CN109669837A - Equipment state method for early warning, system, computer installation and readable storage medium storing program for executing - Google Patents
Equipment state method for early warning, system, computer installation and readable storage medium storing program for executing Download PDFInfo
- Publication number
- CN109669837A CN109669837A CN201811289825.4A CN201811289825A CN109669837A CN 109669837 A CN109669837 A CN 109669837A CN 201811289825 A CN201811289825 A CN 201811289825A CN 109669837 A CN109669837 A CN 109669837A
- Authority
- CN
- China
- Prior art keywords
- load
- monitored object
- system log
- early warning
- data
- 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
- 238000000034 method Methods 0.000 title claims abstract description 31
- 238000009434 installation Methods 0.000 title claims abstract description 28
- 238000012549 training Methods 0.000 claims abstract description 17
- 238000000605 extraction Methods 0.000 claims description 33
- 238000003062 neural network model Methods 0.000 claims description 30
- 238000004590 computer program Methods 0.000 claims description 22
- 230000004913 activation Effects 0.000 claims description 8
- 238000012544 monitoring process Methods 0.000 claims description 5
- 241000208340 Araliaceae Species 0.000 claims description 2
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 claims description 2
- 235000003140 Panax quinquefolius Nutrition 0.000 claims description 2
- 235000008434 ginseng Nutrition 0.000 claims description 2
- 239000000284 extract Substances 0.000 abstract 2
- 230000001537 neural effect Effects 0.000 abstract 1
- 230000006870 function Effects 0.000 description 13
- 230000008859 change Effects 0.000 description 7
- 238000012545 processing Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000005012 migration Effects 0.000 description 4
- 238000013508 migration Methods 0.000 description 4
- 230000010365 information processing Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 210000004556 brain Anatomy 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000011478 gradient descent method Methods 0.000 description 2
- 238000003780 insertion Methods 0.000 description 2
- 230000037431 insertion Effects 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 210000005036 nerve Anatomy 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000002427 irreversible effect Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/3003—Monitoring arrangements specially adapted to the computing system or computing system component being monitored
- G06F11/3024—Monitoring arrangements specially adapted to the computing system or computing system component being monitored where the computing system component is a central processing unit [CPU]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/3003—Monitoring arrangements specially adapted to the computing system or computing system component being monitored
- G06F11/3034—Monitoring arrangements specially adapted to the computing system or computing system component being monitored where the computing system component is a storage system, e.g. DASD based or network based
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/3003—Monitoring arrangements specially adapted to the computing system or computing system component being monitored
- G06F11/3037—Monitoring arrangements specially adapted to the computing system or computing system component being monitored where the computing system component is a memory, e.g. virtual memory, cache
-
- 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
- G06N3/045—Combinations of networks
-
- 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
- G06N3/048—Activation functions
-
- 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
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computing Systems (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Quality & Reliability (AREA)
- Biomedical Technology (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Debugging And Monitoring (AREA)
Abstract
The present invention provides a kind of equipment state method for early warning, system, computer installation and computer readable storage medium.The equipment state method for early warning includes: the legacy system log for obtaining monitored object, and extracts to obtain multiple feature samples data from legacy system log；It is established according to multiple feature samples data and trains to obtain a load estimation model；The current system log of monitored object is obtained, and extracts to obtain multiple characteristics to be measured from current system log；Multiple characteristics to be measured and multiple fixed reference feature data are separately input into the load estimation model and obtain prediction load and reference load；The operation warning information of the monitored object is exported with the reference load according to the prediction load.The present invention is based on neural metwork trainings to obtain load estimation model, can determine whether the monitored object can provide preferable running environment for currently running system/software according to model, user handles monitored object with prior notice.
Description
Technical field
The present invention relates to data processing field more particularly to a kind of equipment state method for early warning, system, computer installation and
Computer readable storage medium.
Background technique
This part intends to provides background for the embodiments of the present invention stated in claims and specific embodiment
Or context.Description herein recognizes it is the prior art not because not being included in this section.
The automatic monitoring for carrying out equipment fault has become a kind of important technical for ensureing that equipment operates normally.When
When a certain parameter of equipment exceeds preset alarm door limit value, equipment can issue corresponding warning message.In general, alarm
Threshold value is the fixed value set when equipment factory.If alarm threshold is arranged too loose, equipment when alarming
Irreversible failure may have been produced, the service life of equipment is seriously affected.If alarm threshold setting is too stringent,
Equipment may often carry out unnecessary alarm, influence the normal use of equipment.Thus, equipment early warning means are mainly that equipment makes
With personnel according to the operating status of current device parameter subjective forecast equipment, accuracy is low.
Summary of the invention
In view of above-mentioned, the present invention provides a kind of equipment state method for early warning, system, computer installation and computer-readable deposits
Storage media may be implemented to carry out early warning to the operating status of equipment in advance.
One embodiment of the application provides a kind of equipment state method for early warning, which comprises
The legacy system log of monitored object is obtained, and feature extraction is carried out to the legacy system log and obtains multiple spies
Levy sample data；
It is established according to multiple feature samples data and trains to obtain a load estimation model；
The current system log of the monitored object is obtained, and current system log progress feature extraction is obtained more
A characteristic to be measured；
By multiple characteristics to be measured be input to the load estimation model obtain it is corresponding with the monitored object
Prediction load；
It obtains multiple fixed reference feature data of the monitored object, and multiple fixed reference feature data is input to described
Load estimation model obtains reference load corresponding with the monitored object, and the plurality of fixed reference feature data are the prison
Control the characteristic threshold value of the available running environment of object；And
The operation warning information of the monitored object is exported with the reference load according to the prediction load.
Preferably, described that the step of feature extraction obtains multiple feature samples data packet is carried out to the legacy system log
It includes:
It is extracted and is obtained and multiple preset keywords from the legacy system log according to multiple preset keyword sections
Matched multiple feature samples data.
Preferably, described feature extraction is carried out to the current system log to obtain multiple characteristics to be measured and include:
It is extracted and is obtained and multiple default keys from the current system log according to multiple preset keywords
The matched multiple characteristics to be measured of word.
Preferably, the load estimation model be BP neural network model, the BP neural network model include input layer,
Hidden layer and output layer, the input layer include n node, and the hidden layer includes m node, the BP neural network model
Are as follows:
Wherein, y is the assessed value of output layer output, when multiple characteristics to be measured are input to the load in advance
When surveying model, the output y of the load estimation model is prediction load, when multiple fixed reference feature data are input to institute
When stating load estimation model, the output y of the load estimation model is the reference load, tiFor the hidden layer with it is described defeated
Connection weight between layer out,(i=1,2,3...m；It j=1,2,3...n is) hidden layer
Input, the output of the as described input layer, WijFor the connection weight between the input layer and the hidden layer；f(Si) for institute
The activation primitive in BP neural network model is stated,
Preferably, the feature samples data, the fixed reference feature data and the characteristic to be measured are the prison
Control the hardware resource data of object.
Preferably, the operation early warning for exporting the monitored object with the reference load according to the prediction load is believed
The step of breath includes:
Whether within a preset range to judge the difference of prediction load and the reference load；And
When the difference of prediction load and the reference load is not in the preset range, the monitored object is exported
Operation warning information.
Preferably, described when the difference of prediction load and the reference load is not in the preset range, output
The step of operation warning information of the monitored object includes:
When the difference of prediction load and the reference load is not in the preset range, loaded according to the prediction
And the size of the difference of the reference load exports different grades of operation warning information.
One embodiment of the application provides a kind of equipment state early warning system, the system comprises:
First extraction module is carried out for obtaining the legacy system log of monitored object, and to the legacy system log
Feature extraction obtains multiple feature samples data；
Model training module, for being established according to multiple feature samples data and training to obtain a load estimation mould
Type；
Second extraction module, for obtaining the current system log of the monitored object, and to the current system log
It carries out feature extraction and obtains multiple characteristics to be measured；
First computing module obtains and institute for multiple characteristics to be measured to be input to the load estimation model
State the corresponding prediction load of monitored object；
Second computing module, for obtaining multiple fixed reference feature data of the monitored object, and by multiple references
Characteristic is input to the load estimation model and obtains reference load corresponding with the monitored object, the plurality of ginseng
Examine the characteristic threshold value that characteristic is the available running environment of the monitored object；And
Output module, for exporting the operation early warning of the monitored object with the reference load according to the prediction load
Information.
One embodiment of the application provides a kind of computer installation, and the computer installation includes processor and memory,
Several computer programs are stored on the memory, the processor is for when executing the computer program stored in memory
The step of realizing equipment state method for early warning as elucidated before.
One embodiment of the application provides a kind of computer readable storage medium, is stored thereon with computer program, described
The step of equipment state method for early warning as elucidated before is realized when computer program is executed by processor.
Above equipment status early warning method, system, computer installation and computer readable storage medium are based on machine learning
Legacy system log with monitored object is and special by the reference of monitored object respectively to establish and train to obtain load estimation model
It levies data and is input to the load estimation model from the characteristic to be measured that current system log is extracted and be calculated with reference to negative
It carries and is loaded with prediction, and then judge whether the monitored object can be current according to the reference load and the difference of prediction load
The system of operation/software provides preferable running environment, when judging cannot to provide preferably as currently running system/software
When running environment, output operation warning information, with prior notice, user handles monitored object.
Detailed description of the invention
It, below will be to required in embodiment description in order to illustrate more clearly of the technical solution of embodiment of the present invention
The attached drawing used is briefly described, it should be apparent that, the accompanying drawings in the following description is some embodiments of the present invention, for
For those of ordinary skill in the art, without creative efforts, it can also be obtained according to these attached drawings other
Attached drawing.
Fig. 1 is the step flow chart of equipment state method for early warning in one embodiment of the invention.
Fig. 2 is the functional block diagram of equipment state early warning system in one embodiment of the invention.
Fig. 3 is computer schematic device in one embodiment of the invention.
Specific embodiment
To better understand the objects, features and advantages of the present invention, with reference to the accompanying drawing and specific real
Applying mode, the present invention will be described in detail.It should be noted that in the absence of conflict, presently filed embodiment and reality
The feature applied in mode can be combined with each other.
In the following description, numerous specific details are set forth in order to facilitate a full understanding of the present invention, described embodiment
Only some embodiments of the invention, rather than whole embodiments.Based on the embodiment in the present invention, this field
Those of ordinary skill's every other embodiment obtained without making creative work, belongs to guarantor of the present invention
The range of shield.
Unless otherwise defined, all technical and scientific terms used herein and belong to technical field of the invention
The normally understood meaning of technical staff is identical.Term as used herein in the specification of the present invention is intended merely to description tool
The purpose of the embodiment of body, it is not intended that in the limitation present invention.
Preferably, equipment state method for early warning of the invention is applied in one or more computer installation.The meter
Calculation machine device be it is a kind of can be according to the instruction for being previously set or store, automatic progress numerical value calculating and/or information processing are set
Standby, hardware includes but is not limited to microprocessor, specific integrated circuit (Application Specific Integrated
Circuit, ASIC), programmable gate array (Field-Programmable Gate Array, FPGA), digital processing unit
(Digital Signal Processor, DSP), embedded device etc..
The computer installation can be the calculating such as desktop PC, laptop, tablet computer, server and set
It is standby.The computer installation can carry out people by modes such as keyboard, mouse, remote controler, touch tablet or voice-operated devices with user
Machine interaction.
Embodiment one:
Fig. 1 is the step flow chart of present device status early warning method preferred embodiment.It is described according to different requirements,
The sequence of step can change in flow chart, and certain steps can be omitted.
As shown in fig.1, the equipment state method for early warning specifically includes following steps.
Step S11, the legacy system log of monitored object is obtained, and feature extraction is carried out to the legacy system log and is obtained
To multiple feature samples data.
In one embodiment, it can be connected to the monitored object by access network, and then obtain the monitoring
The legacy system log of object.The monitored object can be a server or a server cluster.The server is described
Server cluster may include several hardware resources (such as: CPU, memory, I/O interface, memory etc.).The server is described
Server cluster can run similar and different operating system, database, with software, system software.It is to be appreciated that institute
Virtual machine manager (Virtual Machine Manager, VMM), several physics can be had by multiple operations by stating server cluster
Node (Physical Node, PN) is constituted, and runs multiple operating systems on VMM, by the resource scheduling algorithm of VMM, this
A little operating systems share the resource of physical machine.
The legacy system log can refer to the system log before a scheduled date, for example, the monitored object exists
2018.8.12 all system logs before.When the application software or the system software are run, operating system or VMM meeting
Relevant record is carried out, and then forms system log.
The system log that is generated when in one embodiment, the system log may include the operating system of equipment,
Application log and security log etc.；In one embodiment, can by operating system operation in input
The event viewer of eventvwr.msc calling system is to obtain the system log.In other embodiments, for not
Same operating system, the order for obtaining system log may be different.
It in one embodiment, can be according to multiple default passes when carrying out feature extraction to the legacy system log
Key field is extracted from the legacy system log to be obtained and multiple matched multiple feature samples data of preset keyword.
For example, for database, the change in system log recorded data library (for example, MySQL database) is operated,
Including but not limited to create database or table, insertion operation, update operation, delete operation etc., each change operation is with one
In the form write-in journal file of record, system log is formd.Every record may include the timestamp of current record update, be somebody's turn to do
The position (such as offset) being recorded in journal file and other information relevant to database change operation.MySQL data
Usually there is one or more journal file in library, and different journal files uses different digital number shapes by file extension
Formula is distinguish, such as: mysql-bin.00001, mysql-bin.00002.
It may include that (CPU executes non-idle thread time for the utilization rate of CPU for hardware resource, in system log
Percentage), the interruption rate number of device interrupt processor (each second), (system service of CPU call operation is customary for system calling rate
The overall rate of program), memory is using accounting, residual memory space etc..
Step S12, it is established according to multiple feature samples data and trains to obtain a load estimation model.
In one embodiment, the load estimation model can be based on neural network model and multiple feature samples
Notebook data trains the model come.The neural network model can take out human brain neuroid from information processing angle
As different networks being formed by different connection types, it is not necessary that the mathematics side of mapping relations between input and output is determined in advance
Journey obtains the result closest to desired output in given input value only by the training of itself.The neural network model
Including input layer, hidden layer and output layer.The history feature data can be used as the input layer of neural network model, using mind
An assessed value is exported by output layer after the connection of the hidden layer of network model.
In one embodiment, the neural network model can be BP (Back Propagation, backpropagation) mind
Through network model, the BP neural network model be it is a kind of based on gradient descent method by error back propagation training multilayer before
Network is presented, using gradient search technology, to make the real output value of network and the error mean square difference minimum of desired output.
In other embodiments of the invention, other kinds of neural network model can also be selected according to actual needs.
In one embodiment, the input layer includes n node, and the hidden layer includes m node, the BP nerve
Network model can indicate are as follows:
Wherein, y is the assessed value of output layer output, when multiple characteristics to be measured are input to the load in advance
When surveying model, the output y of the load estimation model is prediction load, when multiple fixed reference feature data are input to institute
When stating load estimation model, the output y of the load estimation model is the reference load, tiFor the hidden layer with it is described defeated
Connection weight between layer out,(i=1,2,3...m；J=1,2,3...n), SiFor the hidden layer
Input, the output of the as described input layer, WijFor the connection weight between the input layer and the hidden layer, f () is
Activation primitive in the BP neural network model, when the hidden layer has input, activation primitive is expressed as f (Si).It is described
Activation primitive f (Si) S type function (Sigmoid function), f (S can be usedi) can indicate are as follows:
It is to be appreciated that tiIt can indicate the connection weight between i-th of node of the hidden layer and the output layer,
For example, t11st connection weight between node and the output layer of the as described hidden layer, t2The as described hidden layer
2nd connection weight between node and the output layer, t33rd node of the as described hidden layer and the output layer it
Between connection weight, tmConnection weight between m-th of the node and the output layer of the as described hidden layer.Similarly it is found that
WijConnection weight between i-th of node of the as described hidden layer and j-th of node of the input layer.By to the BP
Neural network model is trained, and can be correspondingly made available tiAnd WijValue, i.e., training obtain each layer of BP neural network model
Parameter, the load estimation model so can be obtained.
Step S13, the current system log of the monitored object is obtained, and feature is carried out to the current system log and is mentioned
Obtain multiple characteristics to be measured.
In one embodiment, the current system log describes the current operating parameter of the monitored object.Right
It, equally can be according to multiple preset keyword sections from the current system log when current system log carries out feature extraction
Middle extraction obtains and multiple matched multiple characteristics to be measured of preset keyword.
Step S14, multiple characteristics to be measured the load estimation model is input to obtain and the monitoring pair
As corresponding prediction loads.
In one embodiment, the training by step S12 to neural network model, the load estimation model can be real
Now the current operating environment of the monitored object is predicted.It at this time can be using multiple characteristics to be measured as described in
The output of the load estimation model is considered as prediction load by the input of load estimation model, and the prediction load can refer to
Operating status of the monitored object under currently running system or software.
Step S15, multiple fixed reference feature data of the monitored object are obtained, and multiple fixed reference feature data are defeated
Enter to the load estimation model and obtains reference load corresponding with the monitored object, the plurality of fixed reference feature data
For the characteristic threshold value of the available running environment of the monitored object.
In one embodiment, the monitored object has several fixed reference feature data, and the fixed reference feature data can table
Show that the monitored object can support the preferable states of system operation.It is to be measured when the monitored object obtained from current system log
When characteristic is higher than corresponding fixed reference feature data, indicate that the monitored object possibly can not preferably meet system operation and want
It asks.
For example, utilization rate is the percentage that finger processor executes non-idle thread time, threshold values one for CPU
As be set as 85% (as fixed reference feature data)；Interruption rate refers to that the number of device interrupt processor each second, threshold values are general
It is set as 1000 times/second (can be used as fixed reference feature data)；System calling rate, which refers to, operates in all processor call operation system clothes
The overall rate of business routine program, if system calling rate is greater than interruption rate, then it represents that hardware device produces excessively in system
Interruption, it is generally no (can be used as fixed reference feature data)；For memory, memory is generally set to using the threshold value of accounting
90% (can be used as fixed reference feature data).Therefore, it is pre- that the fixed reference feature data of the monitored object can be input to the load
It surveys in model, corresponding reference load can be obtained.
Step S16, the operation warning information of the monitored object is exported with the reference load according to the prediction load.
In one embodiment, can by calculate and judge prediction load and the reference load difference whether
The operation warning information of the monitored object is exported in preset range.When the prediction load and the reference load difference not
When in the preset range, indicate that the monitored object possibly can not provide preferable fortune for currently running system/software
Row environment or currently running system/software have had exceeded the available running environment of the monitored object, export institute at this time
State the operation warning information of monitored object.For example, user can issue migration order according to the operation warning information, with
By currently running system, software or data service migration to other servers.When prediction load and the reference load
Difference in the preset range when, indicate that the monitored object can provide preferable fortune for currently running system/software
Row environment does not export the operation warning information.The preset range can be set according to actual use demand, in turn
The effect to give warning in advance can be played.
Embodiment two:
Fig. 2 is the functional block diagram of present device status early warning system preferred embodiment.
As shown in fig.2, the equipment state early warning system 10 may include the first extraction module 101, model training mould
Block 102, the second extraction module 103, the first computing module 104, the second computing module 105, output module 106 and judgment module
107。
First extraction module 101 is used to obtain the legacy system log of monitored object, and to the legacy system day
Will carries out feature extraction and obtains multiple feature samples data.
In one embodiment, first extraction module 101 can be connected to the monitoring pair by access network
As, and then obtain the legacy system log of the monitored object.The monitored object can be a server or a server set
Group.The server or the server cluster may include several hardware resources (such as: CPU, memory, I/O interface, memory
Deng).The server or the server cluster can run similar and different operating system, database, with software, be
System software.It is to be appreciated that the server cluster can have virtual machine manager (Virtual Machine by multiple operations
Manager, VMM), several physical nodes (Physical Node, PN) constitute, run multiple operating systems on VMM, lead to
The resource scheduling algorithm of VMM is crossed, these operating systems share the resource of physical machine.
The legacy system log can refer to the system log before a scheduled date, for example, the monitored object exists
2018.8.12 all system logs before.When the application software or the system software are run, operating system or VMM meeting
Relevant record is carried out, and then forms system log.
The system log that is generated when in one embodiment, the system log may include the operating system of equipment,
Application log and security log etc.；In one embodiment, can by operating system operation in input
The event viewer of eventvwr.msc calling system is to obtain the system log.In other embodiments, for not
Same operating system, the order for obtaining system log may be different.
In one embodiment, when carrying out feature extraction to the legacy system log, first extraction module 101
It can be extracted from the legacy system log according to multiple preset keyword sections and obtain matching with multiple preset keywords
Multiple feature samples data.
For example, for database, the change in system log recorded data library (for example, MySQL database) is operated,
Including but not limited to create database or table, insertion operation, update operation, delete operation etc., each change operation is with one
In the form write-in journal file of record, system log is formd.Every record may include the timestamp of current record update, be somebody's turn to do
The position (such as offset) being recorded in journal file and other information relevant to database change operation.MySQL data
Usually there is one or more journal file in library, and different journal files uses different digital number shapes by file extension
Formula is distinguish, such as: mysql-bin.00001, mysql-bin.00002.
It may include that (CPU executes non-idle thread time for the utilization rate of CPU for hardware resource, in system log
Percentage), the interruption rate number of device interrupt processor (each second), (system service of CPU call operation is customary for system calling rate
The overall rate of program), memory is using accounting, residual memory space etc..
The model training module 102 is used to be established and be trained according to multiple feature samples data to obtain a load pre-
Survey model.
In one embodiment, the model training module 102, which trains the load estimation model come, can be base
In neural network model and multiple feature samples data.The neural network model can be from information processing angle to human brain
Neuroid is abstracted, and different networks is formed by different connection types, without being determined in advance between input and output
The math equation of mapping relations obtains the result closest to desired output in given input value only by the training of itself.
The neural network model includes input layer, hidden layer and output layer.The history feature data can be used as neural network model
Input layer, using after the connection of the hidden layer of neural network model by output layer export an assessed value.
In one embodiment, the neural network model can be BP (Back Propagation, backpropagation) mind
Through network model, the BP neural network model be it is a kind of based on gradient descent method by error back propagation training multilayer before
Network is presented, using gradient search technology, to make the real output value of network and the error mean square difference minimum of desired output.
In other embodiments of the invention, other kinds of neural network model can also be selected according to actual needs.
In one embodiment, the input layer includes n node, and the hidden layer includes m node, the BP nerve
Network model can indicate are as follows:
Wherein, y is the assessed value of output layer output, when multiple characteristics to be measured are input to the load in advance
When surveying model, the output y of the load estimation model is prediction load, when multiple fixed reference feature data are input to institute
When stating load estimation model, the output y of the load estimation model is the reference load, tiFor the hidden layer with it is described defeated
Connection weight between layer out,(i=1,2,3...m；J=1,2,3...n), SiFor the hidden layer
Input, the output of the as described input layer, WijFor the connection weight between the input layer and the hidden layer, f () is
Activation primitive in the BP neural network model, when the hidden layer has input, activation primitive is expressed as f (Si).It is described
Activation primitive f (Si) S type function (Sigmoid function), f (S can be usedi) can indicate are as follows:
It is to be appreciated that tiIt can indicate the connection weight between i-th of node of the hidden layer and the output layer,
For example, t11st connection weight between node and the output layer of the as described hidden layer, t2The as described hidden layer
2nd connection weight between node and the output layer, t33rd node of the as described hidden layer and the output layer it
Between connection weight, tmConnection weight between m-th of the node and the output layer of the as described hidden layer.Similarly it is found that
WijConnection weight between i-th of node of the as described hidden layer and j-th of node of the input layer.By to the BP
Neural network model is trained, and can be correspondingly made available tiAnd WijValue, i.e., training obtain each layer of BP neural network model
Parameter, the load estimation model so can be obtained.
Second extraction module 103 is used to obtain the current system log of the monitored object, and to the current system
System log carries out feature extraction and obtains multiple characteristics to be measured.
In one embodiment, the current system log describes the current operating parameter of the monitored object.Right
When the current system log carries out feature extraction, second extraction module 103 equally can be according to multiple preset keywords
Section is extracted from the current system log to be obtained and multiple matched multiple characteristics to be measured of preset keyword.
First computing module 104 is obtained for multiple characteristics to be measured to be input to the load estimation model
It is loaded to prediction corresponding with the monitored object.
In one embodiment, the training by step S12 to neural network model, the load estimation model can be real
Now the current operating environment of the monitored object is predicted.First computing module 104 can will be multiple described at this time
Characteristic to be measured is input to the load estimation model, and the output of the load estimation model is considered as prediction load, described
Prediction load can refer to operating status of the monitored object under currently running system or software.
Second computing module 105 is used to obtain multiple fixed reference feature data of the monitored object, and by multiple institutes
It states fixed reference feature data and is input to the load estimation model and obtain reference load corresponding with the monitored object, it is plurality of
The fixed reference feature data are the characteristic threshold value of the available running environment of the monitored object.
In one embodiment, the monitored object has several fixed reference feature data, and the fixed reference feature data can table
Show that the monitored object can support the preferable states of system operation.It is to be measured when the monitored object obtained from current system log
When characteristic is higher than corresponding fixed reference feature data, indicate that the monitored object possibly can not preferably meet system operation and want
It asks.
For example, utilization rate is the percentage that finger processor executes non-idle thread time, threshold values one for CPU
As be set as 85% (as fixed reference feature data)；Interruption rate refers to that the number of device interrupt processor each second, threshold values are general
It is set as 1000 times/second (can be used as fixed reference feature data)；System calling rate, which refers to, operates in all processor call operation system clothes
The overall rate of business routine program, if system calling rate is greater than interruption rate, then it represents that hardware device produces excessively in system
Interruption, it is generally no (can be used as fixed reference feature data)；For memory, memory is generally set to using the threshold value of accounting
90% (can be used as fixed reference feature data).Therefore, it is pre- that the fixed reference feature data of the monitored object can be input to the load
It surveys in model, corresponding reference load can be obtained.
The output module 106 is used to export the fortune of the monitored object with the reference load according to the prediction load
Row warning information.
In one embodiment, the output module 106 can be according to the difference of prediction load and the reference load
Whether the operation warning information of the monitored object exported within a preset range.Specifically, the judgment module 107 is for sentencing
The difference for prediction load and the reference load of breaking whether within a preset range, when the prediction loads and the reference load
Difference not in the preset range when, indicate the monitored object possibly can not be provided for currently running system/software compared with
Good running environment or currently running system/software have had exceeded the available running environment of the monitored object, at this time
The output module 106 exports the operation warning information of the monitored object.For example, user can be pre- according to the operation
Alert delivering migration order, by currently running system, software or data service migration to other servers.When described pre-
When the difference of survey load and the reference load is in the preset range, indicate that the monitored object can be currently running system
System/software provides preferable running environment, does not export the operation warning information.The preset range can make according to actual
It is set with demand, and then the effect to give warning in advance can be played.
Fig. 3 is the schematic diagram of computer installation preferred embodiment of the present invention.
The computer installation 1 includes memory 20, processor 30 and is stored in the memory 20 and can be in institute
State the computer program 40 run on processor 30, such as equipment state early warning program.The processor 30 executes the calculating
The step in above equipment status early warning embodiment of the method, such as step S11~S16 shown in FIG. 1 are realized when machine program 40.Or
Person, the processor 30 realize each module in above equipment status early warning system embodiment when executing the computer program 40
Module 101~107 in function, such as Fig. 2.
Illustratively, the computer program 40 can be divided into one or more module/units, it is one or
Multiple module/units are stored in the memory 20, and are executed by the processor 30, to complete the present invention.Described one
A or multiple module/units can be the series of computation machine program instruction section that can complete specific function, and described instruction section is used
In implementation procedure of the description computer program 40 in the computer installation 1.For example, the computer program 40 can be with
The first extraction module 101, model training module 102, the second extraction module 103, the first computing module being divided into Fig. 2
104, the second computing module 105, output module 106 and judgment module 107.Each module concrete function is referring to embodiment two.
The computer installation 1 can be the calculating such as desktop PC, notebook, palm PC and cloud server and set
It is standby.It will be understood by those skilled in the art that the schematic diagram is only the example of computer installation 1, do not constitute to computer
The restriction of device 1 may include perhaps combining certain components or different components, example than illustrating more or fewer components
Such as described computer installation 1 can also include input-output equipment, network access equipment, bus.
Alleged processor 30 can be central processing unit (Central Processing Unit, CPU), can also be
Other general processors, digital signal processor (Digital Signal Processor, DSP), specific integrated circuit
(Application Specific Integrated Circuit, ASIC), ready-made programmable gate array (Field-
Programmable Gate Array, FPGA) either other programmable logic device, discrete gate or transistor logic,
Discrete hardware components etc..General processor can be microprocessor or the processor 30 is also possible to any conventional processing
Device etc., the processor 30 are the control centres of the computer installation 1, utilize various interfaces and the entire computer of connection
The various pieces of device 1.
The memory 20 can be used for storing the computer program 40 and/or module/unit, and the processor 30 passes through
Operation executes the computer program and/or module/unit being stored in the memory 20, and calls and be stored in memory
Data in 20 realize the various functions of the computer installation 1.The memory 20 can mainly include storing program area and deposit
Store up data field, wherein storing program area can application program needed for storage program area, at least one function (for example sound is broadcast
Playing function, image player function etc.) etc.；Storage data area, which can be stored, uses created data (ratio according to computer installation 1
Such as audio data, phone directory) etc..In addition, memory 20 may include high-speed random access memory, it can also include non-easy
The property lost memory, such as hard disk, memory, plug-in type hard disk, intelligent memory card (Smart Media Card, SMC), secure digital
(Secure Digital, SD) card, flash card (Flash Card), at least one disk memory, flush memory device or other
Volatile solid-state part.
If the integrated module/unit of the computer installation 1 is realized in the form of SFU software functional unit and as independence
Product when selling or using, can store in a computer readable storage medium.Based on this understanding, of the invention
It realizes all or part of the process in above-described embodiment method, can also instruct relevant hardware come complete by computer program
At the computer program can be stored in a computer readable storage medium, and the computer program is held by processor
When row, it can be achieved that the step of above-mentioned each embodiment of the method.Wherein, the computer program includes computer program code, institute
Stating computer program code can be source code form, object identification code form, executable file or certain intermediate forms etc..It is described
Computer-readable medium may include: any entity or device, recording medium, U that can carry the computer program code
Disk, mobile hard disk, magnetic disk, CD, computer storage, read-only memory (ROM, Read-Only Memory), arbitrary access
Memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium etc..It needs
It is bright, the content that the computer-readable medium includes can according in jurisdiction make laws and patent practice requirement into
Row increase and decrease appropriate, such as do not include electric load according to legislation and patent practice, computer-readable medium in certain jurisdictions
Wave signal and telecommunication signal.
In several embodiments provided by the present invention, it should be understood that disclosed computer installation and method, it can be with
It realizes by another way.For example, computer installation embodiment described above is only schematical, for example, described
The division of unit, only a kind of logical function partition, there may be another division manner in actual implementation.
It, can also be in addition, each functional unit in each embodiment of the present invention can integrate in same treatment unit
It is that each unit physically exists alone, can also be integrated in same unit with two or more units.Above-mentioned integrated list
Member both can take the form of hardware realization, can also realize in the form of hardware adds software function module.
It is obvious to a person skilled in the art that invention is not limited to the details of the above exemplary embodiments, Er Qie
In the case where without departing substantially from spirit or essential attributes of the invention, the present invention can be realized in other specific forms.Therefore, no matter
From the point of view of which point, the present embodiments are to be considered as illustrative and not restrictive, and the scope of the present invention is by appended power
Benefit requires rather than above description limits, it is intended that all by what is fallen within the meaning and scope of the equivalent elements of the claims
Variation is included in the present invention.Any reference signs in the claims should not be construed as limiting the involved claims.This
Outside, it is clear that one word of " comprising " does not exclude other units or steps, and odd number is not excluded for plural number.It is stated in computer installation claim
Multiple units or computer installation can also be implemented through software or hardware by the same unit or computer installation.The
One, the second equal words are used to indicate names, and are not indicated any particular order.
Finally it should be noted that the above examples are only used to illustrate the technical scheme of the present invention and are not limiting, although reference
Preferred embodiment describes the invention in detail, those skilled in the art should understand that, it can be to of the invention
Technical solution is modified or equivalent replacement, without departing from the spirit and scope of the technical solution of the present invention.
Claims (10)
1. a kind of equipment state method for early warning, which is characterized in that the described method includes:
The legacy system log of monitored object is obtained, and feature extraction is carried out to the legacy system log and obtains multiple feature samples
Notebook data；
It is established according to multiple feature samples data and trains to obtain a load estimation model；
Obtain the current system log of the monitored object, and to the current system log carry out feature extraction obtain it is multiple to
Survey characteristic；
Multiple characteristics to be measured are input to the load estimation model and obtain prediction corresponding with the monitored object
Load；
Multiple fixed reference feature data of the monitored object are obtained, and multiple fixed reference feature data are input to the load
Prediction model obtains reference load corresponding with the monitored object, and the plurality of fixed reference feature data are the monitoring pair
As the characteristic threshold value of available running environment；And
The operation warning information of the monitored object is exported with the reference load according to the prediction load.
2. equipment state method for early warning as described in claim 1, which is characterized in that described to be carried out to the legacy system log
Feature extraction obtains the step of multiple feature samples data and includes:
It is extracted from the legacy system log according to multiple preset keyword sections and obtains matching with multiple preset keywords
Multiple feature samples data.
3. equipment state method for early warning as claimed in claim 2, which is characterized in that described to be carried out to the current system log
Feature extraction obtains multiple characteristics to be measured
It is extracted and is obtained and multiple preset keywords from the current system log according to multiple preset keywords
The multiple characteristics to be measured matched.
4. equipment state method for early warning as claimed in any one of claims 1-3, which is characterized in that the load estimation model
For BP neural network model, the BP neural network model includes input layer, hidden layer and output layer, and the input layer includes n
A node, the hidden layer include m node, the BP neural network model are as follows:
Wherein, y is the assessed value of output layer output, when multiple characteristics to be measured are input to the load estimation mould
When type, the output y of the load estimation model is prediction load, when multiple fixed reference feature data are input to described bear
When carrying prediction model, the output y of the load estimation model is the reference load, tiFor the hidden layer and the output layer
Between connection weight, For the input of the hidden layer,
The output of the as described input layer, WijFor the connection weight between the input layer and the hidden layer；f(Si) it is the BP mind
Through the activation primitive in network model,
5. equipment state method for early warning as described in claim 1, which is characterized in that the feature samples data, the reference
Characteristic and the characteristic to be measured are the hardware resource data of the monitored object.
6. equipment state method for early warning as described in claim 1, which is characterized in that it is described according to the prediction load with it is described
Reference load exports the step of operation warning information of the monitored object and includes:
Whether within a preset range to judge the difference of prediction load and the reference load；And
When the difference of prediction load and the reference load is not in the preset range, the fortune of the monitored object is exported
Row warning information.
7. equipment state method for early warning as claimed in claim 6, which is characterized in that described when prediction load and the ginseng
When examining the difference of load not in the preset range, the step of exporting the operation warning information of the monitored object, includes:
When the difference of prediction load and the reference load is not in the preset range, according to prediction load and institute
The size for stating the difference of reference load exports different grades of operation warning information.
8. a kind of equipment state early warning system, which is characterized in that the system comprises:
First extraction module carries out feature for obtaining the legacy system log of monitored object, and to the legacy system log
Extraction obtains multiple feature samples data；
Model training module, for being established according to multiple feature samples data and training to obtain a load estimation model；
Second extraction module is carried out for obtaining the current system log of the monitored object, and to the current system log
Feature extraction obtains multiple characteristics to be measured；
First computing module obtains and the prison for multiple characteristics to be measured to be input to the load estimation model
Control the corresponding prediction load of object；
Second computing module, for obtaining multiple fixed reference feature data of the monitored object, and by multiple fixed reference features
Data are input to the load estimation model and obtain reference load corresponding with the monitored object, plurality of described with reference to special
Levy the characteristic threshold value that data are the available running environment of the monitored object；And
Output module, the operation early warning for exporting the monitored object with the reference load according to the prediction load are believed
Breath.
9. a kind of computer installation, the computer installation includes processor and memory, is stored on the memory several
Computer program, which is characterized in that such as right is realized when the processor is for executing the computer program stored in memory
It is required that described in any one of 1-7 the step of equipment state method for early warning.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
The step of equipment state method for early warning as described in any one of claim 1-7 is realized when being executed by processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811289825.4A CN109669837A (en) | 2018-10-31 | 2018-10-31 | Equipment state method for early warning, system, computer installation and readable storage medium storing program for executing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811289825.4A CN109669837A (en) | 2018-10-31 | 2018-10-31 | Equipment state method for early warning, system, computer installation and readable storage medium storing program for executing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109669837A true CN109669837A (en) | 2019-04-23 |
Family
ID=66141772
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811289825.4A Pending CN109669837A (en) | 2018-10-31 | 2018-10-31 | Equipment state method for early warning, system, computer installation and readable storage medium storing program for executing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109669837A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110389840A (en) * | 2019-07-25 | 2019-10-29 | 中国工商银行股份有限公司 | Load consumption method for early warning, device, computer equipment and storage medium |
| CN110738120A (en) * | 2019-09-17 | 2020-01-31 | 平安科技（深圳）有限公司 | Environment data adjusting method and device, electronic equipment and medium |
| CN110955586A (en) * | 2019-11-27 | 2020-04-03 | 中国银行股份有限公司 | System fault prediction method, device and equipment based on log |
| CN111078500A (en) * | 2019-12-11 | 2020-04-28 | 何晨 | Method and device for adjusting operation configuration parameters, computer equipment and storage medium |
| CN111200649A (en) * | 2019-12-30 | 2020-05-26 | 北京知道创宇信息技术股份有限公司 | Scheduling method and device and scheduling model generation method and device |
| CN111262728A (en) * | 2020-01-08 | 2020-06-09 | 国网福建省电力有限公司 | Flow load monitoring system based on log port flow |
| CN111708682A (en) * | 2020-06-17 | 2020-09-25 | 腾讯科技（深圳）有限公司 | Data prediction method, device, equipment and storage medium |
| CN111756455A (en) * | 2019-12-26 | 2020-10-09 | 广州极飞科技有限公司 | Method and related device for early warning connection state of electronic equipment and reference station |
| CN112529733A (en) * | 2020-12-07 | 2021-03-19 | 云南电网有限责任公司普洱供电局 | Power distribution network operation safety remote control method, device, equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160379112A1 (en) * | 2015-06-29 | 2016-12-29 | Microsoft Technology Licensing, Llc | Training and operation of computational models |
| CN106650919A (en) * | 2016-12-23 | 2017-05-10 | 国家电网公司信息通信分公司 | Information system fault diagnosis method and device based on convolutional neural network |
| CN107526666A (en) * | 2017-07-17 | 2017-12-29 | 阿里巴巴集团控股有限公司 | Alarm method, system, device and electronic equipment based on deep learning |
| CN108388503A (en) * | 2018-02-13 | 2018-08-10 | 中体彩科技发展有限公司 | Data-base performance monitoring method, system, equipment and computer readable storage medium |
| CN108427720A (en) * | 2018-02-08 | 2018-08-21 | 中国科学院计算技术研究所 | System log sorting technique |
-
2018
- 2018-10-31 CN CN201811289825.4A patent/CN109669837A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160379112A1 (en) * | 2015-06-29 | 2016-12-29 | Microsoft Technology Licensing, Llc | Training and operation of computational models |
| CN106650919A (en) * | 2016-12-23 | 2017-05-10 | 国家电网公司信息通信分公司 | Information system fault diagnosis method and device based on convolutional neural network |
| CN107526666A (en) * | 2017-07-17 | 2017-12-29 | 阿里巴巴集团控股有限公司 | Alarm method, system, device and electronic equipment based on deep learning |
| CN108427720A (en) * | 2018-02-08 | 2018-08-21 | 中国科学院计算技术研究所 | System log sorting technique |
| CN108388503A (en) * | 2018-02-13 | 2018-08-10 | 中体彩科技发展有限公司 | Data-base performance monitoring method, system, equipment and computer readable storage medium |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110389840B (en) * | 2019-07-25 | 2022-02-01 | 中国工商银行股份有限公司 | Load consumption early warning method and device, computer equipment and storage medium |
| CN110389840A (en) * | 2019-07-25 | 2019-10-29 | 中国工商银行股份有限公司 | Load consumption method for early warning, device, computer equipment and storage medium |
| CN110738120A (en) * | 2019-09-17 | 2020-01-31 | 平安科技（深圳）有限公司 | Environment data adjusting method and device, electronic equipment and medium |
| CN110738120B (en) * | 2019-09-17 | 2024-02-09 | 平安科技（深圳）有限公司 | Environment data adjustment method and device, electronic equipment and medium |
| CN110955586A (en) * | 2019-11-27 | 2020-04-03 | 中国银行股份有限公司 | System fault prediction method, device and equipment based on log |
| CN111078500A (en) * | 2019-12-11 | 2020-04-28 | 何晨 | Method and device for adjusting operation configuration parameters, computer equipment and storage medium |
| CN111756455A (en) * | 2019-12-26 | 2020-10-09 | 广州极飞科技有限公司 | Method and related device for early warning connection state of electronic equipment and reference station |
| CN111756455B (en) * | 2019-12-26 | 2022-09-13 | 广州极飞科技股份有限公司 | Method and related device for early warning connection state of electronic equipment and reference station |
| CN111200649B (en) * | 2019-12-30 | 2023-03-24 | 北京知道创宇信息技术股份有限公司 | Scheduling method and device and scheduling model generation method and device |
| CN111200649A (en) * | 2019-12-30 | 2020-05-26 | 北京知道创宇信息技术股份有限公司 | Scheduling method and device and scheduling model generation method and device |
| CN111262728A (en) * | 2020-01-08 | 2020-06-09 | 国网福建省电力有限公司 | Flow load monitoring system based on log port flow |
| CN111708682A (en) * | 2020-06-17 | 2020-09-25 | 腾讯科技（深圳）有限公司 | Data prediction method, device, equipment and storage medium |
| CN112529733A (en) * | 2020-12-07 | 2021-03-19 | 云南电网有限责任公司普洱供电局 | Power distribution network operation safety remote control method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109669837A (en) | Equipment state method for early warning, system, computer installation and readable storage medium storing program for executing | |
| CN104750768B (en) | Method and system for identification, monitoring and ranking event from social media | |
| CN108304250A (en) | Method and apparatus for the node for determining operation machine learning task | |
| US20210042628A1 (en) | Building a federated learning framework | |
| CN107918600A (en) | report development system and method, storage medium and electronic equipment | |
| CN111489095B (en) | Risk user management method, apparatus, computer device and storage medium | |
| CN109598434A (en) | Abnormity early warning method, apparatus, computer installation and storage medium | |
| Pan et al. | Research on dependability of cloud computing systems | |
| CN109542714A (en) | Method for monitoring application program and device, computer installation and computer storage medium | |
| CN109241096A (en) | Data processing method, device and system | |
| CN111090686B (en) | Data processing method, device, server and storage medium | |
| CN111383100A (en) | Risk model-based full life cycle management and control method and device | |
| CN109683880A (en) | Webpage exchange method, device, equipment and storage medium | |
| CN110689225A (en) | Enterprise financial risk portrait creation method based on outbound call and related equipment | |
| CN114707002A (en) | Disaster emergency decision generation method, device, equipment and storage medium | |
| CN109800124A (en) | CPU usage monitoring method, device, electronic equipment and storage medium | |
| CN109446278A (en) | A kind of big data management platform system based on block chain | |
| CN117435999A (en) | Risk assessment method, apparatus, device and medium | |
| Ranganathan et al. | An automated decision support system based on game theoretic optimization for emergency management in urban environments | |
| US11783221B2 (en) | Data exposure for transparency in artificial intelligence | |
| CN114300082B (en) | Information processing method and device and computer readable storage medium | |
| CN114267440B (en) | Medical order information processing method and device and computer readable storage medium | |
| CN111651652B (en) | Emotion tendency identification method, device, equipment and medium based on artificial intelligence | |
| CN115221892A (en) | Work order data processing method and device, storage medium and electronic equipment | |
| Liu et al. | Towards dynamic reconfiguration of composite services via failure estimation of general and domain quality of services |
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 |
Application publication date: 20190423 |
|
| RJ01 | Rejection of invention patent application after publication |