Operation and maintenance control method and device based on intention recognition, equipment and medium

Abstract

The invention relates to the field of intelligent decision and the field of financial science and technology, and discloses an operation and maintenance control method based on intention recognition, and the method comprises the steps: carrying out the anomaly detection of real-time operation and maintenance data according to the historical operation and maintenance data of a platform to be operated and maintained; setting an operation and maintenance intention of the to-be-operated and to-be-maintained platform based on the anomaly detection result, and setting an operation task of the operation and maintenance intention according to the high-level operation and maintenance intention; and setting a decision basis and a decision trigger instruction of the platform to be operated and maintained in combination with the exception detection result and task details of the operation task, setting a specific operation and maintenance scheme after intelligent decision analysis of the platform to be operated and maintained, and performing operation and maintenance processing on the platform to be operated and maintained. The operation and maintenance efficiency can be improved by utilizing the high-level operation and maintenance intention and the decision triggering instruction.

Description

Technical Field

[0001] The present invention relates to the fields of intelligent decision-making and financial technology, and in particular to an operation and maintenance control method, device, equipment and medium based on intent recognition. Background Art

[0002] The intent-recognition-based operation and maintenance control platform refers to a system that uses cutting-edge technologies such as artificial intelligence, big data, cloud computing, and blockchain to improve the operation and maintenance management of the traditional financial industry. It helps the operation and maintenance teams in the financial industry handle various operation and maintenance tasks and problems more efficiently through automated responses to predefined instructions and intent recognition of natural language.

[0003] With the rapid development of information technology, the IT architecture of modern financial enterprises is becoming more and more complex. A large number of devices, applications and log data need to be monitored and processed in real time, which increases the pressure on the operation and maintenance system. Intelligent operation and maintenance, as an advanced operation and maintenance model, can help financial enterprises better cope with market competition and technological changes. Therefore, financial enterprises urgently need to break through these bottlenecks through intelligent operation and maintenance platforms. Traditional intelligent operation and maintenance platforms usually rely on pre-defined instructions and fixed operating procedures, and cannot flexibly respond to dynamic and complex situations that may be encountered in actual operations, thereby affecting the system's service requests and fault handling efficiency. Summary of the invention

[0004] The present invention provides an artificial intelligence-based operation and maintenance control method, device, equipment and medium, so as to improve the operation and maintenance efficiency by utilizing high-level operation and maintenance intentions and decision instructions.

[0005] In a first aspect, an operation and maintenance control method based on intent recognition is provided, comprising:

[0006] Collecting real-time operation and maintenance data and historical operation and maintenance data of the platform to be operated and maintained, and performing anomaly detection on the real-time operation and maintenance data according to the historical operation and maintenance data to obtain anomaly detection data;

[0007] Based on the abnormal situation, create an intention input text of the platform to be operated and maintained, extract key features of the intention input text, and identify the high-level operation and maintenance intention of the intention input text based on the key features, and set the operation task of the intention input text according to the high-level operation and maintenance intention;

[0008] Assigning task details of the operation task, setting a decision basis for the platform to be operated and maintained in combination with the abnormal situation and the task details, setting a decision instruction for the platform to be operated and maintained based on the decision basis, and performing intelligent decision analysis on the platform to be operated and maintained according to the decision basis and the decision instruction to obtain a decision analysis result;

[0009] According to the decision analysis result, a specific operation and maintenance plan for the platform to be operated and maintained is set, and based on the specific operation and maintenance plan, operation and maintenance processing is performed on the platform to be operated and maintained to obtain an operation and maintenance result.

[0010] In a second aspect, an operation and maintenance control device based on intent recognition is provided, comprising:

[0011] The intention decomposition module is used to collect the real-time operation and maintenance data and the historical operation and maintenance data of the platform to be operated and maintained, and perform anomaly detection on the real-time operation and maintenance data according to the historical operation and maintenance data to obtain anomaly detection data;

[0012] A data perception module is used to create an intended input text of the platform to be operated and maintained based on the abnormal situation, extract key features of the intended input text, and identify the high-level operation and maintenance intention of the intended input text based on the key features, and set an operation task for the intended input text according to the high-level operation and maintenance intention;

[0013] A decision analysis module, used to assign task details of the operation task, set a decision basis for the platform to be operated and maintained in combination with the abnormal situation and the task details, set a decision instruction for the platform to be operated and maintained based on the decision basis, and perform intelligent decision analysis on the platform to be operated and maintained according to the decision basis and the decision instruction to obtain a decision analysis result;

[0014] The operation execution module is used to set a specific operation and maintenance plan for the platform to be operated and maintained according to the decision analysis result, and perform operation and maintenance processing on the platform to be operated and maintained based on the specific operation and maintenance plan to obtain an operation and maintenance result.

[0015] In a third aspect, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned operation and maintenance control method based on intent recognition when executing the computer program.

[0016] In a fourth aspect, a computer-readable storage medium is provided, which stores a computer program. When the computer program is executed by a processor, the steps of the above-mentioned operation and maintenance control method based on intent recognition are implemented.

[0017] In the scheme implemented by the above-mentioned operation and maintenance control method, device, equipment and medium based on intention recognition, the real-time operation and maintenance data and historical operation and maintenance data of the platform to be operated and maintained can be collected through the client, and the real-time operation and maintenance data can be detected for anomalies based on the historical operation and maintenance data to obtain anomaly detection data; based on the abnormal situation, the intention input text of the platform to be operated and maintained is created, the key features of the intention input text are extracted, and based on the key features, the high-level operation and maintenance intention of the intention input text is identified, and according to the high-level operation and maintenance intention, the operation task of the intention input text is set; the task details of the operation task are assigned, and the decision basis of the platform to be operated and maintained is set in combination with the abnormal situation and the task details, and the decision instructions of the platform to be operated and maintained are set based on the decision basis, and the platform to be operated and maintained is intelligently analyzed based on the decision basis and the decision instructions to obtain the decision analysis results; according to the decision analysis results, a specific operation and maintenance plan for the platform to be operated and maintained is set, and based on the specific operation and maintenance plan, the platform to be operated and maintained is operated and maintained to obtain the operation and maintenance results. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0019] Figure 1 is a schematic diagram of an application environment of an operation and maintenance control method based on intent recognition in an embodiment of the present invention;

[0020] Figure 2 is a flow chart of an operation and maintenance control method based on intent recognition in one embodiment of the present invention;

[0021] Figure 3 yes Figure 1 A schematic flow chart of a specific implementation of step S3;

[0022] Figure 4 yes Figure 1 A schematic flow chart of a specific implementation of step S4;

[0023] Figure 5 yes Figure 4 A schematic flow chart of a specific implementation of step S7;

[0024] Figure 6 is a structural schematic diagram of an operation and maintenance control device based on intention recognition in one embodiment of the present invention;

[0025] Figure 7is a schematic diagram of a structure of a computer device in one embodiment of the present invention;

[0026] Figure 8 It is another structural schematic diagram of a computer device in one embodiment of the present invention. DETAILED DESCRIPTION

[0027] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0028] The operation and maintenance control method based on intention recognition provided by the embodiment of the present invention can be applied in the following aspects: Figure 1 In an application environment, a client communicates with a server through a network. The server can receive user questions through the client, and perform question recall processing from a preset standard question library according to the user questions to obtain multiple candidate questions; sort the multiple candidate questions according to the semantic matching degree between the user questions and the candidate questions to obtain a first sorting result of the candidate questions; respectively judge the entity alignment between the user questions and each candidate question; adjust the first sorting result according to the entity alignment to obtain a second sorting result of the candidate questions, in which the candidate questions with non-aligned entities are arranged behind the candidate questions with aligned entities, and the candidate questions with aligned entities remain unchanged according to the sorting of the first sorting result; in the sequence of the second sorting result, a preset number of candidate questions are intercepted from the first one in turn as matching questions; finally, the matching answers corresponding to the matching questions are selected to respond to the user questions, and the matching answers are fed back to the client. In the present invention, for complex insurance entities such as insurance business, the entity alignment can be used to optimize the question-answering engine solution, firstly, the semantic matching degree is used for rough sorting, and then the sorting is adjusted by the entity alignment method, and the top matching questions are selected to respond to the corresponding answers, which can effectively avoid the generalization ability defects of the model, greatly and efficiently improve the effect of entity matching, and improve the effect of the question-answering engine. The client may be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, and portable wearable devices. The server may be implemented by an independent server or a server cluster consisting of multiple servers. The present invention is described in detail below through specific embodiments.

[0029] See also Figure 2 As shown, Figure 2 A flowchart of an operation and maintenance control method based on intent recognition provided by an embodiment of the present invention includes the following steps:

[0030] S1. Collect real-time operation and maintenance data and historical operation and maintenance data of the platform to be operated and maintained, and perform anomaly detection on the real-time operation and maintenance data according to the historical operation and maintenance data to obtain anomaly detection data.

[0031] The embodiments of the present invention can help operation and maintenance personnel quickly discover and solve problems and prevent faults from expanding by collecting real-time operation and maintenance data and historical operation and maintenance data of the platform to be operated and maintained, and integrate data from different sources through the perception engine to form a unified data view, thereby providing comprehensive data support for the decision engine and improving the accuracy and efficiency of decision-making. The real-time operation and maintenance data refers to various monitoring indicators and log information collected in real time from the operation and maintenance environment, including financial log data, link information data, traffic information data and alarm data; the historical operation and maintenance data refers to data collected and stored over a period of time in the past about the operating status of IT infrastructure and applications.

[0032] Optionally, the real-time operation and maintenance data and historical operation and maintenance data collection of the platform to be operated and maintained can be implemented using the Grafana monitoring tool.

[0033] Furthermore, the embodiments of the present invention can quickly identify and locate potential problems by performing anomaly detection on the real-time operation and maintenance data based on the historical operation and maintenance data to obtain anomaly detection data, thereby providing data support for operation and maintenance personnel and helping them to promptly discover anomalies and trends. The anomaly detection data refers to data that is collected by analyzing and monitoring the operating status of IT infrastructure and applications and that does not conform to standard data patterns.

[0034] As an embodiment of the present invention, the method of performing anomaly detection on the real-time operation and maintenance data based on the historical operation and maintenance data to obtain anomaly detection data includes: extracting operation and maintenance features of the historical operation and maintenance data; constructing a data training model for the historical operation and maintenance data based on the operation and maintenance features; identifying statistical characteristics of the historical operation and maintenance data, and setting an anomaly threshold of the data training model based on the statistical characteristics; and performing anomaly detection on the real-time operation and maintenance data based on the anomaly threshold to obtain anomaly detection data.

[0035] Among them, the operation and maintenance features refer to key information extracted from historical operation and maintenance data, such as the CPU usage of the server; the data training model refers to the algorithm or model used to train and learn normal behavior patterns in historical operation and maintenance data; the statistical characteristics refer to the mathematical description of the data, including but not limited to the mean, median, variance, standard deviation, skewness, kurtosis, etc.; the abnormal threshold refers to the standard used to determine whether real-time operation and maintenance data is abnormal.

[0036] Optionally, the operation and maintenance feature extraction of the historical operation and maintenance data can be achieved by utilizing the mean of statistical data, and the construction of the data training model of the historical operation and maintenance data based on the operation and maintenance features can be obtained through a machine learning model, such as an Isolation Forest model.

[0037] S2. Based on the abnormal situation, create the intention input text of the platform to be operated and maintained, extract the key features of the intention input text, and based on the key features, identify the high-level operation and maintenance intention of the intention input text, and set the operation task of the intention input text according to the high-level operation and maintenance intention.

[0038] The embodiment of the present invention creates the intention input text of the operation and maintenance platform based on the abnormal situation, and can clarify the actual needs of the operation and maintenance engineer by analyzing the user's intention input data, rather than simply executing commands. The intention input text refers to the text or request input by the operation and maintenance engineer to the operation and maintenance platform in order to complete a certain operation and maintenance task, such as restarting the server.

[0039] As an embodiment of the present invention, the creation of the intention input text of the platform to be operated and maintained based on the abnormal situation includes: identifying the cause of the abnormal situation, and defining the operation and maintenance requirements of the abnormal situation based on the cause; identifying the operation and maintenance type of the abnormal situation based on the operation and maintenance requirements; scheduling the operation and maintenance data of the abnormal situation, and extracting key information of the operation and maintenance data; setting the intention input template of the platform to be operated and maintained according to the operation and maintenance type; and creating the intention input text of the platform to be operated and maintained by combining the key information and the intention input template.

[0040] Among them, the formation cause refers to the specific reason that leads to the occurrence of the abnormal situation, the operation and maintenance requirements refer to the measures that need to be taken based on the formation cause of the abnormal situation in order to restore the normal operation of the system or prevent the problem from expanding, the operation and maintenance type refers to the different operation and maintenance work categories defined according to the operation and maintenance requirements, the operation and maintenance data refers to all relevant data generated during the operation and maintenance process, including log files, monitoring indicators, event records, and configuration information, the key information refers to the data points extracted from the operation and maintenance data that are crucial to identifying and resolving anomalies, and the intent input template refers to a predefined format or framework for creating the intent input text of the platform to be operated and maintained.

[0041] Optionally, the identification of the cause of the abnormal situation can be obtained by analyzing logs, monitoring data and user reports, and the identification of the operation and maintenance type of the abnormal situation based on the operation and maintenance requirements can be achieved by using a classification method.

[0042] Furthermore, the embodiments of the present invention can quickly identify and classify the intentions of operation and maintenance engineers, shorten system response time, and improve operation and maintenance efficiency by extracting key features of the intent input text and identifying high-level operation and maintenance intentions of the intent input text based on the key features. The key features refer to information elements extracted from the intent input text that are crucial to understanding the intent of the text. The high-level operation and maintenance intentions refer to the broad goals or requirements that operation and maintenance engineers hope to achieve when managing, maintaining, and servicing IT infrastructure.

[0043] As an embodiment of the present invention, the identifying the high-level operation and maintenance intention of the intention input text based on the key features includes: constructing an intention category prediction model of the intention input text based on the key features; identifying the probability distribution of the intention input text in the intention category prediction model; identifying the maximum probability value in the probability distribution, and identifying the intention category of the intention input text based on the maximum probability value; setting a judgment threshold of the maximum probability value based on the probability distribution; identifying the prediction credibility of the intention category prediction model for the intention category based on the judgment threshold; and extracting the high-level operation and maintenance intention of the intention input text from the intention category based on the prediction credibility.

[0044] Among them, the intent category prediction model refers to a machine learning model that uses key features to predict the intent category of the text input by the operation and maintenance engineer, the probability distribution refers to the model's probability estimate of the intent input text belonging to each predefined intent category, the maximum probability value refers to the value with the highest probability in the probability distribution of the intent input text output by the model, the intent category refers to the classification label of the operation and maintenance intent expressed by the intent input text, the judgment threshold refers to a measurement value used to determine whether the model's prediction is confident enough, and the prediction credibility refers to the model's confidence in its prediction results.

[0045] Optionally, the construction of the intent category prediction model of the intent input text based on the key features can be generated by a deep learning model, such as a BERT model, and the probability distribution recognition of the intent input text in the intent category prediction model can be implemented by utilizing the output layer of the intent category prediction model, such as a softmax layer, and the maximum probability value recognition in the probability distribution can be found by an argmax function, and the extraction of high-level operation and maintenance intent of the intent input text from the intent category based on the prediction credibility can be implemented by utilizing NLP parsing technology.

[0046] The embodiment of the present invention can reasonably allocate resources and priorities by setting the operation tasks of the intention input text according to the high-level operation and maintenance intention, ensuring that critical and urgent operation and maintenance tasks are given priority. By accurately identifying the intention and extracting the slot information, the system can generate more accurate operation tasks and reduce erroneous operations caused by misunderstanding or incomplete information. The operation task refers to a specific action instruction or workflow generated in the system based on the identified high-level operation and maintenance intention.

[0047] As an embodiment of the present invention, setting the operation task of the intention input text according to the high-level operation and maintenance intention includes: identifying the slot information of the high-level operation and maintenance intention; defining the mapping relationship between the high-level operation and maintenance intention and the slot information; constructing a task template of the high-level operation and maintenance intention based on the mapping relationship; filling the slot information into the task template to obtain a task filling template; setting the task execution steps of the intention input text according to the task filling template; and setting the operation task of the intention input text in combination with the task filling template and the task execution steps.

[0048] Among them, the slot information refers to specific details or parameters related to a specific intention. For example, if the operation and maintenance engineer's intention is to restart the server, then the slot information may include which server, when to restart, etc. The mapping relationship refers to the corresponding instructions between high-level operation and maintenance intentions and corresponding operation tasks. The task template refers to a framework of a series of operation steps predefined for a specific intention. The task filling template refers to an operation task template generated by filling the identified slot information into the template on the basis of the task template. The task execution steps refer to the detailed steps of the specific operation task generated according to the filled template.

[0049] Optionally, the slot information extraction of the high-level operation and maintenance intention can be obtained through a sequence labeling model, such as an HMM model, and the mapping relationship definition between the high-level operation and maintenance intention and the slot information can be implemented using an instruction table. Based on the mapping relationship, the task template construction of the high-level operation and maintenance intention can be designed according to the scope of operation tasks defined in the mapping relationship.

[0050] S3. Assign task details of the operation task, set a decision basis for the platform to be operated and maintained in combination with the abnormal situation and the task details, set a decision instruction for the platform to be operated and maintained based on the decision basis, and perform intelligent decision analysis on the platform to be operated and maintained according to the decision basis and the decision instruction to obtain a decision analysis result.

[0051] The embodiment of the present invention can clarify the resource allocation of the operation engine in a multi-task environment by allocating the task details of the operation task, and ensure that the task is carried out according to the predetermined plan. The task details refer to the steps, methods and techniques taken by the operation engine when performing specific operation and maintenance tasks.

[0052] Optionally, the task detail allocation of the operation task can be implemented by using an automation script tool, such as Ansible to write and execute automation scripts.

[0053] Furthermore, the embodiments of the present invention set the decision basis of the platform to be operated and maintained by combining the abnormal situation and the task details. By analyzing the abnormal situation in real time, potential problems can be quickly identified and responded to, so that the operation and maintenance platform can automatically perform routine operation and maintenance tasks, reduce manual intervention, and improve the automation level of operation and maintenance. The decision basis refers to the decision reference of all relevant information, data, analysis, instructions and logical reasoning relied on when making a decision.

[0054] As an embodiment of the present invention, the decision basis of the platform to be operated and maintained is set in combination with the abnormal situation and the task details, including: extracting the abnormal analysis result of the abnormal situation; configuring the execution engine of the task details based on the abnormal analysis result; setting the response measures of the execution engine to the abnormal situation; analyzing the response effect of the execution engine to the abnormal situation according to the response measures; and setting the decision basis of the platform to be operated and maintained based on the response effect and the response measures.

[0055] Among them, the anomaly analysis result refers to the conclusion obtained after analyzing the operation and maintenance data through the anomaly detection system, the execution engine refers to the system or tool responsible for executing response measures, such as a workflow automation tool, the response effect refers to the result and impact obtained after executing the abnormal situation processing, and the response measure refers to a series of automated or semi-automated actions taken to deal with the detected anomaly.

[0056] Optionally, the response effect analysis of the execution engine to the abnormal situation can be obtained through an automated analysis tool, such as a FindAll tool, and the response measure setting of the execution engine to the abnormal situation can be implemented using an automated response mechanism.

[0057] The embodiment of the present invention sets the decision instructions of the platform to be operated and maintained based on the decision basis, so as to guide the decision engine on how to respond to specific situations, reduce manual intervention, improve response speed and accuracy, and optimize resource allocation and improve resource utilization through intelligent decision-making. The decision instructions refer to the actions that the decision engine should take under specific circumstances.

[0058] As an embodiment of the present invention, the decision instructions of the platform to be operated and maintained are set based on the decision basis, including: identifying the decision engine of the operation and maintenance platform based on the decision basis; analyzing the event type of the decision basis, and setting the trigger condition of the decision engine according to the event type; setting the logical expression of the trigger condition, and setting the operation instruction of the event type based on the logical expression; identifying the urgency of the event type, and defining the task priority of the operation instruction according to the urgency; setting the hierarchical processing mechanism of the operation instruction based on the task priority; setting the decision instruction of the decision engine according to the hierarchical processing mechanism.

[0059] Among them, the decision engine refers to a component that uses predefined logic, instructions, algorithms or machine learning models to analyze data and automatically makes decisions based on these analyses; the event type refers to a specific type of event that is identified and recorded in the system; the trigger condition refers to the specific standard or situation for initiating the decision instruction; the logical expression refers to a set of logical operators and conditions in the decision instruction, and the complex conditions used to define the triggering operation instructions include logical operators such as AND, OR, and NOT; the operation instruction refers to the specific action that the decision engine needs to perform when the trigger condition and logical expression are met; the urgency refers to the severity level of the event or problem; the task priority refers to the execution order determined according to the urgency and importance of multiple operation instructions or response measures when they need to be executed; the hierarchical processing mechanism refers to a system mechanism for allocating resources and response measures according to the urgency of the event and the priority of the task.

[0060] Optionally, based on the event type, the trigger condition setting of the decision engine can be obtained through specific performance indicators, such as CPU usage exceeding 90%, the logical expression setting of the trigger condition can be implemented using a visual programming tool, such as the Mugeda tool, and the urgency identification of the event type can be implemented using a risk assessment model, such as a decision tree model.

[0061] Furthermore, the embodiment of the present invention performs intelligent decision analysis on the platform to be operated and maintained according to the decision basis and the decision instructions to obtain decision analysis results, which can drive the execution of automated scripts and tasks to achieve automation and intelligence of operation and maintenance operations. The decision analysis results are a series of conclusions and suggestions drawn by the intelligent operation and maintenance platform after applying the decision basis and decision instructions, such as fault diagnosis, performance bottlenecks, configuration change suggestions, etc.

[0062] Optionally, based on the decision basis and the decision instruction, the intelligent decision analysis of the platform to be operated and maintained can be implemented using an automated testing tool, such as an APIfox testing tool.

[0063] S4. According to the decision analysis result, a specific operation and maintenance plan for the platform to be operated and maintained is set, and based on the specific operation and maintenance plan, operation and maintenance processing is performed on the platform to be operated and maintained to obtain an operation and maintenance result.

[0064] The embodiment of the present invention can provide clear operation records and audit trails, improve the transparency of operation and maintenance operations, and dynamically adjust task execution strategies according to the decision analysis results to adapt to the ever-changing operation and maintenance environment and user needs by setting a specific operation and maintenance plan for the platform to be operated and maintained according to the decision analysis results. The specific operation and maintenance plan refers to a detailed action plan formulated to implement the operation and maintenance tasks of the decision engine or respond to the user intentions of the intent engine.

[0065] As an embodiment of the present invention, setting a specific operation and maintenance plan for the platform to be operated and maintained according to the decision analysis result includes: identifying specific instructions of the decision analysis result; defining an automation artifact set of the task operation engine according to the specific instructions; scheduling automation artifacts of the automation artifact set, and setting an instruction scheduling mechanism for the specific instructions and the automation artifacts; setting an execution mode of the automation artifacts according to the instruction scheduling mechanism; identifying operable tasks of the task operation engine in combination with the instruction scheduling mechanism and the execution mode; and setting a specific operation and maintenance plan for the platform to be operated and maintained based on the operable tasks.

[0066] Among them, the specific instructions refer to clear action instructions generated by the decision engine based on preset decision instructions and real-time data analysis results, the automation artifact set refers to a set of predefined, reusable automation operations or scripts, the automation artifact refers to a single, executable automation operation or script, the instruction scheduling mechanism refers to the logic and process inside the operation engine for managing and executing specific instructions, and the execution mode refers to the specific method by which the automation artifact is called and executed.

[0067] Optionally, according to the specific instructions, the automation artifact set definition of the task operation engine can be obtained through an automated operation and maintenance tool, such as the Puppet operation and maintenance tool, and the specific instructions and the instruction scheduling mechanism setting of the automation artifact can be implemented using a workflow task scheduler, such as an Azkaban scheduler, and according to the instruction scheduling mechanism, the execution mode setting of the automation artifact can be completed through PLC programming software, such as Rockwell Automation's RSLogix software.

[0068] Furthermore, the embodiment of the present invention performs operation and maintenance processing on the platform to be operated and maintained based on the specific operation and maintenance plan to obtain operation and maintenance results, thereby realizing automatic generation and adaptive adjustment of instructions, thereby improving the quality and speed of decision-making, and reducing dependence on manual operations through automated and intelligent operation and maintenance operations, thereby reducing the operating costs of financial enterprises. At the same time, the intelligent operation and maintenance platform can also realize unattended operation and maintenance operations, reduce manual intervention, improve the automation level of operation and maintenance, and can quickly respond to various operation and maintenance events and problems, and improve the response speed and processing capabilities of the system. The operation execution result refers to the actual effect and feedback information after the operation and maintenance operation is performed according to the specific operation plan.

[0069] It can be seen that in the above scheme, by collecting real-time operation and maintenance data and historical operation and maintenance data of the platform to be operated and maintained, it helps the operation and maintenance personnel to quickly discover and accurately handle abnormal events of the IT system, shorten the average repair time, and upgrade from passive operation and maintenance to active operation and maintenance. At the same time, it can detect abnormalities before the business department reports the fault based on the comparison of historical data and combined with the current situation reasoning, thereby improving the response speed; secondly, the embodiment of the present invention can quickly identify and classify the intentions of the operation and maintenance engineers by extracting the key features of the intent input text and identifying the high-level operation and maintenance intentions of the intent input text based on the key features, thereby shortening the system response time and improving the operation and maintenance efficiency. The key features refer to information elements extracted from the intent input text that are crucial to understanding the text intent; further, the present invention The embodiment performs intelligent decision analysis on the operation and maintenance platform according to the decision basis and the decision instruction to obtain the decision analysis result, which can drive the execution of automated scripts and tasks to realize the automation and intelligence of operation and maintenance operations; finally, the embodiment of the present invention performs operation and maintenance processing on the platform to be operated and maintained based on the specific operation and maintenance plan to obtain the operation and maintenance result, which can realize the automatic generation and adaptive adjustment of instructions, thereby improving the quality and speed of decision-making, and through automated and intelligent operation and maintenance operations, reducing the dependence on manual operations, thereby reducing operating costs. At the same time, the intelligent operation and maintenance platform can also realize unattended operation and maintenance operations, reduce manual intervention, improve the automation level of operation and maintenance, and can quickly respond to various operation and maintenance events and problems, and improve the response speed and processing capacity of the system. Therefore, the operation and maintenance control method, device, computer equipment and computer-readable storage medium based on intent recognition proposed in the embodiment of the present invention can improve the operation and maintenance efficiency by using high-level operation and maintenance intentions and decision instructions.

[0070] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0071] In one embodiment, an operation and maintenance control device based on intent recognition is provided, and the operation and maintenance control device based on intent recognition corresponds one-to-one to the operation and maintenance control method based on intent recognition in the above embodiment. Figure 6 As shown, the operation and maintenance control device based on intention recognition includes a data perception module 101, an intention decomposition module 102, a decision analysis module 103 and an operation execution module 104. The functional modules are described in detail as follows:

[0072] The data sensing module 101 is used to collect real-time operation and maintenance data and historical operation and maintenance data of the platform to be operated and maintained, and perform anomaly detection on the real-time operation and maintenance data according to the historical operation and maintenance data to obtain anomaly detection data;

[0073] The intention decomposition module 102 is used to create an intention input text of the platform to be operated and maintained based on the abnormal situation, extract key features of the intention input text, and identify the high-level operation and maintenance intention of the intention input text based on the key features, and set the operation task of the intention input text according to the high-level operation and maintenance intention;

[0074] The decision analysis module 103 is used to assign task details of the operation task, set a decision basis for the platform to be operated and maintained in combination with the abnormal situation and the task details, set a decision instruction for the platform to be operated and maintained based on the decision basis, and perform intelligent decision analysis on the platform to be operated and maintained according to the decision basis and the decision instruction to obtain a decision analysis result;

[0075] The operation execution module 104 is used to set a specific operation and maintenance plan for the platform to be operated and maintained according to the decision analysis result, and perform operation and maintenance processing on the platform to be operated and maintained based on the specific operation and maintenance plan to obtain an operation and maintenance result.

[0076] In one embodiment, when the data perception module 101 performs anomaly detection on the real-time operation and maintenance data based on the historical operation and maintenance data to obtain anomaly detection data, it is used to: extract the operation and maintenance characteristics of the historical operation and maintenance data; construct a data training model for the historical operation and maintenance data based on the operation and maintenance characteristics; identify the statistical characteristics of the historical operation and maintenance data, and set an anomaly threshold of the data training model based on the statistical characteristics; perform anomaly detection on the real-time operation and maintenance data based on the anomaly threshold to obtain anomaly detection data.

[0077] In one embodiment, when the intention decomposition module 102 is executing to create the intention input text of the platform to be operated and maintained based on the abnormal situation, it is used to: identify the cause of the abnormal situation, and define the operation and maintenance requirements of the abnormal situation based on the cause; identify the operation and maintenance type of the abnormal situation based on the operation and maintenance requirements; schedule the operation and maintenance data of the abnormal situation, and extract the key information of the operation and maintenance data; set the intention input template of the platform to be operated and maintained according to the operation and maintenance type; and create the intention input text of the platform to be operated and maintained by combining the key information and the intention input template.

[0078] In one embodiment, when the intention decomposition module 102 is executing the identification of the high-level operational intention of the intention input text based on the key features, it is used to: construct an intention category prediction model for the intention input text based on the key features; identify the probability distribution of the intention input text in the intention category prediction model; identify the maximum probability value in the probability distribution, and identify the intention category of the intention input text based on the maximum probability value; set a judgment threshold for the maximum probability value based on the probability distribution; identify the prediction credibility of the intention category prediction model for the intention category based on the judgment threshold; and extract the high-level operational intention of the intention input text from the intention category based on the prediction credibility.

[0079] In one embodiment, when the intention decomposition module 102 executes the operation task of setting the intention input text according to the high-level operation and maintenance intention, it is used to: identify the slot information of the high-level operation and maintenance intention; define the mapping relationship between the high-level operation and maintenance intention and the slot information; construct a task template for the high-level operation and maintenance intention based on the mapping relationship; fill the slot information into the task template to obtain a task filling template; set the task execution steps of the operation and maintenance intention according to the task filling template; and set the operation task of the intention input text in combination with the task filling template and the task execution steps.

[0080] In one embodiment, the decision analysis module 103 sets the decision basis of the platform to be operated and maintained in combination with the abnormal situation and the task details during execution, including: extracting the abnormal analysis results of the abnormal situation; configuring the execution engine of the task details based on the abnormal analysis results; setting the response measures of the execution engine to the abnormal situation; analyzing the response effect of the execution engine to the abnormal situation according to the response measures; and setting the decision basis of the platform to be operated and maintained based on the response effect and the response measures.

[0081] In one embodiment, the operation execution module 104 sets a specific operation and maintenance plan for the platform to be operated and maintained according to the decision analysis result, including: identifying specific instructions of the decision analysis result; defining an automation artifact set of the task operation engine according to the specific instructions; scheduling automation artifacts of the automation artifact set, and setting an instruction scheduling mechanism for the specific instructions and the automation artifacts; setting an execution mode of the automation artifacts according to the instruction scheduling mechanism; identifying operable tasks of the task operation engine in combination with the instruction scheduling mechanism and the execution mode; and setting a specific operation and maintenance plan for the platform to be operated and maintained based on the operable tasks.

[0082] For the specific limitations of the operation and maintenance control device based on intent recognition, please refer to the limitations of the intelligent question and answer method above, which will not be repeated here. The various modules in the above-mentioned operation and maintenance control device based on intent recognition can be implemented in whole or in part through software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0083] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 7 As shown. The computer device includes a processor, a memory, a network interface and a database connected via a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile and / or volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external client through a network connection. When the computer program is executed by the processor, it realizes the functions or steps on the service side of an operation and maintenance control method based on intent recognition.

[0084] In one embodiment, a computer device is provided. The computer device may be a client, and its internal structure diagram may be as follows: Figure 8As shown. The computer device includes a processor, a memory, a network interface, a display screen and an input device connected via a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external server via a network connection. When the computer program is executed by the processor, it realizes the functions or steps on the client side of an operation and maintenance control method based on intent recognition.

[0085] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the computer program:

[0086] Collecting real-time operation and maintenance data and historical operation and maintenance data of the platform to be operated and maintained, and performing anomaly detection on the real-time operation and maintenance data according to the historical operation and maintenance data to obtain anomaly detection data;

[0087] Based on the abnormal situation, create an intention input text of the platform to be operated and maintained, extract key features of the intention input text, and identify the high-level operation and maintenance intention of the intention input text based on the key features, and set the operation task of the intention input text according to the high-level operation and maintenance intention;

[0088] Assigning task details of the operation task, setting a decision basis for the platform to be operated and maintained in combination with the abnormal situation and the task details, setting a decision instruction for the platform to be operated and maintained based on the decision basis, and performing intelligent decision analysis on the platform to be operated and maintained according to the decision basis and the decision instruction to obtain a decision analysis result;

[0089] According to the decision analysis result, a specific operation and maintenance plan for the platform to be operated and maintained is set, and based on the specific operation and maintenance plan, operation and maintenance processing is performed on the platform to be operated and maintained to obtain an operation and maintenance result.

[0090] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0091] Collecting real-time operation and maintenance data and historical operation and maintenance data of the platform to be operated and maintained, and performing anomaly detection on the real-time operation and maintenance data according to the historical operation and maintenance data to obtain anomaly detection data;

[0092] Based on the abnormal situation, create an intention input text of the platform to be operated and maintained, extract key features of the intention input text, and identify the high-level operation and maintenance intention of the intention input text based on the key features, and set the operation task of the intention input text according to the high-level operation and maintenance intention;

[0093] Assigning task details of the operation task, setting a decision basis for the platform to be operated and maintained in combination with the abnormal situation and the task details, setting a decision instruction for the platform to be operated and maintained based on the decision basis, and performing intelligent decision analysis on the platform to be operated and maintained according to the decision basis and the decision instruction to obtain a decision analysis result;

[0094] According to the decision analysis result, a specific operation and maintenance plan for the platform to be operated and maintained is set, and based on the specific operation and maintenance plan, operation and maintenance processing is performed on the platform to be operated and maintained to obtain an operation and maintenance result.

[0095] It should be noted that the above functions or steps that can be implemented by the computer-readable storage medium or computer device can refer to the relevant descriptions on the server side and the client side in the aforementioned method embodiment. To avoid repetition, they will not be described one by one here.

[0096] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0097] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0098] The above-described embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some of the technical features therein by equivalents; and these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention, and should be included in the protection scope of the present invention. It should be noted that if software tools or components other than those of the company appear in the embodiments of this application, they are only used for illustration and do not represent actual use.

Claims

1. An operation and maintenance control method based on intention recognition, characterized in that: include: Collecting real-time operation and maintenance data and historical operation and maintenance data of the platform to be operated and maintained, and performing anomaly detection on the real-time operation and maintenance data according to the historical operation and maintenance data to obtain anomaly detection data; Based on the abnormal situation, create an intention input text of the platform to be operated and maintained, extract key features of the intention input text, and identify the high-level operation and maintenance intention of the intention input text based on the key features, and set the operation task of the intention input text according to the high-level operation and maintenance intention; Assigning task details of the operation task, setting a decision basis for the platform to be operated and maintained in combination with the abnormal situation and the task details, setting a decision instruction for the platform to be operated and maintained based on the decision basis, and performing intelligent decision analysis on the platform to be operated and maintained according to the decision basis and the decision instruction to obtain a decision analysis result; According to the decision analysis result, a specific operation and maintenance plan for the platform to be operated and maintained is set, and based on the specific operation and maintenance plan, operation and maintenance processing is performed on the platform to be operated and maintained to obtain an operation and maintenance result.

2. The operation and maintenance control method based on intention recognition according to claim 1, characterized in that: The performing anomaly detection on the real-time operation and maintenance data according to the historical operation and maintenance data to obtain anomaly detection data includes: Extracting operation and maintenance features of the historical operation and maintenance data; Based on the operation and maintenance characteristics, construct a data training model for the historical operation and maintenance data; Identifying statistical characteristics of the historical operation and maintenance data, and setting an abnormal threshold of the data training model according to the statistical characteristics; Based on the abnormality threshold, anomaly detection is performed on the real-time operation and maintenance data to obtain abnormality detection data.

3. The operation and maintenance control method based on intention recognition according to claim 1, characterized in that: The step of creating the intended input text of the platform to be operated and maintained based on the abnormal situation includes: Identify the cause of the abnormal situation, and define the operation and maintenance requirements of the abnormal situation according to the cause; Based on the operation and maintenance requirements, identifying the operation and maintenance type of the abnormal situation; Dispatching the operation and maintenance data of the abnormal situation and key information of the operation and maintenance data; According to the operation and maintenance type, setting an intention input template for the platform to be operated and maintained; The key information and the intention input template are combined to create the intention input text of the platform to be operated and maintained.

4. The operation and maintenance control method based on intention recognition according to claim 1, characterized in that: The identifying the high-level operation and maintenance intent of the intention input text based on the key features includes: Based on the key features, construct an intent category prediction model for the intent input text; Identify the probability distribution of the intended input text in the intent category prediction model; Identifying a maximum probability value in the probability distribution, and identifying an intent category of the intended input text according to the maximum probability value; Based on the probability distribution, setting a judgment threshold of the maximum probability value; According to the judgment threshold, identifying the prediction credibility of the intention category prediction model for the intention category; Based on the prediction credibility, a high-level operation and maintenance intent of the intent input text is extracted from the intent category.

5. The operation and maintenance control method based on intention recognition according to claim 1, characterized in that: The step of setting the operation task of the intention input text according to the high-level operation and maintenance intention includes: Identify slot information of the high-level operation and maintenance intent; Defining a mapping relationship between the high-level operation and maintenance intent and the slot information; Based on the mapping relationship, construct a task template for the high-level operation and maintenance intention; Fill the slot information into the task template to obtain a task filling template; Fill in the template according to the task, and set the task execution steps of the operation and maintenance intention; In combination with the task filling template and the task execution steps, an operation task for the intended input text is set.

6. The operation and maintenance control method based on intention recognition according to claim 1, characterized in that: The step of setting a decision basis for the platform to be operated and maintained in combination with the abnormal situation and the task details includes: Extracting an abnormality analysis result of the abnormal situation; Based on the abnormal analysis result, configuring the execution engine of the task details; Setting the response measures of the execution engine to the abnormal situation; Analyzing the response effect of the execution engine to the abnormal situation according to the response measures; Based on the response effect and the response measures, a decision basis for the platform to be operated and maintained is set.

7. The operation and maintenance control method based on intention recognition as described in claim 1, characterized in that: The step of setting a specific operation and maintenance plan for the platform to be operated and maintained according to the decision analysis result includes: identifying specific instructions for the decision analysis results; According to the specific instructions, define an automation artifact set of the task operation engine; Scheduling the automation artifacts of the automation artifact set, and setting an instruction scheduling mechanism between the specific instructions and the automation artifacts; According to the instruction scheduling mechanism, setting the execution mode of the automation workpiece; In combination with the instruction scheduling mechanism and the execution mode, identifying operable tasks of the task operation engine; Based on the operable tasks, a specific operation and maintenance plan for the platform to be operated and maintained is set.

8. An operation and maintenance control device based on intention recognition, characterized in that: include: A data perception module is used to create an intended input text of the platform to be operated and maintained based on the abnormal situation, extract key features of the intended input text, and identify the high-level operation and maintenance intention of the intended input text based on the key features, and set an operation task for the intended input text according to the high-level operation and maintenance intention; The intention decomposition module is used to collect the real-time operation and maintenance data and the historical operation and maintenance data of the platform to be operated and maintained, and perform anomaly detection on the real-time operation and maintenance data according to the historical operation and maintenance data to obtain anomaly detection data; A decision analysis module, used to assign task details of the operation task, set a decision basis for the platform to be operated and maintained in combination with the abnormal situation and the task details, set a decision instruction for the platform to be operated and maintained based on the decision basis, and perform intelligent decision analysis on the platform to be operated and maintained according to the decision basis and the decision instruction to obtain a decision analysis result; The operation execution module is used to set a specific operation and maintenance plan for the platform to be operated and maintained according to the decision analysis result, and perform operation and maintenance processing on the platform to be operated and maintained based on the specific operation and maintenance plan to obtain an operation and maintenance result.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the operation and maintenance control method based on intent recognition as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the operation and maintenance control method based on intent recognition as described in any one of claims 1 to 7 are implemented.

Images