CN113127542B - Data anomaly analysis method and device - Google Patents
Data anomaly analysis method and device Download PDFInfo
- Publication number
- CN113127542B CN113127542B CN202110489380.XA CN202110489380A CN113127542B CN 113127542 B CN113127542 B CN 113127542B CN 202110489380 A CN202110489380 A CN 202110489380A CN 113127542 B CN113127542 B CN 113127542B
- Authority
- CN
- China
- Prior art keywords
- data
- abnormal
- variable
- cluster
- anomaly
- 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.)
- Active
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 58
- 238000000034 method Methods 0.000 claims abstract description 32
- 238000012544 monitoring process Methods 0.000 claims abstract description 23
- 230000002159 abnormal effect Effects 0.000 claims description 132
- 238000001514 detection method Methods 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 6
- 238000011156 evaluation Methods 0.000 claims description 6
- 230000000694 effects Effects 0.000 abstract description 5
- 230000005856 abnormality Effects 0.000 description 28
- 238000012545 processing Methods 0.000 description 3
- 238000012163 sequencing technique Methods 0.000 description 3
- 238000013135 deep learning Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000013075 data extraction Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 230000000638 stimulation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2462—Approximate or statistical queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/283—Multi-dimensional databases or data warehouses, e.g. MOLAP or ROLAP
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Probability & Statistics with Applications (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Debugging And Monitoring (AREA)
Abstract
The invention relates to a data anomaly analysis method and a device, which are used for acquiring a service component, a server, process information and a reference index of a target data cluster, acquiring monitoring indexes and anomaly variables corresponding to the service component, the server, the process information and the reference index of the target data cluster according to a preset corresponding relation, acquiring data of the target data cluster according to the monitoring indexes and the anomaly variables to obtain data to be analyzed, grouping the anomaly variables in the data to be analyzed to obtain at least one variable group, carrying out anomaly analysis on the data to be analyzed according to the variable group to obtain an anomaly prediction result, and storing the anomaly prediction result. The data anomaly analysis method provided by the invention can effectively conduct anomaly prediction on the data clusters, conduct anomaly analysis on the data clusters according to the groups, conduct anomaly prediction on the data clusters from a plurality of different dimensions, improve the accuracy of data cluster anomaly prediction, and improve the monitoring effect on the data platform.
Description
Technical Field
The invention relates to a data anomaly analysis method and a data anomaly analysis device.
Background
Currently, data processing based on big data is widely used. And a plurality of data clusters are arranged in the data platform corresponding to the big data. The data cluster can adopt different components according to service requirements to build a large data platform suitable for localization. Accordingly, data monitoring of individual data clusters in the data platform is of vital importance. At present, the monitoring mode of each data cluster in the data platform is as follows: the data clusters with abnormal phenomena are analyzed, the abnormal analysis mode can only analyze the data clusters with abnormal phenomena, the abnormal phenomena of the data clusters cannot be effectively predicted, and the monitoring effect is poor.
Disclosure of Invention
The invention provides a data anomaly analysis method and a data anomaly analysis device, which are used for solving the technical problem that the monitoring effect of the existing data anomaly analysis method is poor.
A data anomaly analysis method, comprising:
acquiring a service component, a server, process information and a reference index of a target data cluster;
acquiring monitoring indexes and abnormal variables corresponding to the service components, the servers, the process information and the reference indexes of the target data cluster according to a preset corresponding relation;
data acquisition is carried out on the target data cluster according to the monitoring index and the abnormal variable, so that data to be analyzed are obtained;
grouping the abnormal variables in the data to be analyzed to obtain at least one variable group, and carrying out abnormal analysis on the data to be analyzed according to the variable group to obtain an abnormal prediction result;
and storing the abnormal prediction result.
Further, before the service component, the server, the process information and the reference index of the target data cluster are acquired, the data anomaly analysis method further includes:
acquiring cluster identifiers of all data clusters stored in a data platform;
according to a preset ordering rule and cluster identification of each data cluster, ordering each data cluster to obtain an ordering result, and carrying out data anomaly analysis on each data cluster according to the ordering result.
Further, grouping the abnormal variables in the data to be analyzed to obtain at least one variable group, and performing abnormal analysis on the data to be analyzed according to the variable group to obtain an abnormal prediction result, specifically;
selecting abnormal variables in the data to be analyzed according to a preset selection rule, and forming a variable group from the abnormal variables selected from the same batch;
respectively acquiring corresponding data of each abnormal variable in the data to be analyzed according to the variable group to obtain variable data;
and respectively carrying out anomaly detection on the variable data to obtain a corresponding anomaly prediction result.
Further, according to the variable group, respectively acquiring data corresponding to each abnormal variable in the data to be analyzed to obtain variable data, which specifically includes:
and respectively acquiring data carrying corresponding abnormal variables in the data to be analyzed according to each abnormal variable in the variable group, and integrating the data acquired aiming at the same variable group to acquire the variable data.
Further, after performing anomaly detection on the variable data to obtain a corresponding anomaly prediction result, the data anomaly analysis method further includes:
if all the variable data are not abnormal, acquiring associated data corresponding to the variable data corresponding to the same variable group;
and carrying out exception analysis on the associated data to obtain an additional exception prediction result, and adding the additional exception prediction result into the exception prediction result.
Further, the grouping of the abnormal variables in the data to be analyzed to obtain at least one variable group, and performing an abnormal analysis on the data to be analyzed according to the variable group, so as to obtain an abnormal prediction result, and then the data abnormal analysis method further comprises:
acquiring abnormal notification information corresponding to the target data cluster, and matching the prediction information in the abnormal prediction result with a notification address in the abnormal notification information;
and reminding the corresponding notification address of the successfully matched prediction information.
Further, the obtaining the abnormality notification information corresponding to the target data cluster, and matching the prediction information in the abnormality prediction result with the notification address in the abnormality notification information specifically includes:
acquiring the abnormal notification information, wherein the abnormal notification information comprises at least one notification address, and each notification address corresponds to a right value;
performing abnormal grade evaluation on the prediction information in the abnormal prediction result to obtain a corresponding abnormal value;
and matching the abnormal value of the prediction information with the authority value corresponding to each notification address, finding the authority value equal to the abnormal value, and determining the notification address corresponding to the acquired authority value.
Further, the reminding of the prediction information of successful matching to the corresponding notification address specifically includes:
acquiring a reminding mode corresponding to the acquired authority value according to a preset reminding mode database; the reminding mode database comprises at least two authority values and reminding modes corresponding to the authority values;
and reminding the corresponding notification address according to the obtained reminding mode.
Further, the storing the abnormal prediction result specifically includes:
determining a target storage area of the target data cluster according to the cluster identification of the target data cluster and a preset storage relationship; the preset storage relationship comprises cluster identifiers of all data clusters stored in the data platform and storage areas corresponding to the cluster identifiers of all the data clusters;
and storing the exception prediction result into the target storage area.
A data anomaly analysis device comprises a memory, a processor and a computer program stored in the memory and running on the processor, wherein the processor realizes the data anomaly analysis method when executing the computer program.
The technical effects of the data anomaly analysis method provided by the invention include: obtaining corresponding monitoring indexes and abnormal variables according to service components, servers, process information and reference indexes of the target data clusters, then carrying out data acquisition on the target data clusters according to the obtained monitoring indexes and the abnormal variables to obtain data to be analyzed, then grouping the abnormal variables in the data to be analyzed to obtain at least one variable group, carrying out abnormal analysis on the data to be analyzed according to the variable group to obtain an abnormal prediction result, and finally storing the obtained abnormal prediction result. The data anomaly analysis method provided by the invention is a prediction method for carrying out anomaly prediction on the data cluster, can effectively carry out anomaly prediction on the data cluster, and improves the monitoring effect and accuracy of a data platform; by grouping abnormal variables in the data to be analyzed, carrying out abnormal analysis according to the grouping, and carrying out abnormal prediction on the data cluster from a plurality of different dimensions based on a plurality of variable groups obtained by grouping, the accuracy of the abnormal prediction of the data cluster is improved; by means of data anomaly prediction, problems can be found before anomalies actually occur, and workers can have enough time to solve the problems.
Drawings
Fig. 1 is a flowchart of a data anomaly analysis method provided by the present invention.
Detailed Description
Data anomaly analysis method embodiment:
the embodiment provides a data anomaly analysis method, and a hardware execution body of the data anomaly analysis method may be a computer device, a server device, an intelligent mobile terminal, or the like. In addition, the application scenario of the hardware execution body of the data anomaly analysis method is not limited, and is set according to actual needs.
As shown in fig. 1, the data anomaly analysis method includes the steps of:
step 1: obtaining service components, servers, process information and reference indexes of a target data cluster:
in this embodiment, at least one data cluster is stored in the data platform, and the number of data clusters and the specific composition of the data clusters are determined by the actual application scenario. In this embodiment, the data cluster is configured by using at least two or more servers to form a virtual single database logical image, and is used for providing data services to the user side, where a server identifier communicatively connected to the data cluster and a component identifier corresponding to the data services provided to the user are stored in local data of the data cluster. The target data cluster belongs to a data cluster in the data platform.
And acquiring the service component, the server, the process information and the reference index of the target data cluster. And querying the corresponding service component and server according to each server identifier and component identifier in the target data cluster. The process information includes the process running state of each service component and the server. The reference index is an index parameter preset by a user, and the index parameter comprises a quantity parameter, an operation state parameter and the like.
In general, a plurality of data clusters are disposed in the data platform, and then the processing order of the data clusters needs to be ordered, and in this embodiment, before step 1, the data anomaly analysis method further includes:
and acquiring cluster identifiers of all data clusters stored in the data platform. The cluster identifier may be a cluster name of a corresponding data cluster, or may be other cluster data information indicating uniqueness.
And sequencing each data cluster according to a preset sequencing rule and cluster identification of each data cluster to obtain a sequencing result. The preset ordering rule is set according to actual needs, for example, if the cluster identifier is a cluster name of a corresponding data cluster, the ordering rule may be an arrangement sequence of initial letters of pinyin of a first word of the cluster name.
Then, according to the obtained sorting result, the data anomaly analysis can be performed on each data cluster, and the data clusters with the earlier sorting are subjected to the data anomaly analysis more first.
Step 2: according to a preset corresponding relation, acquiring monitoring indexes and abnormal variables corresponding to the service components, the servers, the process information and the reference indexes of the target data cluster:
and acquiring monitoring indexes and abnormal variables corresponding to the service components, the servers, the process information and the reference indexes of the target data cluster according to the preset corresponding relation. In this embodiment, the preset correspondence includes a combination of at least two service components, a server, process information and a reference index, and a monitoring index and an abnormal variable corresponding to each combination. It should be understood that in the preset corresponding relationship, the combinations of different service components, servers, process information and reference indexes may be the same or different in the corresponding monitoring indexes and abnormal variables.
Then, the service components, the server, the process information and the reference index of the target data cluster are input into a preset corresponding relation, and the monitoring index and the abnormal variable corresponding to the service components, the server, the process information and the reference index of the target data cluster can be obtained.
Step 3: data acquisition is carried out on the target data cluster according to the monitoring index and the abnormal variable, and data to be analyzed are obtained:
according to the monitoring index and the abnormal variable, data acquisition is carried out on the target data cluster to obtain data to be analyzed, and specifically: and processing the data information of any monitoring index or any abnormal variable carried in the target data cluster (such as information stimulation on the data information of any monitoring index or any abnormal variable carried in the target data cluster) to obtain the data to be analyzed.
Step 4: grouping the abnormal variables in the data to be analyzed to obtain at least one variable group, and carrying out abnormal analysis on the data to be analyzed according to the variable group to obtain an abnormal prediction result:
grouping the abnormal variables in the data to be analyzed to obtain at least one variable group, and carrying out abnormal analysis on the data to be analyzed according to the variable group to obtain an abnormal prediction result. The variable group is obtained by grouping the abnormal variables in the data to be analyzed, so that the abnormal variables can be subjected to abnormal analysis on the data to be analyzed in a combined mode, a plurality of analysis prediction results are obtained, different abnormal predictions on the target data cluster from a plurality of dimensions are realized, and the accuracy of the data cluster abnormal prediction method is improved.
As a specific embodiment, the following is given as a specific implementation procedure of this step:
(1) And selecting the abnormal variables in the data to be analyzed according to a preset selection rule, and forming a variable group by using the abnormal variables selected from the same batch. The preset selection rule is specifically set according to actual needs, for example: the abnormal variables in the data to be analyzed are fixedly selected in a preset number mode, and then a variable group with fixed number can be obtained; or randomly selecting the abnormal variables in the data to be analyzed in a preset number mode until the abnormal variables are selected, and obtaining the variable groups with the corresponding number.
(2) And respectively acquiring the data corresponding to each abnormal variable in the data to be analyzed according to the variable group to obtain variable data. In this embodiment, according to each abnormal variable in the variable group, data carrying a corresponding abnormal variable in the data to be analyzed is obtained respectively, and the data obtained for the same variable group are integrated to obtain variable data. The method comprises the steps of obtaining data carrying abnormal variables of a variable group in data to be analyzed for any variable group, and integrating the data carrying the abnormal variables of the variable group in the data to be analyzed to obtain variable data corresponding to the variable group.
(3) And respectively carrying out anomaly detection on the variable data to obtain a corresponding anomaly prediction result. The detection mode for detecting the abnormality of the abnormal data is selected from the existing abnormality detection process according to actual requirements. In this embodiment, model training is performed by adopting a deep learning or convolutional neural network mode according to preset sample abnormal data, so as to obtain an abnormal detection model, where the preset sample abnormal data includes a relationship between each abnormal variable and corresponding abnormal data. The trained abnormality detection model can effectively detect the abnormality of the input variable data so as to judge whether the abnormality variable in the variable data exists or not, and when the abnormality variable is judged to exist, the abnormality of the variable data is judged to possibly exist.
In this embodiment, after the step (3), the data anomaly analysis method further includes:
(4) After abnormality detection is performed on each variable data, if no abnormality occurs in all the variable data, obtaining associated data corresponding to variable data corresponding to the same variable group.
(5) And carrying out exception analysis on the obtained associated data to obtain an additional exception prediction result, and adding the additional exception prediction result into the exception prediction result. And performing abnormality detection on the variable data, training a model by adopting a deep learning or convolution neural network mode according to preset sample abnormality association data to obtain an association detection model, wherein the preset sample abnormality association data comprises the relationship between abnormal data corresponding to each abnormal variable and normal data corresponding to any abnormal variable.
Therefore, by acquiring the associated data of the variable data corresponding to the same variable group, the associated data corresponding to the variable group can be subjected to abnormal prediction, and the reliability of abnormal prediction is improved.
In this embodiment, after step 4, the data anomaly analysis method further includes a reminding process, and a specific implementation process of the reminding process is given below:
(i) And acquiring the abnormal notification information corresponding to the target data cluster, and matching the prediction information in the abnormal prediction result with the notification address in the abnormal notification information.
Firstly, obtaining abnormal notification information, wherein the abnormal notification information comprises at least one notification address, each notification address is provided with a corresponding authority value, and the authority values corresponding to different notification addresses are different. It should be understood that the abnormality notification information is set in advance, and that each data cluster in the data platform corresponds to the abnormality notification information.
And then carrying out abnormal grade evaluation on the prediction information in the abnormal prediction result to obtain a corresponding abnormal value. The abnormality level evaluation may be performed by using a preset abnormality level evaluation rule, where the preset abnormality level evaluation rule includes at least two pieces of prediction information and abnormality levels corresponding to the pieces of prediction information, each of the abnormality levels corresponds to an abnormality value, and the higher the abnormality level, the higher the corresponding abnormality value, and accordingly, the higher the abnormality value, the higher the abnormality degree of the corresponding prediction information.
And finally, matching the abnormal value of the prediction information with the authority value corresponding to each notification address, finding out the authority value equal to the abnormal value of the prediction information, and determining the notification address corresponding to the acquired authority value.
(ii) And reminding the corresponding notification address of the successfully matched prediction information.
The method comprises the steps of presetting a reminding mode database, wherein the reminding mode database comprises at least two authority values and reminding modes corresponding to the authority values, and different authority values correspond to different reminding modes. And then, according to a preset reminding mode database, obtaining a reminding mode corresponding to the obtained authority value, and reminding the corresponding notification address according to the obtained reminding mode.
By acquiring the abnormal notification information corresponding to the target data cluster and matching the prediction information in the abnormal prediction result with the notification address in the abnormal notification information, the error reminding of the notification address by the prediction information can be effectively prevented, and the accuracy of the prediction information transmission is improved.
Step 5: storing the abnormal prediction result:
and storing the abnormal prediction result, wherein in the embodiment, a storage relation is preset, and the preset storage relation comprises cluster identifications of all data clusters stored in the data platform and storage areas corresponding to the cluster identifications of all the data clusters. Different cluster identities, i.e. different clusters of data correspond to different storage areas. Accordingly, each storage area needs to be configured in advance. It should be appreciated that the cluster identity may be used as the storage area name of the corresponding storage area.
And determining a target storage area corresponding to the target data cluster according to the cluster identification of the target data cluster and a preset storage relationship. Then, the abnormality prediction result is stored in the target storage area.
By storing the abnormal prediction results of different data clusters into different storage areas, the reliability of data storage can be improved, and subsequent data extraction is facilitated.
Data anomaly analysis device embodiment:
the embodiment provides a data anomaly analysis device, which includes a memory, a processor, and a computer program stored in the memory and running on the processor, where the processor implements the data anomaly analysis method described above when executing the computer program, and since the method is described in detail above, it is not repeated.
Claims (5)
1. A data anomaly analysis method, comprising:
acquiring a service component, a server, process information and a reference index of a target data cluster;
acquiring monitoring indexes and abnormal variables corresponding to the service components, the servers, the process information and the reference indexes of the target data cluster according to a preset corresponding relation;
data acquisition is carried out on the target data cluster according to the monitoring index and the abnormal variable, so that data to be analyzed are obtained;
grouping the abnormal variables in the data to be analyzed to obtain at least one variable group, and carrying out abnormal analysis on the data to be analyzed according to the variable group to obtain an abnormal prediction result;
storing the abnormal prediction result;
grouping the abnormal variables in the data to be analyzed to obtain at least one variable group, and carrying out abnormal analysis on the data to be analyzed according to the variable group to obtain an abnormal prediction result, specifically;
selecting abnormal variables in the data to be analyzed according to a preset selection rule, and forming a variable group from the abnormal variables selected from the same batch;
respectively acquiring corresponding data of each abnormal variable in the data to be analyzed according to the variable group to obtain variable data;
respectively carrying out anomaly detection on the variable data to obtain a corresponding anomaly prediction result;
the data corresponding to each abnormal variable in the data to be analyzed are respectively obtained according to the variable group, and variable data are obtained, specifically:
according to each abnormal variable in the variable group, respectively acquiring data carrying the corresponding abnormal variable in the data to be analyzed, and integrating the data acquired aiming at the same variable group to acquire the variable data;
after the variable data are subjected to anomaly detection to obtain corresponding anomaly prediction results, the data anomaly analysis method further comprises the following steps:
if all the variable data are not abnormal, acquiring associated data corresponding to the variable data corresponding to the same variable group;
performing exception analysis on the associated data to obtain an additional exception prediction result, and adding the additional exception prediction result into the exception prediction result;
the data anomaly analysis method comprises the steps of grouping the anomaly variables in the data to be analyzed to obtain at least one variable group, carrying out anomaly analysis on the data to be analyzed according to the variable group, and obtaining an anomaly prediction result, wherein the data anomaly analysis method further comprises the following steps:
acquiring abnormal notification information corresponding to the target data cluster, and matching the prediction information in the abnormal prediction result with a notification address in the abnormal notification information;
reminding the corresponding notification address of the successfully matched prediction information;
the obtaining the abnormal notification information corresponding to the target data cluster, and matching the prediction information in the abnormal prediction result with the notification address in the abnormal notification information specifically includes:
acquiring the abnormal notification information, wherein the abnormal notification information comprises at least one notification address, and each notification address corresponds to a right value;
performing abnormal grade evaluation on the prediction information in the abnormal prediction result to obtain a corresponding abnormal value;
and matching the abnormal value of the prediction information with the authority value corresponding to each notification address, finding the authority value equal to the abnormal value, and determining the notification address corresponding to the acquired authority value.
2. The method for analyzing data anomalies according to claim 1, wherein,
before the service component, the server, the process information and the reference index of the target data cluster are acquired, the data anomaly analysis method further comprises the following steps:
acquiring cluster identifiers of all data clusters stored in a data platform;
according to a preset ordering rule and cluster identification of each data cluster, ordering each data cluster to obtain an ordering result, and carrying out data anomaly analysis on each data cluster according to the ordering result.
3. The method for analyzing data anomalies according to claim 1, wherein,
the reminding of the successfully matched prediction information to the corresponding notification address is specifically as follows:
acquiring a reminding mode corresponding to the acquired authority value according to a preset reminding mode database; the reminding mode database comprises at least two authority values and reminding modes corresponding to the authority values;
and reminding the corresponding notification address according to the obtained reminding mode.
4. The method for analyzing data anomalies according to claim 1, wherein,
the storing of the abnormal prediction result is specifically:
determining a target storage area of the target data cluster according to the cluster identification of the target data cluster and a preset storage relationship; the preset storage relationship comprises cluster identifiers of all data clusters stored in the data platform and storage areas corresponding to the cluster identifiers of all the data clusters;
and storing the exception prediction result into the target storage area.
5. A data anomaly analysis device comprising a memory, a processor and a computer program stored on the memory and running on the processor, wherein the processor implements the data anomaly analysis method of any one of claims 1-4 when the computer program is executed by the processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110489380.XA CN113127542B (en) | 2021-05-06 | 2021-05-06 | Data anomaly analysis method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110489380.XA CN113127542B (en) | 2021-05-06 | 2021-05-06 | Data anomaly analysis method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113127542A CN113127542A (en) | 2021-07-16 |
| CN113127542B true CN113127542B (en) | 2023-06-16 |
Family
ID=76781501
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110489380.XA Active CN113127542B (en) | 2021-05-06 | 2021-05-06 | Data anomaly analysis method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113127542B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109690641A (en) * | 2016-08-29 | 2019-04-26 | 韩国水力原子力株式会社 | The method and system for preliminary examination nuclear power plant equipment abnormal signs including determining the processing routine of Chemical Apparatus Importance Classification and alarm validity |
| CN111159844A (en) * | 2019-12-02 | 2020-05-15 | 中国电建集团江西省电力设计院有限公司 | Abnormity detection method for exhaust temperature of gas turbine of power station |
| CN111708343A (en) * | 2019-10-31 | 2020-09-25 | 中国科学院沈阳自动化研究所 | Method for detecting abnormal behavior of field process behavior in manufacturing industry |
| JP2020181443A (en) * | 2019-04-26 | 2020-11-05 | 株式会社豊田中央研究所 | Abnormality detection apparatus, abnormality detection method, and computer program |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111638988B (en) * | 2019-04-28 | 2023-05-12 | 上海伽易信息技术有限公司 | Cloud host fault intelligent prediction method based on deep learning |
| CN111309539A (en) * | 2020-03-26 | 2020-06-19 | 北京奇艺世纪科技有限公司 | Abnormity monitoring method and device and electronic equipment |
| CN112465411B (en) * | 2021-01-27 | 2021-06-04 | 支付宝(杭州)信息技术有限公司 | Risk prediction method, device and equipment |
-
2021
- 2021-05-06 CN CN202110489380.XA patent/CN113127542B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109690641A (en) * | 2016-08-29 | 2019-04-26 | 韩国水力原子力株式会社 | The method and system for preliminary examination nuclear power plant equipment abnormal signs including determining the processing routine of Chemical Apparatus Importance Classification and alarm validity |
| JP2020181443A (en) * | 2019-04-26 | 2020-11-05 | 株式会社豊田中央研究所 | Abnormality detection apparatus, abnormality detection method, and computer program |
| CN111708343A (en) * | 2019-10-31 | 2020-09-25 | 中国科学院沈阳自动化研究所 | Method for detecting abnormal behavior of field process behavior in manufacturing industry |
| CN111159844A (en) * | 2019-12-02 | 2020-05-15 | 中国电建集团江西省电力设计院有限公司 | Abnormity detection method for exhaust temperature of gas turbine of power station |
Non-Patent Citations (2)
| Title |
|---|
| Development of a low cost embedded diagnosis system for servo controlled drives including data mining technologies;Ralf Wegener 等;《2009 IEEE International Symposium on Industrial Electronics》;373-377 * |
| 面向电力大数据的用户用电行为挖掘方法;蒋子规;《中国博士学位论文全文数据库工程科技Ⅱ辑》(第8期);C042-84 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113127542A (en) | 2021-07-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107104978B (en) | Network risk early warning method based on deep learning | |
| CN111339151B (en) | Online examination method, device, equipment and computer storage medium | |
| CN113032792A (en) | System service vulnerability detection method, system, equipment and storage medium | |
| CN109740347A (en) | A kind of identification of the fragile hash function for smart machine firmware and crack method | |
| CN115484112B (en) | Payment big data safety protection method, system and cloud platform | |
| CN113535823B (en) | Abnormal access behavior detection method and device and electronic equipment | |
| CN113127542B (en) | Data anomaly analysis method and device | |
| CN111367782A (en) | Method and device for automatically generating regression test data | |
| CN108733707B (en) | Method and device for determining stability of search function | |
| CN116842240A (en) | Data management and control system based on full-link management and control | |
| CN116431522A (en) | Automatic test method and system for low-code object storage gateway | |
| CN108647139B (en) | System test method, device, storage medium and electronic device | |
| CN113032547B (en) | Big data processing method and system based on artificial intelligence and cloud platform | |
| LU501931B1 (en) | Data exception analysis method and device | |
| CN112600715B (en) | Distribution network operation analysis method and device, storage medium and electronic device | |
| CN112333156B (en) | Network security protection method and network security protection platform based on big data | |
| CN112540906B (en) | Intelligent analysis method and system for business and data relationship based on probe | |
| CN114329449A (en) | System security detection method and device, storage medium and electronic device | |
| CN110765016B (en) | Game test instruction processing method, game test instruction processing system, server and storage device | |
| CN109299224B (en) | Zabbix-based solution query method and device and computer equipment | |
| CN113448806B (en) | Database cluster anomaly detection method and device, terminal device and storage medium | |
| CN112672353A (en) | Information analysis method, system and cloud platform based on cloud computing and 5G interconnection | |
| CN111338837B (en) | Data processing method, device, equipment and medium | |
| CN113239236B (en) | Video processing method and device, electronic equipment and storage medium | |
| CN116882966B (en) | Fault judging method and device for inspection result of operation and maintenance equipment |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |