CN108089962A - A kind of method for detecting abnormality, device and electronic equipment - Google Patents
A kind of method for detecting abnormality, device and electronic equipment Download PDFInfo
- Publication number
- CN108089962A CN108089962A CN201711116162.1A CN201711116162A CN108089962A CN 108089962 A CN108089962 A CN 108089962A CN 201711116162 A CN201711116162 A CN 201711116162A CN 108089962 A CN108089962 A CN 108089962A
- Authority
- CN
- China
- Prior art keywords
- current
- index
- monitored
- value
- time
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/3065—Monitoring arrangements determined by the means or processing involved in reporting the monitored data
- G06F11/3072—Monitoring arrangements determined by the means or processing involved in reporting the monitored data where the reporting involves data filtering, e.g. pattern matching, time or event triggered, adaptive or policy-based reporting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Quality & Reliability (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
An embodiment of the present invention provides a kind of method for detecting abnormality, device and electronic equipment, applied to Internet technical field, the described method includes：Obtain current actual value of the index to be monitored at current time；According to the time recurrent neural networks model pre-established and current time, index to be monitored is obtained in current time corresponding current predicted value, and time recurrent neural networks model is established according to the history actual value of index to be monitored；Using the difference of current actual value and current predicted value as current prediction error, judge current prediction error whether in preset threshold range；If judging current prediction error not in preset threshold range, determine that index to be monitored is abnormal at current time.The embodiment of the present invention is treated monitor control index by time recurrent neural networks model and is predicted, the current predicted value at obtained current time and current actual value are compared, the adaptive ability of abnormality detection is improved, so as to improve the accuracy of abnormality detection.
Description
Technical field
The present invention relates to Internet technical field, more particularly to a kind of method for detecting abnormality, device and electronic equipment.
Background technology
In system O＆M, the problem of Key Performance Indicator is one critically important is monitored, by monitoring Key Performance Indicator
It can note abnormalities in time, warning message is concurrently sent to give system maintenance personnel.In practice, it is different in Key Performance Indicator monitoring
Often detection mainly sets fixed alarm threshold value to realize by operation maintenance personnel.Specifically, when the key performance of monitoring refers to
When mark is more than the alarm threshold value, system labels it as exception, and sends warning message.
However, inventor has found in the implementation of the present invention, at least there are the following problems for the prior art：The pass of monitoring
Key performance indicator is usually influenced by many factors, in the case of affected by many factors, the Key Performance Indicator of monitoring
Value is unstable；If alarm threshold value is arranged to fixed value, then, the wrong report of warning message can be caused.Therefore, it is existing different
The accuracy rate of normal detection method is than relatively low.
The content of the invention
The embodiment of the present invention is designed to provide a kind of method for detecting abnormality, device and electronic equipment, to improve exception
The accuracy rate of detection.Specific technical solution is as follows：
An embodiment of the present invention provides a kind of method for detecting abnormality, the described method includes：
Obtain current actual value of the index to be monitored at current time；
According to the time recurrent neural networks model and the current time pre-established, the index to be monitored is obtained
In the current time corresponding current predicted value, the time recurrent neural networks model is existed according to the index to be monitored
What the history actual value of historical juncture was established；
Using the difference of the current actual value and the current predicted value as current prediction error, judge described current pre-
Error is surveyed whether in preset threshold range；
If judging the current prediction error not in the preset threshold range, determine the index to be monitored described
Current time is abnormal.
Optionally, the method for building up of the time recurrent neural networks model includes：
The index to be monitored is obtained in corresponding history actual value of multiple historical junctures；
Time recurrent neural is carried out to the multiple historical juncture and corresponding history actual value of the multiple historical juncture
Network training obtains time recurrent neural networks model；Wherein, the time recurrent neural networks model includes：Moment and institute
State the correspondence of finger target value to be monitored.
Optionally, the definite method of the preset threshold range includes：
The index to be monitored is obtained in other multiple historical junctures corresponding history actual value, other the multiple history
Moment is different from the multiple historical juncture；
According to the time recurrent neural networks model and other the multiple historical junctures, the finger to be monitored is obtained
It is marked on other the multiple historical junctures corresponding historical forecast value；
It goes through other the multiple historical junctures corresponding history actual value is corresponding with other the multiple historical junctures
The difference of history predicted value is fitted the error sample, determines preset threshold range as error sample.
Optionally, it is described that the error sample is fitted, determine preset threshold range, including：
The error sample is fitted by Gauss model, obtains the average and standard deviation of Gauss model；
Based on the average and the standard deviation, the upper limit value and lower limiting value of preset threshold range are determined.
Optionally, if described judge the current prediction error not in the preset threshold range, determine described to wait to supervise
Control index is abnormal at the current time, including：
If judging, the current prediction error is more than the upper limit value of the preset threshold range, determines the index to be monitored
It is abnormal and uprushes at the current time；Or,
If judging, the current prediction error is less than the lower limiting value of the preset threshold range, determines the index to be monitored
Anticlimax is abnormal at the current time.
Optionally, if judging the current prediction error not in the preset threshold range described, described treat is determined
After the current time is abnormal, the method further includes monitor control index：
Send warning message.
An embodiment of the present invention provides a kind of abnormal detector, described device includes：
Current actual value acquisition module, for obtaining current actual value of the index to be monitored at current time；
Current predicted value acquisition module, for according to the time recurrent neural networks model that pre-establishes and described current
Moment obtains the index to be monitored in the current time corresponding current predicted value, the time recurrent neural network mould
Type is established according to history actual value of the index to be monitored in the historical juncture；
Judgment module, for using the difference of the current actual value and the current predicted value as current prediction error,
Judge the current prediction error whether in preset threshold range；
Abnormal determining module, for when the judging result of the judgment module is no, determining that the index to be monitored exists
The current time is abnormal.
Optionally, the abnormal detector of the embodiment of the present invention, further includes：
First history actual value acquisition module, for obtaining the index to be monitored in corresponding history of multiple historical junctures
Actual value；
Time recurrent neural networks model establishes module, for the multiple historical juncture and the multiple historical juncture
Corresponding history actual value carries out time recurrent neural network training, obtains time recurrent neural networks model；Wherein, when described
Between recurrent neural networks model include：Moment and the correspondence to be monitored for referring to target value.
Optionally, the abnormal detector of the embodiment of the present invention, further includes：
Second history actual value acquisition module, it is corresponding in other multiple historical junctures for obtaining the index to be monitored
History actual value, other the multiple historical junctures are different from the multiple historical juncture；
Historical forecast value acquisition module, for being gone through according to the time recurrent neural networks model and the multiple other
The history moment obtains the index to be monitored in other the multiple historical junctures corresponding historical forecast value；
Preset threshold range determining module, for by other the multiple historical junctures corresponding history actual value with it is described
The difference of multiple other historical junctures corresponding historical forecast value is fitted the error sample, really as error sample
Determine preset threshold range.
Optionally, the preset threshold range determining module is specifically used for, by Gauss model to the error sample into
Row fitting, obtains the average and standard deviation of Gauss model；Based on the average and the standard deviation, preset threshold range is determined
Upper limit value and lower limiting value.
Optionally, the abnormal determining module is specifically used for, if judging, the current prediction error is more than the default threshold
It is worth the upper limit value of scope, determines that the index to be monitored is abnormal at the current time and uprush；If or, judge described current
It predicts that error is less than the lower limiting value of the preset threshold range, determines that the index to be monitored is abnormal at the current time
Anticlimax.
Optionally, the abnormal detector of the embodiment of the present invention, further includes：
Warning message sending module, for sending warning message.
The embodiment of the present invention additionally provides a kind of electronic equipment, including：Processor, communication interface, memory and communication are total
Line, wherein, the processor, the communication interface, the memory complete mutual communication by the communication bus；
The memory, for storing computer program；
The processor during for performing the program stored on the memory, realizes any of the above-described exception
The step of detection method.
At the another aspect that the present invention is implemented, a kind of computer readable storage medium is additionally provided, it is described computer-readable
Instruction is stored in storage medium, when run on a computer so that computer performs any of the above-described abnormal inspection
The step of survey method.
At the another aspect that the present invention is implemented, the embodiment of the present invention additionally provides a kind of computer program production comprising instruction
Product, when run on a computer so that computer performs the step of any of the above-described described method for detecting abnormality.
Method for detecting abnormality provided in an embodiment of the present invention, device and electronic equipment are being worked as by obtaining index to be monitored
The current actual value at preceding moment；According to the time recurrent neural networks model pre-established and current time, obtain to be monitored
Index is in the current predicted value at current time；Using the difference of current actual value and current predicted value as current prediction error, sentence
Whether disconnected current prediction error is in preset threshold range；If judging current prediction error not in preset threshold range, determine
Index to be monitored is abnormal at current time.The embodiment of the present invention passes through the time recurrent neural networks model pair that pre-establishes
Index to be monitored is predicted, obtained current predicted value and current actual value are compared, if judging obtained error not
In preset threshold range, it is determined that index to be monitored is abnormal at current time.Due to time recurrent neural networks model
It is to be established according to history actual value of the index to be monitored in the historical juncture, in this way, pre- according to time recurrent neural networks model
Current time is surveyed, the adaptive ability of abnormality detection is improved, so as to improve the accuracy of abnormality detection.Certainly, this is implemented
Any product or method of invention must be not necessarily required to reach all the above advantage simultaneously.
Description of the drawings
It in order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
There is attached drawing needed in technology description to be briefly described.
Fig. 1 is a kind of flow chart of the method for detecting abnormality of the embodiment of the present invention；
Fig. 2 is the flow chart of the time recurrent neural networks model method for building up of the embodiment of the present invention；
Fig. 3 is the flow chart of the definite method of the preset threshold range of the embodiment of the present invention；
Fig. 4 is a kind of structure chart of the abnormal detector of the embodiment of the present invention；
Fig. 5 is another structure chart of the abnormal detector of the embodiment of the present invention；
Fig. 6 is another structure chart of the abnormal detector of the embodiment of the present invention；
Fig. 7 is the structure chart of the electronic equipment of the embodiment of the present invention.
Specific embodiment
Below in conjunction with the attached drawing in the embodiment of the present invention, the technical solution in the embodiment of the present invention is described.
In order to solve the problems, such as that abnormality detection accuracy rate is low in the prior art, an embodiment of the present invention provides a kind of abnormal inspections
Method, apparatus and electronic equipment are surveyed, to improve the accuracy rate of abnormality detection.
Referring to Fig. 1, Fig. 1 is a kind of flow chart of the method for detecting abnormality of the embodiment of the present invention, is comprised the following steps：
S101 obtains current actual value of the index to be monitored at current time.
In general, in order to determine system whether normal operation, it is necessary to be monitored to some indexs in system, finger to be monitored
Mark, which refers to system maintenance personnel, needs index in the system that monitors, and the index to be monitored in different system can be different, treat
Monitor control index includes：Message transmission rate, network bandwidth, signal strength etc..Index to be monitored can be obtained by survey tool,
And the size of desired value to be monitored can represent the power or size of index to be monitored.Generally, detecting index to be monitored is
No exception refers to whether detection index to be monitored is abnormal at current time, then, in order to detect index to be monitored when current
Carve whether abnormal, it is necessary to obtain value of the index to be monitored at current time in real time by survey tool, i.e., current actual value.
S102 according to the time recurrent neural networks model pre-established and current time, obtains index to be monitored and exists
Current time corresponding current predicted value, time recurrent neural networks model are the history in the historical juncture according to index to be monitored
What actual value was established.
In the embodiment of the present invention, time recurrent neural networks model is by corresponding to each historical juncture in time series
History actual value is trained, for example, can pass through LSTM (Long Short Term Memory, shot and long term memory)
Network is trained historical juncture corresponding history actual value.LSTM is a kind of time recurrent neural network, is suitable for handling
The relatively long important information with time interval in predicted time sequence and delay.LSTM changes note in very accurate way
Recall, remember, update, focus on information using special study mechanism, so contribute to tracking information in longer in the period of.
Therefore, by settling time recurrent neural networks model, index to be monitored can be obtained in corresponding value of each moment.It in this way, will
Input time at current time recurrent neural networks model, you can current time corresponding current predicted value is obtained, according to current pre-
Measured value carries out abnormality detection to treat monitor control index.
S103 using the difference of current actual value and current predicted value as current prediction error, judges current prediction error
Whether in preset threshold range.
In the embodiment of the present invention, current actual value is the value by measuring in real time, and current predicted value is to pass through the time
What recurrent neural networks model was predicted.Obviously, current actual value can incite somebody to action current with current predicted value there are error
Whether the difference of actual value and current predicted value judges the current prediction error in preset threshold range as current prediction error
It is interior.Preset threshold range is pre-set numberical range, which represents current actual value and current predicted value
Difference acceptable scope, preset threshold range can set based on experience value, can also pass through to calculate and obtain, specific to count
Calculation method will be introduced below, and details are not described herein.
S104 if judging current prediction error not in preset threshold range, determines that index to be monitored is sent out at current time
It is raw abnormal.
Specifically, if current prediction error not in preset threshold range, represents current actual value and current predicted value
Difference is excessive.Current predicted value is the predicted value predicted according to time recurrent neural networks model, the current predicted value category
In theoretical value, then, difference is excessive to show exception occur by measuring obtained current actual value, i.e., index to be monitored is current
Moment is abnormal.
S105 if judging current prediction error in preset threshold range, determines that index to be monitored is not sent out at current time
It is raw abnormal.
Certainly, if current prediction error is in preset threshold range, the difference of current actual value and current predicted value is represented
Within the acceptable range, it is not abnormal.
Method for detecting abnormality provided in an embodiment of the present invention, it is current true at current time by obtaining index to be monitored
Value；According to the time recurrent neural networks model pre-established and current time, index to be monitored is obtained at current time
Current predicted value；Using the difference of current actual value and current predicted value as current prediction error, judge that current prediction error is
It is no in preset threshold range；If current prediction error not in preset threshold range, determines index to be monitored at current time
It is abnormal.The embodiment of the present invention is treated monitor control index by the time recurrent neural networks model pre-established and is predicted,
Obtained current predicted value and current actual value are compared, if judging obtained error not in preset threshold range,
Determine that index to be monitored is abnormal at current time.Since time recurrent neural networks model is being gone through according to index to be monitored
What the history actual value at history moment was established, in this way, predicting current time according to time recurrent neural networks model, improve exception
The adaptive ability of detection, so as to improve the accuracy of abnormality detection.
The method for building up of time recurrent neural networks model can be found in Fig. 2 in Fig. 1 embodiments S102, and Fig. 2 is real for the present invention
The flow chart of the time recurrent neural networks model method for building up of example is applied, is comprised the following steps：
S201 obtains index to be monitored in corresponding history actual value of multiple historical junctures.
In the embodiment of the present invention, treat monitor control index carry out prediction refer to predicting index to be monitored in future time instance
Value, then, it is necessary to index to be monitored is obtained in corresponding history actual value of multiple historical junctures, it is pre- according to multiple history actual values
Survey value of the index to be monitored in future time instance.Future time instance is at the time of having not occurred, and only when future time instance reaches, just may be used
To obtain the current actual value of current time (future time instance becomes current time) index to be monitored by the method for measurement.
Wherein, multiple historical junctures are multiple historical junctures in a period, which can be one month, half
A month, week etc., the period can be chosen according to the stability of index to be monitored.For example, index to be monitored is stablized, it is short
History actual value in period can predict future time instance exactly, then obtain multiple historical junctures pair in a week
The history actual value answered；Alternatively, index to be monitored is unstable, the history actual value in short time period cannot be predicted exactly at this time
Future time instance can obtain the corresponding history actual value of multiple historical junctures in one month.
S202 carries out time recurrent neural network to multiple historical junctures and corresponding history actual value of multiple historical junctures
Training, obtains time recurrent neural networks model；Wherein, time recurrent neural networks model includes：Moment and index to be monitored
Value correspondence.
Specifically, index to be monitored is obtained in corresponding history actual value of multiple historical junctures to get to the historical juncture
With the correspondence of history actual value, historical juncture and history actual value can be instructed by time recurrent neural network
Practice, obtain time recurrent neural networks model.So, the time recurrent neural networks model obtained includes：Moment and to be monitored
Refer to the correspondence of target value, that is to say, that can will input the time recurrent neural networks model any time, and obtain this
Meaning moment finger target value to be monitored.In general, any time refers to the future time instance having not occurred.
Method for detecting abnormality provided in an embodiment of the present invention, by corresponding to multiple historical junctures and multiple historical junctures
History actual value carries out time recurrent neural network training, obtains time recurrent neural networks model.Afterwards, when can be by this
Between recurrent neural networks model treat monitor control index and predicted.
The definite method of preset threshold range can be found in Fig. 3 in Fig. 1 embodiments S103, and Fig. 3 is the pre- of the embodiment of the present invention
If the flow chart of the definite method of threshold range, comprises the following steps：
S301 obtains index to be monitored in other multiple historical junctures corresponding history actual value, other multiple history
It carves different from multiple historical junctures.
In the embodiment of the present invention, other multiple historical junctures are different from multiple historical junctures in Fig. 2 embodiments S201
At the time of, the choosing method of other multiple historical junctures can be identical with the choosing method of multiple historical junctures, for example, it may be
Other multiple historical junctures in one month, if multiple historical junctures are August parts, other multiple historical junctures can be with
At the time of being July, other multiple historical junctures corresponding history actual value is obtained, that is, the multiple history for obtaining July are true
Value.
S302 according to time recurrent neural networks model and other multiple historical junctures, obtains index to be monitored more
A other historical junctures corresponding historical forecast value.
From the time recurrent neural networks model established in Fig. 2 embodiments S202, can be obtained by any time
Any time corresponding finger target value to be monitored, certainly, which can also be the historical juncture, by other multiple history
It is pre- in other multiple historical junctures corresponding history can to obtain index to be monitored for input time at moment recurrent neural networks model
Measured value.
S303, other multiple historical junctures corresponding history actual value history corresponding with other multiple historical junctures is pre-
The difference of measured value is fitted error sample, determines preset threshold range as error sample.
In the embodiment of the present invention, multiple other historical junctures corresponding history actual values and other multiple historical junctures correspond to
Historical forecast value there are certain error, during by other multiple historical junctures corresponding history actual value and other multiple history
It carves corresponding historical forecast value to subtract each other, multiple differences can be obtained.Using obtained multiple differences as error sample, then to by mistake
Difference sample is fitted, and determines the maximum and minimum value of error, you can obtains preset threshold range, preset threshold range is one
A numberical range, including upper limit value and lower limiting value, upper limit value is the maximum of error, and lower limiting value is the minimum value of error.
Method for detecting abnormality provided in an embodiment of the present invention, by calculating index to be monitored in other multiple historical junctures pair
The history actual value answered and, other multiple history for being obtained by time recurrent neural networks model and other multiple historical junctures
The difference of moment corresponding historical forecast value, and according to obtained error sample, determine preset threshold range.In this way, it is determining
After preset threshold range, can monitor control index be treated according to the preset threshold range and be detected, improve abnormality detection
Adaptive ability, so as to improve the accuracy of abnormality detection.
In a kind of realization method of the present invention, after Fig. 1 embodiments S104, warning message is sent.
In the embodiment of the present invention, after definite index to be monitored is abnormal, warning message can be sent and tieed up to system
Shield personnel.The form of warning message can be short message, mail etc., in this way, system maintenance personnel can have found that system occurs in time
It is abnormal, and corresponding treatment measures are made, improve the stability of system.
In a kind of realization method of the present invention, in Fig. 3 embodiments S303, error sample is fitted, determines default threshold
It is worth scope, comprises the following steps：
The first step is fitted error sample by Gauss model, obtains the average and standard deviation of Gauss model.
Specifically, Gauss model accurately quantifies things by Gaussian probability-density function (normal distribution curve), by one
A things is decomposed into several models formed based on normal distribution curve.In the embodiment of the present invention, the average of Gauss model is to miss
The average value of difference sample, variance are the average of the square value of the difference of each sample value and average, and standard deviation is the arithmetic of variance
Square root, standard deviation refer to the amplitude that statistical result fluctuates within some period above and below error, are the important ginsengs of normal distribution
One of number.Standard deviation is widely used in the fields such as error theory, quality management, Metrological AFM.
Second step based on average and standard deviation, determines the upper limit value and lower limiting value of preset threshold range.
For normal distribution, the usually sample value there are about 68% is distributed in the scope within 1 standard deviation of average, about
95% sample value is distributed in the scope within 2 standard deviations of average, and about 99.7% sample value is distributed in apart from average 3
Scope within a standard deviation, it is above-mentioned to be known as " 68-95-99.7 rules " or " rule of thumb ".In the embodiment of the present invention, Ke Yigen
According to 1 times of standard deviation, 2 times of standard deviations and 3 times of standard deviations etc., the upper limit value and lower limiting value of preset threshold range are determined.If for example,
Average is μ, and standard deviation σ, preset threshold range is (μ-σ, μ+σ), (+2 σ of μ -2 σ, μ), (+2 σ of μ -2 σ, μ) etc..In this way, according to
The error that historical juncture obtains determines preset threshold range, so as to more accurately judge the error at current time, Jin Erti
The accuracy of high abnormality detection.
In a kind of realization method of the present invention, in Fig. 1 embodiments S104, if judging current prediction error not in predetermined threshold value
In the range of, determine that index to be monitored is abnormal at current time, including：
If judging, current prediction error is more than the upper limit value of preset threshold range, determines that index to be monitored is sent out at current time
Raw exception is uprushed；Or,
If judging, current prediction error is less than the lower limiting value of preset threshold range, determines that index to be monitored is sent out at current time
Raw exception anticlimax.
In the embodiment of the present invention, the difference of current actual value and current predicted value can be that current actual value subtracts currently in advance
Measured value, if judging, obtained current prediction error is more than the upper limit value of preset threshold range, shows that current actual value is much larger than and works as
Preceding predicted value, then determine that index to be monitored is abnormal at current time and uprush.If alternatively, judge that obtained current predictive misses
Difference is less than the lower limiting value of preset threshold range, shows that current actual value is much smaller than current predicted value, then determine index to be monitored
Anticlimax is abnormal at current time.In this way, abnormal type can be determined more specifically, correspondingly, can send different
Warning message, system maintenance personnel can determine which kind of exception has occurred.
Corresponding to above method embodiment, the embodiment of the present invention additionally provides a kind of abnormal detector, referring to Fig. 4, Fig. 4
For a kind of structure chart of the abnormal detector of the embodiment of the present invention, including：
Current actual value acquisition module 401, for obtaining current actual value of the index to be monitored at current time；
Current predicted value acquisition module 402, for according to the time recurrent neural networks model pre-established and currently
Moment obtains index to be monitored in current time corresponding current predicted value, and time recurrent neural networks model is that basis is waited to supervise
Control what history actual value of the index in the historical juncture was established；
Judgment module 403, for using the difference of current actual value and current predicted value as current prediction error, judging to work as
Whether preceding prediction error is in preset threshold range；
Abnormal determining module 404, for when the judging result of judgment module is no, determining index to be monitored when current
Quarter is abnormal.
Abnormal detector provided in an embodiment of the present invention, it is current true at current time by obtaining index to be monitored
Value；According to the time recurrent neural networks model pre-established and current time, index to be monitored is obtained at current time
Current predicted value；Using the difference of current actual value and current predicted value as current prediction error, judge that current prediction error is
It is no in preset threshold range；If current prediction error not in preset threshold range, determines index to be monitored at current time
It is abnormal.The embodiment of the present invention is treated monitor control index by the time recurrent neural networks model pre-established and is predicted,
Current predicted value and current actual value are compared, if the error for judging to obtain is not in preset threshold range, it is determined that treat
Monitor control index is abnormal at current time.Since time recurrent neural networks model is in the historical juncture according to index to be monitored
History actual value establish, in this way, according to time recurrent neural networks model predict current time, improve abnormality detection
Adaptive ability, so as to improve the accuracy of abnormality detection.
It should be noted that the device of the embodiment of the present invention is the device using above-mentioned method for detecting abnormality, then it is above-mentioned different
All embodiments of normal detection method are suitable for the device, and can reach the same or similar advantageous effect.
Referring to Fig. 5, Fig. 5 is another structure chart of the abnormal detector of the embodiment of the present invention, including：
First history actual value acquisition module 501, for obtaining index to be monitored in corresponding history of multiple historical junctures
Actual value；
Time recurrent neural networks model establishes module 502, for multiple historical junctures and correspondence of multiple historical junctures
History actual value carry out time recurrent neural network training, obtain time recurrent neural networks model；Wherein, time recurrence god
Include through network model：Moment and the correspondence to be monitored for referring to target value.
Abnormal detector provided in an embodiment of the present invention, by corresponding to multiple historical junctures and multiple historical junctures
History actual value carries out time recurrent neural network training, obtains time recurrent neural networks model.Afterwards, when can be by this
Between recurrent neural networks model treat monitor control index and predicted.
Referring to Fig. 6, Fig. 6 is another structure chart of the abnormal detector of the embodiment of the present invention, including：
Second history actual value acquisition module 601, it is corresponding in other multiple historical junctures for obtaining index to be monitored
History actual value, other multiple historical junctures are different from multiple historical junctures；
Historical forecast value acquisition module 602, during for according to time recurrent neural networks model and other multiple history
It carves, obtains index to be monitored in other multiple historical junctures corresponding historical forecast value；
Preset threshold range determining module 603, for by other multiple historical junctures corresponding history actual value with it is multiple
The difference of other historical junctures corresponding historical forecast value is fitted error sample, determines default threshold as error sample
It is worth scope.
Abnormal detector provided in an embodiment of the present invention, by calculating index to be monitored in other multiple historical junctures pair
The history actual value answered and, other multiple history for being obtained by time recurrent neural networks model and other multiple historical junctures
The difference of moment corresponding historical forecast value, and according to obtained error sample, determine preset threshold range.In this way, it is determining
After preset threshold range, can monitor control index be treated according to the preset threshold range and be detected, improve abnormality detection
Adaptive ability, so as to improve the accuracy of abnormality detection.
In a kind of realization method of the present invention, abnormal detector further includes：
Warning message sending module, for sending warning message.
In a kind of realization method of the present invention, preset threshold range determining module is specifically used for, by Gauss model to by mistake
Difference sample is fitted, and obtains the average and standard deviation of Gauss model；Based on average and standard deviation, preset threshold range is determined
Upper limit value and lower limiting value.
In a kind of realization method of the present invention, abnormal determining module is specifically used for, if it is pre- to judge that current prediction error is more than
If the upper limit value of threshold range, determine that index to be monitored is abnormal at current time and uprush；If or, judge current prediction error
Less than the lower limiting value of preset threshold range, determine that index to be monitored is abnormal anticlimax at current time.
The embodiment of the present invention additionally provides a kind of electronic equipment, and referring to Fig. 7, Fig. 7 is the electronic equipment of the embodiment of the present invention
Structure chart, including：Processor 701, communication interface 702, memory 703 and communication bus 704, wherein, processor 701 leads to
Letter interface 702, memory 703 complete mutual communication by communication bus 704；
Memory 703, for storing computer program；
Processor 701 during for performing the program stored on memory 703, realizes any exception in above-described embodiment
The step of detection method.
It should be noted that the communication bus 704 that above-mentioned electronic equipment is mentioned can be PCI (Peripheral
Component Interconnect, Peripheral Component Interconnect standard) bus or EISA (Extended Industry Standard
Architecture, expanding the industrial standard structure) bus etc..The communication bus 704 can be divided into address bus, data/address bus,
Controlling bus etc..For ease of representing, only represented in Fig. 7 with a thick line, it is not intended that an only bus or a type
Bus.
Communication interface 702 is for the communication between above-mentioned electronic equipment and other equipment.
Memory 703 can include RAM (Random Access Memory, random access memory), can also include
Nonvolatile memory (non-volatile memory), for example, at least a magnetic disk storage.Optionally, memory may be used also
To be at least one storage device for being located remotely from aforementioned processor.
Above-mentioned processor 701 can be general processor, including：CPU (Central Processing Unit, center
Processor), NP (Network Processor, network processing unit) etc.；It can also be DSP (Digital Signal
Processing, digital signal processor), ASIC (Application Specific Integrated Circuit, it is special
Integrated circuit), FPGA (Field-Programmable Gate Array, field programmable gate array) or other are programmable
Logical device, discrete gate or transistor logic, discrete hardware components.
In the electronic equipment of the embodiment of the present invention, processor is by performing the program stored on memory, so as to pass through
Obtain current actual value of the index to be monitored at current time；According to the time recurrent neural networks model pre-established and work as
The preceding moment obtains current predicted value of the index to be monitored at current time；The difference of current actual value and current predicted value is made
For current prediction error, judge current prediction error whether in preset threshold range；If judge current prediction error not pre-
If in threshold range, determine that index to be monitored is abnormal at current time.The embodiment of the present invention passes through time for pre-establishing
Recurrent neural networks model is treated monitor control index and is predicted, obtained current predicted value and current actual value are compared,
If the error for judging to obtain is not in preset threshold range, it is determined that index to be monitored is abnormal at current time.Due to when
Between recurrent neural networks model be to be established according to history actual value of the index to be monitored in the historical juncture, in this way, according to the time
Recurrent neural networks model predicts current time, the adaptive ability of abnormality detection is improved, so as to improve abnormality detection
Accuracy.
In another embodiment provided by the invention, a kind of computer readable storage medium is additionally provided, which can
It reads to be stored with instruction in storage medium, when run on a computer so that computer performs any different in above-described embodiment
The step of normal detection method.
When the instruction stored in the computer readable storage medium of the embodiment of the present invention is run on computers, so as to pass through
Obtain current actual value of the index to be monitored at current time；According to the time recurrent neural networks model pre-established and work as
The preceding moment obtains current predicted value of the index to be monitored at current time；The difference of current actual value and current predicted value is made
For current prediction error, judge current prediction error whether in preset threshold range；If judge current prediction error not pre-
If in threshold range, determine that index to be monitored is abnormal at current time.The embodiment of the present invention passes through time for pre-establishing
Recurrent neural networks model is treated monitor control index and is predicted, obtained current predicted value and current actual value are compared,
If the error for judging to obtain is not in preset threshold range, it is determined that index to be monitored is abnormal at current time.Due to when
Between recurrent neural networks model be to be established according to history actual value of the index to be monitored in the historical juncture, in this way, according to the time
Recurrent neural networks model predicts current time, the adaptive ability of abnormality detection is improved, so as to improve abnormality detection
Accuracy.
In another embodiment provided by the invention, a kind of computer program product for including instruction is additionally provided, when it
When running on computers so that computer performs the step of any method for detecting abnormality in above-described embodiment.
As it can be seen that the computer program product of the embodiment of the present invention, when run on a computer, so as to be treated by obtaining
Monitor control index is in the current actual value at current time；According to the time recurrent neural networks model that pre-establishes and it is current when
It carves, obtains current predicted value of the index to be monitored at current time；Using the difference of current actual value and current predicted value as work as
Whether preceding prediction error judges current prediction error in preset threshold range；If judge current prediction error not in default threshold
In the range of value, determine that index to be monitored is abnormal at current time.The embodiment of the present invention passes through the time recurrence that pre-establishes
Neural network model is treated monitor control index and is predicted, obtained current predicted value and current actual value are compared, if sentencing
Disconnected obtained error is not in preset threshold range, it is determined that index to be monitored is abnormal at current time.Since the time passs
Returning neural network model is established according to history actual value of the index to be monitored in the historical juncture, in this way, according to time recurrence
Neural Network model predictive current time improves the adaptive ability of abnormality detection, so as to improve the accurate of abnormality detection
Property.
In the above-described embodiments, can come wholly or partly by software, hardware, firmware or its any combination real
It is existing.When implemented in software, can entirely or partly realize in the form of a computer program product.The computer program
Product includes one or more computer instructions.When loading on computers and performing the computer program instructions, all or
It partly generates according to the flow or function described in the embodiment of the present invention.The computer can be all-purpose computer, special meter
Calculation machine, computer network or other programmable devices.The computer instruction can be stored in computer readable storage medium
In or from a computer readable storage medium to another computer readable storage medium transmit, for example, the computer
Instruction can pass through wired (such as coaxial cable, optical fiber, number from a web-site, computer, server or data center
User's line (DSL)) or wireless (such as infrared, wireless, microwave etc.) mode to another web-site, computer, server or
Data center is transmitted.The computer readable storage medium can be any usable medium that computer can access or
It is the data storage devices such as server, the data center integrated comprising one or more usable mediums.The usable medium can be with
It is magnetic medium, (for example, floppy disk, hard disk, tape), optical medium (for example, DVD) or semiconductor medium (such as solid state disk
Solid State Disk (SSD)) etc..
It should be noted that herein, relational terms such as first and second and the like are used merely to a reality
Body or operation are distinguished with another entity or operation, are deposited without necessarily requiring or implying between these entities or operation
In any this actual relation or order.Moreover, term " comprising ", "comprising" or its any other variant are intended to
Non-exclusive inclusion, so that process, method, article or equipment including a series of elements not only will including those
Element, but also including other elements that are not explicitly listed or further include as this process, method, article or equipment
Intrinsic element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that
Also there are other identical elements in process, method, article or equipment including the element.
Each embodiment in this specification is described using relevant mode, identical similar portion between each embodiment
Point just to refer each other, and the highlights of each of the examples are difference from other examples.It is real especially for system
For applying example, since it is substantially similar to embodiment of the method, so description is fairly simple, related part is referring to embodiment of the method
Part explanation.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the scope of the present invention.It is all
Any modifications, equivalent replacements and improvements are made within the spirit and principles in the present invention, are all contained in protection scope of the present invention
It is interior.
Claims (11)
1. a kind of method for detecting abnormality, which is characterized in that the described method includes：
Obtain current actual value of the index to be monitored at current time；
According to the time recurrent neural networks model and the current time pre-established, the index to be monitored is obtained in institute
Current time corresponding current predicted value is stated, the time recurrent neural networks model is in history according to the index to be monitored
What the history actual value at moment was established；
Using the difference of the current actual value and the current predicted value as current prediction error, judge that the current predictive misses
Whether difference is in preset threshold range；
If judging the current prediction error not in the preset threshold range, determine the index to be monitored described current
Moment is abnormal.
2. method for detecting abnormality according to claim 1, which is characterized in that the time recurrent neural networks model is built
Cube method includes：
The index to be monitored is obtained in corresponding history actual value of multiple historical junctures；
Time recurrent neural network is carried out to the multiple historical juncture and corresponding history actual value of the multiple historical juncture
Training, obtains time recurrent neural networks model；Wherein, the time recurrent neural networks model includes：It moment and described treats
The correspondence of the value of monitor control index.
3. method for detecting abnormality according to claim 2, which is characterized in that the definite method bag of the preset threshold range
It includes：
The index to be monitored is obtained in other multiple historical junctures corresponding history actual value, other the multiple historical junctures
It is different from the multiple historical juncture；
According to the time recurrent neural networks model and other the multiple historical junctures, obtain the index to be monitored and exist
The multiple other historical junctures corresponding historical forecast value；
Other the multiple historical junctures corresponding history actual value history corresponding with other the multiple historical junctures is pre-
The difference of measured value is fitted the error sample, determines preset threshold range as error sample.
4. method for detecting abnormality according to claim 3, which is characterized in that it is described that the error sample is fitted,
Determine preset threshold range, including：
The error sample is fitted by Gauss model, obtains the average and standard deviation of Gauss model；
Based on the average and the standard deviation, the upper limit value and lower limiting value of preset threshold range are determined.
5. method for detecting abnormality according to claim 4, which is characterized in that if described judge the current prediction error not
In the preset threshold range, determine that the index to be monitored is abnormal at the current time, including：
If judging, the current prediction error is more than the upper limit value of the preset threshold range, determines the index to be monitored in institute
Stating current time is abnormal and uprushes；Or,
If judging, the current prediction error is less than the lower limiting value of the preset threshold range, determines the index to be monitored in institute
Stating current time is abnormal anticlimax.
6. a kind of abnormal detector, which is characterized in that described device includes：
Current actual value acquisition module, for obtaining current actual value of the index to be monitored at current time；
Current predicted value acquisition module, for according to the time recurrent neural networks model that pre-establishes and it is described current when
It carves, obtains the index to be monitored in the current time corresponding current predicted value, the time recurrent neural networks model
It is to be established according to history actual value of the index to be monitored in the historical juncture；
Judgment module, for using the difference of the current actual value and the current predicted value as current prediction error, judging
Whether the current prediction error is in preset threshold range；
Abnormal determining module, for when the judging result of the judgment module is no, determining the index to be monitored described
Current time is abnormal.
7. abnormal detector according to claim 6, which is characterized in that described device further includes：
First history actual value acquisition module, it is true in corresponding history of multiple historical junctures for obtaining the index to be monitored
Value；
Time recurrent neural networks model establishes module, for the multiple historical juncture and correspondence of the multiple historical juncture
History actual value carry out time recurrent neural network training, obtain time recurrent neural networks model；Wherein, the time passs
Neural network model is returned to include：Moment and the correspondence to be monitored for referring to target value.
8. abnormal detector according to claim 7, which is characterized in that described device further includes：
Second history actual value acquisition module, for obtaining the index to be monitored in other multiple historical junctures corresponding history
Actual value, other the multiple historical junctures are different from the multiple historical juncture；
Historical forecast value acquisition module, during for according to the time recurrent neural networks model and other the multiple history
It carves, obtains the index to be monitored in other the multiple historical junctures corresponding historical forecast value；
Preset threshold range determining module, for by other the multiple historical junctures corresponding history actual value with it is the multiple
The difference of other historical junctures corresponding historical forecast value is fitted the error sample, determines pre- as error sample
If threshold range.
9. abnormal detector according to claim 8, which is characterized in that the preset threshold range determining module is specific
For being fitted by Gauss model to the error sample, obtaining the average and standard deviation of Gauss model；Based on described equal
Value and the standard deviation determine the upper limit value and lower limiting value of preset threshold range.
10. abnormal detector according to claim 9, which is characterized in that the exception determining module is specifically used for, if
Judge that the current prediction error is more than the upper limit value of the preset threshold range, determine the index to be monitored described current
Moment, which is abnormal, uprushes；If or, judge the current prediction error be less than the preset threshold range lower limiting value, determine institute
It states index to be monitored and is abnormal anticlimax at the current time.
11. a kind of electronic equipment, which is characterized in that including：Processor, communication interface, memory and communication bus, wherein, institute
It states processor, the communication interface, the memory and mutual communication is completed by the communication bus；
The memory, for storing computer program；
The processor during for performing the program stored on the memory, realizes that Claims 1 to 5 is any described
The step of method for detecting abnormality.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711116162.1A CN108089962A (en) | 2017-11-13 | 2017-11-13 | A kind of method for detecting abnormality, device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711116162.1A CN108089962A (en) | 2017-11-13 | 2017-11-13 | A kind of method for detecting abnormality, device and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108089962A true CN108089962A (en) | 2018-05-29 |
Family
ID=62172138
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711116162.1A Pending CN108089962A (en) | 2017-11-13 | 2017-11-13 | A kind of method for detecting abnormality, device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108089962A (en) |
Cited By (81)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108776694A (en) * | 2018-06-05 | 2018-11-09 | 哈尔滨工业大学 | A kind of time series abnormal point detecting method and device |
| CN108989889A (en) * | 2018-08-09 | 2018-12-11 | 北京奇艺世纪科技有限公司 | A kind of video playing amount prediction technique, device and electronic equipment |
| CN109213654A (en) * | 2018-07-05 | 2019-01-15 | 北京奇艺世纪科技有限公司 | A kind of method for detecting abnormality and device |
| CN109359966A (en) * | 2018-07-25 | 2019-02-19 | 西北工业大学 | A kind of method and apparatus of detection logistics package charging exception |
| CN109631458A (en) * | 2018-12-04 | 2019-04-16 | 珠海格力电器股份有限公司 | Method and device for judging refrigeration effect of refrigerator, storage medium and refrigerator |
| CN109639654A (en) * | 2018-11-30 | 2019-04-16 | 成都知道创宇信息技术有限公司 | A method of TCP abnormal flow is identified based on adaptive filtering model |
| CN109684118A (en) * | 2018-12-10 | 2019-04-26 | 深圳前海微众银行股份有限公司 | Detection method, device, equipment and the computer readable storage medium of abnormal data |
| CN109711440A (en) * | 2018-12-13 | 2019-05-03 | 新奥数能科技有限公司 | A kind of data exception detection method and device |
| CN109739720A (en) * | 2018-12-04 | 2019-05-10 | 东软集团股份有限公司 | Method for detecting abnormality, device, storage medium and electronic equipment |
| CN109800858A (en) * | 2018-12-21 | 2019-05-24 | 东软集团股份有限公司 | Data exception detection method, device, readable storage medium storing program for executing and electronic equipment |
| CN109890002A (en) * | 2019-01-04 | 2019-06-14 | 中国电子科技集团公司电子科学研究院 | A kind of method and device of the prediction Risk Degree of Maneuvering Environment of knowledge-based inference |
| CN109992473A (en) * | 2019-02-27 | 2019-07-09 | 平安科技（深圳）有限公司 | Monitoring method, device, equipment and the storage medium of application system |
| CN110008079A (en) * | 2018-12-25 | 2019-07-12 | 阿里巴巴集团控股有限公司 | Monitor control index method for detecting abnormality, model training method, device and equipment |
| CN110033130A (en) * | 2019-03-28 | 2019-07-19 | 阿里巴巴集团控股有限公司 | The monitoring method and device of abnormal traffic |
| CN110032490A (en) * | 2018-12-28 | 2019-07-19 | 中国银联股份有限公司 | Method and device thereof for detection system exception |
| CN110032461A (en) * | 2019-02-02 | 2019-07-19 | 阿里巴巴集团控股有限公司 | A kind of determination method and device showing moment exception |
| CN110086649A (en) * | 2019-03-19 | 2019-08-02 | 深圳壹账通智能科技有限公司 | Detection method, device, computer equipment and the storage medium of abnormal flow |
| CN110113226A (en) * | 2019-04-16 | 2019-08-09 | 新华三信息安全技术有限公司 | A kind of method and device of detection device exception |
| CN110231447A (en) * | 2019-06-10 | 2019-09-13 | 精锐视觉智能科技（深圳）有限公司 | The method, apparatus and terminal device of water quality abnormality detection |
| CN110377447A (en) * | 2019-07-17 | 2019-10-25 | 腾讯科技（深圳）有限公司 | A kind of abnormal deviation data examination method, device and server |
| CN110378386A (en) * | 2019-06-20 | 2019-10-25 | 平安科技（深圳）有限公司 | Based on unmarked abnormality recognition method, device and the storage medium for having supervision |
| CN110400052A (en) * | 2019-06-28 | 2019-11-01 | 北京汉迪移动互联网科技股份有限公司 | The monitoring method and device of Key Performance Indicator |
| CN110535864A (en) * | 2019-08-30 | 2019-12-03 | 北京达佳互联信息技术有限公司 | Service method for detecting abnormality, device, equipment and storage medium |
| CN110688244A (en) * | 2019-09-29 | 2020-01-14 | 北京金山安全软件有限公司 | Interactive function detection method and device and electronic equipment |
| CN110704508A (en) * | 2019-09-30 | 2020-01-17 | 佛山科学技术学院 | Intelligent production line abnormal data processing method and device |
| CN110807024A (en) * | 2019-10-12 | 2020-02-18 | 广州市申迪计算机系统有限公司 | Dynamic threshold anomaly detection method and system, storage medium and intelligent device |
| CN110830448A (en) * | 2019-10-16 | 2020-02-21 | 支付宝(杭州)信息技术有限公司 | Target event flow abnormity detection method and device, electronic equipment and medium |
| CN110839032A (en) * | 2019-11-18 | 2020-02-25 | 河南牧业经济学院 | Internet of things abnormal data identification method and system |
| CN110839040A (en) * | 2019-11-20 | 2020-02-25 | 北京天融信网络安全技术有限公司 | Flow monitoring method, model training method, device and storage medium |
| CN110837011A (en) * | 2019-09-27 | 2020-02-25 | 深圳市火乐科技发展有限公司 | Abnormal data processing method and device, intelligent projector and storage medium |
| CN110888788A (en) * | 2019-10-16 | 2020-03-17 | 平安科技（深圳）有限公司 | Anomaly detection method and device, computer equipment and storage medium |
| CN111045894A (en) * | 2019-12-13 | 2020-04-21 | 贵州广思信息网络有限公司广州分公司 | Database anomaly detection method and device, computer equipment and storage medium |
| CN111092849A (en) * | 2018-10-24 | 2020-05-01 | 中移（杭州）信息技术有限公司 | Traffic-based detection method and device for distributed denial of service |
| CN111125195A (en) * | 2019-12-25 | 2020-05-08 | 亚信科技（中国）有限公司 | Data anomaly detection method and device |
| CN111125471A (en) * | 2019-12-11 | 2020-05-08 | 深圳力维智联技术有限公司 | Automatic data labeling method and device |
| CN111130940A (en) * | 2019-12-26 | 2020-05-08 | 众安信息技术服务有限公司 | Abnormal data detection method and device and server |
| CN111178645A (en) * | 2020-04-14 | 2020-05-19 | 深圳市朝阳辉电气设备有限公司 | Power equipment abnormality detection method and device, control equipment and storage medium |
| CN111198799A (en) * | 2019-12-31 | 2020-05-26 | 苏州浪潮智能科技有限公司 | Machine room power consumption early warning method, system, terminal and storage medium based on LSTM |
| CN111209163A (en) * | 2020-01-03 | 2020-05-29 | 中国工商银行股份有限公司 | Application system anomaly detection method and system |
| CN111352794A (en) * | 2018-12-24 | 2020-06-30 | 鸿富锦精密工业(武汉)有限公司 | Abnormality detection method, abnormality detection device, computer device, and storage medium |
| CN111385140A (en) * | 2018-12-28 | 2020-07-07 | 卡巴斯基实验室股份制公司 | System and method for generating data for monitoring network physical system to determine abnormality early |
| CN111382020A (en) * | 2020-03-06 | 2020-07-07 | 中国工商银行股份有限公司 | Transaction flow monitoring method and system |
| CN111414586A (en) * | 2020-03-31 | 2020-07-14 | 北京派得伟业科技发展有限公司 | Environment monitoring method and system |
| CN111709825A (en) * | 2020-06-10 | 2020-09-25 | 中国工商银行股份有限公司 | Abnormal product identification method and system |
| CN111766514A (en) * | 2020-06-19 | 2020-10-13 | 南方电网调峰调频发电有限公司 | Data analysis method for equipment detection points |
| CN111767183A (en) * | 2020-09-01 | 2020-10-13 | 深圳创新奇智科技有限公司 | Equipment abnormality detection method and device, electronic equipment and storage medium |
| CN111882338A (en) * | 2020-08-11 | 2020-11-03 | 网易（杭州）网络有限公司 | Online people number abnormality detection method and device and electronic equipment |
| CN111984503A (en) * | 2020-08-17 | 2020-11-24 | 网宿科技股份有限公司 | Method and device for identifying abnormal data of monitoring index data |
| CN112069028A (en) * | 2020-09-02 | 2020-12-11 | 江苏达科云数据科技有限公司 | Anomaly detection method |
| CN112149860A (en) * | 2019-06-28 | 2020-12-29 | 中国电力科学研究院有限公司 | Automatic anomaly detection method and system |
| CN112164045A (en) * | 2020-09-24 | 2021-01-01 | 安徽德尔电气集团有限公司 | Comprehensive detection system for cable production |
| CN112423031A (en) * | 2019-08-22 | 2021-02-26 | 中国电信股份有限公司 | KPI monitoring method, device and system based on IPTV |
| CN112444748A (en) * | 2020-10-12 | 2021-03-05 | 武汉蔚来能源有限公司 | Battery abnormality detection method, battery abnormality detection device, electronic apparatus, and storage medium |
| CN112612824A (en) * | 2020-12-15 | 2021-04-06 | 重庆梅安森科技股份有限公司 | Water supply pipe network abnormal data detection method based on big data |
| CN112633693A (en) * | 2020-12-24 | 2021-04-09 | 国网福建省电力有限公司电力科学研究院 | Method and equipment for drawing up dam monitoring index based on POT model |
| CN112699946A (en) * | 2020-12-31 | 2021-04-23 | 湖南工商大学 | Anomaly detection method and device for sensing monitoring data and related equipment |
| CN112738098A (en) * | 2020-12-28 | 2021-04-30 | 北京天融信网络安全技术有限公司 | Anomaly detection method and device based on network behavior data |
| CN112787878A (en) * | 2019-11-08 | 2021-05-11 | 大唐移动通信设备有限公司 | Network index prediction method and electronic equipment |
| CN112819373A (en) * | 2021-02-25 | 2021-05-18 | 云南电网有限责任公司电力科学研究院 | Distribution network voltage abnormal data detection method and device |
| CN112825164A (en) * | 2019-11-20 | 2021-05-21 | 顺丰科技有限公司 | Method, device and equipment for detecting abnormal prediction data and storage medium |
| CN112835769A (en) * | 2021-02-24 | 2021-05-25 | 北京顶象技术有限公司 | Service data abnormity diagnosis method, device, equipment and storage medium |
| CN112840355A (en) * | 2018-09-05 | 2021-05-25 | 甲骨文国际公司 | Context-aware feature embedding using deep recurrent neural networks and anomaly detection of sequential log data |
| CN112910567A (en) * | 2021-01-25 | 2021-06-04 | 北京邮电大学 | Interception classification monitoring method based on recurrent neural network and related equipment |
| CN112896388A (en) * | 2021-02-04 | 2021-06-04 | 上海钧正网络科技有限公司 | Riding safety detection method and device, electronic equipment and storage medium |
| CN112926253A (en) * | 2019-12-05 | 2021-06-08 | 中广核环保产业有限公司 | Water quality real-time monitoring method and device and readable storage medium |
| CN113010501A (en) * | 2019-12-19 | 2021-06-22 | 北京国双科技有限公司 | Recovery ratio prediction model obtaining method, recovery ratio prediction method and product |
| CN113391983A (en) * | 2021-06-07 | 2021-09-14 | 北京达佳互联信息技术有限公司 | Alarm information generation method, device, server and storage medium |
| CN113448828A (en) * | 2020-03-26 | 2021-09-28 | 阿里巴巴集团控股有限公司 | Object data detection method and device, electronic equipment and computer storage medium |
| CN113552855A (en) * | 2021-07-23 | 2021-10-26 | 重庆英科铸数网络科技有限公司 | Industrial equipment dynamic threshold setting method and device, electronic equipment and storage medium |
| CN113778836A (en) * | 2021-11-11 | 2021-12-10 | 深圳市明源云科技有限公司 | Cloud native application health monitoring method, device, equipment and readable storage medium |
| CN113821416A (en) * | 2021-09-18 | 2021-12-21 | 中国电信股份有限公司 | Monitoring alarm method, device, storage medium and electronic equipment |
| CN114325395A (en) * | 2020-09-30 | 2022-04-12 | 北京昇科能源科技有限责任公司 | Method and device for determining battery state |
| CN114510852A (en) * | 2022-04-20 | 2022-05-17 | 希望知舟技术(深圳)有限公司 | Production process parameter recommendation method and device based on abnormal working conditions |
| CN114858205A (en) * | 2021-02-03 | 2022-08-05 | 盟立自动化股份有限公司 | Storage equipment and monitoring method thereof |
| CN114881269A (en) * | 2022-07-13 | 2022-08-09 | 山东恩信特种车辆制造有限公司 | Abnormity detection method and device for material conveying pipeline |
| CN114997253A (en) * | 2021-02-23 | 2022-09-02 | 哈尔滨工业大学 | Intelligent state anomaly detection method, monitoring system and monitoring method for satellite constellation |
| CN115348179A (en) * | 2022-08-10 | 2022-11-15 | 中国电信股份有限公司 | Network traffic boundary prediction method, device, equipment and medium |
| CN116304913A (en) * | 2023-04-07 | 2023-06-23 | 中国长江三峡集团有限公司 | Water quality state monitoring method and device based on Bayesian model and electronic equipment |
| CN116638508A (en) * | 2023-05-15 | 2023-08-25 | 上海傅利叶智能科技有限公司 | Equipment abnormality detection method, device and robot |
| US11748632B2 (en) | 2019-10-30 | 2023-09-05 | Sensai Networks Ltd | Analysis of anomalies in a facility |
| WO2024156235A1 (en) * | 2023-01-28 | 2024-08-02 | 天翼云科技有限公司 | Data processing method and apparatus, electronic device, and medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103336906A (en) * | 2013-07-15 | 2013-10-02 | 哈尔滨工业大学 | Sampling GPR method of continuous anomaly detection in collecting data flow of environment sensor |
| US8781982B1 (en) * | 2011-09-23 | 2014-07-15 | Lockheed Martin Corporation | System and method for estimating remaining useful life |
| CN104063747A (en) * | 2014-06-26 | 2014-09-24 | 上海交通大学 | Performance abnormality prediction method in distributed system and system |
| US20150294246A1 (en) * | 2014-04-10 | 2015-10-15 | International Business Machines Corporation | Selecting optimal training data set for service contract prediction |
| CN105302848A (en) * | 2014-10-11 | 2016-02-03 | 山东鲁能软件技术有限公司 | Evaluation value calibration method of equipment intelligent early warning system |
| US20160223600A1 (en) * | 2015-02-03 | 2016-08-04 | Envision Energy (Jiangsu) Co., Ltd. | Power generation performance evaluation method and apparatus for power generator set |
| CN106874280A (en) * | 2015-12-10 | 2017-06-20 | 博雅网络游戏开发（深圳）有限公司 | The alarm method and device of abnormal data |
| CN107086944A (en) * | 2017-06-22 | 2017-08-22 | 北京奇艺世纪科技有限公司 | A kind of method for detecting abnormality and device |
-
2017
- 2017-11-13 CN CN201711116162.1A patent/CN108089962A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8781982B1 (en) * | 2011-09-23 | 2014-07-15 | Lockheed Martin Corporation | System and method for estimating remaining useful life |
| CN103336906A (en) * | 2013-07-15 | 2013-10-02 | 哈尔滨工业大学 | Sampling GPR method of continuous anomaly detection in collecting data flow of environment sensor |
| US20150294246A1 (en) * | 2014-04-10 | 2015-10-15 | International Business Machines Corporation | Selecting optimal training data set for service contract prediction |
| CN104063747A (en) * | 2014-06-26 | 2014-09-24 | 上海交通大学 | Performance abnormality prediction method in distributed system and system |
| CN105302848A (en) * | 2014-10-11 | 2016-02-03 | 山东鲁能软件技术有限公司 | Evaluation value calibration method of equipment intelligent early warning system |
| US20160223600A1 (en) * | 2015-02-03 | 2016-08-04 | Envision Energy (Jiangsu) Co., Ltd. | Power generation performance evaluation method and apparatus for power generator set |
| CN106874280A (en) * | 2015-12-10 | 2017-06-20 | 博雅网络游戏开发（深圳）有限公司 | The alarm method and device of abnormal data |
| CN107086944A (en) * | 2017-06-22 | 2017-08-22 | 北京奇艺世纪科技有限公司 | A kind of method for detecting abnormality and device |
Cited By (119)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108776694A (en) * | 2018-06-05 | 2018-11-09 | 哈尔滨工业大学 | A kind of time series abnormal point detecting method and device |
| CN109213654A (en) * | 2018-07-05 | 2019-01-15 | 北京奇艺世纪科技有限公司 | A kind of method for detecting abnormality and device |
| CN109359966A (en) * | 2018-07-25 | 2019-02-19 | 西北工业大学 | A kind of method and apparatus of detection logistics package charging exception |
| CN109359966B (en) * | 2018-07-25 | 2021-12-21 | 西北工业大学 | Method and device for detecting abnormal charging of logistics packages |
| CN108989889A (en) * | 2018-08-09 | 2018-12-11 | 北京奇艺世纪科技有限公司 | A kind of video playing amount prediction technique, device and electronic equipment |
| CN113190842A (en) * | 2018-09-05 | 2021-07-30 | 甲骨文国际公司 | Context-aware feature embedding using deep recurrent neural networks and anomaly detection of sequential log data |
| CN112840355A (en) * | 2018-09-05 | 2021-05-25 | 甲骨文国际公司 | Context-aware feature embedding using deep recurrent neural networks and anomaly detection of sequential log data |
| CN113190842B (en) * | 2018-09-05 | 2024-02-13 | 甲骨文国际公司 | Context-aware feature embedding and anomaly detection of sequence log data using deep recurrent neural networks |
| CN111092849B (en) * | 2018-10-24 | 2022-01-25 | 中移（杭州）信息技术有限公司 | Traffic-based detection method and device for distributed denial of service |
| CN111092849A (en) * | 2018-10-24 | 2020-05-01 | 中移（杭州）信息技术有限公司 | Traffic-based detection method and device for distributed denial of service |
| CN109639654A (en) * | 2018-11-30 | 2019-04-16 | 成都知道创宇信息技术有限公司 | A method of TCP abnormal flow is identified based on adaptive filtering model |
| CN109631458A (en) * | 2018-12-04 | 2019-04-16 | 珠海格力电器股份有限公司 | Method and device for judging refrigeration effect of refrigerator, storage medium and refrigerator |
| CN109739720A (en) * | 2018-12-04 | 2019-05-10 | 东软集团股份有限公司 | Method for detecting abnormality, device, storage medium and electronic equipment |
| CN109739720B (en) * | 2018-12-04 | 2022-08-02 | 东软集团股份有限公司 | Abnormality detection method, abnormality detection device, storage medium, and electronic apparatus |
| CN109684118A (en) * | 2018-12-10 | 2019-04-26 | 深圳前海微众银行股份有限公司 | Detection method, device, equipment and the computer readable storage medium of abnormal data |
| CN109684118B (en) * | 2018-12-10 | 2022-04-26 | 深圳前海微众银行股份有限公司 | Abnormal data detection method, device, equipment and computer readable storage medium |
| CN109711440A (en) * | 2018-12-13 | 2019-05-03 | 新奥数能科技有限公司 | A kind of data exception detection method and device |
| CN109800858B (en) * | 2018-12-21 | 2021-03-05 | 东软集团股份有限公司 | Application system abnormality detection method and device, readable storage medium and electronic equipment |
| CN109800858A (en) * | 2018-12-21 | 2019-05-24 | 东软集团股份有限公司 | Data exception detection method, device, readable storage medium storing program for executing and electronic equipment |
| CN111352794A (en) * | 2018-12-24 | 2020-06-30 | 鸿富锦精密工业(武汉)有限公司 | Abnormality detection method, abnormality detection device, computer device, and storage medium |
| CN111352794B (en) * | 2018-12-24 | 2022-09-20 | 鸿富锦精密工业(武汉)有限公司 | Abnormality detection method, abnormality detection device, computer device, and storage medium |
| CN110008079A (en) * | 2018-12-25 | 2019-07-12 | 阿里巴巴集团控股有限公司 | Monitor control index method for detecting abnormality, model training method, device and equipment |
| CN111385140A (en) * | 2018-12-28 | 2020-07-07 | 卡巴斯基实验室股份制公司 | System and method for generating data for monitoring network physical system to determine abnormality early |
| CN111385140B (en) * | 2018-12-28 | 2022-11-15 | 卡巴斯基实验室股份制公司 | System and method for generating data for monitoring network physical system to determine abnormality early |
| CN110032490A (en) * | 2018-12-28 | 2019-07-19 | 中国银联股份有限公司 | Method and device thereof for detection system exception |
| CN109890002A (en) * | 2019-01-04 | 2019-06-14 | 中国电子科技集团公司电子科学研究院 | A kind of method and device of the prediction Risk Degree of Maneuvering Environment of knowledge-based inference |
| CN110032461B (en) * | 2019-02-02 | 2023-09-19 | 创新先进技术有限公司 | Method and device for determining abnormal display time |
| CN110032461A (en) * | 2019-02-02 | 2019-07-19 | 阿里巴巴集团控股有限公司 | A kind of determination method and device showing moment exception |
| CN109992473A (en) * | 2019-02-27 | 2019-07-09 | 平安科技（深圳）有限公司 | Monitoring method, device, equipment and the storage medium of application system |
| CN109992473B (en) * | 2019-02-27 | 2022-07-15 | 平安科技（深圳）有限公司 | Application system monitoring method, device, equipment and storage medium |
| CN110086649B (en) * | 2019-03-19 | 2023-06-16 | 深圳壹账通智能科技有限公司 | Abnormal flow detection method, device, computer equipment and storage medium |
| CN110086649A (en) * | 2019-03-19 | 2019-08-02 | 深圳壹账通智能科技有限公司 | Detection method, device, computer equipment and the storage medium of abnormal flow |
| CN110033130A (en) * | 2019-03-28 | 2019-07-19 | 阿里巴巴集团控股有限公司 | The monitoring method and device of abnormal traffic |
| CN110113226B (en) * | 2019-04-16 | 2021-03-12 | 新华三信息安全技术有限公司 | Method and device for detecting equipment abnormity |
| CN110113226A (en) * | 2019-04-16 | 2019-08-09 | 新华三信息安全技术有限公司 | A kind of method and device of detection device exception |
| CN110231447A (en) * | 2019-06-10 | 2019-09-13 | 精锐视觉智能科技（深圳）有限公司 | The method, apparatus and terminal device of water quality abnormality detection |
| CN110378386B (en) * | 2019-06-20 | 2024-09-06 | 平安科技（深圳）有限公司 | Method, device and storage medium for identifying unmarked anomalies based on supervision |
| CN110378386A (en) * | 2019-06-20 | 2019-10-25 | 平安科技（深圳）有限公司 | Based on unmarked abnormality recognition method, device and the storage medium for having supervision |
| CN110400052A (en) * | 2019-06-28 | 2019-11-01 | 北京汉迪移动互联网科技股份有限公司 | The monitoring method and device of Key Performance Indicator |
| CN112149860A (en) * | 2019-06-28 | 2020-12-29 | 中国电力科学研究院有限公司 | Automatic anomaly detection method and system |
| CN110377447B (en) * | 2019-07-17 | 2022-07-22 | 腾讯科技（深圳）有限公司 | Abnormal data detection method and device and server |
| CN110377447A (en) * | 2019-07-17 | 2019-10-25 | 腾讯科技（深圳）有限公司 | A kind of abnormal deviation data examination method, device and server |
| CN112423031A (en) * | 2019-08-22 | 2021-02-26 | 中国电信股份有限公司 | KPI monitoring method, device and system based on IPTV |
| CN110535864B (en) * | 2019-08-30 | 2022-02-25 | 北京达佳互联信息技术有限公司 | Service abnormity detection method, device, equipment and storage medium |
| CN110535864A (en) * | 2019-08-30 | 2019-12-03 | 北京达佳互联信息技术有限公司 | Service method for detecting abnormality, device, equipment and storage medium |
| CN110837011A (en) * | 2019-09-27 | 2020-02-25 | 深圳市火乐科技发展有限公司 | Abnormal data processing method and device, intelligent projector and storage medium |
| CN110688244A (en) * | 2019-09-29 | 2020-01-14 | 北京金山安全软件有限公司 | Interactive function detection method and device and electronic equipment |
| CN110688244B (en) * | 2019-09-29 | 2023-05-26 | 北京金山安全软件有限公司 | Interactive function detection method and device and electronic equipment |
| CN110704508A (en) * | 2019-09-30 | 2020-01-17 | 佛山科学技术学院 | Intelligent production line abnormal data processing method and device |
| CN110807024B (en) * | 2019-10-12 | 2022-04-19 | 广州市申迪计算机系统有限公司 | Dynamic threshold anomaly detection method and system, storage medium and intelligent device |
| CN110807024A (en) * | 2019-10-12 | 2020-02-18 | 广州市申迪计算机系统有限公司 | Dynamic threshold anomaly detection method and system, storage medium and intelligent device |
| CN110888788A (en) * | 2019-10-16 | 2020-03-17 | 平安科技（深圳）有限公司 | Anomaly detection method and device, computer equipment and storage medium |
| CN110830448A (en) * | 2019-10-16 | 2020-02-21 | 支付宝(杭州)信息技术有限公司 | Target event flow abnormity detection method and device, electronic equipment and medium |
| CN110830448B (en) * | 2019-10-16 | 2022-09-13 | 支付宝(杭州)信息技术有限公司 | Target event flow abnormity detection method and device, electronic equipment and medium |
| US11748632B2 (en) | 2019-10-30 | 2023-09-05 | Sensai Networks Ltd | Analysis of anomalies in a facility |
| CN112787878A (en) * | 2019-11-08 | 2021-05-11 | 大唐移动通信设备有限公司 | Network index prediction method and electronic equipment |
| CN112787878B (en) * | 2019-11-08 | 2023-03-14 | 大唐移动通信设备有限公司 | Network index prediction method and electronic equipment |
| CN110839032A (en) * | 2019-11-18 | 2020-02-25 | 河南牧业经济学院 | Internet of things abnormal data identification method and system |
| CN110839040B (en) * | 2019-11-20 | 2021-12-14 | 北京天融信网络安全技术有限公司 | Flow monitoring method, model training method, device and storage medium |
| CN110839040A (en) * | 2019-11-20 | 2020-02-25 | 北京天融信网络安全技术有限公司 | Flow monitoring method, model training method, device and storage medium |
| CN112825164A (en) * | 2019-11-20 | 2021-05-21 | 顺丰科技有限公司 | Method, device and equipment for detecting abnormal prediction data and storage medium |
| CN112825164B (en) * | 2019-11-20 | 2024-06-28 | 顺丰科技有限公司 | Predictive data anomaly detection method, device, equipment and storage medium |
| CN112926253A (en) * | 2019-12-05 | 2021-06-08 | 中广核环保产业有限公司 | Water quality real-time monitoring method and device and readable storage medium |
| CN111125471A (en) * | 2019-12-11 | 2020-05-08 | 深圳力维智联技术有限公司 | Automatic data labeling method and device |
| CN111045894B (en) * | 2019-12-13 | 2024-02-13 | 贵州广思信息网络有限公司广州分公司 | Database abnormality detection method, database abnormality detection device, computer device and storage medium |
| CN111045894A (en) * | 2019-12-13 | 2020-04-21 | 贵州广思信息网络有限公司广州分公司 | Database anomaly detection method and device, computer equipment and storage medium |
| CN113010501B (en) * | 2019-12-19 | 2024-08-02 | 北京国双科技有限公司 | Recovery ratio prediction model acquisition method, recovery ratio prediction method and product |
| CN113010501A (en) * | 2019-12-19 | 2021-06-22 | 北京国双科技有限公司 | Recovery ratio prediction model obtaining method, recovery ratio prediction method and product |
| CN111125195A (en) * | 2019-12-25 | 2020-05-08 | 亚信科技（中国）有限公司 | Data anomaly detection method and device |
| CN111125195B (en) * | 2019-12-25 | 2023-09-08 | 亚信科技（中国）有限公司 | Data anomaly detection method and device |
| CN111130940A (en) * | 2019-12-26 | 2020-05-08 | 众安信息技术服务有限公司 | Abnormal data detection method and device and server |
| CN111198799A (en) * | 2019-12-31 | 2020-05-26 | 苏州浪潮智能科技有限公司 | Machine room power consumption early warning method, system, terminal and storage medium based on LSTM |
| CN111209163A (en) * | 2020-01-03 | 2020-05-29 | 中国工商银行股份有限公司 | Application system anomaly detection method and system |
| CN111382020A (en) * | 2020-03-06 | 2020-07-07 | 中国工商银行股份有限公司 | Transaction flow monitoring method and system |
| CN113448828A (en) * | 2020-03-26 | 2021-09-28 | 阿里巴巴集团控股有限公司 | Object data detection method and device, electronic equipment and computer storage medium |
| CN111414586A (en) * | 2020-03-31 | 2020-07-14 | 北京派得伟业科技发展有限公司 | Environment monitoring method and system |
| CN111178645A (en) * | 2020-04-14 | 2020-05-19 | 深圳市朝阳辉电气设备有限公司 | Power equipment abnormality detection method and device, control equipment and storage medium |
| CN111709825A (en) * | 2020-06-10 | 2020-09-25 | 中国工商银行股份有限公司 | Abnormal product identification method and system |
| CN111709825B (en) * | 2020-06-10 | 2023-09-08 | 中国工商银行股份有限公司 | Abnormal product identification method and system |
| CN111766514A (en) * | 2020-06-19 | 2020-10-13 | 南方电网调峰调频发电有限公司 | Data analysis method for equipment detection points |
| CN111882338B (en) * | 2020-08-11 | 2023-06-30 | 网易（杭州）网络有限公司 | Abnormality detection method and device for online number of people and electronic equipment |
| CN111882338A (en) * | 2020-08-11 | 2020-11-03 | 网易（杭州）网络有限公司 | Online people number abnormality detection method and device and electronic equipment |
| CN111984503A (en) * | 2020-08-17 | 2020-11-24 | 网宿科技股份有限公司 | Method and device for identifying abnormal data of monitoring index data |
| CN111984503B (en) * | 2020-08-17 | 2023-12-01 | 网宿科技股份有限公司 | Method and device for identifying abnormal data of monitoring index data |
| CN111767183A (en) * | 2020-09-01 | 2020-10-13 | 深圳创新奇智科技有限公司 | Equipment abnormality detection method and device, electronic equipment and storage medium |
| CN112069028B (en) * | 2020-09-02 | 2024-07-12 | 江苏臻云技术有限公司 | Abnormality detection method |
| CN112069028A (en) * | 2020-09-02 | 2020-12-11 | 江苏达科云数据科技有限公司 | Anomaly detection method |
| CN112164045A (en) * | 2020-09-24 | 2021-01-01 | 安徽德尔电气集团有限公司 | Comprehensive detection system for cable production |
| CN114325395A (en) * | 2020-09-30 | 2022-04-12 | 北京昇科能源科技有限责任公司 | Method and device for determining battery state |
| CN114325395B (en) * | 2020-09-30 | 2024-01-26 | 北京昇科能源科技有限责任公司 | Battery state determining method and device |
| CN112444748B (en) * | 2020-10-12 | 2024-10-08 | 武汉蔚来能源有限公司 | Battery abnormality detection method, battery abnormality detection device, electronic equipment and storage medium |
| CN112444748A (en) * | 2020-10-12 | 2021-03-05 | 武汉蔚来能源有限公司 | Battery abnormality detection method, battery abnormality detection device, electronic apparatus, and storage medium |
| CN112612824A (en) * | 2020-12-15 | 2021-04-06 | 重庆梅安森科技股份有限公司 | Water supply pipe network abnormal data detection method based on big data |
| CN112633693B (en) * | 2020-12-24 | 2022-05-20 | 国网福建省电力有限公司电力科学研究院 | Method and equipment for drawing up dam monitoring index based on POT model |
| CN112633693A (en) * | 2020-12-24 | 2021-04-09 | 国网福建省电力有限公司电力科学研究院 | Method and equipment for drawing up dam monitoring index based on POT model |
| CN112738098A (en) * | 2020-12-28 | 2021-04-30 | 北京天融信网络安全技术有限公司 | Anomaly detection method and device based on network behavior data |
| CN112699946B (en) * | 2020-12-31 | 2022-06-21 | 湖南工商大学 | Anomaly detection method and device for sensing monitoring data and related equipment |
| CN112699946A (en) * | 2020-12-31 | 2021-04-23 | 湖南工商大学 | Anomaly detection method and device for sensing monitoring data and related equipment |
| CN112910567A (en) * | 2021-01-25 | 2021-06-04 | 北京邮电大学 | Interception classification monitoring method based on recurrent neural network and related equipment |
| CN112910567B (en) * | 2021-01-25 | 2022-07-01 | 北京邮电大学 | Interception classification monitoring method based on recurrent neural network and related equipment |
| CN114858205A (en) * | 2021-02-03 | 2022-08-05 | 盟立自动化股份有限公司 | Storage equipment and monitoring method thereof |
| CN114858205B (en) * | 2021-02-03 | 2024-03-01 | 盟立自动化股份有限公司 | Storage equipment and monitoring method thereof |
| CN112896388A (en) * | 2021-02-04 | 2021-06-04 | 上海钧正网络科技有限公司 | Riding safety detection method and device, electronic equipment and storage medium |
| CN114997253A (en) * | 2021-02-23 | 2022-09-02 | 哈尔滨工业大学 | Intelligent state anomaly detection method, monitoring system and monitoring method for satellite constellation |
| CN112835769A (en) * | 2021-02-24 | 2021-05-25 | 北京顶象技术有限公司 | Service data abnormity diagnosis method, device, equipment and storage medium |
| CN112819373A (en) * | 2021-02-25 | 2021-05-18 | 云南电网有限责任公司电力科学研究院 | Distribution network voltage abnormal data detection method and device |
| CN113391983A (en) * | 2021-06-07 | 2021-09-14 | 北京达佳互联信息技术有限公司 | Alarm information generation method, device, server and storage medium |
| CN113552855A (en) * | 2021-07-23 | 2021-10-26 | 重庆英科铸数网络科技有限公司 | Industrial equipment dynamic threshold setting method and device, electronic equipment and storage medium |
| CN113821416A (en) * | 2021-09-18 | 2021-12-21 | 中国电信股份有限公司 | Monitoring alarm method, device, storage medium and electronic equipment |
| CN113778836A (en) * | 2021-11-11 | 2021-12-10 | 深圳市明源云科技有限公司 | Cloud native application health monitoring method, device, equipment and readable storage medium |
| CN114510852A (en) * | 2022-04-20 | 2022-05-17 | 希望知舟技术(深圳)有限公司 | Production process parameter recommendation method and device based on abnormal working conditions |
| CN114881269A (en) * | 2022-07-13 | 2022-08-09 | 山东恩信特种车辆制造有限公司 | Abnormity detection method and device for material conveying pipeline |
| CN114881269B (en) * | 2022-07-13 | 2022-09-27 | 山东恩信特种车辆制造有限公司 | Abnormity detection method and device for material conveying pipeline |
| CN115348179B (en) * | 2022-08-10 | 2024-02-02 | 中国电信股份有限公司 | Network traffic boundary prediction method, device, equipment and medium |
| CN115348179A (en) * | 2022-08-10 | 2022-11-15 | 中国电信股份有限公司 | Network traffic boundary prediction method, device, equipment and medium |
| WO2024156235A1 (en) * | 2023-01-28 | 2024-08-02 | 天翼云科技有限公司 | Data processing method and apparatus, electronic device, and medium |
| CN116304913B (en) * | 2023-04-07 | 2024-08-20 | 中国长江三峡集团有限公司 | Water quality state monitoring method and device based on Bayesian model and electronic equipment |
| CN116304913A (en) * | 2023-04-07 | 2023-06-23 | 中国长江三峡集团有限公司 | Water quality state monitoring method and device based on Bayesian model and electronic equipment |
| CN116638508A (en) * | 2023-05-15 | 2023-08-25 | 上海傅利叶智能科技有限公司 | Equipment abnormality detection method, device and robot |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108089962A (en) | A kind of method for detecting abnormality, device and electronic equipment | |
| CN111143102B (en) | Abnormal data detection method and device, storage medium and electronic equipment | |
| CN107766299A (en) | The abnormal monitoring method of data target and its system, storage medium, electronic equipment | |
| Ali et al. | An overview of control charts for high‐quality processes | |
| Chen et al. | Condition-based maintenance using the inverse Gaussian degradation model | |
| CN105718715B (en) | Method for detecting abnormality and equipment | |
| Le et al. | Optimal maintenance strategy of deteriorating system under imperfect maintenance and inspection using mixed inspectionscheduling | |
| EP3896420A1 (en) | Method, device and electronic apparatus for detecting performance status of optical module in engineering application | |
| CN113050019B (en) | Voltage transformer evaluation method and system for fusing data-driven evaluation result and verification procedure | |
| CN108170581A (en) | A kind of fault early warning method, device and electronic equipment | |
| Qu et al. | A CUSUM scheme for event monitoring | |
| US10184974B2 (en) | Systems and methods for determining whether a circuit is operating properly | |
| CN106776214A (en) | A kind of server health degree appraisal procedure | |
| JP7199081B2 (en) | PRODUCTION CONTROL DEVICE, PRODUCTION CONTROL SYSTEM AND PRODUCTION CONTROL METHOD | |
| JP6678824B2 (en) | Unsteady detection device, unsteady detection system, and unsteady detection method | |
| CN116413604A (en) | Battery parameter monitoring method, system, device and storage medium | |
| CN109951466B (en) | Port flow monitoring method and device, electronic equipment and machine-readable storage medium | |
| EP2998814A1 (en) | System for predicting abnormality occurrence using plc log data | |
| CN115686756A (en) | Virtual machine migration method and device, storage medium and electronic equipment | |
| CN113916673A (en) | Safety early warning method and system based on container state monitoring | |
| CN117171366B (en) | Knowledge graph construction method and system for power grid dispatching operation situation | |
| CN113821933A (en) | APP flow prediction method and device, computer equipment and storage medium | |
| JP6381498B2 (en) | Weighing meter state change detection device and program | |
| CN109660512B (en) | Sensitive information flow direction vectorization method, abnormal flow direction identification method and device | |
| TW202105449A (en) | Maintenance for remote plasma sources |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180529 |