CN110377445A - Failure prediction method and device - Google Patents
Failure prediction method and device Download PDFInfo
- Publication number
- CN110377445A CN110377445A CN201910580238.9A CN201910580238A CN110377445A CN 110377445 A CN110377445 A CN 110377445A CN 201910580238 A CN201910580238 A CN 201910580238A CN 110377445 A CN110377445 A CN 110377445A
- Authority
- CN
- China
- Prior art keywords
- failure
- status data
- equipment
- data
- 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.)
- Withdrawn
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/07—Responding to the occurrence of a fault, e.g. fault tolerance
- G06F11/0703—Error or fault processing not based on redundancy, i.e. by taking additional measures to deal with the error or fault not making use of redundancy in operation, in hardware, or in data representation
- G06F11/0706—Error or fault processing not based on redundancy, i.e. by taking additional measures to deal with the error or fault not making use of redundancy in operation, in hardware, or in data representation the processing taking place on a specific hardware platform or in a specific software environment
- G06F11/0709—Error or fault processing not based on redundancy, i.e. by taking additional measures to deal with the error or fault not making use of redundancy in operation, in hardware, or in data representation the processing taking place on a specific hardware platform or in a specific software environment in a distributed system consisting of a plurality of standalone computer nodes, e.g. clusters, client-server systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/07—Responding to the occurrence of a fault, e.g. fault tolerance
- G06F11/0703—Error or fault processing not based on redundancy, i.e. by taking additional measures to deal with the error or fault not making use of redundancy in operation, in hardware, or in data representation
- G06F11/079—Root cause analysis, i.e. error or fault diagnosis
Abstract
The invention discloses a kind of failure prediction method and devices, this method comprises: the status data of the equipment in the acquisition predetermined time, screens collected status data, obtain status data relevant to failure；The incidence relation between status data relevant to failure, fault type and fault rate is obtained using default rule；According to the incidence relation, model of failure distribution is generated；Obtain the current status data of the equipment；According to the current status data of the equipment and the model of failure distribution, the failure predication result of the equipment is obtained.Failure prediction method and device disclosed by the invention can predict the equipment fault in data center, ensure the stable operation of equipment, reduce failure and bring loss occurs.
Description
Technical field
The present invention relates to field of computer technology, and in particular to a kind of failure prediction method and device.
Background technique
With using internet, cloud computing and big data as the rapid development of the information economy of representative, data center's scale and
Complexity is gradually increased, and device category, quantity are more and more, and equipment fault influences the stable operation of data center, therefore, for
The failure predication of equipment is also more important in data center.And at present traditional fault diagnosis technology be when failure occurs, or
Person's failure generates alarm after occurring, and O&M demand has been unable to satisfy, if many failures cannot accomplish look-ahead.When equipment event
When barrier occurs, the normal operation of the business in data center will affect, the loss to enterprise is also that can not estimate.Therefore how
Accomplish that the failure predication to equipment in data center is a problem to be solved.
Summary of the invention
In order to solve the above-mentioned technical problems, the present invention provides a kind of failure prediction methods and device can be to data center
In equipment fault predicted, ensure the stable operation of equipment, reduce failure and bring loss occurs.
In order to solve the above-mentioned technical problems, the present invention provides a kind of failure prediction methods characterized by comprising
The status data in the equipment in the predetermined time is acquired, collected status data is screened, is obtained and event
Hinder relevant status data；
Using default rule obtain the status data relevant to failure, fault type and fault rate it
Between incidence relation；
According to the incidence relation, model of failure distribution is generated；
Obtain the current status data of the equipment；
According to the current status data of the equipment and the model of failure distribution, the failure predication of the equipment is obtained
As a result.
In one exemplary embodiment, the above method also has the following characteristics that
The status data of the equipment includes: the performance data of one or more parts of the equipment, operating status number
According to and daily record data.
In one exemplary embodiment, the above method also has the following characteristics that
It is described that collected status data is screened, obtain status data relevant to failure, comprising: set from described
In the performance datas of standby one or more parts, running state data and daily record data, according to historical state data and therefore
The statistical result for hindering the degree of correlation is filtered out with the high data of the failure degree of correlation for failure predication.
In one exemplary embodiment, the above method also has the following characteristics that
Using default rule obtain the status data relevant to failure, fault type and fault rate it
Between incidence relation, comprising:
The incidence relation of historical state data and failure according to the pre-stored data, passes through Keywords matching, decision tree or mind
Through network mode, clustering is carried out to the status data relevant to failure, obtains the status number relevant to failure
According to the incidence relation between, fault type and fault rate.
In one exemplary embodiment, the above method also has the following characteristics that
The current status data and the model of failure distribution according to the equipment, obtains the failure of the equipment
Prediction result, comprising:
Status data in the current status data of the equipment and the model of failure distribution is compared；
According to the comparison result of the status data in the current status data of the equipment and the model of failure distribution, obtain
Obtain the failure predication result of the equipment.
In one exemplary embodiment, the above method also has the following characteristics that
The comparison knot of status data in the current status data and the model of failure distribution according to the equipment
Fruit obtains the failure predication result of the equipment, comprising:
When there is status data consistent with the current status data of the equipment in the model of failure distribution, obtain
Fault type corresponding with the status data and fault rate in the model of failure distribution.
In order to solve the above-mentioned technical problems, the present invention provides a kind of fault prediction devices, including memory and processor；
It is characterized by:
The memory, for storing computer-readable instruction；
The processor, for executing the computer-readable instruction, to perform the following operations:
The status data in the equipment in the predetermined time is acquired, collected status data is screened, is obtained and event
Hinder relevant status data；
Using default rule obtain the status data relevant to failure, fault type and fault rate it
Between incidence relation；
According to the incidence relation, model of failure distribution is generated；
Obtain the current status data of the equipment；
According to the current status data of the equipment and the model of failure distribution, the failure predication of the equipment is obtained
As a result.
In one exemplary embodiment, above-mentioned failure is preset device and is also had the following characteristics that
The status data of the equipment includes: the performance data of one or more parts of the equipment, operating status number
According to and daily record data.
In one exemplary embodiment, above-mentioned failure is preset device and is also had the following characteristics that
It is described that collected status data is screened, obtain status data relevant to failure, comprising: set from described
In the performance datas of standby one or more parts, running state data and daily record data, according to historical state data and therefore
The statistical result for hindering the degree of correlation is filtered out with the high data of the failure degree of correlation for failure predication.
In one exemplary embodiment, above-mentioned failure is preset device and is also had the following characteristics that
Using default rule obtain the status data relevant to failure, fault type and fault rate it
Between incidence relation, comprising:
The incidence relation of historical state data and failure according to the pre-stored data, passes through Keywords matching, decision tree or mind
Through network mode, clustering is carried out to the status data relevant to failure, obtains the status number relevant to failure
According to the incidence relation between, fault type and fault rate.
In one exemplary embodiment, above-mentioned failure is preset device and is also had the following characteristics that
The current status data and the model of failure distribution according to the equipment, obtains the failure of the equipment
Prediction result, comprising:
Status data in the current status data of the equipment and the model of failure distribution is compared；
According to the comparison result of the status data in the current status data of the equipment and the model of failure distribution, obtain
Obtain the failure predication result of the equipment.
In one exemplary embodiment, above-mentioned failure is preset device and is also had the following characteristics that
The comparison knot of status data in the current status data and the model of failure distribution according to the equipment
Fruit obtains the failure predication result of the equipment, comprising:
When there is status data consistent with the current status data of the equipment in the model of failure distribution, obtain
Fault type corresponding with the status data and fault rate in the model of failure distribution.
To sum up, failure prediction method and device provided by the present application pass through the status number in the equipment in the acquisition predetermined time
According to being screened to collected status data, obtain status data relevant to failure；It is obtained and event using default rule
Hinder the incidence relation between relevant status data, fault type and fault rate；According to the incidence relation, generate
Model of failure distribution；Obtain the current status data of equipment；According to the current status data of the equipment and the failure point
Cloth model obtains the failure predication of the equipment as a result, it is possible to predict the equipment fault in data center, ensures equipment
Stable operation, reduce failure occur bring loss.
Other features and advantages of the present invention will be illustrated in the following description, also, partly becomes from specification
It obtains it is clear that understand through the implementation of the invention.The objectives and other advantages of the invention can be by specification, right
Specifically noted structure is achieved and obtained in claim and attached drawing.
Detailed description of the invention
Attached drawing is used to provide to further understand technical solution of the present invention, and constitutes part of specification, with this
The embodiment of application technical solution for explaining the present invention together, does not constitute the limitation to technical solution of the present invention.
Fig. 1 is the flow chart of the failure prediction method of the embodiment of the present invention；
Fig. 2 is the three-dimensional distribution map of the status data of exemplary embodiment of the present, fault type and fault rate；
Fig. 3 is the schematic diagram of the fault prediction device of the embodiment of the present invention.
Specific embodiment
To make the objectives, technical solutions, and advantages of the present invention clearer, below in conjunction with attached drawing to the present invention
Embodiment be described in detail.It should be noted that in the absence of conflict, in the embodiment and embodiment in the application
Feature can mutual any combination.
Fig. 1 is the flow chart of the failure prediction method of the embodiment of the present invention, and according to the flow chart, the failure of the present embodiment is pre-
Survey method, comprising:
Step S101: the status data in equipment in the acquisition predetermined time screens collected status data,
Obtain status data relevant to failure.
In this step, the status data at the time point of each setting can be acquired in the given time, be also possible to
In the scheduled time, at every fixed time the period acquisition status data.Wherein, the scheduled time can be user-defined
It is also possible to the time of system setting, which can be one day, one week or one month time, to pre- in the application
There is no limit for fixed time span.In an exemplary embodiment, the predetermined time set by user is one day, Mei Geyi
Status data of hour acquisition.
Step S102: the status data relevant to failure, fault type and failure are obtained using default rule
Incidence relation between probability of happening.
Step S103: according to the incidence relation, model of failure distribution is generated
In this step, model of failure distribution can be, status data as described in Figure 2, fault type and failure hair
The three-dimensional distribution map of raw probability, is also possible to according to the number between status data, fault type and fault rate three
Model is learned, can also be the other kinds of of the relationship between status data, fault type and fault rate three of embodying
Model etc..
Step S104: the current status data of the equipment is obtained.
Step S105: according to the current status data of the equipment and the model of failure distribution, the equipment is obtained
Failure predication result.
In one exemplary embodiment, the status data of the equipment includes: one or more parts of the equipment
Performance data, running state data and daily record data.One or more parts of equipment are one or more compositions of equipment
Original part, include: CPU, hard disk, fan, memory etc..Wherein, performance data can refer to performance indicator, for example, CPU
Utilization rate, the utilization rate of memory, memory or IOPS (read-write number per second) of hard disk etc..
In one exemplary embodiment, the status data of the equipment includes: one or more parts of the equipment
Performance data, running state data and daily record data.
In one exemplary embodiment, described that collected status data is screened, it obtains relevant to failure
Status data, comprising: from the performance data, running state data and daily record data of one or more parts of the equipment,
According to the statistical result to historical state data and the failure degree of correlation, filter out pre- for failure with the high data of the failure degree of correlation
It surveys.
In another exemplary embodiment, described that collected status data is screened, it obtains related to failure
Status data, comprising: performance data, running state data and daily record data from one or more parts of the equipment
In, according to the statistical result to historical state data and the failure degree of correlation, filter out with the data of the failure degree of correlation for failure
Prediction.
In two examples above embodiment, the degree of correlation of data and failure generates event after may indicate that some existing data
The probability of barrier shows that the degree of correlation of the data and failure is high when the probability of malfunction is more than certain threshold value；When the probability of malfunction
When equal to or less than certain threshold value, show that the data are low with the degree of correlation of failure.
In one exemplary embodiment, the status data relevant to failure, failure are obtained using default rule
Incidence relation between type and fault rate, comprising:
The incidence relation of historical state data and failure according to the pre-stored data, passes through Keywords matching, decision tree or mind
Through network mode, clustering is carried out to the status data relevant to failure, obtains the status number relevant to failure
According to the incidence relation between, fault type and fault rate.
In other exemplary embodiments of the invention, outside except through modes such as Keywords matching, decision tree or neural networks, for
The relevant status data of failure carries out clustering, can also be gathered using other modes pair status data relevant to failure
Alanysis, the application are not limited.
In one exemplary embodiment, the current status data according to the equipment and the failure distributed mode
Type obtains the failure predication result of the equipment, comprising:
Status data in the current status data of the equipment and the model of failure distribution is compared；
According to the comparison result of the status data in the current status data of the equipment and the model of failure distribution, obtain
Obtain the failure predication result of the equipment.
In one exemplary embodiment, the current status data and the model of failure distribution according to the equipment
In status data comparison result, obtain the failure predication result of the equipment, comprising:
When there is status data consistent with the current status data of the equipment in the model of failure distribution, obtain
Fault type corresponding with the status data and fault rate in the model of failure distribution.
In the present embodiment, by screening to collected status data, status data relevant to failure is obtained；
The association between status data relevant to failure, fault type and fault rate is obtained using default rule to close
System；According to the incidence relation, model of failure distribution is generated；Obtain the current status data of equipment；According to working as the equipment
Preceding status data and the model of failure distribution obtain the failure predication of the equipment as a result, it is possible to in data center
Equipment fault is predicted, ensures the stable operation of equipment, reduces failure and bring loss occurs.
Above-mentioned failure prediction method is further described with concrete application example below.
Step 1: in the scheduled one week time, the daily status data of acquisition server internal fan, to collected state
Data are screened, and wherein the status data of fan includes the performance data, running state data and daily record data of fan, root
According to the historical state data and the failure degree of correlation of fan, the status data of acquisition is screened, is filtered out from status data
The high status data with the failure degree of correlation: rotation speed of the fan.
Step 2: the incidence relation of historical state data and failure according to the pre-stored data passes through Keywords matching, decision
Tree or neural network fashion carry out clustering to the status data relevant to failure, obtain described relevant to failure
Incidence relation between status data, fault type and fault rate.
Step 3: being closed according to the association between status data relevant to failure, fault type and fault rate
System generates the three-dimensional failure distribution map between status data, fault type and fault rate.
Step 4: obtaining current status data-fan current rotating speed of server internal fan；
Step 5: by between the current rotating speed of fan and above-mentioned status data, fault type and fault rate
Status data in three-dimensional failure distribution map compares, consistent with current status data when being stored in above-mentioned failure distribution map
Status data when, obtain failure distribution map in fault type corresponding with the status data and fault rate.Such as wind
The rated speed of fan is 5000RPM/s, when the current rotating speed of fan is rotation speed of the fan 1000RPM/s, according to above-mentioned three-dimensional failure
Distribution map, available: fault type is fan failure, and the probability to break down is 80%.In another example the rated speed of fan
For 5000RPM/s, when the current rotating speed of fan is 7000RPM/s, according to three-dimensional failure distribution map, available three differences
Fault type and its corresponding fault rate: first fault type is cooling system failure (air-conditioning etc.), this therefore
The probability that barrier occurs is 50%；Second failure type is fan failure, this fault rate is 30%；Third failure classes
Type is sensor fault, this fault rate is 10%.That is when rotation speed of the fan is 7000RPM/s, server can
Three kinds of failures can occur.
Fig. 3 is the fault prediction device of the embodiment of the present invention, including memory 10 and processor 20.
Memory 10, for storing computer-readable instruction；
Processor 20, for executing the computer-readable instruction, to perform the following operations:
The status data in the equipment in the predetermined time is acquired, collected status data is screened, is obtained and event
Hinder relevant status data；
Using default rule obtain the status data relevant to failure, fault type and fault rate it
Between incidence relation；
According to the incidence relation, model of failure distribution is generated；
Obtain the current status data of the equipment；
According to the current status data of the equipment and the model of failure distribution, the failure predication of the equipment is obtained
As a result.
In one exemplary embodiment, the status data of the equipment includes: one or more parts of the equipment
Performance data, running state data and daily record data.
In one exemplary embodiment, described that collected status data is screened, it obtains relevant to failure
Status data, comprising: from the performance data, running state data and daily record data of one or more parts of the equipment,
According to the statistical result to historical state data and the failure degree of correlation, filter out pre- for failure with the high data of the failure degree of correlation
It surveys.
In one exemplary embodiment, the status data relevant to failure, failure are obtained using default rule
Incidence relation between type and fault rate, comprising:
The incidence relation of historical state data and failure according to the pre-stored data, passes through Keywords matching, decision tree or mind
Through network mode, clustering is carried out to the status data relevant to failure, obtains the status number relevant to failure
According to the incidence relation between, fault type and fault rate.
In one exemplary embodiment, the current status data according to the equipment and the failure distributed mode
Type obtains the failure predication result of the equipment, comprising:
Status data in the current status data of the equipment and the model of failure distribution is compared；
According to the comparison result of the status data in the current status data of the equipment and the model of failure distribution, obtain
Obtain the failure predication result of the equipment.
In one exemplary embodiment, the current status data and the model of failure distribution according to the equipment
In status data comparison result, obtain the failure predication result of the equipment, comprising:
When there is status data consistent with the current status data of the equipment in the model of failure distribution, obtain
Fault type corresponding with the status data and fault rate in the model of failure distribution.
Other realization details of Installation practice can be found in embodiment of the method above.
Those of ordinary skill in the art will appreciate that all or part of the steps in the above method can be instructed by program
Related hardware is completed, and described program can store in computer readable storage medium, such as read-only memory, disk or CD
Deng.Optionally, one or more integrated circuits can be used also to realize in all or part of the steps of above-described embodiment.Accordingly
Ground, each module/unit in above-described embodiment can take the form of hardware realization, can also use the shape of software function module
Formula is realized.The present invention is not limited to the combinations of the hardware and software of any particular form.
The above is only a preferred embodiment of the present invention, and certainly, the invention may also have other embodiments, without departing substantially from this
In the case where spirit and its essence, those skilled in the art make various corresponding changes in accordance with the present invention
And deformation, but these corresponding changes and modifications all should fall within the scope of protection of the appended claims of the present invention.
Claims (12)
1. a kind of failure prediction method characterized by comprising
The status data for acquiring the equipment in the predetermined time, screens collected status data, obtains related to failure
Status data；
It is obtained using default rule described between status data relevant to failure, fault type and fault rate
Incidence relation；
According to the incidence relation, model of failure distribution is generated；
Obtain the current status data of the equipment；
According to the current status data of the equipment and the model of failure distribution, the failure predication knot of the equipment is obtained
Fruit.
2. the method according to claim 1, wherein the status data of the equipment includes: the one of the equipment
A or multiple portions performance datas, running state data and daily record data.
3. according to the method described in claim 2, obtaining it is characterized in that, described screen collected status data
Status data relevant to failure, comprising: from the performance data of one or more parts of the equipment, running state data and
In daily record data, according to the statistical result to historical state data and the failure degree of correlation, the number high with the failure degree of correlation is filtered out
According to for failure predication.
4. according to claim 1 to method described in 3 any one, which is characterized in that using default rule obtain it is described with
Incidence relation between the relevant status data of failure, fault type and fault rate, comprising:
The incidence relation of historical state data and failure according to the pre-stored data, passes through Keywords matching, decision tree or nerve net
Network mode carries out clustering to the status data relevant to failure, obtains the status data relevant to failure, event
Hinder the incidence relation between type and fault rate.
5. the method according to claim 1, wherein the current status data and institute according to the equipment
Model of failure distribution is stated, the failure predication result of the equipment is obtained, comprising:
Status data in the current status data of the equipment and the model of failure distribution is compared；
According to the comparison result of the status data in the current status data of the equipment and the model of failure distribution, institute is obtained
State the failure predication result of equipment.
6. according to the method described in claim 5, it is characterized in that, the current status data according to the equipment and described
The comparison result of status data in model of failure distribution obtains the failure predication result of the equipment, comprising:
When there is status data consistent with the current status data of the equipment in the model of failure distribution, described in acquisition
Fault type corresponding with the status data and fault rate in model of failure distribution.
7. a kind of failure presets device, including memory and processor；It is characterized by:
The memory, for storing computer-readable instruction；
The processor, for executing the computer-readable instruction, to perform the following operations:
The status data in the equipment in the predetermined time is acquired, collected status data is screened, is obtained and failure phase
The status data of pass；
It is obtained using default rule described between status data relevant to failure, fault type and fault rate
Incidence relation；
According to the incidence relation, model of failure distribution is generated；
Obtain the current status data of the equipment；
According to the current status data of the equipment and the model of failure distribution, the failure predication knot of the equipment is obtained
Fruit.
8. device according to claim 7, which is characterized in that the status data of the equipment includes: the one of the equipment
A or multiple portions performance datas, running state data and daily record data.
9. device according to claim 8, which is characterized in that it is described that collected status data is screened, it obtains
Status data relevant to failure, comprising: from the performance data of one or more parts of the equipment, running state data and
In daily record data, according to the statistical result to historical state data and the failure degree of correlation, the number high with the failure degree of correlation is filtered out
According to for failure predication.
10. according to device described in any one of claim 7 to 9, which is characterized in that using default rule obtain it is described with
Incidence relation between the relevant status data of failure, fault type and fault rate, comprising:
The incidence relation of historical state data and failure according to the pre-stored data, passes through Keywords matching, decision tree or nerve net
Network mode carries out clustering to the status data relevant to failure, obtains the status data relevant to failure, event
Hinder the incidence relation between type and fault rate.
11. device according to claim 7, which is characterized in that the current status data according to the equipment and
The model of failure distribution obtains the failure predication result of the equipment, comprising:
Status data in the current status data of the equipment and the model of failure distribution is compared；
According to the comparison result of the status data in the current status data of the equipment and the model of failure distribution, institute is obtained
State the failure predication result of equipment.
12. device according to claim 11, which is characterized in that the current status data and institute according to the equipment
The comparison result for stating the status data in model of failure distribution obtains the failure predication result of the equipment, comprising:
When there is status data consistent with the current status data of the equipment in the model of failure distribution, described in acquisition
Fault type corresponding with the status data and fault rate in model of failure distribution.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910580238.9A CN110377445A (en) | 2019-06-28 | 2019-06-28 | Failure prediction method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910580238.9A CN110377445A (en) | 2019-06-28 | 2019-06-28 | Failure prediction method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110377445A true CN110377445A (en) | 2019-10-25 |
Family
ID=68251314
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910580238.9A Withdrawn CN110377445A (en) | 2019-06-28 | 2019-06-28 | Failure prediction method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110377445A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108919776A (en) * | 2018-06-19 | 2018-11-30 | 深圳市元征科技股份有限公司 | A kind of assessment of failure method and terminal |
| CN111865699A (en) * | 2020-07-31 | 2020-10-30 | 中国工商银行股份有限公司 | Fault identification method and device, computing equipment and medium |
| CN112612679A (en) * | 2020-12-29 | 2021-04-06 | 太平金融科技服务（上海）有限公司 | System running state monitoring method and device, computer equipment and storage medium |
-
2019
- 2019-06-28 CN CN201910580238.9A patent/CN110377445A/en not_active Withdrawn
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108919776A (en) * | 2018-06-19 | 2018-11-30 | 深圳市元征科技股份有限公司 | A kind of assessment of failure method and terminal |
| CN108919776B (en) * | 2018-06-19 | 2021-04-09 | 深圳市元征科技股份有限公司 | Fault assessment method and terminal |
| CN111865699A (en) * | 2020-07-31 | 2020-10-30 | 中国工商银行股份有限公司 | Fault identification method and device, computing equipment and medium |
| CN112612679A (en) * | 2020-12-29 | 2021-04-06 | 太平金融科技服务（上海）有限公司 | System running state monitoring method and device, computer equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11818196B2 (en) | Method and apparatus for predicting experience degradation events in microservice-based applications | |
| US11526511B1 (en) | Monitoring interface for information technology environment | |
| Zhang et al. | Data stream clustering with affinity propagation | |
| CN107666410B (en) | Network security analysis system and method | |
| US11671312B2 (en) | Service detail monitoring console | |
| US10235638B2 (en) | Adaptive key performance indicator thresholds | |
| CN103354924B (en) | For monitoring the method and system of performance indications | |
| US20170329462A1 (en) | Graphical user interface for static and adaptive thresholds | |
| CN110377445A (en) | Failure prediction method and device | |
| US8260622B2 (en) | Compliant-based service level objectives | |
| US20160292611A1 (en) | System Monitoring with Key Performance Indicators from Shared Base Search of Machine Data | |
| US8265973B2 (en) | Analytic-based scaling of information technology resources | |
| US9093841B2 (en) | Power distribution network event correlation and analysis | |
| US20210097431A1 (en) | Debugging and profiling of machine learning model training | |
| US8209410B2 (en) | System and method for storage management | |
| CN109992473A (en) | Monitoring method, device, equipment and the storage medium of application system | |
| US10956293B2 (en) | Automated process performance determination | |
| US20150066813A1 (en) | Outage window scheduler tool | |
| CN104462612A (en) | Method and device for monitoring database information | |
| CN108492150A (en) | The determination method and system of entity temperature | |
| CN114302103A (en) | Intelligent monitoring operation and maintenance system | |
| US10574552B2 (en) | Operation of data network | |
| CN114443441B (en) | Storage system management method, device and equipment and readable storage medium | |
| US11468365B2 (en) | GPU code injection to summarize machine learning training data | |
| US20220413982A1 (en) | Event and incident timelines |
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 | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20191025 |