CN110955575A - Business system fault positioning method based on correlation analysis model - Google Patents
Business system fault positioning method based on correlation analysis model Download PDFInfo
- Publication number
- CN110955575A CN110955575A CN201911115624.7A CN201911115624A CN110955575A CN 110955575 A CN110955575 A CN 110955575A CN 201911115624 A CN201911115624 A CN 201911115624A CN 110955575 A CN110955575 A CN 110955575A
- Authority
- CN
- China
- Prior art keywords
- data
- correlation analysis
- event
- index
- analysis model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/3003—Monitoring arrangements specially adapted to the computing system or computing system component being monitored
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/32—Monitoring with visual or acoustical indication of the functioning of the machine
- G06F11/324—Display of status information
- G06F11/327—Alarm or error message display
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/34—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment
- G06F11/3452—Performance evaluation by statistical analysis
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Quality & Reliability (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Probability & Statistics with Applications (AREA)
- Computer Hardware Design (AREA)
- Debugging And Monitoring (AREA)
- Test And Diagnosis Of Digital Computers (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention relates to a business system fault positioning method based on an association analysis model, which comprises the following steps of (1) collecting monitoring index data of a business system in real time; (2) carrying out data preprocessing and storage on the collected monitoring index data; (3) carrying out anomaly detection on the processed monitoring index data, transmitting anomaly index information into a correlation analysis model, and finding out a suspected fault root event; (4) and the abnormal index information and the suspected fault root cause event positioned by the correlation analysis model are used as alarm information together, and the alarm information is pushed to corresponding operation and maintenance personnel to assist the operation and maintenance personnel in quickly repairing the system abnormality. The method can provide more valuable information for the fault root cause event of the positioning system, and compared with the traditional fault positioning method, the correlation analysis model has higher speed and higher accuracy.
Description
Technical Field
The invention relates to a positioning method, in particular to a business system fault positioning method based on an association analysis model.
Background
With the rapid development of network technologies, emerging network technologies such as cloud computing and big data are rapidly popularized, and in order to obtain more valuable information, the data volume processed by various service systems is increased rapidly, and the application benefit is greatly improved. However, as the amount of system data increases dramatically, and the data structure and business logic become complicated, the frequency of business system failures also increases gradually, and it becomes more difficult to locate the root cause of system failures. Most of fault location of a service system is that operation and maintenance personnel gradually explore and analyze system logs according to index abnormal alarm information, and although a problem root is usually found out, the process is time-consuming and the operation and maintenance personnel are required to have rich experience. A more automatic method is to assist operation and maintenance personnel to acquire and decide information through some rules or algorithms, but the speed and the precision are all to be improved.
In addition, for fault location, a root cause event of a fault needs to be searched, a fault diagnosis tree model is generally adopted for fault location in the traditional fault root cause event searching, the fault diagnosis tree is composed of a domain expert knowledge base and an inference machine (logic pushing to an engine), operation and maintenance experience knowledge of operation and maintenance personnel is stored in the domain expert knowledge base in a tree structure, the tree structure is formed by analysis directions of different levels of indexes and a downward detection method, and the inference machine adopts a binary decision tree algorithm in machine learning to perform step-by-step exploration from a certain node of the tree and finally lock the fault root cause. And finally, the operation and maintenance knowledge (fault tracking chain) of the root cause event is successfully found out and then added into the domain expert knowledge base, so that the experience knowledge of the knowledge base is continuously enriched. The fault diagnosis tree model can generally find out suspected fault root events, but is time-consuming, and if the fault events are new, the accuracy rate is to be improved.
Disclosure of Invention
The invention aims to provide a business system fault positioning method based on an association analysis model, which is higher in speed and accuracy.
In order to achieve the purpose, the invention adopts the following technical scheme:
a business system fault positioning method based on an association analysis model comprises the following steps:
(1) collecting monitoring index data of a service system in real time; the monitoring index data comprises basic resource monitoring data, application performance monitoring data and network safety monitoring data; the monitoring index data of the real-time acquisition business system is acquired by adopting an acquisition Agent client side;
(2) carrying out data preprocessing and storage on the collected monitoring index data;
(3) carrying out anomaly detection on the processed monitoring index data, transmitting anomaly index information into a correlation analysis model, and finding out a suspected fault root event;
(4) and the abnormal index information and the suspected fault root cause event positioned by the correlation analysis model are used as alarm information together, and the alarm information is pushed to corresponding operation and maintenance personnel to assist the operation and maintenance personnel in quickly repairing the system abnormality.
In the method, the basic resource monitoring data comprises a CPU utilization rate, a memory ratio and a disk I/O rate; the application performance monitoring data comprises response time, error rate, server side resetting rate and certain function availability of a system page; the network safety monitoring data comprises network delay, throughput and network bandwidth.
The data processing specifically comprises the following steps:
abnormal value processing, which is used for detecting the abnormal value of the acquired data, eliminating the abnormal value and replacing the abnormal value by the data mean value of two adjacent moments before and after the abnormal point; missing value processing is used for carrying out interpolation and filling in on the missing value so as to enable the acquired data to be complete; the unified formatting is used for carrying out unified formatting processing on the monitoring index data of different types and different dimensions; and data desensitization is used for carrying out network transmission and storage after the acquired data are encrypted.
The abnormality detection method comprises a fixed threshold value method, a dynamic threshold value method and an index data prediction method. The fixed threshold method: setting an abnormal data threshold, and if the index value is greater than the threshold, determining that abnormality occurs;
the dynamic threshold method comprises the following steps: the set threshold value is adjusted along with the floating rule of the index data value;
the index data prediction method comprises the following steps: and fitting a function according with the rule according to the index historical data rule, predicting the index value at the next moment according to the function, and if the index value exceeds a preset range, determining that the abnormality occurs.
Further, the correlation analysis model comprises a correlation analysis submodule and a fault diagnosis tree submodule;
the correlation analysis module is used for finding out a direct mapping relation between the KPI and the event, so that when the index data is abnormal, a root cause event directly mapped with the abnormal index can be searched in the KPI-event correlation library.
The correlation analysis submodule comprises event correlation analysis and KPI correlation analysis; the correlation analysis refers to fully mining the relation among all the occurred root cause events, and mining the historical root cause events by frequent item sets; the KIP association analysis refers to fully mining association relations among all KPI indexes, including KPI libraries and KPI association sets of all KPI indexes, wherein the KPI association sets include association relations among all KPI indexes.
When the index is abnormal, firstly inquiring whether a mapping event corresponding to the index exists in a KPI-event association library, and if so, directly positioning a suspected root cause event; if not, the suspected root cause event is positioned by the fault diagnosis tree submodule, if the locked suspected root cause event is indeed the fault root cause, the tracking list for locking the root cause event is added into the expert knowledge base, and the root cause event is added into the KPI-event correlation base.
According to the technical scheme, the business system fault positioning method based on the correlation analysis model fully excavates the correlation between the KPI and the index, between the event and between the index and the event, provides more valuable information for positioning the system fault root cause event, and has higher speed and higher accuracy of the correlation analysis model compared with the traditional fault positioning method.
Drawings
FIG. 1 is a flow chart of a method of the present invention;
FIG. 2 is a diagram of a correlation analysis model composition module of the present invention.
Detailed Description
The invention is further described below with reference to the accompanying drawings:
in this embodiment, the method for locating a fault in a service system based on an association analysis model includes the following steps:
the method comprises the following steps: collecting monitoring index data of a service system in real time;
the monitoring index data comprises basic resource monitoring data, application performance monitoring data, network safety monitoring data and the like.
The basic resource monitoring data comprises CPU utilization rate, memory ratio, disk I/O rate and the like; the application performance monitoring data comprises response time, error rate, server side resetting rate, certain function availability and the like of a system page; the network safety monitoring data comprises network delay, throughput, network bandwidth and the like. In order to not occupy the resources of the system, the acquisition method generally adopts an acquisition Agent client to acquire real-time data.
Step two: carrying out data preprocessing and storage on the collected monitoring index data;
the data formats of the collected monitoring index data are often not uniform, and the collected data are often discontinuous due to system faults and other reasons, so that the collected data need to be subjected to data preprocessing operations such as data cleaning, uniform formatting, value complementing and desensitization and then stored.
In this embodiment, the data preprocessing is performed on the monitoring index data, and specifically includes the following aspects:
abnormal value processing: detecting an abnormal value of the acquired data, removing the abnormal value, and replacing the abnormal value by using a data mean value of two adjacent moments before and after an abnormal point;
missing value processing: the method is characterized in that the loss condition of the acquired data is often caused by system faults, such as system maintenance, power failure and the like, and interpolation is generally carried out on the loss value to complete the acquired data so as to carry out corresponding analysis and calculation according to the acquired data at a later stage;
unified formatting: the collected monitoring index data are often heterogeneous in multiple sources due to different sources, and the monitoring index data of different types and different dimensions need to be subjected to unified formatting treatment so as to be stored and calculated.
Data desensitization: in order to ensure data safety, after the acquisition client acquires the original data of the monitoring index, data desensitization operation is required. The acquired data is encrypted through an encryption algorithm and then transmitted and stored in a network.
Step three: carrying out anomaly detection on the processed monitoring index data, transmitting anomaly index information into a correlation analysis model, and finding out a suspected fault root event;
there are many methods for detecting whether the index data is abnormal, and the following method may be adopted in this embodiment:
if the index value is larger than the threshold value by a fixed threshold value method, determining that the abnormality occurs;
the dynamic threshold method, the setting of the threshold is adjusted along with the floating rule of the index data value;
the index data prediction method is that a function conforming to the rule is fitted according to the rule of the index historical data, the index value at the next moment is predicted according to the function, and if the index value exceeds a preset range, the abnormality is considered to occur.
As shown in fig. 2, the association analysis model provided by the present invention includes an association analysis submodule and a fault diagnosis tree submodule, so as to fully mine and utilize the association relationship between abnormal events and events, between KPIs (monitoring indicators) and KPIs, and between events and KPIs, so as to quickly locate fault root cause events; the correlation analysis model comprises a correlation analysis submodule and a fault diagnosis tree submodule.
The main purpose of the correlation analysis submodule is to find out the direct mapping relation between KPI and event, so that when the index data is abnormal, the root cause event directly mapped with the abnormal index can be searched in the KPI-event correlation base, and the fault positioning efficiency is greatly improved. The KPI-event correlation library stores direct mapping relation between KPI and event, if the abnormity of some KPI index a is caused by event A, the mapping relation between the index a and event A is stored, such as storing in key value pair, one-key multiple value, multiple-key multiple value form. The filling of the KPI-event correlation library content, namely the mapping relation, is derived from the correlation analysis submodule and the fault diagnosis tree submodule.
Specifically, the correlation analysis submodule includes event correlation analysis and KPI correlation analysis;
event correlation analysis: the method is characterized in that the incidence relation among all the occurred root cause events is fully mined, and the method consists of a uniform event library comprising all historical root cause events and a mining method of 'frequent item set mining'. By frequently mining historical root cause events, the mined frequent root cause events often contain suspected root cause events which cause the index abnormality. The frequent item set mining algorithm can adopt an FP-growth algorithm with parallel execution capacity and is suitable for large databases.
KIP association analysis: the method fully excavates the association relationship among all KPI indexes, and consists of a KPI library and a KPI association set, wherein the KPI library comprises all KPI indexes. The KPI set comprises all the association relations among KPI indexes, if the abnormality of index a causes the abnormality of index b, and the abnormality of index b causes the abnormality of index c, the association relations of a pointing to b, a pointing to c, and b pointing to c are all stored in the KPI association set. The KPI association set and the event frequent item set change along with the dynamic changes of the uniform event library and the KPI library, and the newly added association relation is transmitted into the association configuration library. The association configuration library further converts the KPI association relationship and the event association relationship into a KPI-event association relationship, and if the original mapping from the index a to the event A exists, and a new association relationship from the newly added index a to the index B and the event A to the event B is received, two mapping relationships from the index a to the event B and from the index B to the event A can be newly added. The association configuration library dynamically updates the newly added mapping relationship to the KPI-event library.
The fault diagnosis tree submodule: when the index is abnormal, firstly inquiring whether a mapping event corresponding to the index exists in a KPI-event association library, and if so, directly positioning a suspected root cause event; if not, the suspected root cause event is positioned by the fault diagnosis tree submodule, if the locked suspected root cause event is indeed the fault source, the tracking list for locking the root cause event is added into the expert knowledge base, and the root cause event is added into the KPI-event association base, so that the content in the base is continuously enriched.
The KPI event correlation library is provided with the correlation relation of KPI events by a correlation analysis submodule and a fault diagnosis tree submodule together, the more the mapping relation in the correlation library is, the higher the probability that the suspected root event is locked directly when the index is abnormal is, and the higher the efficiency is. Compared with the traditional fault root cause positioning only depending on a fault diagnosis tree module, the fault root cause event positioning efficiency positioned by the correlation analysis model is higher, and the accuracy is higher.
Step four: and the abnormal index information and the suspected fault root cause event positioned by the correlation analysis model are used as alarm information together, and the alarm information is pushed to corresponding operation and maintenance personnel to assist the operation and maintenance personnel in quickly repairing the system abnormality.
The above-mentioned embodiments are merely illustrative of the preferred embodiments of the present invention, and do not limit the scope of the present invention, and various modifications and improvements of the technical solution of the present invention by those skilled in the art should fall within the protection scope defined by the claims of the present invention without departing from the spirit of the present invention.
Claims (10)
1. A business system fault positioning method based on an association analysis model is characterized by comprising the following steps:
(1) collecting monitoring index data of a service system in real time;
(2) carrying out data preprocessing and storage on the collected monitoring index data;
(3) carrying out anomaly detection on the processed monitoring index data, transmitting anomaly index information into a correlation analysis model, and finding out a suspected fault root event;
(4) and the abnormal index information and the suspected fault root cause event positioned by the correlation analysis model are used as alarm information together, and the alarm information is pushed to corresponding operation and maintenance personnel to assist the operation and maintenance personnel in quickly repairing the system abnormality.
2. The business system fault location method based on the correlation analysis model as claimed in claim 1, wherein in step (1), the monitoring index data includes basic resource monitoring data, application performance monitoring data and network security monitoring data.
3. The business system fault location method based on the correlation analysis model as claimed in claim 2, wherein: the basic resource monitoring data comprises CPU utilization rate, memory ratio and disk I/O rate; the application performance monitoring data comprises response time, error rate, server side resetting rate and certain function availability of a system page; the network safety monitoring data comprises network delay, throughput and network bandwidth.
4. The business system fault location method based on the correlation analysis model as claimed in claim 1, wherein: in the step (1), the monitoring index data of the service system is collected in real time, and the collection method adopts a collection Agent client to collect the real-time data.
5. The business system fault location method based on the correlation analysis model as claimed in claim 1, wherein: in the step (2), the data processing specifically includes:
abnormal value processing: detecting an abnormal value of the acquired data, removing the abnormal value, and replacing the abnormal value by using a data mean value of two adjacent moments before and after an abnormal point;
missing value processing: interpolation filling is carried out on the missing value, so that the acquired data is complete;
unified formatting: carrying out unified formatting treatment on monitoring index data of different types and different dimensions;
data desensitization: and encrypting the acquired data, and then performing network transmission and storage.
6. The business system fault location method based on the correlation analysis model as claimed in claim 1, wherein: in the step (3), the method for detecting the abnormality of the processed monitoring index data includes a fixed threshold method, a dynamic threshold method and an index data prediction method.
7. The business system fault location method based on the correlation analysis model as claimed in claim 6, wherein:
the fixed threshold method: setting an abnormal data threshold, and if the index value is greater than the threshold, determining that abnormality occurs;
the dynamic threshold method comprises the following steps: the set threshold value is adjusted along with the floating rule of the index data value;
the index data prediction method comprises the following steps: and fitting a function according with the rule according to the index historical data rule, predicting the index value at the next moment according to the function, and if the index value exceeds a preset range, determining that the abnormality occurs.
8. The business system fault location method based on the correlation analysis model as claimed in claim 1, wherein: in the step (3), the correlation analysis model comprises a correlation analysis submodule and a fault diagnosis tree submodule;
the correlation analysis module is used for finding out a direct mapping relation between the KPI and the event, so that when the index data is abnormal, a root cause event directly mapped with the abnormal index can be searched in the KPI-event correlation library.
9. The business system fault location method based on the correlation analysis model as claimed in claim 8, wherein: the correlation analysis submodule comprises event correlation analysis and KPI correlation analysis;
the event correlation analysis refers to fully mining the relation among all the occurred root cause events, and mining the historical root cause events by frequent item sets;
the KIP association analysis refers to fully mining association relations among all KPI indexes, including KPI libraries and KPI association sets of all KPI indexes, wherein the KPI association sets include association relations among all KPI indexes.
10. The business system fault location method based on the correlation analysis model as claimed in claim 9, further comprising the steps of:
when the index is abnormal, firstly inquiring whether a mapping event corresponding to the index exists in a KPI-event association library, and if so, directly positioning a suspected root cause event; if not, the suspected root cause event is positioned by the fault diagnosis tree submodule, if the locked suspected root cause event is indeed the fault root cause, the tracking list for locking the root cause event is added into the expert knowledge base, and the root cause event is added into the KPI-event correlation base.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911115624.7A CN110955575A (en) | 2019-11-14 | 2019-11-14 | Business system fault positioning method based on correlation analysis model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911115624.7A CN110955575A (en) | 2019-11-14 | 2019-11-14 | Business system fault positioning method based on correlation analysis model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110955575A true CN110955575A (en) | 2020-04-03 |
Family
ID=69977370
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911115624.7A Pending CN110955575A (en) | 2019-11-14 | 2019-11-14 | Business system fault positioning method based on correlation analysis model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110955575A (en) |
Cited By (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111506637A (en) * | 2020-06-17 | 2020-08-07 | 北京必示科技有限公司 | Multi-dimensional anomaly detection method and device based on KPI (Key Performance indicator) and storage medium |
| CN111639115A (en) * | 2020-04-29 | 2020-09-08 | 国家电网有限公司客户服务中心 | Five-dimensional model-based analysis method for operation and maintenance data abnormity of power grid information system |
| CN111722952A (en) * | 2020-05-25 | 2020-09-29 | 中国建设银行股份有限公司 | Fault analysis method, system, equipment and storage medium of business system |
| CN112463834A (en) * | 2020-12-02 | 2021-03-09 | 中国建设银行股份有限公司 | Method and device for automatically realizing root cause analysis in streaming processing and electronic equipment |
| CN112532455A (en) * | 2020-12-01 | 2021-03-19 | 新华三人工智能科技有限公司 | Abnormal root cause positioning method and device |
| CN112583640A (en) * | 2020-12-02 | 2021-03-30 | 厦门渊亭信息科技有限公司 | Service fault detection method and device based on knowledge graph |
| CN112860472A (en) * | 2021-02-05 | 2021-05-28 | 建信金融科技有限责任公司 | System fault position determining method and device, electronic equipment and storage medium |
| CN113489602A (en) * | 2021-06-18 | 2021-10-08 | 广东工业大学 | Communication fault positioning method and system based on data mining |
| CN113656323A (en) * | 2021-08-27 | 2021-11-16 | 国家计算机网络与信息安全管理中心 | Method for automatically testing, positioning and repairing fault and storage medium |
| CN113762765A (en) * | 2021-09-02 | 2021-12-07 | 南方电网数字电网研究院有限公司 | Index analysis method, index analysis system, electronic device and storage medium |
| CN113766444A (en) * | 2021-09-23 | 2021-12-07 | 中国联合网络通信集团有限公司 | Fault positioning method, device and equipment |
| CN113918374A (en) * | 2021-12-08 | 2022-01-11 | 云智慧（北京）科技有限公司 | Root cause analysis method, device and equipment of operation and maintenance system |
| CN114637654A (en) * | 2022-03-30 | 2022-06-17 | 北京国信网联科技有限公司 | Fault monitoring and analyzing method based on AIOps intelligent operation center |
| CN114707004A (en) * | 2022-05-24 | 2022-07-05 | 国网浙江省电力有限公司信息通信分公司 | Method and system for extracting and processing case-affair relation based on image model and language model |
| CN114966304A (en) * | 2022-04-13 | 2022-08-30 | 中移互联网有限公司 | Fault positioning method and device and electronic equipment |
| CN115242606A (en) * | 2022-06-21 | 2022-10-25 | 北京字跳网络技术有限公司 | Data processing method, data processing apparatus, server, storage medium, and program product |
| CN115442833A (en) * | 2021-06-03 | 2022-12-06 | ***通信集团四川有限公司 | Complaint root cause analysis method and device and electronic equipment |
| CN115514679A (en) * | 2022-11-11 | 2022-12-23 | 浙江万胜智能科技股份有限公司 | Abnormal source monitoring method and system based on communication module |
| CN117149501A (en) * | 2023-10-31 | 2023-12-01 | 中邮消费金融有限公司 | Problem repair system and method |
| WO2023246582A1 (en) * | 2022-06-23 | 2023-12-28 | 中兴通讯股份有限公司 | Fault locating system and method, electronic device, and storage medium |
| CN113656323B (en) * | 2021-08-27 | 2024-05-28 | 国家计算机网络与信息安全管理中心 | Method for automatically testing, positioning and repairing faults and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105045256A (en) * | 2015-07-08 | 2015-11-11 | 北京泰乐德信息技术有限公司 | Rail traffic real-time fault diagnosis method and system based on data comparative analysis |
| CN108009040A (en) * | 2017-12-12 | 2018-05-08 | 杭州时趣信息技术有限公司 | A kind of definite failure root because method, system and computer-readable recording medium |
| CN109656793A (en) * | 2018-11-22 | 2019-04-19 | 安徽继远软件有限公司 | A kind of information system performance stereoscopic monitoring method based on multi-source heterogeneous data fusion |
| CN110134566A (en) * | 2019-04-29 | 2019-08-16 | 国网上海市电力公司 | Information system performance monitoring method under a kind of cloud environment based on label technique |
-
2019
- 2019-11-14 CN CN201911115624.7A patent/CN110955575A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105045256A (en) * | 2015-07-08 | 2015-11-11 | 北京泰乐德信息技术有限公司 | Rail traffic real-time fault diagnosis method and system based on data comparative analysis |
| CN108009040A (en) * | 2017-12-12 | 2018-05-08 | 杭州时趣信息技术有限公司 | A kind of definite failure root because method, system and computer-readable recording medium |
| CN109656793A (en) * | 2018-11-22 | 2019-04-19 | 安徽继远软件有限公司 | A kind of information system performance stereoscopic monitoring method based on multi-source heterogeneous data fusion |
| CN110134566A (en) * | 2019-04-29 | 2019-08-16 | 国网上海市电力公司 | Information system performance monitoring method under a kind of cloud environment based on label technique |
Cited By (27)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111639115A (en) * | 2020-04-29 | 2020-09-08 | 国家电网有限公司客户服务中心 | Five-dimensional model-based analysis method for operation and maintenance data abnormity of power grid information system |
| CN111722952A (en) * | 2020-05-25 | 2020-09-29 | 中国建设银行股份有限公司 | Fault analysis method, system, equipment and storage medium of business system |
| CN111506637A (en) * | 2020-06-17 | 2020-08-07 | 北京必示科技有限公司 | Multi-dimensional anomaly detection method and device based on KPI (Key Performance indicator) and storage medium |
| CN112532455A (en) * | 2020-12-01 | 2021-03-19 | 新华三人工智能科技有限公司 | Abnormal root cause positioning method and device |
| CN112532455B (en) * | 2020-12-01 | 2022-07-29 | 新华三人工智能科技有限公司 | Abnormal root cause positioning method and device |
| CN112463834A (en) * | 2020-12-02 | 2021-03-09 | 中国建设银行股份有限公司 | Method and device for automatically realizing root cause analysis in streaming processing and electronic equipment |
| CN112583640A (en) * | 2020-12-02 | 2021-03-30 | 厦门渊亭信息科技有限公司 | Service fault detection method and device based on knowledge graph |
| CN112860472A (en) * | 2021-02-05 | 2021-05-28 | 建信金融科技有限责任公司 | System fault position determining method and device, electronic equipment and storage medium |
| CN115442833A (en) * | 2021-06-03 | 2022-12-06 | ***通信集团四川有限公司 | Complaint root cause analysis method and device and electronic equipment |
| CN113489602A (en) * | 2021-06-18 | 2021-10-08 | 广东工业大学 | Communication fault positioning method and system based on data mining |
| CN113656323A (en) * | 2021-08-27 | 2021-11-16 | 国家计算机网络与信息安全管理中心 | Method for automatically testing, positioning and repairing fault and storage medium |
| CN113656323B (en) * | 2021-08-27 | 2024-05-28 | 国家计算机网络与信息安全管理中心 | Method for automatically testing, positioning and repairing faults and storage medium |
| CN113762765A (en) * | 2021-09-02 | 2021-12-07 | 南方电网数字电网研究院有限公司 | Index analysis method, index analysis system, electronic device and storage medium |
| CN113766444A (en) * | 2021-09-23 | 2021-12-07 | 中国联合网络通信集团有限公司 | Fault positioning method, device and equipment |
| CN113766444B (en) * | 2021-09-23 | 2023-07-04 | 中国联合网络通信集团有限公司 | Fault positioning method, device and equipment |
| CN113918374B (en) * | 2021-12-08 | 2022-03-08 | 云智慧（北京）科技有限公司 | Root cause analysis method, device and equipment of operation and maintenance system |
| CN113918374A (en) * | 2021-12-08 | 2022-01-11 | 云智慧（北京）科技有限公司 | Root cause analysis method, device and equipment of operation and maintenance system |
| CN114637654A (en) * | 2022-03-30 | 2022-06-17 | 北京国信网联科技有限公司 | Fault monitoring and analyzing method based on AIOps intelligent operation center |
| CN114966304A (en) * | 2022-04-13 | 2022-08-30 | 中移互联网有限公司 | Fault positioning method and device and electronic equipment |
| CN114707004B (en) * | 2022-05-24 | 2022-08-16 | 国网浙江省电力有限公司信息通信分公司 | Method and system for extracting and processing case-affair relation based on image model and language model |
| CN114707004A (en) * | 2022-05-24 | 2022-07-05 | 国网浙江省电力有限公司信息通信分公司 | Method and system for extracting and processing case-affair relation based on image model and language model |
| CN115242606A (en) * | 2022-06-21 | 2022-10-25 | 北京字跳网络技术有限公司 | Data processing method, data processing apparatus, server, storage medium, and program product |
| CN115242606B (en) * | 2022-06-21 | 2024-04-16 | 北京字跳网络技术有限公司 | Data processing method, device, server, storage medium and program product |
| WO2023246582A1 (en) * | 2022-06-23 | 2023-12-28 | 中兴通讯股份有限公司 | Fault locating system and method, electronic device, and storage medium |
| CN115514679A (en) * | 2022-11-11 | 2022-12-23 | 浙江万胜智能科技股份有限公司 | Abnormal source monitoring method and system based on communication module |
| CN117149501A (en) * | 2023-10-31 | 2023-12-01 | 中邮消费金融有限公司 | Problem repair system and method |
| CN117149501B (en) * | 2023-10-31 | 2024-02-06 | 中邮消费金融有限公司 | Problem repair system and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110955575A (en) | Business system fault positioning method based on correlation analysis model | |
| CN110958136A (en) | Deep learning-based log analysis early warning method | |
| CN112416645B (en) | Fault root cause deducing and positioning method and device based on artificial intelligence | |
| CN113268399B (en) | Alarm processing method and device and electronic equipment | |
| CN107104951B (en) | Method and device for detecting network attack source | |
| CN113553210A (en) | Alarm data processing method, device, equipment and storage medium | |
| CN112416724B (en) | Alarm processing method, system, computer device and storage medium | |
| US10628250B2 (en) | Search for information related to an incident | |
| CN115529595A (en) | Method, device, equipment and medium for detecting abnormity of log data | |
| CN111581056B (en) | Software engineering database maintenance and early warning system based on artificial intelligence | |
| EP3789882B1 (en) | Automatic configuration of logging infrastructure for software deployments using source code | |
| CN115544519A (en) | Method for carrying out security association analysis on threat information of metering automation system | |
| CN110830483B (en) | Webpage log attack information detection method, system, equipment and readable storage medium | |
| CN113516565A (en) | Intelligent alarm processing method and device for power monitoring system based on knowledge base | |
| CN107579944B (en) | Artificial intelligence and MapReduce-based security attack prediction method | |
| US20230087309A1 (en) | Cyberattack identification in a network environment | |
| CN116846612A (en) | Attack chain completion method and device, electronic equipment and storage medium | |
| CN109634808B (en) | Chain monitoring event root cause analysis method based on correlation analysis | |
| KR101484186B1 (en) | Indexing apparatus and method for search of security monitoring data | |
| CN115577364A (en) | Vulnerability mining method for result fusion of multiple static analysis tools | |
| CN111209158B (en) | Mining monitoring method and cluster monitoring system for server cluster | |
| CN112418449A (en) | Generation method, positioning method and device of power supply line fault positioning model | |
| CN115484150B (en) | Alarm information processing method, system, equipment and storage medium | |
| CN116915459B (en) | Network threat analysis method based on large language model | |
| CN117573428B (en) | Disaster recovery backup method, device, computer equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |