CN109948937A - Security risk detection method, system, equipment and the medium of artificial intelligence self study - Google Patents
Security risk detection method, system, equipment and the medium of artificial intelligence self study Download PDFInfo
- Publication number
- CN109948937A CN109948937A CN201910228163.8A CN201910228163A CN109948937A CN 109948937 A CN109948937 A CN 109948937A CN 201910228163 A CN201910228163 A CN 201910228163A CN 109948937 A CN109948937 A CN 109948937A
- Authority
- CN
- China
- Prior art keywords
- model
- disaggregated model
- target component
- existing
- new
- 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.)
- Granted
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 43
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 32
- 238000012544 monitoring process Methods 0.000 claims abstract description 94
- 230000006870 function Effects 0.000 claims description 63
- 238000000034 method Methods 0.000 claims description 32
- 238000012545 processing Methods 0.000 claims description 20
- 238000004590 computer program Methods 0.000 claims description 5
- 230000032683 aging Effects 0.000 claims description 4
- 230000002159 abnormal effect Effects 0.000 description 28
- 230000005611 electricity Effects 0.000 description 7
- 230000008569 process Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 230000005291 magnetic effect Effects 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 230000004069 differentiation Effects 0.000 description 3
- 238000011835 investigation Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 230000010485 coping Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000009413 insulation Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
Landscapes
- Alarm Systems (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The embodiment of the invention discloses security risk detection method, system, equipment and the media of a kind of artificial intelligence self study, which comprises obtains the monitoring data of electrical system；If the monitoring data meet the first preset condition, at least one target component is determined based on the monitoring data；Judge to whether there is and the matched disaggregated model of at least one target component in existing model library according to the parameter type of at least one target component and numberical range, if it exists, then based on the hidden danger classification for obtaining security risk existing for the electrical system with the matched disaggregated model of at least one target component；If establishing new disaggregated model based at least one described target component, and new disaggregated model is added to the existing model library there is no with the matched disaggregated model of at least one target component in existing model library.By using above-mentioned technical proposal, the active detecting to the potential security risk of electrical system is realized.
Description
Technical field
The present embodiments relate to electrical safety technical field more particularly to a kind of security risks of artificial intelligence self study
Detection method, system, equipment and medium.
Background technique
With the development of modern science and technology, electric energy has been correspondingly made available extensive development and utilization.Electric energy is answered extensively
With both having benefited human society, while huge security risk also is brought to human society.Electrical fire is relatively conventional
A kind of electrical disaster, the heat for being often referred to release after breaking down because of electric wiring, electrical equipment and power supplying and distributing equipment draw
Fire fire caused by electrical ontology or other combustibles.Due to the particularity of electrical fire, do not occur electrical fire it
Before, it does not see, touches less than causing electric fire disaster warning difficulty larger.
At this stage, it is long-term to be mainly based upon residual-current electrical fire monitoring system for common electric fire disaster warning method
Constantly perhaps temperature is when residual current or temperature are more than given threshold to the residual current of real-time monitoring electric wiring, then
It alarms, otherwise, does not alarm immediately.
As it can be seen that above-mentioned electric fire disaster warning method will not actively detect the security risk of electrical system, and therefore, nothing
Method detects in time has not yet been reached the potential security risk for causing fire existing for electrical system.
Summary of the invention
The embodiment of the present invention provides security risk detection method, system, equipment and the medium of a kind of artificial intelligence self study,
The accurate detection to the potential security risk of electrical system is realized by the method.
In a first aspect, the embodiment of the invention provides a kind of security risk detection method of artificial intelligence self study, it is described
Method includes:
Obtain the monitoring data of electrical system；
If the monitoring data meet the first preset condition, determine that at least one target is joined based on the monitoring data
Number；
Judge whether deposit in existing model library according to the parameter type of at least one target component and numberical range
With the matched disaggregated model of at least one target component, and if it exists, then be based on and at least one described target component
The disaggregated model matched obtains the hidden danger classification of security risk existing for the electrical system；
If in existing model library there is no with the matched disaggregated model of at least one target component, based on it is described extremely
A few target component establishes new disaggregated model, and new disaggregated model is added to the existing model library.
Further, new disaggregated model is established based at least one described target component, and new disaggregated model is added
Add to the existing model library, comprising:
Receive the new disaggregated model established based at least one described target component；
The new disaggregated model is matched with each model in existing model library, with judge whether there is with it is described new
The identical existing model of the function of disaggregated model；
If it exists, then by the new disaggregated model existing model combination identical with function.
Further, the new disaggregated model is matched with each model in existing model library, to judge whether to deposit
In existing model identical with the function of the new disaggregated model, comprising:
The corresponding processing mode of new disaggregated model processing mode corresponding with model each in existing model library is carried out
Matching, if matching similarity reaches given threshold, it is determined that there is existing model identical with the function of the new disaggregated model；
And/or
It will be each in the parameter type of the corresponding target component of the new disaggregated model and numberical range and existing model library
The parameter type and numberical range of the corresponding target component of model are matched, if matching similarity reaches given threshold,
Determine there is existing model identical with the function of the new disaggregated model.
Further, by the new disaggregated model existing model combination identical with function, comprising:
The new disaggregated model existing model identical with function is associated storage.
Further, existing model identical with the function of the new disaggregated model if it does not exist, then by the new classification
Model is matched with each newly-increased disaggregated model in newly-increased model library, to judge whether there is and the new disaggregated model function
Identical newly-increased disaggregated model；
If it exists, then the new disaggregated model newly-increased disaggregated model identical with function is merged, otherwise, by described new point
Class model is added to newly-increased model library.
Further, after the new disaggregated model newly-increased disaggregated model identical with function being merged, further includes:
If the quantity of the identical newly-increased disaggregated model of function reaches given threshold, by the identical newly-increased classification mould of the function
Type is added to the existing model library.
Further, if the monitoring data are unsatisfactory for the first preset condition, by the monitoring data according to default rule
Then stored；The target component includes: phase temperature, phase current, reactive power, power factor or phase temperature increment and phase
At least one of ratio of current increment；
The hidden danger classification includes: poor contact, short circuit, electric leakage, overload and at least one of circuit aging.
Second aspect, it is described the embodiment of the invention provides a kind of Security Vulnerability Detecting System of artificial intelligence self study
System includes:
Module is obtained, for obtaining the monitoring data of electrical system；
Determining module is determined extremely if meeting the first preset condition for the monitoring data based on the monitoring data
A few target component；
Judgment module, for judging existing mould according to the parameter type and numberical range of at least one target component
It whether there is and the matched disaggregated model of at least one target component in type library；
Detection module, for if it exists with the matched disaggregated model of at least one target component, then based on it is described
The matched disaggregated model of at least one target component obtains the hidden danger classification of security risk existing for the electrical system；
Module is established, if for being not present and the matched classification mould of at least one described target component in existing model library
Type then establishes new disaggregated model based at least one described target component, and new disaggregated model is added to described existing
Model library.
The third aspect the embodiment of the invention provides a kind of electronic equipment, including memory, processor and is stored in storage
On device and the computer program that can run on a processor, realize that such as right is wanted when the processor executes the computer program
Seek the security risk detection method of the described in any item artificial intelligence self studies of 1-7.
Fourth aspect, the embodiment of the invention provides a kind of storage medium comprising computer executable instructions, the meters
Calculation machine executable instruction realizes that the described in any item artificial intelligence of claim 1-7 such as are learnt by oneself when being executed by computer processor
The security risk detection method of habit.
The security risk detection method of a kind of artificial intelligence self study provided in an embodiment of the present invention, by obtaining electrical system
The monitoring data of system；If the monitoring data meet the first preset condition, at least one mesh is determined based on the monitoring data
Mark parameter；Judge to whether there is in existing model library according to the parameter type of at least one target component and numberical range
With the matched disaggregated model of at least one target component, and if it exists, be then based on matching at least one described target component
Disaggregated model obtain the hidden danger classification of security risk existing for the electrical system；If in existing model library there is no with it is described
The matched disaggregated model of at least one target component then establishes new disaggregated model based at least one described target component, and
New disaggregated model is added to the technological means of the existing model library, solves electric fire disaster warning method in the prior art
It the problem of actively security risk of electrical system will not being detected, realizes and is had not yet been reached to existing for a variety of electrical systems
Cause the timely detection of the potential security risk of fire.
Detailed description of the invention
To describe the technical solutions in the embodiments of the present invention more clearly, institute in being described below to the embodiment of the present invention
Attached drawing to be used is needed to be briefly described, it should be apparent that, the accompanying drawings in the following description is only some implementations of the invention
Example, for those of ordinary skill in the art, without creative efforts, can also implement according to the present invention
The content of example and these attached drawings obtain other attached drawings.
Fig. 1 is a kind of security risk detection method process signal for artificial intelligence self study that the embodiment of the present invention one provides
Figure；
Fig. 2 is a kind of flow diagram for method for processing abnormal data that the embodiment of the present invention one provides；
Fig. 3 is a kind of security risk detection method process signal of artificial intelligence self study provided by Embodiment 2 of the present invention
Figure；
Fig. 4 is a kind of Security Vulnerability Detecting System structural representation for artificial intelligence self study that the embodiment of the present invention three provides
Figure；
Fig. 5 is the structural schematic diagram for a kind of electronic equipment that the embodiment of the present invention four provides.
Specific embodiment
To keep the technical problems solved, the adopted technical scheme and the technical effect achieved by the invention clearer, below
It will the technical scheme of the embodiment of the invention will be described in further detail in conjunction with attached drawing, it is clear that described embodiment is only
It is a part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those skilled in the art exist
Every other embodiment obtained under the premise of creative work is not made, shall fall within the protection scope of the present invention.
Embodiment one
Fig. 1 is a kind of security risk detection method process signal for artificial intelligence self study that the embodiment of the present invention one provides
Figure.The detection method of fire safety evaluating hidden danger disclosed in the present embodiment is suitable for the potential safety to the electrical system various scenes
The case where hidden danger is detected, the various scenes for example can be market, hospital, factory, hotel, house, office building, amusement
The security risk detection method of place, warehouse or school etc., the artificial intelligent self-learning can be by artificial intelligence self study
Security Vulnerability Detecting System executes, and wherein the system can be implemented by software and/or hardware, and be typically integrated in terminal, example
Such as server.Referring specifically to shown in Fig. 1, this method be may include steps of:
110, the monitoring data of electrical system are obtained.
Wherein, the monitoring data and electrical system when the monitoring data of electrical system include electrical system operation are because failure is stopped
Monitoring data when machine.It, can be because of electric wiring, electrical equipment and power supplying and distributing equipment since electrical system is in power supply process
It breaks down and releases amount of heat, to ignite electrical ontology or other combustibles and lead to fire, in order to ensure electricity
The safety of gas system can actively obtain the monitoring data of electrical system at regular intervals, and be based on the monitoring data
The safety of electrical system is analyzed, to determine that electrical system there are when security risk, takes corresponding measure, really in time
Protect the safety of electrical system.Wherein, the monitoring data include but is not limited to following data, as current data, temperature data and
Power data etc. may there is also new monitoring data with constantly bringing forth new ideas for electrical system.
Specifically, the monitoring data can be obtained by the sensor configured in electrical system corresponding position, such as logical
It crosses and configures the temperature data that the temperature sensor in electric wiring obtains monitored route, or by configuring in electric wiring
In detector obtain the residual circuit data etc. of monitored route.
Illustratively, the monitoring data of electrical system are obtained, comprising:
Obtain the monitoring data of electrical system in real time according to setpoint frequency by monitoring terminal；
Wherein, the monitoring terminal is to configure to be used to monitor the various electrical nature numbers of electrical system in electrical system front end
According to equipment.Monitor terminal monitoring frequency can self-setting, the superperformance for monitoring terminal ensures the multiplicity of monitoring data
Property and accuracy, the present embodiment not to monitoring terminal structure and monitoring mode be defined, as long as wide variety can be obtained
And accurate monitoring data.After monitoring terminal acquisition monitoring data, further monitoring data can be packaged and be uploaded to cloud
Server completes subsequent data differentiation, verification, target component calculating and the detection of hidden danger classification by Cloud Server；Or
After monitoring terminal acquisition monitoring data, the behaviour that subsequent data differentiation, verification and target component calculate is completed by monitoring terminal
Make, and by calculated result, i.e. target component is uploaded to Cloud Server, the detection of hidden danger classification is carried out by Cloud Server.
If 120, the monitoring data meet the first preset condition, at least one target is determined based on the monitoring data
Parameter.
Wherein, first preset condition specifically can be a numberical range or numerical intervals, can also be specific
Data attribute mark.For example, first preset condition is specific when the monitoring data are the residual current of electric wiring
It can be the current values range obtained according to regulation of the national standard to electric wiring residual current, such as [300mA-
1000mA], if the residual current monitored is fallen in the numberical range, it is determined that the monitoring data meet the first default item
Otherwise part determines that the monitoring data are unsatisfactory for the first preset condition.
Further, the monitoring data include electrical system operation when data and electrical system due to failure and
Data when shutdown, and it is used to determine the data when data of electrical system security risk are electrical system operation, so described
First preset condition specifically can also be the attribute-bit for belonging to data when electrical system is run for identifying monitoring data, if
The attribute-bit of the data monitored is consistent with the attribute-bit of data when belonging to electrical system operation, it is determined that the monitoring
Data meet the first preset condition.It should be noted that when the monitoring data of acquisition are uploaded to Cloud Server by monitoring terminal,
Attribute-bit would generally be added to monitoring data, to identify monitoring data when current monitoring data are electrical system operations,
Or monitoring data when electrical system is shut down.
If the monitoring data meet the first preset condition, determine that at least one target is joined based on the monitoring data
Number, specifically, the monitoring data refer to that the initial data when electrical system monitored is run, the target component refer to for dividing
Analyse electrical system can be with the presence or absence of security risk and the data of the corresponding hidden danger classification of security risk, the target component
Described monitoring data itself, such as monitoring data are the temperature value of electric wiring, meanwhile, the target component is also electric wiring
Temperature value；The target component can also be to be obtained by carrying out certain calculation process to the monitoring data.
Illustratively, at least one target component is determined based on the monitoring data, comprising:
The monitoring data are calculated according to preset formula, to determine at least one target component.
Such as when the monitoring data include line current, the target component be can be based on line current according to line current
The phase current for certain phase that conversion formula between phase current is calculated or the target component are being averaged for line current
Value；When the monitoring data include electric current and voltage, the target component be can be by electric current, voltage based on according to power
Calculate the power data that formula obtains；It, can be according to preset formula when the monitoring data include: phase temperature T and phase current I
(K2=T/I) ratio K 2 of phase temperature T and phase current I is calculated, K2 is then the target component.Preferably, the target component
Include: in the ratio of phase temperature, phase current, reactive power, power factor or phase temperature increment and phase current increment at least
One.
If the monitoring data are unsatisfactory for the first preset condition, then it is assumed that the monitoring data are abnormal data, will be described
Abnormal data is stored according to preset rules.Specifically, a kind of process of the processing method of abnormal data shown in Figure 2
Schematic diagram, described method includes following steps:
210, whether effective judge the abnormal data, if so, step 220 is continued to execute, it is no to then follow the steps 260.
By the monitoring data be electrical system run when current data for, if it is the currently monitored to current data be
2000mA, it is clear that it is unsatisfactory for the first preset condition ([300mA-1000mA]), therefore the current data is abnormal data, due to the electricity
Flow data belongs to data when electrical system operation, therefore the current data is valid data, at this point, then saving the current data
To exception database, and exception information warning is generated, to remind relevant person in charge to carry out safe investigation to electrical system.If the electricity
Flow data belongs to data when electrical system is shut down because of failure, it is determined that the current data is invalid data, and directly rejecting is
It can.
220, the abnormal data is saved to exception database, and generates exception information warning, to remind related be responsible for
People carries out safe investigation to electrical system, continues to execute step 230.
230, judge whether the abnormal data can merge with abnormal data existing in exception database, if so,
Step 240a is executed, it is no to then follow the steps 240b.
Judge whether the abnormal data can merge with abnormal data existing in exception database, specially judges different
With the presence or absence of the existing abnormal data for being in identical numberical range with the abnormal data in regular data library, and if it exists, then determine
In the presence of the matched data that can merge with the abnormal data, then the abnormal data is merged with matched data, merging
Essence are as follows: the abnormal data and matched data correlation are stored, its purpose is to identify the abnormal data with match
Data can represent identical security risk, facilitate engineering staff carry out hidden troubles removing, the matched data refer to and institute
State the existing abnormal data that abnormal data is in identical numberical range.
240a, the abnormal data and matched existing abnormal data are merged, and judges the abnormal number after merging
According to the frequency of appearance, if the frequency reaches given threshold, step 250a is continued to execute, it is no to then follow the steps 250b.
The frequency that abnormal data after merging occurs is higher, illustrates that hidden danger corresponding with the abnormal data occurs in electrical system
A possibility that it is bigger.
240b, it is stored in the abnormal data as new abnormal data in exception database.
250a, using the abnormal data after the merging as new hidden danger classification parameter, and update hidden danger classification parameter number
According to library.When engineering staff determines the corresponding hidden danger classification of the hidden danger classification parameter, then by the hidden danger classification parameter with it is corresponding
Hidden danger classification save as new disaggregated model into existing model library, with the model kind in existing model library of enriching constantly
Class improves the classification feature of existing model library.
250b, the abnormal data after the merging is saved to exception database.
260, it rejects.
130, judging to have in model library according to the parameter type of at least one target component and numberical range is
It is no to exist and the matched disaggregated model of at least one target component, and if it exists, to then follow the steps 140；If it does not exist, then it holds
Row step 150.
Wherein, the parameter type of the target component refers specifically to the meaning of parameter, such as parameter type can be electric current, temperature
Degree or power etc..Each disaggregated model in existing model library, which specifically can be, pre- to be first passed through a large amount of training sample and is trained
Obtained one or more kinds of network models, the training sample include target component and are electrically when having the target component
Hidden danger classification, the network model existing for uniting for example may is that deep neural network model or convolutional neural networks model
Deng.Each disaggregated model in existing model library can also be pair between predetermined target component and corresponding hidden danger classification
Should be related to, for example, when target component include: the temperature of A phase, the electric current of A phase, the temperature increment of A phase and phase current increment ratio
Value, when reactive power and power factor, the corresponding relationship between target component and corresponding hidden danger classification can be found in 1 institute of table
Show:
Table 1: the corresponding relationship between target component and corresponding hidden danger classification
It should be noted that above-mentioned table 1 only serves exemplary, the present embodiment is not defined.
As a result, after getting at least one described target component, judge in existing model library with the presence or absence of with it is described
The matched disaggregated model of at least one target component, specifically, the parameter type based at least one target component and
Corresponding numberical range judges to whether there is matched disaggregated model in existing model library, and if it exists, then call with it is described at least
One matched disaggregated model of target component, obtains the hidden of security risk existing for current electrical system based on the disaggregated model
Suffer from classification.
140, it is based on obtaining with the matched disaggregated model of at least one described target component and pacify existing for the electrical system
The hidden danger classification of full hidden danger.
Exist specifically, obtaining current electrical system based on the corresponding relationship between target component and corresponding hidden danger classification
Security risk hidden danger classification.Wherein, the hidden danger classification include: poor contact, short circuit, electric leakage, overload, it is circuit aging,
Use at least one of high-power electric appliance, combustibles accumulation and insulation damages.It should be noted that with application scenarios
Increase, there is also many new hidden danger classifications, however it is not limited to above-mentioned several.
Further, the disaggregated model can also provide the corresponding processing mode of hidden danger classification, such as hidden danger classification is " electricity
When road aging ", corresponding processing mode is " replacing line wires in time " etc., and the disaggregated model can also provide hidden danger classification pair
The hidden danger rank answered then can further trigger alarm at this time and carry out early warning, to improve phase for example, electric leakage rank is " serious "
The attention of pass personnel.
150, new disaggregated model is established based at least one described target component, and new disaggregated model is added to institute
State existing model library.
If in existing model library there is no with the matched disaggregated model of at least one target component, can be by artificial
Investigation, or by the self-learning function of neural network, determine hidden danger classification existing for current electrical system, and by described at least
One target component is supplemented in model library with corresponding hidden danger classification as new disaggregated model, constantly to enrich model library
In disaggregated model, improve model library in disaggregated model classification feature.
Based on the above technical solution, further, according to the parameter type of at least one target component with
And numberical range judge in existing model library with the presence or absence of with before the matched disaggregated model of at least one target component, institute
The method of stating can also include:
Judge the electrical system with the presence or absence of security risk according at least one described target component, and if it exists, then after
It is continuous execute described in " according to the parameter type of at least one target component and numberical range judge in existing model library whether
In the presence of with the matched disaggregated model of at least one target component " the step of.Illustratively, according at least one described target
Parameter judges the electrical system with the presence or absence of security risk, comprising:
Determine the electrical system with the presence or absence of security risk according to the grade of the target component, it is assumed for example that the mesh
The temperature that parameter is certain phase is marked, and corresponding temperature value is 50 degree, obtaining grade discrimination result by grade discrimination is 2 grades, is reached
To security risk rank, it is thus determined that there are security risks for current electrical system；If corresponding temperature value is 10 degree, by grade
It is 0 grade, not up to security risk rank that differentiation, which obtains grade discrimination result, it is thus determined that there is no safety is hidden for current electrical system
Suffer from.
Alternatively, judging whether the setting key value at least one described target component is more than given threshold, if so, really
There are security risks for the fixed electrical system.Wherein, the setting key value can be the temperature in a parameter, such as the example above
Angle value, can also be the combination between several parameters, such as when temperature reaches 30 degree, while phase current reaches 100mA, it is determined that
There are security risks for current electrical system.The setting key value and corresponding threshold value can be configured according to engineering experience.
If it is determined that there are security risks for current electrical system, then further progress security even analysis, executes step
130, to determine hidden danger classification, and countermeasure can be taken according to hidden danger classification, to avoid safety accident, if there is no peace
Full hidden danger, returns to step 110, continues the monitoring data for obtaining electrical system, is continuously pacified to electrical system
Full hidden danger monitoring.
The security risk detection method of a kind of artificial intelligence self study provided in this embodiment, by being based in model library
The monitoring data of some disaggregated model combination electrical system front ends, realize the detection to electrical system hidden danger classification, reach
The purpose that the phase carries out fire alarm in time is fermented in electrical fire, reduces the incidence of electrical fire, meanwhile, when in model library
There is no when disaggregated model matched with current target parameter, new disaggregated model is established based on current target parameter, and add
To model library, the real-time expansion to model library is realized, the detection function of model library is improved.
Embodiment two
Fig. 3 is that a kind of process of the security risk detection method of artificial intelligence self study provided by Embodiment 2 of the present invention is shown
It is intended to, the technical solution of the present embodiment is further optimized on the basis of the above embodiments, specifically, to above-mentioned step
It is rapid 150 " new disaggregated model to be established based at least one described target component, and new disaggregated model is added to described existing
Model library " is optimized, and the benefit of optimization is the real-time expansion realized to model library, improves the detection function of model library
Energy.The part of not detailed description please refers to embodiment one in this method embodiment.Referring specifically to shown in Fig. 3, this method includes
Following steps:
310, the monitoring data of electrical system are obtained, if the monitoring data meet the first preset condition, based on described
Monitoring data determine at least one target component.
320, judging to have in model library according to the parameter type of at least one target component and numberical range is
It is no to exist and the matched disaggregated model of at least one target component, and if it exists, to then follow the steps 330；If it does not exist, then it holds
Row step 340.
330, it is based on obtaining with the matched disaggregated model of at least one described target component and pacify existing for the electrical system
The hidden danger classification of full hidden danger.
340, the new disaggregated model established based at least one described target component is received.
Specifically, artificial participation can be added, new disaggregated model is established based at least one described target component, specifically may be used
The corresponding hidden danger classification of the target component is determined by way of manually checking, then by the target component with it is corresponding hidden
Suffer from classification as new disaggregated model and be uploaded to Cloud Server, the new disaggregated model is stored by Cloud Server.
350, the new disaggregated model is matched with each model in existing model library, to judge whether there is and institute
State the identical existing model of function of new disaggregated model, and if it exists, step 360a is then continued to execute, it is no to then follow the steps 360b.
Specifically, by by the parameter type of new disaggregated model, numberical range and corresponding hidden danger classification and existing mould
The parameter type of each model, numberical range and corresponding hidden danger classification are matched in type library, are judged whether there is and are newly divided
The identical existing model of the function of class model.Such as the parameter type of new disaggregated model is electric current, current value 500mA is corresponding
Hidden danger classification be electric leakage, while the parameter type of a disaggregated model in existing model library is also electric current, and current value is
400mA, corresponding hidden danger classification are electric leakage, then it is assumed that the existing disaggregated model is identical as the function of the new disaggregated model, can
The two is merged, substantially the storing the identical model interaction of two functions of merging thinks that the two models can be used for examining
Identical hidden danger classification is surveyed, with the storage mode of each disaggregated model of specification, each disaggregated model in model library is improved and is matched calling
Speed, and then improve security risk detection efficiency.
Illustratively, the new disaggregated model is matched with each model in existing model library, to judge whether to deposit
In existing model identical with the function of the new disaggregated model, comprising:
The corresponding processing mode of new disaggregated model processing mode corresponding with model each in existing model library is carried out
Matching, if matching similarity reaches given threshold, it is determined that there is existing model identical with the function of the new disaggregated model；
And/or
It will be each in the parameter type of the corresponding target component of the new disaggregated model and numberical range and existing model library
The parameter type and numberical range of the corresponding target component of model are matched, if matching similarity reaches given threshold,
Determine there is existing model identical with the function of the new disaggregated model.
The corresponding processing mode of model is specifically, the corresponding hidden danger classification of such as model is overload, then corresponding processing side
Formula is to mitigate load etc..
360a, by the new disaggregated model and the identical existing model combination of function.
360b, the new disaggregated model is matched with each newly-increased disaggregated model in newly-increased model library, is with judgement
It is no to there is newly-increased disaggregated model identical with the new disaggregated model function, and if it exists, to then follow the steps 370a, otherwise execute step
Rapid 370b.
If existing model identical with the function of the new disaggregated model is not present in existing model library, by described new point
Class model is saved to newly-increased disaggregated model library, and by each newly-increased disaggregated model in the new disaggregated model and newly-increased model library into
Row matching, to judge whether there is newly-increased disaggregated model identical with the new disaggregated model function, and if it exists, then will it is described newly
Disaggregated model newly-increased disaggregated model identical with function merges, and otherwise, is added to the new disaggregated model as newly-increased model
Newly-increased model library.
370a, the new disaggregated model newly-increased disaggregated model identical with function is merged, and continues to execute step 380.
370b, the new disaggregated model is added to newly-increased model library.
It is if 380, the quantity of the identical newly-increased disaggregated model of function reaches given threshold, the function is identical newly-increased
Disaggregated model is added to the existing model library as mature disaggregated model.
The security risk detection method of a kind of artificial intelligence self study provided in this embodiment, on the basis of above-described embodiment
On, when in existing model library there is no with the matched disaggregated model of at least one target component, then based on described at least one
A target component establishes new disaggregated model, and new disaggregated model is added to the existing model library based on certain rule,
The real-time expansion to existing model library is realized, the detection function of model library is improved.
Embodiment three
Fig. 4 is that a kind of structure of the Security Vulnerability Detecting System for artificial intelligence self study that the embodiment of the present invention three provides is shown
It is intended to.It is shown in Figure 4, the system comprises: obtain module 410, determining module 420, judgment module 430, detection module 440
With establish module 450；
Wherein, module 410 is obtained, for obtaining the monitoring data of electrical system；Determining module 420, if being used for the prison
Measured data meets the first preset condition, then determines at least one target component based on the monitoring data；Judgment module 430 is used
Judge to whether there is and institute in existing model library in the parameter type and numberical range according at least one target component
State the matched disaggregated model of at least one target component；Detection module 440, for if it exists at least one described target component
Matched disaggregated model is then based on obtaining the electrical system presence with the matched disaggregated model of at least one described target component
Security risk hidden danger classification；Module 450 is established, if for there is no join at least one described target in existing model library
The matched disaggregated models of number then establish new disaggregated model based at least one described target component, and by new disaggregated model
It is added to the existing model library.
Further, establishing module 450 includes:
Receiving unit, for receiving the new disaggregated model established based at least one described target component；
Judging unit, for matching the new disaggregated model with each model in existing model library, to judge to be
It is no to there is existing model identical with the function of the new disaggregated model；
Combining unit is used for the new disaggregated model existing model combination identical with function.
Further, judging unit be specifically used for will the corresponding processing mode of the new disaggregated model in existing model library
The corresponding processing mode of each model is matched, if matching similarity reaches given threshold, it is determined that exist and the new classification
The identical existing model of the function of model；And/or
It will be each in the parameter type of the corresponding target component of the new disaggregated model and numberical range and existing model library
The parameter type and numberical range of the corresponding target component of model are matched, if matching similarity reaches given threshold,
Determine there is existing model identical with the function of the new disaggregated model.
Further, combining unit is specifically used for:
The new disaggregated model existing model identical with function is associated storage.
Further, the system also includes matching modules, for when there is no the function phases with the new disaggregated model
With existing model when, the new disaggregated model is matched with each newly-increased disaggregated model in newly-increased model library, with judge
With the presence or absence of newly-increased disaggregated model identical with the new disaggregated model function；
The combining unit is also used to merge the new disaggregated model newly-increased disaggregated model identical with function,
Further, the system also includes adding modules, for when there is no as the new disaggregated model function identical
Newly-increased disaggregated model when, the new disaggregated model is added to newly-increased model library.
Further, the adding module is also used to close the new disaggregated model newly-increased disaggregated model identical with function
And later, if the quantity of the identical newly-increased disaggregated model of function reaches given threshold, by the identical newly-increased classification of the function
Model is added to the existing model library.
Further, if the monitoring data are unsatisfactory for the first preset condition, by the monitoring data according to default rule
Then stored；The target component includes: phase temperature, phase current, reactive power, power factor or phase temperature increment and phase
At least one of ratio of current increment；The hidden danger classification includes: that poor contact, short circuit, electric leakage, overload and circuit are old
At least one of change.
The Security Vulnerability Detecting System of artificial intelligence self study provided in this embodiment, by based on existing in model library
The monitoring data of disaggregated model combination electrical system front end, realize the detection to electrical system hidden danger classification, have reached in electricity
Gas fire ferments the purpose for the phase carrying out fire alarm in time, reduces the incidence of electrical fire, meanwhile, when not deposited in model library
In disaggregated model matched with current target parameter, new disaggregated model is established based on current target parameter, and be added to mould
Type library realizes the real-time expansion to model library, improves the detection function of model library.
The executable present invention of the Security Vulnerability Detecting System of artificial intelligence self study provided by the embodiment of the present invention is any
The security risk detection method of artificial intelligence self study provided by embodiment has the corresponding functional module of execution method and has
Beneficial effect.The not technical detail of detailed description in the above-described embodiments, reference can be made to provided by any embodiment of the invention artificial
The security risk detection method of intelligent self-learning.
Example IV
Fig. 5 is the structural schematic diagram for a kind of electronic equipment that the embodiment of the present invention four provides.Fig. 5, which is shown, to be suitable for being used in fact
The block diagram of the example electronic device 12 of existing embodiment of the present invention.The electronic equipment 12 that Fig. 5 is shown is only an example, no
The function and use scope for coping with the embodiment of the present invention bring any restrictions.
As shown in figure 5, electronic equipment 12 is showed in the form of universal computing device.The component of electronic equipment 12 may include
But be not limited to: one or more processor or processing unit 16, system storage 28, connect different system components (including
System storage 28 and processing unit 16) bus 18.
Bus 18 indicates one of a few class bus structures or a variety of, including memory bus or Memory Controller,
Peripheral bus, graphics acceleration port, processor or the local bus using any bus structures in a variety of bus structures.It lifts
For example, these architectures include but is not limited to industry standard architecture (ISA) bus, microchannel architecture (MAC)
Bus, enhanced isa bus, Video Electronics Standards Association (VESA) local bus and peripheral component interconnection (PCI) bus.
Electronic equipment 12 typically comprises a variety of computer system readable media.These media can be it is any can be electric
The usable medium that sub- equipment 12 accesses, including volatile and non-volatile media, moveable and immovable medium.
System storage 28 may include the computer system readable media of form of volatile memory, such as arbitrary access
Memory (RAM) 30 and/or cache memory 32.Electronic equipment 12 may further include other removable/not removable
Dynamic, volatile/non-volatile computer system storage medium.Only as an example, storage system 34 can be used for read and write can not
Mobile, non-volatile magnetic media (Fig. 5 do not show, commonly referred to as " hard disk drive ").Although being not shown in Fig. 5, Ke Yiti
For the disc driver for being read and write to removable non-volatile magnetic disk (such as " floppy disk "), and to moving non-volatile light
The CD drive of disk (such as CD-ROM, DVD-ROM or other optical mediums) read-write.In these cases, each driver
It can be connected by one or more data media interfaces with bus 18.Memory 28 may include that at least one program produces
Product, the program product have one group (such as the Security Vulnerability Detecting System of artificial intelligence self study acquisition module 410, determine
Module 420, judgment module 430, detection module 440 and establish module 450) program module, these program modules are configured to hold
The function of row various embodiments of the present invention.
With one group of (such as acquisition module 410, determining module of the Security Vulnerability Detecting System of artificial intelligence self study
420, judgment module 430, detection module 440 and establish module 450) program/utility 40 of program module 42, can store
In such as memory 28, such program module 42 include but is not limited to operating system, one or more application program, its
It may include the realization of network environment in its program module and program data, each of these examples or certain combination.
Program module 42 usually executes function and/or method in embodiment described in the invention.
Electronic equipment 12 can also be with one or more external equipments 14 (such as keyboard, sensing equipment, display 24 etc.)
Communication, can also be enabled a user to one or more equipment interact with the electronic equipment 12 communicate, and/or with make the electricity
Any equipment (such as network interface card, modem etc.) that sub- equipment 12 can be communicated with one or more of the other calculating equipment
Communication.This communication can be carried out by input/output (I/O) interface 22.Also, electronic equipment 12 can also be suitable by network
Orchestration 20 and one or more network (such as local area network (LAN), wide area network (WAN) and/or public network, such as internet)
Communication.As shown, network adapter 20 is communicated by bus 18 with other modules of electronic equipment 12.Although should be understood that
It is not shown in the figure, other hardware and/or software module can be used in conjunction with electronic equipment 12, including but not limited to: microcode is set
Standby driver, redundant processing unit, external disk drive array, RAID system, tape drive and data backup storage system
System etc..
Processing unit 16 by the program that is stored in system storage 28 of operation, thereby executing various function application and
Data processing, such as realize the security risk detection method of artificial intelligence self study provided by the embodiment of the present invention, this method
Include:
Obtain the monitoring data of electrical system；
If the monitoring data meet the first preset condition, determine that at least one target is joined based on the monitoring data
Number；
Judge whether deposit in existing model library according to the parameter type of at least one target component and numberical range
With the matched disaggregated model of at least one target component, and if it exists, then be based on and at least one described target component
The disaggregated model matched obtains the hidden danger classification of security risk existing for the electrical system；
If in existing model library there is no with the matched disaggregated model of at least one target component, based on it is described extremely
A few target component establishes new disaggregated model, and new disaggregated model is added to the existing model library.
Processing unit 16 by the program that is stored in system storage 28 of operation, thereby executing various function application and
Data processing, such as realize the security risk detection method of artificial intelligence self study provided by the embodiment of the present invention.
Certainly, it will be understood by those skilled in the art that processor can also realize it is provided by any embodiment of the invention
The technical solution of the security risk detection method of artificial intelligence self study.
Embodiment five
The embodiment of the present invention five additionally provides a kind of computer readable storage medium, is stored thereon with computer program, should
The security risk detection method of the artificial intelligence self study as provided by the embodiment of the present invention is realized when program is executed by processor,
This method comprises:
Obtain the monitoring data of electrical system；
If the monitoring data meet the first preset condition, determine that at least one target is joined based on the monitoring data
Number；
Judge whether deposit in existing model library according to the parameter type of at least one target component and numberical range
With the matched disaggregated model of at least one target component, and if it exists, then be based on and at least one described target component
The disaggregated model matched obtains the hidden danger classification of security risk existing for the electrical system；
If in existing model library there is no with the matched disaggregated model of at least one target component, based on it is described extremely
A few target component establishes new disaggregated model, and new disaggregated model is added to the existing model library.
Certainly, a kind of computer readable storage medium provided by the embodiment of the present invention, the computer program stored thereon
The method operation being not limited to the described above, can also be performed the peace of artificial intelligence self study provided by any embodiment of the invention
Relevant operation in full perils detecting method.
The computer storage medium of the embodiment of the present invention, can be using any of one or more computer-readable media
Combination.Computer-readable medium can be computer-readable signal media or computer readable storage medium.It is computer-readable
Storage medium for example may be-but not limited to-the system of electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor, system or
Device, or any above combination.The more specific example (non exhaustive list) of computer readable storage medium includes: tool
There are electrical connection, the portable computer diskette, hard disk, random access memory (RAM), read-only memory of one or more conducting wires
(ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-
ROM), light storage device, magnetic memory device or above-mentioned any appropriate combination.In this document, computer-readable storage
Medium can be any tangible medium for including or store program, which can be commanded execution system, system or device
Using or it is in connection.
Computer-readable signal media may include in a base band or as carrier wave a part propagate data-signal,
Wherein carry computer-readable program code.The data-signal of this propagation can take various forms, including but unlimited
In electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be that computer can
Any computer-readable medium other than storage medium is read, which can send, propagates or transmit and be used for
By the use of instruction execution system, system or device or program in connection.
The program code for including on computer-readable medium can transmit with any suitable medium, including --- but it is unlimited
In wireless, electric wire, optical cable, RF etc. or above-mentioned any appropriate combination.
The computer for executing operation of the present invention can be write with one or more programming languages or combinations thereof
Program code, described program design language include object oriented program language-such as Java, Smalltalk, C++,
Further include conventional procedural programming language-such as " C " language or similar programming language.Program code can be with
It fully executes, partly execute on the user computer on the user computer, being executed as an independent software package, portion
Divide and partially executes or executed on a remote computer or server completely on the remote computer on the user computer.?
Be related in the situation of remote computer, remote computer can pass through the network of any kind --- including local area network (LAN) or
Wide area network (WAN)-be connected to subscriber computer, or, it may be connected to outer computer (such as mentioned using Internet service
It is connected for quotient by internet).
Note that the above is only a better embodiment of the present invention and the applied technical principle.It will be appreciated by those skilled in the art that
The invention is not limited to the specific embodiments described herein, be able to carry out for a person skilled in the art it is various it is apparent variation,
It readjusts and substitutes without departing from protection scope of the present invention.Therefore, although being carried out by above embodiments to the present invention
It is described in further detail, but the present invention is not limited to the above embodiments only, without departing from the inventive concept, also
It may include more other equivalent embodiments, and the scope of the invention is determined by the scope of the appended claims.
Claims (10)
1. a kind of security risk detection method of artificial intelligence self study characterized by comprising
Obtain the monitoring data of electrical system；
If the monitoring data meet the first preset condition, at least one target component is determined based on the monitoring data；
According to the parameter type of at least one target component and numberical range judge in existing model library with the presence or absence of with
The matched disaggregated model of at least one target component, and if it exists, then based on matched at least one described target component
Disaggregated model obtains the hidden danger classification of security risk existing for the electrical system；
If in existing model library there is no with the matched disaggregated model of at least one target component, based on described at least one
A target component establishes new disaggregated model, and new disaggregated model is added to the existing model library.
2. the method according to claim 1, wherein establishing new classification based at least one described target component
Model, and new disaggregated model is added to the existing model library, comprising:
Receive the new disaggregated model established based at least one described target component；
The new disaggregated model is matched with each model in existing model library, to judge whether there is and the new classification
The identical existing model of the function of model；
If it exists, then by the new disaggregated model existing model combination identical with function.
3. according to the method described in claim 2, it is characterized in that, by each mould in the new disaggregated model and existing model library
Type is matched, to judge whether there is existing model identical with the function of the new disaggregated model, comprising:
The corresponding processing mode of new disaggregated model processing mode corresponding with model each in existing model library is matched,
If matching similarity reaches given threshold, it is determined that there is existing model identical with the function of the new disaggregated model；With/
Or,
By each model in the parameter type of the corresponding target component of the new disaggregated model and numberical range and existing model library
The parameter type and numberical range of corresponding target component are matched, if matching similarity reaches given threshold, it is determined that
In the presence of existing model identical with the function of the new disaggregated model.
4. according to the method described in claim 2, it is characterized in that, by the new disaggregated model existing model identical with function
Merge, comprising:
The new disaggregated model existing model identical with function is associated storage.
5. according to the method described in claim 2, it is characterized in that, identical with the function of the new disaggregated model if it does not exist
Existing model, then match the new disaggregated model with each newly-increased disaggregated model in newly-increased model library, to judge whether
In the presence of newly-increased disaggregated model identical with the new disaggregated model function；
If it exists, then the new disaggregated model newly-increased disaggregated model identical with function is merged, otherwise, by the new classification mould
Type is added to newly-increased model library.
6. according to the method described in claim 5, it is characterized in that, by the new disaggregated model newly-increased classification identical with function
After model combination, further includes:
If the quantity of the identical newly-increased disaggregated model of function reaches given threshold, the identical newly-increased disaggregated model of the function is added
Add to the existing model library.
7. method according to claim 1-6, which is characterized in that preset if the monitoring data are unsatisfactory for first
Condition then stores the monitoring data according to preset rules；The target component includes: phase temperature, phase current, idle
At least one of the ratio of power, power factor or phase temperature increment and phase current increment；
The hidden danger classification includes: poor contact, short circuit, electric leakage, overload and at least one of circuit aging.
8. a kind of Security Vulnerability Detecting System of artificial intelligence self study, which is characterized in that the system comprises:
Module is obtained, for obtaining the monitoring data of electrical system；
Determining module determines at least one based on the monitoring data if meeting the first preset condition for the monitoring data
A target component；
Judgment module, for judging existing model library according to the parameter type and numberical range of at least one target component
In whether there is and the matched disaggregated model of at least one target component；
Detection module, for if it exists with the matched disaggregated model of at least one target component, then based on it is described at least
One matched disaggregated model of target component obtains the hidden danger classification of security risk existing for the electrical system；
Establish module, if in existing model library there is no with the matched disaggregated model of at least one target component,
New disaggregated model is established based at least one described target component, and new disaggregated model is added to the existing model
Library.
9. a kind of electronic equipment including memory, processor and stores the calculating that can be run on a memory and on a processor
Machine program, which is characterized in that the processor is realized as described in any one of claim 1-7 when executing the computer program
Artificial intelligence self study security risk detection method.
10. a kind of storage medium comprising computer executable instructions, the computer executable instructions are by computer disposal
The security risk detection method such as artificial intelligence self study of any of claims 1-7 is realized when device executes.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910228163.8A CN109948937B (en) | 2019-03-25 | 2019-03-25 | Method, system, equipment and medium for detecting potential safety hazard of artificial intelligence self-learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910228163.8A CN109948937B (en) | 2019-03-25 | 2019-03-25 | Method, system, equipment and medium for detecting potential safety hazard of artificial intelligence self-learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109948937A true CN109948937A (en) | 2019-06-28 |
| CN109948937B CN109948937B (en) | 2024-01-09 |
Family
ID=67010834
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910228163.8A Active CN109948937B (en) | 2019-03-25 | 2019-03-25 | Method, system, equipment and medium for detecting potential safety hazard of artificial intelligence self-learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109948937B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112561866A (en) * | 2020-12-04 | 2021-03-26 | 重庆忽米网络科技有限公司 | Semiconductor substrate photoresist layer defect detection system based on AI and cloud computing technology |
| CN113674249A (en) * | 2021-08-24 | 2021-11-19 | 重庆忽米网络科技有限公司 | PCB printing quality detection method based on industrial internet |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090099988A1 (en) * | 2007-10-12 | 2009-04-16 | Microsoft Corporation | Active learning using a discriminative classifier and a generative model to detect and/or prevent malicious behavior |
| CN103440725A (en) * | 2013-09-03 | 2013-12-11 | 苏州太谷电力股份有限公司 | Electrical fire warning service method and system |
| CN104573740A (en) * | 2014-12-22 | 2015-04-29 | 山东鲁能软件技术有限公司 | SVM classification model-based equipment fault diagnosing method |
| CN107341550A (en) * | 2017-05-03 | 2017-11-10 | 北京海顿中科技术有限公司 | Failure/hidden danger KBS and method for building up |
| CN108959034A (en) * | 2018-07-05 | 2018-12-07 | 北京木瓜移动科技股份有限公司 | A kind of monitoring alarm method, device, electronic equipment and storage medium |
| CN109345752A (en) * | 2018-12-05 | 2019-02-15 | 合肥能安科技有限公司 | A kind of electrical safety monitoring and pre-alarming method and device |
-
2019
- 2019-03-25 CN CN201910228163.8A patent/CN109948937B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090099988A1 (en) * | 2007-10-12 | 2009-04-16 | Microsoft Corporation | Active learning using a discriminative classifier and a generative model to detect and/or prevent malicious behavior |
| CN103440725A (en) * | 2013-09-03 | 2013-12-11 | 苏州太谷电力股份有限公司 | Electrical fire warning service method and system |
| CN104573740A (en) * | 2014-12-22 | 2015-04-29 | 山东鲁能软件技术有限公司 | SVM classification model-based equipment fault diagnosing method |
| CN107341550A (en) * | 2017-05-03 | 2017-11-10 | 北京海顿中科技术有限公司 | Failure/hidden danger KBS and method for building up |
| CN108959034A (en) * | 2018-07-05 | 2018-12-07 | 北京木瓜移动科技股份有限公司 | A kind of monitoring alarm method, device, electronic equipment and storage medium |
| CN109345752A (en) * | 2018-12-05 | 2019-02-15 | 合肥能安科技有限公司 | A kind of electrical safety monitoring and pre-alarming method and device |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112561866A (en) * | 2020-12-04 | 2021-03-26 | 重庆忽米网络科技有限公司 | Semiconductor substrate photoresist layer defect detection system based on AI and cloud computing technology |
| CN113674249A (en) * | 2021-08-24 | 2021-11-19 | 重庆忽米网络科技有限公司 | PCB printing quality detection method based on industrial internet |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109948937B (en) | 2024-01-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109920193B (en) | Intelligent detection method, system, equipment and medium for electrical fire hazard | |
| CN110557457A (en) | Intelligent electricity safety early warning and cloud protection system | |
| CN102681518B (en) | Cable network running integrated management system and intelligent control platform | |
| CN104978821B (en) | A kind of intelligent radio rack fire monitoring system | |
| CN109859431B (en) | Method, system, equipment and medium for detecting fire safety hidden danger | |
| CN108335468A (en) | A kind of cable monitoring system | |
| US20190296540A1 (en) | Intelligent control method and system | |
| CN207731442U (en) | A kind of distributed intelligence electric fire monitoring system | |
| CN109948937A (en) | Security risk detection method, system, equipment and the medium of artificial intelligence self study | |
| CN110147762A (en) | A kind of embedded type fire control wrong report elimination system | |
| CN109591645A (en) | A kind of knee charging management method, system and terminal device | |
| CN107065622A (en) | A kind of electric operation information feedback method and device | |
| CN207727662U (en) | A kind of wisdom pump house | |
| CN207281967U (en) | A kind of intelligent household security system based on Internet of Things | |
| CN109872487A (en) | One kind being based on Lora domestic safety prevention system | |
| CN206163650U (en) | Battery real time intelligence monitoring system | |
| CN117409526A (en) | Electrical fire extremely early warning and monitoring system and fire extinguishing method | |
| Liu et al. | Detection of electric bicycle indoor charging for electrical safety: A nilm approach | |
| CN204791387U (en) | Intelligence smoke detector | |
| CN116146910A (en) | Gas leakage detection method based on infrared temperature-sensing camera | |
| CN205844850U (en) | A kind of electric power letter logical fortune inspection communications equipment room detecting system | |
| CN114882666A (en) | Intelligent household fire early warning method and system, terminal device and storage medium | |
| CN210323813U (en) | Intelligent safety power consumption energy management system | |
| CN107634577A (en) | Outage detection control circuit and gas meter, flow meter | |
| CN113778525A (en) | Air switch control method and device, computer equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20240506 Address after: Building A, 2402, Zhongshe Plaza, No. 1028 Buji Road, Lvjing Community, Dongxiao Street, Luohu District, Shenzhen City, Guangdong Province, 518019 Patentee after: Shenzhen Ruantong Smart Technology Co.,Ltd. Country or region after: China Address before: 430070 Liqiao creative building, 553 Wenhua Road, Hongshan District, Wuhan City, Hubei Province (office only) Patentee before: ISS TECHNOLOGY Co.,Ltd. Country or region before: China |