the target operation and maintenance scenario, the method further includes: Obtaining a solution suggestion for the operation and maintenance problem, and obtaining an initial solution suggestion for the initial operation and maintenance problem; Comparing the processing suggestion with the initial processing suggestion to obtain a suggestion comparison result; The updating of the initial problem map according to the problem comparison result to obtain the target problem map of the target operation and maintenance scenario includes: The initial problem map is updated according to the problem comparison result and the suggestion comparison result to obtain a target problem map for the target operation and maintenance scenario.

7. The method according to claim 1, characterized in that The performing fault analysis on the operation and maintenance data to obtain the operation and maintenance problems of the operation and maintenance data includes: Performing fault identification on the operation and maintenance data to obtain operation and maintenance problems of the operation and maintenance data; and / or, Fault prediction is performed on the operation and maintenance data to obtain operation and maintenance problems of the operation and maintenance data.

8. The method according to claim 7, characterized in that The performing fault prediction on the operation and maintenance data to obtain the operation and maintenance problem of the operation and maintenance data includes: Obtaining historical operation and maintenance data of the target operation and maintenance scenario and historical operation and maintenance issues of the historical operation and maintenance data; Based on the historical operation and maintenance data and the historical operation and maintenance problems, fault prediction is performed on the operation and maintenance data to obtain the operation and maintenance problems of the operation and maintenance data.

9. The method according to any one of claims 1 to 8, characterized in that Before performing fault analysis on the operation and maintenance data to obtain the operation and maintenance problems of the operation and maintenance data, the method further includes: Obtaining scenario information corresponding to the operation and maintenance data; Verifying the operation and maintenance data according to the scenario information to obtain a verification result; If it is determined based on the verification result that the operation and maintenance data does not meet the verification condition, modify the operation and maintenance data to obtain modified operation and maintenance data, wherein the modified operation and maintenance data meets the verification condition; The performing fault analysis on the operation and maintenance data to obtain the operation and maintenance problems of the operation and maintenance data includes: Perform fault analysis on the modified operation and maintenance data to obtain operation and maintenance problems of the operation and maintenance data.

10. The method according to any one of claims 1 to 8, characterized in that After generating a target answer result for the at least one target operation and maintenance problem according to the target problem map, the method further includes: Receive pending operation and maintenance issues sent by the client; Filtering out, from the at least one target operation and maintenance problem, a matching operation and maintenance problem that matches the operation and maintenance problem to be processed; Determining the matching answer result of the matching operation and maintenance problem as the answer result of the operation and maintenance problem to be processed; Feedback the answer to the pending operation and maintenance issue to the client.

11. The method according to claim 10, characterized in that After determining the matching answer result of the matching operation and maintenance problem as the answer result of the operation and maintenance problem to be processed, the method further includes: Obtaining pending operation and maintenance data of the pending operation and maintenance problem; The operation and maintenance data to be processed is added to the target problem graph as a child node of the matching operation and maintenance problem to obtain an updated target problem graph.

12. An operation and maintenance data processing device, characterized in that: include: An acquisition module configured to acquire operation and maintenance data of a target operation and maintenance scenario; an analysis module configured to perform fault analysis on the operation and maintenance data to obtain operation and maintenance problems of the operation and maintenance data; an updating module configured to update the initial problem graph of the target operation and maintenance scenario based on the operation and maintenance problem to obtain a target problem graph of the target operation and maintenance scenario, wherein the initial problem graph includes at least one initial subgraph, the initial subgraph is constructed with the initial operation and maintenance problem as a root node and the initial operation and maintenance data of the initial operation and maintenance problem as child nodes, and the target problem graph includes at least one target operation and maintenance problem; A generation module is configured to generate a target answer result for the at least one target operation and maintenance problem based on the target problem map.

13. A computing device, characterized in that include: memory and processor; The memory is used to store computer programs / instructions, and the processor is used to execute the computer programs / instructions. When the computer program / instructions are executed by the processor, the steps of the method according to any one of claims 1 to 11 are implemented.

14. A computer-readable storage medium, characterized in that It stores a computer program / instruction, which implements the steps of the method according to any one of claims 1 to 11 when executed by a processor.

15. A computer program product, characterized in that The method comprises a computer program / instruction which, when executed by a processor, implements the steps of the method according to any one of claims 1 to 11.

Images