Airport information system fault root cause location and fault automatic processing method and system

Abstract

The present invention belongs to the technical field of information fault processing, and discloses a method and system for locating the root cause of airport information system faults and automatically processing faults. The alarm information of the airport information system is collected, and the alarm information includes information system IP information, information system alarm information, system server CPU information, I / O information, disk information, application software information, and middleware information; the association weights of alarms and influencing factors of information system faults are calculated by the FP‑Growth algorithm, and the influencing factors of airport information system faults include network factors, server equipment factors, middleware factors, application factors, and database factors. The present invention collects indicator data of the airport information system, uses a large model and the FP‑Growth algorithm to locate the root cause of business system fault alarms, and according to the built-in automation script, the system automatically processes the script through commands, quickly recovers system faults, and improves the stability and security of the airport system.

Description

Technical Field

[0001] The present invention belongs to the technical field of information fault processing, and in particular relates to a method and system for locating the root cause of a fault in an airport information system and automatically processing the fault. Background Art

[0002] The exponential growth of the technical complexity of airport information systems has brought about many challenges. It is necessary to continuously improve the professional capabilities of technical personnel, optimize the fault handling process, and strengthen the system monitoring and early warning mechanism to improve the operation and maintenance efficiency to ensure the stable operation of the airport information system. The root cause location and automatic fault handling of airport information system faults play a key role in improving the operation and maintenance efficiency, and are the most effective means for the airport information system to quickly recover from faults. Therefore, the airport business system needs to adopt a method for locating the root cause of airport information system faults and automatic fault handling, which can greatly shorten the fault handling time, reduce the system downtime, ensure the continuous stability of the airport information system, and improve operational efficiency and service quality.

[0003] The invention patent (publication number CN112152830B, publication date 20190628) discloses an intelligent fault root cause analysis method and system. The method determines the cause of the fault through the indicator correlation relationship and fault tracing map of the fault occurrence time period; based on the cause of the fault, the solution corresponding to the fault is obtained from the operation and maintenance knowledge base. The technical solution provided by the present invention can quickly locate the cause of the fault and recommend solutions, which greatly reduces the burden on IT operation and maintenance personnel, improves operation and maintenance efficiency, and ensures the normal operation of the system.

[0004] The invention patent (publication number CN115952902A, publication date 20230411) discloses an AI-based operation and maintenance fault determination method, device, equipment and storage medium. The method includes: determining the fault phenomenon network element and fault time, determining the related network elements corresponding to the fault phenomenon network element; obtaining the operation and maintenance data to be analyzed corresponding to the fault phenomenon network element and the related network element; preprocessing the operation and maintenance data to be analyzed to obtain vectorized element information; inputting the vectorized element information into a pre-trained fault root cause analysis model, and outputting the fault root cause corresponding to the operation and maintenance data to be analyzed; determining standardized training samples by processing historical operation and maintenance data, obtaining a fault root cause analysis model based on standardized training samples, and then analyzing the operation and maintenance data based on the trained fault root cause analysis model to determine the fault root cause, thereby improving the processing capacity of operation and maintenance data and the accuracy of fault root cause mining.

[0005] The above methods are based on fault tracing maps and vectorized network elements to locate the root cause of information system failures. However, airport business is unique and complex, and requires more accurate and intelligent fault location and automatic fault handling mechanisms to ensure the stable operation of its system. Therefore, a method for locating the root cause of airport information system failures and automatic fault handling is needed. Summary of the invention

[0006] In order to overcome the problems existing in the related art, the disclosed embodiments of the present invention provide a method and system for locating the root cause of airport information system faults and automatically handling faults. The purpose of the present invention is to collect airport business system alarm information, use the FP-Growth algorithm and the Tongyi Qianwen model to analyze the root cause of system faults, and use built-in automated scripts to quickly realize automatic recovery of system faults to ensure the normal operation of the airport system.

[0007] The technical solution is as follows: A method for locating the root cause of a fault in an airport information system and automatically handling the fault, comprising:

[0008] S1, collects the alarm information of the airport information system, which includes information system IP information, information system alarm information, system server CPU information, I / O information, disk information, application software information, and middleware information;

[0009] S2, calculate the correlation weights of alarms and influencing factors of information system failures through the FP-Growth algorithm. The influencing factors of airport information system failures include network factors, server equipment factors, middleware factors, application factors, and database factors;

[0010] S3, based on prompt word training and fine-tuning technology, enhances the log analysis capability of the Tongyi Qianwen large model. Through prompt engineering combined with fault influencing factors and their weights, the Tongyi Qianwen large model is requested to perform log analysis and generate a root cause report.

[0011] S4, according to the root cause report, matches the built-in automation script, triggers and executes the script through the script command, and restores the fault;

[0012] S5, according to the current fault alarm situation of the airport, adjust the corresponding parameters to improve the accuracy of locating the root cause, realize fault recovery, and improve the safety of airport operations.

[0013] In step S2, the association weights of alarms and influencing factors of information system failures are calculated by the FP-Growth algorithm, including:

[0014] S201, alarm information time sequence preprocessing, forming alarm events at each moment, the expression is:

[0015] ;

[0016] In the formula, for Always warn of events, for Always warn of events, The server IP address when the alarm event occurs. for The CPU usage of the server at the moment, for The disk IO in and out traffic of the server at all times. for Server memory usage at the moment, for The available space size of the server's C drive at the moment;

[0017] S202, the transactions in the alarm information within a period of time are formed into a transaction data set, which is expressed as:

[0018] ;

[0019] in, This is the first alarm event in a period of time. This is the second alarm event within a period of time. This is the third alarm event within a period of time. For a period of time An alarm event;

[0020] S203, the items in each transaction that have alarm information are classified as a separate item, all of which are alarm-related items, and each such transaction corresponds to a As labels, they are called alarm correlation factors on each server;

[0021] S204, based on the FP-Growth correlation algorithm, correlation analysis is performed between the influencing factors of the information system failure and the alarm;

[0022] S205, obtaining the correlation degree between the influencing factors of the system failure and the alarm information according to the alarm correlation analysis model, and calculating the correlation weight between the influencing factors of the information system failure and the alarm information according to the correlation degree;

[0023] S206, repeating steps S203 to S205 until the frequent fault influencing factors can no longer generate alarms.

[0024] In step S203, the expression of the alarm correlation factor on each server is:

[0025] ;

[0026] In the formula, For each server, the alarm correlation factor is: is the number of failures that occurred on the server, is the total number of failures.

[0027] In step S204, the expression of the alarm association analysis model is:

[0028] ;

[0029] In the formula, is the correlation degree between the alarm event X and the fault influencing factor M, is the total number of alarm events in the time period, is the correlation between the fault influencing factor M and the alarm event X, For warning events, As an influencing factor.

[0030] In step S205, the expression of the correlation weight between the influencing factors of the information system failure and the alarm information is:

[0031] ;

[0032] In the formula, is the association weight between the fault influencing factor M and the alarm event X, is the number of times the alarm event X occurs;

[0033] (1) When ,The factors affecting system failure and the alarm information are strongly correlated;

[0034] (2) When ,The influencing factors of system failure and the alarm information are independent of each other;

[0035] (3) When ,The ,factors affecting system failures and the alarm information are weakly correlated.

[0036] In step S3, a root cause report is generated, including:

[0037] S301, obtaining log information of all failure influencing factors of the monitoring system through a system monitoring tool;

[0038] S302, pre-setting prompt word categories of network, server hardware, application system, middleware, and database in the Tongyi Qianwen large model;

[0039] S303, manually analyzing and matching preset prompt word categories and historical question logs, the Tongyi Qianwen big model trains the matched prompt word categories and historical question logs, enhances the log understanding and analysis capabilities, and quickly extracts key information through keywords;

[0040] S304, the Tongyi Qianwen model screens the preset prompt word categories according to the weights of the associated fault influencing factors;

[0041] S305, the Tongyi Qianwen model returns the question log of the most likely influencing factor according to the category of the prompt words after screening;

[0042] S306, based on the error log, the system automatically generates a root cause report including the server IP, middleware, error code, and error log.

[0043] In step S4, the script is triggered and executed through a script command to recover from the fault, including:

[0044] S401, collect common problems and establish a built-in automation script;

[0045] Collect common software problems including common errors of rabbitMQ, Ngix, Tomcat, JBoss, SpringBoot, and Redis; automatically obtain monitoring server deployment software instances and startup paths by directly reading the Windows registry; set up Python automated restart scripts for Linux and Windows middleware through the system;

[0046] S402, matching the information in the problem root cause report with the automation script according to the software instance name and the common error problem code;

[0047] S403, once a suitable automation script is matched, the system automatically triggers and executes the script through a command;

[0048] S404, the system automatically obtains the script execution result on the server and notifies the user of the result.

[0049] Another object of the present invention is to provide a system for locating the root cause of a fault in an airport information system and automatically handling the fault, the system implementing the method for locating the root cause of a fault in an airport information system and automatically handling the fault, comprising:

[0050] Resource data module, collects the alarm information of the airport information system, which includes information system IP information, information system alarm information, system server CPU information, I / O information, disk information, application software information, and middleware information;

[0051] The correlation information building module is used to calculate the correlation weights of alarms and influencing factors of information system failures through the FP-Growth algorithm. The influencing factors of airport information system failures include network factors, server equipment factors, middleware factors, application factors, and database factors.

[0052] The problem root cause construction module, based on prompt word training and fine-tuning technology, enhances the log analysis capability of the Tongyi Qianwen large model. Through prompt engineering combined with fault influencing factors and their weights, the Tongyi Qianwen large model is requested to perform log analysis and generate a problem root cause report;

[0053] Matching automation script module, matching built-in automation script according to the problem root cause report;

[0054] Automatic fault handling building module, triggering and executing scripts through script commands to recover from faults;

[0055] The root cause analysis and automatic fault handling improvement module adjusts the corresponding parameters according to the current fault alarm conditions of the airport, improves the accuracy of locating the root cause, realizes fault recovery, and improves the safety of airport operations.

[0056] Another object of the present invention is to provide a storage medium for receiving user input programs, wherein the stored computer program enables an electronic device to execute the airport information system fault root cause location and fault automatic processing method.

[0057] Another object of the present invention is to provide a computer-readable storage medium storing a computer program, wherein when the computer program is executed by a processor, the processor executes the method for locating the root cause of faults in the airport information system and automatically handling faults.

[0058] In combination with all the above-mentioned technical solutions, the beneficial effects of the present invention are as follows: the present invention collects indicator data of the airport information system, uses a large model and the FP-Growth algorithm to locate the root cause of the business system fault alarm, and according to the built-in automation script, the system automatically processes the script through commands to quickly recover from system failures, thereby improving the stability and security of the airport system and enhancing passenger flight satisfaction.

[0059] When the airport information system goes down due to a system failure, it will extend the travel time of passengers, increase the operating costs of the airport, reduce passenger flight satisfaction, and cause passenger complaints. The present invention can effectively locate the root cause and quickly restore the airport information system failure, reduce the risk of human error, reduce system downtime, improve the security and availability of the airport information system, ensure the continuous stability of the airport information system, and improve operational efficiency and service quality.

[0060] The present invention introduces airport alarm information and monitoring information data as key indicators and uses the Tongyi Qianwen large model to more accurately determine the root cause of the fault. At the same time, through automated scripts, system faults can be automatically and quickly restored, providing a strong guarantee for the stable operation of the airport information system. When an airport system fails, the traditional method of checking logs step by step is used, and the fault recovery speed is slow, which prolongs the travel time of passengers and easily causes complaints from passengers. By introducing key monitoring indicators and large models, the present invention can quickly locate the root cause of the fault and automatically repair the fault, which can improve the efficiency and accuracy of system recovery, reduce the risk of human error, and ensure the stability and security of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] The accompanying drawings herein are incorporated in and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the description, serve to explain the principles of the present disclosure;

[0062] Figure 1 This is a flow chart of a method for locating the root cause of a fault in an airport information system and automatically handling the fault provided by an embodiment of the present invention;

[0063] Figure 2 It is a schematic diagram of a system for locating the root cause of a fault in an airport information system and automatically handling the fault provided by an embodiment of the present invention;

[0064] Figure 3 It is a hierarchical structure principle diagram of a method for locating the root cause of a fault in an airport information system and automatically handling the fault provided by an embodiment of the present invention;

[0065] In the figure: 1. Resource data module; 2. Related information construction module; 3. Problem root cause construction module; 4. Matching automation script module; 5. Fault automatic processing construction module; 6. Root cause analysis and fault automatic processing improvement module. DETAILED DESCRIPTION

[0066] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below in conjunction with the accompanying drawings. In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention can be implemented in many other ways different from those described herein, and those skilled in the art can make similar improvements without violating the connotation of the present invention, so the present invention is not limited by the specific implementation disclosed below.

[0067] The innovative point of the airport information system fault root cause location and automatic fault handling method and system provided by the embodiment of the present invention is: collecting monitoring alarms and monitoring indicators of the airport information system, using a large model to accurately locate the root cause of the fault, and combining with automated scripts to quickly recover from the fault and improve the stability and security of the system.

[0068] Embodiment 1, as Figure 1 As shown, the airport information system fault root cause location and fault automatic processing method provided by the embodiment of the present invention includes:

[0069] S1, collects the alarm information of the airport information system, which includes information system IP information, information system alarm information, system server CPU information, I / O information, disk information, application software information, and middleware information;

[0070] S2, calculate the correlation weights of alarms and influencing factors of information system failures through the FP-Growth algorithm. The influencing factors of airport information system failures include network factors, server equipment factors, middleware factors, application factors, and database factors;

[0071] S3, based on prompt word training and fine-tuning technology, enhances the log analysis capability of the Tongyi Qianwen large model. Through prompt engineering combined with fault influencing factors and their weights, the Tongyi Qianwen large model is requested to perform log analysis and generate a root cause report.

[0072] S4, according to the root cause report, matches the built-in automation script, triggers and executes the script through the script command, and restores the fault;

[0073] S5, according to the current fault alarm situation of the airport, adjust the corresponding parameters to improve the accuracy of locating the root cause, realize fault recovery, and improve the safety of airport operations.

[0074] In the embodiment of the present invention, in step S1, the airport information system alarm information is collected;

[0075] In the embodiment of the present invention, in step S2, the association weights of the alarm and the influencing factors of the information system failure are calculated by the FP-Growth algorithm, including:

[0076] S201, alarm information time sequence preprocessing, forming alarm events at each moment, the expression is:

[0077] ;

[0078] In the formula, for Always warn of events, for Always warn of events, The server IP address when the alarm event occurs. for The CPU usage of the server at the moment, for The disk IO in and out traffic of the server at all times. for Server memory usage at the moment, for The available space size of the server's C drive at the moment;

[0079] S202, the transactions in the alarm information within a period of time are formed into a transaction data set, which is expressed as:

[0080] ;

[0081] in, This is the first alarm event in a period of time. This is the second alarm event within a period of time. This is the third alarm event within a period of time. For a period of time An alarm event;

[0082] S203, the items in each transaction that have alarm information are classified as a separate item, all of which are alarm-related items, and each such transaction corresponds to a As labels, they are called alarm correlation factors on each server;

[0083] The expression of the alarm correlation factor on each server is:

[0084] ;

[0085] In the formula, For each server, the alarm correlation factor is: is the number of failures that occurred on the server, is the total number of failures.

[0086] S204, based on the FP-Growth correlation algorithm, correlation analysis is performed between the influencing factors of the information system failure and the alarm;

[0087] The expression of the alarm correlation analysis model is:

[0088] ;

[0089] In the formula, is the correlation degree between the alarm event X and the fault influencing factor M, is the total number of alarm events in the time period, is the correlation between the fault influencing factor M and the alarm event X, For warning events, As an influencing factor.

[0090] S205, obtaining the correlation degree between the influencing factors of the system failure and the alarm information according to the alarm correlation analysis model, and calculating the correlation weight between the influencing factors of the information system failure and the alarm information according to the correlation degree;

[0091] The expression of the correlation weight between the influencing factors of information system failure and the alarm information is:

[0092] ;

[0093] In the formula, is the association weight between the fault influencing factor M and the alarm event X, is the number of times the alarm event X occurs;

[0094] (1) When ,The factors affecting system failure and the alarm information are strongly correlated;

[0095] (2) When ,The influencing factors of system failure and the alarm information are independent of each other;

[0096] (3) When ,The ,factors affecting system failures and the alarm information are weakly correlated.

[0097] S206, repeating steps S203 to S205 until the frequent fault influencing factors can no longer generate alarms.

[0098] In the embodiment of the present invention, in step S3, according to the associated fault influencing factors, combined with the large model algorithm, the error information of the informatization system fault influencing factors is identified, and the implementation steps are as follows:

[0099] S301, obtaining log information of all failure influencing factors of the monitoring system through a system monitoring tool;

[0100] S302, pre-setting prompt word categories such as network, server hardware, application system, middleware, database, etc. in the Tongyi Qianwen large model;

[0101] S303, through manual analysis and matching of preset prompt word categories and historical question logs, the Tongyi Qianwen big model trains the matched prompt word categories and historical question logs to enhance the log understanding and analysis capabilities, and finally the key information can be quickly extracted through keywords;

[0102] S304, the large model selects the preset prompt words according to the weights of the associated fault influencing factors;

[0103] S305, the large model returns the error log of the most likely influencing factor according to the filtered prompt words;

[0104] S306, generating a root cause report based on the error log, including the server IP, middleware, error code, error log, etc.

[0105] In the embodiment of the present invention, in step S4, according to the problem root cause report, the built-in automation script is matched to realize automatic fault processing, and the implementation steps are as follows:

[0106] S401, based on common error problems, establish a built-in automation script. The specific method is as follows:

[0107] (1) Collect common middleware error issues, including rabbitMQ, Ngix, Tomcat, JBoss, SpringBoot, Redis, etc.

[0108] (2) Automatically obtain the monitoring server deployment software instance and startup path by directly reading the Windows registry.

[0109] (3) Set up the Python automated restart script for Linux and Windows in the middleware;

[0110] S402, matching the information in the problem root cause report with the automation script according to the software instance name and the common error problem code;

[0111] S403, once a suitable automation script is matched, the system automatically triggers and executes the script through a script command;

[0112] S404, the system automatically obtains the script execution results on the server and notifies the user of the results to ensure that the fault has been successfully resolved and the stable operation of the airport system is guaranteed.

[0113] In the embodiment of the present invention, step S6 adjusts corresponding parameters according to the existing fault alarm situation of the airport to improve the accuracy of locating the root cause, quickly realize fault recovery, and improve the safety of airport operation.

[0114] Embodiment 2, as Figure 2 As shown, the embodiment of the present invention includes a system for locating the root cause of a fault in an airport information system and automatically handling the fault, including:

[0115] Resource data module 1, collects alarm information of the airport information system, which includes information system IP information, information system alarm information, system server CPU information, I / O information, disk information, application software information, and middleware information;

[0116] The correlation information building module 2 is used to calculate the correlation weights of the alarm and the influencing factors of the information system failure through the FP-Growth algorithm. The influencing factors of the airport information system failure include network factors, server equipment factors, middleware factors, application factors, and database factors;

[0117] Problem root cause construction module 3, based on prompt word training and fine-tuning technology, enhances the log analysis capability of the Tongyi Qianwen large model. Through prompt engineering combined with fault influencing factors and their weights, the Tongyi Qianwen large model is requested to perform log analysis and generate a problem root cause report;

[0118] Matching automation script module 4, matching built-in automation scripts according to the problem root cause report;

[0119] The automatic fault handling module 5 is used to trigger and execute the script through the script command to recover the fault;

[0120] The root cause analysis and automatic fault handling improvement module 6 adjusts the corresponding parameters according to the current fault alarm situation of the airport, improves the accuracy of locating the root cause, realizes fault recovery, and improves the safety of airport operations.

[0121] Embodiment 3, as Figure 3 As shown, as another embodiment of the present invention, the embodiment of the present invention includes a method for locating the root cause of a fault in an airport information system and automatically handling the fault, including:

[0122] Alarm information input is used to collect all alarm information of the information system within a period of time;

[0123] Root cause location: Use the correlation algorithm to calculate the correlation and weight between alarm items and influencing factors of the information system, and combine with the big model to quickly identify the root cause of the problem;

[0124] Automatic fault handling: built-in automation scripts are used to automatically execute scripts, solve faults, and realize automatic fault handling;

[0125] Automatic fault handling is improved, further improving the weight calculation method of the association algorithm and improving the recognition accuracy of the training model, so as to more accurately and efficiently identify the root cause of the problem, solve the fault, and realize automatic processing.

[0126] Experimental example: Root cause location and automatic fault handling for an airport’s information system failure.

[0127] like Figure 3 As shown, an embodiment of the present invention includes a method for locating the root cause of an airport information system fault and automatically handling the fault, including: step S1, the alarm information can be obtained by connecting to the airport operation and maintenance monitoring platform, and the key resource indicators of the business system can be obtained through the system monitoring tool.

[0128] Step S2, the FP-Growth algorithm calculates the weights of the associated influencing factors, and the implementation steps are as follows:

[0129] S201, alarm information time sequence preprocessing, forming alarm affairs at each moment ;

[0130] S202, forming a transaction data set from the transactions in the alarm information within a period of time ;

[0131] S203, the items in each transaction that represent "alarm information" are uniformly classified as a separate item, all of which are "alarm related matters", and each such transaction corresponds to a As a label, it is called "alarm related matters", and its formula is as follows:

[0132] ;

[0133] In the formula, For each server, the alarm correlation factor is: is the number of failures that occurred on the server, is the total number of failures.

[0134] S204. Based on the FP-Growth correlation algorithm, correlation analysis is performed on informatization system influencing factors and alarms. System influencing factors include network, server hardware, application system, middleware, etc., and an alarm correlation analysis model is established;

[0135] ;

[0136] In the formula, is the correlation degree between the alarm event X and the fault influencing factor M, is the total number of alarm events in the time period, is the correlation between the fault influencing factor M and the alarm event X, For warning events, As an influencing factor.

[0137] S205, calculating the correlation weights of the correlation influencing factors and the alarm information according to the alarm correlation analysis model; ; In the formula, is the association weight between the fault influencing factor M and the alarm event X, is the number of occurrences of alarm event X;

[0138] (1) When ,The factors affecting system failure and the alarm information are strongly correlated;

[0139] (2) When ,The influencing factors of system failure and the alarm information are independent of each other;

[0140] (3) When ,The ,factors affecting system failures and the alarm information are weakly correlated.

[0141] S206, repeating steps S203 to S205 until no more alarm frequent fault influencing factors are generated, as shown in Table 1;

[0142] Table 1 Factors and weights associated with failures of an airport's information system:

[0143]

[0144] Step S3, based on the associated influencing factors and weights, combined with the Tongyi Qianwen model, locate the specific influencing factor log error information of the Jiaodong Airport baggage tracking system and generate a root cause report. The implementation steps are as follows:

[0145] (1) Obtain log information of all failure-influencing factors of the baggage tracking system through system monitoring tools, including network, server operating system, application system operation log, RabbitMQ operation log, Ngix operation log, Redis operation log, and database Oracle11g operation log;

[0146] (2) Pre-set prompt word categories such as network, server hardware, application system, middleware, and database in the Tongyi Qianwen model;

[0147] (3) Through manual analysis and matching of preset prompt word categories and historical question logs, the Tongyi Qianwen large model trains the matched prompt word categories and historical question logs to enhance the ability to understand and analyze logs, and finally quickly extract key information through keywords;

[0148] (4) The Tongyi Qianwen model selects pre-set prompt word categories based on the associated fault influencing factors with a weight greater than 1, such as application system, RabbitMQ, Redis, and database Oracle11g;

[0149] (5) Tongyi Qianwen big model returns the RabbitMQ error log, the most likely influencing factor, based on the filtered prompt words;

[0150] (6) Generate a root cause report based on the RabbitMQ error log, including the server IP 10.32.5.12, middleware RabbitMQ, error code internal_error, error log, etc.;

[0151] Step S4, according to the root cause report, through RabbitMQ, the error code matches the built-in automation script, and automatically publishes the script for restarting RabbitMQ to the 10.32.5.12 server through commands, restarts RabbitMQ, and recovers the RabbitMQ fault. The baggage tracking system can load the vehicle normally and the RabbitMQ messages can be consumed normally.

[0152] By adopting the airport information system fault root cause location and fault automatic processing method of the present invention, the root cause of the airport information system fault can be quickly located, the fault can be quickly restored, and the stability and security of the airport information system can be improved.

[0153] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any modifications, equivalent substitutions and improvements made by any technician familiar with the technical field within the technical scope disclosed by the present invention and within the spirit and principles of the present invention should be covered within the protection scope of the present invention.

Claims

1. A method for locating the root cause of an airport information system fault and automatically handling the fault, characterized in that: The method includes: S1, collect the alarm information of the airport information system, which includes information system IP information, information system alarm information, system server CPU information, I / O information, disk information, application software information, and middleware information; S2, calculate the correlation weights of alarms and influencing factors of information system failures through the FP-Growth algorithm. The influencing factors of airport information system failures include network factors, server equipment factors, middleware factors, application factors, and database factors; S3, based on prompt word training and fine-tuning technology, enhance the log analysis capability of the Tongyi Qianwen big model, through the prompt engineering combined with the influencing factors of information system failures and the associated weights of the alarms and influencing factors of information system failures, request the Tongyi Qianwen big model to perform log analysis and generate a root cause report; S4, according to the root cause report, matches the built-in automation script, triggers and executes the script through the script command, and restores the fault; S5, according to the current fault alarm situation of the airport, adjust the corresponding parameters to improve the accuracy of locating the root cause, realize fault recovery, and improve the safety of airport operation; In step S3, a root cause report is generated, including: S301, obtaining log information of all informatization system failure influencing factors of the monitoring system through a system monitoring tool; S302, pre-setting prompt word categories of network, server hardware, application system, middleware, and database in the Tongyi Qianwen large model; S303, manually analyzing and matching preset prompt word categories and historical question logs, the Tongyi Qianwen big model trains the matched prompt word categories and historical question logs, enhances the log understanding and analysis capabilities, and quickly extracts key information through keywords; S304, the Tongyi Qianwen big model selects the preset prompt word categories according to the correlation weights of the alarm and the influencing factors of the information system failure; S305, the Tongyi Qianwen model returns the question log of the most likely influencing factor according to the category of the prompt words after screening; S306, based on the error log, the system automatically generates a root cause report including the server IP, middleware, error code, and error log.

2. The method for locating the root cause of a fault in an airport information system and automatically handling the fault according to claim 1 is characterized in that: In step S2, the association weights of alarms and influencing factors of information system failures are calculated by the FP-Growth algorithm, including: S201, alarm information time sequence preprocessing, forming alarm events at each moment, the expression is: I t ={G t ,IP,CPU t ,IO t ,M t ,D t } In the formula, I t is the alarm event at time t, G t is the alarm event at time t, IP is the server IP address when the alarm event occurs, CPU t is the CPU usage of the server at time t, IO t is the disk IO inbound and outbound traffic of the server at time t, M t is the server memory occupancy at time t, D t is the available space size of the server's C drive at time t; S202, the transactions in the alarm information within a period of time are formed into a transaction data set, which is expressed as: Ⅰ={I1,I2,I3…I k } Among them, I1 is the first alarm event within a period of time, I2 is the second alarm event within a period of time, and I3 is the third alarm event within a period of time. k is the kth alarm event within a period of time; S203, the servers that have alarm information in each transaction are uniformly classified into a separate project, each of which is an alarm-related item on each server, and each such alarm-related item corresponds to a lambda i As labels, they are called alarm correlation factors on each server; S204, based on the FP-Growth correlation algorithm, correlation analysis is performed between the influencing factors of the information system failure and the alarm; S205, obtaining the correlation degree between the influencing factors of the system failure and the alarm information according to the alarm correlation analysis model, and calculating the correlation weight between the influencing factors of the information system failure and the alarm information according to the correlation degree; S206, repeating steps S203 to S205 until no more frequent fault influencing factors are generated; In step S203, the expression of the alarm correlation factor on each server is: In the formula, λ i For each server, D i On each server In the alarm related items Failure Total number of alarms , D is the total number of alarm faults; In step S204, the expression of the alarm association analysis model is: In the formula, S X＝M is the correlation degree between alarm event X and fault influencing factor M, N is the total number of alarm events in the time period, (X∪M) is the correlation relationship between fault influencing factor M and alarm event X, X is the alarm event, and M is the influencing factor.

3. The method for locating the root cause of a fault in an airport information system and automatically handling the fault according to claim 2 is characterized in that: In step S205, the expression of the correlation weight between the influencing factors of the information system failure and the alarm information is: In the formula, K X＝M is the association weight between fault influencing factor M and alarm event X, N(X) is the number of occurrences of alarm event X; (1) When K X＝M >1, the influencing factors of system failure and alarm information are strongly correlated; (2) When K X＝M =1, the system failure influencing factors and alarm information are independent of each other; (3) When K X＝M <1, the system failure influencing factors and alarm information are weakly correlated.

4. The method for locating the root cause of a fault in an airport information system and automatically handling the fault according to claim 1 is characterized in that: In step S4, the script is triggered and executed through a script command to recover from the fault, including: S401, collect common problems and establish a built-in automation script; Collect common software problems including common errors of rabbitMQ, Ngix, Tomcat, JBoss, SpringBoot, and Redis; automatically obtain monitoring server deployment software instances and startup paths by directly reading the Windows registry; set up Python automated restart scripts for Linux and Windows middleware through the system; S402, matching the information in the problem root cause report with the automation script according to the software instance name and the common error problem code; S403, once a suitable automation script is matched, the system automatically triggers and executes the script through a command; S404, the system automatically obtains the script execution result on the server and notifies the user of the result.

5. A system for locating the root cause of faults in airport information systems and automatically handling faults, characterized in that: The system implements the method for locating the root cause of a fault in an airport information system and automatically handling the fault as claimed in any one of claims 1 to 4, and the system comprises: Resource data module (1), collects alarm information of the airport information system, the alarm information includes information system IP information, information system alarm information, system server CPU information, I / O information, disk information, application software information, and middleware information; The correlation information building module (2) is used to calculate the correlation weight between the alarm and the influencing factors of the information system failure through the FP-Growth algorithm. The influencing factors of the airport information system failure include network factors, server equipment factors, middleware factors, application factors, and database factors; The problem root cause construction module (3) is based on prompt word training and fine-tuning technology to enhance the log analysis capability of the Tongyi Qianwen big model. Through the prompt engineering, the influencing factors of the information system failure and the associated weights of the alarm and the influencing factors of the information system failure are combined, and the Tongyi Qianwen big model is requested to perform log analysis and generate a problem root cause report. Matching automation script module (4), matching built-in automation script according to the problem root cause report; The fault automatic processing building module (5) triggers and executes the script through the script command to recover the fault; The root cause analysis and automatic fault handling improvement module (6) adjusts corresponding parameters according to the current fault alarm situation of the airport, improves the accuracy of locating the root cause, realizes fault recovery, and improves the safety of airport operation.

6. A program storage medium for receiving user input, characterized in that: The stored computer program enables the electronic device to execute the method for locating the root cause of a fault and automatically handling a fault in an airport information system as described in any one of claims 1 to 4.

7. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the processor executes the method for locating the root cause of a fault and automatically handling a fault in an airport information system as described in any one of claims 1 to 4.

Images